From bde000ae459f2829ed88e967f7fa7665b4e3afaf Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 May 2022 17:05:09 +0200 Subject: net: mac802154: Follow the count of ongoing transmissions In order to create a synchronous API for MLME command purposes, we need to be able to track the end of the ongoing transmissions. Let's introduce an atomic variable which is incremented when a transmission starts and decremented when relevant so that we know at any moment whether there is an ongoing transmission. The counter gets decremented in the following situations: - The operation is asynchronous and there was a failure during the offloading process. - The operation is synchronous and the synchronous operation failed. - The operation finished, either successfully or not. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220519150516.443078-5-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index d8d8719315fd..678ff00c7d70 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -214,6 +214,9 @@ struct wpan_phy { /* the network namespace this phy lives in currently */ possible_net_t _net; + /* Transmission monitoring */ + atomic_t ongoing_txs; + char priv[] __aligned(NETDEV_ALIGN); }; -- cgit v1.2.3 From 20a19d1df3e4079cbaa045ec89bbefb831d4705d Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 May 2022 17:05:10 +0200 Subject: net: mac802154: Bring the ability to hold the transmit queue Create a hold_txs atomic variable and increment/decrement it when relevant, ie. when we want to hold the queue or release it: currently all the "stopped" situations are suitable, but very soon we will more extensively use this feature for MLME purposes. Upon release, the atomic counter is decremented and checked. If it is back to 0, then the netif queue gets woken up. This makes the whole process fully transparent, provided that all the users of ieee802154_wake/stop_queue() now call ieee802154_hold/release_queue() instead. In no situation individual drivers should call any of these helpers manually in order to avoid messing with the counters. There are other functions more suited for this purpose which have been introduced, such as the _xmit_complete() and _xmit_error() helpers which will handle all that for them. One advantage is that, as no more drivers call the stop/wake helpers directly, we can safely stop exporting them and only declare the hold/release ones in a header only accessible to the core. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220519150516.443078-6-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 6 +++-- include/net/mac802154.h | 27 ----------------------- net/ieee802154/core.c | 2 ++ net/mac802154/cfg.c | 4 ++-- net/mac802154/ieee802154_i.h | 19 ++++++++++++++++ net/mac802154/tx.c | 6 ++--- net/mac802154/util.c | 52 ++++++++++++++++++++++++++++++++++++++------ 7 files changed, 75 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 678ff00c7d70..e87f1b07f20f 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include @@ -214,8 +214,10 @@ struct wpan_phy { /* the network namespace this phy lives in currently */ possible_net_t _net; - /* Transmission monitoring */ + /* Transmission monitoring and control */ + spinlock_t queue_lock; atomic_t ongoing_txs; + atomic_t hold_txs; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/net/mac802154.h b/include/net/mac802154.h index bdac0ddbdcdb..357d25ef627a 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -460,33 +460,6 @@ void ieee802154_unregister_hw(struct ieee802154_hw *hw); */ void ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi); -/** - * ieee802154_wake_queue - wake ieee802154 queue - * @hw: pointer as obtained from ieee802154_alloc_hw(). - * - * Tranceivers usually have either one transmit framebuffer or one framebuffer - * for both transmitting and receiving. Hence, the core currently only handles - * one frame at a time for each phy, which means we had to stop the queue to - * avoid new skb to come during the transmission. The queue then needs to be - * woken up after the operation. - * - * Drivers should use this function instead of netif_wake_queue. - */ -void ieee802154_wake_queue(struct ieee802154_hw *hw); - -/** - * ieee802154_stop_queue - stop ieee802154 queue - * @hw: pointer as obtained from ieee802154_alloc_hw(). - * - * Tranceivers usually have either one transmit framebuffer or one framebuffer - * for both transmitting and receiving. Hence, the core currently only handles - * one frame at a time for each phy, which means we need to tell upper layers to - * stop giving us new skbs while we are busy with the transmitted one. The queue - * must then be stopped before transmitting. - * - * Drivers should use this function instead of netif_stop_queue. - */ -void ieee802154_stop_queue(struct ieee802154_hw *hw); /** * ieee802154_xmit_complete - frame transmission complete diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index de259b5170ab..47a4de6df88b 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -130,6 +130,8 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) init_waitqueue_head(&rdev->dev_wait); + spin_lock_init(&rdev->wpan_phy.queue_lock); + return &rdev->wpan_phy; } EXPORT_SYMBOL(wpan_phy_new); diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 1e4a9f74ed43..b51100fd9e3f 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -46,7 +46,7 @@ static int ieee802154_suspend(struct wpan_phy *wpan_phy) if (!local->open_count) goto suspend; - ieee802154_stop_queue(&local->hw); + ieee802154_hold_queue(local); synchronize_net(); /* stop hardware - this must stop RX */ @@ -72,7 +72,7 @@ static int ieee802154_resume(struct wpan_phy *wpan_phy) return ret; wake_up: - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); local->suspended = false; return 0; } diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index a8b7b9049f14..0c7ff9e0b632 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -130,6 +130,25 @@ netdev_tx_t ieee802154_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer); +/** + * ieee802154_hold_queue - hold ieee802154 queue + * @local: main mac object + * + * Hold a queue by incrementing an atomic counter and requesting the netif + * queues to be stopped. The queues cannot be woken up while the counter has not + * been reset with as any ieee802154_release_queue() calls as needed. + */ +void ieee802154_hold_queue(struct ieee802154_local *local); + +/** + * ieee802154_release_queue - release ieee802154 queue + * @local: main mac object + * + * Release a queue which is held by decrementing an atomic counter and wake it + * up only if the counter reaches 0. + */ +void ieee802154_release_queue(struct ieee802154_local *local); + /* MIB callbacks */ void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan); diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 33f64ecd96c7..6a53c83cf039 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -43,7 +43,7 @@ void ieee802154_xmit_sync_worker(struct work_struct *work) err_tx: /* Restart the netif queue on each sub_if_data object. */ - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); atomic_dec(&local->phy->ongoing_txs); kfree_skb(skb); netdev_dbg(dev, "transmission failed\n"); @@ -75,7 +75,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } /* Stop the netif queue on each sub_if_data object. */ - ieee802154_stop_queue(&local->hw); + ieee802154_hold_queue(local); atomic_inc(&local->phy->ongoing_txs); /* Drivers should preferably implement the async callback. In some rare @@ -99,7 +99,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) return NETDEV_TX_OK; err_wake_netif_queue: - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); atomic_dec(&local->phy->ongoing_txs); err_free_skb: kfree_skb(skb); diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 76dc663e2af4..0ed8b5bcbe8a 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -13,7 +13,17 @@ /* privid for wpan_phys to determine whether they belong to us or not */ const void *const mac802154_wpan_phy_privid = &mac802154_wpan_phy_privid; -void ieee802154_wake_queue(struct ieee802154_hw *hw) +/** + * ieee802154_wake_queue - wake ieee802154 queue + * @local: main mac object + * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we had to stop the queue to + * avoid new skb to come during the transmission. The queue then needs to be + * woken up after the operation. + */ +static void ieee802154_wake_queue(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); struct ieee802154_sub_if_data *sdata; @@ -27,9 +37,18 @@ void ieee802154_wake_queue(struct ieee802154_hw *hw) } rcu_read_unlock(); } -EXPORT_SYMBOL(ieee802154_wake_queue); -void ieee802154_stop_queue(struct ieee802154_hw *hw) +/** + * ieee802154_stop_queue - stop ieee802154 queue + * @local: main mac object + * + * Tranceivers usually have either one transmit framebuffer or one framebuffer + * for both transmitting and receiving. Hence, the core currently only handles + * one frame at a time for each phy, which means we need to tell upper layers to + * stop giving us new skbs while we are busy with the transmitted one. The queue + * must then be stopped before transmitting. + */ +static void ieee802154_stop_queue(struct ieee802154_hw *hw) { struct ieee802154_local *local = hw_to_local(hw); struct ieee802154_sub_if_data *sdata; @@ -43,14 +62,33 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw) } rcu_read_unlock(); } -EXPORT_SYMBOL(ieee802154_stop_queue); + +void ieee802154_hold_queue(struct ieee802154_local *local) +{ + unsigned long flags; + + spin_lock_irqsave(&local->phy->queue_lock, flags); + if (!atomic_fetch_inc(&local->phy->hold_txs)) + ieee802154_stop_queue(&local->hw); + spin_unlock_irqrestore(&local->phy->queue_lock, flags); +} + +void ieee802154_release_queue(struct ieee802154_local *local) +{ + unsigned long flags; + + spin_lock_irqsave(&local->phy->queue_lock, flags); + if (!atomic_dec_and_test(&local->phy->hold_txs)) + ieee802154_wake_queue(&local->hw); + spin_unlock_irqrestore(&local->phy->queue_lock, flags); +} enum hrtimer_restart ieee802154_xmit_ifs_timer(struct hrtimer *timer) { struct ieee802154_local *local = container_of(timer, struct ieee802154_local, ifs_timer); - ieee802154_wake_queue(&local->hw); + ieee802154_release_queue(local); return HRTIMER_NORESTART; } @@ -84,7 +122,7 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, hw->phy->sifs_period * NSEC_PER_USEC, HRTIMER_MODE_REL); } else { - ieee802154_wake_queue(hw); + ieee802154_release_queue(local); } dev_consume_skb_any(skb); @@ -98,7 +136,7 @@ void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, struct ieee802154_local *local = hw_to_local(hw); local->tx_result = reason; - ieee802154_wake_queue(hw); + ieee802154_release_queue(local); dev_kfree_skb_any(skb); atomic_dec(&hw->phy->ongoing_txs); } -- cgit v1.2.3 From f0feb34904735ffa21fe7b0c50f9f9527ec74b7a Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 May 2022 17:05:13 +0200 Subject: net: mac802154: Introduce a tx queue flushing mechanism Right now we are able to stop a queue but we have no indication if a transmission is ongoing or not. Thanks to recent additions, we can track the number of ongoing transmissions so we know if the last transmission is over. Adding on top of it an internal wait queue also allows to be woken up asynchronously when this happens. If, beforehands, we marked the queue to be held and stopped it, we end up flushing and stopping the tx queue. Thanks to this feature, we will soon be able to introduce a synchronous transmit API. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220519150516.443078-9-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 1 + net/ieee802154/core.c | 1 + net/mac802154/cfg.c | 2 +- net/mac802154/ieee802154_i.h | 1 + net/mac802154/tx.c | 26 ++++++++++++++++++++++++-- net/mac802154/util.c | 6 ++++-- 6 files changed, 32 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index e87f1b07f20f..0804d79669a4 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -218,6 +218,7 @@ struct wpan_phy { spinlock_t queue_lock; atomic_t ongoing_txs; atomic_t hold_txs; + wait_queue_head_t sync_txq; char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 47a4de6df88b..57546e07e06a 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -129,6 +129,7 @@ wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size) wpan_phy_net_set(&rdev->wpan_phy, &init_net); init_waitqueue_head(&rdev->dev_wait); + init_waitqueue_head(&rdev->wpan_phy.sync_txq); spin_lock_init(&rdev->wpan_phy.queue_lock); diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index b51100fd9e3f..93df24f75572 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -46,7 +46,7 @@ static int ieee802154_suspend(struct wpan_phy *wpan_phy) if (!local->open_count) goto suspend; - ieee802154_hold_queue(local); + ieee802154_sync_and_hold_queue(local); synchronize_net(); /* stop hardware - this must stop RX */ diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index e34db1d49ef4..a057827fc48a 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -124,6 +124,7 @@ extern struct ieee802154_mlme_ops mac802154_mlme_wpan; void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb); void ieee802154_xmit_sync_worker(struct work_struct *work); +int ieee802154_sync_and_hold_queue(struct ieee802154_local *local); netdev_tx_t ieee802154_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); netdev_tx_t diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 607019b8f8ab..38f74b8b6740 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -44,7 +44,8 @@ void ieee802154_xmit_sync_worker(struct work_struct *work) err_tx: /* Restart the netif queue on each sub_if_data object. */ ieee802154_release_queue(local); - atomic_dec(&local->phy->ongoing_txs); + if (!atomic_dec_and_test(&local->phy->ongoing_txs)) + wake_up(&local->phy->sync_txq); kfree_skb(skb); netdev_dbg(dev, "transmission failed\n"); } @@ -100,12 +101,33 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) err_wake_netif_queue: ieee802154_release_queue(local); - atomic_dec(&local->phy->ongoing_txs); + if (!atomic_dec_and_test(&local->phy->ongoing_txs)) + wake_up(&local->phy->sync_txq); err_free_skb: kfree_skb(skb); return NETDEV_TX_OK; } +static int ieee802154_sync_queue(struct ieee802154_local *local) +{ + int ret; + + ieee802154_hold_queue(local); + ieee802154_disable_queue(local); + wait_event(local->phy->sync_txq, !atomic_read(&local->phy->ongoing_txs)); + ret = local->tx_result; + ieee802154_release_queue(local); + + return ret; +} + +int ieee802154_sync_and_hold_queue(struct ieee802154_local *local) +{ + ieee802154_hold_queue(local); + + return ieee802154_sync_queue(local); +} + static netdev_tx_t ieee802154_hot_tx(struct ieee802154_local *local, struct sk_buff *skb) { diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 999534f64485..5e1fcc7b0123 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -140,7 +140,8 @@ void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, } dev_consume_skb_any(skb); - atomic_dec(&hw->phy->ongoing_txs); + if (!atomic_dec_and_test(&hw->phy->ongoing_txs)) + wake_up(&hw->phy->sync_txq); } EXPORT_SYMBOL(ieee802154_xmit_complete); @@ -152,7 +153,8 @@ void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, local->tx_result = reason; ieee802154_release_queue(local); dev_kfree_skb_any(skb); - atomic_dec(&hw->phy->ongoing_txs); + if (!atomic_dec_and_test(&hw->phy->ongoing_txs)) + wake_up(&hw->phy->sync_txq); } EXPORT_SYMBOL(ieee802154_xmit_error); -- cgit v1.2.3 From 2b13db13af50a5dcdb944723c828915a50f0c3b2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 19 May 2022 17:05:15 +0200 Subject: net: mac802154: Add a warning in the hot path We should never start a transmission after the queue has been stopped. But because it might work we don't kill the function here but rather warn loudly the user that something is wrong. Set a flag when the queue should remain stopped. Reset this flag when the queue actually gets restarded. Just check this value to know if a transmission is legitimate, warn if it is not. Turn the flags variable into an unsigned long to allow the use of atomic helpers on it. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20220519150516.443078-11-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 5 ++++- net/mac802154/tx.c | 16 +++++++++++++++- net/mac802154/util.c | 1 + 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 0804d79669a4..428cece22205 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -166,11 +166,14 @@ wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) * level setting. * @WPAN_PHY_FLAG_CCA_MODE: Indicates that transceiver will support cca mode * setting. + * @WPAN_PHY_FLAG_STATE_QUEUE_STOPPED: Indicates that the transmit queue was + * temporarily stopped. */ enum wpan_phy_flags { WPAN_PHY_FLAG_TXPOWER = BIT(1), WPAN_PHY_FLAG_CCA_ED_LEVEL = BIT(2), WPAN_PHY_FLAG_CCA_MODE = BIT(3), + WPAN_PHY_FLAG_STATE_QUEUE_STOPPED = BIT(4), }; struct wpan_phy { @@ -182,7 +185,7 @@ struct wpan_phy { */ const void *privid; - u32 flags; + unsigned long flags; /* * This is a PIB according to 802.15.4-2011. diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 4827391600f6..6188f42276e7 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -123,9 +123,13 @@ static int ieee802154_sync_queue(struct ieee802154_local *local) int ieee802154_sync_and_hold_queue(struct ieee802154_local *local) { + int ret; + ieee802154_hold_queue(local); + ret = ieee802154_sync_queue(local); + set_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); - return ieee802154_sync_queue(local); + return ret; } int ieee802154_mlme_op_pre(struct ieee802154_local *local) @@ -172,9 +176,19 @@ int ieee802154_mlme_tx_one(struct ieee802154_local *local, struct sk_buff *skb) return ret; } +static bool ieee802154_queue_is_stopped(struct ieee802154_local *local) +{ + return test_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); +} + static netdev_tx_t ieee802154_hot_tx(struct ieee802154_local *local, struct sk_buff *skb) { + /* Warn if the net interface tries to transmit frames while the + * ieee802154 core assumes the queue is stopped. + */ + WARN_ON_ONCE(ieee802154_queue_is_stopped(local)); + return ieee802154_tx(local, skb); } diff --git a/net/mac802154/util.c b/net/mac802154/util.c index 5e1fcc7b0123..60eb7bd3bfc1 100644 --- a/net/mac802154/util.c +++ b/net/mac802154/util.c @@ -29,6 +29,7 @@ static void ieee802154_wake_queue(struct ieee802154_hw *hw) struct ieee802154_sub_if_data *sdata; rcu_read_lock(); + clear_bit(WPAN_PHY_FLAG_STATE_QUEUE_STOPPED, &local->phy->flags); list_for_each_entry_rcu(sdata, &local->interfaces, list) { if (!sdata->dev) continue; -- cgit v1.2.3 From 8a76145a2ec2a81dfe34d7ac42e8c242f095e8c8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 5 Oct 2022 21:24:51 -0700 Subject: bpf: explicitly define BPF_FUNC_xxx integer values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Historically enum bpf_func_id's BPF_FUNC_xxx enumerators relied on implicit sequential values being assigned by compiler. This is convenient, as new BPF helpers are always added at the very end, but it also has its downsides, some of them being: - with over 200 helpers now it's very hard to know what's each helper's ID, which is often important to know when working with BPF assembly (e.g., by dumping raw bpf assembly instructions with llvm-objdump -d command). it's possible to work around this by looking into vmlinux.h, dumping /sys/btf/kernel/vmlinux, looking at libbpf-provided bpf_helper_defs.h, etc. But it always feels like an unnecessary step and one should be able to quickly figure this out from UAPI header. - when backporting and cherry-picking only some BPF helpers onto older kernels it's important to be able to skip some enum values for helpers that weren't backported, but preserve absolute integer IDs to keep BPF helper IDs stable so that BPF programs stay portable across upstream and backported kernels. While neither problem is insurmountable, they come up frequently enough and are annoying enough to warrant improving the situation. And for the backporting the problem can easily go unnoticed for a while, especially if backport is done with people not very familiar with BPF subsystem overall. Anyways, it's easy to fix this by making sure that __BPF_FUNC_MAPPER macro provides explicit helper IDs. Unfortunately that would potentially break existing users that use UAPI-exposed __BPF_FUNC_MAPPER and are expected to pass macro that accepts only symbolic helper identifier (e.g., map_lookup_elem for bpf_map_lookup_elem() helper). As such, we need to introduce a new macro (___BPF_FUNC_MAPPER) which would specify both identifier and integer ID, but in such a way as to allow existing __BPF_FUNC_MAPPER be expressed in terms of new ___BPF_FUNC_MAPPER macro. And that's what this patch is doing. To avoid duplication and allow __BPF_FUNC_MAPPER stay *exactly* the same, ___BPF_FUNC_MAPPER accepts arbitrary "context" arguments, which can be used to pass any extra macros, arguments, and whatnot. In our case we use this to pass original user-provided macro that expects single argument and __BPF_FUNC_MAPPER is using it's own three-argument __BPF_FUNC_MAPPER_APPLY intermediate macro to impedance-match new and old "callback" macros. Once we resolve this, we use new ___BPF_FUNC_MAPPER to define enum bpf_func_id with explicit values. The other users of __BPF_FUNC_MAPPER in kernel (namely in kernel/bpf/disasm.c) are kept exactly the same both as demonstration that backwards compat works, but also to avoid unnecessary code churn. Note that new ___BPF_FUNC_MAPPER() doesn't forcefully insert comma between values, as that might not be appropriate in all possible cases where ___BPF_FUNC_MAPPER might be used by users. This doesn't reduce usability, as it's trivial to insert that comma inside "callback" macro. To validate all the manually specified IDs are exactly right, we used BTF to compare before and after values: $ bpftool btf dump file ~/linux-build/default/vmlinux | rg bpf_func_id -A 211 > after.txt $ git stash # stach UAPI changes $ make -j90 ... re-building kernel without UAPI changes ... $ bpftool btf dump file ~/linux-build/default/vmlinux | rg bpf_func_id -A 211 > before.txt $ diff -u before.txt after.txt --- before.txt 2022-10-05 10:48:18.119195916 -0700 +++ after.txt 2022-10-05 10:46:49.446615025 -0700 @@ -1,4 +1,4 @@ -[14576] ENUM 'bpf_func_id' encoding=UNSIGNED size=4 vlen=211 +[9560] ENUM 'bpf_func_id' encoding=UNSIGNED size=4 vlen=211 'BPF_FUNC_unspec' val=0 'BPF_FUNC_map_lookup_elem' val=1 'BPF_FUNC_map_update_elem' val=2 As can be seen from diff above, the only thing that changed was resulting BTF type ID of ENUM bpf_func_id, not any of the enumerators, their names or integer values. The only other place that needed fixing was scripts/bpf_doc.py used to generate man pages and bpf_helper_defs.h header for libbpf and selftests. That script is tightly-coupled to exact shape of ___BPF_FUNC_MAPPER macro definition, so had to be trivially adapted. Cc: Quentin Monnet Reported-by: Andrea Terzolo Signed-off-by: Andrii Nakryiko Reviewed-by: Quentin Monnet Acked-by: Jiri Olsa Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221006042452.2089843-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 432 +++++++++++++++++++++-------------------- scripts/bpf_doc.py | 19 +- tools/include/uapi/linux/bpf.h | 432 +++++++++++++++++++++-------------------- 3 files changed, 447 insertions(+), 436 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 51b9aa640ad2..17f61338f8f8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5436,225 +5436,231 @@ union bpf_attr { * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. */ -#define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - FN(redirect_map), \ - FN(sk_redirect_map), \ - FN(sock_map_update), \ - FN(xdp_adjust_meta), \ - FN(perf_event_read_value), \ - FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), \ - FN(sock_ops_cb_flags_set), \ - FN(msg_redirect_map), \ - FN(msg_apply_bytes), \ - FN(msg_cork_bytes), \ - FN(msg_pull_data), \ - FN(bind), \ - FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), \ - FN(get_stack), \ - FN(skb_load_bytes_relative), \ - FN(fib_lookup), \ - FN(sock_hash_update), \ - FN(msg_redirect_hash), \ - FN(sk_redirect_hash), \ - FN(lwt_push_encap), \ - FN(lwt_seg6_store_bytes), \ - FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), \ - FN(rc_repeat), \ - FN(rc_keydown), \ - FN(skb_cgroup_id), \ - FN(get_current_cgroup_id), \ - FN(get_local_storage), \ - FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), \ - FN(sk_lookup_tcp), \ - FN(sk_lookup_udp), \ - FN(sk_release), \ - FN(map_push_elem), \ - FN(map_pop_elem), \ - FN(map_peek_elem), \ - FN(msg_push_data), \ - FN(msg_pop_data), \ - FN(rc_pointer_rel), \ - FN(spin_lock), \ - FN(spin_unlock), \ - FN(sk_fullsock), \ - FN(tcp_sock), \ - FN(skb_ecn_set_ce), \ - FN(get_listener_sock), \ - FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), \ - FN(sysctl_get_name), \ - FN(sysctl_get_current_value), \ - FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), \ - FN(strtol), \ - FN(strtoul), \ - FN(sk_storage_get), \ - FN(sk_storage_delete), \ - FN(send_signal), \ - FN(tcp_gen_syncookie), \ - FN(skb_output), \ - FN(probe_read_user), \ - FN(probe_read_kernel), \ - FN(probe_read_user_str), \ - FN(probe_read_kernel_str), \ - FN(tcp_send_ack), \ - FN(send_signal_thread), \ - FN(jiffies64), \ - FN(read_branch_records), \ - FN(get_ns_current_pid_tgid), \ - FN(xdp_output), \ - FN(get_netns_cookie), \ - FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), \ - FN(ktime_get_boot_ns), \ - FN(seq_printf), \ - FN(seq_write), \ - FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), \ - FN(ringbuf_output), \ - FN(ringbuf_reserve), \ - FN(ringbuf_submit), \ - FN(ringbuf_discard), \ - FN(ringbuf_query), \ - FN(csum_level), \ - FN(skc_to_tcp6_sock), \ - FN(skc_to_tcp_sock), \ - FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), \ - FN(get_task_stack), \ - FN(load_hdr_opt), \ - FN(store_hdr_opt), \ - FN(reserve_hdr_opt), \ - FN(inode_storage_get), \ - FN(inode_storage_delete), \ - FN(d_path), \ - FN(copy_from_user), \ - FN(snprintf_btf), \ - FN(seq_printf_btf), \ - FN(skb_cgroup_classid), \ - FN(redirect_neigh), \ - FN(per_cpu_ptr), \ - FN(this_cpu_ptr), \ - FN(redirect_peer), \ - FN(task_storage_get), \ - FN(task_storage_delete), \ - FN(get_current_task_btf), \ - FN(bprm_opts_set), \ - FN(ktime_get_coarse_ns), \ - FN(ima_inode_hash), \ - FN(sock_from_file), \ - FN(check_mtu), \ - FN(for_each_map_elem), \ - FN(snprintf), \ - FN(sys_bpf), \ - FN(btf_find_by_name_kind), \ - FN(sys_close), \ - FN(timer_init), \ - FN(timer_set_callback), \ - FN(timer_start), \ - FN(timer_cancel), \ - FN(get_func_ip), \ - FN(get_attach_cookie), \ - FN(task_pt_regs), \ - FN(get_branch_snapshot), \ - FN(trace_vprintk), \ - FN(skc_to_unix_sock), \ - FN(kallsyms_lookup_name), \ - FN(find_vma), \ - FN(loop), \ - FN(strncmp), \ - FN(get_func_arg), \ - FN(get_func_ret), \ - FN(get_func_arg_cnt), \ - FN(get_retval), \ - FN(set_retval), \ - FN(xdp_get_buff_len), \ - FN(xdp_load_bytes), \ - FN(xdp_store_bytes), \ - FN(copy_from_user_task), \ - FN(skb_set_tstamp), \ - FN(ima_file_hash), \ - FN(kptr_xchg), \ - FN(map_lookup_percpu_elem), \ - FN(skc_to_mptcp_sock), \ - FN(dynptr_from_mem), \ - FN(ringbuf_reserve_dynptr), \ - FN(ringbuf_submit_dynptr), \ - FN(ringbuf_discard_dynptr), \ - FN(dynptr_read), \ - FN(dynptr_write), \ - FN(dynptr_data), \ - FN(tcp_raw_gen_syncookie_ipv4), \ - FN(tcp_raw_gen_syncookie_ipv6), \ - FN(tcp_raw_check_syncookie_ipv4), \ - FN(tcp_raw_check_syncookie_ipv6), \ - FN(ktime_get_tai_ns), \ - FN(user_ringbuf_drain), \ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ /* */ +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ -#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index d5c389df6045..2fe07c9e3fe0 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -253,28 +253,27 @@ class HeaderParser(object): break def parse_define_helpers(self): - # Parse FN(...) in #define __BPF_FUNC_MAPPER to compare later with the + # Parse FN(...) in #define ___BPF_FUNC_MAPPER to compare later with the # number of unique function names present in description and use the # correct enumeration value. # Note: seek_to(..) discards the first line below the target search text, - # resulting in FN(unspec) being skipped and not added to self.define_unique_helpers. - self.seek_to('#define __BPF_FUNC_MAPPER(FN)', + # resulting in FN(unspec, 0, ##ctx) being skipped and not added to + # self.define_unique_helpers. + self.seek_to('#define ___BPF_FUNC_MAPPER(FN, ctx...)', 'Could not find start of eBPF helper definition list') # Searches for one FN(\w+) define or a backslash for newline - p = re.compile('\s*FN\((\w+)\)|\\\\') + p = re.compile('\s*FN\((\w+), (\d+), ##ctx\)|\\\\') fn_defines_str = '' - i = 1 # 'unspec' is skipped as mentioned above while True: capture = p.match(self.line) if capture: fn_defines_str += self.line - self.helper_enum_vals[capture.expand(r'bpf_\1')] = i - i += 1 + self.helper_enum_vals[capture.expand(r'bpf_\1')] = int(capture[2]) else: break self.line = self.reader.readline() # Find the number of occurences of FN(\w+) - self.define_unique_helpers = re.findall('FN\(\w+\)', fn_defines_str) + self.define_unique_helpers = re.findall('FN\(\w+, \d+, ##ctx\)', fn_defines_str) def assign_helper_values(self): seen_helpers = set() @@ -423,7 +422,7 @@ class PrinterHelpersRST(PrinterRST): """ def __init__(self, parser): self.elements = parser.helpers - self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '___BPF_FUNC_MAPPER') def print_header(self): header = '''\ @@ -636,7 +635,7 @@ class PrinterHelpers(Printer): """ def __init__(self, parser): self.elements = parser.helpers - self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '__BPF_FUNC_MAPPER') + self.elem_number_check(parser.desc_unique_helpers, parser.define_unique_helpers, 'helper', '___BPF_FUNC_MAPPER') type_fwds = [ 'struct bpf_fib_lookup', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 51b9aa640ad2..17f61338f8f8 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5436,225 +5436,231 @@ union bpf_attr { * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. */ -#define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - FN(redirect_map), \ - FN(sk_redirect_map), \ - FN(sock_map_update), \ - FN(xdp_adjust_meta), \ - FN(perf_event_read_value), \ - FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), \ - FN(sock_ops_cb_flags_set), \ - FN(msg_redirect_map), \ - FN(msg_apply_bytes), \ - FN(msg_cork_bytes), \ - FN(msg_pull_data), \ - FN(bind), \ - FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), \ - FN(get_stack), \ - FN(skb_load_bytes_relative), \ - FN(fib_lookup), \ - FN(sock_hash_update), \ - FN(msg_redirect_hash), \ - FN(sk_redirect_hash), \ - FN(lwt_push_encap), \ - FN(lwt_seg6_store_bytes), \ - FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), \ - FN(rc_repeat), \ - FN(rc_keydown), \ - FN(skb_cgroup_id), \ - FN(get_current_cgroup_id), \ - FN(get_local_storage), \ - FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), \ - FN(sk_lookup_tcp), \ - FN(sk_lookup_udp), \ - FN(sk_release), \ - FN(map_push_elem), \ - FN(map_pop_elem), \ - FN(map_peek_elem), \ - FN(msg_push_data), \ - FN(msg_pop_data), \ - FN(rc_pointer_rel), \ - FN(spin_lock), \ - FN(spin_unlock), \ - FN(sk_fullsock), \ - FN(tcp_sock), \ - FN(skb_ecn_set_ce), \ - FN(get_listener_sock), \ - FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), \ - FN(sysctl_get_name), \ - FN(sysctl_get_current_value), \ - FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), \ - FN(strtol), \ - FN(strtoul), \ - FN(sk_storage_get), \ - FN(sk_storage_delete), \ - FN(send_signal), \ - FN(tcp_gen_syncookie), \ - FN(skb_output), \ - FN(probe_read_user), \ - FN(probe_read_kernel), \ - FN(probe_read_user_str), \ - FN(probe_read_kernel_str), \ - FN(tcp_send_ack), \ - FN(send_signal_thread), \ - FN(jiffies64), \ - FN(read_branch_records), \ - FN(get_ns_current_pid_tgid), \ - FN(xdp_output), \ - FN(get_netns_cookie), \ - FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), \ - FN(ktime_get_boot_ns), \ - FN(seq_printf), \ - FN(seq_write), \ - FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), \ - FN(ringbuf_output), \ - FN(ringbuf_reserve), \ - FN(ringbuf_submit), \ - FN(ringbuf_discard), \ - FN(ringbuf_query), \ - FN(csum_level), \ - FN(skc_to_tcp6_sock), \ - FN(skc_to_tcp_sock), \ - FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), \ - FN(get_task_stack), \ - FN(load_hdr_opt), \ - FN(store_hdr_opt), \ - FN(reserve_hdr_opt), \ - FN(inode_storage_get), \ - FN(inode_storage_delete), \ - FN(d_path), \ - FN(copy_from_user), \ - FN(snprintf_btf), \ - FN(seq_printf_btf), \ - FN(skb_cgroup_classid), \ - FN(redirect_neigh), \ - FN(per_cpu_ptr), \ - FN(this_cpu_ptr), \ - FN(redirect_peer), \ - FN(task_storage_get), \ - FN(task_storage_delete), \ - FN(get_current_task_btf), \ - FN(bprm_opts_set), \ - FN(ktime_get_coarse_ns), \ - FN(ima_inode_hash), \ - FN(sock_from_file), \ - FN(check_mtu), \ - FN(for_each_map_elem), \ - FN(snprintf), \ - FN(sys_bpf), \ - FN(btf_find_by_name_kind), \ - FN(sys_close), \ - FN(timer_init), \ - FN(timer_set_callback), \ - FN(timer_start), \ - FN(timer_cancel), \ - FN(get_func_ip), \ - FN(get_attach_cookie), \ - FN(task_pt_regs), \ - FN(get_branch_snapshot), \ - FN(trace_vprintk), \ - FN(skc_to_unix_sock), \ - FN(kallsyms_lookup_name), \ - FN(find_vma), \ - FN(loop), \ - FN(strncmp), \ - FN(get_func_arg), \ - FN(get_func_ret), \ - FN(get_func_arg_cnt), \ - FN(get_retval), \ - FN(set_retval), \ - FN(xdp_get_buff_len), \ - FN(xdp_load_bytes), \ - FN(xdp_store_bytes), \ - FN(copy_from_user_task), \ - FN(skb_set_tstamp), \ - FN(ima_file_hash), \ - FN(kptr_xchg), \ - FN(map_lookup_percpu_elem), \ - FN(skc_to_mptcp_sock), \ - FN(dynptr_from_mem), \ - FN(ringbuf_reserve_dynptr), \ - FN(ringbuf_submit_dynptr), \ - FN(ringbuf_discard_dynptr), \ - FN(dynptr_read), \ - FN(dynptr_write), \ - FN(dynptr_data), \ - FN(tcp_raw_gen_syncookie_ipv4), \ - FN(tcp_raw_gen_syncookie_ipv6), \ - FN(tcp_raw_check_syncookie_ipv4), \ - FN(tcp_raw_check_syncookie_ipv6), \ - FN(ktime_get_tai_ns), \ - FN(user_ringbuf_drain), \ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ /* */ +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ -#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN -- cgit v1.2.3 From 1d9e4c91db17c9bf6f94ac234a4d4f2bffd52b97 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Tue, 6 Sep 2022 19:02:04 +0200 Subject: wifi: mac80211: add pointer from link STA to STA While often not needed, this considerably simplifies going from a link to the STA. This helps in cases such as debugfs where a single pointer should allow accessing a specific link and the STA. Signed-off-by: Benjamin Berg Signed-off-by: Johannes Berg --- include/net/mac80211.h | 3 +++ net/mac80211/sta_info.c | 1 + 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ac2bad57933f..7778a92d9582 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2176,6 +2176,7 @@ struct ieee80211_sta_aggregates { * All link specific info for a STA link for a non MLD STA(single) * or a MLD STA(multiple entries) are stored here. * + * @sta: reference to owning STA * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr * in ieee80211_sta. For MLO Link STA this addr can be same or different * from addr in ieee80211_sta (representing MLD STA addr) @@ -2196,6 +2197,8 @@ struct ieee80211_sta_aggregates { * */ struct ieee80211_link_sta { + struct ieee80211_sta *sta; + u8 addr[ETH_ALEN]; u8 link_id; enum ieee80211_smps_mode smps_mode; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index cebfd148bb40..71b1488bd390 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -511,6 +511,7 @@ static void sta_info_add_link(struct sta_info *sta, link_info->sta = sta; link_info->link_id = link_id; link_info->pub = link_sta; + link_info->pub->sta = &sta->sta; link_sta->link_id = link_id; rcu_assign_pointer(sta->link[link_id], link_info); rcu_assign_pointer(sta->sta.link[link_id], link_sta); -- cgit v1.2.3 From d2caad527c191563116809990081ab4fc0dafdb6 Mon Sep 17 00:00:00 2001 From: Benjamin Berg Date: Tue, 6 Sep 2022 14:26:52 +0200 Subject: wifi: mac80211: add API to show the link STAs in debugfs Create debugfs data per-link. For drivers, there is a new operation link_sta_add_debugfs which will always be called. For non-MLO, the station directory will be used directly rather than creating a corresponding subdirectory. As such, non-MLO drivers can simply continue to create the data from sta_debugfs_add. Signed-off-by: Benjamin Berg [add missing inlines if !CONFIG_MAC80211_DEBUGFS] Signed-off-by: Johannes Berg --- include/net/mac80211.h | 11 ++++ net/mac80211/debugfs_sta.c | 127 +++++++++++++++++++++++++++++++++++++-------- net/mac80211/debugfs_sta.h | 12 +++++ net/mac80211/driver-ops.c | 27 +++++++++- net/mac80211/driver-ops.h | 16 ++++++ net/mac80211/sta_info.c | 25 +++++++++ net/mac80211/sta_info.h | 5 ++ 7 files changed, 200 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7778a92d9582..c413050ec8dd 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3790,6 +3790,13 @@ struct ieee80211_prep_tx_info { * should be within a CONFIG_MAC80211_DEBUGFS conditional. This * callback can sleep. * + * @link_sta_add_debugfs: Drivers can use this callback to add debugfs files + * when a link is added to a mac80211 station. This callback + * should be within a CPTCFG_MAC80211_DEBUGFS conditional. This + * callback can sleep. + * For non-MLO the callback will be called once for the deflink with the + * station's directory rather than a separate subdirectory. + * * @sta_notify: Notifies low level driver about power state transition of an * associated station, AP, IBSS/WDS/mesh peer etc. For a VIF operating * in AP mode, this callback will not be called when the flag @@ -4260,6 +4267,10 @@ struct ieee80211_ops { struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct dentry *dir); + void (*link_sta_add_debugfs)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_link_sta *link_sta, + struct dentry *dir); #endif void (*sta_notify)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum sta_notify_cmd, struct ieee80211_sta *sta); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index d3397c1248d3..68c07d4b95a5 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #include @@ -435,8 +435,16 @@ static ssize_t sta_agg_status_write(struct file *file, const char __user *userbu } STA_OPS_RW(agg_status); -static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +/* link sta attributes */ +#define LINK_STA_OPS(name) \ +static const struct file_operations link_sta_ ##name## _ops = { \ + .read = link_sta_##name##_read, \ + .open = simple_open, \ + .llseek = generic_file_llseek, \ +} + +static ssize_t link_sta_ht_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { #define PRINT_HT_CAP(_cond, _str) \ do { \ @@ -446,8 +454,8 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, char *buf, *p; int i; ssize_t bufsz = 512; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_ht_cap *htc = &sta->sta.deflink.ht_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_ht_cap *htc = &link_sta->pub->ht_cap; ssize_t ret; buf = kzalloc(bufsz, GFP_KERNEL); @@ -524,14 +532,14 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, kfree(buf); return ret; } -STA_OPS(ht_capa); +LINK_STA_OPS(ht_capa); -static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static ssize_t link_sta_vht_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { char *buf, *p; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_vht_cap *vhtc = &sta->sta.deflink.vht_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_vht_cap *vhtc = &link_sta->pub->vht_cap; ssize_t ret; ssize_t bufsz = 512; @@ -638,15 +646,15 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, kfree(buf); return ret; } -STA_OPS(vht_capa); +LINK_STA_OPS(vht_capa); -static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, - size_t count, loff_t *ppos) +static ssize_t link_sta_he_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) { char *buf, *p; size_t buf_sz = PAGE_SIZE; - struct sta_info *sta = file->private_data; - struct ieee80211_sta_he_cap *hec = &sta->sta.deflink.he_cap; + struct link_sta_info *link_sta = file->private_data; + struct ieee80211_sta_he_cap *hec = &link_sta->pub->he_cap; struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; u8 ppe_size; u8 *cap; @@ -1011,7 +1019,7 @@ out: kfree(buf); return ret; } -STA_OPS(he_capa); +LINK_STA_OPS(he_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ @@ -1048,12 +1056,7 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(num_ps_buf_frames); DEBUGFS_ADD(last_seq_ctrl); DEBUGFS_ADD(agg_status); - DEBUGFS_ADD(ht_capa); - DEBUGFS_ADD(vht_capa); - DEBUGFS_ADD(he_capa); - - DEBUGFS_ADD_COUNTER(rx_duplicates, deflink.rx_stats.num_duplicates); - DEBUGFS_ADD_COUNTER(rx_fragments, deflink.rx_stats.fragments); + /* FIXME: Kept here as the statistics are only done on the deflink */ DEBUGFS_ADD_COUNTER(tx_filtered, deflink.status_stats.filtered); if (local->ops->wake_tx_queue) { @@ -1076,3 +1079,83 @@ void ieee80211_sta_debugfs_remove(struct sta_info *sta) debugfs_remove_recursive(sta->debugfs_dir); sta->debugfs_dir = NULL; } + +#undef DEBUGFS_ADD +#undef DEBUGFS_ADD_COUNTER + +#define DEBUGFS_ADD(name) \ + debugfs_create_file(#name, 0400, \ + link_sta->debugfs_dir, link_sta, &link_sta_ ##name## _ops) +#define DEBUGFS_ADD_COUNTER(name, field) \ + debugfs_create_ulong(#name, 0400, link_sta->debugfs_dir, &link_sta->field) + +void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta) +{ + if (WARN_ON(!link_sta->sta->debugfs_dir)) + return; + + /* For non-MLO, leave the files in the main directory. */ + if (link_sta->sta->sta.valid_links) { + char link_dir_name[10]; + + snprintf(link_dir_name, sizeof(link_dir_name), + "link-%d", link_sta->link_id); + + link_sta->debugfs_dir = + debugfs_create_dir(link_dir_name, + link_sta->sta->debugfs_dir); + } else { + if (WARN_ON(link_sta != &link_sta->sta->deflink)) + return; + + link_sta->debugfs_dir = link_sta->sta->debugfs_dir; + } + + DEBUGFS_ADD(ht_capa); + DEBUGFS_ADD(vht_capa); + DEBUGFS_ADD(he_capa); + + DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); + DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); +} + +void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta) +{ + if (!link_sta->debugfs_dir || !link_sta->sta->debugfs_dir) { + link_sta->debugfs_dir = NULL; + return; + } + + if (link_sta->debugfs_dir == link_sta->sta->debugfs_dir) { + WARN_ON(link_sta != &link_sta->sta->deflink); + link_sta->sta->debugfs_dir = NULL; + return; + } + + debugfs_remove_recursive(link_sta->debugfs_dir); + link_sta->debugfs_dir = NULL; +} + +void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta) +{ + if (WARN_ON(!link_sta->debugfs_dir)) + return; + + drv_link_sta_add_debugfs(link_sta->sta->local, link_sta->sta->sdata, + link_sta->pub, link_sta->debugfs_dir); +} + +void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta) +{ + if (!link_sta->debugfs_dir) + return; + + if (WARN_ON(link_sta->debugfs_dir == link_sta->sta->debugfs_dir)) + return; + + /* Recreate the directory excluding the driver data */ + debugfs_remove_recursive(link_sta->debugfs_dir); + link_sta->debugfs_dir = NULL; + + ieee80211_link_sta_debugfs_add(link_sta); +} diff --git a/net/mac80211/debugfs_sta.h b/net/mac80211/debugfs_sta.h index d2e7c27ad6d1..cde8148bdb18 100644 --- a/net/mac80211/debugfs_sta.h +++ b/net/mac80211/debugfs_sta.h @@ -7,9 +7,21 @@ #ifdef CONFIG_MAC80211_DEBUGFS void ieee80211_sta_debugfs_add(struct sta_info *sta); void ieee80211_sta_debugfs_remove(struct sta_info *sta); + +void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta); +void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta); + +void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta); +void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta); #else static inline void ieee80211_sta_debugfs_add(struct sta_info *sta) {} static inline void ieee80211_sta_debugfs_remove(struct sta_info *sta) {} + +static inline void ieee80211_link_sta_debugfs_add(struct link_sta_info *link_sta) {} +static inline void ieee80211_link_sta_debugfs_remove(struct link_sta_info *link_sta) {} + +static inline void ieee80211_link_sta_debugfs_drv_add(struct link_sta_info *link_sta) {} +static inline void ieee80211_link_sta_debugfs_drv_remove(struct link_sta_info *link_sta) {} #endif #endif /* __MAC80211_DEBUGFS_STA_H */ diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 5392ffa18270..d737db4e07e2 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -7,6 +7,7 @@ #include "ieee80211_i.h" #include "trace.h" #include "driver-ops.h" +#include "debugfs_sta.h" int drv_start(struct ieee80211_local *local) { @@ -497,6 +498,11 @@ int drv_change_sta_links(struct ieee80211_local *local, struct ieee80211_sta *sta, u16 old_links, u16 new_links) { + struct sta_info *info = container_of(sta, struct sta_info, sta); + struct link_sta_info *link_sta; + unsigned long links_to_add; + unsigned long links_to_rem; + unsigned int link_id; int ret = -EOPNOTSUPP; might_sleep(); @@ -510,11 +516,30 @@ int drv_change_sta_links(struct ieee80211_local *local, if (old_links == new_links) return 0; + links_to_add = ~old_links & new_links; + links_to_rem = old_links & ~new_links; + + for_each_set_bit(link_id, &links_to_rem, IEEE80211_MLD_MAX_NUM_LINKS) { + link_sta = rcu_dereference_protected(info->link[link_id], + lockdep_is_held(&local->sta_mtx)); + + ieee80211_link_sta_debugfs_drv_remove(link_sta); + } + trace_drv_change_sta_links(local, sdata, sta, old_links, new_links); if (local->ops->change_sta_links) ret = local->ops->change_sta_links(&local->hw, &sdata->vif, sta, old_links, new_links); trace_drv_return_int(local, ret); - return ret; + if (ret) + return ret; + + for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { + link_sta = rcu_dereference_protected(info->link[link_id], + lockdep_is_held(&local->sta_mtx)); + ieee80211_link_sta_debugfs_drv_add(link_sta); + } + + return 0; } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 81e40b0a3b16..809bad53e15b 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -480,6 +480,22 @@ static inline void drv_sta_add_debugfs(struct ieee80211_local *local, local->ops->sta_add_debugfs(&local->hw, &sdata->vif, sta, dir); } + +static inline void drv_link_sta_add_debugfs(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_link_sta *link_sta, + struct dentry *dir) +{ + might_sleep(); + + sdata = get_bss_sdata(sdata); + if (!check_sdata_in_driver(sdata)) + return; + + if (local->ops->link_sta_add_debugfs) + local->ops->link_sta_add_debugfs(&local->hw, &sdata->vif, + link_sta, dir); +} #endif static inline void drv_sta_pre_rcu_remove(struct ieee80211_local *local, diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 71b1488bd390..e6beaea4075e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -366,6 +366,9 @@ static void sta_remove_link(struct sta_info *sta, unsigned int link_id, if (unhash) link_sta_info_hash_del(sta->local, link_sta); + if (test_sta_flag(sta, WLAN_STA_INSERTED)) + ieee80211_link_sta_debugfs_remove(link_sta); + if (link_sta != &sta->deflink) alloc = container_of(link_sta, typeof(*alloc), info); @@ -875,6 +878,26 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); + if (sta->sta.valid_links) { + int i; + + for (i = 0; i < ARRAY_SIZE(sta->link); i++) { + struct link_sta_info *link_sta; + + link_sta = rcu_dereference_protected(sta->link[i], + lockdep_is_held(&local->sta_mtx)); + + if (!link_sta) + continue; + + ieee80211_link_sta_debugfs_add(link_sta); + if (sdata->vif.active_links & BIT(i)) + ieee80211_link_sta_debugfs_drv_add(link_sta); + } + } else { + ieee80211_link_sta_debugfs_add(&sta->deflink); + ieee80211_link_sta_debugfs_drv_add(&sta->deflink); + } sinfo->generation = local->sta_generation; cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); @@ -2824,6 +2847,8 @@ int ieee80211_sta_allocate_link(struct sta_info *sta, unsigned int link_id) sta_info_add_link(sta, link_id, &alloc->info, &alloc->sta); + ieee80211_link_sta_debugfs_add(&alloc->info); + return 0; } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 2517ea714dc4..6e672bf9c79d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -513,6 +513,7 @@ struct ieee80211_fragment_cache { * @status_stats.avg_ack_signal: average ACK signal * @cur_max_bandwidth: maximum bandwidth to use for TX to the station, * taken from HT/VHT capabilities or VHT operating mode notification + * @debugfs_dir: debug filesystem directory dentry * @pub: public (driver visible) link STA data * TODO Move other link params from sta_info as required for MLD operation */ @@ -560,6 +561,10 @@ struct link_sta_info { enum ieee80211_sta_rx_bandwidth cur_max_bandwidth; +#ifdef CONFIG_MAC80211_DEBUGFS + struct dentry *debugfs_dir; +#endif + struct ieee80211_link_sta *pub; }; -- cgit v1.2.3 From 53ad07e9823bca10c26e71d662b58c3e80e8ff2a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Sep 2022 11:27:57 +0200 Subject: wifi: cfg80211: support reporting failed links For assoc and connect result APIs, support reporting failed links; they should still come with the BSS pointer in the case of assoc, so they're released correctly. In the case of connect result, this is optional. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 7 +++++++ net/wireless/mlme.c | 4 ++++ net/wireless/nl80211.c | 5 ++++- net/wireless/sme.c | 14 ++++++++++++++ 4 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e09ff87146c1..4d35a4234417 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6933,6 +6933,8 @@ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); * @ap_mld_addr: AP MLD address (in case of MLO) * @links: per-link information indexed by link ID, use links[0] for * non-MLO connections + * @links.status: Set this (along with a BSS pointer) for links that + * were rejected by the AP. */ struct cfg80211_rx_assoc_resp { const u8 *buf; @@ -6944,6 +6946,7 @@ struct cfg80211_rx_assoc_resp { struct { const u8 *addr; struct cfg80211_bss *bss; + u16 status; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; @@ -7454,6 +7457,9 @@ struct cfg80211_fils_resp_params { * if the bss is expired during the connection, esp. for those drivers * implementing connect op. Only one parameter among @bssid and @bss needs * to be specified. + * @links.status: per-link status code, to report a status code that's not + * %WLAN_STATUS_SUCCESS for a given link, it must also be in the + * @valid_links bitmap and may have a BSS pointer (which is then released) */ struct cfg80211_connect_resp_params { int status; @@ -7470,6 +7476,7 @@ struct cfg80211_connect_resp_params { const u8 *addr; const u8 *bssid; struct cfg80211_bss *bss; + u16 status; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 581df7f4c524..58e1fb18f85a 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -42,6 +42,10 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, unsigned int link_id; for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { + cr.links[link_id].status = data->links[link_id].status; + WARN_ON_ONCE(cr.links[link_id].status != WLAN_STATUS_SUCCESS && + (!cr.ap_mld_addr || !cr.links[link_id].bss)); + cr.links[link_id].bss = data->links[link_id].bss; if (!cr.links[link_id].bss) continue; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8ff8b1c040f0..ad7393cd3d18 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17745,6 +17745,7 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, link_info_size += (cr->links[link].bssid || cr->links[link].bss) ? nla_total_size(ETH_ALEN) : 0; + link_info_size += nla_total_size(sizeof(u16)); } } @@ -17813,7 +17814,9 @@ void nl80211_send_connect_result(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_BSSID, ETH_ALEN, bssid)) || (cr->links[link].addr && nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, - cr->links[link].addr))) + cr->links[link].addr)) || + nla_put_u16(msg, NL80211_ATTR_STATUS_CODE, + cr->links[link].status)) goto nla_put_failure; nla_nest_end(msg, nested_mlo_links); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index d513536617bd..f94497e9db43 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -793,6 +793,10 @@ void __cfg80211_connect_result(struct net_device *dev, } for_each_valid_link(cr, link) { + /* don't do extra lookups for failures */ + if (cr->links[link].status != WLAN_STATUS_SUCCESS) + continue; + if (cr->links[link].bss) continue; @@ -829,6 +833,16 @@ void __cfg80211_connect_result(struct net_device *dev, } memset(wdev->links, 0, sizeof(wdev->links)); + for_each_valid_link(cr, link) { + if (cr->links[link].status == WLAN_STATUS_SUCCESS) + continue; + cr->valid_links &= ~BIT(link); + /* don't require bss pointer for failed links */ + if (!cr->links[link].bss) + continue; + cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); + cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); + } wdev->valid_links = cr->valid_links; for_each_valid_link(cr, link) wdev->links[link].client.current_bss = -- cgit v1.2.3 From 7b6f08771bf6045c32a2a1e18201c1aeeb78d72a Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Wed, 7 Sep 2022 10:34:30 +0300 Subject: wifi: ieee80211: Support validating ML station profile length Add a function to validate EHT Multi-Link per station profile length. Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 79690938d9a2..bdf668f9dace 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4685,6 +4685,46 @@ struct ieee80211_mle_per_sta_profile { u8 variable[]; } __packed; +/** + * ieee80211_mle_sta_prof_size_ok - validate multi-link element sta profile size + * @data: pointer to the sub element data + * @len: length of the containing sub element + */ +static inline bool ieee80211_mle_sta_prof_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; + u16 control; + u8 fixed = sizeof(*prof); + u8 info_len = 1; + + if (len < fixed) + return false; + + control = le16_to_cpu(prof->control); + + if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) + info_len += 6; + if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) + info_len += 8; + if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) + info_len += 1; + + if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && + control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) { + if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) + info_len += 2; + else + info_len += 1; + } + + return prof->sta_info_len >= info_len && + fixed + prof->sta_info_len <= len; +} + #define for_each_mle_subelement(_elem, _data, _len) \ if (ieee80211_mle_size_ok(_data, _len)) \ for_each_element(_elem, \ -- cgit v1.2.3 From 1403b109c9a5244dc6ab79154f04eecc209ef3d2 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Wed, 7 Sep 2022 17:23:09 +0300 Subject: wifi: cfg80211/mac80211: Fix ML element common size calculation The common size is part of the length in the data so don't add it again. Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index bdf668f9dace..442b13333da8 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4573,18 +4573,17 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { case IEEE80211_ML_CONTROL_TYPE_BASIC: - common += sizeof(struct ieee80211_mle_basic_common_info); - break; case IEEE80211_ML_CONTROL_TYPE_PREQ: - common += sizeof(struct ieee80211_mle_preq_common_info); + case IEEE80211_ML_CONTROL_TYPE_TDLS: + /* + * The length is the first octet pointed by mle->variable so no + * need to add anything + */ break; case IEEE80211_ML_CONTROL_TYPE_RECONF: if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) common += ETH_ALEN; return common; - case IEEE80211_ML_CONTROL_TYPE_TDLS: - common += sizeof(struct ieee80211_mle_tdls_common_info); - break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR) common += ETH_ALEN; -- cgit v1.2.3 From fb99c7d4d6d0fb4fe5a953e0c5f6c37a5b796b98 Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Sun, 11 Sep 2022 16:55:12 +0300 Subject: wifi: cfg80211/mac80211: Fix ML element common size validation The Multi-Link element can be fragmented, thus its size can exceed 254. Thus, modify ieee80211_mle_size_ok() to use 'size_t len' instead of 'u8 len'. Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 442b13333da8..b935a85b2f44 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4601,7 +4601,7 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) * @data: pointer to the element data * @len: length of the containing element */ -static inline bool ieee80211_mle_size_ok(const u8 *data, u8 len) +static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) { const struct ieee80211_multi_link_elem *mle = (const void *)data; u8 fixed = sizeof(*mle); -- cgit v1.2.3 From 45ebac4f059b92906e7e86dd1a780739f883857c Mon Sep 17 00:00:00 2001 From: Ilan Peer Date: Tue, 6 Sep 2022 11:48:56 +0300 Subject: wifi: mac80211: Parse station profile from association response When processing an association response frame for a Multi-Link connection, extract the per station profile for each additional link, and use it for parsing the link elements. As the Multi-Link element might be fragmented, add support for reassembling a fragmented element. To simplify memory management logic, extend 'struct ieee802_11_elems' to hold a scratch buffer, which is used for the defragmentation. Once an element is reconstructed in the scratch area, point the corresponding element pointer to it. Currently only defragmentation of Multi-Link element and the contained per-STA profile subelement is supported. Signed-off-by: Ilan Peer Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 1 + net/mac80211/ieee80211_i.h | 26 +++++++- net/mac80211/mlme.c | 17 ++++- net/mac80211/util.c | 150 ++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 188 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b935a85b2f44..f51e939f28f2 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4666,6 +4666,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) enum ieee80211_mle_subelems { IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, + IEEE80211_MLE_SUBELEM_FRAGMENT = 254, }; #define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 4e1d4c339f2d..5dcbc8de53fd 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1707,8 +1707,27 @@ struct ieee802_11_elems { u8 tx_pwr_env_num; u8 eht_cap_len; + /* mult-link element can be de-fragmented and thus u8 is not sufficient */ + size_t multi_link_len; + + /* + * store the per station profile pointer and length in case that the + * parsing also handled Multi-Link element parsing for a specific link + * ID. + */ + struct ieee80211_mle_per_sta_profile *prof; + size_t sta_prof_len; + /* whether a parse error occurred while retrieving these elements */ bool parse_error; + + /* + * scratch buffer that can be used for various element parsing related + * tasks, e.g., element de-fragmentation etc. + */ + size_t scratch_len; + u8 *scratch_pos; + u8 scratch[]; }; static inline struct ieee80211_local *hw_to_local( @@ -2197,9 +2216,13 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, * represent a non-transmitting BSS in which case the data * for that non-transmitting BSS is returned * @link_id: the link ID to parse elements for, if a STA profile - * is present in the multi-link element, or -1 to ignore + * is present in the multi-link element, or -1 to ignore; + * note that the code currently assumes parsing an association + * (or re-association) response frame if this is given * @from_ap: frame is received from an AP (currently used only * for EHT capabilities parsing) + * @scratch_len: if non zero, specifies the requested length of the scratch + * buffer; otherwise, 'len' is used. */ struct ieee80211_elems_parse_params { const u8 *start; @@ -2210,6 +2233,7 @@ struct ieee80211_elems_parse_params { struct cfg80211_bss *bss; int link_id; bool from_ap; + size_t scratch_len; }; struct ieee802_11_elems * diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 54b8d5065bbd..a7e06c8ddaf3 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3923,11 +3923,12 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, struct ieee80211_mgd_assoc_data *assoc_data = sdata->u.mgd.assoc_data; struct ieee80211_bss_conf *bss_conf = link->conf; struct ieee80211_local *local = sdata->local; + unsigned int link_id = link->link_id; struct ieee80211_elems_parse_params parse_params = { .start = elem_start, .len = elem_len, .bss = cbss, - .link_id = link == &sdata->deflink ? -1 : link->link_id, + .link_id = link_id == assoc_data->assoc_link_id ? -1 : link_id, .from_ap = true, }; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; @@ -3942,8 +3943,18 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, if (!elems) return false; - /* FIXME: use from STA profile element after parsing that */ - capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); + if (link_id == assoc_data->assoc_link_id) { + capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info); + } else if (!elems->prof) { + ret = false; + goto out; + } else { + const u8 *ptr = elems->prof->variable + + elems->prof->sta_info_len - 1; + + /* FIXME: need to also handle the status code */ + capab_info = get_unaligned_le16(ptr); + } if (!is_s1g && !elems->supp_rates) { sdata_info(sdata, "no SuppRates element in AssocResp\n"); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index bf7461c41bef..40b75fa82b15 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1026,8 +1026,10 @@ ieee80211_parse_extension_element(u32 *crc, elems->eht_operation = data; break; case WLAN_EID_EXT_EHT_MULTI_LINK: - if (ieee80211_mle_size_ok(data, len)) + if (ieee80211_mle_size_ok(data, len)) { elems->multi_link = (void *)data; + elems->multi_link_len = len; + } break; } } @@ -1497,6 +1499,145 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len, return found ? profile_len : 0; } +static void ieee80211_defragment_element(struct ieee802_11_elems *elems, + void **elem_ptr, size_t *len, + size_t total_len, u8 frag_id) +{ + u8 *data = *elem_ptr, *pos, *start; + const struct element *elem; + + /* + * Since 'data' points to the data of the element, not the element + * itself, allow 254 in case it was an extended element where the + * extended ID isn't part of the data we see here and thus not part of + * 'len' either. + */ + if (!data || (*len != 254 && *len != 255)) + return; + + start = elems->scratch_pos; + + if (WARN_ON(*len > (elems->scratch + elems->scratch_len - + elems->scratch_pos))) + return; + + memcpy(elems->scratch_pos, data, *len); + elems->scratch_pos += *len; + + pos = data + *len; + total_len -= *len; + for_each_element(elem, pos, total_len) { + if (elem->id != frag_id) + break; + + if (WARN_ON(elem->datalen > + (elems->scratch + elems->scratch_len - + elems->scratch_pos))) + return; + + memcpy(elems->scratch_pos, elem->data, elem->datalen); + elems->scratch_pos += elem->datalen; + + *len += elem->datalen; + } + + *elem_ptr = start; +} + +static void ieee80211_mle_get_sta_prof(struct ieee802_11_elems *elems, + u8 link_id) +{ + const struct ieee80211_multi_link_elem *ml = elems->multi_link; + size_t ml_len = elems->multi_link_len; + const struct element *sub; + + if (!ml || !ml_len) + return; + + if (le16_get_bits(ml->control, IEEE80211_ML_CONTROL_TYPE) != + IEEE80211_ML_CONTROL_TYPE_BASIC) + return; + + for_each_mle_subelement(sub, (u8 *)ml, ml_len) { + struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; + u16 control; + + if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE) + continue; + + if (!ieee80211_mle_sta_prof_size_ok(sub->data, sub->datalen)) + return; + + control = le16_to_cpu(prof->control); + + if (link_id != u16_get_bits(control, + IEEE80211_MLE_STA_CONTROL_LINK_ID)) + continue; + + if (!(control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE)) + return; + + elems->prof = prof; + elems->sta_prof_len = sub->datalen; + + /* the sub element can be fragmented */ + ieee80211_defragment_element(elems, (void **)&elems->prof, + &elems->sta_prof_len, + ml_len - (sub->data - (u8 *)ml), + IEEE80211_MLE_SUBELEM_FRAGMENT); + return; + } +} + +static void ieee80211_mle_parse_link(struct ieee802_11_elems *elems, + struct ieee80211_elems_parse_params *params) +{ + struct ieee80211_mle_per_sta_profile *prof; + struct ieee80211_elems_parse_params sub = { + .action = params->action, + .from_ap = params->from_ap, + .link_id = -1, + }; + const struct element *non_inherit = NULL; + const u8 *end; + + if (params->link_id == -1) + return; + + ieee80211_defragment_element(elems, (void **)&elems->multi_link, + &elems->multi_link_len, + elems->total_len - ((u8 *)elems->multi_link - + elems->ie_start), + WLAN_EID_FRAGMENT); + + ieee80211_mle_get_sta_prof(elems, params->link_id); + prof = elems->prof; + + if (!prof) + return; + + /* check if we have the 4 bytes for the fixed part in assoc response */ + if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) { + elems->prof = NULL; + elems->sta_prof_len = 0; + return; + } + + /* + * Skip the capability information and the status code that are expected + * as part of the station profile in association response frames. Note + * the -1 is because the 'sta_info_len' is accounted to as part of the + * per-STA profile, but not part of the 'u8 variable[]' portion. + */ + sub.start = prof->variable + prof->sta_info_len - 1 + 4; + end = (const u8 *)prof + elems->sta_prof_len; + sub.len = end - sub.start; + + non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + sub.start, sub.len); + _ieee802_11_parse_elems_full(&sub, elems, non_inherit); +} + struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) { @@ -1504,12 +1645,15 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) const struct element *non_inherit = NULL; u8 *nontransmitted_profile; int nontransmitted_profile_len = 0; + size_t scratch_len = params->scratch_len ?: 2 * params->len; - elems = kzalloc(sizeof(*elems), GFP_ATOMIC); + elems = kzalloc(sizeof(*elems) + scratch_len, GFP_ATOMIC); if (!elems) return NULL; elems->ie_start = params->start; elems->total_len = params->len; + elems->scratch_len = scratch_len; + elems->scratch_pos = elems->scratch; nontransmitted_profile = kmalloc(params->len, GFP_ATOMIC); if (nontransmitted_profile) { @@ -1537,6 +1681,8 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) _ieee802_11_parse_elems_full(&sub, elems, NULL); } + ieee80211_mle_parse_link(elems, params); + if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; -- cgit v1.2.3 From 1e0f8cc96b7162075d2e3b6bef856497884a3ae8 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 6 Sep 2022 22:37:03 +0200 Subject: wifi: nl80211: use link ID in NL80211_CMD_SET_BSS We clearly need the link ID here, to know the right BSS to configure. Use/require it. Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 ++ net/wireless/nl80211.c | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 4d35a4234417..659dd1bee70f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2105,6 +2105,7 @@ struct mpath_info { * * Used to change BSS parameters (mainly for AP mode). * + * @link_id: link_id or -1 for non-MLD * @use_cts_prot: Whether to use CTS protection * (0 = no, 1 = yes, -1 = do not change) * @use_short_preamble: Whether the use of short preambles is allowed @@ -2122,6 +2123,7 @@ struct mpath_info { * @p2p_opp_ps: P2P opportunistic PS (-1 = no change) */ struct bss_parameters { + int link_id; int use_cts_prot; int use_short_preamble; int use_short_slot_time; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ad7393cd3d18..1d0277758d0e 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7780,6 +7780,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) int err; memset(¶ms, 0, sizeof(params)); + params.link_id = nl80211_link_id_or_invalid(info->attrs); /* default to not changing parameters */ params.use_cts_prot = -1; params.use_short_preamble = -1; @@ -16564,7 +16565,8 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_set_bss, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP), + .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_GET_REG, -- cgit v1.2.3 From f3630c4f82ae43682bf84e6ddcbd7e97285d4699 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 27 Sep 2022 11:39:23 +0200 Subject: wifi: mac80211: add RCU _check() link access variants We might sometimes need to use RCU and locking in the same code path, so add the two variants link_conf_dereference_check() and link_sta_dereference_check(). Signed-off-by: Johannes Berg --- include/net/mac80211.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c413050ec8dd..cda4584dfd51 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1915,6 +1915,10 @@ static inline bool lockdep_vif_mutex_held(struct ieee80211_vif *vif) rcu_dereference_protected((vif)->link_conf[link_id], \ lockdep_vif_mutex_held(vif)) +#define link_conf_dereference_check(vif, link_id) \ + rcu_dereference_check((vif)->link_conf[link_id], \ + lockdep_vif_mutex_held(vif)) + /** * enum ieee80211_key_flags - key flags * @@ -2311,6 +2315,10 @@ static inline bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta) rcu_dereference_protected((sta)->link[link_id], \ lockdep_sta_mutex_held(sta)) +#define link_sta_dereference_check(sta, link_id) \ + rcu_dereference_check((sta)->link[link_id], \ + lockdep_sta_mutex_held(sta)) + #define for_each_sta_active_link(vif, sta, link_sta, link_id) \ for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) \ if ((!(vif)->active_links || \ -- cgit v1.2.3 From 1177aaa7fe9373c762cd5bf5f5de8517bac989d5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Sat, 17 Sep 2022 03:14:53 +0200 Subject: wifi: fix multi-link element subelement iteration The subelements obviously start after the common data, including the common multi-link element structure definition itself. This bug was possibly just hidden by the higher bits of the control being set to 0, so the iteration just found one bogus element and most of the code could continue anyway. Fixes: 0f48b8b88aa9 ("wifi: ieee80211: add definitions for multi-link element") Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f51e939f28f2..6252f02f38b7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4593,7 +4593,7 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) return 0; } - return common + mle->variable[0]; + return sizeof(*mle) + common + mle->variable[0]; } /** -- cgit v1.2.3 From 0ff57171d6d225558c81a69439d5323e35b40549 Mon Sep 17 00:00:00 2001 From: Vinayak Yadawad Date: Wed, 7 Sep 2022 18:14:48 +0530 Subject: cfg80211: Update Transition Disable policy during port authorization In case of 4way handshake offload, transition disable policy updated by the AP during EAPOL 3/4 is not updated to the upper layer. This results in mismatch between transition disable policy between the upper layer and the driver. This patch addresses this issue by updating transition disable policy as part of port authorization indication. Signed-off-by: Vinayak Yadawad Signed-off-by: Johannes Berg --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 +- include/net/cfg80211.h | 4 +++- include/uapi/linux/nl80211.h | 3 +++ net/wireless/core.h | 5 ++++- net/wireless/nl80211.c | 8 +++++++- net/wireless/nl80211.h | 3 ++- net/wireless/sme.c | 12 ++++++++---- net/wireless/util.c | 4 +++- 8 files changed, 31 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index bf184c0e64cb..3f2336062217 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -6268,7 +6268,7 @@ done: brcmf_dbg(CONN, "Report roaming result\n"); if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X && profile->is_ft) { - cfg80211_port_authorized(ndev, profile->bssid, GFP_KERNEL); + cfg80211_port_authorized(ndev, profile->bssid, NULL, 0, GFP_KERNEL); brcmf_dbg(CONN, "Report port authorized\n"); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 659dd1bee70f..11a370e64143 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7683,6 +7683,8 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, * * @dev: network device * @bssid: the BSSID of the AP + * @td_bitmap: transition disable policy + * @td_bitmap_len: Length of transition disable policy * @gfp: allocation flags * * This function should be called by a driver that supports 4 way handshake @@ -7693,7 +7695,7 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, * indicate the 802.11 association. */ void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, - gfp_t gfp); + const u8* td_bitmap, u8 td_bitmap_len, gfp_t gfp); /** * cfg80211_disconnected - notify cfg80211 that connection was dropped diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c32e7616a366..c14a91bbca7c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2749,6 +2749,8 @@ enum nl80211_commands { * When used with %NL80211_CMD_FRAME_TX_STATUS, indicates the ack RX * timestamp. When used with %NL80211_CMD_FRAME RX notification, indicates * the incoming frame RX timestamp. + * @NL80211_ATTR_TD_BITMAP: Transition Disable bitmap, for subsequent + * (re)associations. * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3276,6 +3278,7 @@ enum nl80211_attrs { NL80211_ATTR_TX_HW_TIMESTAMP, NL80211_ATTR_RX_HW_TIMESTAMP, + NL80211_ATTR_TD_BITMAP, /* add attributes here, update the policy in nl80211.c */ diff --git a/net/wireless/core.h b/net/wireless/core.h index 775e16cb99ed..af85d8909935 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -271,6 +271,8 @@ struct cfg80211_event { } ij; struct { u8 bssid[ETH_ALEN]; + const u8 *td_bitmap; + u8 td_bitmap_len; } pa; }; }; @@ -409,7 +411,8 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1d0277758d0e..fe368af39554 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17942,7 +17942,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, } void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid) + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { struct sk_buff *msg; void *hdr; @@ -17962,6 +17963,11 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) goto nla_put_failure; + if ((td_bitmap_len > 0) && td_bitmap) + if (nla_put(msg, NL80211_ATTR_TD_BITMAP, + td_bitmap_len, td_bitmap)) + goto nla_put_failure; + genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 855d540ddfb9..ba9457e94c43 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -83,7 +83,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid); + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f94497e9db43..4b5b6ee0fe01 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1251,7 +1251,8 @@ out: } EXPORT_SYMBOL(cfg80211_roamed); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { ASSERT_WDEV_LOCK(wdev); @@ -1264,11 +1265,11 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) return; nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, - bssid); + bssid, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, - gfp_t gfp) + const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -1278,12 +1279,15 @@ void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, if (WARN_ON(!bssid)) return; - ev = kzalloc(sizeof(*ev), gfp); + ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.bssid, bssid, ETH_ALEN); + ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); + ev->pa.td_bitmap_len = td_bitmap_len; + memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending diff --git a/net/wireless/util.c b/net/wireless/util.c index 01493568a21d..f09d528e5199 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -988,7 +988,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: - __cfg80211_port_authorized(wdev, ev->pa.bssid); + __cfg80211_port_authorized(wdev, ev->pa.bssid, + ev->pa.td_bitmap, + ev->pa.td_bitmap_len); break; } wdev_unlock(wdev); -- cgit v1.2.3 From c850e31f79f049af5022f07cd9961605b4470d0b Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Sun, 9 Oct 2022 18:30:38 +0200 Subject: wifi: mac80211: add internal handler for wake_tx_queue Start to align the TX handling to only use internal TX queues (iTXQs): Provide a handler for drivers not having a custom wake_tx_queue callback and update the documentation. Signed-off-by: Alexander Wetzel Signed-off-by: Johannes Berg --- include/net/mac80211.h | 51 +++++++++++++++++++++++++++++++------------------- net/mac80211/util.c | 46 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 78 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index cda4584dfd51..721c450a9ccd 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -89,15 +89,13 @@ /** * DOC: mac80211 software tx queueing * - * mac80211 provides an optional intermediate queueing implementation designed - * to allow the driver to keep hardware queues short and provide some fairness - * between different stations/interfaces. - * In this model, the driver pulls data frames from the mac80211 queue instead - * of letting mac80211 push them via drv_tx(). - * Other frames (e.g. control or management) are still pushed using drv_tx(). + * mac80211 uses an intermediate queueing implementation, designed to allow the + * driver to keep hardware queues short and to provide some fairness between + * different stations/interfaces. * - * Drivers indicate that they use this model by implementing the .wake_tx_queue - * driver operation. + * Drivers must provide the .wake_tx_queue driver operation by either + * linking it to ieee80211_handle_wake_tx_queue() or implementing a custom + * handler. * * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with * another per-sta for non-data/non-mgmt and bufferable management frames, and @@ -106,9 +104,12 @@ * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. * - * The driver can't access the queue directly. To dequeue a frame from a - * txq, it calls ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a - * queue, it calls the .wake_tx_queue driver op. + * The driver can't access the internal TX queues (iTXQs) directly. + * Whenever mac80211 adds a new frame to a queue, it calls the .wake_tx_queue + * driver op. + * Drivers implementing a custom .wake_tx_queue op can get them by calling + * ieee80211_tx_dequeue(). Drivers using ieee80211_handle_wake_tx_queue() will + * simply get the individual frames pushed via the .tx driver operation. * * Drivers can optionally delegate responsibility for scheduling queues to * mac80211, to take advantage of airtime fairness accounting. In this case, to @@ -1826,7 +1827,7 @@ struct ieee80211_vif_cfg { * for this interface. * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). - * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) + * @txq: the multicast data TX queue * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, * protected by fq->lock. * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see @@ -2259,8 +2260,8 @@ struct ieee80211_link_sta { * For non MLO STA it will point to the deflink data. For MLO STA * ieee80211_sta_recalc_aggregates() must be called to update it. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. - * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that - * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames + * @txq: per-TID data TX queues; note that the last entry (%IEEE80211_NUM_TIDS) + * is used for non-data frames * @deflink: This holds the default link STA information, for non MLO STA all link * specific STA information is accessed through @deflink or through * link[0] which points to address of @deflink. For MLO Link STA @@ -5713,7 +5714,7 @@ void ieee80211_key_replay(struct ieee80211_key_conf *keyconf); * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * - * Drivers should use this function instead of netif_wake_queue. + * Drivers must use this function instead of netif_wake_queue. */ void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue); @@ -5722,7 +5723,7 @@ void ieee80211_wake_queue(struct ieee80211_hw *hw, int queue); * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * - * Drivers should use this function instead of netif_stop_queue. + * Drivers must use this function instead of netif_stop_queue. */ void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue); @@ -5731,7 +5732,7 @@ void ieee80211_stop_queue(struct ieee80211_hw *hw, int queue); * @hw: pointer as obtained from ieee80211_alloc_hw(). * @queue: queue number (counted from zero). * - * Drivers should use this function instead of netif_stop_queue. + * Drivers must use this function instead of netif_queue_stopped. * * Return: %true if the queue is stopped. %false otherwise. */ @@ -5742,7 +5743,7 @@ int ieee80211_queue_stopped(struct ieee80211_hw *hw, int queue); * ieee80211_stop_queues - stop all queues * @hw: pointer as obtained from ieee80211_alloc_hw(). * - * Drivers should use this function instead of netif_stop_queue. + * Drivers must use this function instead of netif_tx_stop_all_queues. */ void ieee80211_stop_queues(struct ieee80211_hw *hw); @@ -5750,7 +5751,7 @@ void ieee80211_stop_queues(struct ieee80211_hw *hw); * ieee80211_wake_queues - wake all queues * @hw: pointer as obtained from ieee80211_alloc_hw(). * - * Drivers should use this function instead of netif_wake_queue. + * Drivers must use this function instead of netif_tx_wake_all_queues. */ void ieee80211_wake_queues(struct ieee80211_hw *hw); @@ -6971,6 +6972,18 @@ static inline struct sk_buff *ieee80211_tx_dequeue_ni(struct ieee80211_hw *hw, return skb; } +/** + * ieee80211_handle_wake_tx_queue - mac80211 handler for wake_tx_queue callback + * + * @hw: pointer as obtained from wake_tx_queue() callback(). + * @txq: pointer as obtained from wake_tx_queue() callback(). + * + * Drivers can use this function for the mandatory mac80211 wake_tx_queue + * callback in struct ieee80211_ops. They should not call this function. + */ +void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); + /** * ieee80211_next_txq - get next tx queue to pull packets from * diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 40b75fa82b15..a4bf86f17c39 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -288,6 +288,52 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ctstoself_duration); +static void wake_tx_push_queue(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_txq *queue) +{ + int q = sdata->vif.hw_queue[queue->ac]; + struct ieee80211_tx_control control = { + .sta = queue->sta, + }; + struct sk_buff *skb; + unsigned long flags; + bool q_stopped; + + while (1) { + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + q_stopped = local->queue_stop_reasons[q]; + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + + if (q_stopped) + break; + + skb = ieee80211_tx_dequeue(&local->hw, queue); + if (!skb) + break; + + drv_tx(local, &control, skb); + } +} + +/* wake_tx_queue handler for driver not implementing a custom one*/ +void ieee80211_handle_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); + struct ieee80211_txq *queue; + + /* Use ieee80211_next_txq() for airtime fairness accounting */ + ieee80211_txq_schedule_start(hw, txq->ac); + while ((queue = ieee80211_next_txq(hw, txq->ac))) { + wake_tx_push_queue(local, sdata, queue); + ieee80211_return_txq(hw, queue, false); + } + ieee80211_txq_schedule_end(hw, txq->ac); +} +EXPORT_SYMBOL(ieee80211_handle_wake_tx_queue); + static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) { struct ieee80211_local *local = sdata->local; -- cgit v1.2.3 From a6a6163b9a934df5965792d60af1f53aa51fdd39 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 7 Oct 2022 10:53:03 +0200 Subject: mac802154: Introduce filtering levels The 802154 specification details several filtering levels in which the PHY and the MAC could be. The amount of filtering will vary if they are in promiscuous mode or in scanning mode. Otherwise they are expected to do some very basic checks, such as enforcing the frame validity. Either the PHY is able to do so, and the MAC has nothing to do, or the PHY has a lower filtering level than expected and the MAC should take over. For now we just define these levels in an enumeration. In a second time, we will add a per-PHY parameter showing the expected filtering level as well as a per device current filtering level, and will initialize all these fields. In a third time, we will use them to apply more filtering by software when the PHY is limited. Indeed, if the drivers know they cannot reach the requested level of filtering, they will overwrite the "current filtering" parameter so that it reflects what they do. Then, in the core, the expected filtering level will be used to decide whether some additional software processing is needed or not. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20221007085310.503366-2-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/linux/ieee802154.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index f1f9412b6ac6..0303eb84d596 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -276,6 +276,30 @@ enum { IEEE802154_SYSTEM_ERROR = 0xff, }; +/** + * enum ieee802154_filtering_level - Filtering levels applicable to a PHY + * + * @IEEE802154_FILTERING_NONE: No filtering at all, what is received is + * forwarded to the softMAC + * @IEEE802154_FILTERING_1_FCS: First filtering level, frames with an invalid + * FCS should be dropped + * @IEEE802154_FILTERING_2_PROMISCUOUS: Second filtering level, promiscuous + * mode as described in the spec, identical in terms of filtering to the + * level one on PHY side, but at the MAC level the frame should be + * forwarded to the upper layer directly + * @IEEE802154_FILTERING_3_SCAN: Third filtering level, scan related, where + * only beacons must be processed, all remaining traffic gets dropped + * @IEEE802154_FILTERING_4_FRAME_FIELDS: Fourth filtering level actually + * enforcing the validity of the content of the frame with various checks + */ +enum ieee802154_filtering_level { + IEEE802154_FILTERING_NONE, + IEEE802154_FILTERING_1_FCS, + IEEE802154_FILTERING_2_PROMISCUOUS, + IEEE802154_FILTERING_3_SCAN, + IEEE802154_FILTERING_4_FRAME_FIELDS, +}; + /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 #define IEEE802154_FCTL_ACKREQ 0x0020 -- cgit v1.2.3 From ac8037c35bd1fb1799d39f52205f813e6585b58b Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Fri, 7 Oct 2022 10:53:05 +0200 Subject: mac802154: set filter at drv_start() The current filtering level is set on the first interface up on a wpan phy. If we support scan functionality we need to change the filtering level on the fly on an operational phy and switching back again. This patch will move the receive mode parameter e.g. address filter and promiscuous mode to the drv_start() functionality to allow changing the receive mode on an operational phy not on first ifup only. In future this should be handled on driver layer because each hardware has it's own way to enter a specific filtering level. However this should offer to switch to mode IEEE802154_FILTERING_NONE and back to IEEE802154_FILTERING_4_FRAME_FIELDS. Only IEEE802154_FILTERING_4_FRAME_FIELDS and IEEE802154_FILTERING_NONE are somewhat supported by current hardware. All other filtering levels can be supported in future but will end in IEEE802154_FILTERING_NONE as the receive part can kind of "emulate" those receive paths by doing additional filtering routines. There are in total three filtering levels in the code: - the per-interface default level (should not be changed) - the required per-interface level (mac commands may play with it) - the actual per-PHY (hw) level that is currently in use Signed-off-by: Alexander Aring [ Link: https://lore.kernel.org/r/20221007085310.503366-4-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 7 +++-- net/mac802154/cfg.c | 2 +- net/mac802154/driver-ops.h | 71 +++++++++++++++++++++++++++++++++++++++++++- net/mac802154/ieee802154_i.h | 12 ++++++++ net/mac802154/iface.c | 44 ++++++++++----------------- net/mac802154/rx.c | 12 +++++++- 6 files changed, 115 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 428cece22205..e1481f9cf049 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -223,6 +223,11 @@ struct wpan_phy { atomic_t hold_txs; wait_queue_head_t sync_txq; + /* Current filtering level on reception. + * Only allowed to be changed if phy is not operational. + */ + enum ieee802154_filtering_level filtering; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -374,8 +379,6 @@ struct wpan_dev { bool lbt; - bool promiscuous_mode; - /* fallback for acknowledgment bit setting */ bool ackreq; }; diff --git a/net/mac802154/cfg.c b/net/mac802154/cfg.c index 93df24f75572..dc2d918fac68 100644 --- a/net/mac802154/cfg.c +++ b/net/mac802154/cfg.c @@ -67,7 +67,7 @@ static int ieee802154_resume(struct wpan_phy *wpan_phy) goto wake_up; /* restart hardware */ - ret = drv_start(local); + ret = drv_start(local, local->phy->filtering, &local->addr_filt); if (ret) return ret; diff --git a/net/mac802154/driver-ops.h b/net/mac802154/driver-ops.h index c9d54088a567..a7af3f0ddb3e 100644 --- a/net/mac802154/driver-ops.h +++ b/net/mac802154/driver-ops.h @@ -129,12 +129,81 @@ drv_set_promiscuous_mode(struct ieee802154_local *local, bool on) return ret; } -static inline int drv_start(struct ieee802154_local *local) +static inline int drv_start(struct ieee802154_local *local, + enum ieee802154_filtering_level level, + const struct ieee802154_hw_addr_filt *addr_filt) { int ret; might_sleep(); + /* setup receive mode parameters e.g. address mode */ + if (local->hw.flags & IEEE802154_HW_AFILT) { + ret = drv_set_pan_id(local, addr_filt->pan_id); + if (ret < 0) + return ret; + + ret = drv_set_short_addr(local, addr_filt->short_addr); + if (ret < 0) + return ret; + + ret = drv_set_extended_addr(local, addr_filt->ieee_addr); + if (ret < 0) + return ret; + } + + switch (level) { + case IEEE802154_FILTERING_NONE: + fallthrough; + case IEEE802154_FILTERING_1_FCS: + fallthrough; + case IEEE802154_FILTERING_2_PROMISCUOUS: + /* TODO: Requires a different receive mode setup e.g. + * at86rf233 hardware. + */ + fallthrough; + case IEEE802154_FILTERING_3_SCAN: + if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { + ret = drv_set_promiscuous_mode(local, true); + if (ret < 0) + return ret; + } else { + return -EOPNOTSUPP; + } + + /* In practice other filtering levels can be requested, but as + * for now most hardware/drivers only support + * IEEE802154_FILTERING_NONE, we fallback to this actual + * filtering level in hardware and make our own additional + * filtering in mac802154 receive path. + * + * TODO: Move this logic to the device drivers as hardware may + * support more higher level filters. Hardware may also require + * a different order how register are set, which could currently + * be buggy, so all received parameters need to be moved to the + * start() callback and let the driver go into the mode before + * it will turn on receive handling. + */ + local->phy->filtering = IEEE802154_FILTERING_NONE; + break; + case IEEE802154_FILTERING_4_FRAME_FIELDS: + /* Do not error out if IEEE802154_HW_PROMISCUOUS because we + * expect the hardware to operate at the level + * IEEE802154_FILTERING_4_FRAME_FIELDS anyway. + */ + if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { + ret = drv_set_promiscuous_mode(local, false); + if (ret < 0) + return ret; + } + + local->phy->filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; + break; + default: + WARN_ON(1); + return -EINVAL; + } + trace_802154_drv_start(local); local->started = true; smp_mb(); diff --git a/net/mac802154/ieee802154_i.h b/net/mac802154/ieee802154_i.h index 010365a6364e..509e0172fe82 100644 --- a/net/mac802154/ieee802154_i.h +++ b/net/mac802154/ieee802154_i.h @@ -26,6 +26,8 @@ struct ieee802154_local { struct ieee802154_hw hw; const struct ieee802154_ops *ops; + /* hardware address filter */ + struct ieee802154_hw_addr_filt addr_filt; /* ieee802154 phy */ struct wpan_phy *phy; @@ -82,6 +84,16 @@ struct ieee802154_sub_if_data { struct ieee802154_local *local; struct net_device *dev; + /* Each interface starts and works in nominal state at a given filtering + * level given by iface_default_filtering, which is set once for all at + * the interface creation and should not evolve over time. For some MAC + * operations however, the filtering level may change temporarily, as + * reflected in the required_filtering field. The actual filtering at + * the PHY level may be different and is shown in struct wpan_phy. + */ + enum ieee802154_filtering_level iface_default_filtering; + enum ieee802154_filtering_level required_filtering; + unsigned long state; char name[IFNAMSIZ]; diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 500ed1b81250..d9b50884d34e 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -147,25 +147,12 @@ static int ieee802154_setup_hw(struct ieee802154_sub_if_data *sdata) struct wpan_dev *wpan_dev = &sdata->wpan_dev; int ret; - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { - ret = drv_set_promiscuous_mode(local, - wpan_dev->promiscuous_mode); - if (ret < 0) - return ret; - } + sdata->required_filtering = sdata->iface_default_filtering; if (local->hw.flags & IEEE802154_HW_AFILT) { - ret = drv_set_pan_id(local, wpan_dev->pan_id); - if (ret < 0) - return ret; - - ret = drv_set_extended_addr(local, wpan_dev->extended_addr); - if (ret < 0) - return ret; - - ret = drv_set_short_addr(local, wpan_dev->short_addr); - if (ret < 0) - return ret; + local->addr_filt.pan_id = wpan_dev->pan_id; + local->addr_filt.ieee_addr = wpan_dev->extended_addr; + local->addr_filt.short_addr = wpan_dev->short_addr; } if (local->hw.flags & IEEE802154_HW_LBT) { @@ -206,7 +193,8 @@ static int mac802154_slave_open(struct net_device *dev) if (res) goto err; - res = drv_start(local); + res = drv_start(local, sdata->required_filtering, + &local->addr_filt); if (res) goto err; } @@ -223,15 +211,16 @@ err: static int ieee802154_check_mac_settings(struct ieee802154_local *local, - struct wpan_dev *wpan_dev, - struct wpan_dev *nwpan_dev) + struct ieee802154_sub_if_data *sdata, + struct ieee802154_sub_if_data *nsdata) { + struct wpan_dev *nwpan_dev = &nsdata->wpan_dev; + struct wpan_dev *wpan_dev = &sdata->wpan_dev; + ASSERT_RTNL(); - if (local->hw.flags & IEEE802154_HW_PROMISCUOUS) { - if (wpan_dev->promiscuous_mode != nwpan_dev->promiscuous_mode) - return -EBUSY; - } + if (sdata->iface_default_filtering != nsdata->iface_default_filtering) + return -EBUSY; if (local->hw.flags & IEEE802154_HW_AFILT) { if (wpan_dev->pan_id != nwpan_dev->pan_id || @@ -285,8 +274,7 @@ ieee802154_check_concurrent_iface(struct ieee802154_sub_if_data *sdata, /* check all phy mac sublayer settings are the same. * We have only one phy, different values makes trouble. */ - ret = ieee802154_check_mac_settings(local, wpan_dev, - &nsdata->wpan_dev); + ret = ieee802154_check_mac_settings(local, sdata, nsdata); if (ret < 0) return ret; } @@ -586,7 +574,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, sdata->dev->priv_destructor = mac802154_wpan_free; sdata->dev->netdev_ops = &mac802154_wpan_ops; sdata->dev->ml_priv = &mac802154_mlme_wpan; - wpan_dev->promiscuous_mode = false; + sdata->iface_default_filtering = IEEE802154_FILTERING_4_FRAME_FIELDS; wpan_dev->header_ops = &ieee802154_header_ops; mutex_init(&sdata->sec_mtx); @@ -600,7 +588,7 @@ ieee802154_setup_sdata(struct ieee802154_sub_if_data *sdata, case NL802154_IFTYPE_MONITOR: sdata->dev->needs_free_netdev = true; sdata->dev->netdev_ops = &mac802154_monitor_ops; - wpan_dev->promiscuous_mode = true; + sdata->iface_default_filtering = IEEE802154_FILTERING_NONE; break; default: BUG(); diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index b8ce84618a55..8543c28948a0 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -268,10 +268,20 @@ void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb) ieee802154_monitors_rx(local, skb); + /* TODO: Avoid delivering frames received at the level + * IEEE802154_FILTERING_NONE on interfaces not expecting it because of + * the missing auto ACK handling feature. + */ + + /* TODO: Handle upcomming receive path where the PHY is at the + * IEEE802154_FILTERING_NONE level during a scan. + */ + /* Check if transceiver doesn't validate the checksum. * If not we validate the checksum here. */ - if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM) { + if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM || + local->phy->filtering == IEEE802154_FILTERING_NONE) { crc = crc_ccitt(0, skb->data, skb->len); if (crc) { rcu_read_unlock(); -- cgit v1.2.3 From ea562d8c486eebd2707bcd193974078a2a47affc Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 7 Oct 2022 10:53:07 +0200 Subject: ieee802154: hwsim: Implement address filtering We have access to the address filters being theoretically applied, we also have access to the actual filtering level applied, so let's add a proper frame validation sequence in hwsim. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20221007085310.503366-6-miquel.raynal@bootlin.com [stefan@datenfreihafen.org: fixup some checkpatch warnings] Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 110 ++++++++++++++++++++++++++++++- include/net/ieee802154_netdev.h | 8 +++ 2 files changed, 116 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 458be66b5195..75d802e0b685 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -139,6 +140,112 @@ static int hwsim_hw_addr_filt(struct ieee802154_hw *hw, return 0; } +static void hwsim_hw_receive(struct ieee802154_hw *hw, struct sk_buff *skb, + u8 lqi) +{ + struct ieee802154_hdr hdr; + struct hwsim_phy *phy = hw->priv; + struct hwsim_pib *pib; + + rcu_read_lock(); + pib = rcu_dereference(phy->pib); + + if (!pskb_may_pull(skb, 3)) { + dev_dbg(hw->parent, "invalid frame\n"); + goto drop; + } + + memcpy(&hdr, skb->data, 3); + + /* Level 4 filtering: Frame fields validity */ + if (hw->phy->filtering == IEEE802154_FILTERING_4_FRAME_FIELDS) { + /* a) Drop reserved frame types */ + switch (mac_cb(skb)->type) { + case IEEE802154_FC_TYPE_BEACON: + case IEEE802154_FC_TYPE_DATA: + case IEEE802154_FC_TYPE_ACK: + case IEEE802154_FC_TYPE_MAC_CMD: + break; + default: + dev_dbg(hw->parent, "unrecognized frame type 0x%x\n", + mac_cb(skb)->type); + goto drop; + } + + /* b) Drop reserved frame versions */ + switch (hdr.fc.version) { + case IEEE802154_2003_STD: + case IEEE802154_2006_STD: + case IEEE802154_STD: + break; + default: + dev_dbg(hw->parent, + "unrecognized frame version 0x%x\n", + hdr.fc.version); + goto drop; + } + + /* c) PAN ID constraints */ + if ((mac_cb(skb)->dest.mode == IEEE802154_ADDR_LONG || + mac_cb(skb)->dest.mode == IEEE802154_ADDR_SHORT) && + mac_cb(skb)->dest.pan_id != pib->filt.pan_id && + mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) { + dev_dbg(hw->parent, + "unrecognized PAN ID %04x\n", + le16_to_cpu(mac_cb(skb)->dest.pan_id)); + goto drop; + } + + /* d1) Short address constraints */ + if (mac_cb(skb)->dest.mode == IEEE802154_ADDR_SHORT && + mac_cb(skb)->dest.short_addr != pib->filt.short_addr && + mac_cb(skb)->dest.short_addr != cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { + dev_dbg(hw->parent, + "unrecognized short address %04x\n", + le16_to_cpu(mac_cb(skb)->dest.short_addr)); + goto drop; + } + + /* d2) Extended address constraints */ + if (mac_cb(skb)->dest.mode == IEEE802154_ADDR_LONG && + mac_cb(skb)->dest.extended_addr != pib->filt.ieee_addr) { + dev_dbg(hw->parent, + "unrecognized long address 0x%016llx\n", + mac_cb(skb)->dest.extended_addr); + goto drop; + } + + /* d4) Specific PAN coordinator case (no parent) */ + if ((mac_cb(skb)->type == IEEE802154_FC_TYPE_DATA || + mac_cb(skb)->type == IEEE802154_FC_TYPE_MAC_CMD) && + mac_cb(skb)->dest.mode == IEEE802154_ADDR_NONE) { + dev_dbg(hw->parent, + "relaying is not supported\n"); + goto drop; + } + + /* e) Beacon frames follow specific PAN ID rules */ + if (mac_cb(skb)->type == IEEE802154_FC_TYPE_BEACON && + pib->filt.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST) && + mac_cb(skb)->dest.pan_id != pib->filt.pan_id) { + dev_dbg(hw->parent, + "invalid beacon PAN ID %04x\n", + le16_to_cpu(mac_cb(skb)->dest.pan_id)); + goto drop; + } + } + + rcu_read_unlock(); + + ieee802154_rx_irqsafe(hw, skb, lqi); + + return; + +drop: + rcu_read_unlock(); + kfree_skb(skb); +} + static int hwsim_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) { struct hwsim_phy *current_phy = hw->priv; @@ -166,8 +273,7 @@ static int hwsim_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) einfo = rcu_dereference(e->info); if (newskb) - ieee802154_rx_irqsafe(e->endpoint->hw, newskb, - einfo->lqi); + hwsim_hw_receive(e->endpoint->hw, newskb, einfo->lqi); } } rcu_read_unlock(); diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index d0d188c3294b..1b82bbafe8c7 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -69,6 +69,14 @@ struct ieee802154_hdr_fc { #endif }; +enum ieee802154_frame_version { + IEEE802154_2003_STD, + IEEE802154_2006_STD, + IEEE802154_STD, + IEEE802154_RESERVED_STD, + IEEE802154_MULTIPURPOSE_STD = IEEE802154_2003_STD, +}; + struct ieee802154_hdr { struct ieee802154_hdr_fc fc; u8 seq; -- cgit v1.2.3 From a4b5b4c56dd8b1dd46b2f13cb09f5f8031978f86 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 7 Oct 2022 10:53:08 +0200 Subject: mac802154: Drop IEEE802154_HW_RX_DROP_BAD_CKSUM This IEEE802154_HW_RX_DROP_BAD_CKSUM flag was only used by hwsim to reflect the fact that it would not validate the checksum (FCS). So this was only useful while the only filtering level hwsim was capable of was "NONE". Now that the driver has been improved we no longer need this flag. Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20221007085310.503366-7-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- drivers/net/ieee802154/mac802154_hwsim.c | 3 ++- include/net/mac802154.h | 4 ---- net/mac802154/rx.c | 7 ++----- 3 files changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 75d802e0b685..1db7da3ccc1a 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -287,6 +287,7 @@ static int hwsim_hw_start(struct ieee802154_hw *hw) struct hwsim_phy *phy = hw->priv; phy->suspended = false; + return 0; } @@ -933,7 +934,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, phy->idx = idx; INIT_LIST_HEAD(&phy->edges); - hw->flags = IEEE802154_HW_PROMISCUOUS | IEEE802154_HW_RX_DROP_BAD_CKSUM; + hw->flags = IEEE802154_HW_PROMISCUOUS; hw->parent = dev; err = ieee802154_register_hw(hw); diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 357d25ef627a..4a3a9de9da73 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -111,9 +111,6 @@ struct ieee802154_hw { * promiscuous mode setting. * * @IEEE802154_HW_RX_OMIT_CKSUM: Indicates that receiver omits FCS. - * - * @IEEE802154_HW_RX_DROP_BAD_CKSUM: Indicates that receiver will not filter - * frames with bad checksum. */ enum ieee802154_hw_flags { IEEE802154_HW_TX_OMIT_CKSUM = BIT(0), @@ -123,7 +120,6 @@ enum ieee802154_hw_flags { IEEE802154_HW_AFILT = BIT(4), IEEE802154_HW_PROMISCUOUS = BIT(5), IEEE802154_HW_RX_OMIT_CKSUM = BIT(6), - IEEE802154_HW_RX_DROP_BAD_CKSUM = BIT(7), }; /* Indicates that receiver omits FCS and xmitter will add FCS on it's own. */ diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 8543c28948a0..80dd52bc6bf1 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -277,11 +277,8 @@ void ieee802154_rx(struct ieee802154_local *local, struct sk_buff *skb) * IEEE802154_FILTERING_NONE level during a scan. */ - /* Check if transceiver doesn't validate the checksum. - * If not we validate the checksum here. - */ - if (local->hw.flags & IEEE802154_HW_RX_DROP_BAD_CKSUM || - local->phy->filtering == IEEE802154_FILTERING_NONE) { + /* Level 1 filtering: Check the FCS by software when relevant */ + if (local->hw.phy->filtering == IEEE802154_FILTERING_NONE) { crc = crc_ccitt(0, skb->data, skb->len); if (crc) { rcu_read_unlock(); -- cgit v1.2.3 From e6c86c513f440bec5f1046539c7e3c6c653842da Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 14 Oct 2022 19:39:43 +0800 Subject: rcu-tasks: Provide rcu_trace_implies_rcu_gp() As an accident of implementation, an RCU Tasks Trace grace period also acts as an RCU grace period. However, this could change at any time. This commit therefore creates an rcu_trace_implies_rcu_gp() that currently returns true to codify this accident. Code relying on this accident must call this function to verify that this accident is still happening. Reported-by: Hou Tao Signed-off-by: Paul E. McKenney Cc: Alexei Starovoitov Cc: Martin KaFai Lau Link: https://lore.kernel.org/r/20221014113946.965131-2-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/rcupdate.h | 12 ++++++++++++ kernel/rcu/tasks.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 08605ce7379d..8822f06e4b40 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -240,6 +240,18 @@ static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ +/** + * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? + * + * As an accident of implementation, an RCU Tasks Trace grace period also + * acts as an RCU grace period. However, this could change at any time. + * Code relying on this accident must call this function to verify that + * this accident is still happening. + * + * You have been warned! + */ +static inline bool rcu_trace_implies_rcu_gp(void) { return true; } + /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index f5bf6fb430da..9435e5a7b53e 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1535,6 +1535,8 @@ static void rcu_tasks_trace_postscan(struct list_head *hop) { // Wait for late-stage exiting tasks to finish exiting. // These might have passed the call to exit_tasks_rcu_finish(). + + // If you remove the following line, update rcu_trace_implies_rcu_gp()!!! synchronize_rcu(); // Any tasks that exit after this point will set // TRC_NEED_QS_CHECKED in ->trc_reader_special.b.need_qs. -- cgit v1.2.3 From a2fd08448f2b7591fc7ec8dec2e5e025a43f0cee Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 17 Oct 2022 14:18:26 +0200 Subject: net: remove smc911x driver This driver was used on Arm and SH machines until 2009, when the last platforms moved to the smsc911x driver for the same hardware. Time to retire this version. Link: https://lore.kernel.org/netdev/1232010482-3744-1-git-send-email-steve.glendinning@smsc.com/ Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20221017121900.3520108-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/smsc/Kconfig | 14 - drivers/net/ethernet/smsc/Makefile | 1 - drivers/net/ethernet/smsc/smc911x.c | 2198 ----------------------------------- drivers/net/ethernet/smsc/smc911x.h | 901 -------------- include/linux/smc911x.h | 14 - 5 files changed, 3128 deletions(-) delete mode 100644 drivers/net/ethernet/smsc/smc911x.c delete mode 100644 drivers/net/ethernet/smsc/smc911x.h delete mode 100644 include/linux/smc911x.h (limited to 'include') diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig index 2524c907f386..5f22a8a4d27b 100644 --- a/drivers/net/ethernet/smsc/Kconfig +++ b/drivers/net/ethernet/smsc/Kconfig @@ -75,20 +75,6 @@ config EPIC100 More specific information and updates are available from . -config SMC911X - tristate "SMSC LAN911[5678] support" - select CRC32 - select MII - depends on (ARM || SUPERH || COMPILE_TEST) - help - This is a driver for SMSC's LAN911x series of Ethernet chipsets - including the new LAN9115, LAN9116, LAN9117, and LAN9118. - Say Y here if you want it compiled into the kernel. - - This driver is also available as a module. The module will be - called smc911x. If you want to compile it as a module, say M - here and read - config SMSC911X tristate "SMSC LAN911x/LAN921x families embedded ethernet support" depends on HAS_IOMEM diff --git a/drivers/net/ethernet/smsc/Makefile b/drivers/net/ethernet/smsc/Makefile index 4105912b1629..1501fa364c13 100644 --- a/drivers/net/ethernet/smsc/Makefile +++ b/drivers/net/ethernet/smsc/Makefile @@ -8,5 +8,4 @@ obj-$(CONFIG_SMC91X) += smc91x.o obj-$(CONFIG_PCMCIA_SMC91C92) += smc91c92_cs.o obj-$(CONFIG_EPIC100) += epic100.o obj-$(CONFIG_SMSC9420) += smsc9420.o -obj-$(CONFIG_SMC911X) += smc911x.o obj-$(CONFIG_SMSC911X) += smsc911x.o diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c deleted file mode 100644 index 52ecfb461c41..000000000000 --- a/drivers/net/ethernet/smsc/smc911x.c +++ /dev/null @@ -1,2198 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * smc911x.c - * This is a driver for SMSC's LAN911{5,6,7,8} single-chip Ethernet devices. - * - * Copyright (C) 2005 Sensoria Corp - * Derived from the unified SMC91x driver by Nicolas Pitre - * and the smsc911x.c reference driver by SMSC - * - * Arguments: - * watchdog = TX watchdog timeout - * tx_fifo_kb = Size of TX FIFO in KB - * - * History: - * 04/16/05 Dustin McIntire Initial version - */ -static const char version[] = - "smc911x.c: v1.0 04-16-2005 by Dustin McIntire \n"; - -/* Debugging options */ -#define ENABLE_SMC_DEBUG_RX 0 -#define ENABLE_SMC_DEBUG_TX 0 -#define ENABLE_SMC_DEBUG_DMA 0 -#define ENABLE_SMC_DEBUG_PKTS 0 -#define ENABLE_SMC_DEBUG_MISC 0 -#define ENABLE_SMC_DEBUG_FUNC 0 - -#define SMC_DEBUG_RX ((ENABLE_SMC_DEBUG_RX ? 1 : 0) << 0) -#define SMC_DEBUG_TX ((ENABLE_SMC_DEBUG_TX ? 1 : 0) << 1) -#define SMC_DEBUG_DMA ((ENABLE_SMC_DEBUG_DMA ? 1 : 0) << 2) -#define SMC_DEBUG_PKTS ((ENABLE_SMC_DEBUG_PKTS ? 1 : 0) << 3) -#define SMC_DEBUG_MISC ((ENABLE_SMC_DEBUG_MISC ? 1 : 0) << 4) -#define SMC_DEBUG_FUNC ((ENABLE_SMC_DEBUG_FUNC ? 1 : 0) << 5) - -#ifndef SMC_DEBUG -#define SMC_DEBUG ( SMC_DEBUG_RX | \ - SMC_DEBUG_TX | \ - SMC_DEBUG_DMA | \ - SMC_DEBUG_PKTS | \ - SMC_DEBUG_MISC | \ - SMC_DEBUG_FUNC \ - ) -#endif - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include - -#include - -#include "smc911x.h" - -/* - * Transmit timeout, default 5 seconds. - */ -static int watchdog = 5000; -module_param(watchdog, int, 0400); -MODULE_PARM_DESC(watchdog, "transmit timeout in milliseconds"); - -static int tx_fifo_kb=8; -module_param(tx_fifo_kb, int, 0400); -MODULE_PARM_DESC(tx_fifo_kb,"transmit FIFO size in KB (1 0 -#define DBG(n, dev, args...) \ - do { \ - if (SMC_DEBUG & (n)) \ - netdev_dbg(dev, args); \ - } while (0) - -#define PRINTK(dev, args...) netdev_info(dev, args) -#else -#define DBG(n, dev, args...) \ - while (0) { \ - netdev_dbg(dev, args); \ - } -#define PRINTK(dev, args...) netdev_dbg(dev, args) -#endif - -#if SMC_DEBUG_PKTS > 0 -static void PRINT_PKT(u_char *buf, int length) -{ - int i; - int remainder; - int lines; - - lines = length / 16; - remainder = length % 16; - - for (i = 0; i < lines ; i ++) { - int cur; - printk(KERN_DEBUG); - for (cur = 0; cur < 8; cur++) { - u_char a, b; - a = *buf++; - b = *buf++; - pr_cont("%02x%02x ", a, b); - } - pr_cont("\n"); - } - printk(KERN_DEBUG); - for (i = 0; i < remainder/2 ; i++) { - u_char a, b; - a = *buf++; - b = *buf++; - pr_cont("%02x%02x ", a, b); - } - pr_cont("\n"); -} -#else -static inline void PRINT_PKT(u_char *buf, int length) { } -#endif - - -/* this enables an interrupt in the interrupt mask register */ -#define SMC_ENABLE_INT(lp, x) do { \ - unsigned int __mask; \ - __mask = SMC_GET_INT_EN((lp)); \ - __mask |= (x); \ - SMC_SET_INT_EN((lp), __mask); \ -} while (0) - -/* this disables an interrupt from the interrupt mask register */ -#define SMC_DISABLE_INT(lp, x) do { \ - unsigned int __mask; \ - __mask = SMC_GET_INT_EN((lp)); \ - __mask &= ~(x); \ - SMC_SET_INT_EN((lp), __mask); \ -} while (0) - -/* - * this does a soft reset on the device - */ -static void smc911x_reset(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int reg, timeout=0, resets=1, irq_cfg; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* Take out of PM setting first */ - if ((SMC_GET_PMT_CTRL(lp) & PMT_CTRL_READY_) == 0) { - /* Write to the bytetest will take out of powerdown */ - SMC_SET_BYTE_TEST(lp, 0); - timeout=10; - do { - udelay(10); - reg = SMC_GET_PMT_CTRL(lp) & PMT_CTRL_READY_; - } while (--timeout && !reg); - if (timeout == 0) { - PRINTK(dev, "smc911x_reset timeout waiting for PM restore\n"); - return; - } - } - - /* Disable all interrupts */ - spin_lock_irqsave(&lp->lock, flags); - SMC_SET_INT_EN(lp, 0); - spin_unlock_irqrestore(&lp->lock, flags); - - while (resets--) { - SMC_SET_HW_CFG(lp, HW_CFG_SRST_); - timeout=10; - do { - udelay(10); - reg = SMC_GET_HW_CFG(lp); - /* If chip indicates reset timeout then try again */ - if (reg & HW_CFG_SRST_TO_) { - PRINTK(dev, "chip reset timeout, retrying...\n"); - resets++; - break; - } - } while (--timeout && (reg & HW_CFG_SRST_)); - } - if (timeout == 0) { - PRINTK(dev, "smc911x_reset timeout waiting for reset\n"); - return; - } - - /* make sure EEPROM has finished loading before setting GPIO_CFG */ - timeout=1000; - while (--timeout && (SMC_GET_E2P_CMD(lp) & E2P_CMD_EPC_BUSY_)) - udelay(10); - - if (timeout == 0){ - PRINTK(dev, "smc911x_reset timeout waiting for EEPROM busy\n"); - return; - } - - /* Initialize interrupts */ - SMC_SET_INT_EN(lp, 0); - SMC_ACK_INT(lp, -1); - - /* Reset the FIFO level and flow control settings */ - SMC_SET_HW_CFG(lp, (lp->tx_fifo_kb & 0xF) << 16); -//TODO: Figure out what appropriate pause time is - SMC_SET_FLOW(lp, FLOW_FCPT_ | FLOW_FCEN_); - SMC_SET_AFC_CFG(lp, lp->afc_cfg); - - - /* Set to LED outputs */ - SMC_SET_GPIO_CFG(lp, 0x70070000); - - /* - * Deassert IRQ for 1*10us for edge type interrupts - * and drive IRQ pin push-pull - */ - irq_cfg = (1 << 24) | INT_CFG_IRQ_EN_ | INT_CFG_IRQ_TYPE_; -#ifdef SMC_DYNAMIC_BUS_CONFIG - if (lp->cfg.irq_polarity) - irq_cfg |= INT_CFG_IRQ_POL_; -#endif - SMC_SET_IRQ_CFG(lp, irq_cfg); - - /* clear anything saved */ - if (lp->pending_tx_skb != NULL) { - dev_kfree_skb (lp->pending_tx_skb); - lp->pending_tx_skb = NULL; - dev->stats.tx_errors++; - dev->stats.tx_aborted_errors++; - } -} - -/* - * Enable Interrupts, Receive, and Transmit - */ -static void smc911x_enable(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned mask, cfg, cr; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - - SMC_SET_MAC_ADDR(lp, dev->dev_addr); - - /* Enable TX */ - cfg = SMC_GET_HW_CFG(lp); - cfg &= HW_CFG_TX_FIF_SZ_ | 0xFFF; - cfg |= HW_CFG_SF_; - SMC_SET_HW_CFG(lp, cfg); - SMC_SET_FIFO_TDA(lp, 0xFF); - /* Update TX stats on every 64 packets received or every 1 sec */ - SMC_SET_FIFO_TSL(lp, 64); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - - SMC_GET_MAC_CR(lp, cr); - cr |= MAC_CR_TXEN_ | MAC_CR_HBDIS_; - SMC_SET_MAC_CR(lp, cr); - SMC_SET_TX_CFG(lp, TX_CFG_TX_ON_); - - /* Add 2 byte padding to start of packets */ - SMC_SET_RX_CFG(lp, (2<<8) & RX_CFG_RXDOFF_); - - /* Turn on receiver and enable RX */ - if (cr & MAC_CR_RXEN_) - DBG(SMC_DEBUG_RX, dev, "Receiver already enabled\n"); - - SMC_SET_MAC_CR(lp, cr | MAC_CR_RXEN_); - - /* Interrupt on every received packet */ - SMC_SET_FIFO_RSA(lp, 0x01); - SMC_SET_FIFO_RSL(lp, 0x00); - - /* now, enable interrupts */ - mask = INT_EN_TDFA_EN_ | INT_EN_TSFL_EN_ | INT_EN_RSFL_EN_ | - INT_EN_GPT_INT_EN_ | INT_EN_RXDFH_INT_EN_ | INT_EN_RXE_EN_ | - INT_EN_PHY_INT_EN_; - if (IS_REV_A(lp->revision)) - mask|=INT_EN_RDFL_EN_; - else { - mask|=INT_EN_RDFO_EN_; - } - SMC_ENABLE_INT(lp, mask); - - spin_unlock_irqrestore(&lp->lock, flags); -} - -/* - * this puts the device in an inactive state - */ -static void smc911x_shutdown(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned cr; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "%s: --> %s\n", CARDNAME, __func__); - - /* Disable IRQ's */ - SMC_SET_INT_EN(lp, 0); - - /* Turn of Rx and TX */ - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CR(lp, cr); - cr &= ~(MAC_CR_TXEN_ | MAC_CR_RXEN_ | MAC_CR_HBDIS_); - SMC_SET_MAC_CR(lp, cr); - SMC_SET_TX_CFG(lp, TX_CFG_STOP_TX_); - spin_unlock_irqrestore(&lp->lock, flags); -} - -static inline void smc911x_drop_pkt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int fifo_count, timeout, reg; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_RX, dev, "%s: --> %s\n", - CARDNAME, __func__); - fifo_count = SMC_GET_RX_FIFO_INF(lp) & 0xFFFF; - if (fifo_count <= 4) { - /* Manually dump the packet data */ - while (fifo_count--) - SMC_GET_RX_FIFO(lp); - } else { - /* Fast forward through the bad packet */ - SMC_SET_RX_DP_CTRL(lp, RX_DP_CTRL_FFWD_BUSY_); - timeout=50; - do { - udelay(10); - reg = SMC_GET_RX_DP_CTRL(lp) & RX_DP_CTRL_FFWD_BUSY_; - } while (--timeout && reg); - if (timeout == 0) { - PRINTK(dev, "timeout waiting for RX fast forward\n"); - } - } -} - -/* - * This is the procedure to handle the receipt of a packet. - * It should be called after checking for packet presence in - * the RX status FIFO. It must be called with the spin lock - * already held. - */ -static inline void smc911x_rcv(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int pkt_len, status; - struct sk_buff *skb; - unsigned char *data; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_RX, dev, "--> %s\n", - __func__); - status = SMC_GET_RX_STS_FIFO(lp); - DBG(SMC_DEBUG_RX, dev, "Rx pkt len %d status 0x%08x\n", - (status & 0x3fff0000) >> 16, status & 0xc000ffff); - pkt_len = (status & RX_STS_PKT_LEN_) >> 16; - if (status & RX_STS_ES_) { - /* Deal with a bad packet */ - dev->stats.rx_errors++; - if (status & RX_STS_CRC_ERR_) - dev->stats.rx_crc_errors++; - else { - if (status & RX_STS_LEN_ERR_) - dev->stats.rx_length_errors++; - if (status & RX_STS_MCAST_) - dev->stats.multicast++; - } - /* Remove the bad packet data from the RX FIFO */ - smc911x_drop_pkt(dev); - } else { - /* Receive a valid packet */ - /* Alloc a buffer with extra room for DMA alignment */ - skb = netdev_alloc_skb(dev, pkt_len+32); - if (unlikely(skb == NULL)) { - PRINTK(dev, "Low memory, rcvd packet dropped.\n"); - dev->stats.rx_dropped++; - smc911x_drop_pkt(dev); - return; - } - /* Align IP header to 32 bits - * Note that the device is configured to add a 2 - * byte padding to the packet start, so we really - * want to write to the orignal data pointer */ - data = skb->data; - skb_reserve(skb, 2); - skb_put(skb,pkt_len-4); -#ifdef SMC_USE_DMA - { - unsigned int fifo; - /* Lower the FIFO threshold if possible */ - fifo = SMC_GET_FIFO_INT(lp); - if (fifo & 0xFF) fifo--; - DBG(SMC_DEBUG_RX, dev, "Setting RX stat FIFO threshold to %d\n", - fifo & 0xff); - SMC_SET_FIFO_INT(lp, fifo); - /* Setup RX DMA */ - SMC_SET_RX_CFG(lp, RX_CFG_RX_END_ALGN16_ | ((2<<8) & RX_CFG_RXDOFF_)); - lp->rxdma_active = 1; - lp->current_rx_skb = skb; - SMC_PULL_DATA(lp, data, (pkt_len+2+15) & ~15); - /* Packet processing deferred to DMA RX interrupt */ - } -#else - SMC_SET_RX_CFG(lp, RX_CFG_RX_END_ALGN4_ | ((2<<8) & RX_CFG_RXDOFF_)); - SMC_PULL_DATA(lp, data, pkt_len+2+3); - - DBG(SMC_DEBUG_PKTS, dev, "Received packet\n"); - PRINT_PKT(data, min(pkt_len - 4, 64U)); - skb->protocol = eth_type_trans(skb, dev); - netif_rx(skb); - dev->stats.rx_packets++; - dev->stats.rx_bytes += pkt_len-4; -#endif - } -} - -/* - * This is called to actually send a packet to the chip. - */ -static void smc911x_hardware_send_pkt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - struct sk_buff *skb; - unsigned int cmdA, cmdB, len; - unsigned char *buf; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", __func__); - BUG_ON(lp->pending_tx_skb == NULL); - - skb = lp->pending_tx_skb; - lp->pending_tx_skb = NULL; - - /* cmdA {25:24] data alignment [20:16] start offset [10:0] buffer length */ - /* cmdB {31:16] pkt tag [10:0] length */ -#ifdef SMC_USE_DMA - /* 16 byte buffer alignment mode */ - buf = (char*)((u32)(skb->data) & ~0xF); - len = (skb->len + 0xF + ((u32)skb->data & 0xF)) & ~0xF; - cmdA = (1<<24) | (((u32)skb->data & 0xF)<<16) | - TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ | - skb->len; -#else - buf = (char *)((uintptr_t)skb->data & ~0x3); - len = (skb->len + 3 + ((uintptr_t)skb->data & 3)) & ~0x3; - cmdA = (((uintptr_t)skb->data & 0x3) << 16) | - TX_CMD_A_INT_FIRST_SEG_ | TX_CMD_A_INT_LAST_SEG_ | - skb->len; -#endif - /* tag is packet length so we can use this in stats update later */ - cmdB = (skb->len << 16) | (skb->len & 0x7FF); - - DBG(SMC_DEBUG_TX, dev, "TX PKT LENGTH 0x%04x (%d) BUF 0x%p CMDA 0x%08x CMDB 0x%08x\n", - len, len, buf, cmdA, cmdB); - SMC_SET_TX_FIFO(lp, cmdA); - SMC_SET_TX_FIFO(lp, cmdB); - - DBG(SMC_DEBUG_PKTS, dev, "Transmitted packet\n"); - PRINT_PKT(buf, min(len, 64U)); - - /* Send pkt via PIO or DMA */ -#ifdef SMC_USE_DMA - lp->current_tx_skb = skb; - SMC_PUSH_DATA(lp, buf, len); - /* DMA complete IRQ will free buffer and set jiffies */ -#else - SMC_PUSH_DATA(lp, buf, len); - netif_trans_update(dev); - dev_kfree_skb_irq(skb); -#endif - if (!lp->tx_throttle) { - netif_wake_queue(dev); - } - SMC_ENABLE_INT(lp, INT_EN_TDFA_EN_ | INT_EN_TSFL_EN_); -} - -/* - * Since I am not sure if I will have enough room in the chip's ram - * to store the packet, I call this routine which either sends it - * now, or set the card to generates an interrupt when ready - * for the packet. - */ -static netdev_tx_t -smc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int free; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", - __func__); - - spin_lock_irqsave(&lp->lock, flags); - - BUG_ON(lp->pending_tx_skb != NULL); - - free = SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TDFREE_; - DBG(SMC_DEBUG_TX, dev, "TX free space %d\n", free); - - /* Turn off the flow when running out of space in FIFO */ - if (free <= SMC911X_TX_FIFO_LOW_THRESHOLD) { - DBG(SMC_DEBUG_TX, dev, "Disabling data flow due to low FIFO space (%d)\n", - free); - /* Reenable when at least 1 packet of size MTU present */ - SMC_SET_FIFO_TDA(lp, (SMC911X_TX_FIFO_LOW_THRESHOLD)/64); - lp->tx_throttle = 1; - netif_stop_queue(dev); - } - - /* Drop packets when we run out of space in TX FIFO - * Account for overhead required for: - * - * Tx command words 8 bytes - * Start offset 15 bytes - * End padding 15 bytes - */ - if (unlikely(free < (skb->len + 8 + 15 + 15))) { - netdev_warn(dev, "No Tx free space %d < %d\n", - free, skb->len); - lp->pending_tx_skb = NULL; - dev->stats.tx_errors++; - dev->stats.tx_dropped++; - spin_unlock_irqrestore(&lp->lock, flags); - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - -#ifdef SMC_USE_DMA - { - /* If the DMA is already running then defer this packet Tx until - * the DMA IRQ starts it - */ - if (lp->txdma_active) { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "Tx DMA running, deferring packet\n"); - lp->pending_tx_skb = skb; - netif_stop_queue(dev); - spin_unlock_irqrestore(&lp->lock, flags); - return NETDEV_TX_OK; - } else { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "Activating Tx DMA\n"); - lp->txdma_active = 1; - } - } -#endif - lp->pending_tx_skb = skb; - smc911x_hardware_send_pkt(dev); - spin_unlock_irqrestore(&lp->lock, flags); - - return NETDEV_TX_OK; -} - -/* - * This handles a TX status interrupt, which is only called when: - * - a TX error occurred, or - * - TX of a packet completed. - */ -static void smc911x_tx(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int tx_status; - - DBG(SMC_DEBUG_FUNC | SMC_DEBUG_TX, dev, "--> %s\n", - __func__); - - /* Collect the TX status */ - while (((SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TSUSED_) >> 16) != 0) { - DBG(SMC_DEBUG_TX, dev, "Tx stat FIFO used 0x%04x\n", - (SMC_GET_TX_FIFO_INF(lp) & TX_FIFO_INF_TSUSED_) >> 16); - tx_status = SMC_GET_TX_STS_FIFO(lp); - dev->stats.tx_packets++; - dev->stats.tx_bytes+=tx_status>>16; - DBG(SMC_DEBUG_TX, dev, "Tx FIFO tag 0x%04x status 0x%04x\n", - (tx_status & 0xffff0000) >> 16, - tx_status & 0x0000ffff); - /* count Tx errors, but ignore lost carrier errors when in - * full-duplex mode */ - if ((tx_status & TX_STS_ES_) && !(lp->ctl_rfduplx && - !(tx_status & 0x00000306))) { - dev->stats.tx_errors++; - } - if (tx_status & TX_STS_MANY_COLL_) { - dev->stats.collisions+=16; - dev->stats.tx_aborted_errors++; - } else { - dev->stats.collisions+=(tx_status & TX_STS_COLL_CNT_) >> 3; - } - /* carrier error only has meaning for half-duplex communication */ - if ((tx_status & (TX_STS_LOC_ | TX_STS_NO_CARR_)) && - !lp->ctl_rfduplx) { - dev->stats.tx_carrier_errors++; - } - if (tx_status & TX_STS_LATE_COLL_) { - dev->stats.collisions++; - dev->stats.tx_aborted_errors++; - } - } -} - - -/*---PHY CONTROL AND CONFIGURATION-----------------------------------------*/ -/* - * Reads a register from the MII Management serial interface - */ - -static int smc911x_phy_read(struct net_device *dev, int phyaddr, int phyreg) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int phydata; - - SMC_GET_MII(lp, phyreg, phyaddr, phydata); - - DBG(SMC_DEBUG_MISC, dev, "%s: phyaddr=0x%x, phyreg=0x%02x, phydata=0x%04x\n", - __func__, phyaddr, phyreg, phydata); - return phydata; -} - - -/* - * Writes a register to the MII Management serial interface - */ -static void smc911x_phy_write(struct net_device *dev, int phyaddr, int phyreg, - int phydata) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_MISC, dev, "%s: phyaddr=0x%x, phyreg=0x%x, phydata=0x%x\n", - __func__, phyaddr, phyreg, phydata); - - SMC_SET_MII(lp, phyreg, phyaddr, phydata); -} - -/* - * Finds and reports the PHY address (115 and 117 have external - * PHY interface 118 has internal only - */ -static void smc911x_phy_detect(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr; - unsigned int cfg, id1, id2; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - lp->phy_type = 0; - - /* - * Scan all 32 PHY addresses if necessary, starting at - * PHY#1 to PHY#31, and then PHY#0 last. - */ - switch(lp->version) { - case CHIP_9115: - case CHIP_9117: - case CHIP_9215: - case CHIP_9217: - cfg = SMC_GET_HW_CFG(lp); - if (cfg & HW_CFG_EXT_PHY_DET_) { - cfg &= ~HW_CFG_PHY_CLK_SEL_; - cfg |= HW_CFG_PHY_CLK_SEL_CLK_DIS_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg |= HW_CFG_EXT_PHY_EN_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg &= ~HW_CFG_PHY_CLK_SEL_; - cfg |= HW_CFG_PHY_CLK_SEL_EXT_PHY_; - SMC_SET_HW_CFG(lp, cfg); - udelay(10); /* Wait for clocks to stop */ - - cfg |= HW_CFG_SMI_SEL_; - SMC_SET_HW_CFG(lp, cfg); - - for (phyaddr = 1; phyaddr < 32; ++phyaddr) { - - /* Read the PHY identifiers */ - SMC_GET_PHY_ID1(lp, phyaddr & 31, id1); - SMC_GET_PHY_ID2(lp, phyaddr & 31, id2); - - /* Make sure it is a valid identifier */ - if (id1 != 0x0000 && id1 != 0xffff && - id1 != 0x8000 && id2 != 0x0000 && - id2 != 0xffff && id2 != 0x8000) { - /* Save the PHY's address */ - lp->mii.phy_id = phyaddr & 31; - lp->phy_type = id1 << 16 | id2; - break; - } - } - if (phyaddr < 32) - /* Found an external PHY */ - break; - } - fallthrough; - default: - /* Internal media only */ - SMC_GET_PHY_ID1(lp, 1, id1); - SMC_GET_PHY_ID2(lp, 1, id2); - /* Save the PHY's address */ - lp->mii.phy_id = 1; - lp->phy_type = id1 << 16 | id2; - } - - DBG(SMC_DEBUG_MISC, dev, "phy_id1=0x%x, phy_id2=0x%x phyaddr=0x%x\n", - id1, id2, lp->mii.phy_id); -} - -/* - * Sets the PHY to a configuration as determined by the user. - * Called with spin_lock held. - */ -static int smc911x_phy_fixed(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - int bmcr; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* Enter Link Disable state */ - SMC_GET_PHY_BMCR(lp, phyaddr, bmcr); - bmcr |= BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - /* - * Set our fixed capabilities - * Disable auto-negotiation - */ - bmcr &= ~BMCR_ANENABLE; - if (lp->ctl_rfduplx) - bmcr |= BMCR_FULLDPLX; - - if (lp->ctl_rspeed == 100) - bmcr |= BMCR_SPEED100; - - /* Write our capabilities to the phy control register */ - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - /* Re-Configure the Receive/Phy Control register */ - bmcr &= ~BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - - return 1; -} - -/** - * smc911x_phy_reset - reset the phy - * @dev: net device - * @phy: phy address - * - * Issue a software reset for the specified PHY and - * wait up to 100ms for the reset to complete. We should - * not access the PHY for 50ms after issuing the reset. - * - * The time to wait appears to be dependent on the PHY. - * - */ -static int smc911x_phy_reset(struct net_device *dev, int phy) -{ - struct smc911x_local *lp = netdev_priv(dev); - int timeout; - unsigned long flags; - unsigned int reg; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s()\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - reg = SMC_GET_PMT_CTRL(lp); - reg &= ~0xfffff030; - reg |= PMT_CTRL_PHY_RST_; - SMC_SET_PMT_CTRL(lp, reg); - spin_unlock_irqrestore(&lp->lock, flags); - for (timeout = 2; timeout; timeout--) { - msleep(50); - spin_lock_irqsave(&lp->lock, flags); - reg = SMC_GET_PMT_CTRL(lp); - spin_unlock_irqrestore(&lp->lock, flags); - if (!(reg & PMT_CTRL_PHY_RST_)) { - /* extra delay required because the phy may - * not be completed with its reset - * when PHY_BCR_RESET_ is cleared. 256us - * should suffice, but use 500us to be safe - */ - udelay(500); - break; - } - } - - return reg & PMT_CTRL_PHY_RST_; -} - -/** - * smc911x_phy_powerdown - powerdown phy - * @dev: net device - * @phy: phy address - * - * Power down the specified PHY - */ -static void smc911x_phy_powerdown(struct net_device *dev, int phy) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int bmcr; - - /* Enter Link Disable state */ - SMC_GET_PHY_BMCR(lp, phy, bmcr); - bmcr |= BMCR_PDOWN; - SMC_SET_PHY_BMCR(lp, phy, bmcr); -} - -/** - * smc911x_phy_check_media - check the media status and adjust BMCR - * @dev: net device - * @init: set true for initialisation - * - * Select duplex mode depending on negotiation state. This - * also updates our carrier state. - */ -static void smc911x_phy_check_media(struct net_device *dev, int init) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - unsigned int bmcr, cr; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (mii_check_media(&lp->mii, netif_msg_link(lp), init)) { - /* duplex state has changed */ - SMC_GET_PHY_BMCR(lp, phyaddr, bmcr); - SMC_GET_MAC_CR(lp, cr); - if (lp->mii.full_duplex) { - DBG(SMC_DEBUG_MISC, dev, "Configuring for full-duplex mode\n"); - bmcr |= BMCR_FULLDPLX; - cr |= MAC_CR_RCVOWN_; - } else { - DBG(SMC_DEBUG_MISC, dev, "Configuring for half-duplex mode\n"); - bmcr &= ~BMCR_FULLDPLX; - cr &= ~MAC_CR_RCVOWN_; - } - SMC_SET_PHY_BMCR(lp, phyaddr, bmcr); - SMC_SET_MAC_CR(lp, cr); - } -} - -/* - * Configures the specified PHY through the MII management interface - * using Autonegotiation. - * Calls smc911x_phy_fixed() if the user has requested a certain config. - * If RPC ANEG bit is set, the media selection is dependent purely on - * the selection by the MII (either in the MII BMCR reg or the result - * of autonegotiation.) If the RPC ANEG bit is cleared, the selection - * is controlled by the RPC SPEED and RPC DPLX bits. - */ -static void smc911x_phy_configure(struct work_struct *work) -{ - struct smc911x_local *lp = container_of(work, struct smc911x_local, - phy_configure); - struct net_device *dev = lp->netdev; - int phyaddr = lp->mii.phy_id; - int my_phy_caps; /* My PHY capabilities */ - int my_ad_caps; /* My Advertised capabilities */ - int status __always_unused; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s()\n", __func__); - - /* - * We should not be called if phy_type is zero. - */ - if (lp->phy_type == 0) - return; - - if (smc911x_phy_reset(dev, phyaddr)) { - netdev_info(dev, "PHY reset timed out\n"); - return; - } - spin_lock_irqsave(&lp->lock, flags); - - /* - * Enable PHY Interrupts (for register 18) - * Interrupts listed here are enabled - */ - SMC_SET_PHY_INT_MASK(lp, phyaddr, PHY_INT_MASK_ENERGY_ON_ | - PHY_INT_MASK_ANEG_COMP_ | PHY_INT_MASK_REMOTE_FAULT_ | - PHY_INT_MASK_LINK_DOWN_); - - /* If the user requested no auto neg, then go set his request */ - if (lp->mii.force_media) { - smc911x_phy_fixed(dev); - goto smc911x_phy_configure_exit; - } - - /* Copy our capabilities from MII_BMSR to MII_ADVERTISE */ - SMC_GET_PHY_BMSR(lp, phyaddr, my_phy_caps); - if (!(my_phy_caps & BMSR_ANEGCAPABLE)) { - netdev_info(dev, "Auto negotiation NOT supported\n"); - smc911x_phy_fixed(dev); - goto smc911x_phy_configure_exit; - } - - /* CSMA capable w/ both pauses */ - my_ad_caps = ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM; - - if (my_phy_caps & BMSR_100BASE4) - my_ad_caps |= ADVERTISE_100BASE4; - if (my_phy_caps & BMSR_100FULL) - my_ad_caps |= ADVERTISE_100FULL; - if (my_phy_caps & BMSR_100HALF) - my_ad_caps |= ADVERTISE_100HALF; - if (my_phy_caps & BMSR_10FULL) - my_ad_caps |= ADVERTISE_10FULL; - if (my_phy_caps & BMSR_10HALF) - my_ad_caps |= ADVERTISE_10HALF; - - /* Disable capabilities not selected by our user */ - if (lp->ctl_rspeed != 100) - my_ad_caps &= ~(ADVERTISE_100BASE4|ADVERTISE_100FULL|ADVERTISE_100HALF); - - if (!lp->ctl_rfduplx) - my_ad_caps &= ~(ADVERTISE_100FULL|ADVERTISE_10FULL); - - /* Update our Auto-Neg Advertisement Register */ - SMC_SET_PHY_MII_ADV(lp, phyaddr, my_ad_caps); - lp->mii.advertising = my_ad_caps; - - /* - * Read the register back. Without this, it appears that when - * auto-negotiation is restarted, sometimes it isn't ready and - * the link does not come up. - */ - udelay(10); - SMC_GET_PHY_MII_ADV(lp, phyaddr, status); - - DBG(SMC_DEBUG_MISC, dev, "phy caps=0x%04x\n", my_phy_caps); - DBG(SMC_DEBUG_MISC, dev, "phy advertised caps=0x%04x\n", my_ad_caps); - - /* Restart auto-negotiation process in order to advertise my caps */ - SMC_SET_PHY_BMCR(lp, phyaddr, BMCR_ANENABLE | BMCR_ANRESTART); - - smc911x_phy_check_media(dev, 1); - -smc911x_phy_configure_exit: - spin_unlock_irqrestore(&lp->lock, flags); -} - -/* - * smc911x_phy_interrupt - * - * Purpose: Handle interrupts relating to PHY register 18. This is - * called from the "hard" interrupt handler under our private spinlock. - */ -static void smc911x_phy_interrupt(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int phyaddr = lp->mii.phy_id; - int status __always_unused; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (lp->phy_type == 0) - return; - - smc911x_phy_check_media(dev, 0); - /* read to clear status bits */ - SMC_GET_PHY_INT_SRC(lp, phyaddr,status); - DBG(SMC_DEBUG_MISC, dev, "PHY interrupt status 0x%04x\n", - status & 0xffff); - DBG(SMC_DEBUG_MISC, dev, "AFC_CFG 0x%08x\n", - SMC_GET_AFC_CFG(lp)); -} - -/*--- END PHY CONTROL AND CONFIGURATION-------------------------------------*/ - -/* - * This is the main routine of the driver, to handle the device when - * it needs some attention. - */ -static irqreturn_t smc911x_interrupt(int irq, void *dev_id) -{ - struct net_device *dev = dev_id; - struct smc911x_local *lp = netdev_priv(dev); - unsigned int status, mask, timeout; - unsigned int rx_overrun=0, cr, pkts; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - - /* Spurious interrupt check */ - if ((SMC_GET_IRQ_CFG(lp) & (INT_CFG_IRQ_INT_ | INT_CFG_IRQ_EN_)) != - (INT_CFG_IRQ_INT_ | INT_CFG_IRQ_EN_)) { - spin_unlock_irqrestore(&lp->lock, flags); - return IRQ_NONE; - } - - mask = SMC_GET_INT_EN(lp); - SMC_SET_INT_EN(lp, 0); - - /* set a timeout value, so I don't stay here forever */ - timeout = 8; - - - do { - status = SMC_GET_INT(lp); - - DBG(SMC_DEBUG_MISC, dev, "INT 0x%08x MASK 0x%08x OUTSIDE MASK 0x%08x\n", - status, mask, status & ~mask); - - status &= mask; - if (!status) - break; - - /* Handle SW interrupt condition */ - if (status & INT_STS_SW_INT_) { - SMC_ACK_INT(lp, INT_STS_SW_INT_); - mask &= ~INT_EN_SW_INT_EN_; - } - /* Handle various error conditions */ - if (status & INT_STS_RXE_) { - SMC_ACK_INT(lp, INT_STS_RXE_); - dev->stats.rx_errors++; - } - if (status & INT_STS_RXDFH_INT_) { - SMC_ACK_INT(lp, INT_STS_RXDFH_INT_); - dev->stats.rx_dropped+=SMC_GET_RX_DROP(lp); - } - /* Undocumented interrupt-what is the right thing to do here? */ - if (status & INT_STS_RXDF_INT_) { - SMC_ACK_INT(lp, INT_STS_RXDF_INT_); - } - - /* Rx Data FIFO exceeds set level */ - if (status & INT_STS_RDFL_) { - if (IS_REV_A(lp->revision)) { - rx_overrun=1; - SMC_GET_MAC_CR(lp, cr); - cr &= ~MAC_CR_RXEN_; - SMC_SET_MAC_CR(lp, cr); - DBG(SMC_DEBUG_RX, dev, "RX overrun\n"); - dev->stats.rx_errors++; - dev->stats.rx_fifo_errors++; - } - SMC_ACK_INT(lp, INT_STS_RDFL_); - } - if (status & INT_STS_RDFO_) { - if (!IS_REV_A(lp->revision)) { - SMC_GET_MAC_CR(lp, cr); - cr &= ~MAC_CR_RXEN_; - SMC_SET_MAC_CR(lp, cr); - rx_overrun=1; - DBG(SMC_DEBUG_RX, dev, "RX overrun\n"); - dev->stats.rx_errors++; - dev->stats.rx_fifo_errors++; - } - SMC_ACK_INT(lp, INT_STS_RDFO_); - } - /* Handle receive condition */ - if ((status & INT_STS_RSFL_) || rx_overrun) { - unsigned int fifo; - DBG(SMC_DEBUG_RX, dev, "RX irq\n"); - fifo = SMC_GET_RX_FIFO_INF(lp); - pkts = (fifo & RX_FIFO_INF_RXSUSED_) >> 16; - DBG(SMC_DEBUG_RX, dev, "Rx FIFO pkts %d, bytes %d\n", - pkts, fifo & 0xFFFF); - if (pkts != 0) { -#ifdef SMC_USE_DMA - unsigned int fifo; - if (lp->rxdma_active){ - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, - "RX DMA active\n"); - /* The DMA is already running so up the IRQ threshold */ - fifo = SMC_GET_FIFO_INT(lp) & ~0xFF; - fifo |= pkts & 0xFF; - DBG(SMC_DEBUG_RX, dev, - "Setting RX stat FIFO threshold to %d\n", - fifo & 0xff); - SMC_SET_FIFO_INT(lp, fifo); - } else -#endif - smc911x_rcv(dev); - } - SMC_ACK_INT(lp, INT_STS_RSFL_); - } - /* Handle transmit FIFO available */ - if (status & INT_STS_TDFA_) { - DBG(SMC_DEBUG_TX, dev, "TX data FIFO space available irq\n"); - SMC_SET_FIFO_TDA(lp, 0xFF); - lp->tx_throttle = 0; -#ifdef SMC_USE_DMA - if (!lp->txdma_active) -#endif - netif_wake_queue(dev); - SMC_ACK_INT(lp, INT_STS_TDFA_); - } - /* Handle transmit done condition */ -#if 1 - if (status & (INT_STS_TSFL_ | INT_STS_GPT_INT_)) { - DBG(SMC_DEBUG_TX | SMC_DEBUG_MISC, dev, - "Tx stat FIFO limit (%d) /GPT irq\n", - (SMC_GET_FIFO_INT(lp) & 0x00ff0000) >> 16); - smc911x_tx(dev); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - SMC_ACK_INT(lp, INT_STS_TSFL_); - SMC_ACK_INT(lp, INT_STS_TSFL_ | INT_STS_GPT_INT_); - } -#else - if (status & INT_STS_TSFL_) { - DBG(SMC_DEBUG_TX, dev, "TX status FIFO limit (%d) irq\n", ?); - smc911x_tx(dev); - SMC_ACK_INT(lp, INT_STS_TSFL_); - } - - if (status & INT_STS_GPT_INT_) { - DBG(SMC_DEBUG_RX, dev, "IRQ_CFG 0x%08x FIFO_INT 0x%08x RX_CFG 0x%08x\n", - SMC_GET_IRQ_CFG(lp), - SMC_GET_FIFO_INT(lp), - SMC_GET_RX_CFG(lp)); - DBG(SMC_DEBUG_RX, dev, "Rx Stat FIFO Used 0x%02x Data FIFO Used 0x%04x Stat FIFO 0x%08x\n", - (SMC_GET_RX_FIFO_INF(lp) & 0x00ff0000) >> 16, - SMC_GET_RX_FIFO_INF(lp) & 0xffff, - SMC_GET_RX_STS_FIFO_PEEK(lp)); - SMC_SET_GPT_CFG(lp, GPT_CFG_TIMER_EN_ | 10000); - SMC_ACK_INT(lp, INT_STS_GPT_INT_); - } -#endif - - /* Handle PHY interrupt condition */ - if (status & INT_STS_PHY_INT_) { - DBG(SMC_DEBUG_MISC, dev, "PHY irq\n"); - smc911x_phy_interrupt(dev); - SMC_ACK_INT(lp, INT_STS_PHY_INT_); - } - } while (--timeout); - - /* restore mask state */ - SMC_SET_INT_EN(lp, mask); - - DBG(SMC_DEBUG_MISC, dev, "Interrupt done (%d loops)\n", - 8-timeout); - - spin_unlock_irqrestore(&lp->lock, flags); - - return IRQ_HANDLED; -} - -#ifdef SMC_USE_DMA -static void -smc911x_tx_dma_irq(void *data) -{ - struct smc911x_local *lp = data; - struct net_device *dev = lp->netdev; - struct sk_buff *skb = lp->current_tx_skb; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n"); - BUG_ON(skb == NULL); - dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); - netif_trans_update(dev); - dev_kfree_skb_irq(skb); - lp->current_tx_skb = NULL; - if (lp->pending_tx_skb != NULL) - smc911x_hardware_send_pkt(dev); - else { - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, - "No pending Tx packets. DMA disabled\n"); - spin_lock_irqsave(&lp->lock, flags); - lp->txdma_active = 0; - if (!lp->tx_throttle) { - netif_wake_queue(dev); - } - spin_unlock_irqrestore(&lp->lock, flags); - } - - DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, - "TX DMA irq completed\n"); -} -static void -smc911x_rx_dma_irq(void *data) -{ - struct smc911x_local *lp = data; - struct net_device *dev = lp->netdev; - struct sk_buff *skb = lp->current_rx_skb; - unsigned long flags; - unsigned int pkts; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n"); - dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); - BUG_ON(skb == NULL); - lp->current_rx_skb = NULL; - PRINT_PKT(skb->data, skb->len); - skb->protocol = eth_type_trans(skb, dev); - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; - netif_rx(skb); - - spin_lock_irqsave(&lp->lock, flags); - pkts = (SMC_GET_RX_FIFO_INF(lp) & RX_FIFO_INF_RXSUSED_) >> 16; - if (pkts != 0) { - smc911x_rcv(dev); - }else { - lp->rxdma_active = 0; - } - spin_unlock_irqrestore(&lp->lock, flags); - DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, - "RX DMA irq completed. DMA RX FIFO PKTS %d\n", - pkts); -} -#endif /* SMC_USE_DMA */ - -#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling receive - used by netconsole and other diagnostic tools - * to allow network i/o with interrupts disabled. - */ -static void smc911x_poll_controller(struct net_device *dev) -{ - disable_irq(dev->irq); - smc911x_interrupt(dev->irq, dev); - enable_irq(dev->irq); -} -#endif - -/* Our watchdog timed out. Called by the networking layer */ -static void smc911x_timeout(struct net_device *dev, unsigned int txqueue) -{ - struct smc911x_local *lp = netdev_priv(dev); - int status, mask; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - status = SMC_GET_INT(lp); - mask = SMC_GET_INT_EN(lp); - spin_unlock_irqrestore(&lp->lock, flags); - DBG(SMC_DEBUG_MISC, dev, "INT 0x%02x MASK 0x%02x\n", - status, mask); - - /* Dump the current TX FIFO contents and restart */ - mask = SMC_GET_TX_CFG(lp); - SMC_SET_TX_CFG(lp, mask | TX_CFG_TXS_DUMP_ | TX_CFG_TXD_DUMP_); - /* - * Reconfiguring the PHY doesn't seem like a bad idea here, but - * smc911x_phy_configure() calls msleep() which calls schedule_timeout() - * which calls schedule(). Hence we use a work queue. - */ - if (lp->phy_type != 0) - schedule_work(&lp->phy_configure); - - /* We can accept TX packets again */ - netif_trans_update(dev); /* prevent tx timeout */ - netif_wake_queue(dev); -} - -/* - * This routine will, depending on the values passed to it, - * either make it accept multicast packets, go into - * promiscuous mode (for TCPDUMP and cousins) or accept - * a select set of multicast packets - */ -static void smc911x_set_multicast_list(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int multicast_table[2]; - unsigned int mcr, update_multicast = 0; - unsigned long flags; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CR(lp, mcr); - spin_unlock_irqrestore(&lp->lock, flags); - - if (dev->flags & IFF_PROMISC) { - - DBG(SMC_DEBUG_MISC, dev, "RCR_PRMS\n"); - mcr |= MAC_CR_PRMS_; - } - /* - * Here, I am setting this to accept all multicast packets. - * I don't need to zero the multicast table, because the flag is - * checked before the table is - */ - else if (dev->flags & IFF_ALLMULTI || netdev_mc_count(dev) > 16) { - DBG(SMC_DEBUG_MISC, dev, "RCR_ALMUL\n"); - mcr |= MAC_CR_MCPAS_; - } - - /* - * This sets the internal hardware table to filter out unwanted - * multicast packets before they take up memory. - * - * The SMC chip uses a hash table where the high 6 bits of the CRC of - * address are the offset into the table. If that bit is 1, then the - * multicast packet is accepted. Otherwise, it's dropped silently. - * - * To use the 6 bits as an offset into the table, the high 1 bit is - * the number of the 32 bit register, while the low 5 bits are the bit - * within that register. - */ - else if (!netdev_mc_empty(dev)) { - struct netdev_hw_addr *ha; - - /* Set the Hash perfec mode */ - mcr |= MAC_CR_HPFILT_; - - /* start with a table of all zeros: reject all */ - memset(multicast_table, 0, sizeof(multicast_table)); - - netdev_for_each_mc_addr(ha, dev) { - u32 position; - - /* upper 6 bits are used as hash index */ - position = ether_crc(ETH_ALEN, ha->addr)>>26; - - multicast_table[position>>5] |= 1 << (position&0x1f); - } - - /* be sure I get rid of flags I might have set */ - mcr &= ~(MAC_CR_PRMS_ | MAC_CR_MCPAS_); - - /* now, the table can be loaded into the chipset */ - update_multicast = 1; - } else { - DBG(SMC_DEBUG_MISC, dev, "~(MAC_CR_PRMS_|MAC_CR_MCPAS_)\n"); - mcr &= ~(MAC_CR_PRMS_ | MAC_CR_MCPAS_); - - /* - * since I'm disabling all multicast entirely, I need to - * clear the multicast list - */ - memset(multicast_table, 0, sizeof(multicast_table)); - update_multicast = 1; - } - - spin_lock_irqsave(&lp->lock, flags); - SMC_SET_MAC_CR(lp, mcr); - if (update_multicast) { - DBG(SMC_DEBUG_MISC, dev, - "update mcast hash table 0x%08x 0x%08x\n", - multicast_table[0], multicast_table[1]); - SMC_SET_HASHL(lp, multicast_table[0]); - SMC_SET_HASHH(lp, multicast_table[1]); - } - spin_unlock_irqrestore(&lp->lock, flags); -} - - -/* - * Open and Initialize the board - * - * Set up everything, reset the card, etc.. - */ -static int -smc911x_open(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* reset the hardware */ - smc911x_reset(dev); - - /* Configure the PHY, initialize the link state */ - smc911x_phy_configure(&lp->phy_configure); - - /* Turn on Tx + Rx */ - smc911x_enable(dev); - - netif_start_queue(dev); - - return 0; -} - -/* - * smc911x_close - * - * this makes the board clean up everything that it can - * and not talk to the outside world. Caused by - * an 'ifconfig ethX down' - */ -static int smc911x_close(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - netif_stop_queue(dev); - netif_carrier_off(dev); - - /* clear everything */ - smc911x_shutdown(dev); - - if (lp->phy_type != 0) { - /* We need to ensure that no calls to - * smc911x_phy_configure are pending. - */ - cancel_work_sync(&lp->phy_configure); - smc911x_phy_powerdown(dev, lp->mii.phy_id); - } - - if (lp->pending_tx_skb) { - dev_kfree_skb(lp->pending_tx_skb); - lp->pending_tx_skb = NULL; - } - - return 0; -} - -/* - * Ethtool support - */ -static int -smc911x_ethtool_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct smc911x_local *lp = netdev_priv(dev); - int status; - unsigned long flags; - u32 supported; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - mii_ethtool_get_link_ksettings(&lp->mii, cmd); - spin_unlock_irqrestore(&lp->lock, flags); - } else { - supported = SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_TP | SUPPORTED_AUI; - - if (lp->ctl_rspeed == 10) - cmd->base.speed = SPEED_10; - else if (lp->ctl_rspeed == 100) - cmd->base.speed = SPEED_100; - - cmd->base.autoneg = AUTONEG_DISABLE; - cmd->base.port = 0; - SMC_GET_PHY_SPECIAL(lp, lp->mii.phy_id, status); - cmd->base.duplex = - (status & (PHY_SPECIAL_SPD_10FULL_ | PHY_SPECIAL_SPD_100FULL_)) ? - DUPLEX_FULL : DUPLEX_HALF; - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.supported, supported); - - } - - return 0; -} - -static int -smc911x_ethtool_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - unsigned long flags; - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - ret = mii_ethtool_set_link_ksettings(&lp->mii, cmd); - spin_unlock_irqrestore(&lp->lock, flags); - } else { - if (cmd->base.autoneg != AUTONEG_DISABLE || - cmd->base.speed != SPEED_10 || - (cmd->base.duplex != DUPLEX_HALF && - cmd->base.duplex != DUPLEX_FULL) || - (cmd->base.port != PORT_TP && - cmd->base.port != PORT_AUI)) - return -EINVAL; - - lp->ctl_rfduplx = cmd->base.duplex == DUPLEX_FULL; - - ret = 0; - } - - return ret; -} - -static void -smc911x_ethtool_getdrvinfo(struct net_device *dev, struct ethtool_drvinfo *info) -{ - strscpy(info->driver, CARDNAME, sizeof(info->driver)); - strscpy(info->version, version, sizeof(info->version)); - strscpy(info->bus_info, dev_name(dev->dev.parent), - sizeof(info->bus_info)); -} - -static int smc911x_ethtool_nwayreset(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret = -EINVAL; - unsigned long flags; - - if (lp->phy_type != 0) { - spin_lock_irqsave(&lp->lock, flags); - ret = mii_nway_restart(&lp->mii); - spin_unlock_irqrestore(&lp->lock, flags); - } - - return ret; -} - -static u32 smc911x_ethtool_getmsglevel(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - return lp->msg_enable; -} - -static void smc911x_ethtool_setmsglevel(struct net_device *dev, u32 level) -{ - struct smc911x_local *lp = netdev_priv(dev); - lp->msg_enable = level; -} - -static int smc911x_ethtool_getregslen(struct net_device *dev) -{ - /* System regs + MAC regs + PHY regs */ - return (((E2P_CMD - ID_REV)/4 + 1) + - (WUCSR - MAC_CR)+1 + 32) * sizeof(u32); -} - -static void smc911x_ethtool_getregs(struct net_device *dev, - struct ethtool_regs *regs, void *buf) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned long flags; - u32 reg,i,j=0; - u32 *data = (u32*)buf; - - regs->version = lp->version; - for(i=ID_REV;i<=E2P_CMD;i+=4) { - data[j++] = SMC_inl(lp, i); - } - for(i=MAC_CR;i<=WUCSR;i++) { - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MAC_CSR(lp, i, reg); - spin_unlock_irqrestore(&lp->lock, flags); - data[j++] = reg; - } - for(i=0;i<=31;i++) { - spin_lock_irqsave(&lp->lock, flags); - SMC_GET_MII(lp, i, lp->mii.phy_id, reg); - spin_unlock_irqrestore(&lp->lock, flags); - data[j++] = reg & 0xFFFF; - } -} - -static int smc911x_ethtool_wait_eeprom_ready(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - unsigned int timeout; - int e2p_cmd; - - e2p_cmd = SMC_GET_E2P_CMD(lp); - for(timeout=10;(e2p_cmd & E2P_CMD_EPC_BUSY_) && timeout; timeout--) { - if (e2p_cmd & E2P_CMD_EPC_TIMEOUT_) { - PRINTK(dev, "%s timeout waiting for EEPROM to respond\n", - __func__); - return -EFAULT; - } - mdelay(1); - e2p_cmd = SMC_GET_E2P_CMD(lp); - } - if (timeout == 0) { - PRINTK(dev, "%s timeout waiting for EEPROM CMD not busy\n", - __func__); - return -ETIMEDOUT; - } - return 0; -} - -static inline int smc911x_ethtool_write_eeprom_cmd(struct net_device *dev, - int cmd, int addr) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - SMC_SET_E2P_CMD(lp, E2P_CMD_EPC_BUSY_ | - ((cmd) & (0x7<<28)) | - ((addr) & 0xFF)); - return 0; -} - -static inline int smc911x_ethtool_read_eeprom_byte(struct net_device *dev, - u8 *data) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - *data = SMC_GET_E2P_DATA(lp); - return 0; -} - -static inline int smc911x_ethtool_write_eeprom_byte(struct net_device *dev, - u8 data) -{ - struct smc911x_local *lp = netdev_priv(dev); - int ret; - - if ((ret = smc911x_ethtool_wait_eeprom_ready(dev))!=0) - return ret; - SMC_SET_E2P_DATA(lp, data); - return 0; -} - -static int smc911x_ethtool_geteeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - u8 eebuf[SMC911X_EEPROM_LEN]; - int i, ret; - - for(i=0;ioffset, eeprom->len); - return 0; -} - -static int smc911x_ethtool_seteeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - int i, ret; - - /* Enable erase */ - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_EWEN_, 0 ))!=0) - return ret; - for(i=eeprom->offset;i<(eeprom->offset+eeprom->len);i++) { - /* erase byte */ - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_ERASE_, i ))!=0) - return ret; - /* write byte */ - if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0) - return ret; - if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0) - return ret; - } - return 0; -} - -static int smc911x_ethtool_geteeprom_len(struct net_device *dev) -{ - return SMC911X_EEPROM_LEN; -} - -static const struct ethtool_ops smc911x_ethtool_ops = { - .get_drvinfo = smc911x_ethtool_getdrvinfo, - .get_msglevel = smc911x_ethtool_getmsglevel, - .set_msglevel = smc911x_ethtool_setmsglevel, - .nway_reset = smc911x_ethtool_nwayreset, - .get_link = ethtool_op_get_link, - .get_regs_len = smc911x_ethtool_getregslen, - .get_regs = smc911x_ethtool_getregs, - .get_eeprom_len = smc911x_ethtool_geteeprom_len, - .get_eeprom = smc911x_ethtool_geteeprom, - .set_eeprom = smc911x_ethtool_seteeprom, - .get_link_ksettings = smc911x_ethtool_get_link_ksettings, - .set_link_ksettings = smc911x_ethtool_set_link_ksettings, -}; - -/* - * smc911x_findirq - * - * This routine has a simple purpose -- make the SMC chip generate an - * interrupt, so an auto-detect routine can detect it, and find the IRQ, - */ -static int smc911x_findirq(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int timeout = 20; - unsigned long cookie; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - cookie = probe_irq_on(); - - /* - * Force a SW interrupt - */ - - SMC_SET_INT_EN(lp, INT_EN_SW_INT_EN_); - - /* - * Wait until positive that the interrupt has been generated - */ - do { - int int_status; - udelay(10); - int_status = SMC_GET_INT_EN(lp); - if (int_status & INT_EN_SW_INT_EN_) - break; /* got the interrupt */ - } while (--timeout); - - /* - * there is really nothing that I can do here if timeout fails, - * as autoirq_report will return a 0 anyway, which is what I - * want in this case. Plus, the clean up is needed in both - * cases. - */ - - /* and disable all interrupts again */ - SMC_SET_INT_EN(lp, 0); - - /* and return what I found */ - return probe_irq_off(cookie); -} - -static const struct net_device_ops smc911x_netdev_ops = { - .ndo_open = smc911x_open, - .ndo_stop = smc911x_close, - .ndo_start_xmit = smc911x_hard_start_xmit, - .ndo_tx_timeout = smc911x_timeout, - .ndo_set_rx_mode = smc911x_set_multicast_list, - .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = eth_mac_addr, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = smc911x_poll_controller, -#endif -}; - -/* - * Function: smc911x_probe(unsigned long ioaddr) - * - * Purpose: - * Tests to see if a given ioaddr points to an SMC911x chip. - * Returns a 0 on success - * - * Algorithm: - * (1) see if the endian word is OK - * (1) see if I recognize the chip ID in the appropriate register - * - * Here I do typical initialization tasks. - * - * o Initialize the structure if needed - * o print out my vanity message if not done so already - * o print out what type of hardware is detected - * o print out the ethernet address - * o find the IRQ - * o set up my private data - * o configure the dev structure with my subroutines - * o actually GRAB the irq. - * o GRAB the region - */ -static int smc911x_probe(struct net_device *dev) -{ - struct smc911x_local *lp = netdev_priv(dev); - int i, retval; - unsigned int val, chip_id, revision; - const char *version_string; - unsigned long irq_flags; -#ifdef SMC_USE_DMA - struct dma_slave_config config; - dma_cap_mask_t mask; -#endif - u8 addr[ETH_ALEN]; - - DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); - - /* First, see if the endian word is recognized */ - val = SMC_GET_BYTE_TEST(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: endian probe returned 0x%04x\n", - CARDNAME, val); - if (val != 0x87654321) { - netdev_err(dev, "Invalid chip endian 0x%08x\n", val); - retval = -ENODEV; - goto err_out; - } - - /* - * check if the revision register is something that I - * recognize. These might need to be added to later, - * as future revisions could be added. - */ - chip_id = SMC_GET_PN(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: id probe returned 0x%04x\n", - CARDNAME, chip_id); - for(i=0;chip_ids[i].id != 0; i++) { - if (chip_ids[i].id == chip_id) break; - } - if (!chip_ids[i].id) { - netdev_err(dev, "Unknown chip ID %04x\n", chip_id); - retval = -ENODEV; - goto err_out; - } - version_string = chip_ids[i].name; - - revision = SMC_GET_REV(lp); - DBG(SMC_DEBUG_MISC, dev, "%s: revision = 0x%04x\n", CARDNAME, revision); - - /* At this point I'll assume that the chip is an SMC911x. */ - DBG(SMC_DEBUG_MISC, dev, "%s: Found a %s\n", - CARDNAME, chip_ids[i].name); - - /* Validate the TX FIFO size requested */ - if ((tx_fifo_kb < 2) || (tx_fifo_kb > 14)) { - netdev_err(dev, "Invalid TX FIFO size requested %d\n", - tx_fifo_kb); - retval = -EINVAL; - goto err_out; - } - - /* fill in some of the fields */ - lp->version = chip_ids[i].id; - lp->revision = revision; - lp->tx_fifo_kb = tx_fifo_kb; - /* Reverse calculate the RX FIFO size from the TX */ - lp->tx_fifo_size=(lp->tx_fifo_kb<<10) - 512; - lp->rx_fifo_size= ((0x4000 - 512 - lp->tx_fifo_size) / 16) * 15; - - /* Set the automatic flow control values */ - switch(lp->tx_fifo_kb) { - /* - * AFC_HI is about ((Rx Data Fifo Size)*2/3)/64 - * AFC_LO is AFC_HI/2 - * BACK_DUR is about 5uS*(AFC_LO) rounded down - */ - case 2:/* 13440 Rx Data Fifo Size */ - lp->afc_cfg=0x008C46AF;break; - case 3:/* 12480 Rx Data Fifo Size */ - lp->afc_cfg=0x0082419F;break; - case 4:/* 11520 Rx Data Fifo Size */ - lp->afc_cfg=0x00783C9F;break; - case 5:/* 10560 Rx Data Fifo Size */ - lp->afc_cfg=0x006E374F;break; - case 6:/* 9600 Rx Data Fifo Size */ - lp->afc_cfg=0x0064328F;break; - case 7:/* 8640 Rx Data Fifo Size */ - lp->afc_cfg=0x005A2D7F;break; - case 8:/* 7680 Rx Data Fifo Size */ - lp->afc_cfg=0x0050287F;break; - case 9:/* 6720 Rx Data Fifo Size */ - lp->afc_cfg=0x0046236F;break; - case 10:/* 5760 Rx Data Fifo Size */ - lp->afc_cfg=0x003C1E6F;break; - case 11:/* 4800 Rx Data Fifo Size */ - lp->afc_cfg=0x0032195F;break; - /* - * AFC_HI is ~1520 bytes less than RX Data Fifo Size - * AFC_LO is AFC_HI/2 - * BACK_DUR is about 5uS*(AFC_LO) rounded down - */ - case 12:/* 3840 Rx Data Fifo Size */ - lp->afc_cfg=0x0024124F;break; - case 13:/* 2880 Rx Data Fifo Size */ - lp->afc_cfg=0x0015073F;break; - case 14:/* 1920 Rx Data Fifo Size */ - lp->afc_cfg=0x0006032F;break; - default: - PRINTK(dev, "ERROR -- no AFC_CFG setting found"); - break; - } - - DBG(SMC_DEBUG_MISC | SMC_DEBUG_TX | SMC_DEBUG_RX, dev, - "%s: tx_fifo %d rx_fifo %d afc_cfg 0x%08x\n", CARDNAME, - lp->tx_fifo_size, lp->rx_fifo_size, lp->afc_cfg); - - spin_lock_init(&lp->lock); - - /* Get the MAC address */ - SMC_GET_MAC_ADDR(lp, addr); - eth_hw_addr_set(dev, addr); - - /* now, reset the chip, and put it into a known state */ - smc911x_reset(dev); - - /* - * If dev->irq is 0, then the device has to be banged on to see - * what the IRQ is. - * - * Specifying an IRQ is done with the assumption that the user knows - * what (s)he is doing. No checking is done!!!! - */ - if (dev->irq < 1) { - int trials; - - trials = 3; - while (trials--) { - dev->irq = smc911x_findirq(dev); - if (dev->irq) - break; - /* kick the card and try again */ - smc911x_reset(dev); - } - } - if (dev->irq == 0) { - netdev_warn(dev, "Couldn't autodetect your IRQ. Use irq=xx.\n"); - retval = -ENODEV; - goto err_out; - } - dev->irq = irq_canonicalize(dev->irq); - - dev->netdev_ops = &smc911x_netdev_ops; - dev->watchdog_timeo = msecs_to_jiffies(watchdog); - dev->ethtool_ops = &smc911x_ethtool_ops; - - INIT_WORK(&lp->phy_configure, smc911x_phy_configure); - lp->mii.phy_id_mask = 0x1f; - lp->mii.reg_num_mask = 0x1f; - lp->mii.force_media = 0; - lp->mii.full_duplex = 0; - lp->mii.dev = dev; - lp->mii.mdio_read = smc911x_phy_read; - lp->mii.mdio_write = smc911x_phy_write; - - /* - * Locate the phy, if any. - */ - smc911x_phy_detect(dev); - - /* Set default parameters */ - lp->msg_enable = NETIF_MSG_LINK; - lp->ctl_rfduplx = 1; - lp->ctl_rspeed = 100; - -#ifdef SMC_DYNAMIC_BUS_CONFIG - irq_flags = lp->cfg.irq_flags; -#else - irq_flags = IRQF_SHARED | SMC_IRQ_SENSE; -#endif - - /* Grab the IRQ */ - retval = request_irq(dev->irq, smc911x_interrupt, - irq_flags, dev->name, dev); - if (retval) - goto err_out; - -#ifdef SMC_USE_DMA - - dma_cap_zero(mask); - dma_cap_set(DMA_SLAVE, mask); - lp->rxdma = dma_request_channel(mask, NULL, NULL); - lp->txdma = dma_request_channel(mask, NULL, NULL); - lp->rxdma_active = 0; - lp->txdma_active = 0; - - memset(&config, 0, sizeof(config)); - config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - config.src_addr = lp->physaddr + RX_DATA_FIFO; - config.dst_addr = lp->physaddr + TX_DATA_FIFO; - config.src_maxburst = 32; - config.dst_maxburst = 32; - retval = dmaengine_slave_config(lp->rxdma, &config); - if (retval) { - dev_err(lp->dev, "dma rx channel configuration failed: %d\n", - retval); - goto err_out; - } - retval = dmaengine_slave_config(lp->txdma, &config); - if (retval) { - dev_err(lp->dev, "dma tx channel configuration failed: %d\n", - retval); - goto err_out; - } -#endif - - retval = register_netdev(dev); - if (retval == 0) { - /* now, print out the card info, in a short format.. */ - netdev_info(dev, "%s (rev %d) at %#lx IRQ %d", - version_string, lp->revision, - dev->base_addr, dev->irq); - -#ifdef SMC_USE_DMA - if (lp->rxdma) - pr_cont(" RXDMA %p", lp->rxdma); - - if (lp->txdma) - pr_cont(" TXDMA %p", lp->txdma); -#endif - pr_cont("\n"); - if (!is_valid_ether_addr(dev->dev_addr)) { - netdev_warn(dev, "Invalid ethernet MAC address. Please set using ifconfig\n"); - } else { - /* Print the Ethernet address */ - netdev_info(dev, "Ethernet addr: %pM\n", - dev->dev_addr); - } - - if (lp->phy_type == 0) { - PRINTK(dev, "No PHY found\n"); - } else if ((lp->phy_type & ~0xff) == LAN911X_INTERNAL_PHY_ID) { - PRINTK(dev, "LAN911x Internal PHY\n"); - } else { - PRINTK(dev, "External PHY 0x%08x\n", lp->phy_type); - } - } - -err_out: -#ifdef SMC_USE_DMA - if (retval) { - if (lp->rxdma) - dma_release_channel(lp->rxdma); - if (lp->txdma) - dma_release_channel(lp->txdma); - } -#endif - return retval; -} - -/* - * smc911x_drv_probe(void) - * - * Output: - * 0 --> there is a device - * anything else, error - */ -static int smc911x_drv_probe(struct platform_device *pdev) -{ - struct net_device *ndev; - struct resource *res; - struct smc911x_local *lp; - void __iomem *addr; - int ret; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - ret = -ENODEV; - goto out; - } - - /* - * Request the regions. - */ - if (!request_mem_region(res->start, SMC911X_IO_EXTENT, CARDNAME)) { - ret = -EBUSY; - goto out; - } - - ndev = alloc_etherdev(sizeof(struct smc911x_local)); - if (!ndev) { - ret = -ENOMEM; - goto release_1; - } - SET_NETDEV_DEV(ndev, &pdev->dev); - - ndev->dma = (unsigned char)-1; - ndev->irq = platform_get_irq(pdev, 0); - if (ndev->irq < 0) { - ret = ndev->irq; - goto release_both; - } - - lp = netdev_priv(ndev); - lp->netdev = ndev; -#ifdef SMC_DYNAMIC_BUS_CONFIG - { - struct smc911x_platdata *pd = dev_get_platdata(&pdev->dev); - if (!pd) { - ret = -EINVAL; - goto release_both; - } - memcpy(&lp->cfg, pd, sizeof(lp->cfg)); - } -#endif - - addr = ioremap(res->start, SMC911X_IO_EXTENT); - if (!addr) { - ret = -ENOMEM; - goto release_both; - } - - platform_set_drvdata(pdev, ndev); - lp->base = addr; - ndev->base_addr = res->start; - ret = smc911x_probe(ndev); - if (ret != 0) { - iounmap(addr); -release_both: - free_netdev(ndev); -release_1: - release_mem_region(res->start, SMC911X_IO_EXTENT); -out: - pr_info("%s: not found (%d).\n", CARDNAME, ret); - } -#ifdef SMC_USE_DMA - else { - lp->physaddr = res->start; - lp->dev = &pdev->dev; - } -#endif - - return ret; -} - -static int smc911x_drv_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - struct smc911x_local *lp = netdev_priv(ndev); - struct resource *res; - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - - unregister_netdev(ndev); - - free_irq(ndev->irq, ndev); - -#ifdef SMC_USE_DMA - { - if (lp->rxdma) - dma_release_channel(lp->rxdma); - if (lp->txdma) - dma_release_channel(lp->txdma); - } -#endif - iounmap(lp->base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, SMC911X_IO_EXTENT); - - free_netdev(ndev); - return 0; -} - -static int smc911x_drv_suspend(struct platform_device *dev, pm_message_t state) -{ - struct net_device *ndev = platform_get_drvdata(dev); - struct smc911x_local *lp = netdev_priv(ndev); - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - if (ndev) { - if (netif_running(ndev)) { - netif_device_detach(ndev); - smc911x_shutdown(ndev); -#if POWER_DOWN - /* Set D2 - Energy detect only setting */ - SMC_SET_PMT_CTRL(lp, 2<<12); -#endif - } - } - return 0; -} - -static int smc911x_drv_resume(struct platform_device *dev) -{ - struct net_device *ndev = platform_get_drvdata(dev); - - DBG(SMC_DEBUG_FUNC, ndev, "--> %s\n", __func__); - if (ndev) { - struct smc911x_local *lp = netdev_priv(ndev); - - if (netif_running(ndev)) { - smc911x_reset(ndev); - if (lp->phy_type != 0) - smc911x_phy_configure(&lp->phy_configure); - smc911x_enable(ndev); - netif_device_attach(ndev); - } - } - return 0; -} - -static struct platform_driver smc911x_driver = { - .probe = smc911x_drv_probe, - .remove = smc911x_drv_remove, - .suspend = smc911x_drv_suspend, - .resume = smc911x_drv_resume, - .driver = { - .name = CARDNAME, - }, -}; - -module_platform_driver(smc911x_driver); diff --git a/drivers/net/ethernet/smsc/smc911x.h b/drivers/net/ethernet/smsc/smc911x.h deleted file mode 100644 index d4edcc0da87c..000000000000 --- a/drivers/net/ethernet/smsc/smc911x.h +++ /dev/null @@ -1,901 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/*------------------------------------------------------------------------ - . smc911x.h - macros for SMSC's LAN911{5,6,7,8} single-chip Ethernet device. - . - . Copyright (C) 2005 Sensoria Corp. - . Derived from the unified SMC91x driver by Nicolas Pitre - . - . - . Information contained in this file was obtained from the LAN9118 - . manual from SMC. To get a copy, if you really want one, you can find - . information under www.smsc.com. - . - . Authors - . Dustin McIntire - . - ---------------------------------------------------------------------------*/ -#ifndef _SMC911X_H_ -#define _SMC911X_H_ - -#include -/* - * Use the DMA feature on PXA chips - */ -#ifdef CONFIG_ARCH_PXA - #define SMC_USE_PXA_DMA 1 - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_FALLING -#elif defined(CONFIG_SH_MAGIC_PANEL_R2) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW -#elif defined(CONFIG_ARCH_OMAP3) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW - #define SMC_MEM_RESERVED 1 -#elif defined(CONFIG_ARCH_OMAP2) - #define SMC_USE_16BIT 0 - #define SMC_USE_32BIT 1 - #define SMC_IRQ_SENSE IRQF_TRIGGER_LOW - #define SMC_MEM_RESERVED 1 -#else -/* - * Default configuration - */ - -#define SMC_DYNAMIC_BUS_CONFIG -#endif - -#ifdef SMC_USE_PXA_DMA -#define SMC_USE_DMA -#endif - -/* store this information for the driver.. */ -struct smc911x_local { - /* - * If I have to wait until the DMA is finished and ready to reload a - * packet, I will store the skbuff here. Then, the DMA will send it - * out and free it. - */ - struct sk_buff *pending_tx_skb; - - /* version/revision of the SMC911x chip */ - u16 version; - u16 revision; - - /* FIFO sizes */ - int tx_fifo_kb; - int tx_fifo_size; - int rx_fifo_size; - int afc_cfg; - - /* Contains the current active receive/phy mode */ - int ctl_rfduplx; - int ctl_rspeed; - - u32 msg_enable; - u32 phy_type; - struct mii_if_info mii; - - /* work queue */ - struct work_struct phy_configure; - - int tx_throttle; - spinlock_t lock; - - struct net_device *netdev; - -#ifdef SMC_USE_DMA - /* DMA needs the physical address of the chip */ - u_long physaddr; - struct dma_chan *rxdma; - struct dma_chan *txdma; - int rxdma_active; - int txdma_active; - struct sk_buff *current_rx_skb; - struct sk_buff *current_tx_skb; - struct device *dev; -#endif - void __iomem *base; -#ifdef SMC_DYNAMIC_BUS_CONFIG - struct smc911x_platdata cfg; -#endif -}; - -/* - * Define the bus width specific IO macros - */ - -#ifdef SMC_DYNAMIC_BUS_CONFIG -static inline unsigned int SMC_inl(struct smc911x_local *lp, int reg) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) - return readl(ioaddr); - - if (lp->cfg.flags & SMC911X_USE_16BIT) - return readw(ioaddr) | (readw(ioaddr + 2) << 16); - - BUG(); -} - -static inline void SMC_outl(unsigned int value, struct smc911x_local *lp, - int reg) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - writel(value, ioaddr); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - writew(value & 0xffff, ioaddr); - writew(value >> 16, ioaddr + 2); - return; - } - - BUG(); -} - -static inline void SMC_insl(struct smc911x_local *lp, int reg, - void *addr, unsigned int count) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - ioread32_rep(ioaddr, addr, count); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - ioread16_rep(ioaddr, addr, count * 2); - return; - } - - BUG(); -} - -static inline void SMC_outsl(struct smc911x_local *lp, int reg, - void *addr, unsigned int count) -{ - void __iomem *ioaddr = lp->base + reg; - - if (lp->cfg.flags & SMC911X_USE_32BIT) { - iowrite32_rep(ioaddr, addr, count); - return; - } - - if (lp->cfg.flags & SMC911X_USE_16BIT) { - iowrite16_rep(ioaddr, addr, count * 2); - return; - } - - BUG(); -} -#else -#if SMC_USE_16BIT -#define SMC_inl(lp, r) ((readw((lp)->base + (r)) & 0xFFFF) + (readw((lp)->base + (r) + 2) << 16)) -#define SMC_outl(v, lp, r) \ - do{ \ - writew(v & 0xFFFF, (lp)->base + (r)); \ - writew(v >> 16, (lp)->base + (r) + 2); \ - } while (0) -#define SMC_insl(lp, r, p, l) ioread16_rep((short*)((lp)->base + (r)), p, l*2) -#define SMC_outsl(lp, r, p, l) iowrite16_rep((short*)((lp)->base + (r)), p, l*2) - -#elif SMC_USE_32BIT -#define SMC_inl(lp, r) readl((lp)->base + (r)) -#define SMC_outl(v, lp, r) writel(v, (lp)->base + (r)) -#define SMC_insl(lp, r, p, l) ioread32_rep((int*)((lp)->base + (r)), p, l) -#define SMC_outsl(lp, r, p, l) iowrite32_rep((int*)((lp)->base + (r)), p, l) - -#endif /* SMC_USE_16BIT */ -#endif /* SMC_DYNAMIC_BUS_CONFIG */ - - -#ifdef SMC_USE_PXA_DMA - -/* - * Use a DMA for RX and TX packets. - */ -#include - -static dma_addr_t rx_dmabuf, tx_dmabuf; -static int rx_dmalen, tx_dmalen; -static void smc911x_rx_dma_irq(void *data); -static void smc911x_tx_dma_irq(void *data); - -#ifdef SMC_insl -#undef SMC_insl -#define SMC_insl(lp, r, p, l) \ - smc_pxa_dma_insl(lp, lp->physaddr, r, lp->rxdma, p, l) - -static inline void -smc_pxa_dma_insl(struct smc911x_local *lp, u_long physaddr, - int reg, struct dma_chan *dma, u_char *buf, int len) -{ - struct dma_async_tx_descriptor *tx; - - /* 64 bit alignment is required for memory to memory DMA */ - if ((long)buf & 4) { - *((u32 *)buf) = SMC_inl(lp, reg); - buf += 4; - len--; - } - - len *= 4; - rx_dmabuf = dma_map_single(lp->dev, buf, len, DMA_FROM_DEVICE); - rx_dmalen = len; - tx = dmaengine_prep_slave_single(dma, rx_dmabuf, rx_dmalen, - DMA_DEV_TO_MEM, 0); - if (tx) { - tx->callback = smc911x_rx_dma_irq; - tx->callback_param = lp; - dmaengine_submit(tx); - dma_async_issue_pending(dma); - } -} -#endif - -#ifdef SMC_outsl -#undef SMC_outsl -#define SMC_outsl(lp, r, p, l) \ - smc_pxa_dma_outsl(lp, lp->physaddr, r, lp->txdma, p, l) - -static inline void -smc_pxa_dma_outsl(struct smc911x_local *lp, u_long physaddr, - int reg, struct dma_chan *dma, u_char *buf, int len) -{ - struct dma_async_tx_descriptor *tx; - - /* 64 bit alignment is required for memory to memory DMA */ - if ((long)buf & 4) { - SMC_outl(*((u32 *)buf), lp, reg); - buf += 4; - len--; - } - - len *= 4; - tx_dmabuf = dma_map_single(lp->dev, buf, len, DMA_TO_DEVICE); - tx_dmalen = len; - tx = dmaengine_prep_slave_single(dma, tx_dmabuf, tx_dmalen, - DMA_DEV_TO_MEM, 0); - if (tx) { - tx->callback = smc911x_tx_dma_irq; - tx->callback_param = lp; - dmaengine_submit(tx); - dma_async_issue_pending(dma); - } -} -#endif -#endif /* SMC_USE_PXA_DMA */ - - -/* Chip Parameters and Register Definitions */ - -#define SMC911X_TX_FIFO_LOW_THRESHOLD (1536*2) - -#define SMC911X_IO_EXTENT 0x100 - -#define SMC911X_EEPROM_LEN 7 - -/* Below are the register offsets and bit definitions - * of the Lan911x memory space - */ -#define RX_DATA_FIFO (0x00) - -#define TX_DATA_FIFO (0x20) -#define TX_CMD_A_INT_ON_COMP_ (0x80000000) -#define TX_CMD_A_INT_BUF_END_ALGN_ (0x03000000) -#define TX_CMD_A_INT_4_BYTE_ALGN_ (0x00000000) -#define TX_CMD_A_INT_16_BYTE_ALGN_ (0x01000000) -#define TX_CMD_A_INT_32_BYTE_ALGN_ (0x02000000) -#define TX_CMD_A_INT_DATA_OFFSET_ (0x001F0000) -#define TX_CMD_A_INT_FIRST_SEG_ (0x00002000) -#define TX_CMD_A_INT_LAST_SEG_ (0x00001000) -#define TX_CMD_A_BUF_SIZE_ (0x000007FF) -#define TX_CMD_B_PKT_TAG_ (0xFFFF0000) -#define TX_CMD_B_ADD_CRC_DISABLE_ (0x00002000) -#define TX_CMD_B_DISABLE_PADDING_ (0x00001000) -#define TX_CMD_B_PKT_BYTE_LENGTH_ (0x000007FF) - -#define RX_STATUS_FIFO (0x40) -#define RX_STS_PKT_LEN_ (0x3FFF0000) -#define RX_STS_ES_ (0x00008000) -#define RX_STS_BCST_ (0x00002000) -#define RX_STS_LEN_ERR_ (0x00001000) -#define RX_STS_RUNT_ERR_ (0x00000800) -#define RX_STS_MCAST_ (0x00000400) -#define RX_STS_TOO_LONG_ (0x00000080) -#define RX_STS_COLL_ (0x00000040) -#define RX_STS_ETH_TYPE_ (0x00000020) -#define RX_STS_WDOG_TMT_ (0x00000010) -#define RX_STS_MII_ERR_ (0x00000008) -#define RX_STS_DRIBBLING_ (0x00000004) -#define RX_STS_CRC_ERR_ (0x00000002) -#define RX_STATUS_FIFO_PEEK (0x44) -#define TX_STATUS_FIFO (0x48) -#define TX_STS_TAG_ (0xFFFF0000) -#define TX_STS_ES_ (0x00008000) -#define TX_STS_LOC_ (0x00000800) -#define TX_STS_NO_CARR_ (0x00000400) -#define TX_STS_LATE_COLL_ (0x00000200) -#define TX_STS_MANY_COLL_ (0x00000100) -#define TX_STS_COLL_CNT_ (0x00000078) -#define TX_STS_MANY_DEFER_ (0x00000004) -#define TX_STS_UNDERRUN_ (0x00000002) -#define TX_STS_DEFERRED_ (0x00000001) -#define TX_STATUS_FIFO_PEEK (0x4C) -#define ID_REV (0x50) -#define ID_REV_CHIP_ID_ (0xFFFF0000) /* RO */ -#define ID_REV_REV_ID_ (0x0000FFFF) /* RO */ - -#define INT_CFG (0x54) -#define INT_CFG_INT_DEAS_ (0xFF000000) /* R/W */ -#define INT_CFG_INT_DEAS_CLR_ (0x00004000) -#define INT_CFG_INT_DEAS_STS_ (0x00002000) -#define INT_CFG_IRQ_INT_ (0x00001000) /* RO */ -#define INT_CFG_IRQ_EN_ (0x00000100) /* R/W */ -#define INT_CFG_IRQ_POL_ (0x00000010) /* R/W Not Affected by SW Reset */ -#define INT_CFG_IRQ_TYPE_ (0x00000001) /* R/W Not Affected by SW Reset */ - -#define INT_STS (0x58) -#define INT_STS_SW_INT_ (0x80000000) /* R/WC */ -#define INT_STS_TXSTOP_INT_ (0x02000000) /* R/WC */ -#define INT_STS_RXSTOP_INT_ (0x01000000) /* R/WC */ -#define INT_STS_RXDFH_INT_ (0x00800000) /* R/WC */ -#define INT_STS_RXDF_INT_ (0x00400000) /* R/WC */ -#define INT_STS_TX_IOC_ (0x00200000) /* R/WC */ -#define INT_STS_RXD_INT_ (0x00100000) /* R/WC */ -#define INT_STS_GPT_INT_ (0x00080000) /* R/WC */ -#define INT_STS_PHY_INT_ (0x00040000) /* RO */ -#define INT_STS_PME_INT_ (0x00020000) /* R/WC */ -#define INT_STS_TXSO_ (0x00010000) /* R/WC */ -#define INT_STS_RWT_ (0x00008000) /* R/WC */ -#define INT_STS_RXE_ (0x00004000) /* R/WC */ -#define INT_STS_TXE_ (0x00002000) /* R/WC */ -//#define INT_STS_ERX_ (0x00001000) /* R/WC */ -#define INT_STS_TDFU_ (0x00000800) /* R/WC */ -#define INT_STS_TDFO_ (0x00000400) /* R/WC */ -#define INT_STS_TDFA_ (0x00000200) /* R/WC */ -#define INT_STS_TSFF_ (0x00000100) /* R/WC */ -#define INT_STS_TSFL_ (0x00000080) /* R/WC */ -//#define INT_STS_RXDF_ (0x00000040) /* R/WC */ -#define INT_STS_RDFO_ (0x00000040) /* R/WC */ -#define INT_STS_RDFL_ (0x00000020) /* R/WC */ -#define INT_STS_RSFF_ (0x00000010) /* R/WC */ -#define INT_STS_RSFL_ (0x00000008) /* R/WC */ -#define INT_STS_GPIO2_INT_ (0x00000004) /* R/WC */ -#define INT_STS_GPIO1_INT_ (0x00000002) /* R/WC */ -#define INT_STS_GPIO0_INT_ (0x00000001) /* R/WC */ - -#define INT_EN (0x5C) -#define INT_EN_SW_INT_EN_ (0x80000000) /* R/W */ -#define INT_EN_TXSTOP_INT_EN_ (0x02000000) /* R/W */ -#define INT_EN_RXSTOP_INT_EN_ (0x01000000) /* R/W */ -#define INT_EN_RXDFH_INT_EN_ (0x00800000) /* R/W */ -//#define INT_EN_RXDF_INT_EN_ (0x00400000) /* R/W */ -#define INT_EN_TIOC_INT_EN_ (0x00200000) /* R/W */ -#define INT_EN_RXD_INT_EN_ (0x00100000) /* R/W */ -#define INT_EN_GPT_INT_EN_ (0x00080000) /* R/W */ -#define INT_EN_PHY_INT_EN_ (0x00040000) /* R/W */ -#define INT_EN_PME_INT_EN_ (0x00020000) /* R/W */ -#define INT_EN_TXSO_EN_ (0x00010000) /* R/W */ -#define INT_EN_RWT_EN_ (0x00008000) /* R/W */ -#define INT_EN_RXE_EN_ (0x00004000) /* R/W */ -#define INT_EN_TXE_EN_ (0x00002000) /* R/W */ -//#define INT_EN_ERX_EN_ (0x00001000) /* R/W */ -#define INT_EN_TDFU_EN_ (0x00000800) /* R/W */ -#define INT_EN_TDFO_EN_ (0x00000400) /* R/W */ -#define INT_EN_TDFA_EN_ (0x00000200) /* R/W */ -#define INT_EN_TSFF_EN_ (0x00000100) /* R/W */ -#define INT_EN_TSFL_EN_ (0x00000080) /* R/W */ -//#define INT_EN_RXDF_EN_ (0x00000040) /* R/W */ -#define INT_EN_RDFO_EN_ (0x00000040) /* R/W */ -#define INT_EN_RDFL_EN_ (0x00000020) /* R/W */ -#define INT_EN_RSFF_EN_ (0x00000010) /* R/W */ -#define INT_EN_RSFL_EN_ (0x00000008) /* R/W */ -#define INT_EN_GPIO2_INT_ (0x00000004) /* R/W */ -#define INT_EN_GPIO1_INT_ (0x00000002) /* R/W */ -#define INT_EN_GPIO0_INT_ (0x00000001) /* R/W */ - -#define BYTE_TEST (0x64) -#define FIFO_INT (0x68) -#define FIFO_INT_TX_AVAIL_LEVEL_ (0xFF000000) /* R/W */ -#define FIFO_INT_TX_STS_LEVEL_ (0x00FF0000) /* R/W */ -#define FIFO_INT_RX_AVAIL_LEVEL_ (0x0000FF00) /* R/W */ -#define FIFO_INT_RX_STS_LEVEL_ (0x000000FF) /* R/W */ - -#define RX_CFG (0x6C) -#define RX_CFG_RX_END_ALGN_ (0xC0000000) /* R/W */ -#define RX_CFG_RX_END_ALGN4_ (0x00000000) /* R/W */ -#define RX_CFG_RX_END_ALGN16_ (0x40000000) /* R/W */ -#define RX_CFG_RX_END_ALGN32_ (0x80000000) /* R/W */ -#define RX_CFG_RX_DMA_CNT_ (0x0FFF0000) /* R/W */ -#define RX_CFG_RX_DUMP_ (0x00008000) /* R/W */ -#define RX_CFG_RXDOFF_ (0x00001F00) /* R/W */ -//#define RX_CFG_RXBAD_ (0x00000001) /* R/W */ - -#define TX_CFG (0x70) -//#define TX_CFG_TX_DMA_LVL_ (0xE0000000) /* R/W */ -//#define TX_CFG_TX_DMA_CNT_ (0x0FFF0000) /* R/W Self Clearing */ -#define TX_CFG_TXS_DUMP_ (0x00008000) /* Self Clearing */ -#define TX_CFG_TXD_DUMP_ (0x00004000) /* Self Clearing */ -#define TX_CFG_TXSAO_ (0x00000004) /* R/W */ -#define TX_CFG_TX_ON_ (0x00000002) /* R/W */ -#define TX_CFG_STOP_TX_ (0x00000001) /* Self Clearing */ - -#define HW_CFG (0x74) -#define HW_CFG_TTM_ (0x00200000) /* R/W */ -#define HW_CFG_SF_ (0x00100000) /* R/W */ -#define HW_CFG_TX_FIF_SZ_ (0x000F0000) /* R/W */ -#define HW_CFG_TR_ (0x00003000) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_ (0x00000060) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_INT_PHY_ (0x00000000) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_EXT_PHY_ (0x00000020) /* R/W */ -#define HW_CFG_PHY_CLK_SEL_CLK_DIS_ (0x00000040) /* R/W */ -#define HW_CFG_SMI_SEL_ (0x00000010) /* R/W */ -#define HW_CFG_EXT_PHY_DET_ (0x00000008) /* RO */ -#define HW_CFG_EXT_PHY_EN_ (0x00000004) /* R/W */ -#define HW_CFG_32_16_BIT_MODE_ (0x00000004) /* RO */ -#define HW_CFG_SRST_TO_ (0x00000002) /* RO */ -#define HW_CFG_SRST_ (0x00000001) /* Self Clearing */ - -#define RX_DP_CTRL (0x78) -#define RX_DP_CTRL_RX_FFWD_ (0x80000000) /* R/W */ -#define RX_DP_CTRL_FFWD_BUSY_ (0x80000000) /* RO */ - -#define RX_FIFO_INF (0x7C) -#define RX_FIFO_INF_RXSUSED_ (0x00FF0000) /* RO */ -#define RX_FIFO_INF_RXDUSED_ (0x0000FFFF) /* RO */ - -#define TX_FIFO_INF (0x80) -#define TX_FIFO_INF_TSUSED_ (0x00FF0000) /* RO */ -#define TX_FIFO_INF_TDFREE_ (0x0000FFFF) /* RO */ - -#define PMT_CTRL (0x84) -#define PMT_CTRL_PM_MODE_ (0x00003000) /* Self Clearing */ -#define PMT_CTRL_PHY_RST_ (0x00000400) /* Self Clearing */ -#define PMT_CTRL_WOL_EN_ (0x00000200) /* R/W */ -#define PMT_CTRL_ED_EN_ (0x00000100) /* R/W */ -#define PMT_CTRL_PME_TYPE_ (0x00000040) /* R/W Not Affected by SW Reset */ -#define PMT_CTRL_WUPS_ (0x00000030) /* R/WC */ -#define PMT_CTRL_WUPS_NOWAKE_ (0x00000000) /* R/WC */ -#define PMT_CTRL_WUPS_ED_ (0x00000010) /* R/WC */ -#define PMT_CTRL_WUPS_WOL_ (0x00000020) /* R/WC */ -#define PMT_CTRL_WUPS_MULTI_ (0x00000030) /* R/WC */ -#define PMT_CTRL_PME_IND_ (0x00000008) /* R/W */ -#define PMT_CTRL_PME_POL_ (0x00000004) /* R/W */ -#define PMT_CTRL_PME_EN_ (0x00000002) /* R/W Not Affected by SW Reset */ -#define PMT_CTRL_READY_ (0x00000001) /* RO */ - -#define GPIO_CFG (0x88) -#define GPIO_CFG_LED3_EN_ (0x40000000) /* R/W */ -#define GPIO_CFG_LED2_EN_ (0x20000000) /* R/W */ -#define GPIO_CFG_LED1_EN_ (0x10000000) /* R/W */ -#define GPIO_CFG_GPIO2_INT_POL_ (0x04000000) /* R/W */ -#define GPIO_CFG_GPIO1_INT_POL_ (0x02000000) /* R/W */ -#define GPIO_CFG_GPIO0_INT_POL_ (0x01000000) /* R/W */ -#define GPIO_CFG_EEPR_EN_ (0x00700000) /* R/W */ -#define GPIO_CFG_GPIOBUF2_ (0x00040000) /* R/W */ -#define GPIO_CFG_GPIOBUF1_ (0x00020000) /* R/W */ -#define GPIO_CFG_GPIOBUF0_ (0x00010000) /* R/W */ -#define GPIO_CFG_GPIODIR2_ (0x00000400) /* R/W */ -#define GPIO_CFG_GPIODIR1_ (0x00000200) /* R/W */ -#define GPIO_CFG_GPIODIR0_ (0x00000100) /* R/W */ -#define GPIO_CFG_GPIOD4_ (0x00000010) /* R/W */ -#define GPIO_CFG_GPIOD3_ (0x00000008) /* R/W */ -#define GPIO_CFG_GPIOD2_ (0x00000004) /* R/W */ -#define GPIO_CFG_GPIOD1_ (0x00000002) /* R/W */ -#define GPIO_CFG_GPIOD0_ (0x00000001) /* R/W */ - -#define GPT_CFG (0x8C) -#define GPT_CFG_TIMER_EN_ (0x20000000) /* R/W */ -#define GPT_CFG_GPT_LOAD_ (0x0000FFFF) /* R/W */ - -#define GPT_CNT (0x90) -#define GPT_CNT_GPT_CNT_ (0x0000FFFF) /* RO */ - -#define ENDIAN (0x98) -#define FREE_RUN (0x9C) -#define RX_DROP (0xA0) -#define MAC_CSR_CMD (0xA4) -#define MAC_CSR_CMD_CSR_BUSY_ (0x80000000) /* Self Clearing */ -#define MAC_CSR_CMD_R_NOT_W_ (0x40000000) /* R/W */ -#define MAC_CSR_CMD_CSR_ADDR_ (0x000000FF) /* R/W */ - -#define MAC_CSR_DATA (0xA8) -#define AFC_CFG (0xAC) -#define AFC_CFG_AFC_HI_ (0x00FF0000) /* R/W */ -#define AFC_CFG_AFC_LO_ (0x0000FF00) /* R/W */ -#define AFC_CFG_BACK_DUR_ (0x000000F0) /* R/W */ -#define AFC_CFG_FCMULT_ (0x00000008) /* R/W */ -#define AFC_CFG_FCBRD_ (0x00000004) /* R/W */ -#define AFC_CFG_FCADD_ (0x00000002) /* R/W */ -#define AFC_CFG_FCANY_ (0x00000001) /* R/W */ - -#define E2P_CMD (0xB0) -#define E2P_CMD_EPC_BUSY_ (0x80000000) /* Self Clearing */ -#define E2P_CMD_EPC_CMD_ (0x70000000) /* R/W */ -#define E2P_CMD_EPC_CMD_READ_ (0x00000000) /* R/W */ -#define E2P_CMD_EPC_CMD_EWDS_ (0x10000000) /* R/W */ -#define E2P_CMD_EPC_CMD_EWEN_ (0x20000000) /* R/W */ -#define E2P_CMD_EPC_CMD_WRITE_ (0x30000000) /* R/W */ -#define E2P_CMD_EPC_CMD_WRAL_ (0x40000000) /* R/W */ -#define E2P_CMD_EPC_CMD_ERASE_ (0x50000000) /* R/W */ -#define E2P_CMD_EPC_CMD_ERAL_ (0x60000000) /* R/W */ -#define E2P_CMD_EPC_CMD_RELOAD_ (0x70000000) /* R/W */ -#define E2P_CMD_EPC_TIMEOUT_ (0x00000200) /* RO */ -#define E2P_CMD_MAC_ADDR_LOADED_ (0x00000100) /* RO */ -#define E2P_CMD_EPC_ADDR_ (0x000000FF) /* R/W */ - -#define E2P_DATA (0xB4) -#define E2P_DATA_EEPROM_DATA_ (0x000000FF) /* R/W */ -/* end of LAN register offsets and bit definitions */ - -/* - **************************************************************************** - **************************************************************************** - * MAC Control and Status Register (Indirect Address) - * Offset (through the MAC_CSR CMD and DATA port) - **************************************************************************** - **************************************************************************** - * - */ -#define MAC_CR (0x01) /* R/W */ - -/* MAC_CR - MAC Control Register */ -#define MAC_CR_RXALL_ (0x80000000) -// TODO: delete this bit? It is not described in the data sheet. -#define MAC_CR_HBDIS_ (0x10000000) -#define MAC_CR_RCVOWN_ (0x00800000) -#define MAC_CR_LOOPBK_ (0x00200000) -#define MAC_CR_FDPX_ (0x00100000) -#define MAC_CR_MCPAS_ (0x00080000) -#define MAC_CR_PRMS_ (0x00040000) -#define MAC_CR_INVFILT_ (0x00020000) -#define MAC_CR_PASSBAD_ (0x00010000) -#define MAC_CR_HFILT_ (0x00008000) -#define MAC_CR_HPFILT_ (0x00002000) -#define MAC_CR_LCOLL_ (0x00001000) -#define MAC_CR_BCAST_ (0x00000800) -#define MAC_CR_DISRTY_ (0x00000400) -#define MAC_CR_PADSTR_ (0x00000100) -#define MAC_CR_BOLMT_MASK_ (0x000000C0) -#define MAC_CR_DFCHK_ (0x00000020) -#define MAC_CR_TXEN_ (0x00000008) -#define MAC_CR_RXEN_ (0x00000004) - -#define ADDRH (0x02) /* R/W mask 0x0000FFFFUL */ -#define ADDRL (0x03) /* R/W mask 0xFFFFFFFFUL */ -#define HASHH (0x04) /* R/W */ -#define HASHL (0x05) /* R/W */ - -#define MII_ACC (0x06) /* R/W */ -#define MII_ACC_PHY_ADDR_ (0x0000F800) -#define MII_ACC_MIIRINDA_ (0x000007C0) -#define MII_ACC_MII_WRITE_ (0x00000002) -#define MII_ACC_MII_BUSY_ (0x00000001) - -#define MII_DATA (0x07) /* R/W mask 0x0000FFFFUL */ - -#define FLOW (0x08) /* R/W */ -#define FLOW_FCPT_ (0xFFFF0000) -#define FLOW_FCPASS_ (0x00000004) -#define FLOW_FCEN_ (0x00000002) -#define FLOW_FCBSY_ (0x00000001) - -#define VLAN1 (0x09) /* R/W mask 0x0000FFFFUL */ -#define VLAN1_VTI1_ (0x0000ffff) - -#define VLAN2 (0x0A) /* R/W mask 0x0000FFFFUL */ -#define VLAN2_VTI2_ (0x0000ffff) - -#define WUFF (0x0B) /* WO */ - -#define WUCSR (0x0C) /* R/W */ -#define WUCSR_GUE_ (0x00000200) -#define WUCSR_WUFR_ (0x00000040) -#define WUCSR_MPR_ (0x00000020) -#define WUCSR_WAKE_EN_ (0x00000004) -#define WUCSR_MPEN_ (0x00000002) - -/* - **************************************************************************** - * Chip Specific MII Defines - **************************************************************************** - * - * Phy register offsets and bit definitions - * - */ - -#define PHY_MODE_CTRL_STS ((u32)17) /* Mode Control/Status Register */ -//#define MODE_CTRL_STS_FASTRIP_ ((u16)0x4000) -#define MODE_CTRL_STS_EDPWRDOWN_ ((u16)0x2000) -//#define MODE_CTRL_STS_LOWSQEN_ ((u16)0x0800) -//#define MODE_CTRL_STS_MDPREBP_ ((u16)0x0400) -//#define MODE_CTRL_STS_FARLOOPBACK_ ((u16)0x0200) -//#define MODE_CTRL_STS_FASTEST_ ((u16)0x0100) -//#define MODE_CTRL_STS_REFCLKEN_ ((u16)0x0010) -//#define MODE_CTRL_STS_PHYADBP_ ((u16)0x0008) -//#define MODE_CTRL_STS_FORCE_G_LINK_ ((u16)0x0004) -#define MODE_CTRL_STS_ENERGYON_ ((u16)0x0002) - -#define PHY_INT_SRC ((u32)29) -#define PHY_INT_SRC_ENERGY_ON_ ((u16)0x0080) -#define PHY_INT_SRC_ANEG_COMP_ ((u16)0x0040) -#define PHY_INT_SRC_REMOTE_FAULT_ ((u16)0x0020) -#define PHY_INT_SRC_LINK_DOWN_ ((u16)0x0010) -#define PHY_INT_SRC_ANEG_LP_ACK_ ((u16)0x0008) -#define PHY_INT_SRC_PAR_DET_FAULT_ ((u16)0x0004) -#define PHY_INT_SRC_ANEG_PGRX_ ((u16)0x0002) - -#define PHY_INT_MASK ((u32)30) -#define PHY_INT_MASK_ENERGY_ON_ ((u16)0x0080) -#define PHY_INT_MASK_ANEG_COMP_ ((u16)0x0040) -#define PHY_INT_MASK_REMOTE_FAULT_ ((u16)0x0020) -#define PHY_INT_MASK_LINK_DOWN_ ((u16)0x0010) -#define PHY_INT_MASK_ANEG_LP_ACK_ ((u16)0x0008) -#define PHY_INT_MASK_PAR_DET_FAULT_ ((u16)0x0004) -#define PHY_INT_MASK_ANEG_PGRX_ ((u16)0x0002) - -#define PHY_SPECIAL ((u32)31) -#define PHY_SPECIAL_ANEG_DONE_ ((u16)0x1000) -#define PHY_SPECIAL_RES_ ((u16)0x0040) -#define PHY_SPECIAL_RES_MASK_ ((u16)0x0FE1) -#define PHY_SPECIAL_SPD_ ((u16)0x001C) -#define PHY_SPECIAL_SPD_10HALF_ ((u16)0x0004) -#define PHY_SPECIAL_SPD_10FULL_ ((u16)0x0014) -#define PHY_SPECIAL_SPD_100HALF_ ((u16)0x0008) -#define PHY_SPECIAL_SPD_100FULL_ ((u16)0x0018) - -#define LAN911X_INTERNAL_PHY_ID (0x0007C000) - -/* Chip ID values */ -#define CHIP_9115 0x0115 -#define CHIP_9116 0x0116 -#define CHIP_9117 0x0117 -#define CHIP_9118 0x0118 -#define CHIP_9211 0x9211 -#define CHIP_9215 0x115A -#define CHIP_9217 0x117A -#define CHIP_9218 0x118A - -struct chip_id { - u16 id; - char *name; -}; - -static const struct chip_id chip_ids[] = { - { CHIP_9115, "LAN9115" }, - { CHIP_9116, "LAN9116" }, - { CHIP_9117, "LAN9117" }, - { CHIP_9118, "LAN9118" }, - { CHIP_9211, "LAN9211" }, - { CHIP_9215, "LAN9215" }, - { CHIP_9217, "LAN9217" }, - { CHIP_9218, "LAN9218" }, - { 0, NULL }, -}; - -#define IS_REV_A(x) ((x & 0xFFFF)==0) - -/* - * Macros to abstract register access according to the data bus - * capabilities. Please use those and not the in/out primitives. - */ -/* FIFO read/write macros */ -#define SMC_PUSH_DATA(lp, p, l) SMC_outsl( lp, TX_DATA_FIFO, p, (l) >> 2 ) -#define SMC_PULL_DATA(lp, p, l) SMC_insl ( lp, RX_DATA_FIFO, p, (l) >> 2 ) -#define SMC_SET_TX_FIFO(lp, x) SMC_outl( x, lp, TX_DATA_FIFO ) -#define SMC_GET_RX_FIFO(lp) SMC_inl( lp, RX_DATA_FIFO ) - - -/* I/O mapped register read/write macros */ -#define SMC_GET_TX_STS_FIFO(lp) SMC_inl( lp, TX_STATUS_FIFO ) -#define SMC_GET_RX_STS_FIFO(lp) SMC_inl( lp, RX_STATUS_FIFO ) -#define SMC_GET_RX_STS_FIFO_PEEK(lp) SMC_inl( lp, RX_STATUS_FIFO_PEEK ) -#define SMC_GET_PN(lp) (SMC_inl( lp, ID_REV ) >> 16) -#define SMC_GET_REV(lp) (SMC_inl( lp, ID_REV ) & 0xFFFF) -#define SMC_GET_IRQ_CFG(lp) SMC_inl( lp, INT_CFG ) -#define SMC_SET_IRQ_CFG(lp, x) SMC_outl( x, lp, INT_CFG ) -#define SMC_GET_INT(lp) SMC_inl( lp, INT_STS ) -#define SMC_ACK_INT(lp, x) SMC_outl( x, lp, INT_STS ) -#define SMC_GET_INT_EN(lp) SMC_inl( lp, INT_EN ) -#define SMC_SET_INT_EN(lp, x) SMC_outl( x, lp, INT_EN ) -#define SMC_GET_BYTE_TEST(lp) SMC_inl( lp, BYTE_TEST ) -#define SMC_SET_BYTE_TEST(lp, x) SMC_outl( x, lp, BYTE_TEST ) -#define SMC_GET_FIFO_INT(lp) SMC_inl( lp, FIFO_INT ) -#define SMC_SET_FIFO_INT(lp, x) SMC_outl( x, lp, FIFO_INT ) -#define SMC_SET_FIFO_TDA(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<24); \ - SMC_SET_FIFO_INT( (lp), __mask | (x)<<24 ); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_TSL(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<16); \ - SMC_SET_FIFO_INT( (lp), __mask | (((x) & 0xFF)<<16)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_RSA(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~(0xFF<<8); \ - SMC_SET_FIFO_INT( (lp), __mask | (((x) & 0xFF)<<8)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_SET_FIFO_RSL(lp, x) \ - do { \ - unsigned long __flags; \ - int __mask; \ - local_irq_save(__flags); \ - __mask = SMC_GET_FIFO_INT((lp)) & ~0xFF; \ - SMC_SET_FIFO_INT( (lp),__mask | ((x) & 0xFF)); \ - local_irq_restore(__flags); \ - } while (0) -#define SMC_GET_RX_CFG(lp) SMC_inl( lp, RX_CFG ) -#define SMC_SET_RX_CFG(lp, x) SMC_outl( x, lp, RX_CFG ) -#define SMC_GET_TX_CFG(lp) SMC_inl( lp, TX_CFG ) -#define SMC_SET_TX_CFG(lp, x) SMC_outl( x, lp, TX_CFG ) -#define SMC_GET_HW_CFG(lp) SMC_inl( lp, HW_CFG ) -#define SMC_SET_HW_CFG(lp, x) SMC_outl( x, lp, HW_CFG ) -#define SMC_GET_RX_DP_CTRL(lp) SMC_inl( lp, RX_DP_CTRL ) -#define SMC_SET_RX_DP_CTRL(lp, x) SMC_outl( x, lp, RX_DP_CTRL ) -#define SMC_GET_PMT_CTRL(lp) SMC_inl( lp, PMT_CTRL ) -#define SMC_SET_PMT_CTRL(lp, x) SMC_outl( x, lp, PMT_CTRL ) -#define SMC_GET_GPIO_CFG(lp) SMC_inl( lp, GPIO_CFG ) -#define SMC_SET_GPIO_CFG(lp, x) SMC_outl( x, lp, GPIO_CFG ) -#define SMC_GET_RX_FIFO_INF(lp) SMC_inl( lp, RX_FIFO_INF ) -#define SMC_SET_RX_FIFO_INF(lp, x) SMC_outl( x, lp, RX_FIFO_INF ) -#define SMC_GET_TX_FIFO_INF(lp) SMC_inl( lp, TX_FIFO_INF ) -#define SMC_SET_TX_FIFO_INF(lp, x) SMC_outl( x, lp, TX_FIFO_INF ) -#define SMC_GET_GPT_CFG(lp) SMC_inl( lp, GPT_CFG ) -#define SMC_SET_GPT_CFG(lp, x) SMC_outl( x, lp, GPT_CFG ) -#define SMC_GET_RX_DROP(lp) SMC_inl( lp, RX_DROP ) -#define SMC_SET_RX_DROP(lp, x) SMC_outl( x, lp, RX_DROP ) -#define SMC_GET_MAC_CMD(lp) SMC_inl( lp, MAC_CSR_CMD ) -#define SMC_SET_MAC_CMD(lp, x) SMC_outl( x, lp, MAC_CSR_CMD ) -#define SMC_GET_MAC_DATA(lp) SMC_inl( lp, MAC_CSR_DATA ) -#define SMC_SET_MAC_DATA(lp, x) SMC_outl( x, lp, MAC_CSR_DATA ) -#define SMC_GET_AFC_CFG(lp) SMC_inl( lp, AFC_CFG ) -#define SMC_SET_AFC_CFG(lp, x) SMC_outl( x, lp, AFC_CFG ) -#define SMC_GET_E2P_CMD(lp) SMC_inl( lp, E2P_CMD ) -#define SMC_SET_E2P_CMD(lp, x) SMC_outl( x, lp, E2P_CMD ) -#define SMC_GET_E2P_DATA(lp) SMC_inl( lp, E2P_DATA ) -#define SMC_SET_E2P_DATA(lp, x) SMC_outl( x, lp, E2P_DATA ) - -/* MAC register read/write macros */ -#define SMC_GET_MAC_CSR(lp,a,v) \ - do { \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_CMD((lp),MAC_CSR_CMD_CSR_BUSY_ | \ - MAC_CSR_CMD_R_NOT_W_ | (a) ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - v = SMC_GET_MAC_DATA((lp)); \ - } while (0) -#define SMC_SET_MAC_CSR(lp,a,v) \ - do { \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_DATA((lp), v); \ - SMC_SET_MAC_CMD((lp), MAC_CSR_CMD_CSR_BUSY_ | (a) ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - } while (0) -#define SMC_GET_MAC_CR(lp, x) SMC_GET_MAC_CSR( (lp), MAC_CR, x ) -#define SMC_SET_MAC_CR(lp, x) SMC_SET_MAC_CSR( (lp), MAC_CR, x ) -#define SMC_GET_ADDRH(lp, x) SMC_GET_MAC_CSR( (lp), ADDRH, x ) -#define SMC_SET_ADDRH(lp, x) SMC_SET_MAC_CSR( (lp), ADDRH, x ) -#define SMC_GET_ADDRL(lp, x) SMC_GET_MAC_CSR( (lp), ADDRL, x ) -#define SMC_SET_ADDRL(lp, x) SMC_SET_MAC_CSR( (lp), ADDRL, x ) -#define SMC_GET_HASHH(lp, x) SMC_GET_MAC_CSR( (lp), HASHH, x ) -#define SMC_SET_HASHH(lp, x) SMC_SET_MAC_CSR( (lp), HASHH, x ) -#define SMC_GET_HASHL(lp, x) SMC_GET_MAC_CSR( (lp), HASHL, x ) -#define SMC_SET_HASHL(lp, x) SMC_SET_MAC_CSR( (lp), HASHL, x ) -#define SMC_GET_MII_ACC(lp, x) SMC_GET_MAC_CSR( (lp), MII_ACC, x ) -#define SMC_SET_MII_ACC(lp, x) SMC_SET_MAC_CSR( (lp), MII_ACC, x ) -#define SMC_GET_MII_DATA(lp, x) SMC_GET_MAC_CSR( (lp), MII_DATA, x ) -#define SMC_SET_MII_DATA(lp, x) SMC_SET_MAC_CSR( (lp), MII_DATA, x ) -#define SMC_GET_FLOW(lp, x) SMC_GET_MAC_CSR( (lp), FLOW, x ) -#define SMC_SET_FLOW(lp, x) SMC_SET_MAC_CSR( (lp), FLOW, x ) -#define SMC_GET_VLAN1(lp, x) SMC_GET_MAC_CSR( (lp), VLAN1, x ) -#define SMC_SET_VLAN1(lp, x) SMC_SET_MAC_CSR( (lp), VLAN1, x ) -#define SMC_GET_VLAN2(lp, x) SMC_GET_MAC_CSR( (lp), VLAN2, x ) -#define SMC_SET_VLAN2(lp, x) SMC_SET_MAC_CSR( (lp), VLAN2, x ) -#define SMC_SET_WUFF(lp, x) SMC_SET_MAC_CSR( (lp), WUFF, x ) -#define SMC_GET_WUCSR(lp, x) SMC_GET_MAC_CSR( (lp), WUCSR, x ) -#define SMC_SET_WUCSR(lp, x) SMC_SET_MAC_CSR( (lp), WUCSR, x ) - -/* PHY register read/write macros */ -#define SMC_GET_MII(lp,a,phy,v) \ - do { \ - u32 __v; \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_SET_MII_ACC( (lp), ((phy)<<11) | ((a)<<6) | \ - MII_ACC_MII_BUSY_); \ - do { \ - SMC_GET_MII_ACC( (lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_GET_MII_DATA((lp), v); \ - } while (0) -#define SMC_SET_MII(lp,a,phy,v) \ - do { \ - u32 __v; \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - SMC_SET_MII_DATA((lp), v); \ - SMC_SET_MII_ACC( (lp), ((phy)<<11) | ((a)<<6) | \ - MII_ACC_MII_BUSY_ | \ - MII_ACC_MII_WRITE_ ); \ - do { \ - SMC_GET_MII_ACC((lp), __v); \ - } while ( __v & MII_ACC_MII_BUSY_ ); \ - } while (0) -#define SMC_GET_PHY_BMCR(lp,phy,x) SMC_GET_MII( (lp), MII_BMCR, phy, x ) -#define SMC_SET_PHY_BMCR(lp,phy,x) SMC_SET_MII( (lp), MII_BMCR, phy, x ) -#define SMC_GET_PHY_BMSR(lp,phy,x) SMC_GET_MII( (lp), MII_BMSR, phy, x ) -#define SMC_GET_PHY_ID1(lp,phy,x) SMC_GET_MII( (lp), MII_PHYSID1, phy, x ) -#define SMC_GET_PHY_ID2(lp,phy,x) SMC_GET_MII( (lp), MII_PHYSID2, phy, x ) -#define SMC_GET_PHY_MII_ADV(lp,phy,x) SMC_GET_MII( (lp), MII_ADVERTISE, phy, x ) -#define SMC_SET_PHY_MII_ADV(lp,phy,x) SMC_SET_MII( (lp), MII_ADVERTISE, phy, x ) -#define SMC_GET_PHY_MII_LPA(lp,phy,x) SMC_GET_MII( (lp), MII_LPA, phy, x ) -#define SMC_SET_PHY_MII_LPA(lp,phy,x) SMC_SET_MII( (lp), MII_LPA, phy, x ) -#define SMC_GET_PHY_CTRL_STS(lp,phy,x) SMC_GET_MII( (lp), PHY_MODE_CTRL_STS, phy, x ) -#define SMC_SET_PHY_CTRL_STS(lp,phy,x) SMC_SET_MII( (lp), PHY_MODE_CTRL_STS, phy, x ) -#define SMC_GET_PHY_INT_SRC(lp,phy,x) SMC_GET_MII( (lp), PHY_INT_SRC, phy, x ) -#define SMC_SET_PHY_INT_SRC(lp,phy,x) SMC_SET_MII( (lp), PHY_INT_SRC, phy, x ) -#define SMC_GET_PHY_INT_MASK(lp,phy,x) SMC_GET_MII( (lp), PHY_INT_MASK, phy, x ) -#define SMC_SET_PHY_INT_MASK(lp,phy,x) SMC_SET_MII( (lp), PHY_INT_MASK, phy, x ) -#define SMC_GET_PHY_SPECIAL(lp,phy,x) SMC_GET_MII( (lp), PHY_SPECIAL, phy, x ) - - - -/* Misc read/write macros */ - -#ifndef SMC_GET_MAC_ADDR -#define SMC_GET_MAC_ADDR(lp, addr) \ - do { \ - unsigned int __v; \ - \ - SMC_GET_MAC_CSR((lp), ADDRL, __v); \ - addr[0] = __v; addr[1] = __v >> 8; \ - addr[2] = __v >> 16; addr[3] = __v >> 24; \ - SMC_GET_MAC_CSR((lp), ADDRH, __v); \ - addr[4] = __v; addr[5] = __v >> 8; \ - } while (0) -#endif - -#define SMC_SET_MAC_ADDR(lp, addr) \ - do { \ - SMC_SET_MAC_CSR((lp), ADDRL, \ - addr[0] | \ - (addr[1] << 8) | \ - (addr[2] << 16) | \ - (addr[3] << 24)); \ - SMC_SET_MAC_CSR((lp), ADDRH, addr[4]|(addr[5] << 8));\ - } while (0) - - -#define SMC_WRITE_EEPROM_CMD(lp, cmd, addr) \ - do { \ - while (SMC_GET_E2P_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - SMC_SET_MAC_CMD((lp), MAC_CSR_CMD_R_NOT_W_ | a ); \ - while (SMC_GET_MAC_CMD((lp)) & MAC_CSR_CMD_CSR_BUSY_); \ - } while (0) - -#endif /* _SMC911X_H_ */ diff --git a/include/linux/smc911x.h b/include/linux/smc911x.h deleted file mode 100644 index 8cace8189e74..000000000000 --- a/include/linux/smc911x.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __SMC911X_H__ -#define __SMC911X_H__ - -#define SMC911X_USE_16BIT (1 << 0) -#define SMC911X_USE_32BIT (1 << 1) - -struct smc911x_platdata { - unsigned long flags; - unsigned long irq_flags; /* IRQF_... */ - int irq_polarity; -}; - -#endif /* __SMC911X_H__ */ -- cgit v1.2.3 From f392a1846489720fc2e063d1210633b6cf4ec5a4 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 17 Oct 2022 16:22:35 -0400 Subject: net: phylink: provide phylink_validate_mask_caps() helper Provide a helper that restricts the link modes according to the phylink capabilities. Signed-off-by: Russell King (Oracle) [rebased on net-next/master and added documentation] Signed-off-by: Sean Anderson Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 41 +++++++++++++++++++++++++++++------------ include/linux/phylink.h | 3 +++ 2 files changed, 32 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 75464df191ef..ef10f5a70e5a 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -562,31 +562,48 @@ unsigned long phylink_get_capabilities(phy_interface_t interface, EXPORT_SYMBOL_GPL(phylink_get_capabilities); /** - * phylink_generic_validate() - generic validate() callback implementation - * @config: a pointer to a &struct phylink_config. + * phylink_validate_mask_caps() - Restrict link modes based on caps * @supported: ethtool bitmask for supported link modes. - * @state: a pointer to a &struct phylink_link_state. + * @state: an (optional) pointer to a &struct phylink_link_state. + * @mac_capabilities: bitmask of MAC capabilities * - * Generic implementation of the validate() callback that MAC drivers can - * use when they pass the range of supported interfaces and MAC capabilities. - * This makes use of phylink_get_linkmodes(). + * Calculate the supported link modes based on @mac_capabilities, and restrict + * @supported and @state based on that. Use this function if your capabiliies + * aren't constant, such as if they vary depending on the interface. */ -void phylink_generic_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +void phylink_validate_mask_caps(unsigned long *supported, + struct phylink_link_state *state, + unsigned long mac_capabilities) { __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; unsigned long caps; phylink_set_port_modes(mask); phylink_set(mask, Autoneg); - caps = phylink_get_capabilities(state->interface, - config->mac_capabilities, + caps = phylink_get_capabilities(state->interface, mac_capabilities, state->rate_matching); phylink_caps_to_linkmodes(mask, caps); linkmode_and(supported, supported, mask); - linkmode_and(state->advertising, state->advertising, mask); + if (state) + linkmode_and(state->advertising, state->advertising, mask); +} +EXPORT_SYMBOL_GPL(phylink_validate_mask_caps); + +/** + * phylink_generic_validate() - generic validate() callback implementation + * @config: a pointer to a &struct phylink_config. + * @supported: ethtool bitmask for supported link modes. + * @state: a pointer to a &struct phylink_link_state. + * + * Generic implementation of the validate() callback that MAC drivers can + * use when they pass the range of supported interfaces and MAC capabilities. + */ +void phylink_generic_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + phylink_validate_mask_caps(supported, state, config->mac_capabilities); } EXPORT_SYMBOL_GPL(phylink_generic_validate); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 664dd409feb9..c29c3f174972 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -556,6 +556,9 @@ void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); unsigned long phylink_get_capabilities(phy_interface_t interface, unsigned long mac_capabilities, int rate_matching); +void phylink_validate_mask_caps(unsigned long *supported, + struct phylink_link_state *state, + unsigned long caps); void phylink_generic_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -- cgit v1.2.3 From 51c352bdbcd23d7ce46b06c1e64c82754dc44044 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 18 Oct 2022 15:37:27 +0100 Subject: netlink: add support for formatted extack messages Include an 80-byte buffer in struct netlink_ext_ack that can be used for scnprintf()ed messages. This does mean that the resulting string can't be enumerated, translated etc. in the way NL_SET_ERR_MSG() was designed to allow. Signed-off-by: Edward Cree Reviewed-by: Jakub Kicinski Signed-off-by: Jakub Kicinski --- include/linux/netlink.h | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index d51e041d2242..d81bde5a5844 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -64,6 +64,7 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) /* this can be increased when necessary - don't expose to userland */ #define NETLINK_MAX_COOKIE_LEN 20 +#define NETLINK_MAX_FMTMSG_LEN 80 /** * struct netlink_ext_ack - netlink extended ACK report struct @@ -75,6 +76,8 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) * @miss_nest: nest missing an attribute (%NULL if missing top level attr) * @cookie: cookie data to return to userspace (for success) * @cookie_len: actual cookie data length + * @_msg_buf: output buffer for formatted message strings - don't access + * directly, use %NL_SET_ERR_MSG_FMT */ struct netlink_ext_ack { const char *_msg; @@ -84,13 +87,13 @@ struct netlink_ext_ack { u16 miss_type; u8 cookie[NETLINK_MAX_COOKIE_LEN]; u8 cookie_len; + char _msg_buf[NETLINK_MAX_FMTMSG_LEN]; }; /* Always use this macro, this allows later putting the * message into a separate section or such for things * like translation or listing all possible messages. - * Currently string formatting is not supported (due - * to the lack of an output buffer.) + * If string formatting is needed use NL_SET_ERR_MSG_FMT. */ #define NL_SET_ERR_MSG(extack, msg) do { \ static const char __msg[] = msg; \ @@ -102,9 +105,31 @@ struct netlink_ext_ack { __extack->_msg = __msg; \ } while (0) +/* We splice fmt with %s at each end even in the snprintf so that both calls + * can use the same string constant, avoiding its duplication in .ro + */ +#define NL_SET_ERR_MSG_FMT(extack, fmt, args...) do { \ + struct netlink_ext_ack *__extack = (extack); \ + \ + if (!__extack) \ + break; \ + if (snprintf(__extack->_msg_buf, NETLINK_MAX_FMTMSG_LEN, \ + "%s" fmt "%s", "", ##args, "") >= \ + NETLINK_MAX_FMTMSG_LEN) \ + net_warn_ratelimited("%s" fmt "%s", "truncated extack: ", \ + ##args, "\n"); \ + \ + do_trace_netlink_extack(__extack->_msg_buf); \ + \ + __extack->_msg = __extack->_msg_buf; \ +} while (0) + #define NL_SET_ERR_MSG_MOD(extack, msg) \ NL_SET_ERR_MSG((extack), KBUILD_MODNAME ": " msg) +#define NL_SET_ERR_MSG_FMT_MOD(extack, fmt, args...) \ + NL_SET_ERR_MSG_FMT((extack), KBUILD_MODNAME ": " fmt, ##args) + #define NL_SET_BAD_ATTR_POLICY(extack, attr, pol) do { \ if ((extack)) { \ (extack)->bad_attr = (attr); \ -- cgit v1.2.3 From 6fdfdef7fdb57e6b9f768c9ca0718dcb5e727a85 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Wed, 19 Oct 2022 21:07:33 +0300 Subject: sctp: remove unnecessary NULL check in sctp_association_init() '&asoc->ulpq' passed to sctp_ulpq_init() as the first argument, then sctp_qlpq_init() initializes it and eventually returns the address of the struct member back. Therefore, in this case, the return pointer cannot be NULL. Moreover, it seems sctp_ulpq_init() has always been used only in sctp_association_init(), so there's really no need to return ulpq anymore. Detected using the static analysis tool - Svace. Signed-off-by: Alexey Kodanev Reviewed-by: Xin Long Link: https://lore.kernel.org/r/20221019180735.161388-1-aleksei.kodanev@bell-sw.com Signed-off-by: Jakub Kicinski --- include/net/sctp/ulpqueue.h | 3 +-- net/sctp/associola.c | 4 +--- net/sctp/ulpqueue.c | 5 +---- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index 0eaf8650e3b2..60f6641290c3 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -35,8 +35,7 @@ struct sctp_ulpq { }; /* Prototypes. */ -struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *, - struct sctp_association *); +void sctp_ulpq_init(struct sctp_ulpq *ulpq, struct sctp_association *asoc); void sctp_ulpq_flush(struct sctp_ulpq *ulpq); void sctp_ulpq_free(struct sctp_ulpq *); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 3460abceba44..63ba5551c13f 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -226,8 +226,7 @@ static struct sctp_association *sctp_association_init( /* Create an output queue. */ sctp_outq_init(asoc, &asoc->outqueue); - if (!sctp_ulpq_init(&asoc->ulpq, asoc)) - goto fail_init; + sctp_ulpq_init(&asoc->ulpq, asoc); if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) goto stream_free; @@ -277,7 +276,6 @@ static struct sctp_association *sctp_association_init( stream_free: sctp_stream_free(&asoc->stream); -fail_init: sock_put(asoc->base.sk); sctp_endpoint_put(asoc->ep); return NULL; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 0a8510a0c5e6..24960dcb6a21 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -38,8 +38,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq); /* 1st Level Abstractions */ /* Initialize a ULP queue from a block of memory. */ -struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq, - struct sctp_association *asoc) +void sctp_ulpq_init(struct sctp_ulpq *ulpq, struct sctp_association *asoc) { memset(ulpq, 0, sizeof(struct sctp_ulpq)); @@ -48,8 +47,6 @@ struct sctp_ulpq *sctp_ulpq_init(struct sctp_ulpq *ulpq, skb_queue_head_init(&ulpq->reasm_uo); skb_queue_head_init(&ulpq->lobby); ulpq->pd_mode = 0; - - return ulpq; } -- cgit v1.2.3 From 1f8c4eeb945553baf868bbec7a8c59810df97a07 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Oct 2022 15:36:02 -0700 Subject: inet6: Remove inet6_destroy_sock(). The last user of inet6_destroy_sock() is its wrapper inet6_cleanup_sock(). Let's rename inet6_destroy_sock() to inet6_cleanup_sock(). Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/transp_v6.h | 2 -- net/ipv6/af_inet6.c | 8 +------- 2 files changed, 1 insertion(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index b830463e3dff..d27b1caf3753 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -58,8 +58,6 @@ ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006) -void inet6_destroy_sock(struct sock *sk); - #define IPV6_SEQ_DGRAM_HEADER \ " sl " \ "local_address " \ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6540551ea7ec..68075295d587 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -490,7 +490,7 @@ int inet6_release(struct socket *sock) } EXPORT_SYMBOL(inet6_release); -void inet6_destroy_sock(struct sock *sk) +void inet6_cleanup_sock(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; @@ -515,12 +515,6 @@ void inet6_destroy_sock(struct sock *sk) txopt_put(opt); } } -EXPORT_SYMBOL_GPL(inet6_destroy_sock); - -void inet6_cleanup_sock(struct sock *sk) -{ - inet6_destroy_sock(sk); -} EXPORT_SYMBOL_GPL(inet6_cleanup_sock); /* -- cgit v1.2.3 From 404c76783f322120266a4ef659abe418dc74f5c6 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 20 Oct 2022 17:20:03 +0200 Subject: ethtool: Add support for 800Gbps link modes Add support for 800Gbps speed, link modes of 100Gbps per lane. As mentioned in slide 21 in IEEE documentation [1], all adopted 802.3df copper and optical PMDs baselines using 100G/lane will be supported. Add the relevant PMDs which are mentioned in slide 5 in IEEE documentation [1] and were approved on 10-2022 [2]: BP - KR8 Cu Cable - CR8 MMF 50m - VR8 MMF 100m - SR8 SMF 500m - DR8 SMF 2km - DR8-2 [1]: https://www.ieee802.org/3/df/public/22_10/22_1004/shrikhande_3df_01a_221004.pdf [2]: https://ieee802.org/3/df/KeyMotions_3df_221005.pdf Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 11 ++++++++++- include/uapi/linux/ethtool.h | 8 ++++++++ net/ethtool/common.c | 14 ++++++++++++++ 3 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 2c8bf438ea61..5d08c627a516 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -13,7 +13,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 93, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 99, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -49,6 +49,8 @@ const char *phy_speed_to_str(int speed) return "200Gbps"; case SPEED_400000: return "400Gbps"; + case SPEED_800000: + return "800Gbps"; case SPEED_UNKNOWN: return "Unknown"; default: @@ -157,6 +159,13 @@ EXPORT_SYMBOL_GPL(phy_interface_num_ports); .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT} static const struct phy_setting settings[] = { + /* 800G */ + PHY_SETTING( 800000, FULL, 800000baseCR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseKR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseDR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseDR8_2_Full ), + PHY_SETTING( 800000, FULL, 800000baseSR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseVR8_Full ), /* 400G */ PHY_SETTING( 400000, FULL, 400000baseCR8_Full ), PHY_SETTING( 400000, FULL, 400000baseKR8_Full ), diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index dc2aa3d75b39..f341de2ae612 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1737,6 +1737,13 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, + ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT = 93, + ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT = 94, + ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT = 95, + ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, + ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, + ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, + /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; @@ -1848,6 +1855,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_100000 100000 #define SPEED_200000 200000 #define SPEED_400000 400000 +#define SPEED_800000 800000 #define SPEED_UNKNOWN -1 diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 566adf85e658..ee3e02da0013 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -202,6 +202,12 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(100, FX, Half), __DEFINE_LINK_MODE_NAME(100, FX, Full), __DEFINE_LINK_MODE_NAME(10, T1L, Full), + __DEFINE_LINK_MODE_NAME(800000, CR8, Full), + __DEFINE_LINK_MODE_NAME(800000, KR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8_2, Full), + __DEFINE_LINK_MODE_NAME(800000, SR8, Full), + __DEFINE_LINK_MODE_NAME(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -238,6 +244,8 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_X 1 #define __LINK_MODE_LANES_FX 1 #define __LINK_MODE_LANES_T1L 1 +#define __LINK_MODE_LANES_VR8 8 +#define __LINK_MODE_LANES_DR8_2 8 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -352,6 +360,12 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(100, FX, Half), __DEFINE_LINK_MODE_PARAMS(100, FX, Full), __DEFINE_LINK_MODE_PARAMS(10, T1L, Full), + __DEFINE_LINK_MODE_PARAMS(800000, CR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), + __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); -- cgit v1.2.3 From a5ef058dc4d9a3e60d1808a0700e18e0e37e408e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 20 Oct 2022 19:48:51 +0200 Subject: net: introduce and use custom sockopt socket flag We will soon introduce custom setsockopt for UDP sockets, too. Instead of doing even more complex arbitrary checks inside sock_use_custom_sol_socket(), add a new socket flag and set it for the relevant socket types (currently only MPTCP). Reviewed-by: Matthieu Baerts Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Acked-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/net.h | 1 + net/mptcp/protocol.c | 4 ++++ net/socket.c | 8 +------- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/net.h b/include/linux/net.h index 711c3593c3b8..59350fd85823 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -41,6 +41,7 @@ struct net; #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 +#define SOCK_CUSTOM_SOCKOPT 5 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2e16c897c229..e60d144bfb2d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2708,6 +2708,8 @@ static int mptcp_init_sock(struct sock *sk) if (ret) return ret; + set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); + /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */ @@ -3684,6 +3686,8 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct mptcp_subflow_context *subflow; struct sock *newsk = newsock->sk; + set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); + lock_sock(newsk); /* PM/worker can now acquire the first subflow socket diff --git a/net/socket.c b/net/socket.c index 00da9ce3dba0..55c5d536e5f6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2199,13 +2199,7 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, static bool sock_use_custom_sol_socket(const struct socket *sock) { - const struct sock *sk = sock->sk; - - /* Use sock->ops->setsockopt() for MPTCP */ - return IS_ENABLED(CONFIG_MPTCP) && - sk->sk_protocol == IPPROTO_MPTCP && - sk->sk_type == SOCK_STREAM && - (sk->sk_family == AF_INET || sk->sk_family == AF_INET6); + return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } /* -- cgit v1.2.3 From 8a3854c7b8e4532063b14bed34115079b7d0cb36 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 20 Oct 2022 19:48:52 +0200 Subject: udp: track the forward memory release threshold in an hot cacheline When the receiver process and the BH runs on different cores, udp_rmem_release() experience a cache miss while accessing sk_rcvbuf, as the latter shares the same cacheline with sk_forward_alloc, written by the BH. With this patch, UDP tracks the rcvbuf value and its update via custom SOL_SOCKET socket options, and copies the forward memory threshold value used by udp_rmem_release() in a different cacheline, already accessed by the above function and uncontended. Since the UDP socket init operation grown a bit, factor out the common code between v4 and v6 in a shared helper. Overall the above give a 10% peek throughput increase under UDP flood. Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Acked-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/linux/udp.h | 3 +++ include/net/udp.h | 9 +++++++++ net/ipv4/udp.c | 18 +++++++++++++++--- net/ipv6/udp.c | 4 ++-- 4 files changed, 29 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/udp.h b/include/linux/udp.h index e96da4157d04..5cdba00a904a 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -87,6 +87,9 @@ struct udp_sock { /* This field is dirtied by udp_recvmsg() */ int forward_deficit; + + /* This fields follows rcvbuf value, and is touched by udp_recvmsg */ + int forward_threshold; }; #define UDP_MAX_SEGMENTS (1 << 6UL) diff --git a/include/net/udp.h b/include/net/udp.h index fee053bcd17c..de4b528522bb 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -174,6 +174,15 @@ INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); +static inline void udp_lib_init_sock(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + + skb_queue_head_init(&up->reader_queue); + up->forward_threshold = sk->sk_rcvbuf >> 2; + set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); +} + /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c83e5271030b..e77c8f0e9087 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1448,7 +1448,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && + if (size < READ_ONCE(up->forward_threshold) && !skb_queue_empty(&up->reader_queue)) return; } else { @@ -1622,7 +1622,7 @@ static void udp_destruct_sock(struct sock *sk) int udp_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udp_destruct_sock; return 0; } @@ -2671,6 +2671,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, int err = 0; int is_udplite = IS_UDPLITE(sk); + if (level == SOL_SOCKET) { + err = sk_setsockopt(sk, level, optname, optval, optlen); + + if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) { + sockopt_lock_sock(sk); + /* paired with READ_ONCE in udp_rmem_release() */ + WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2); + sockopt_release_sock(sk); + } + return err; + } + if (optlen < sizeof(int)) return -EINVAL; @@ -2784,7 +2796,7 @@ EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_push_pending_frames); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2260406740d3..297f7cc06044 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -64,7 +64,7 @@ static void udpv6_destruct_sock(struct sock *sk) int udpv6_init_sock(struct sock *sk) { - skb_queue_head_init(&udp_sk(sk)->reader_queue); + udp_lib_init_sock(sk); sk->sk_destruct = udpv6_destruct_sock; return 0; } @@ -1669,7 +1669,7 @@ void udpv6_destroy_sock(struct sock *sk) int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) return udp_lib_setsockopt(sk, level, optname, optval, optlen, udp_v6_push_pending_frames); -- cgit v1.2.3 From 0cafd77dcd032d1687efaba5598cf07bce85997f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 20 Oct 2022 23:20:18 +0000 Subject: net: add a refcount tracker for kernel sockets Commit ffa84b5ffb37 ("net: add netns refcount tracker to struct sock") added a tracker to sockets, but did not track kernel sockets. We still have syzbot reports hinting about netns being destroyed while some kernel TCP sockets had not been dismantled. This patch tracks kernel sockets, and adds a ref_tracker_dir_print() call to net_free() right before the netns is freed. Normally, each layer is responsible for properly releasing its kernel sockets before last call to net_free(). This debugging facility is enabled with CONFIG_NET_NS_REFCNT_TRACKER=y Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Tested-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/net_namespace.h | 30 ++++++++++++++++++++++-------- net/core/net_namespace.c | 5 +++++ net/core/sock.c | 14 ++++++++++++++ net/netlink/af_netlink.c | 11 +++++++++++ net/rds/tcp.c | 3 +++ 5 files changed, 55 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 8c3587d5c308..78beaa765c73 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -92,7 +92,9 @@ struct net { struct ns_common ns; struct ref_tracker_dir refcnt_tracker; - + struct ref_tracker_dir notrefcnt_tracker; /* tracker for objects not + * refcounted against netns + */ struct list_head dev_base_head; struct proc_dir_entry *proc_net; struct proc_dir_entry *proc_net_stat; @@ -320,19 +322,31 @@ static inline int check_net(const struct net *net) #endif -static inline void netns_tracker_alloc(struct net *net, - netns_tracker *tracker, gfp_t gfp) +static inline void __netns_tracker_alloc(struct net *net, + netns_tracker *tracker, + bool refcounted, + gfp_t gfp) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER - ref_tracker_alloc(&net->refcnt_tracker, tracker, gfp); + ref_tracker_alloc(refcounted ? &net->refcnt_tracker : + &net->notrefcnt_tracker, + tracker, gfp); #endif } -static inline void netns_tracker_free(struct net *net, - netns_tracker *tracker) +static inline void netns_tracker_alloc(struct net *net, netns_tracker *tracker, + gfp_t gfp) +{ + __netns_tracker_alloc(net, tracker, true, gfp); +} + +static inline void __netns_tracker_free(struct net *net, + netns_tracker *tracker, + bool refcounted) { #ifdef CONFIG_NET_NS_REFCNT_TRACKER - ref_tracker_free(&net->refcnt_tracker, tracker); + ref_tracker_free(refcounted ? &net->refcnt_tracker : + &net->notrefcnt_tracker, tracker); #endif } @@ -346,7 +360,7 @@ static inline struct net *get_net_track(struct net *net, static inline void put_net_track(struct net *net, netns_tracker *tracker) { - netns_tracker_free(net, tracker); + __netns_tracker_free(net, tracker, true); put_net(net); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 0ec2f5906a27..12c68edf7682 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -309,6 +309,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128); + ref_tracker_dir_init(&net->notrefcnt_tracker, 128); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); @@ -429,6 +430,10 @@ static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); + + /* There should not be any trackers left there. */ + ref_tracker_dir_exit(&net->notrefcnt_tracker); + kmem_cache_free(net_cachep, net); } } diff --git a/net/core/sock.c b/net/core/sock.c index a3ba0358c77c..aa608dc0930b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2094,6 +2094,9 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); + } else { + __netns_tracker_alloc(net, &sk->ns_tracker, + false, priority); } sock_net_set(sk, net); @@ -2149,6 +2152,9 @@ static void __sk_destruct(struct rcu_head *head) if (likely(sk->sk_net_refcnt)) put_net_track(sock_net(sk), &sk->ns_tracker); + else + __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); + sk_prot_free(sk->sk_prot_creator, sk); } @@ -2237,6 +2243,14 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) if (likely(newsk->sk_net_refcnt)) { get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); + } else { + /* Kernel sockets are not elevating the struct net refcount. + * Instead, use a tracker to more easily detect if a layer + * is not properly dismantling its kernel sockets at netns + * destroy time. + */ + __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, + false, priority); } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a662e8a5ff84..f0c94d394ab1 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -812,6 +812,17 @@ static int netlink_release(struct socket *sock) } sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1); + + /* Because struct net might disappear soon, do not keep a pointer. */ + if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) { + __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false); + /* Because of deferred_put_nlk_sk and use of work queue, + * it is possible netns will be freed before this socket. + */ + sock_net_set(sk, &init_net); + __netns_tracker_alloc(&init_net, &sk->ns_tracker, + false, GFP_KERNEL); + } call_rcu(&nlk->rcu, deferred_put_nlk_sk); return 0; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 4444fd82b66d..c5b86066ff66 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -503,6 +503,9 @@ bool rds_tcp_tune(struct socket *sock) release_sock(sk); return false; } + /* Update ns_tracker to current stack trace and refcounted tracker */ + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); -- cgit v1.2.3 From 233baf9a1bc46f18ad3bec688f52ea5f818a8a25 Mon Sep 17 00:00:00 2001 From: xu xin Date: Thu, 20 Oct 2022 06:54:41 +0000 Subject: net: remove useless parameter of __sock_cmsg_send The parameter 'msg' has never been used by __sock_cmsg_send, so we can remove it safely. Reported-by: Zeal Robot Signed-off-by: xu xin Reviewed-by: Zhang Yunkai Acked-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- net/core/sock.c | 4 ++-- net/ipv4/ip_sockglue.c | 2 +- net/ipv6/datagram.c | 2 +- 4 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 9e464f6409a7..b1dacc4d68c9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1901,7 +1901,7 @@ static inline void sockcm_init(struct sockcm_cookie *sockc, *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; } -int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, +int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc); int sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct sockcm_cookie *sockc); diff --git a/net/core/sock.c b/net/core/sock.c index aa608dc0930b..2786c1107e53 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2744,7 +2744,7 @@ failure: } EXPORT_SYMBOL(sock_alloc_send_pskb); -int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, +int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, struct sockcm_cookie *sockc) { u32 tsflags; @@ -2798,7 +2798,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, return -EINVAL; if (cmsg->cmsg_level != SOL_SOCKET) continue; - ret = __sock_cmsg_send(sk, msg, cmsg, sockc); + ret = __sock_cmsg_send(sk, cmsg, sockc); if (ret) return ret; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6e19cad154f5..5f16807d3235 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -267,7 +267,7 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, } #endif if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, &ipc->sockc); + err = __sock_cmsg_send(sk, cmsg, &ipc->sockc); if (err) return err; continue; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 5ecb56522f9d..df7e032ce87d 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -771,7 +771,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk, } if (cmsg->cmsg_level == SOL_SOCKET) { - err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc); + err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc); if (err) return err; continue; -- cgit v1.2.3 From 4727bab4e9bbeafeff6acdfcb077a7a548cbde30 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 21 Oct 2022 10:58:22 +0800 Subject: net: skb: move skb_pp_recycle() to skbuff.c skb_pp_recycle() is only used by skb_free_head() in skbuff.c, so move it to skbuff.c. Signed-off-by: Yunsheng Lin Acked-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/linux/skbuff.h | 7 ------- net/core/skbuff.c | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 7be5bb4c94b6..59c9fd55699d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -5050,12 +5050,5 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb) } #endif -static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) -{ - if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) - return false; - return page_pool_return_skb_page(virt_to_page(data)); -} - #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d9719e72f9d..9b3b19816d2d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -748,6 +748,13 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; -- cgit v1.2.3 From 398900498485fa9465386454681763d81efaad25 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 21 Oct 2022 16:09:59 +0100 Subject: net: sfp: provide a definition for the power level select bit Provide a named definition for the power level select bit in the extended status register, rather than using BIT(0) in the code. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- drivers/net/phy/sfp.c | 6 +++--- include/linux/sfp.h | 2 ++ 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index af676e28ba6a..16bce0ea68d9 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -1837,13 +1837,13 @@ static int sfp_sm_mod_hpower(struct sfp *sfp, bool enable) * all bytes 0xff) at 0x51 but does not accept writes. In any case, * if the bit is already set, we're already in high power mode. */ - if (!!(val & BIT(0)) == enable) + if (!!(val & SFP_EXT_STATUS_PWRLVL_SELECT) == enable) return 0; if (enable) - val |= BIT(0); + val |= SFP_EXT_STATUS_PWRLVL_SELECT; else - val &= ~BIT(0); + val &= ~SFP_EXT_STATUS_PWRLVL_SELECT; err = sfp_write(sfp, true, SFP_EXT_STATUS, &val, sizeof(val)); if (err != sizeof(val)) { diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d1f343853b6c..01ae9f1dd2ad 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -489,6 +489,8 @@ enum { SFP_WARN1_RXPWR_LOW = BIT(6), SFP_EXT_STATUS = 0x76, + SFP_EXT_STATUS_PWRLVL_SELECT = BIT(0), + SFP_VSL = 0x78, SFP_PAGE = 0x7f, }; -- cgit v1.2.3 From 4a6a676f8c16ec17d2f8d69ce3b5d680277ed0d2 Mon Sep 17 00:00:00 2001 From: Amritha Nambiar Date: Fri, 21 Oct 2022 00:58:39 -0700 Subject: act_skbedit: skbedit queue mapping for receive queue Add support for skbedit queue mapping action on receive side. This is supported only in hardware, so the skip_sw flag is enforced. This enables offloading filters for receive queue selection in the hardware using the skbedit action. Traffic arrives on the Rx queue requested in the skbedit action parameter. A new tc action flag TCA_ACT_FLAGS_AT_INGRESS is introduced to identify the traffic direction the action queue_mapping is requested on during filter addition. This is used to disallow offloading the skbedit queue mapping action on transmit side. Example: $tc filter add dev $IFACE ingress protocol ip flower dst_ip $DST_IP\ action skbedit queue_mapping $rxq_id skip_sw Reviewed-by: Sridhar Samudrala Signed-off-by: Amritha Nambiar Signed-off-by: Paolo Abeni --- include/net/act_api.h | 1 + include/net/flow_offload.h | 2 ++ include/net/tc_act/tc_skbedit.h | 29 +++++++++++++++++++++++++++++ net/sched/act_skbedit.c | 14 ++++++++++++-- net/sched/cls_api.c | 7 +++++++ 5 files changed, 51 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index 61f2ceb3939e..c94ea1a306e0 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -67,6 +67,7 @@ struct tc_action { #define TCA_ACT_FLAGS_BIND (1U << (TCA_ACT_FLAGS_USER_BITS + 1)) #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) +#define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index e343f9f8363e..7a60bc6d72c9 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -155,6 +155,7 @@ enum flow_action_id { FLOW_ACTION_MARK, FLOW_ACTION_PTYPE, FLOW_ACTION_PRIORITY, + FLOW_ACTION_RX_QUEUE_MAPPING, FLOW_ACTION_WAKE, FLOW_ACTION_QUEUE, FLOW_ACTION_SAMPLE, @@ -247,6 +248,7 @@ struct flow_action_entry { u32 csum_flags; /* FLOW_ACTION_CSUM */ u32 mark; /* FLOW_ACTION_MARK */ u16 ptype; /* FLOW_ACTION_PTYPE */ + u16 rx_queue; /* FLOW_ACTION_RX_QUEUE_MAPPING */ u32 priority; /* FLOW_ACTION_PRIORITY */ struct { /* FLOW_ACTION_QUEUE */ u32 ctx; diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index dc1079f28e13..9649600fb3dc 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -95,12 +95,41 @@ static inline u32 tcf_skbedit_priority(const struct tc_action *a) return priority; } +static inline u16 tcf_skbedit_rx_queue_mapping(const struct tc_action *a) +{ + u16 rx_queue; + + rcu_read_lock(); + rx_queue = rcu_dereference(to_skbedit(a)->params)->queue_mapping; + rcu_read_unlock(); + + return rx_queue; +} + /* Return true iff action is queue_mapping */ static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); } +/* Return true if action is on ingress traffic */ +static inline bool is_tcf_skbedit_ingress(u32 flags) +{ + return flags & TCA_ACT_FLAGS_AT_INGRESS; +} + +static inline bool is_tcf_skbedit_tx_queue_mapping(const struct tc_action *a) +{ + return is_tcf_skbedit_queue_mapping(a) && + !is_tcf_skbedit_ingress(a->tcfa_flags); +} + +static inline bool is_tcf_skbedit_rx_queue_mapping(const struct tc_action *a) +{ + return is_tcf_skbedit_queue_mapping(a) && + is_tcf_skbedit_ingress(a->tcfa_flags); +} + /* Return true iff action is inheritdsfield */ static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) { diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 7f598784fd30..1710780c908a 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -148,6 +148,11 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) { + if (is_tcf_skbedit_ingress(act_flags) && + !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) { + NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw"); + return -EOPNOTSUPP; + } flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } @@ -374,9 +379,12 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data } else if (is_tcf_skbedit_priority(act)) { entry->id = FLOW_ACTION_PRIORITY; entry->priority = tcf_skbedit_priority(act); - } else if (is_tcf_skbedit_queue_mapping(act)) { - NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used"); + } else if (is_tcf_skbedit_tx_queue_mapping(act)) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side"); return -EOPNOTSUPP; + } else if (is_tcf_skbedit_rx_queue_mapping(act)) { + entry->id = FLOW_ACTION_RX_QUEUE_MAPPING; + entry->rx_queue = tcf_skbedit_rx_queue_mapping(act); } else if (is_tcf_skbedit_inheritdsfield(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used"); return -EOPNOTSUPP; @@ -394,6 +402,8 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data fl_action->id = FLOW_ACTION_PTYPE; else if (is_tcf_skbedit_priority(act)) fl_action->id = FLOW_ACTION_PRIORITY; + else if (is_tcf_skbedit_rx_queue_mapping(act)) + fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING; else return -EOPNOTSUPP; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 50566db45949..23d1cfa4f58c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1953,6 +1953,11 @@ static void tfilter_put(struct tcf_proto *tp, void *fh) tp->ops->put(tp, fh); } +static bool is_qdisc_ingress(__u32 classid) +{ + return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2144,6 +2149,8 @@ replay: flags |= TCA_ACT_FLAGS_REPLACE; if (!rtnl_held) flags |= TCA_ACT_FLAGS_NO_RTNL; + if (is_qdisc_ingress(parent)) + flags |= TCA_ACT_FLAGS_AT_INGRESS; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { -- cgit v1.2.3 From b261eda84ec136240a9ca753389853a3a1bccca2 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 21 Oct 2022 13:44:34 -0700 Subject: soreuseport: Fix socket selection for SO_INCOMING_CPU. Kazuho Oku reported that setsockopt(SO_INCOMING_CPU) does not work with setsockopt(SO_REUSEPORT) since v4.6. With the combination of SO_REUSEPORT and SO_INCOMING_CPU, we could build a highly efficient server application. setsockopt(SO_INCOMING_CPU) associates a CPU with a TCP listener or UDP socket, and then incoming packets processed on the CPU will likely be distributed to the socket. Technically, a socket could even receive packets handled on another CPU if no sockets in the reuseport group have the same CPU receiving the flow. The logic exists in compute_score() so that a socket will get a higher score if it has the same CPU with the flow. However, the score gets ignored after the blamed two commits, which introduced a faster socket selection algorithm for SO_REUSEPORT. This patch introduces a counter of sockets with SO_INCOMING_CPU in a reuseport group to check if we should iterate all sockets to find a proper one. We increment the counter when * calling listen() if the socket has SO_INCOMING_CPU and SO_REUSEPORT * enabling SO_INCOMING_CPU if the socket is in a reuseport group Also, we decrement it when * detaching a socket out of the group to apply SO_INCOMING_CPU to migrated TCP requests * disabling SO_INCOMING_CPU if the socket is in a reuseport group When the counter reaches 0, we can get back to the O(1) selection algorithm. The overall changes are negligible for the non-SO_INCOMING_CPU case, and the only notable thing is that we have to update sk_incomnig_cpu under reuseport_lock. Otherwise, the race prevents transitioning to the O(n) algorithm and results in the wrong socket selection. cpu1 (setsockopt) cpu2 (listen) +-----------------+ +-------------+ lock_sock(sk1) lock_sock(sk2) reuseport_update_incoming_cpu(sk1, val) . | /* set CPU as 0 */ |- WRITE_ONCE(sk1->incoming_cpu, val) | | spin_lock_bh(&reuseport_lock) | reuseport_grow(sk2, reuse) | . | |- more_socks_size = reuse->max_socks * 2U; | |- if (more_socks_size > U16_MAX && | | reuse->num_closed_socks) | | . | | |- RCU_INIT_POINTER(sk1->sk_reuseport_cb, NULL); | | `- __reuseport_detach_closed_sock(sk1, reuse) | | . | | `- reuseport_put_incoming_cpu(sk1, reuse) | | . | | | /* Read shutdown()ed sk1's sk_incoming_cpu | | | * without lock_sock(). | | | */ | | `- if (sk1->sk_incoming_cpu >= 0) | | . | | | /* decrement not-yet-incremented | | | * count, which is never incremented. | | | */ | | `- __reuseport_put_incoming_cpu(reuse); | | | `- spin_lock_bh(&reuseport_lock) | |- spin_lock_bh(&reuseport_lock) | |- reuse = rcu_dereference_protected(sk1->sk_reuseport_cb, ...) |- if (!reuse) | . | | /* Cannot increment reuse->incoming_cpu. */ | `- goto out; | `- spin_unlock_bh(&reuseport_lock) Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection") Fixes: c125e80b8868 ("soreuseport: fast reuseport TCP socket selection") Reported-by: Kazuho Oku Signed-off-by: Kuniyuki Iwashima Signed-off-by: Paolo Abeni --- include/net/sock_reuseport.h | 2 + net/core/sock.c | 2 +- net/core/sock_reuseport.c | 94 +++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 92 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index efc9085c6892..6ec140b0a61b 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -16,6 +16,7 @@ struct sock_reuseport { u16 max_socks; /* length of socks */ u16 num_socks; /* elements in socks */ u16 num_closed_socks; /* closed elements in socks */ + u16 incoming_cpu; /* The last synq overflow event timestamp of this * reuse->socks[] group. */ @@ -58,5 +59,6 @@ static inline bool reuseport_has_conns(struct sock *sk) } void reuseport_has_conns_set(struct sock *sk); +void reuseport_update_incoming_cpu(struct sock *sk, int val); #endif /* _SOCK_REUSEPORT_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 2786c1107e53..4571914a4aa8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1436,7 +1436,7 @@ set_sndbuf: break; } case SO_INCOMING_CPU: - WRITE_ONCE(sk->sk_incoming_cpu, val); + reuseport_update_incoming_cpu(sk, val); break; case SO_CNX_ADVICE: diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index fb90e1e00773..5a165286e4d8 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -37,6 +37,70 @@ void reuseport_has_conns_set(struct sock *sk) } EXPORT_SYMBOL(reuseport_has_conns_set); +static void __reuseport_get_incoming_cpu(struct sock_reuseport *reuse) +{ + /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ + WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu + 1); +} + +static void __reuseport_put_incoming_cpu(struct sock_reuseport *reuse) +{ + /* Paired with READ_ONCE() in reuseport_select_sock_by_hash(). */ + WRITE_ONCE(reuse->incoming_cpu, reuse->incoming_cpu - 1); +} + +static void reuseport_get_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) +{ + if (sk->sk_incoming_cpu >= 0) + __reuseport_get_incoming_cpu(reuse); +} + +static void reuseport_put_incoming_cpu(struct sock *sk, struct sock_reuseport *reuse) +{ + if (sk->sk_incoming_cpu >= 0) + __reuseport_put_incoming_cpu(reuse); +} + +void reuseport_update_incoming_cpu(struct sock *sk, int val) +{ + struct sock_reuseport *reuse; + int old_sk_incoming_cpu; + + if (unlikely(!rcu_access_pointer(sk->sk_reuseport_cb))) { + /* Paired with REAE_ONCE() in sk_incoming_cpu_update() + * and compute_score(). + */ + WRITE_ONCE(sk->sk_incoming_cpu, val); + return; + } + + spin_lock_bh(&reuseport_lock); + + /* This must be done under reuseport_lock to avoid a race with + * reuseport_grow(), which accesses sk->sk_incoming_cpu without + * lock_sock() when detaching a shutdown()ed sk. + * + * Paired with READ_ONCE() in reuseport_select_sock_by_hash(). + */ + old_sk_incoming_cpu = sk->sk_incoming_cpu; + WRITE_ONCE(sk->sk_incoming_cpu, val); + + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + + /* reuseport_grow() has detached a closed sk. */ + if (!reuse) + goto out; + + if (old_sk_incoming_cpu < 0 && val >= 0) + __reuseport_get_incoming_cpu(reuse); + else if (old_sk_incoming_cpu >= 0 && val < 0) + __reuseport_put_incoming_cpu(reuse); + +out: + spin_unlock_bh(&reuseport_lock); +} + static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) @@ -64,6 +128,7 @@ static void __reuseport_add_sock(struct sock *sk, /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ smp_wmb(); reuse->num_socks++; + reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_sock(struct sock *sk, @@ -76,6 +141,7 @@ static bool __reuseport_detach_sock(struct sock *sk, reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; + reuseport_put_incoming_cpu(sk, reuse); return true; } @@ -86,6 +152,7 @@ static void __reuseport_add_closed_sock(struct sock *sk, reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); + reuseport_get_incoming_cpu(sk, reuse); } static bool __reuseport_detach_closed_sock(struct sock *sk, @@ -99,6 +166,7 @@ static bool __reuseport_detach_closed_sock(struct sock *sk, reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; /* paired with READ_ONCE() in inet_csk_bind_conflict() */ WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); + reuseport_put_incoming_cpu(sk, reuse); return true; } @@ -166,6 +234,7 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; + reuseport_get_incoming_cpu(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -209,6 +278,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; + more_reuse->incoming_cpu = reuse->incoming_cpu; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); @@ -458,18 +528,32 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, u32 hash, u16 num_socks) { + struct sock *first_valid_sk = NULL; int i, j; i = j = reciprocal_scale(hash, num_socks); - while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { + do { + struct sock *sk = reuse->socks[i]; + + if (sk->sk_state != TCP_ESTABLISHED) { + /* Paired with WRITE_ONCE() in __reuseport_(get|put)_incoming_cpu(). */ + if (!READ_ONCE(reuse->incoming_cpu)) + return sk; + + /* Paired with WRITE_ONCE() in reuseport_update_incoming_cpu(). */ + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) + return sk; + + if (!first_valid_sk) + first_valid_sk = sk; + } + i++; if (i >= num_socks) i = 0; - if (i == j) - return NULL; - } + } while (i != j); - return reuse->socks[i]; + return first_valid_sk; } /** -- cgit v1.2.3 From ac1f8c049319847b1b4c6b387fdb2e3f7fb84ffc Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 28 Sep 2022 23:55:06 +0200 Subject: netfilter: nft_payload: move struct nft_payload_set definition where it belongs Not required to expose this header in nf_tables_core.h, move it to where it is used, ie. nft_payload. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 10 ---------- net/netfilter/nft_payload.c | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 1223af68cd9a..990c3767a350 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -66,16 +66,6 @@ struct nft_payload { u8 dreg; }; -struct nft_payload_set { - enum nft_payload_bases base:8; - u8 offset; - u8 len; - u8 sreg; - u8 csum_type; - u8 csum_offset; - u8 csum_flags; -}; - extern const struct nft_expr_ops nft_payload_fast_ops; extern const struct nft_expr_ops nft_bitwise_fast_ops; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 088244f9d838..07621d509a68 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -665,6 +665,16 @@ static int nft_payload_csum_inet(struct sk_buff *skb, const u32 *src, return 0; } +struct nft_payload_set { + enum nft_payload_bases base:8; + u8 offset; + u8 len; + u8 sreg; + u8 csum_type; + u8 csum_offset; + u8 csum_flags; +}; + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) -- cgit v1.2.3 From e7a1caa67ce62765fe174cae08e537d542bb44f8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 15 Oct 2022 00:20:50 +0200 Subject: netfilter: nf_tables: reduce nft_pktinfo by 8 bytes structure is reduced from 32 to 24 bytes. While at it, also check that iphdrlen is sane, this is guaranteed for NFPROTO_IPV4 but not for ingress or bridge, so add checks for this. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 4 ++-- include/net/netfilter/nf_tables_ipv4.h | 4 ++++ include/net/netfilter/nf_tables_ipv6.h | 6 +++--- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index cdb7db9b0e25..f6db510689a8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -32,8 +32,8 @@ struct nft_pktinfo { u8 flags; u8 tprot; u16 fragoff; - unsigned int thoff; - unsigned int inneroff; + u16 thoff; + u16 inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index c4a6147b0ef8..112708f7a6b4 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -35,6 +35,8 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) return -1; else if (len < thoff) return -1; + else if (thoff < sizeof(*iph)) + return -1; pkt->flags = NFT_PKTINFO_L4PROTO; pkt->tprot = iph->protocol; @@ -69,6 +71,8 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) return -1; } else if (len < thoff) { goto inhdr_error; + } else if (thoff < sizeof(*iph)) { + return -1; } pkt->flags = NFT_PKTINFO_L4PROTO; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index ec7eaeaf4f04..467d59b9e533 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -13,7 +13,7 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt) unsigned short frag_off; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); - if (protohdr < 0) { + if (protohdr < 0 || thoff > U16_MAX) { nft_set_pktinfo_unspec(pkt); return; } @@ -47,7 +47,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); - if (protohdr < 0) + if (protohdr < 0 || thoff > U16_MAX) return -1; pkt->flags = NFT_PKTINFO_L4PROTO; @@ -93,7 +93,7 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) } protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); - if (protohdr < 0) + if (protohdr < 0 || thoff > U16_MAX) goto inhdr_error; pkt->flags = NFT_PKTINFO_L4PROTO; -- cgit v1.2.3 From d037abc2414b4539401e0e6aa278bedc4628ad69 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 21 Oct 2022 16:17:53 +0200 Subject: netfilter: nft_objref: make it builtin nft_objref is needed to reference named objects, it makes no sense to disable it. Before: text data bss dec filename 4014 424 0 4438 nft_objref.o 4174 1128 0 5302 nft_objref.ko 359351 15276 864 375491 nf_tables.ko After: text data bss dec filename 3815 408 0 4223 nft_objref.o 363161 15692 864 379717 nf_tables.ko Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables_core.h | 1 + net/netfilter/Kconfig | 6 ------ net/netfilter/Makefile | 4 ++-- net/netfilter/nf_tables_core.c | 1 + net/netfilter/nft_objref.c | 22 +--------------------- 5 files changed, 5 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 990c3767a350..83d763631f81 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -18,6 +18,7 @@ extern struct nft_expr_type nft_meta_type; extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; extern struct nft_expr_type nft_last_type; +extern struct nft_expr_type nft_objref_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 4b8d04640ff3..0846bd75b1da 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -568,12 +568,6 @@ config NFT_TUNNEL This option adds the "tunnel" expression that you can use to set tunneling policies. -config NFT_OBJREF - tristate "Netfilter nf_tables stateful object reference module" - help - This option adds the "objref" expression that allows you to refer to - stateful objects, such as counters and quotas. - config NFT_QUEUE depends on NETFILTER_NETLINK_QUEUE tristate "Netfilter nf_tables queue module" diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0f060d100880..7a6b518ba2b4 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -86,7 +86,8 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ - nft_counter.o nft_chain_route.o nf_tables_offload.o \ + nft_counter.o nft_objref.o \ + nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o @@ -104,7 +105,6 @@ obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o -obj-$(CONFIG_NFT_OBJREF) += nft_objref.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index cee3e4e905ec..6dcead50208c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -340,6 +340,7 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_exthdr_type, &nft_last_type, &nft_counter_type, + &nft_objref_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 5d8d91b3904d..74e0eea4abac 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -82,7 +82,6 @@ static void nft_objref_activate(const struct nft_ctx *ctx, obj->use++; } -static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_object *)), @@ -195,7 +194,6 @@ static void nft_objref_map_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static struct nft_expr_type nft_objref_type; static const struct nft_expr_ops nft_objref_map_ops = { .type = &nft_objref_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), @@ -233,28 +231,10 @@ static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = { [NFTA_OBJREF_SET_ID] = { .type = NLA_U32 }, }; -static struct nft_expr_type nft_objref_type __read_mostly = { +struct nft_expr_type nft_objref_type __read_mostly = { .name = "objref", .select_ops = nft_objref_select_ops, .policy = nft_objref_policy, .maxattr = NFTA_OBJREF_MAX, .owner = THIS_MODULE, }; - -static int __init nft_objref_module_init(void) -{ - return nft_register_expr(&nft_objref_type); -} - -static void __exit nft_objref_module_exit(void) -{ - nft_unregister_expr(&nft_objref_type); -} - -module_init(nft_objref_module_init); -module_exit(nft_objref_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso "); -MODULE_ALIAS_NFT_EXPR("objref"); -MODULE_DESCRIPTION("nftables stateful object reference module"); -- cgit v1.2.3 From 3a07327d10a09379315c844c63f27941f5081e0a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 25 Oct 2022 13:48:15 +0200 Subject: netfilter: nft_inner: support for inner tunnel header matching This new expression allows you to match on the inner headers that are encapsulated by any of the existing tunneling protocols. This expression parses the inner packet to set the link, network and transport offsets, so the existing expressions (with a few updates) can be reused to match on the inner headers. The inner expression supports for different tunnel combinations such as: - ethernet frame over IPv4/IPv6 packet, eg. VxLAN. - IPv4/IPv6 packet over IPv4/IPv6 packet, eg. IPIP. - IPv4/IPv6 packet over IPv4/IPv6 + transport header, eg. GRE. - transport header (ESP or SCTP) over transport header (usually UDP) The following fields are used to describe the tunnel protocol: - flags, which describe how to parse the inner headers: NFT_PAYLOAD_CTX_INNER_TUN, the tunnel provides its own header. NFT_PAYLOAD_CTX_INNER_ETHER, the ethernet frame is available as inner header. NFT_PAYLOAD_CTX_INNER_NH, the network header is available as inner header. NFT_PAYLOAD_CTX_INNER_TH, the transport header is available as inner header. For example, VxLAN sets on all of these flags. While GRE only sets on NFT_PAYLOAD_CTX_INNER_NH and NFT_PAYLOAD_CTX_INNER_TH. Then, ESP over UDP only sets on NFT_PAYLOAD_CTX_INNER_TH. The tunnel description is composed of the following attributes: - header size: in case the tunnel comes with its own header, eg. VxLAN. - type: this provides a hint to userspace on how to delinearize the rule. This is useful for VxLAN and Geneve since they run over UDP, since transport does not provide a hint. This is also useful in case hardware offload is ever supported. The type is not currently interpreted by the kernel. - expression: currently only payload supported. Follow up patch adds also inner meta support which is required by autogenerated dependencies. The exthdr expression should be supported too at some point. There is a new inner_ops operation that needs to be set on to allow to use an existing expression from the inner expression. This patch adds a new NFT_PAYLOAD_TUN_HEADER base which allows to match on the tunnel header fields, eg. vxlan vni. The payload expression is embedded into nft_inner private area and this private data area is passed to the payload inner eval function via direct call. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 + include/net/netfilter/nf_tables_core.h | 24 +++ include/uapi/linux/netfilter/nf_tables.h | 26 +++ net/netfilter/Makefile | 2 +- net/netfilter/nf_tables_api.c | 37 ++++ net/netfilter/nf_tables_core.c | 1 + net/netfilter/nft_inner.c | 336 +++++++++++++++++++++++++++++++ net/netfilter/nft_payload.c | 89 +++++++- 8 files changed, 518 insertions(+), 2 deletions(-) create mode 100644 net/netfilter/nft_inner.c (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f6db510689a8..2dbfe7524a7e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -375,6 +375,10 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) return (void *)expr->data; } +struct nft_expr_info; + +int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, + struct nft_expr_info *info); int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, @@ -864,6 +868,7 @@ struct nft_expr_type { const struct nlattr * const tb[]); void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; + const struct nft_expr_ops *inner_ops; struct list_head list; const char *name; struct module *owner; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 83d763631f81..be2b2b5d0a52 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -19,6 +19,7 @@ extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; extern struct nft_expr_type nft_last_type; extern struct nft_expr_type nft_objref_type; +extern struct nft_expr_type nft_inner_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; @@ -139,4 +140,27 @@ void nft_rt_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + +enum { + NFT_PAYLOAD_CTX_INNER_TUN = (1 << 0), + NFT_PAYLOAD_CTX_INNER_LL = (1 << 1), + NFT_PAYLOAD_CTX_INNER_NH = (1 << 2), + NFT_PAYLOAD_CTX_INNER_TH = (1 << 3), +}; + +struct nft_inner_tun_ctx { + u16 inner_tunoff; + u16 inner_lloff; + u16 inner_nhoff; + u16 inner_thoff; + __be16 llproto; + u8 l4proto; + u8 flags; +}; + +int nft_payload_inner_offset(const struct nft_pktinfo *pkt); +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx); + #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 466fd3f4447c..05a15dce8271 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -760,6 +760,7 @@ enum nft_payload_bases { NFT_PAYLOAD_NETWORK_HEADER, NFT_PAYLOAD_TRANSPORT_HEADER, NFT_PAYLOAD_INNER_HEADER, + NFT_PAYLOAD_TUN_HEADER, }; /** @@ -779,6 +780,31 @@ enum nft_payload_csum_flags { NFT_PAYLOAD_L4CSUM_PSEUDOHDR = (1 << 0), }; +enum nft_inner_type { + NFT_INNER_UNSPEC = 0, + NFT_INNER_VXLAN, +}; + +enum nft_inner_flags { + NFT_INNER_HDRSIZE = (1 << 0), + NFT_INNER_LL = (1 << 1), + NFT_INNER_NH = (1 << 2), + NFT_INNER_TH = (1 << 3), +}; +#define NFT_INNER_MASK (NFT_INNER_HDRSIZE | NFT_INNER_LL | \ + NFT_INNER_NH | NFT_INNER_TH) + +enum nft_inner_attributes { + NFTA_INNER_UNSPEC, + NFTA_INNER_NUM, + NFTA_INNER_TYPE, + NFTA_INNER_FLAGS, + NFTA_INNER_HDRSIZE, + NFTA_INNER_EXPR, + __NFTA_INNER_MAX +}; +#define NFTA_INNER_MAX (__NFTA_INNER_MAX - 1) + /** * enum nft_payload_attributes - nf_tables payload expression netlink attributes * diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 7a6b518ba2b4..1d4db1943936 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -86,7 +86,7 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ - nft_counter.o nft_objref.o \ + nft_counter.o nft_objref.o nft_inner.o \ nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 58d9cbc9ccdc..6b79f5e18f08 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2857,6 +2857,43 @@ err1: return err; } +int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, + struct nft_expr_info *info) +{ + struct nlattr *tb[NFTA_EXPR_MAX + 1]; + const struct nft_expr_type *type; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, + nft_expr_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_EXPR_DATA]) + return -EINVAL; + + type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); + if (IS_ERR(type)) + return PTR_ERR(type); + + if (!type->inner_ops) + return -EOPNOTSUPP; + + err = nla_parse_nested_deprecated(info->tb, type->maxattr, + tb[NFTA_EXPR_DATA], + type->policy, NULL); + if (err < 0) + goto err_nla_parse; + + info->attr = nla; + info->ops = type->inner_ops; + + return 0; + +err_nla_parse: + return err; +} + static int nf_tables_newexpr(const struct nft_ctx *ctx, const struct nft_expr_info *expr_info, struct nft_expr *expr) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 6dcead50208c..709a736c301c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -341,6 +341,7 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_last_type, &nft_counter_type, &nft_objref_type, + &nft_inner_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c new file mode 100644 index 000000000000..1e4079b5b431 --- /dev/null +++ b/net/netfilter/nft_inner.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 Pablo Neira Ayuso + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Same layout as nft_expr but it embeds the private expression data area. */ +struct __nft_expr { + const struct nft_expr_ops *ops; + union { + struct nft_payload payload; + } __attribute__((aligned(__alignof__(u64)))); +}; + +enum { + NFT_INNER_EXPR_PAYLOAD, +}; + +struct nft_inner { + u8 flags; + u8 hdrsize; + u8 type; + u8 expr_type; + + struct __nft_expr expr; +}; + +static int nft_inner_parse_l2l3(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 off) +{ + __be16 llproto, outer_llproto; + u32 nhoff, thoff; + + if (priv->flags & NFT_INNER_LL) { + struct vlan_ethhdr *veth, _veth; + struct ethhdr *eth, _eth; + u32 hdrsize; + + eth = skb_header_pointer(pkt->skb, off, sizeof(_eth), &_eth); + if (!eth) + return -1; + + switch (eth->h_proto) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + llproto = eth->h_proto; + hdrsize = sizeof(_eth); + break; + case htons(ETH_P_8021Q): + veth = skb_header_pointer(pkt->skb, off, sizeof(_veth), &_veth); + if (!eth) + return -1; + + outer_llproto = veth->h_vlan_encapsulated_proto; + llproto = veth->h_vlan_proto; + hdrsize = sizeof(_veth); + break; + default: + return -1; + } + + ctx->inner_lloff = off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_LL; + off += hdrsize; + } else { + struct iphdr *iph; + u32 _version; + + iph = skb_header_pointer(pkt->skb, off, sizeof(_version), &_version); + if (!iph) + return -1; + + switch (iph->version) { + case 4: + llproto = htons(ETH_P_IP); + break; + case 6: + llproto = htons(ETH_P_IPV6); + break; + default: + return -1; + } + } + + ctx->llproto = llproto; + if (llproto == htons(ETH_P_8021Q)) + llproto = outer_llproto; + + nhoff = off; + + switch (llproto) { + case htons(ETH_P_IP): { + struct iphdr *iph, _iph; + + iph = skb_header_pointer(pkt->skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return -1; + + if (iph->ihl < 5 || iph->version != 4) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff + (iph->ihl * 4); + if ((ntohs(iph->frag_off) & IP_OFFSET) == 0) { + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = iph->protocol; + } + } + break; + case htons(ETH_P_IPV6): { + struct ipv6hdr *ip6h, _ip6h; + int fh_flags = IP6_FH_F_AUTH; + unsigned short fragoff; + int l4proto; + + ip6h = skb_header_pointer(pkt->skb, nhoff, sizeof(_ip6h), &_ip6h); + if (!ip6h) + return -1; + + if (ip6h->version != 6) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff; + l4proto = ipv6_find_hdr(pkt->skb, &thoff, -1, &fragoff, &fh_flags); + if (l4proto < 0 || thoff > U16_MAX) + return -1; + + if (fragoff == 0) { + thoff = nhoff + sizeof(_ip6h); + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = l4proto; + } + } + break; + default: + return -1; + } + + return 0; +} + +static int nft_inner_parse_tunhdr(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 *off) +{ + if (pkt->tprot != IPPROTO_UDP || + pkt->tprot != IPPROTO_GRE) + return -1; + + ctx->inner_tunoff = *off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; + *off += priv->hdrsize; + + return 0; +} + +static int nft_inner_parse(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + struct nft_inner_tun_ctx ctx = {}; + u32 off = pkt->inneroff; + + if (priv->flags & NFT_INNER_HDRSIZE && + nft_inner_parse_tunhdr(priv, pkt, &ctx, &off) < 0) + return -1; + + if (priv->flags & (NFT_INNER_LL | NFT_INNER_NH)) { + if (nft_inner_parse_l2l3(priv, pkt, &ctx, off) < 0) + return -1; + } else if (priv->flags & NFT_INNER_TH) { + ctx.inner_thoff = off; + ctx.flags |= NFT_PAYLOAD_CTX_INNER_TH; + } + + *tun_ctx = ctx; + + return 0; +} + +static void nft_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_inner *priv = nft_expr_priv(expr); + struct nft_inner_tun_ctx tun_ctx = {}; + + if (nft_payload_inner_offset(pkt) < 0) + goto err; + + if (nft_inner_parse(priv, pkt, &tun_ctx) < 0) + goto err; + + switch (priv->expr_type) { + case NFT_INNER_EXPR_PAYLOAD: + nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, &tun_ctx); + break; + default: + WARN_ON_ONCE(1); + goto err; + } + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_inner_policy[NFTA_INNER_MAX + 1] = { + [NFTA_INNER_NUM] = { .type = NLA_U32 }, + [NFTA_INNER_FLAGS] = { .type = NLA_U32 }, + [NFTA_INNER_HDRSIZE] = { .type = NLA_U32 }, + [NFTA_INNER_TYPE] = { .type = NLA_U32 }, + [NFTA_INNER_EXPR] = { .type = NLA_NESTED }, +}; + +struct nft_expr_info { + const struct nft_expr_ops *ops; + const struct nlattr *attr; + struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; +}; + +static int nft_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_inner *priv = nft_expr_priv(expr); + u32 flags, hdrsize, type, num; + struct nft_expr_info expr_info; + int err; + + if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_HDRSIZE] || + !tb[NFTA_INNER_TYPE] || + !tb[NFTA_INNER_EXPR]) + return -EINVAL; + + flags = ntohl(nla_get_be32(tb[NFTA_INNER_FLAGS])); + if (flags & ~NFT_INNER_MASK) + return -EOPNOTSUPP; + + num = ntohl(nla_get_be32(tb[NFTA_INNER_NUM])); + if (num != 0) + return -EOPNOTSUPP; + + hdrsize = ntohl(nla_get_be32(tb[NFTA_INNER_HDRSIZE])); + type = ntohl(nla_get_be32(tb[NFTA_INNER_TYPE])); + + if (type > U8_MAX) + return -EINVAL; + + if (flags & NFT_INNER_HDRSIZE) { + if (hdrsize == 0 || hdrsize > 64) + return -EOPNOTSUPP; + } + + priv->flags = flags; + priv->hdrsize = hdrsize; + priv->type = type; + + err = nft_expr_inner_parse(ctx, tb[NFTA_INNER_EXPR], &expr_info); + if (err < 0) + return err; + + priv->expr.ops = expr_info.ops; + + if (!strcmp(expr_info.ops->type->name, "payload")) + priv->expr_type = NFT_INNER_EXPR_PAYLOAD; + else + return -EINVAL; + + err = expr_info.ops->init(ctx, (struct nft_expr *)&priv->expr, + (const struct nlattr * const*)expr_info.tb); + if (err < 0) + return err; + + return 0; +} + +static int nft_inner_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_inner *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_INNER_NUM, htonl(0)) || + nla_put_be32(skb, NFTA_INNER_TYPE, htonl(priv->type)) || + nla_put_be32(skb, NFTA_INNER_FLAGS, htonl(priv->flags)) || + nla_put_be32(skb, NFTA_INNER_HDRSIZE, htonl(priv->hdrsize))) + goto nla_put_failure; + + if (nft_expr_dump(skb, NFTA_INNER_EXPR, + (struct nft_expr *)&priv->expr) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_inner_ops = { + .type = &nft_inner_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_inner)), + .eval = nft_inner_eval, + .init = nft_inner_init, + .dump = nft_inner_dump, +}; + +struct nft_expr_type nft_inner_type __read_mostly = { + .name = "inner", + .ops = &nft_inner_ops, + .policy = nft_inner_policy, + .maxattr = NFTA_INNER_MAX, + .owner = THIS_MODULE, +}; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 84b490d6cc75..9d2ac764a14c 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -144,7 +144,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) return 0; } -static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +int nft_payload_inner_offset(const struct nft_pktinfo *pkt) { if (!(pkt->flags & NFT_PKTINFO_INNER) && __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0) @@ -587,6 +587,92 @@ const struct nft_expr_ops nft_payload_fast_ops = { .offload = nft_payload_offload, }; +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_payload *priv = nft_expr_priv(expr); + const struct sk_buff *skb = pkt->skb; + u32 *dest = ®s->data[priv->dreg]; + int offset; + + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + + switch (priv->base) { + case NFT_PAYLOAD_TUN_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TUN)) + goto err; + + offset = tun_ctx->inner_tunoff; + break; + case NFT_PAYLOAD_LL_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_LL)) + goto err; + + offset = tun_ctx->inner_lloff; + break; + case NFT_PAYLOAD_NETWORK_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_NH)) + goto err; + + offset = tun_ctx->inner_nhoff; + break; + case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + offset = tun_ctx->inner_thoff; + break; + default: + WARN_ON_ONCE(1); + goto err; + } + offset += priv->offset; + + if (skb_copy_bits(skb, offset, dest, priv->len) < 0) + goto err; + + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static int nft_payload_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_payload *priv = nft_expr_priv(expr); + u32 base; + + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); + switch (base) { + case NFT_PAYLOAD_TUN_HEADER: + case NFT_PAYLOAD_LL_HEADER: + case NFT_PAYLOAD_NETWORK_HEADER: + case NFT_PAYLOAD_TRANSPORT_HEADER: + break; + default: + return -EOPNOTSUPP; + } + + priv->base = base; + priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); + priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); +} + +static const struct nft_expr_ops nft_payload_inner_ops = { + .type = &nft_payload_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_payload)), + .init = nft_payload_inner_init, + .dump = nft_payload_dump, + /* direct call to nft_payload_inner_eval(). */ +}; + static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum) { *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum)); @@ -930,6 +1016,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, struct nft_expr_type nft_payload_type __read_mostly = { .name = "payload", .select_ops = nft_payload_select_ops, + .inner_ops = &nft_payload_inner_ops, .policy = nft_payload_policy, .maxattr = NFTA_PAYLOAD_MAX, .owner = THIS_MODULE, -- cgit v1.2.3 From 0e795b37ba044893107f887b037594645a6fc584 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Oct 2022 13:03:32 +0200 Subject: netfilter: nft_inner: add percpu inner context Add NFT_PKTINFO_INNER_FULL flag to annotate that inner offsets are available. Store nft_inner_tun_ctx object in percpu area to cache existing inner offsets for this skbuff. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 1 + include/net/netfilter/nf_tables_core.h | 1 + net/netfilter/nft_inner.c | 26 ++++++++++++++++++++++---- 3 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2dbfe7524a7e..38e2b396e38a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -24,6 +24,7 @@ struct module; enum { NFT_PKTINFO_L4PROTO = (1 << 0), NFT_PKTINFO_INNER = (1 << 1), + NFT_PKTINFO_INNER_FULL = (1 << 2), }; struct nft_pktinfo { diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index be2b2b5d0a52..3e825381ac5c 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -149,6 +149,7 @@ enum { }; struct nft_inner_tun_ctx { + u16 type; u16 inner_tunoff; u16 inner_lloff; u16 inner_nhoff; diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 1e4079b5b431..29f2eefe0357 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -21,6 +21,8 @@ #include #include +static DEFINE_PER_CPU(struct nft_inner_tun_ctx, nft_pcpu_tun_ctx); + /* Same layout as nft_expr but it embeds the private expression data area. */ struct __nft_expr { const struct nft_expr_ops *ops; @@ -180,7 +182,7 @@ static int nft_inner_parse_tunhdr(const struct nft_inner *priv, } static int nft_inner_parse(const struct nft_inner *priv, - const struct nft_pktinfo *pkt, + struct nft_pktinfo *pkt, struct nft_inner_tun_ctx *tun_ctx) { struct nft_inner_tun_ctx ctx = {}; @@ -199,25 +201,41 @@ static int nft_inner_parse(const struct nft_inner *priv, } *tun_ctx = ctx; + tun_ctx->type = priv->type; + pkt->flags |= NFT_PKTINFO_INNER_FULL; return 0; } +static bool nft_inner_parse_needed(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + const struct nft_inner_tun_ctx *tun_ctx) +{ + if (!(pkt->flags & NFT_PKTINFO_INNER_FULL)) + return true; + + if (priv->type != tun_ctx->type) + return true; + + return false; +} + static void nft_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { + struct nft_inner_tun_ctx *tun_ctx = this_cpu_ptr(&nft_pcpu_tun_ctx); const struct nft_inner *priv = nft_expr_priv(expr); - struct nft_inner_tun_ctx tun_ctx = {}; if (nft_payload_inner_offset(pkt) < 0) goto err; - if (nft_inner_parse(priv, pkt, &tun_ctx) < 0) + if (nft_inner_parse_needed(priv, pkt, tun_ctx) && + nft_inner_parse(priv, (struct nft_pktinfo *)pkt, tun_ctx) < 0) goto err; switch (priv->expr_type) { case NFT_INNER_EXPR_PAYLOAD: - nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, &tun_ctx); + nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, tun_ctx); break; default: WARN_ON_ONCE(1); -- cgit v1.2.3 From a150d122b6bdb84df532057aa3b2faf8c6485792 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Oct 2022 13:03:33 +0200 Subject: netfilter: nft_meta: add inner match support Add support for inner meta matching on: - NFT_META_PROTOCOL: to match on the ethertype, this can be used regardless tunnel protocol provides no link layer header, in that case nft_inner sets on the ethertype based on the IP header version field. - NFT_META_L4PROTO: to match on the layer 4 protocol. These meta expression are usually autogenerated as dependencies by userspace nftables. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_meta.h | 6 ++++ net/netfilter/nft_inner.c | 8 ++++++ net/netfilter/nft_meta.c | 62 ++++++++++++++++++++++++++++++++++++++++ 3 files changed, 76 insertions(+) (limited to 'include') diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index 9b51cc67de54..f3a5285a511c 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -46,4 +46,10 @@ int nft_meta_set_validate(const struct nft_ctx *ctx, bool nft_meta_get_reduce(struct nft_regs_track *track, const struct nft_expr *expr); + +struct nft_inner_tun_ctx; +void nft_meta_inner_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx); + #endif diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 29f2eefe0357..c43a2fe0ceb7 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -28,11 +29,13 @@ struct __nft_expr { const struct nft_expr_ops *ops; union { struct nft_payload payload; + struct nft_meta meta; } __attribute__((aligned(__alignof__(u64)))); }; enum { NFT_INNER_EXPR_PAYLOAD, + NFT_INNER_EXPR_META, }; struct nft_inner { @@ -237,6 +240,9 @@ static void nft_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, case NFT_INNER_EXPR_PAYLOAD: nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, tun_ctx); break; + case NFT_INNER_EXPR_META: + nft_meta_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, tun_ctx); + break; default: WARN_ON_ONCE(1); goto err; @@ -306,6 +312,8 @@ static int nft_inner_init(const struct nft_ctx *ctx, if (!strcmp(expr_info.ops->type->name, "payload")) priv->expr_type = NFT_INNER_EXPR_PAYLOAD; + else if (!strcmp(expr_info.ops->type->name, "meta")) + priv->expr_type = NFT_INNER_EXPR_META; else return -EINVAL; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 55d2d49c3425..8c39adeebb5c 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -831,9 +831,71 @@ nft_meta_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); } +static int nft_meta_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_meta *priv = nft_expr_priv(expr); + unsigned int len; + + priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); + switch (priv->key) { + case NFT_META_PROTOCOL: + len = sizeof(u16); + break; + case NFT_META_L4PROTO: + len = sizeof(u32); + break; + default: + return -EOPNOTSUPP; + } + priv->len = len; + + return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, + NULL, NFT_DATA_VALUE, len); +} + +void nft_meta_inner_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_meta *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + + switch (priv->key) { + case NFT_META_PROTOCOL: + nft_reg_store16(dest, (__force u16)tun_ctx->llproto); + break; + case NFT_META_L4PROTO: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + nft_reg_store8(dest, tun_ctx->l4proto); + break; + default: + WARN_ON_ONCE(1); + goto err; + } + return; + +err: + regs->verdict.code = NFT_BREAK; +} +EXPORT_SYMBOL_GPL(nft_meta_inner_eval); + +static const struct nft_expr_ops nft_meta_inner_ops = { + .type = &nft_meta_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), + .init = nft_meta_inner_init, + .dump = nft_meta_get_dump, + /* direct call to nft_meta_inner_eval(). */ +}; + struct nft_expr_type nft_meta_type __read_mostly = { .name = "meta", .select_ops = nft_meta_select_ops, + .inner_ops = &nft_meta_inner_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, -- cgit v1.2.3 From 0db14b95660b63dceeb7e89f2e3ffa97d331fce0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Oct 2022 13:03:34 +0200 Subject: netfilter: nft_inner: add geneve support Geneve tunnel header may contain options, parse geneve header and update offset to point to the link layer header according to the opt_len field. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nft_inner.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 05a15dce8271..e4b739d57480 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -783,6 +783,7 @@ enum nft_payload_csum_flags { enum nft_inner_type { NFT_INNER_UNSPEC = 0, NFT_INNER_VXLAN, + NFT_INNER_GENEVE, }; enum nft_inner_flags { diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index c43a2fe0ceb7..19fdc8c70cd1 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -181,6 +182,22 @@ static int nft_inner_parse_tunhdr(const struct nft_inner *priv, ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; *off += priv->hdrsize; + switch (priv->type) { + case NFT_INNER_GENEVE: { + struct genevehdr *gnvh, _gnvh; + + gnvh = skb_header_pointer(pkt->skb, pkt->inneroff, + sizeof(_gnvh), &_gnvh); + if (!gnvh) + return -1; + + *off += gnvh->opt_len * 4; + } + break; + default: + break; + } + return 0; } -- cgit v1.2.3 From 73feb8d5fa3b755bb51077c0aabfb6aa556fd498 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 25 Oct 2022 15:41:41 +0200 Subject: kallsyms: Make module_kallsyms_on_each_symbol generally available Making module_kallsyms_on_each_symbol generally available, so it can be used outside CONFIG_LIVEPATCH option in following changes. Rather than adding another ifdef option let's make the function generally available (when CONFIG_KALLSYMS and CONFIG_MODULES options are defined). Cc: Christoph Hellwig Acked-by: Song Liu Signed-off-by: Jiri Olsa Link: https://lore.kernel.org/r/20221025134148.3300700-2-jolsa@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/module.h | 9 +++++++++ kernel/module/kallsyms.c | 2 -- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/module.h b/include/linux/module.h index ec61fb53979a..35876e89eb93 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -879,8 +879,17 @@ static inline bool module_sig_ok(struct module *module) } #endif /* CONFIG_MODULE_SIG */ +#if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data); +#else +static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index f5c5c9175333..4523f99b0358 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -494,7 +494,6 @@ unsigned long module_kallsyms_lookup_name(const char *name) return ret; } -#ifdef CONFIG_LIVEPATCH int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, unsigned long), void *data) @@ -531,4 +530,3 @@ out: mutex_unlock(&module_mutex); return ret; } -#endif /* CONFIG_LIVEPATCH */ -- cgit v1.2.3 From b5f0de6df6dce8d641ef58ef7012f3304dffb9a1 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Oct 2022 02:56:03 -0700 Subject: net: dev: Convert sa_data to flexible array in struct sockaddr One of the worst offenders of "fake flexible arrays" is struct sockaddr, as it is the classic example of why GCC and Clang have been traditionally forced to treat all trailing arrays as fake flexible arrays: in the distant misty past, sa_data became too small, and code started just treating it as a flexible array, even though it was fixed-size. The special case by the compiler is specifically that sizeof(sa->sa_data) and FORTIFY_SOURCE (which uses __builtin_object_size(sa->sa_data, 1)) do not agree (14 and -1 respectively), which makes FORTIFY_SOURCE treat it as a flexible array. However, the coming -fstrict-flex-arrays compiler flag will remove these special cases so that FORTIFY_SOURCE can gain coverage over all the trailing arrays in the kernel that are _not_ supposed to be treated as a flexible array. To deal with this change, convert sa_data to a true flexible array. To keep the structure size the same, move sa_data into a union with a newly introduced sa_data_min with the original size. The result is that FORTIFY_SOURCE can continue to have no idea how large sa_data may actually be, but anything using sizeof(sa->sa_data) must switch to sizeof(sa->sa_data_min). Cc: Jens Axboe Cc: Pavel Begunkov Cc: David Ahern Cc: Dylan Yudaken Cc: Yajun Deng Cc: Petr Machata Cc: Hangbin Liu Cc: Leon Romanovsky Cc: syzbot Cc: Willem de Bruijn Cc: Pablo Neira Ayuso Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221018095503.never.671-kees@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/socket.h | 5 ++++- net/core/dev.c | 2 +- net/core/dev_ioctl.c | 2 +- net/packet/af_packet.c | 10 +++++----- 4 files changed, 11 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/socket.h b/include/linux/socket.h index de3701a2a212..13c3a237b9c9 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -33,7 +33,10 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - char sa_data[14]; /* 14 bytes of protocol address */ + union { + char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ + DECLARE_FLEX_ARRAY(char, sa_data); + }; }; struct linger { diff --git a/net/core/dev.c b/net/core/dev.c index 3be256051e99..fff62068a53d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8822,7 +8822,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 7674bb9f3076..5cdbfbf9a7dc 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -342,7 +342,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6ce8dd19f33c..8c5b3da0c29f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3277,7 +3277,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3288,8 +3288,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, pkt_sk(sk)->num); } @@ -3561,11 +3561,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); -- cgit v1.2.3 From 271de525e1d7f564e88a9d212c50998b49a54476 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Oct 2022 11:45:16 -0700 Subject: bpf: Remove prog->active check for bpf_lsm and bpf_iter The commit 64696c40d03c ("bpf: Add __bpf_prog_{enter,exit}_struct_ops for struct_ops trampoline") removed prog->active check for struct_ops prog. The bpf_lsm and bpf_iter is also using trampoline. Like struct_ops, the bpf_lsm and bpf_iter have fixed hooks for the prog to attach. The kernel does not call the same hook in a recursive way. This patch also removes the prog->active check for bpf_lsm and bpf_iter. A later patch has a test to reproduce the recursion issue for a sleepable bpf_lsm program. This patch appends the '_recur' naming to the existing enter and exit functions that track the prog->active counter. New __bpf_prog_{enter,exit}[_sleepable] function are added to skip the prog->active tracking. The '_struct_ops' version is also removed. It also moves the decision on picking the enter and exit function to the new bpf_trampoline_{enter,exit}(). It returns the '_recur' ones for all tracing progs to use. For bpf_lsm, bpf_iter, struct_ops (no prog->active tracking after 64696c40d03c), and bpf_lsm_cgroup (no prog->active tracking after 69fd337a975c7), it will return the functions that don't track the prog->active. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221025184524.3526117-2-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- arch/arm64/net/bpf_jit_comp.c | 9 ++--- arch/x86/net/bpf_jit_comp.c | 19 ++-------- include/linux/bpf.h | 24 ++++++------- include/linux/bpf_verifier.h | 15 +++++++- kernel/bpf/syscall.c | 5 +-- kernel/bpf/trampoline.c | 80 ++++++++++++++++++++++++++++++++++++------- 6 files changed, 98 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 30f76178608b..62f805f427b7 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1649,13 +1649,8 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l, struct bpf_prog *p = l->link.prog; int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); - if (p->aux->sleepable) { - enter_prog = (u64)__bpf_prog_enter_sleepable; - exit_prog = (u64)__bpf_prog_exit_sleepable; - } else { - enter_prog = (u64)__bpf_prog_enter; - exit_prog = (u64)__bpf_prog_exit; - } + enter_prog = (u64)bpf_trampoline_enter(p); + exit_prog = (u64)bpf_trampoline_exit(p); if (l->cookie == 0) { /* if cookie is zero, one instruction is enough to store it */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index d7dd8e0db8da..36ffe67ad6e5 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1894,10 +1894,6 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, int run_ctx_off, bool save_ret) { - void (*exit)(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit; - u64 (*enter)(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter; u8 *prog = *pprog; u8 *jmp_insn; int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); @@ -1916,23 +1912,12 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off); - if (p->aux->sleepable) { - enter = __bpf_prog_enter_sleepable; - exit = __bpf_prog_exit_sleepable; - } else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) { - enter = __bpf_prog_enter_struct_ops; - exit = __bpf_prog_exit_struct_ops; - } else if (p->expected_attach_type == BPF_LSM_CGROUP) { - enter = __bpf_prog_enter_lsm_cgroup; - exit = __bpf_prog_exit_lsm_cgroup; - } - /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: lea rsi, [rbp - ctx_cookie_off] */ EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_call(&prog, enter, prog)) + if (emit_call(&prog, bpf_trampoline_enter(p), prog)) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -1977,7 +1962,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_call(&prog, exit, prog)) + if (emit_call(&prog, bpf_trampoline_exit(p), prog)) return -EINVAL; *pprog = prog; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9e7d46d16032..1279e699dc98 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -854,22 +854,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *i const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *orig_call); -/* these two functions are called from generated trampoline */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); -u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx); -void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx); +u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); +typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx); +typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx); +bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); +bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); struct bpf_ksym { unsigned long start; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9e1e6965f407..1a32baa78ce2 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -642,10 +642,23 @@ static inline u32 type_flag(u32 type) } /* only use after check_attach_btf_id() */ -static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) +static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { return prog->type == BPF_PROG_TYPE_EXT ? prog->aux->dst_prog->type : prog->type; } +static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) +{ + switch (resolve_prog_type(prog)) { + case BPF_PROG_TYPE_TRACING: + return prog->expected_attach_type != BPF_TRACE_ITER; + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_LSM: + return false; + default: + return true; + } +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7b373a5e861f..a0b4266196a8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -5133,13 +5133,14 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) run_ctx.bpf_cookie = 0; run_ctx.saved_run_ctx = NULL; - if (!__bpf_prog_enter_sleepable(prog, &run_ctx)) { + if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); - __bpf_prog_exit_sleepable(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); + __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, + &run_ctx); bpf_prog_put(prog); return 0; #endif diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index bf0906e1e2b9..d6395215b849 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -864,7 +864,7 @@ static __always_inline u64 notrace bpf_prog_start_time(void) * [2..MAX_U64] - execute bpf prog and record execution time. * This is start time. */ -u64 notrace __bpf_prog_enter(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { rcu_read_lock(); @@ -901,7 +901,8 @@ static void notrace update_prog_stats(struct bpf_prog *prog, } } -void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -912,8 +913,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_ rcu_read_unlock(); } -u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { /* Runtime stats are exported via actual BPF_LSM_CGROUP @@ -927,8 +928,8 @@ u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog, return NO_START_TIME; } -void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -937,7 +938,8 @@ void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start, rcu_read_unlock(); } -u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx) +u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) { rcu_read_lock_trace(); migrate_disable(); @@ -953,8 +955,8 @@ u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_r return bpf_prog_start_time(); } -void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -964,8 +966,30 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, rcu_read_unlock_trace(); } -u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) +static u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) +{ + rcu_read_lock_trace(); + migrate_disable(); + might_fault(); + + run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx); + + return bpf_prog_start_time(); +} + +static void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) +{ + bpf_reset_run_ctx(run_ctx->saved_run_ctx); + + update_prog_stats(prog, start); + migrate_enable(); + rcu_read_unlock_trace(); +} + +static u64 notrace __bpf_prog_enter(struct bpf_prog *prog, + struct bpf_tramp_run_ctx *run_ctx) __acquires(RCU) { rcu_read_lock(); @@ -976,8 +1000,8 @@ u64 notrace __bpf_prog_enter_struct_ops(struct bpf_prog *prog, return bpf_prog_start_time(); } -void notrace __bpf_prog_exit_struct_ops(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) +static void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, + struct bpf_tramp_run_ctx *run_ctx) __releases(RCU) { bpf_reset_run_ctx(run_ctx->saved_run_ctx); @@ -997,6 +1021,36 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) percpu_ref_put(&tr->pcref); } +bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) +{ + bool sleepable = prog->aux->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_enter_sleepable_recur : + __bpf_prog_enter_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_enter_lsm_cgroup; + + return sleepable ? __bpf_prog_enter_sleepable : __bpf_prog_enter; +} + +bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) +{ + bool sleepable = prog->aux->sleepable; + + if (bpf_prog_check_recur(prog)) + return sleepable ? __bpf_prog_exit_sleepable_recur : + __bpf_prog_exit_recur; + + if (resolve_prog_type(prog) == BPF_PROG_TYPE_LSM && + prog->expected_attach_type == BPF_LSM_CGROUP) + return __bpf_prog_exit_lsm_cgroup; + + return sleepable ? __bpf_prog_exit_sleepable : __bpf_prog_exit; +} + int __weak arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, -- cgit v1.2.3 From 0593dd34e53489557569d5e6d27371b49aa9b41f Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Oct 2022 11:45:17 -0700 Subject: bpf: Append _recur naming to the bpf_task_storage helper proto This patch adds the "_recur" naming to the bpf_task_storage_{get,delete} proto. In a latter patch, they will only be used by the tracing programs that requires a deadlock detection because a tracing prog may use bpf_task_storage_{get,delete} recursively and cause a deadlock. Another following patch will add a different helper proto for the non tracing programs because they do not need the deadlock prevention. This patch does this rename to prepare for this future proto additions. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221025184524.3526117-3-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- kernel/bpf/bpf_task_storage.c | 12 ++++++------ kernel/trace/bpf_trace.c | 4 ++-- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1279e699dc98..b04fe3f4342e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2519,8 +2519,8 @@ extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; -extern const struct bpf_func_proto bpf_task_storage_get_proto; -extern const struct bpf_func_proto bpf_task_storage_delete_proto; +extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; +extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 6f290623347e..bce50ae03f42 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -228,7 +228,7 @@ out: } /* *gfp_flags* is a hidden argument provided by the verifier */ -BPF_CALL_5(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, +BPF_CALL_5(bpf_task_storage_get_recur, struct bpf_map *, map, struct task_struct *, task, void *, value, u64, flags, gfp_t, gfp_flags) { struct bpf_local_storage_data *sdata; @@ -260,7 +260,7 @@ unlock: (unsigned long)sdata->data; } -BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, +BPF_CALL_2(bpf_task_storage_delete_recur, struct bpf_map *, map, struct task_struct *, task) { int ret; @@ -322,8 +322,8 @@ const struct bpf_map_ops task_storage_map_ops = { .map_owner_storage_ptr = task_storage_ptr, }; -const struct bpf_func_proto bpf_task_storage_get_proto = { - .func = bpf_task_storage_get, +const struct bpf_func_proto bpf_task_storage_get_recur_proto = { + .func = bpf_task_storage_get_recur, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, @@ -333,8 +333,8 @@ const struct bpf_func_proto bpf_task_storage_get_proto = { .arg4_type = ARG_ANYTHING, }; -const struct bpf_func_proto bpf_task_storage_delete_proto = { - .func = bpf_task_storage_delete, +const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { + .func = bpf_task_storage_delete_recur, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 2460e38f75ff..83b9b9afe235 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1488,9 +1488,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; case BPF_FUNC_task_storage_get: - return &bpf_task_storage_get_proto; + return &bpf_task_storage_get_recur_proto; case BPF_FUNC_task_storage_delete: - return &bpf_task_storage_delete_proto; + return &bpf_task_storage_delete_recur_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; case BPF_FUNC_snprintf: -- cgit v1.2.3 From 4279adb094a17132423f1271c3d11b593fc2327e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Oct 2022 11:45:20 -0700 Subject: bpf: Add new bpf_task_storage_get proto with no deadlock detection The bpf_lsm and bpf_iter do not recur that will cause a deadlock. The situation is similar to the bpf_pid_task_storage_lookup_elem() which is called from the syscall map_lookup_elem. It does not need deadlock detection. Otherwise, it will cause unnecessary failure when calling the bpf_task_storage_get() helper. This patch adds bpf_task_storage_get proto that does not do deadlock detection. It will be used by bpf_lsm and bpf_iter programs. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221025184524.3526117-6-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/bpf_task_storage.c | 28 ++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 5 ++++- 3 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b04fe3f4342e..ef3f98afa45d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2520,6 +2520,7 @@ extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; +extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index bc52bc8b59f7..c3a841be438f 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -269,6 +269,23 @@ BPF_CALL_5(bpf_task_storage_get_recur, struct bpf_map *, map, struct task_struct return (unsigned long)data; } +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, + task, void *, value, u64, flags, gfp_t, gfp_flags) +{ + void *data; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~BPF_LOCAL_STORAGE_GET_F_CREATE || !task) + return (unsigned long)NULL; + + bpf_task_storage_lock(); + data = __bpf_task_storage_get(map, task, value, flags, + gfp_flags, true); + bpf_task_storage_unlock(); + return (unsigned long)data; +} + BPF_CALL_2(bpf_task_storage_delete_recur, struct bpf_map *, map, struct task_struct *, task) { @@ -342,6 +359,17 @@ const struct bpf_func_proto bpf_task_storage_get_recur_proto = { .arg4_type = ARG_ANYTHING, }; +const struct bpf_func_proto bpf_task_storage_get_proto = { + .func = bpf_task_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { .func = bpf_task_storage_delete_recur, .gpl_only = false, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 83b9b9afe235..e9759b0f7199 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -1488,7 +1489,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_this_cpu_ptr: return &bpf_this_cpu_ptr_proto; case BPF_FUNC_task_storage_get: - return &bpf_task_storage_get_recur_proto; + if (bpf_prog_check_recur(prog)) + return &bpf_task_storage_get_recur_proto; + return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_recur_proto; case BPF_FUNC_for_each_map_elem: -- cgit v1.2.3 From 8a7dac37f27a3dfbd814bf29a73d6417db2c81d9 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 25 Oct 2022 11:45:22 -0700 Subject: bpf: Add new bpf_task_storage_delete proto with no deadlock detection The bpf_lsm and bpf_iter do not recur that will cause a deadlock. The situation is similar to the bpf_pid_task_storage_delete_elem() which is called from the syscall map_delete_elem. It does not need deadlock detection. Otherwise, it will cause unnecessary failure when calling the bpf_task_storage_delete() helper. This patch adds bpf_task_storage_delete proto that does not do deadlock detection. It will be used by bpf_lsm and bpf_iter program. Signed-off-by: Martin KaFai Lau Link: https://lore.kernel.org/r/20221025184524.3526117-8-martin.lau@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/bpf_task_storage.c | 28 ++++++++++++++++++++++++++++ kernel/trace/bpf_trace.c | 4 +++- 3 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ef3f98afa45d..a5dbac8f5aba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2522,6 +2522,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; +extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index f3f79b618a68..ba3fe72d1fa5 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -311,6 +311,25 @@ BPF_CALL_2(bpf_task_storage_delete_recur, struct bpf_map *, map, struct task_str return ret; } +BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, + task) +{ + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!task) + return -EINVAL; + + bpf_task_storage_lock(); + /* This helper must only be called from places where the lifetime of the task + * is guaranteed. Either by being refcounted or by being protected + * by an RCU read-side critical section. + */ + ret = task_storage_delete(task, map, true); + bpf_task_storage_unlock(); + return ret; +} + static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; @@ -382,3 +401,12 @@ const struct bpf_func_proto bpf_task_storage_delete_recur_proto = { .arg2_type = ARG_PTR_TO_BTF_ID, .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; + +const struct bpf_func_proto bpf_task_storage_delete_proto = { + .func = bpf_task_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], +}; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e9759b0f7199..eed1bd952c3a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1493,7 +1493,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_get_recur_proto; return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: - return &bpf_task_storage_delete_recur_proto; + if (bpf_prog_check_recur(prog)) + return &bpf_task_storage_delete_recur_proto; + return &bpf_task_storage_delete_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; case BPF_FUNC_snprintf: -- cgit v1.2.3 From 5e67b8ef125bb6e83bf0f0442ad7ffc09e7956f9 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 25 Oct 2022 21:28:40 -0700 Subject: bpf: Make struct cgroup btf id global Make struct cgroup btf id global so later patch can reuse the same btf id. Acked-by: David Vernet Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221026042840.672602-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 1 + kernel/bpf/cgroup_iter.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 2aea877d644f..c9744efd202f 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -265,5 +265,6 @@ MAX_BTF_TRACING_TYPE, }; extern u32 btf_tracing_ids[]; +extern u32 bpf_cgroup_btf_id[]; #endif diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 0d200a993489..c6ffc706d583 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -157,7 +157,7 @@ static const struct seq_operations cgroup_iter_seq_ops = { .show = cgroup_iter_seq_show, }; -BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup) +BTF_ID_LIST_GLOBAL_SINGLE(bpf_cgroup_btf_id, struct, cgroup) static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux) { -- cgit v1.2.3 From c83597fa5dc6b322e9bdf929e5f4136a3f4aa4db Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 25 Oct 2022 21:28:45 -0700 Subject: bpf: Refactor some inode/task/sk storage functions for reuse Refactor codes so that inode/task/sk storage implementation can maximally share the same code. I also added some comments in new function bpf_local_storage_unlink_nolock() to make codes easy to understand. There is no functionality change. Acked-by: David Vernet Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221026042845.672944-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_local_storage.h | 17 ++-- kernel/bpf/bpf_inode_storage.c | 38 +------- kernel/bpf/bpf_local_storage.c | 190 ++++++++++++++++++++++++-------------- kernel/bpf/bpf_task_storage.c | 38 +------- net/core/bpf_sk_storage.c | 35 +------ 5 files changed, 137 insertions(+), 181 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 7ea18d4da84b..6d37a40cd90e 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -116,21 +116,22 @@ static struct bpf_local_storage_cache name = { \ .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ } -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx); - /* Helper functions for bpf_local_storage */ int bpf_local_storage_map_alloc_check(union bpf_attr *attr); -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); +struct bpf_map * +bpf_local_storage_map_alloc(union bpf_attr *attr, + struct bpf_local_storage_cache *cache); struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, +bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage); + +void bpf_local_storage_map_free(struct bpf_map *map, + struct bpf_local_storage_cache *cache, int __percpu *busy_counter); int bpf_local_storage_map_check_btf(const struct bpf_map *map, @@ -141,10 +142,6 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem); -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_omem, bool use_trace_rcu); - void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 5f7683b19199..6a1d4d22816a 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -56,11 +56,9 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, void bpf_inode_storage_free(struct inode *inode) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_inode_storage = false; struct bpf_storage_blob *bsb; - struct hlist_node *n; bsb = bpf_inode(inode); if (!bsb) @@ -74,30 +72,11 @@ void bpf_inode_storage_free(struct inode *inode) return; } - /* Neither the bpf_prog nor the bpf-map's syscall - * could be modifying the local_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * local_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the local_storage->list and - * the map's bucket->list. - */ raw_spin_lock_bh(&local_storage->lock); - hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { - /* Always unlink from map before unlinking from - * local_storage. - */ - bpf_selem_unlink_map(selem); - free_inode_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); - } + free_inode_storage = bpf_local_storage_unlink_nolock(local_storage); raw_spin_unlock_bh(&local_storage->lock); rcu_read_unlock(); - /* free_inoode_storage should always be true as long as - * local_storage->list was non-empty. - */ if (free_inode_storage) kfree_rcu(local_storage, rcu); } @@ -226,23 +205,12 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &inode_cache); } static void inode_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, NULL); + bpf_local_storage_map_free(map, &inode_cache, NULL); } BTF_ID_LIST_SINGLE(inode_storage_map_btf_ids, struct, diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 781d14167140..93d9b1b17bc8 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -113,9 +113,9 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_mem, bool use_trace_rcu) +static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_mem, bool use_trace_rcu) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -501,7 +501,7 @@ unlock_err: return ERR_PTR(err); } -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) +static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; @@ -525,76 +525,14 @@ u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) return res; } -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx) +static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, - int __percpu *busy_counter) -{ - struct bpf_local_storage_elem *selem; - struct bpf_local_storage_map_bucket *b; - unsigned int i; - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the owner->storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or when the storage is freed e.g. - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe( - rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_local_storage_elem, map_node))) { - if (busy_counter) { - migrate_disable(); - this_cpu_inc(*busy_counter); - } - bpf_selem_unlink(selem, false); - if (busy_counter) { - this_cpu_dec(*busy_counter); - migrate_enable(); - } - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* While freeing the storage we may still need to access the map. - * - * e.g. when bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exit immediately. - * - * However, while freeing the storage one still needs to access the - * smap->elem_size to do the uncharging in - * bpf_selem_unlink_storage_nolock(). - * - * Hence, wait another rcu grace period for the storage to be freed. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - bpf_map_area_free(smap); -} - int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || @@ -614,7 +552,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) +static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; unsigned int i; @@ -664,3 +602,117 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, return 0; } + +bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) +{ + struct bpf_local_storage_elem *selem; + bool free_storage = false; + struct hlist_node *n; + + /* Neither the bpf_prog nor the bpf_map's syscall + * could be modifying the local_storage->list now. + * Thus, no elem can be added to or deleted from the + * local_storage->list by the bpf_prog or by the bpf_map's syscall. + * + * It is racing with bpf_local_storage_map_free() alone + * when unlinking elem from the local_storage->list and + * the map's bucket->list. + */ + hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { + /* Always unlink from map before unlinking from + * local_storage. + */ + bpf_selem_unlink_map(selem); + /* If local_storage list has only one element, the + * bpf_selem_unlink_storage_nolock() will return true. + * Otherwise, it will return false. The current loop iteration + * intends to remove all local storage. So the last iteration + * of the loop will set the free_cgroup_storage to true. + */ + free_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, false, false); + } + + return free_storage; +} + +struct bpf_map * +bpf_local_storage_map_alloc(union bpf_attr *attr, + struct bpf_local_storage_cache *cache) +{ + struct bpf_local_storage_map *smap; + + smap = __bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + + smap->cache_idx = bpf_local_storage_cache_idx_get(cache); + return &smap->map; +} + +void bpf_local_storage_map_free(struct bpf_map *map, + struct bpf_local_storage_cache *cache, + int __percpu *busy_counter) +{ + struct bpf_local_storage_map_bucket *b; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + unsigned int i; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(cache, smap->cache_idx); + + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the owner->storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or when the storage is freed e.g. + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + if (busy_counter) { + migrate_disable(); + this_cpu_inc(*busy_counter); + } + bpf_selem_unlink(selem, false); + if (busy_counter) { + this_cpu_dec(*busy_counter); + migrate_enable(); + } + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exit immediately. + * + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). + * + * Hence, wait another rcu grace period for the storage to be freed. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + bpf_map_area_free(smap); +} diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index ba3fe72d1fa5..8e832db8151a 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -71,10 +71,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, void bpf_task_storage_free(struct task_struct *task) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_task_storage = false; - struct hlist_node *n; unsigned long flags; rcu_read_lock(); @@ -85,32 +83,13 @@ void bpf_task_storage_free(struct task_struct *task) return; } - /* Neither the bpf_prog nor the bpf-map's syscall - * could be modifying the local_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * local_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the local_storage->list and - * the map's bucket->list. - */ bpf_task_storage_lock(); raw_spin_lock_irqsave(&local_storage->lock, flags); - hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { - /* Always unlink from map before unlinking from - * local_storage. - */ - bpf_selem_unlink_map(selem); - free_task_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); - } + free_task_storage = bpf_local_storage_unlink_nolock(local_storage); raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_task_storage_unlock(); rcu_read_unlock(); - /* free_task_storage should always be true as long as - * local_storage->list was non-empty. - */ if (free_task_storage) kfree_rcu(local_storage, rcu); } @@ -337,23 +316,12 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &task_cache); } static void task_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, &bpf_task_storage_busy); + bpf_local_storage_map_free(map, &task_cache, &bpf_task_storage_busy); } BTF_ID_LIST_SINGLE(task_storage_map_btf_ids, struct, bpf_local_storage_map) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..49884e7de080 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -48,10 +48,8 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *sk_storage; bool free_sk_storage = false; - struct hlist_node *n; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); @@ -60,24 +58,8 @@ void bpf_sk_storage_free(struct sock *sk) return; } - /* Netiher the bpf_prog nor the bpf-map's syscall - * could be modifying the sk_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * sk_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the sk_storage->list and - * the map's bucket->list. - */ raw_spin_lock_bh(&sk_storage->lock); - hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { - /* Always unlink from map before unlinking from - * sk_storage. - */ - bpf_selem_unlink_map(selem); - free_sk_storage = bpf_selem_unlink_storage_nolock( - sk_storage, selem, true, false); - } + free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage); raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -87,23 +69,12 @@ void bpf_sk_storage_free(struct sock *sk) static void bpf_sk_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, NULL); + bpf_local_storage_map_free(map, &sk_cache, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, -- cgit v1.2.3 From c4bcfb38a95edb1021a53f2d0356a78120ecfbe4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 25 Oct 2022 21:28:50 -0700 Subject: bpf: Implement cgroup storage available to non-cgroup-attached bpf progs Similar to sk/inode/task storage, implement similar cgroup local storage. There already exists a local storage implementation for cgroup-attached bpf programs. See map type BPF_MAP_TYPE_CGROUP_STORAGE and helper bpf_get_local_storage(). But there are use cases such that non-cgroup attached bpf progs wants to access cgroup local storage data. For example, tc egress prog has access to sk and cgroup. It is possible to use sk local storage to emulate cgroup local storage by storing data in socket. But this is a waste as it could be lots of sockets belonging to a particular cgroup. Alternatively, a separate map can be created with cgroup id as the key. But this will introduce additional overhead to manipulate the new map. A cgroup local storage, similar to existing sk/inode/task storage, should help for this use case. The life-cycle of storage is managed with the life-cycle of the cgroup struct. i.e. the storage is destroyed along with the owning cgroup with a call to bpf_cgrp_storage_free() when cgroup itself is deleted. The userspace map operations can be done by using a cgroup fd as a key passed to the lookup, update and delete operations. Typically, the following code is used to get the current cgroup: struct task_struct *task = bpf_get_current_task_btf(); ... task->cgroups->dfl_cgrp ... and in structure task_struct definition: struct task_struct { .... struct css_set __rcu *cgroups; .... } With sleepable program, accessing task->cgroups is not protected by rcu_read_lock. So the current implementation only supports non-sleepable program and supporting sleepable program will be the next step together with adding rcu_read_lock protection for rcu tagged structures. Since map name BPF_MAP_TYPE_CGROUP_STORAGE has been used for old cgroup local storage support, the new map name BPF_MAP_TYPE_CGRP_STORAGE is used for cgroup storage available to non-cgroup-attached bpf programs. The old cgroup storage supports bpf_get_local_storage() helper to get the cgroup data. The new cgroup storage helper bpf_cgrp_storage_get() can provide similar functionality. While old cgroup storage pre-allocates storage memory, the new mechanism can also pre-allocate with a user space bpf_map_update_elem() call to avoid potential run-time memory allocation failure. Therefore, the new cgroup storage can provide all functionality w.r.t. the old one. So in uapi bpf.h, the old BPF_MAP_TYPE_CGROUP_STORAGE is alias to BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED to indicate the old cgroup storage can be deprecated since the new one can provide the same functionality. Acked-by: David Vernet Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221026042850.673791-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/bpf_types.h | 1 + include/linux/cgroup-defs.h | 4 + include/uapi/linux/bpf.h | 50 ++++++++- kernel/bpf/Makefile | 2 +- kernel/bpf/bpf_cgrp_storage.c | 247 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/helpers.c | 6 + kernel/bpf/syscall.c | 3 +- kernel/bpf/verifier.c | 13 ++- kernel/cgroup/cgroup.c | 1 + kernel/trace/bpf_trace.c | 4 + scripts/bpf_doc.py | 2 + tools/include/uapi/linux/bpf.h | 50 ++++++++- 13 files changed, 385 insertions(+), 5 deletions(-) create mode 100644 kernel/bpf/bpf_cgrp_storage.c (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a5dbac8f5aba..9fd68b0b3e9c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2041,6 +2041,7 @@ struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); void bpf_task_storage_free(struct task_struct *task); +void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, @@ -2295,6 +2296,10 @@ static inline bool has_current_bpf_ctx(void) static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } + +static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2535,6 +2540,8 @@ extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; +extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; +extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2c6a4f2562a7..d4ee3ccd3753 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -86,6 +86,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops) #ifdef CONFIG_CGROUPS BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_CGRP_STORAGE, cgrp_storage_map_ops) #endif #ifdef CONFIG_CGROUP_BPF BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..c466fdc3a32a 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -504,6 +504,10 @@ struct cgroup { /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_local_storage __rcu *bpf_cgrp_storage; +#endif + /* All ancestors including self */ struct cgroup *ancestors[]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -922,7 +922,14 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, @@ -935,6 +942,7 @@ enum bpf_map_type { BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -5435,6 +5443,44 @@ union bpf_attr { * **-E2BIG** if user-space has tried to publish a sample which is * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define ___BPF_FUNC_MAPPER(FN, ctx...) \ FN(unspec, 0, ##ctx) \ @@ -5647,6 +5693,8 @@ union bpf_attr { FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ FN(ktime_get_tai_ns, 208, ##ctx) \ FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 341c94f208f4..3a12e6b400a2 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -25,7 +25,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif ifeq ($(CONFIG_CGROUPS),y) -obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o +obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o bpf_cgrp_storage.o endif obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c new file mode 100644 index 000000000000..309403800f82 --- /dev/null +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + */ + +#include +#include +#include +#include +#include + +DEFINE_BPF_STORAGE_CACHE(cgroup_cache); + +static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy); + +static void bpf_cgrp_storage_lock(void) +{ + migrate_disable(); + this_cpu_inc(bpf_cgrp_storage_busy); +} + +static void bpf_cgrp_storage_unlock(void) +{ + this_cpu_dec(bpf_cgrp_storage_busy); + migrate_enable(); +} + +static bool bpf_cgrp_storage_trylock(void) +{ + migrate_disable(); + if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) { + this_cpu_dec(bpf_cgrp_storage_busy); + migrate_enable(); + return false; + } + return true; +} + +static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) +{ + struct cgroup *cg = owner; + + return &cg->bpf_cgrp_storage; +} + +void bpf_cgrp_storage_free(struct cgroup *cgroup) +{ + struct bpf_local_storage *local_storage; + bool free_cgroup_storage = false; + unsigned long flags; + + rcu_read_lock(); + local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); + if (!local_storage) { + rcu_read_unlock(); + return; + } + + bpf_cgrp_storage_lock(); + raw_spin_lock_irqsave(&local_storage->lock, flags); + free_cgroup_storage = bpf_local_storage_unlink_nolock(local_storage); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_cgrp_storage_unlock(); + rcu_read_unlock(); + + if (free_cgroup_storage) + kfree_rcu(local_storage, rcu); +} + +static struct bpf_local_storage_data * +cgroup_storage_lookup(struct cgroup *cgroup, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_local_storage *cgroup_storage; + struct bpf_local_storage_map *smap; + + cgroup_storage = rcu_dereference_check(cgroup->bpf_cgrp_storage, + bpf_rcu_lock_held()); + if (!cgroup_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(cgroup_storage, smap, cacheit_lockit); +} + +static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct cgroup *cgroup; + int fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return ERR_CAST(cgroup); + + bpf_cgrp_storage_lock(); + sdata = cgroup_storage_lookup(cgroup, map, true); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return sdata ? sdata->data : NULL; +} + +static int bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *sdata; + struct cgroup *cgroup; + int fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return PTR_ERR(cgroup); + + bpf_cgrp_storage_lock(); + sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, + value, map_flags, GFP_ATOMIC); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return PTR_ERR_OR_ZERO(sdata); +} + +static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = cgroup_storage_lookup(cgroup, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata), true); + return 0; +} + +static int bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct cgroup *cgroup; + int err, fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return PTR_ERR(cgroup); + + bpf_cgrp_storage_lock(); + err = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return err; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) +{ + return bpf_local_storage_map_alloc(attr, &cgroup_cache); +} + +static void cgroup_storage_map_free(struct bpf_map *map) +{ + bpf_local_storage_map_free(map, &cgroup_cache, NULL); +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, + void *, value, u64, flags, gfp_t, gfp_flags) +{ + struct bpf_local_storage_data *sdata; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + if (!cgroup) + return (unsigned long)NULL; + + if (!bpf_cgrp_storage_trylock()) + return (unsigned long)NULL; + + sdata = cgroup_storage_lookup(cgroup, map, true); + if (sdata) + goto unlock; + + /* only allocate new storage, when the cgroup is refcounted */ + if (!percpu_ref_is_dying(&cgroup->self.refcnt) && + (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) + sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, + value, BPF_NOEXIST, gfp_flags); + +unlock: + bpf_cgrp_storage_unlock(); + return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; +} + +BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgroup) +{ + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!cgroup) + return -EINVAL; + + if (!bpf_cgrp_storage_trylock()) + return -EBUSY; + + ret = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + return ret; +} + +BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_local_storage_map) +const struct bpf_map_ops cgrp_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = cgroup_storage_map_alloc, + .map_free = cgroup_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_cgrp_storage_lookup_elem, + .map_update_elem = bpf_cgrp_storage_update_elem, + .map_delete_elem = bpf_cgrp_storage_delete_elem, + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_id = &cgroup_storage_map_btf_ids[0], + .map_owner_storage_ptr = cgroup_storage_ptr, +}; + +const struct bpf_func_proto bpf_cgrp_storage_get_proto = { + .func = bpf_cgrp_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_cgroup_btf_id[0], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { + .func = bpf_cgrp_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_cgroup_btf_id[0], +}; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a6b04faed282..124fd199ce5c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1663,6 +1663,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_dynptr_write_proto; case BPF_FUNC_dynptr_data: return &bpf_dynptr_data_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_cgrp_storage_get: + return &bpf_cgrp_storage_get_proto; + case BPF_FUNC_cgrp_storage_delete: + return &bpf_cgrp_storage_delete_proto; +#endif default: break; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a0b4266196a8..11df90962101 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1016,7 +1016,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && - map->map_type != BPF_MAP_TYPE_TASK_STORAGE) + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ddc1452cf023..8f849a763b79 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6350,6 +6350,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_CGRP_STORAGE: + if (func_id != BPF_FUNC_cgrp_storage_get && + func_id != BPF_FUNC_cgrp_storage_delete) + goto error; + break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) @@ -6462,6 +6467,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; + case BPF_FUNC_cgrp_storage_get: + case BPF_FUNC_cgrp_storage_delete: + if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) + goto error; + break; default: break; } @@ -14139,7 +14149,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->imm == BPF_FUNC_task_storage_get || insn->imm == BPF_FUNC_sk_storage_get || - insn->imm == BPF_FUNC_inode_storage_get) { + insn->imm == BPF_FUNC_inode_storage_get || + insn->imm == BPF_FUNC_cgrp_storage_get) { if (env->prog->aux->sleepable) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); else diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 764bdd5fd8d1..12001928511b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5245,6 +5245,7 @@ static void css_free_rwork_fn(struct work_struct *work) atomic_dec(&cgrp->root->nr_cgrps); cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); + bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index eed1bd952c3a..ce0228c72a93 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1455,6 +1455,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; + case BPF_FUNC_cgrp_storage_get: + return &bpf_cgrp_storage_get_proto; + case BPF_FUNC_cgrp_storage_delete: + return &bpf_cgrp_storage_delete_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index c0e6690be82a..fdb0aff8cb5a 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -685,6 +685,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct __sk_buff', 'struct sk_msg_md', @@ -742,6 +743,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct path', 'struct btf_ptr', 'struct inode', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -922,7 +922,14 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, @@ -935,6 +942,7 @@ enum bpf_map_type { BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -5435,6 +5443,44 @@ union bpf_attr { * **-E2BIG** if user-space has tried to publish a sample which is * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define ___BPF_FUNC_MAPPER(FN, ctx...) \ FN(unspec, 0, ##ctx) \ @@ -5647,6 +5693,8 @@ union bpf_attr { FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ FN(ktime_get_tai_ns, 208, ##ctx) \ FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't -- cgit v1.2.3 From 28581b9c2c94cc912354eadc98c1146fdc7092e6 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Tue, 25 Oct 2022 13:53:00 +0300 Subject: bond: Disable TLS features indication Bond agnostically interacts with TLS device-offload requests via the .ndo_sk_get_lower_dev operation. Return value is true iff bond guarantees fixed mapping between the TLS connection and a lower netdev. Due to this nature, the bond TLS device offload features are not explicitly controllable in the bond layer. As of today, these are read-only values based on the evaluation of bond_sk_check(). However, this indication might be incorrect and misleading, when the feature bits are "fixed" by some dependency features. For example, NETIF_F_HW_TLS_TX/RX are forcefully cleared in case the corresponding checksum offload is disabled. But in fact the bond ability to still offload TLS connections to the lower device is not hurt. This means that these bits can not be trusted, and hence better become unused. This patch revives some old discussion [1] and proposes a much simpler solution: Clear the bond's TLS features bits. Everyone should stop reading them. [1] https://lore.kernel.org/netdev/20210526095747.22446-1-tariqt@nvidia.com/ Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20221025105300.4718-1-tariqt@nvidia.com Signed-off-by: Paolo Abeni --- drivers/net/bonding/bond_main.c | 13 +------------ drivers/net/bonding/bond_options.c | 18 ------------------ include/net/bonding.h | 4 ---- 3 files changed, 1 insertion(+), 34 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index e84c49bf4d0c..1cd4e71916f8 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -307,7 +307,7 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, return dev_queue_xmit(skb); } -bool bond_sk_check(struct bonding *bond) +static bool bond_sk_check(struct bonding *bond) { switch (BOND_MODE(bond)) { case BOND_MODE_8023AD: @@ -1398,13 +1398,6 @@ static netdev_features_t bond_fix_features(struct net_device *dev, netdev_features_t mask; struct slave *slave; -#if IS_ENABLED(CONFIG_TLS_DEVICE) - if (bond_sk_check(bond)) - features |= BOND_TLS_FEATURES; - else - features &= ~BOND_TLS_FEATURES; -#endif - mask = features; features &= ~NETIF_F_ONE_FOR_ALL; @@ -5806,10 +5799,6 @@ void bond_setup(struct net_device *bond_dev) if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP) bond_dev->features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ -#if IS_ENABLED(CONFIG_TLS_DEVICE) - if (bond_sk_check(bond)) - bond_dev->features |= BOND_TLS_FEATURES; -#endif } /* Destroy a bonding device. diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 3498db1c1b3c..f71d5517f829 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -842,19 +842,6 @@ static bool bond_set_xfrm_features(struct bonding *bond) return true; } -static bool bond_set_tls_features(struct bonding *bond) -{ - if (!IS_ENABLED(CONFIG_TLS_DEVICE)) - return false; - - if (bond_sk_check(bond)) - bond->dev->wanted_features |= BOND_TLS_FEATURES; - else - bond->dev->wanted_features &= ~BOND_TLS_FEATURES; - - return true; -} - static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { @@ -885,7 +872,6 @@ static int bond_option_mode_set(struct bonding *bond, bool update = false; update |= bond_set_xfrm_features(bond); - update |= bond_set_tls_features(bond); if (update) netdev_update_features(bond->dev); @@ -1418,10 +1404,6 @@ static int bond_option_xmit_hash_policy_set(struct bonding *bond, newval->string, newval->value); bond->params.xmit_policy = newval->value; - if (bond->dev->reg_state == NETREG_REGISTERED) - if (bond_set_tls_features(bond)) - netdev_update_features(bond->dev); - return 0; } diff --git a/include/net/bonding.h b/include/net/bonding.h index e999f851738b..ea36ab7f9e72 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -92,8 +92,6 @@ #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) -#define BOND_TLS_FEATURES (NETIF_F_HW_TLS_TX | NETIF_F_HW_TLS_RX) - #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -280,8 +278,6 @@ struct bond_vlan_tag { unsigned short vlan_id; }; -bool bond_sk_check(struct bonding *bond); - /** * Returns NULL if the net_device does not belong to any of the bond's slaves * -- cgit v1.2.3 From e753df8fbca592d36f539ed950fcdf412166c549 Mon Sep 17 00:00:00 2001 From: Michal Jaron Date: Tue, 25 Oct 2022 09:12:52 -0700 Subject: ice: Add support Flex RXD Add new VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC flag, opcode VIRTCHNL_OP_GET_SUPPORTED_RXDIDS and add member rxdid in struct virtchnl_rxq_info to support AVF Flex RXD extension. Add support to allow VF to query flexible descriptor RXDIDs supported by DDP package and configure Rx queues with selected RXDID for IAVF. Add code to allow VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message to be processed. Add necessary macros for registers. Signed-off-by: Leyi Rong Signed-off-by: Xu Ting Signed-off-by: Michal Jaron Signed-off-by: Mateusz Palczewski Tested-by: Maxime Coquelin Tested-by: Konrad Jankowski Signed-off-by: Jacob Keller Link: https://lore.kernel.org/r/20221025161252.1952939-1-jacob.e.keller@intel.com Signed-off-by: Paolo Abeni --- drivers/net/ethernet/intel/ice/ice.h | 2 + drivers/net/ethernet/intel/ice/ice_hw_autogen.h | 3 + drivers/net/ethernet/intel/ice/ice_virtchnl.c | 86 ++++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_virtchnl.h | 2 + .../ethernet/intel/ice/ice_virtchnl_allowlist.c | 6 ++ include/linux/avf/virtchnl.h | 14 +++- 6 files changed, 111 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d75c8d11f867..f88ee051e71c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -609,6 +609,8 @@ struct ice_pf { u16 num_dmac_chnl_fltrs; struct hlist_head tc_flower_fltr_list; + u64 supported_rxdids; + __le64 nvm_phy_type_lo; /* NVM PHY type low */ __le64 nvm_phy_type_hi; /* NVM PHY type high */ struct ice_link_default_override_tlv link_dflt_override; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index d16738a3d3a7..a92dc9a16035 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -110,6 +110,9 @@ #define PRTDCB_TUP2TC 0x001D26C0 #define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4)) #define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4)) +#define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0 #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 2b4c791b6cba..c1fa94381f4e 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -462,6 +462,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; } + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; @@ -1618,6 +1621,9 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } for (i = 0; i < qci->num_queue_pairs; i++) { + struct ice_hw *hw; + u32 rxdid; + u16 pf_q; qpi = &qci->qpair[i]; if (qpi->txq.vsi_id != qci->vsi_id || qpi->rxq.vsi_id != qci->vsi_id || @@ -1686,6 +1692,25 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } } + + /* VF Rx queue RXDID configuration */ + pf_q = vsi->rxq_map[qpi->rxq.queue_id]; + rxdid = qpi->rxq.rxdid; + hw = &vsi->back->hw; + + /* If Rx flex desc is supported, select RXDID for Rx queues. + * Otherwise, use legacy 32byte descriptor format. + * Legacy 16byte descriptor is not supported. If this RXDID + * is selected, return error. + */ + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) { + if (!(BIT(rxdid) & pf->supported_rxdids)) + goto error_param; + } else { + rxdid = ICE_RXDID_LEGACY_1; + } + + ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x03, false); } /* send the response to the VF */ @@ -2456,6 +2481,62 @@ error_param: v_ret, NULL, 0); } +/** + * ice_vc_query_rxdid - query RXDID supported by DDP package + * @vf: pointer to VF info + * + * Called from VF to query a bitmap of supported flexible + * descriptor RXDIDs of a DDP package. + */ +static int ice_vc_query_rxdid(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; + struct virtchnl_supported_rxdids *rxdid = NULL; + struct ice_hw *hw = &vf->pf->hw; + struct ice_pf *pf = vf->pf; + int len = 0; + int ret, i; + u32 regval; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + if (!(vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + + len = sizeof(struct virtchnl_supported_rxdids); + rxdid = kzalloc(len, GFP_KERNEL); + if (!rxdid) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + len = 0; + goto err; + } + + /* Read flexiflag registers to determine whether the + * corresponding RXDID is configured and supported or not. + * Since Legacy 16byte descriptor format is not supported, + * start from Legacy 32byte descriptor. + */ + for (i = ICE_RXDID_LEGACY_1; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) { + regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0)); + if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) + & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) + rxdid->supported_rxdids |= BIT(i); + } + + pf->supported_rxdids = rxdid->supported_rxdids; + +err: + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + v_ret, (u8 *)rxdid, len); + kfree(rxdid); + return ret; +} + /** * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization * @vf: VF to enable/disable VLAN stripping for on initialization @@ -3490,6 +3571,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .cfg_promiscuous_mode_msg = ice_vc_cfg_promiscuous_mode_msg, .add_vlan_msg = ice_vc_add_vlan_msg, .remove_vlan_msg = ice_vc_remove_vlan_msg, + .query_rxdid = ice_vc_query_rxdid, .ena_vlan_stripping = ice_vc_ena_vlan_stripping, .dis_vlan_stripping = ice_vc_dis_vlan_stripping, .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, @@ -3624,6 +3706,7 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode, .add_vlan_msg = ice_vc_add_vlan_msg, .remove_vlan_msg = ice_vc_remove_vlan_msg, + .query_rxdid = ice_vc_query_rxdid, .ena_vlan_stripping = ice_vc_ena_vlan_stripping, .dis_vlan_stripping = ice_vc_dis_vlan_stripping, .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, @@ -3764,6 +3847,9 @@ error_handler: case VIRTCHNL_OP_DEL_VLAN: err = ops->remove_vlan_msg(vf, msg); break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + err = ops->query_rxdid(vf); + break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: err = ops->ena_vlan_stripping(vf); break; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index b5a3fd8adbb4..4867a92ebefb 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -17,6 +17,7 @@ * broadcast, and 16 for additional unicast/multicast filters */ #define ICE_MAX_MACADDR_PER_VF 18 +#define ICE_FLEX_DESC_RXDID_MAX_NUM 64 struct ice_virtchnl_ops { int (*get_ver_msg)(struct ice_vf *vf, u8 *msg); @@ -35,6 +36,7 @@ struct ice_virtchnl_ops { int (*cfg_promiscuous_mode_msg)(struct ice_vf *vf, u8 *msg); int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg); int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg); + int (*query_rxdid)(struct ice_vf *vf); int (*ena_vlan_stripping)(struct ice_vf *vf); int (*dis_vlan_stripping)(struct ice_vf *vf); int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5a82216e7d03..7d547fa616fa 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -70,6 +70,11 @@ static const u32 rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA, }; +/* VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC */ +static const u32 rx_flex_desc_allowlist_opcodes[] = { + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, +}; + /* VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF */ static const u32 adv_rss_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_RSS_CFG, VIRTCHNL_OP_DEL_RSS_CFG, @@ -96,6 +101,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_REQ_QUEUES, req_queues_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN, vlan_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RSS_PF, rss_pf_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, rx_flex_desc_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2ce27e8e4f19..d91af50ac58d 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -136,7 +136,8 @@ enum virtchnl_ops { VIRTCHNL_OP_DISABLE_CHANNELS = 31, VIRTCHNL_OP_ADD_CLOUD_FILTER = 32, VIRTCHNL_OP_DEL_CLOUD_FILTER = 33, - /* opcode 34 - 44 are reserved */ + /* opcode 34 - 43 are reserved */ + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS = 44, VIRTCHNL_OP_ADD_RSS_CFG = 45, VIRTCHNL_OP_DEL_RSS_CFG = 46, VIRTCHNL_OP_ADD_FDIR_FILTER = 47, @@ -263,6 +264,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM BIT(22) #define VIRTCHNL_VF_OFFLOAD_ADQ BIT(23) #define VIRTCHNL_VF_OFFLOAD_USO BIT(25) +#define VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC BIT(26) #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) #define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) @@ -318,7 +320,9 @@ struct virtchnl_rxq_info { u16 splithdr_enabled; /* deprecated with AVF 1.0 */ u32 databuffer_size; u32 max_pkt_size; - u32 pad1; + u8 pad0; + u8 rxdid; + u8 pad1[2]; u64 dma_ring_addr; enum virtchnl_rx_hsplit rx_split_pos; /* deprecated with AVF 1.0 */ u32 pad2; @@ -970,6 +974,10 @@ struct virtchnl_filter { VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); +struct virtchnl_supported_rxdids { + u64 supported_rxdids; +}; + /* VIRTCHNL_OP_EVENT * PF sends this message to inform the VF driver of events that may affect it. * No direct response is expected from the VF, though it may generate other @@ -1499,6 +1507,8 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_DEL_CLOUD_FILTER: valid_len = sizeof(struct virtchnl_filter); break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + break; case VIRTCHNL_OP_ADD_RSS_CFG: case VIRTCHNL_OP_DEL_RSS_CFG: valid_len = sizeof(struct virtchnl_rss_cfg); -- cgit v1.2.3 From bd456f283b66704920fae8e655ebc769cb743420 Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:11 +0000 Subject: tcp: add sysctls for TCP PLB parameters PLB (Protective Load Balancing) is a host based mechanism for load balancing across switch links. It leverages congestion signals(e.g. ECN) from transport layer to randomly change the path of the connection experiencing congestion. PLB changes the path of the connection by changing the outgoing IPv6 flow label for IPv6 connections (implemented in Linux by calling sk_rethink_txhash()). Because of this implementation mechanism, PLB can currently only work for IPv6 traffic. For more information, see the SIGCOMM 2022 paper: https://doi.org/10.1145/3544216.3544226 This commit adds new sysctl knobs and sets their default values for TCP PLB. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 75 ++++++++++++++++++++++++++++++++++ include/net/netns/ipv4.h | 5 +++ net/ipv4/sysctl_net_ipv4.c | 43 +++++++++++++++++++ net/ipv4/tcp_ipv4.c | 8 ++++ 4 files changed, 131 insertions(+) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index e7b3fa7bb3f7..815efc89ad73 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1069,6 +1069,81 @@ tcp_child_ehash_entries - INTEGER Default: 0 +tcp_plb_enabled - BOOLEAN + If set and the underlying congestion control (e.g. DCTCP) supports + and enables PLB feature, TCP PLB (Protective Load Balancing) is + enabled. PLB is described in the following paper: + https://doi.org/10.1145/3544216.3544226. Based on PLB parameters, + upon sensing sustained congestion, TCP triggers a change in + flow label field for outgoing IPv6 packets. A change in flow label + field potentially changes the path of outgoing packets for switches + that use ECMP/WCMP for routing. + + PLB changes socket txhash which results in a change in IPv6 Flow Label + field, and currently no-op for IPv4 headers. It is possible + to apply PLB for IPv4 with other network header fields (e.g. TCP + or IPv4 options) or using encapsulation where outer header is used + by switches to determine next hop. In either case, further host + and switch side changes will be needed. + + When set, PLB assumes that congestion signal (e.g. ECN) is made + available and used by congestion control module to estimate a + congestion measure (e.g. ce_ratio). PLB needs a congestion measure to + make repathing decisions. + + Default: FALSE + +tcp_plb_idle_rehash_rounds - INTEGER + Number of consecutive congested rounds (RTT) seen after which + a rehash can be performed, given there are no packets in flight. + This is referred to as M in PLB paper: + https://doi.org/10.1145/3544216.3544226. + + Possible Values: 0 - 31 + + Default: 3 + +tcp_plb_rehash_rounds - INTEGER + Number of consecutive congested rounds (RTT) seen after which + a forced rehash can be performed. Be careful when setting this + parameter, as a small value increases the risk of retransmissions. + This is referred to as N in PLB paper: + https://doi.org/10.1145/3544216.3544226. + + Possible Values: 0 - 31 + + Default: 12 + +tcp_plb_suspend_rto_sec - INTEGER + Time, in seconds, to suspend PLB in event of an RTO. In order to avoid + having PLB repath onto a connectivity "black hole", after an RTO a TCP + connection suspends PLB repathing for a random duration between 1x and + 2x of this parameter. Randomness is added to avoid concurrent rehashing + of multiple TCP connections. This should be set corresponding to the + amount of time it takes to repair a failed link. + + Possible Values: 0 - 255 + + Default: 60 + +tcp_plb_cong_thresh - INTEGER + Fraction of packets marked with congestion over a round (RTT) to + tag that round as congested. This is referred to as K in the PLB paper: + https://doi.org/10.1145/3544216.3544226. + + The 0-1 fraction range is mapped to 0-256 range to avoid floating + point operations. For example, 128 means that if at least 50% of + the packets in a round were marked as congested then the round + will be tagged as congested. + + Setting threshold to 0 means that PLB repaths every RTT regardless + of congestion. This is not intended behavior for PLB and should be + used only for experimentation purpose. + + Possible Values: 0 - 256 + + Default: 128 + UDP variables ============= diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1b8004679445..25f90bba4889 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -183,6 +183,11 @@ struct netns_ipv4 { unsigned long tfo_active_disable_stamp; u32 tcp_challenge_timestamp; u32 tcp_challenge_count; + u8 sysctl_tcp_plb_enabled; + u8 sysctl_tcp_plb_idle_rehash_rounds; + u8 sysctl_tcp_plb_rehash_rounds; + u8 sysctl_tcp_plb_suspend_rto_sec; + int sysctl_tcp_plb_cong_thresh; int sysctl_udp_wmem_min; int sysctl_udp_rmem_min; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9b8a6db7a66b..0af28cedd071 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -40,6 +40,8 @@ static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; +static int tcp_plb_max_rounds = 31; +static int tcp_plb_max_cong_thresh = 256; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -1384,6 +1386,47 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, + { + .procname = "tcp_plb_enabled", + .data = &init_net.ipv4.sysctl_tcp_plb_enabled, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "tcp_plb_idle_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_idle_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_rehash_rounds", + .data = &init_net.ipv4.sysctl_tcp_plb_rehash_rounds, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra2 = &tcp_plb_max_rounds, + }, + { + .procname = "tcp_plb_suspend_rto_sec", + .data = &init_net.ipv4.sysctl_tcp_plb_suspend_rto_sec, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, + { + .procname = "tcp_plb_cong_thresh", + .data = &init_net.ipv4.sysctl_tcp_plb_cong_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_plb_max_cong_thresh, + }, { } }; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87d440f47a70..58b838b56c7f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3218,6 +3218,14 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; atomic_set(&net->ipv4.tfo_active_disable_times, 0); + /* Set default values for PLB */ + net->ipv4.sysctl_tcp_plb_enabled = 0; /* Disabled by default */ + net->ipv4.sysctl_tcp_plb_idle_rehash_rounds = 3; + net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; + net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; + /* Default congestion threshold for PLB to mark a round is 50% */ + net->ipv4.sysctl_tcp_plb_cong_thresh = 128; + /* Reno is always built in */ if (!net_eq(net, &init_net) && bpf_try_module_get(init_net.ipv4.tcp_congestion_control, -- cgit v1.2.3 From 1a91bb7c3ebf95e908ec33220defbcda1ecc072f Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:12 +0000 Subject: tcp: add PLB functionality for TCP Congestion control algorithms track PLB state and cause the connection to trigger a path change when either of the 2 conditions is satisfied: - No packets are in flight and (# consecutive congested rounds >= sysctl_tcp_plb_idle_rehash_rounds) - (# consecutive congested rounds >= sysctl_tcp_plb_rehash_rounds) A round (RTT) is marked as congested when congestion signal (ECN ce_ratio) over an RTT is greater than sysctl_tcp_plb_cong_thresh. In the event of RTO, PLB (via tcp_write_timeout()) triggers a path change and disables congestion-triggered path changes for random time between (sysctl_tcp_plb_suspend_rto_sec, 2*sysctl_tcp_plb_suspend_rto_sec) to avoid hopping onto the "connectivity blackhole". RTO-triggered path changes can still happen during this cool-off period. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 28 ++++++++++++++ net/ipv4/Makefile | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_plb.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 137 insertions(+), 2 deletions(-) create mode 100644 net/ipv4/tcp_plb.c (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 14d45661a84d..6b814e788f00 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2140,6 +2140,34 @@ extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, extern void tcp_rack_reo_timeout(struct sock *sk); extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); +/* tcp_plb.c */ + +/* + * Scaling factor for fractions in PLB. For example, tcp_plb_update_state + * expects cong_ratio which represents fraction of traffic that experienced + * congestion over a single RTT. In order to avoid floating point operations, + * this fraction should be mapped to (1 << TCP_PLB_SCALE) and passed in. + */ +#define TCP_PLB_SCALE 8 + +/* State for PLB (Protective Load Balancing) for a single TCP connection. */ +struct tcp_plb_state { + u8 consec_cong_rounds:5, /* consecutive congested rounds */ + unused:3; + u32 pause_until; /* jiffies32 when PLB can resume rerouting */ +}; + +static inline void tcp_plb_init(const struct sock *sk, + struct tcp_plb_state *plb) +{ + plb->consec_cong_rounds = 0; + plb->pause_until = 0; +} +void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, + const int cong_ratio); +void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb); +void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb); + /* At how many usecs into the future should the RTO fire? */ static inline s64 tcp_rto_delta_us(const struct sock *sk) { diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index bbdd9c44f14e..af7d2cf490fb 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -10,7 +10,7 @@ obj-y := route.o inetpeer.o protocol.o \ tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \ tcp_rate.o tcp_recovery.o tcp_ulp.o \ - tcp_offload.o datagram.o raw.o udp.o udplite.o \ + tcp_offload.o tcp_plb.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 58b838b56c7f..ebab9e8b184c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3224,7 +3224,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_plb_rehash_rounds = 12; net->ipv4.sysctl_tcp_plb_suspend_rto_sec = 60; /* Default congestion threshold for PLB to mark a round is 50% */ - net->ipv4.sysctl_tcp_plb_cong_thresh = 128; + net->ipv4.sysctl_tcp_plb_cong_thresh = (1 << TCP_PLB_SCALE) / 2; /* Reno is always built in */ if (!net_eq(net, &init_net) && diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c new file mode 100644 index 000000000000..f4ced370acad --- /dev/null +++ b/net/ipv4/tcp_plb.c @@ -0,0 +1,107 @@ +/* Protective Load Balancing (PLB) + * + * PLB was designed to reduce link load imbalance across datacenter + * switches. PLB is a host-based optimization; it leverages congestion + * signals from the transport layer to randomly change the path of the + * connection experiencing sustained congestion. PLB prefers to repath + * after idle periods to minimize packet reordering. It repaths by + * changing the IPv6 Flow Label on the packets of a connection, which + * datacenter switches include as part of ECMP/WCMP hashing. + * + * PLB is described in detail in: + * + * Mubashir Adnan Qureshi, Yuchung Cheng, Qianwen Yin, Qiaobin Fu, + * Gautam Kumar, Masoud Moshref, Junhua Yan, Van Jacobson, + * David Wetherall,Abdul Kabbani: + * "PLB: Congestion Signals are Simple and Effective for + * Network Load Balancing" + * In ACM SIGCOMM 2022, Amsterdam Netherlands. + * + */ + +#include + +/* Called once per round-trip to update PLB state for a connection. */ +void tcp_plb_update_state(const struct sock *sk, struct tcp_plb_state *plb, + const int cong_ratio) +{ + struct net *net = sock_net(sk); + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + if (cong_ratio >= 0) { + if (cong_ratio < READ_ONCE(net->ipv4.sysctl_tcp_plb_cong_thresh)) + plb->consec_cong_rounds = 0; + else if (plb->consec_cong_rounds < + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds)) + plb->consec_cong_rounds++; + } +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state); + +/* Check whether recent congestion has been persistent enough to warrant + * a load balancing decision that switches the connection to another path. + */ +void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 max_suspend; + bool forced_rehash = false, idle_rehash = false; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + forced_rehash = plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_rehash_rounds); + /* If sender goes idle then we check whether to rehash. */ + idle_rehash = READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds) && + !tcp_sk(sk)->packets_out && + plb->consec_cong_rounds >= + READ_ONCE(net->ipv4.sysctl_tcp_plb_idle_rehash_rounds); + + if (!forced_rehash && !idle_rehash) + return; + + /* Note that tcp_jiffies32 can wrap; we detect wraps by checking for + * cases where the max suspension end is before the actual suspension + * end. We clear pause_until to 0 to indicate there is no recent + * RTO event that constrains PLB rehashing. + */ + max_suspend = 2 * READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + if (plb->pause_until && + (!before(tcp_jiffies32, plb->pause_until) || + before(tcp_jiffies32 + max_suspend, plb->pause_until))) + plb->pause_until = 0; + + if (plb->pause_until) + return; + + sk_rethink_txhash(sk); + plb->consec_cong_rounds = 0; +} +EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); + +/* Upon RTO, disallow load balancing for a while, to avoid having load + * balancing decisions switch traffic to a black-holed path that was + * previously avoided with a sk_rethink_txhash() call at RTO time. + */ +void tcp_plb_update_state_upon_rto(struct sock *sk, struct tcp_plb_state *plb) +{ + struct net *net = sock_net(sk); + u32 pause; + + if (!READ_ONCE(net->ipv4.sysctl_tcp_plb_enabled)) + return; + + pause = READ_ONCE(net->ipv4.sysctl_tcp_plb_suspend_rto_sec) * HZ; + pause += prandom_u32_max(pause); + plb->pause_until = tcp_jiffies32 + pause; + + /* Reset PLB state upon RTO, since an RTO causes a sk_rethink_txhash() call + * that may switch this connection to a path with completely different + * congestion characteristics. + */ + plb->consec_cong_rounds = 0; +} +EXPORT_SYMBOL_GPL(tcp_plb_update_state_upon_rto); -- cgit v1.2.3 From 29c1c44646aec5d5134f2365259a84becc1ee7d3 Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:14 +0000 Subject: tcp: add u32 counter in tcp_sock and an SNMP counter for PLB A u32 counter is added to tcp_sock for counting the number of PLB triggered rehashes for a TCP connection. An SNMP counter is also added to count overall PLB triggered rehash events for a host. These counters are hooked up to PLB implementation for DCTCP. TCP_NLA_REHASH is added to SCM_TIMESTAMPING_OPT_STATS that reports the rehash attempts triggered due to PLB or timeouts. This gives a historical view of sustained congestion or timeouts experienced by the TCP connection. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/uapi/linux/snmp.h | 1 + include/uapi/linux/tcp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_plb.c | 2 ++ 6 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 41b1da621a45..ca7f05a130d2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -423,6 +423,7 @@ struct tcp_sock { u32 probe_seq_start; u32 probe_seq_end; } mtu_probe; + u32 plb_rehash; /* PLB-triggered rehash attempts */ u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG * while socket was owned by user. */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 4d7470036a8b..6600cb0164c2 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -292,6 +292,7 @@ enum LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ + LINUX_MIB_TCPPLBREHASH, /* TCPPLBRehash */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8fc09e8638b3..c9abe86eda5f 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -315,6 +315,7 @@ enum { TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ TCP_NLA_TTL, /* TTL or hop limit of a packet received */ + TCP_NLA_REHASH, /* PLB and timeout triggered rehash attempts */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5386f460bd20..f88daace9de3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ef14efa1fb70..1da7c53b6cb5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3176,6 +3176,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; + tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rack.mstamp = 0; @@ -3973,6 +3974,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } @@ -4049,6 +4051,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); + nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c index f4ced370acad..bb1a08fda113 100644 --- a/net/ipv4/tcp_plb.c +++ b/net/ipv4/tcp_plb.c @@ -79,6 +79,8 @@ void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) sk_rethink_txhash(sk); plb->consec_cong_rounds = 0; + tcp_sk(sk)->plb_rehash++; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH); } EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); -- cgit v1.2.3 From 71fc704768f601ed3fa36310822a5e03f310f781 Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:15 +0000 Subject: tcp: add rcv_wnd and plb_rehash to TCP_INFO rcv_wnd can be useful to diagnose TCP performance where receiver window becomes the bottleneck. rehash reports the PLB and timeout triggered rehash attempts by the TCP connection. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 5 +++++ net/ipv4/tcp.c | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c9abe86eda5f..879eeb0a084b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -284,6 +284,11 @@ struct tcp_info { __u32 tcpi_snd_wnd; /* peer's advertised receive window after * scaling (bytes) */ + __u32 tcpi_rcv_wnd; /* local advertised receive window after + * scaling (bytes) + */ + + __u32 tcpi_rehash; /* PLB or timeout triggered rehash attempts */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1da7c53b6cb5..de8f0cd7cb32 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3940,6 +3940,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_rcv_wnd = tp->rcv_wnd; + info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } -- cgit v1.2.3 From 9c5a170677c3c8facc83e931a57f4c99c0511ae0 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 27 Oct 2022 14:10:37 +0100 Subject: net: phylink: add phylink_get_link_timer_ns() helper Add a helper to convert the PHY interface mode to the required link timer setting as stated by the appropriate standard. Inappropriate interface modes return an error. Signed-off-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 63800bf4a7ac..1df3e5e316e8 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -616,6 +616,30 @@ int phylink_speed_up(struct phylink *pl); void phylink_set_port_modes(unsigned long *bits); +/** + * phylink_get_link_timer_ns - return the PCS link timer value + * @interface: link &typedef phy_interface_t mode + * + * Return the PCS link timer setting in nanoseconds for the PHY @interface + * mode, or -EINVAL if not appropriate. + */ +static inline int phylink_get_link_timer_ns(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_USXGMII: + return 1600000; + + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + return 10000000; + + default: + return -EINVAL; + } +} + void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, -- cgit v1.2.3 From 17dd361119e5bc4cfb85aed660674a846b613817 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 27 Oct 2022 14:21:16 +0100 Subject: net: sfp: convert register indexes from hex to decimal The register indexes in the standards are in decimal rather than hex, so lets specify them in decimal in the header file so we can easily cross-reference without converting between hex and decimal. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/sfp.h | 180 ++++++++++++++++++++++++++-------------------------- 1 file changed, 90 insertions(+), 90 deletions(-) (limited to 'include') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 01ae9f1dd2ad..4e2db155664d 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -332,37 +332,37 @@ enum { /* SFP EEPROM registers */ enum { - SFP_PHYS_ID = 0x00, - SFP_PHYS_EXT_ID = 0x01, - SFP_CONNECTOR = 0x02, - SFP_COMPLIANCE = 0x03, - SFP_ENCODING = 0x0b, - SFP_BR_NOMINAL = 0x0c, - SFP_RATE_ID = 0x0d, - SFP_LINK_LEN_SM_KM = 0x0e, - SFP_LINK_LEN_SM_100M = 0x0f, - SFP_LINK_LEN_50UM_OM2_10M = 0x10, - SFP_LINK_LEN_62_5UM_OM1_10M = 0x11, - SFP_LINK_LEN_COPPER_1M = 0x12, - SFP_LINK_LEN_50UM_OM4_10M = 0x12, - SFP_LINK_LEN_50UM_OM3_10M = 0x13, - SFP_VENDOR_NAME = 0x14, - SFP_VENDOR_OUI = 0x25, - SFP_VENDOR_PN = 0x28, - SFP_VENDOR_REV = 0x38, - SFP_OPTICAL_WAVELENGTH_MSB = 0x3c, - SFP_OPTICAL_WAVELENGTH_LSB = 0x3d, - SFP_CABLE_SPEC = 0x3c, - SFP_CC_BASE = 0x3f, - SFP_OPTIONS = 0x40, /* 2 bytes, MSB, LSB */ - SFP_BR_MAX = 0x42, - SFP_BR_MIN = 0x43, - SFP_VENDOR_SN = 0x44, - SFP_DATECODE = 0x54, - SFP_DIAGMON = 0x5c, - SFP_ENHOPTS = 0x5d, - SFP_SFF8472_COMPLIANCE = 0x5e, - SFP_CC_EXT = 0x5f, + SFP_PHYS_ID = 0, + SFP_PHYS_EXT_ID = 1, + SFP_CONNECTOR = 2, + SFP_COMPLIANCE = 3, + SFP_ENCODING = 11, + SFP_BR_NOMINAL = 12, + SFP_RATE_ID = 13, + SFP_LINK_LEN_SM_KM = 14, + SFP_LINK_LEN_SM_100M = 15, + SFP_LINK_LEN_50UM_OM2_10M = 16, + SFP_LINK_LEN_62_5UM_OM1_10M = 17, + SFP_LINK_LEN_COPPER_1M = 18, + SFP_LINK_LEN_50UM_OM4_10M = 18, + SFP_LINK_LEN_50UM_OM3_10M = 19, + SFP_VENDOR_NAME = 20, + SFP_VENDOR_OUI = 37, + SFP_VENDOR_PN = 40, + SFP_VENDOR_REV = 56, + SFP_OPTICAL_WAVELENGTH_MSB = 60, + SFP_OPTICAL_WAVELENGTH_LSB = 61, + SFP_CABLE_SPEC = 60, + SFP_CC_BASE = 63, + SFP_OPTIONS = 64, /* 2 bytes, MSB, LSB */ + SFP_BR_MAX = 66, + SFP_BR_MIN = 67, + SFP_VENDOR_SN = 68, + SFP_DATECODE = 84, + SFP_DIAGMON = 92, + SFP_ENHOPTS = 93, + SFP_SFF8472_COMPLIANCE = 94, + SFP_CC_EXT = 95, SFP_PHYS_EXT_ID_SFP = 0x04, SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), @@ -404,63 +404,63 @@ enum { /* SFP Diagnostics */ enum { /* Alarm and warnings stored MSB at lower address then LSB */ - SFP_TEMP_HIGH_ALARM = 0x00, - SFP_TEMP_LOW_ALARM = 0x02, - SFP_TEMP_HIGH_WARN = 0x04, - SFP_TEMP_LOW_WARN = 0x06, - SFP_VOLT_HIGH_ALARM = 0x08, - SFP_VOLT_LOW_ALARM = 0x0a, - SFP_VOLT_HIGH_WARN = 0x0c, - SFP_VOLT_LOW_WARN = 0x0e, - SFP_BIAS_HIGH_ALARM = 0x10, - SFP_BIAS_LOW_ALARM = 0x12, - SFP_BIAS_HIGH_WARN = 0x14, - SFP_BIAS_LOW_WARN = 0x16, - SFP_TXPWR_HIGH_ALARM = 0x18, - SFP_TXPWR_LOW_ALARM = 0x1a, - SFP_TXPWR_HIGH_WARN = 0x1c, - SFP_TXPWR_LOW_WARN = 0x1e, - SFP_RXPWR_HIGH_ALARM = 0x20, - SFP_RXPWR_LOW_ALARM = 0x22, - SFP_RXPWR_HIGH_WARN = 0x24, - SFP_RXPWR_LOW_WARN = 0x26, - SFP_LASER_TEMP_HIGH_ALARM = 0x28, - SFP_LASER_TEMP_LOW_ALARM = 0x2a, - SFP_LASER_TEMP_HIGH_WARN = 0x2c, - SFP_LASER_TEMP_LOW_WARN = 0x2e, - SFP_TEC_CUR_HIGH_ALARM = 0x30, - SFP_TEC_CUR_LOW_ALARM = 0x32, - SFP_TEC_CUR_HIGH_WARN = 0x34, - SFP_TEC_CUR_LOW_WARN = 0x36, - SFP_CAL_RXPWR4 = 0x38, - SFP_CAL_RXPWR3 = 0x3c, - SFP_CAL_RXPWR2 = 0x40, - SFP_CAL_RXPWR1 = 0x44, - SFP_CAL_RXPWR0 = 0x48, - SFP_CAL_TXI_SLOPE = 0x4c, - SFP_CAL_TXI_OFFSET = 0x4e, - SFP_CAL_TXPWR_SLOPE = 0x50, - SFP_CAL_TXPWR_OFFSET = 0x52, - SFP_CAL_T_SLOPE = 0x54, - SFP_CAL_T_OFFSET = 0x56, - SFP_CAL_V_SLOPE = 0x58, - SFP_CAL_V_OFFSET = 0x5a, - SFP_CHKSUM = 0x5f, - - SFP_TEMP = 0x60, - SFP_VCC = 0x62, - SFP_TX_BIAS = 0x64, - SFP_TX_POWER = 0x66, - SFP_RX_POWER = 0x68, - SFP_LASER_TEMP = 0x6a, - SFP_TEC_CUR = 0x6c, - - SFP_STATUS = 0x6e, + SFP_TEMP_HIGH_ALARM = 0, + SFP_TEMP_LOW_ALARM = 2, + SFP_TEMP_HIGH_WARN = 4, + SFP_TEMP_LOW_WARN = 6, + SFP_VOLT_HIGH_ALARM = 8, + SFP_VOLT_LOW_ALARM = 10, + SFP_VOLT_HIGH_WARN = 12, + SFP_VOLT_LOW_WARN = 14, + SFP_BIAS_HIGH_ALARM = 16, + SFP_BIAS_LOW_ALARM = 18, + SFP_BIAS_HIGH_WARN = 20, + SFP_BIAS_LOW_WARN = 22, + SFP_TXPWR_HIGH_ALARM = 24, + SFP_TXPWR_LOW_ALARM = 26, + SFP_TXPWR_HIGH_WARN = 28, + SFP_TXPWR_LOW_WARN = 30, + SFP_RXPWR_HIGH_ALARM = 32, + SFP_RXPWR_LOW_ALARM = 34, + SFP_RXPWR_HIGH_WARN = 36, + SFP_RXPWR_LOW_WARN = 38, + SFP_LASER_TEMP_HIGH_ALARM = 40, + SFP_LASER_TEMP_LOW_ALARM = 42, + SFP_LASER_TEMP_HIGH_WARN = 44, + SFP_LASER_TEMP_LOW_WARN = 46, + SFP_TEC_CUR_HIGH_ALARM = 48, + SFP_TEC_CUR_LOW_ALARM = 50, + SFP_TEC_CUR_HIGH_WARN = 52, + SFP_TEC_CUR_LOW_WARN = 54, + SFP_CAL_RXPWR4 = 56, + SFP_CAL_RXPWR3 = 60, + SFP_CAL_RXPWR2 = 64, + SFP_CAL_RXPWR1 = 68, + SFP_CAL_RXPWR0 = 72, + SFP_CAL_TXI_SLOPE = 76, + SFP_CAL_TXI_OFFSET = 78, + SFP_CAL_TXPWR_SLOPE = 80, + SFP_CAL_TXPWR_OFFSET = 82, + SFP_CAL_T_SLOPE = 84, + SFP_CAL_T_OFFSET = 86, + SFP_CAL_V_SLOPE = 88, + SFP_CAL_V_OFFSET = 90, + SFP_CHKSUM = 95, + + SFP_TEMP = 96, + SFP_VCC = 98, + SFP_TX_BIAS = 100, + SFP_TX_POWER = 102, + SFP_RX_POWER = 104, + SFP_LASER_TEMP = 106, + SFP_TEC_CUR = 108, + + SFP_STATUS = 110, SFP_STATUS_TX_DISABLE = BIT(7), SFP_STATUS_TX_DISABLE_FORCE = BIT(6), SFP_STATUS_TX_FAULT = BIT(2), SFP_STATUS_RX_LOS = BIT(1), - SFP_ALARM0 = 0x70, + SFP_ALARM0 = 112, SFP_ALARM0_TEMP_HIGH = BIT(7), SFP_ALARM0_TEMP_LOW = BIT(6), SFP_ALARM0_VCC_HIGH = BIT(5), @@ -470,11 +470,11 @@ enum { SFP_ALARM0_TXPWR_HIGH = BIT(1), SFP_ALARM0_TXPWR_LOW = BIT(0), - SFP_ALARM1 = 0x71, + SFP_ALARM1 = 113, SFP_ALARM1_RXPWR_HIGH = BIT(7), SFP_ALARM1_RXPWR_LOW = BIT(6), - SFP_WARN0 = 0x74, + SFP_WARN0 = 116, SFP_WARN0_TEMP_HIGH = BIT(7), SFP_WARN0_TEMP_LOW = BIT(6), SFP_WARN0_VCC_HIGH = BIT(5), @@ -484,15 +484,15 @@ enum { SFP_WARN0_TXPWR_HIGH = BIT(1), SFP_WARN0_TXPWR_LOW = BIT(0), - SFP_WARN1 = 0x75, + SFP_WARN1 = 117, SFP_WARN1_RXPWR_HIGH = BIT(7), SFP_WARN1_RXPWR_LOW = BIT(6), - SFP_EXT_STATUS = 0x76, + SFP_EXT_STATUS = 118, SFP_EXT_STATUS_PWRLVL_SELECT = BIT(0), - SFP_VSL = 0x78, - SFP_PAGE = 0x7f, + SFP_VSL = 120, + SFP_PAGE = 127, }; struct fwnode_handle; -- cgit v1.2.3 From d83845d224a059165902ecd0e1203015c5713a78 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 27 Oct 2022 14:21:21 +0100 Subject: net: sfp: move field definitions along side register index Just as we do for the A2h enum, arrange the A0h enum to have the field definitions next to their corresponding register index. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/sfp.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 4e2db155664d..52b98f9666a2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -333,7 +333,10 @@ enum { /* SFP EEPROM registers */ enum { SFP_PHYS_ID = 0, + SFP_PHYS_EXT_ID = 1, + SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_CONNECTOR = 2, SFP_COMPLIANCE = 3, SFP_ENCODING = 11, @@ -354,17 +357,8 @@ enum { SFP_OPTICAL_WAVELENGTH_LSB = 61, SFP_CABLE_SPEC = 60, SFP_CC_BASE = 63, - SFP_OPTIONS = 64, /* 2 bytes, MSB, LSB */ - SFP_BR_MAX = 66, - SFP_BR_MIN = 67, - SFP_VENDOR_SN = 68, - SFP_DATECODE = 84, - SFP_DIAGMON = 92, - SFP_ENHOPTS = 93, - SFP_SFF8472_COMPLIANCE = 94, - SFP_CC_EXT = 95, - SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_OPTIONS = 64, /* 2 bytes, MSB, LSB */ SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), SFP_OPTIONS_PAGING_A2 = BIT(12), SFP_OPTIONS_RETIMER = BIT(11), @@ -378,11 +372,20 @@ enum { SFP_OPTIONS_TX_FAULT = BIT(3), SFP_OPTIONS_LOS_INVERTED = BIT(2), SFP_OPTIONS_LOS_NORMAL = BIT(1), + + SFP_BR_MAX = 66, + SFP_BR_MIN = 67, + SFP_VENDOR_SN = 68, + SFP_DATECODE = 84, + + SFP_DIAGMON = 92, SFP_DIAGMON_DDM = BIT(6), SFP_DIAGMON_INT_CAL = BIT(5), SFP_DIAGMON_EXT_CAL = BIT(4), SFP_DIAGMON_RXPWR_AVG = BIT(3), SFP_DIAGMON_ADDRMODE = BIT(2), + + SFP_ENHOPTS = 93, SFP_ENHOPTS_ALARMWARN = BIT(7), SFP_ENHOPTS_SOFT_TX_DISABLE = BIT(6), SFP_ENHOPTS_SOFT_TX_FAULT = BIT(5), @@ -390,6 +393,8 @@ enum { SFP_ENHOPTS_SOFT_RATE_SELECT = BIT(3), SFP_ENHOPTS_APP_SELECT_SFF8079 = BIT(2), SFP_ENHOPTS_SOFT_RATE_SFF8431 = BIT(1), + + SFP_SFF8472_COMPLIANCE = 94, SFP_SFF8472_COMPLIANCE_NONE = 0x00, SFP_SFF8472_COMPLIANCE_REV9_3 = 0x01, SFP_SFF8472_COMPLIANCE_REV9_5 = 0x02, @@ -399,6 +404,8 @@ enum { SFP_SFF8472_COMPLIANCE_REV11_3 = 0x06, SFP_SFF8472_COMPLIANCE_REV11_4 = 0x07, SFP_SFF8472_COMPLIANCE_REV12_0 = 0x08, + + SFP_CC_EXT = 95, }; /* SFP Diagnostics */ -- cgit v1.2.3 From 58ba426388d9fe56aa638f555b01d6e63cada88c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 27 Oct 2022 17:10:14 -0400 Subject: net/packet: add PACKET_FANOUT_FLAG_IGNORE_OUTGOING Extend packet socket option PACKET_IGNORE_OUTGOING to fanout groups. The socket option sets ptype.ignore_outgoing, which makes dev_queue_xmit_nit skip the socket. When the socket joins a fanout group, the option is not reflected in the struct ptype of the group. dev_queue_xmit_nit only tests the fanout ptype, so the flag is ignored once a socket joins a fanout group. Inheriting the option from a socket would change established behavior. Different sockets in the group can set different flags, and can also change them at runtime. Testing in packet_rcv_fanout defeats the purpose of the original patch, which is to avoid skb_clone in dev_queue_xmit_nit (esp. for MSG_ZEROCOPY packets). Instead, introduce a new fanout group flag with the same behavior. Tested with https://github.com/wdebruij/kerneltools/blob/master/tests/test_psock_fanout_ignore_outgoing.c Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20221027211014.3581513-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_packet.h | 1 + net/packet/af_packet.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index c07caf7b40db..a8516b3594a4 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -70,6 +70,7 @@ struct sockaddr_ll { #define PACKET_FANOUT_EBPF 7 #define PACKET_FANOUT_FLAG_ROLLOVER 0x1000 #define PACKET_FANOUT_FLAG_UNIQUEID 0x2000 +#define PACKET_FANOUT_FLAG_IGNORE_OUTGOING 0x4000 #define PACKET_FANOUT_FLAG_DEFRAG 0x8000 struct tpacket_stats { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8c5b3da0c29f..44f20cf8a0c0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1777,6 +1777,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; + match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; -- cgit v1.2.3 From f3fb589aeb88c5bf7a7a804d36a8fa219b72e290 Mon Sep 17 00:00:00 2001 From: Juhee Kang Date: Fri, 28 Oct 2022 01:04:24 +0900 Subject: net: remove unused netdev_unregistering() Currently, use dev->reg_state == NETREG_UNREGISTERING to check the status which is NETREG_UNREGISTERING, rather than using netdev_unregistering. Also, A helper function which is netdev_unregistering on nedevice.h is no longer used. Thus, netdev_unregistering removes from netdevice.h. Signed-off-by: Juhee Kang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eddf8ee270e7..99e58b773266 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5101,11 +5101,6 @@ static inline const char *netdev_name(const struct net_device *dev) return dev->name; } -static inline bool netdev_unregistering(const struct net_device *dev) -{ - return dev->reg_state == NETREG_UNREGISTERING; -} - static inline const char *netdev_reg_state(const struct net_device *dev) { switch (dev->reg_state) { -- cgit v1.2.3 From 738136a0e3757a8534df3ad97d6ff6d7f429f6c1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Oct 2022 14:25:53 -0700 Subject: netlink: split up copies in the ack construction Clean up the use of unsafe_memcpy() by adding a flexible array at the end of netlink message header and splitting up the header and data copies. Reviewed-by: Kees Cook Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 21 +++++++++++++++++++++ include/uapi/linux/netlink.h | 2 ++ net/netlink/af_netlink.c | 29 ++++++++++++++++++++--------- 3 files changed, 43 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/netlink.h b/include/net/netlink.h index 4418b1981e31..784b4688fc6f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -931,6 +931,27 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se return __nlmsg_put(skb, portid, seq, type, payload, flags); } +/** + * nlmsg_append - Add more data to a nlmsg in a skb + * @skb: socket buffer to store message in + * @size: length of message payload + * + * Append data to an existing nlmsg, used when constructing a message + * with multiple fixed-format headers (which is rare). + * Returns NULL if the tailroom of the skb is insufficient to store + * the extra payload. + */ +static inline void *nlmsg_append(struct sk_buff *skb, u32 size) +{ + if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) + return NULL; + + if (NLMSG_ALIGN(size) - size) + memset(skb_tail_pointer(skb) + size, 0, + NLMSG_ALIGN(size) - size); + return __skb_put(skb, NLMSG_ALIGN(size)); +} + /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e2ae82e3f9f7..5da0da59bf01 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,6 +48,7 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID + * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -55,6 +56,7 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; + __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f0c94d394ab1..b10d5e50b99d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2499,19 +2499,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); - if (!skb) { - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - sk_error_report(NETLINK_CB(in_skb).sk); - return; - } + if (!skb) + goto err_bad_put; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - NLMSG_ERROR, payload, flags); + NLMSG_ERROR, sizeof(*errmsg), flags); + if (!rep) + goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; - unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) - ? nlh->nlmsg_len : sizeof(*nlh), - /* Bounds checked by the skb layer. */); + errmsg->msg = *nlh; + + if (!(flags & NLM_F_CAPPED)) { + if (!nlmsg_append(skb, nlmsg_len(nlh))) + goto err_bad_put; + + memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + nlmsg_len(nlh)); + } if (tlvlen) netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack); @@ -2519,6 +2524,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); + + return; + +err_bad_put: + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); -- cgit v1.2.3 From 8c2a535e089b2ab82cf50c876bd10c8ed33252c9 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Oct 2022 20:52:59 -0700 Subject: net: geneve: fix array of flexible structures warnings New compilers don't like flexible array of flexible structs: include/net/geneve.h:62:34: warning: array of flexible structures Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/geneve.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/geneve.h b/include/net/geneve.h index bced0b1d9fe4..5c96827a487e 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -59,7 +59,7 @@ struct genevehdr { __be16 proto_type; u8 vni[3]; u8 rsvd2; - struct geneve_opt options[]; + u8 options[]; }; static inline bool netif_is_geneve(const struct net_device *dev) -- cgit v1.2.3 From b9a61b97798ca6d0c856a217e61e2177bd8f6eae Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 28 Oct 2022 04:04:12 -0700 Subject: ptp: add missing documentation for parameters The ptp_find_pin_unlocked function and the ptp_system_timestamp structure didn't document their parameters and fields. Fix this. Signed-off-by: Jacob Keller Acked-by: Richard Cochran Signed-off-by: David S. Miller --- include/linux/ptp_clock_kernel.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 92b44161408e..ad4aaadc2f7a 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -45,6 +45,8 @@ struct system_device_crosststamp; /** * struct ptp_system_timestamp - system time corresponding to a PHC timestamp + * @pre_ts: system timestamp before capturing PHC + * @post_ts: system timestamp after capturing PHC */ struct ptp_system_timestamp { struct timespec64 pre_ts; @@ -316,6 +318,11 @@ int ptp_find_pin(struct ptp_clock *ptp, * should most likely call ptp_find_pin() directly from their * ptp_clock_info::enable() method. * +* @ptp: The clock obtained from ptp_clock_register(). +* @func: One of the ptp_pin_function enumerated values. +* @chan: The particular functional channel to find. +* Return: Pin index in the range of zero to ptp_clock_caps.n_pins - 1, +* or -1 if the auxiliary function cannot be found. */ int ptp_find_pin_unlocked(struct ptp_clock *ptp, -- cgit v1.2.3 From 1060707e380994e7c9b754b6eb74f25459b4a5b3 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Fri, 28 Oct 2022 04:04:13 -0700 Subject: ptp: introduce helpers to adjust by scaled parts per million Many drivers implement the .adjfreq or .adjfine PTP op function with the same basic logic: 1. Determine a base frequency value 2. Multiply this by the abs() of the requested adjustment, then divide by the appropriate divisor (1 billion, or 65,536 billion). 3. Add or subtract this difference from the base frequency to calculate a new adjustment. A few drivers need the difference and direction rather than the combined new increment value. I recently converted the Intel drivers to .adjfine and the scaled parts per million (65.536 parts per billion) logic. To avoid overflow with minimal loss of precision, mul_u64_u64_div_u64 was used. The basic logic used by all of these drivers is very similar, and leads to a lot of duplicate code to perform the same task. Rather than keep this duplicate code, introduce diff_by_scaled_ppm and adjust_by_scaled_ppm. These helper functions calculate the difference or adjustment necessary based on the scaled parts per million input. The diff_by_scaled_ppm function returns true if the difference should be subtracted, and false otherwise. Update the Intel drivers to use the new helper functions. Other vendor drivers will be converted to .adjfine and this helper function in the following changes. Signed-off-by: Jacob Keller Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/e1000e/ptp.c | 16 ++-------- drivers/net/ethernet/intel/i40e/i40e_ptp.c | 17 ++-------- drivers/net/ethernet/intel/ice/ice_ptp.c | 18 ++--------- drivers/net/ethernet/intel/igb/igb_ptp.c | 18 ++--------- drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 24 +++------------ include/linux/ptp_clock_kernel.h | 46 ++++++++++++++++++++++++++++ 6 files changed, 60 insertions(+), 79 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 0e488e4fa5c1..6e5a1720e6cd 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -29,17 +29,11 @@ static int e1000e_phc_adjfine(struct ptp_clock_info *ptp, long delta) struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); struct e1000_hw *hw = &adapter->hw; - bool neg_adj = false; unsigned long flags; - u64 adjustment; - u32 timinca, incvalue; + u64 incvalue; + u32 timinca; s32 ret_val; - if (delta < 0) { - neg_adj = true; - delta = -delta; - } - /* Get the System Time Register SYSTIM base frequency */ ret_val = e1000e_get_base_timinca(adapter, &timinca); if (ret_val) @@ -48,11 +42,7 @@ static int e1000e_phc_adjfine(struct ptp_clock_info *ptp, long delta) spin_lock_irqsave(&adapter->systim_lock, flags); incvalue = timinca & E1000_TIMINCA_INCVALUE_MASK; - - adjustment = mul_u64_u64_div_u64(incvalue, (u64)delta, - 1000000ULL << 16); - - incvalue = neg_adj ? (incvalue - adjustment) : (incvalue + adjustment); + incvalue = adjust_by_scaled_ppm(incvalue, delta); timinca &= ~E1000_TIMINCA_INCVALUE_MASK; timinca |= incvalue; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index ffea0c9c82f1..c37abbb3cd06 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -347,23 +347,12 @@ static int i40e_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); struct i40e_hw *hw = &pf->hw; - u64 adj, freq, diff; - int neg_adj = 0; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } + u64 adj, base_adj; smp_mb(); /* Force any pending update before accessing. */ - freq = I40E_PTP_40GB_INCVAL * READ_ONCE(pf->ptp_adj_mult); - diff = mul_u64_u64_div_u64(freq, (u64)scaled_ppm, - 1000000ULL << 16); + base_adj = I40E_PTP_40GB_INCVAL * READ_ONCE(pf->ptp_adj_mult); - if (neg_adj) - adj = I40E_PTP_40GB_INCVAL - diff; - else - adj = I40E_PTP_40GB_INCVAL + diff; + adj = adjust_by_scaled_ppm(base_adj, scaled_ppm); wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF); wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 011b727ab190..5cf198a33e26 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1444,24 +1444,10 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct ice_pf *pf = ptp_info_to_pf(info); struct ice_hw *hw = &pf->hw; - u64 incval, diff; - int neg_adj = 0; + u64 incval; int err; - incval = ice_base_incval(pf); - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - diff = mul_u64_u64_div_u64(incval, (u64)scaled_ppm, - 1000000ULL << 16); - if (neg_adj) - incval -= diff; - else - incval += diff; - + incval = adjust_by_scaled_ppm(ice_base_incval(pf), scaled_ppm); err = ice_ptp_write_incval_locked(hw, incval); if (err) { dev_err(ice_pf_to_dev(pf), "PTP failed to set incval, err %d\n", diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 15e57460e19e..6f471b91f562 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -195,23 +195,9 @@ static int igb_ptp_adjfine_82576(struct ptp_clock_info *ptp, long scaled_ppm) struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); struct e1000_hw *hw = &igb->hw; - int neg_adj = 0; - u64 rate; - u32 incvalue; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - incvalue = INCVALUE_82576; - rate = mul_u64_u64_div_u64(incvalue, (u64)scaled_ppm, - 1000000ULL << 16); + u64 incvalue; - if (neg_adj) - incvalue -= rate; - else - incvalue += rate; + incvalue = adjust_by_scaled_ppm(INCVALUE_82576, scaled_ppm); wr32(E1000_TIMINCA, INCPERIOD_82576 | (incvalue & INCVALUE_82576_MASK)); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index f8605f57bd06..fd3f77a9e28d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -451,21 +451,11 @@ static int ixgbe_ptp_adjfine_82599(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; - u64 incval, diff; - int neg_adj = 0; - - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } + u64 incval; smp_mb(); incval = READ_ONCE(adapter->base_incval); - - diff = mul_u64_u64_div_u64(incval, scaled_ppm, - 1000000ULL << 16); - - incval = neg_adj ? (incval - diff) : (incval + diff); + incval = adjust_by_scaled_ppm(incval, scaled_ppm); switch (hw->mac.type) { case ixgbe_mac_X540: @@ -502,17 +492,11 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; - int neg_adj = 0; + bool neg_adj; u64 rate; u32 inca; - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - - rate = mul_u64_u64_div_u64(IXGBE_X550_BASE_PERIOD, scaled_ppm, - 1000000ULL << 16); + neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate); /* warn if rate is too large */ if (rate >= INCVALUE_MASK) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index ad4aaadc2f7a..f4781c5766d6 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -248,6 +248,52 @@ static inline long scaled_ppm_to_ppb(long ppm) return (long)ppb; } +/** + * diff_by_scaled_ppm - Calculate difference using scaled ppm + * @base: the base increment value to adjust + * @scaled_ppm: scaled parts per million to adjust by + * @diff: on return, the absolute value of calculated diff + * + * Calculate the difference to adjust the base increment using scaled parts + * per million. + * + * Use mul_u64_u64_div_u64 to perform the difference calculation in avoid + * possible overflow. + * + * Returns: true if scaled_ppm is negative, false otherwise + */ +static inline bool diff_by_scaled_ppm(u64 base, long scaled_ppm, u64 *diff) +{ + bool negative = false; + + if (scaled_ppm < 0) { + negative = true; + scaled_ppm = -scaled_ppm; + } + + *diff = mul_u64_u64_div_u64(base, (u64)scaled_ppm, 1000000ULL << 16); + + return negative; +} + +/** + * adjust_by_scaled_ppm - Adjust a base increment by scaled parts per million + * @base: the base increment value to adjust + * @scaled_ppm: scaled parts per million frequency adjustment + * + * Helper function which calculates a new increment value based on the + * requested scaled parts per million adjustment. + */ +static inline u64 adjust_by_scaled_ppm(u64 base, long scaled_ppm) +{ + u64 diff; + + if (diff_by_scaled_ppm(base, scaled_ppm, &diff)) + return base - diff; + + return base + diff; +} + #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) /** -- cgit v1.2.3 From 1d997f1013079c05b642c739901e3584a3ae558d Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 28 Oct 2022 04:42:21 -0400 Subject: rtnetlink: pass netlink message header and portid to rtnl_configure_link() This patch pass netlink message header and portid to rtnl_configure_link() All the functions in this call chain need to add the parameters so we can use them in the last call rtnl_notify(), and notify the userspace about the new link info if NLM_F_ECHO flag is set. - rtnl_configure_link() - __dev_notify_flags() - rtmsg_ifinfo() - rtmsg_ifinfo_event() - rtmsg_ifinfo_build_skb() - rtmsg_ifinfo_send() - rtnl_notify() Also move __dev_notify_flags() declaration to net/core/dev.h, as Jakub suggested. Signed-off-by: Hangbin Liu Reviewed-by: Guillaume Nault Signed-off-by: Jakub Kicinski --- drivers/net/can/vxcan.c | 2 +- drivers/net/geneve.c | 2 +- drivers/net/veth.c | 2 +- drivers/net/vxlan/vxlan_core.c | 4 ++-- drivers/net/wwan/wwan_core.c | 2 +- include/linux/netdevice.h | 2 -- include/linux/rtnetlink.h | 9 +++++---- include/net/netlink.h | 11 +++++++++++ include/net/rtnetlink.h | 3 ++- net/core/dev.c | 25 +++++++++++++------------ net/core/dev.h | 4 ++++ net/core/rtnetlink.c | 35 +++++++++++++++++++---------------- net/ipv4/ip_gre.c | 2 +- 13 files changed, 61 insertions(+), 42 deletions(-) (limited to 'include') diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 26a472d2ea58..4068d962203d 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -236,7 +236,7 @@ static int vxcan_newlink(struct net *net, struct net_device *dev, netif_carrier_off(peer); - err = rtnl_configure_link(peer, ifmp); + err = rtnl_configure_link(peer, ifmp, 0, NULL); if (err < 0) goto unregister_network_device; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index f393e454f45c..89ff7f8e8c7e 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1907,7 +1907,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, if (err) goto err; - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto err; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 740506c44427..ac7c0653695f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1773,7 +1773,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, veth_disable_gro(peer); netif_carrier_off(peer); - err = rtnl_configure_link(peer, ifmp); + err = rtnl_configure_link(peer, ifmp, 0, NULL); if (err < 0) goto err_configure_peer; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 6ab669dcd1c6..92224b36787a 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3794,7 +3794,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, goto errout; } - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto unlink; @@ -4416,7 +4416,7 @@ struct net_device *vxlan_dev_create(struct net *net, const char *name, return ERR_PTR(err); } - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) { LIST_HEAD(list_kill); diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 62e9f7d6c9fe..d72ee18476d1 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -1058,7 +1058,7 @@ static void wwan_create_default_link(struct wwan_device *wwandev, goto unlock; } - rtnl_configure_link(dev, NULL); /* Link initialized, notify new link */ + rtnl_configure_link(dev, NULL, 0, NULL); /* Link initialized, notify new link */ unlock: rtnl_unlock(); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 99e58b773266..4b5052db978f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3855,8 +3855,6 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); -void __dev_notify_flags(struct net_device *, unsigned int old_flags, - unsigned int gchanges); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index ae2c6a3cec5d..92ad75549e9c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -12,21 +12,22 @@ extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); extern int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid); extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, - u32 group, struct nlmsghdr *nlh, gfp_t flags); + u32 group, const struct nlmsghdr *nlh, gfp_t flags); extern void rtnl_set_sk_err(struct net *net, u32 group, int error); extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics); extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, gfp_t flags, + u32 portid, const struct nlmsghdr *nlh); void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, gfp_t flags, int *new_nsid, int new_ifindex); struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex); + int new_ifindex, u32 portid, u32 seq); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, - gfp_t flags); + gfp_t flags, u32 portid, const struct nlmsghdr *nlh); /* RTNL is used as a global lock for all changes to network configuration */ diff --git a/include/net/netlink.h b/include/net/netlink.h index 784b4688fc6f..464e2e026f7b 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -899,6 +899,17 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh) return nlh ? !!(nlh->nlmsg_flags & NLM_F_ECHO) : 0; } +/** + * nlmsg_seq - return the seq number of netlink message + * @nlh: netlink message header + * + * Returns 0 if netlink message is NULL + */ +static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) +{ + return nlh ? nlh->nlmsg_seq : 0; +} + /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bf8bb3357825..cd94f65dc2a9 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -187,7 +187,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, struct nlattr *tb[], struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev); -int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); +int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, + u32 portid, const struct nlmsghdr *nlh); int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, struct netlink_ext_ack *exterr); diff --git a/net/core/dev.c b/net/core/dev.c index cfb68db040a4..19e0db536022 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1333,7 +1333,7 @@ void netdev_state_change(struct net_device *dev) call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } EXPORT_SYMBOL(netdev_state_change); @@ -1469,7 +1469,7 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) if (ret < 0) return ret; - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; @@ -1541,7 +1541,7 @@ void dev_close_many(struct list_head *head, bool unlink) __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); @@ -8351,7 +8351,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) - __dev_notify_flags(dev, old_flags, IFF_PROMISC); + __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } @@ -8406,7 +8406,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, - dev->gflags ^ old_gflags); + dev->gflags ^ old_gflags, 0, NULL); } return 0; } @@ -8569,12 +8569,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, - unsigned int gchanges) + unsigned int gchanges, u32 portid, + const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) - rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) @@ -8616,7 +8617,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); - __dev_notify_flags(dev, old_flags, changes); + __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } EXPORT_SYMBOL(dev_change_flags); @@ -10101,7 +10102,7 @@ int register_netdevice(struct net_device *dev) */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; @@ -10849,7 +10850,7 @@ void unregister_netdevice_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); + GFP_KERNEL, NULL, 0, 0, 0); /* * Flush the unicast and multicast chains @@ -10864,7 +10865,7 @@ void unregister_netdevice_many(struct list_head *head) dev->netdev_ops->ndo_uninit(dev); if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, 0, NULL); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); @@ -11042,7 +11043,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; diff --git a/net/core/dev.h b/net/core/dev.h index cbb8a925175a..6b3c7302f570 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -88,6 +88,10 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier); void __dev_set_rx_mode(struct net_device *dev); +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, + unsigned int gchanges, u32 portid, + const struct nlmsghdr *nlh); + static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 74864dc46a7e..c9dd9730f3c6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -760,7 +760,7 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) EXPORT_SYMBOL(rtnl_unicast); void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, - struct nlmsghdr *nlh, gfp_t flags) + const struct nlmsghdr *nlh, gfp_t flags) { struct sock *rtnl = net->rtnl; @@ -3180,7 +3180,8 @@ out: return err; } -int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) +int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, + u32 portid, const struct nlmsghdr *nlh) { unsigned int old_flags; int err; @@ -3194,10 +3195,10 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags), portid, nlh); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - __dev_notify_flags(dev, old_flags, ~0U); + __dev_notify_flags(dev, old_flags, ~0U, portid, nlh); } return 0; } @@ -3369,7 +3370,7 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, goto out; } - err = rtnl_configure_link(dev, ifm); + err = rtnl_configure_link(dev, ifm, 0, NULL); if (err < 0) goto out_unregister; if (link_net) { @@ -3896,7 +3897,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex) + int new_ifindex, u32 portid, u32 seq) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -3907,7 +3908,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, goto errout; err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), - type, 0, 0, change, 0, 0, event, + type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ @@ -3922,16 +3923,18 @@ errout: return NULL; } -void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) +void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, + u32 portid, const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); + rtnl_notify(skb, net, portid, RTNLGRP_LINK, nlh, flags); } static void rtmsg_ifinfo_event(int type, struct net_device *dev, unsigned int change, u32 event, - gfp_t flags, int *new_nsid, int new_ifindex) + gfp_t flags, int *new_nsid, int new_ifindex, + u32 portid, const struct nlmsghdr *nlh) { struct sk_buff *skb; @@ -3939,23 +3942,23 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex); + new_ifindex, portid, nlmsg_seq(nlh)); if (skb) - rtmsg_ifinfo_send(skb, dev, flags); + rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) + gfp_t flags, u32 portid, const struct nlmsghdr *nlh) { rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, - NULL, 0); + NULL, 0, portid, nlh); } void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, gfp_t flags, int *new_nsid, int new_ifindex) { rtmsg_ifinfo_event(type, dev, change, rtnl_get_event(0), flags, - new_nsid, new_ifindex); + new_nsid, new_ifindex, 0, NULL); } static int nlmsg_populate_fdb_fill(struct sk_buff *skb, @@ -6140,7 +6143,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_CHANGELOWERSTATE: case NETDEV_CHANGE_TX_QUEUE_LEN: rtmsg_ifinfo_event(RTM_NEWLINK, dev, 0, rtnl_get_event(event), - GFP_KERNEL, NULL, 0); + GFP_KERNEL, NULL, 0, 0, NULL); break; default: break; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f866d6282b2b..d8ee5238c395 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1665,7 +1665,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, if (err) goto out; - err = rtnl_configure_link(dev, NULL); + err = rtnl_configure_link(dev, NULL, 0, NULL); if (err < 0) goto out; -- cgit v1.2.3 From f3a63cce1b4fbde7738395c5a2dea83f05de3407 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 28 Oct 2022 04:42:24 -0400 Subject: rtnetlink: Honour NLM_F_ECHO flag in rtnl_delete_link This patch use the new helper unregister_netdevice_many_notify() for rtnl_delete_link(), so that the kernel could reply unicast when userspace set NLM_F_ECHO flag to request the new created interface info. At the same time, the parameters of rtnl_delete_link() need to be updated since we need nlmsghdr and portid info. Suggested-by: Guillaume Nault Signed-off-by: Hangbin Liu Reviewed-by: Guillaume Nault Signed-off-by: Jakub Kicinski --- include/net/rtnetlink.h | 2 +- net/core/rtnetlink.c | 7 ++++--- net/openvswitch/vport-geneve.c | 2 +- net/openvswitch/vport-gre.c | 2 +- net/openvswitch/vport-netdev.c | 2 +- net/openvswitch/vport-vxlan.c | 2 +- 6 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index cd94f65dc2a9..d9076a7a430c 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -186,7 +186,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[], struct netlink_ext_ack *extack); -int rtnl_delete_link(struct net_device *dev); +int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm, u32 portid, const struct nlmsghdr *nlh); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 839ff8b7eadc..d2f27548fc0b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3110,7 +3110,7 @@ static int rtnl_group_dellink(const struct net *net, int group) return 0; } -int rtnl_delete_link(struct net_device *dev) +int rtnl_delete_link(struct net_device *dev, u32 portid, const struct nlmsghdr *nlh) { const struct rtnl_link_ops *ops; LIST_HEAD(list_kill); @@ -3120,7 +3120,7 @@ int rtnl_delete_link(struct net_device *dev) return -EOPNOTSUPP; ops->dellink(dev, &list_kill); - unregister_netdevice_many(&list_kill); + unregister_netdevice_many_notify(&list_kill, portid, nlh); return 0; } @@ -3130,6 +3130,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + u32 portid = NETLINK_CB(skb).portid; struct net *tgt_net = net; struct net_device *dev = NULL; struct ifinfomsg *ifm; @@ -3171,7 +3172,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } - err = rtnl_delete_link(dev); + err = rtnl_delete_link(dev, portid, nlh); out: if (netnsid >= 0) diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 89a8e1501809..b10e1602c6b1 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -91,7 +91,7 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); goto error; diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index e6b5e76a962a..4014c9b5eb79 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -57,7 +57,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); return ERR_PTR(err); diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index 2f61d5bdce1a..903537a5da22 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -172,7 +172,7 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) * if it's not already shutting down. */ if (vport->dev->reg_state == NETREG_REGISTERED) - rtnl_delete_link(vport->dev); + rtnl_delete_link(vport->dev, 0, NULL); netdev_put(vport->dev, &vport->dev_tracker); vport->dev = NULL; rtnl_unlock(); diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 188e9c1360a1..0b881b043bcf 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -120,7 +120,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) err = dev_change_flags(dev, dev->flags | IFF_UP, NULL); if (err < 0) { - rtnl_delete_link(dev); + rtnl_delete_link(dev, 0, NULL); rtnl_unlock(); ovs_vport_free(vport); goto error; -- cgit v1.2.3 From 0e84afe8ebfbb9eade3f4f6de4720887bf908e26 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Oct 2022 15:45:16 +0000 Subject: net: dropreason: add SKB_CONSUMED reason This will allow to simply use in the future: kfree_skb_reason(skb, reason); Instead of repeating sequences like: if (dropped) kfree_skb_reason(skb, reason); else consume_skb(skb); For instance, following patch in the series is adding @reason to skb_release_data() and skb_release_all(), so that we can propagate a meaningful @reason whenever consume_skb()/kfree_skb() have to take care of a potential frag_list. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/dropreason.h | 2 ++ net/core/skbuff.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dropreason.h b/include/net/dropreason.h index c1cbcdbaf149..0bd18c14dae0 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -80,6 +80,8 @@ enum skb_drop_reason { * @SKB_NOT_DROPPED_YET: skb is not dropped yet (used for no-drop case) */ SKB_NOT_DROPPED_YET = 0, + /** @SKB_CONSUMED: packet has been consumed */ + SKB_CONSUMED, /** @SKB_DROP_REASON_NOT_SPECIFIED: drop reason is not specified */ SKB_DROP_REASON_NOT_SPECIFIED, /** @SKB_DROP_REASON_NO_SOCKET: socket not found */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d84a17eada5..7ce797cd121f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -94,6 +94,7 @@ EXPORT_SYMBOL(sysctl_max_skb_frags); #undef FN #define FN(reason) [SKB_DROP_REASON_##reason] = #reason, const char * const drop_reasons[] = { + [SKB_CONSUMED] = "CONSUMED", DEFINE_DROP_REASON(FN, FN) }; EXPORT_SYMBOL(drop_reasons); @@ -894,7 +895,10 @@ kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) DEBUG_NET_WARN_ON_ONCE(reason <= 0 || reason >= SKB_DROP_REASON_MAX); - trace_kfree_skb(skb, __builtin_return_address(0), reason); + if (reason == SKB_CONSUMED) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, __builtin_return_address(0), reason); __kfree_skb(skb); } EXPORT_SYMBOL(kfree_skb_reason); -- cgit v1.2.3 From 4ecbb1c27c363686d11a241cd682a454a8454c2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Oct 2022 15:45:18 +0000 Subject: net: dropreason: add SKB_DROP_REASON_DUP_FRAG This is used to track when a duplicate segment received by various reassembly units is dropped. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/dropreason.h | 3 +++ net/ipv4/ip_fragment.c | 13 +++++++++---- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- net/ipv6/reassembly.c | 13 +++++++++---- 4 files changed, 22 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 0bd18c14dae0..602d555a5f83 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -68,6 +68,7 @@ FN(IP_INADDRERRORS) \ FN(IP_INNOROUTES) \ FN(PKT_TOO_BIG) \ + FN(DUP_FRAG) \ FNe(MAX) /** @@ -300,6 +301,8 @@ enum skb_drop_reason { * MTU) */ SKB_DROP_REASON_PKT_TOO_BIG, + /** @SKB_DROP_REASON_DUP_FRAG: duplicate fragment */ + SKB_DROP_REASON_DUP_FRAG, /** * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be * used as a real 'reason' diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fb153569889e..676bd8d25955 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -278,10 +278,14 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) struct net_device *dev; unsigned int fragsize; int err = -ENOENT; + SKB_DR(reason); u8 ecn; - if (qp->q.flags & INET_FRAG_COMPLETE) + /* If reassembly is already done, @skb must be a duplicate frag. */ + if (qp->q.flags & INET_FRAG_COMPLETE) { + SKB_DR_SET(reason, DUP_FRAG); goto err; + } if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) && unlikely(ip_frag_too_far(qp)) && @@ -382,8 +386,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) insert_error: if (err == IPFRAG_DUP) { - kfree_skb(skb); - return -EINVAL; + SKB_DR_SET(reason, DUP_FRAG); + err = -EINVAL; + goto err; } err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); @@ -391,7 +396,7 @@ discard_qp: inet_frag_kill(&qp->q); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return err; } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 38db0064d661..d13240f13607 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -253,7 +253,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, if (err) { if (err == IPFRAG_DUP) { /* No error for duplicates, pretend they got queued. */ - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_DUP_FRAG); return -EINPROGRESS; } goto insert_error; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index ff866f2a879e..5bc8a28e67f9 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -112,10 +112,14 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct sk_buff *prev_tail; struct net_device *dev; int err = -ENOENT; + SKB_DR(reason); u8 ecn; - if (fq->q.flags & INET_FRAG_COMPLETE) + /* If reassembly is already done, @skb must be a duplicate frag. */ + if (fq->q.flags & INET_FRAG_COMPLETE) { + SKB_DR_SET(reason, DUP_FRAG); goto err; + } err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; @@ -226,8 +230,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, insert_error: if (err == IPFRAG_DUP) { - kfree_skb(skb); - return -EINVAL; + SKB_DR_SET(reason, DUP_FRAG); + err = -EINVAL; + goto err; } err = -EINVAL; __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), @@ -237,7 +242,7 @@ discard_fq: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); err: - kfree_skb(skb); + kfree_skb_reason(skb, reason); return err; } -- cgit v1.2.3 From 77adfd3a1d44c4730fd2af99b497e04ddc2b5837 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Oct 2022 15:45:19 +0000 Subject: net: dropreason: add SKB_DROP_REASON_FRAG_REASM_TIMEOUT Used to track skbs freed after a timeout happened in a reassmbly unit. Passing a @reason argument to inet_frag_rbtree_purge() allows to use correct consumed status for frags that have been successfully re-assembled. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/dropreason.h | 3 +++ include/net/inet_frag.h | 6 +++++- include/net/ipv6_frag.h | 3 ++- net/ipv4/inet_fragment.c | 14 ++++++++++---- net/ipv4/ip_fragment.c | 6 ++++-- 5 files changed, 24 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 602d555a5f83..1d45a74148c3 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -69,6 +69,7 @@ FN(IP_INNOROUTES) \ FN(PKT_TOO_BIG) \ FN(DUP_FRAG) \ + FN(FRAG_REASM_TIMEOUT) \ FNe(MAX) /** @@ -303,6 +304,8 @@ enum skb_drop_reason { SKB_DROP_REASON_PKT_TOO_BIG, /** @SKB_DROP_REASON_DUP_FRAG: duplicate fragment */ SKB_DROP_REASON_DUP_FRAG, + /** @SKB_DROP_REASON_FRAG_REASM_TIMEOUT: fragment reassembly timeout */ + SKB_DROP_REASON_FRAG_REASM_TIMEOUT, /** * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be * used as a real 'reason' diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 0b0876610553..b23ddec3cd5c 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -7,6 +7,7 @@ #include #include #include +#include /* Per netns frag queues directory */ struct fqdir { @@ -34,12 +35,14 @@ struct fqdir { * @INET_FRAG_LAST_IN: final fragment has arrived * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction * @INET_FRAG_HASH_DEAD: inet_frag_kill() has not removed fq from rhashtable + * @INET_FRAG_DROP: if skbs must be dropped (instead of being consumed) */ enum { INET_FRAG_FIRST_IN = BIT(0), INET_FRAG_LAST_IN = BIT(1), INET_FRAG_COMPLETE = BIT(2), INET_FRAG_HASH_DEAD = BIT(3), + INET_FRAG_DROP = BIT(4), }; struct frag_v4_compare_key { @@ -139,7 +142,8 @@ void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key); /* Free all skbs in the queue; return the sum of their truesizes. */ -unsigned int inet_frag_rbtree_purge(struct rb_root *root); +unsigned int inet_frag_rbtree_purge(struct rb_root *root, + enum skb_drop_reason reason); static inline void inet_frag_put(struct inet_frag_queue *q) { diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h index 5052c66e22d2..7321ffe3a108 100644 --- a/include/net/ipv6_frag.h +++ b/include/net/ipv6_frag.h @@ -76,6 +76,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) if (fq->q.flags & INET_FRAG_COMPLETE) goto out; + fq->q.flags |= INET_FRAG_DROP; inet_frag_kill(&fq->q); dev = dev_get_by_index_rcu(net, fq->iif); @@ -101,7 +102,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); - kfree_skb(head); + kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); goto out_rcu_unlock; out: diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9f9ac5013a7..7072fc0783ef 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -133,6 +133,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) count = del_timer_sync(&fq->timer) ? 1 : 0; spin_lock_bh(&fq->lock); + fq->flags |= INET_FRAG_DROP; if (!(fq->flags & INET_FRAG_COMPLETE)) { fq->flags |= INET_FRAG_COMPLETE; count++; @@ -260,7 +261,8 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } -unsigned int inet_frag_rbtree_purge(struct rb_root *root) +unsigned int inet_frag_rbtree_purge(struct rb_root *root, + enum skb_drop_reason reason) { struct rb_node *p = rb_first(root); unsigned int sum = 0; @@ -274,7 +276,7 @@ unsigned int inet_frag_rbtree_purge(struct rb_root *root) struct sk_buff *next = FRAG_CB(skb)->next_frag; sum += skb->truesize; - kfree_skb(skb); + kfree_skb_reason(skb, reason); skb = next; } } @@ -284,17 +286,21 @@ EXPORT_SYMBOL(inet_frag_rbtree_purge); void inet_frag_destroy(struct inet_frag_queue *q) { - struct fqdir *fqdir; unsigned int sum, sum_truesize = 0; + enum skb_drop_reason reason; struct inet_frags *f; + struct fqdir *fqdir; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); + reason = (q->flags & INET_FRAG_DROP) ? + SKB_DROP_REASON_FRAG_REASM_TIMEOUT : + SKB_CONSUMED; WARN_ON(del_timer(&q->timer) != 0); /* Release all fragment data. */ fqdir = q->fqdir; f = fqdir->f; - sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments, reason); sum = sum_truesize + f->qsize; call_rcu(&q->rcu, inet_frag_destroy_rcu); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 676bd8d25955..85e8113259c3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -153,6 +153,7 @@ static void ip_expire(struct timer_list *t) if (qp->q.flags & INET_FRAG_COMPLETE) goto out; + qp->q.flags |= INET_FRAG_DROP; ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); @@ -194,7 +195,7 @@ out: spin_unlock(&qp->q.lock); out_rcu_unlock: rcu_read_unlock(); - kfree_skb(head); + kfree_skb_reason(head, SKB_DROP_REASON_FRAG_REASM_TIMEOUT); ipq_put(qp); } @@ -254,7 +255,8 @@ static int ip_frag_reinit(struct ipq *qp) return -ETIMEDOUT; } - sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments); + sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, + SKB_DROP_REASON_NOT_SPECIFIED); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; -- cgit v1.2.3 From 3bdfb04f13ebdd4ae50fc5dc595663874781e48c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Oct 2022 15:45:20 +0000 Subject: net: dropreason: add SKB_DROP_REASON_FRAG_TOO_FAR IPv4 reassembly unit can decide to drop frags based on /proc/sys/net/ipv4/ipfrag_max_dist sysctl. Add a specific drop reason to track this specific and weird case. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/dropreason.h | 6 ++++++ net/ipv4/ip_fragment.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/dropreason.h b/include/net/dropreason.h index 1d45a74148c3..70539288f995 100644 --- a/include/net/dropreason.h +++ b/include/net/dropreason.h @@ -70,6 +70,7 @@ FN(PKT_TOO_BIG) \ FN(DUP_FRAG) \ FN(FRAG_REASM_TIMEOUT) \ + FN(FRAG_TOO_FAR) \ FNe(MAX) /** @@ -306,6 +307,11 @@ enum skb_drop_reason { SKB_DROP_REASON_DUP_FRAG, /** @SKB_DROP_REASON_FRAG_REASM_TIMEOUT: fragment reassembly timeout */ SKB_DROP_REASON_FRAG_REASM_TIMEOUT, + /** + * @SKB_DROP_REASON_FRAG_TOO_FAR: ipv4 fragment too far. + * (/proc/sys/net/ipv4/ipfrag_max_dist) + */ + SKB_DROP_REASON_FRAG_TOO_FAR, /** * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be * used as a real 'reason' diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 85e8113259c3..69c00ffdcf3e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -256,7 +256,7 @@ static int ip_frag_reinit(struct ipq *qp) } sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments, - SKB_DROP_REASON_NOT_SPECIFIED); + SKB_DROP_REASON_FRAG_TOO_FAR); sub_frag_mem_limit(qp->q.fqdir, sum_truesize); qp->q.flags = 0; -- cgit v1.2.3 From d08b0f8f46e45a274fc8c9a5bc92cb9da70d9887 Mon Sep 17 00:00:00 2001 From: Shane Parslow Date: Sat, 29 Oct 2022 02:03:56 -0700 Subject: net: wwan: iosm: add rpc interface for xmm modems Add a new iosm wwan port that connects to the modem rpc interface. This interface provides a configuration channel, and in the case of the 7360, is the only way to configure the modem (as it does not support mbim). The new interface is compatible with existing software, such as open_xdatachannel.py from the xmm7360-pci project [1]. [1] https://github.com/xmm7360/xmm7360-pci Signed-off-by: Shane Parslow Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c | 2 +- drivers/net/wwan/wwan_core.c | 4 ++++ include/linux/wwan.h | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c index 128c999e08bb..bcfbc6b3d617 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c @@ -39,7 +39,7 @@ static struct ipc_chnl_cfg modem_cfg[] = { /* RPC - 0 */ { IPC_MEM_CTRL_CHL_ID_1, IPC_MEM_PIPE_2, IPC_MEM_PIPE_3, IPC_MEM_MAX_TDS_RPC, IPC_MEM_MAX_TDS_RPC, - IPC_MEM_MAX_DL_RPC_BUF_SIZE, WWAN_PORT_UNKNOWN }, + IPC_MEM_MAX_DL_RPC_BUF_SIZE, WWAN_PORT_XMMRPC }, /* IAT0 */ { IPC_MEM_CTRL_CHL_ID_2, IPC_MEM_PIPE_4, IPC_MEM_PIPE_5, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_DL_AT_BUF_SIZE, diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index d72ee18476d1..966d0ccd2276 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -319,6 +319,10 @@ static const struct { .name = "FIREHOSE", .devsuf = "firehose", }, + [WWAN_PORT_XMMRPC] = { + .name = "XMMRPC", + .devsuf = "xmmrpc", + }, }; static ssize_t type_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 5ce2acf444fb..24d76500b1cc 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -15,6 +15,7 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol + * @WWAN_PORT_XMMRPC: Control protocol for Intel XMM modems * * @WWAN_PORT_MAX: Highest supported port types * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type @@ -26,6 +27,7 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, + WWAN_PORT_XMMRPC, /* Add new port types above this line */ -- cgit v1.2.3 From 777fa87c7682228e155cf0892ba61cb2ab1fe3ae Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 31 Oct 2022 12:44:09 +0100 Subject: bonding (gcc13): synchronize bond_{a,t}lb_xmit() types Both bond_alb_xmit() and bond_tlb_xmit() produce a valid warning with gcc-13: drivers/net/bonding/bond_alb.c:1409:13: error: conflicting types for 'bond_tlb_xmit' due to enum/integer mismatch; have 'netdev_tx_t(struct sk_buff *, struct net_device *)' ... include/net/bond_alb.h:160:5: note: previous declaration of 'bond_tlb_xmit' with type 'int(struct sk_buff *, struct net_device *)' drivers/net/bonding/bond_alb.c:1523:13: error: conflicting types for 'bond_alb_xmit' due to enum/integer mismatch; have 'netdev_tx_t(struct sk_buff *, struct net_device *)' ... include/net/bond_alb.h:159:5: note: previous declaration of 'bond_alb_xmit' with type 'int(struct sk_buff *, struct net_device *)' I.e. the return type of the declaration is int, while the definitions spell netdev_tx_t. Synchronize both of them to the latter. Cc: Martin Liska Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Jiri Slaby (SUSE) Link: https://lore.kernel.org/r/20221031114409.10417-1-jirislaby@kernel.org Signed-off-by: Jakub Kicinski --- include/net/bond_alb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 191c36afa1f4..9dc082b2d543 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -156,8 +156,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave); void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave); void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char link); void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave); -int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); -int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev); +netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev); struct slave *bond_xmit_alb_slave_get(struct bonding *bond, struct sk_buff *skb); struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, -- cgit v1.2.3 From ec32c0c42d0a7208571c4c77f140bffaa4e5e304 Mon Sep 17 00:00:00 2001 From: Daniel Machon Date: Tue, 1 Nov 2022 10:48:29 +0100 Subject: net: dcb: add new pcp selector to app object Add new PCP selector for the 8021Qaz APP managed object. As the PCP selector is not part of the 8021Qaz standard, a new non-std extension attribute DCB_ATTR_DCB_APP has been introduced. Also two helper functions to translate between selector and app attribute type has been added. The new selector has been given a value of 255, to minimize the risk of future overlap of std- and non-std attributes. The new DCB_ATTR_DCB_APP is sent alongside the ieee std attribute in the app table. This means that the dcb_app struct can now both contain std- and non-std app attributes. Currently there is no overlap between the selector values of the two attributes. The purpose of adding the PCP selector, is to be able to offload PCP-based queue classification to the 8021Q Priority Code Point table, see 6.9.3 of IEEE Std 802.1Q-2018. PCP and DEI is encoded in the protocol field as 8*dei+pcp, so that a mapping of PCP 2 and DEI 1 to priority 3 is encoded as {255, 10, 3}. Signed-off-by: Daniel Machon Reviewed-by: Petr Machata Signed-off-by: Paolo Abeni --- include/uapi/linux/dcbnl.h | 6 +++++ net/dcb/dcbnl.c | 58 ++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 60 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index a791a94013a6..dc7ef96207ca 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -218,6 +218,9 @@ struct cee_pfc { #define IEEE_8021QAZ_APP_SEL_ANY 4 #define IEEE_8021QAZ_APP_SEL_DSCP 5 +/* Non-std selector values */ +#define DCB_APP_SEL_PCP 255 + /* This structure contains the IEEE 802.1Qaz APP managed object. This * object is also used for the CEE std as well. * @@ -247,6 +250,8 @@ struct dcb_app { __u16 protocol; }; +#define IEEE_8021QAZ_APP_SEL_MAX 255 + /** * struct dcb_peer_app_info - APP feature information sent by the peer * @@ -425,6 +430,7 @@ enum ieee_attrs { enum ieee_attrs_app { DCB_ATTR_IEEE_APP_UNSPEC, DCB_ATTR_IEEE_APP, + DCB_ATTR_DCB_APP, __DCB_ATTR_IEEE_APP_MAX }; #define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..0c17bb28ae60 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -179,6 +179,38 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { static LIST_HEAD(dcb_app_list); static DEFINE_SPINLOCK(dcb_lock); +static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) +{ + switch (selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + case IEEE_8021QAZ_APP_SEL_STREAM: + case IEEE_8021QAZ_APP_SEL_DGRAM: + case IEEE_8021QAZ_APP_SEL_ANY: + case IEEE_8021QAZ_APP_SEL_DSCP: + return DCB_ATTR_IEEE_APP; + case DCB_APP_SEL_PCP: + return DCB_ATTR_DCB_APP; + default: + return DCB_ATTR_IEEE_APP_UNSPEC; + } +} + +static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) +{ + switch (type) { + case DCB_ATTR_IEEE_APP: + case DCB_ATTR_DCB_APP: + return true; + default: + return false; + } +} + +static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) +{ + return dcbnl_app_attr_type_get(selector) == type; +} + static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, u32 flags, struct nlmsghdr **nlhp) { @@ -1116,8 +1148,9 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { - err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app), - &itr->app); + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); return -EMSGSIZE; @@ -1493,9 +1526,10 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; if (nla_len(attr) < sizeof(struct dcb_app)) { @@ -1504,6 +1538,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_setapp) err = ops->ieee_setapp(netdev, app_data); else @@ -1554,11 +1595,20 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; + app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_delapp) err = ops->ieee_delapp(netdev, app_data); else -- cgit v1.2.3 From 6182d5875c330a5a611687caa05f47752455720c Mon Sep 17 00:00:00 2001 From: Daniel Machon Date: Tue, 1 Nov 2022 10:48:30 +0100 Subject: net: dcb: add new apptrust attribute Add new apptrust extension attributes to the 8021Qaz APP managed object. Two new attributes, DCB_ATTR_DCB_APP_TRUST_TABLE and DCB_ATTR_DCB_APP_TRUST, has been added. Trusted selectors are passed in the nested attribute DCB_ATTR_DCB_APP_TRUST, in order of precedence. The new attributes are meant to allow drivers, whose hw supports the notion of trust, to be able to set whether a particular app selector is trusted - and in which order. Signed-off-by: Daniel Machon Reviewed-by: Petr Machata Signed-off-by: Paolo Abeni --- include/net/dcbnl.h | 4 +++ include/uapi/linux/dcbnl.h | 2 ++ net/dcb/dcbnl.c | 76 ++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 80 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 2b2d86fb3131..8841ab6c2de7 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -109,6 +109,10 @@ struct dcbnl_rtnl_ops { /* buffer settings */ int (*dcbnl_getbuffer)(struct net_device *, struct dcbnl_buffer *); int (*dcbnl_setbuffer)(struct net_device *, struct dcbnl_buffer *); + + /* apptrust */ + int (*dcbnl_setapptrust)(struct net_device *, u8 *, int); + int (*dcbnl_getapptrust)(struct net_device *, u8 *, int *); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index dc7ef96207ca..99047223ab26 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -410,6 +410,7 @@ enum dcbnl_attrs { * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only + * @DCB_ATTR_DCB_APP_TRUST_TABLE: selector trust table */ enum ieee_attrs { DCB_ATTR_IEEE_UNSPEC, @@ -423,6 +424,7 @@ enum ieee_attrs { DCB_ATTR_IEEE_QCN, DCB_ATTR_IEEE_QCN_STATS, DCB_ATTR_DCB_BUFFER, + DCB_ATTR_DCB_APP_TRUST_TABLE, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 0c17bb28ae60..cec0632f96db 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -166,6 +166,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, + [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, }; /* DCB number of traffic classes nested attributes. */ @@ -1062,9 +1063,9 @@ nla_put_failure: /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { - struct nlattr *ieee, *app; - struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee, *app, *apptrust; + struct dcb_app_type *itr; int dcbx; int err; @@ -1166,6 +1167,30 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); + if (ops->dcbnl_getapptrust) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + int nselectors, i; + + apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); + if (!apptrust) + return -EMSGSIZE; + + err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); + if (!err) { + for (i = 0; i < nselectors; i++) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(selectors[i]); + err = nla_put_u8(skb, type, selectors[i]); + if (err) { + nla_nest_cancel(skb, apptrust); + return err; + } + } + } + + nla_nest_end(skb, apptrust); + } + /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; @@ -1554,6 +1579,53 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } } + if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + struct nlattr *attr; + int nselectors = 0; + int rem; + + if (!ops->dcbnl_setapptrust) { + err = -EOPNOTSUPP; + goto err; + } + + nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], + rem) { + enum ieee_attrs_app type = nla_type(attr); + u8 selector; + int i; + + if (!dcbnl_app_attr_type_validate(type) || + nla_len(attr) != 1 || + nselectors >= sizeof(selectors)) { + err = -EINVAL; + goto err; + } + + selector = nla_get_u8(attr); + + if (!dcbnl_app_selector_validate(type, selector)) { + err = -EINVAL; + goto err; + } + + /* Duplicate selector ? */ + for (i = 0; i < nselectors; i++) { + if (selectors[i] == selector) { + err = -EINVAL; + goto err; + } + } + + selectors[nselectors++] = selector; + } + + err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); + if (err) + goto err; + } + err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); -- cgit v1.2.3 From 23da464dd6b8935b66f4ee306ad8947fd32ccd75 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:51 +0530 Subject: bpf: Allow specifying volatile type modifier for kptrs This is useful in particular to mark the pointer as volatile, so that compiler treats each load and store to the field as a volatile access. The alternative is having to define and use READ_ONCE and WRITE_ONCE in the BPF program. Signed-off-by: Kumar Kartikeya Dwivedi Acked-by: David Vernet Link: https://lore.kernel.org/r/20221103191013.1236066-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 5 +++++ kernel/bpf/btf.c | 3 +++ 2 files changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index f9aababc5d78..86aad9b2ce02 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -288,6 +288,11 @@ static inline bool btf_type_is_typedef(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; } +static inline bool btf_type_is_volatile(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_VOLATILE; +} + static inline bool btf_type_is_func(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 35c07afac924..f4d21eef6ebd 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3225,6 +3225,9 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, enum bpf_kptr_type type; u32 res_id; + /* Permit modifiers on the pointer itself */ + if (btf_type_is_volatile(t)) + t = btf_type_by_id(btf, t->type); /* For PTR, sz is always == 8 */ if (!btf_type_is_ptr(t)) return BTF_FIELD_IGNORE; -- cgit v1.2.3 From a35ec8e38cdd1766f29924ca391a01de20163931 Mon Sep 17 00:00:00 2001 From: "Hans J. Schultz" Date: Tue, 1 Nov 2022 21:39:21 +0200 Subject: bridge: Add MAC Authentication Bypass (MAB) support Hosts that support 802.1X authentication are able to authenticate themselves by exchanging EAPOL frames with an authenticator (Ethernet bridge, in this case) and an authentication server. Access to the network is only granted by the authenticator to successfully authenticated hosts. The above is implemented in the bridge using the "locked" bridge port option. When enabled, link-local frames (e.g., EAPOL) can be locally received by the bridge, but all other frames are dropped unless the host is authenticated. That is, unless the user space control plane installed an FDB entry according to which the source address of the frame is located behind the locked ingress port. The entry can be dynamic, in which case learning needs to be enabled so that the entry will be refreshed by incoming traffic. There are deployments in which not all the devices connected to the authenticator (the bridge) support 802.1X. Such devices can include printers and cameras. One option to support such deployments is to unlock the bridge ports connecting these devices, but a slightly more secure option is to use MAB. When MAB is enabled, the MAC address of the connected device is used as the user name and password for the authentication. For MAB to work, the user space control plane needs to be notified about MAC addresses that are trying to gain access so that they will be compared against an allow list. This can be implemented via the regular learning process with the sole difference that learned FDB entries are installed with a new "locked" flag indicating that the entry cannot be used to authenticate the device. The flag cannot be set by user space, but user space can clear the flag by replacing the entry, thereby authenticating the device. Locked FDB entries implement the following semantics with regards to roaming, aging and forwarding: 1. Roaming: Locked FDB entries can roam to unlocked (authorized) ports, in which case the "locked" flag is cleared. FDB entries cannot roam to locked ports regardless of MAB being enabled or not. Therefore, locked FDB entries are only created if an FDB entry with the given {MAC, VID} does not already exist. This behavior prevents unauthenticated devices from disrupting traffic destined to already authenticated devices. 2. Aging: Locked FDB entries age and refresh by incoming traffic like regular entries. 3. Forwarding: Locked FDB entries forward traffic like regular entries. If user space detects an unauthorized MAC behind a locked port and wishes to prevent traffic with this MAC DA from reaching the host, it can do so using tc or a different mechanism. Enable the above behavior using a new bridge port option called "mab". It can only be enabled on a bridge port that is both locked and has learning enabled. Locked FDB entries are flushed from the port once MAB is disabled. A new option is added because there are pure 802.1X deployments that are not interested in notifications about locked FDB entries. Signed-off-by: Hans J. Schultz Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + include/uapi/linux/neighbour.h | 8 +++++++- net/bridge/br_fdb.c | 24 ++++++++++++++++++++++++ net/bridge/br_input.c | 21 +++++++++++++++++++-- net/bridge/br_netlink.c | 21 ++++++++++++++++++++- net/bridge/br_private.h | 3 ++- net/core/rtnetlink.c | 5 +++++ 8 files changed, 79 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index d62ef428e3aa..1668ac4d7adc 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -59,6 +59,7 @@ struct br_ip_list { #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) #define BR_PORT_LOCKED BIT(21) +#define BR_PORT_MAB BIT(22) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5e7a1041df3a..d92b3f79eba3 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -561,6 +561,7 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, + IFLA_BRPORT_MAB, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index a998bf761635..5e67a7eaf4a7 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -52,7 +52,8 @@ enum { #define NTF_STICKY (1 << 6) #define NTF_ROUTER (1 << 7) /* Extended flags under NDA_FLAGS_EXT: */ -#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_LOCKED (1 << 1) /* * Neighbor Cache Entry States. @@ -86,6 +87,11 @@ enum { * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf * of a user space control plane, and automatically refreshed so that (if * possible) they remain in NUD_REACHABLE state. + * + * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the + * bridge in response to a host trying to communicate via a locked bridge port + * with MAB enabled. Their purpose is to notify user space that a host requires + * authentication. */ struct nda_cacheinfo { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e7f4fccb6adb..3b83af4458b8 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -105,6 +105,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; + u32 ext_flags = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) @@ -125,11 +126,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_EXT_LEARNED; if (test_bit(BR_FDB_STICKY, &fdb->flags)) ndm->ndm_flags |= NTF_STICKY; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + ext_flags |= NTF_EXT_LOCKED; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) + goto nla_put_failure; + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@ -171,6 +177,7 @@ static inline size_t fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + + nla_total_size(sizeof(u32)) /* NDA_FLAGS_EXT */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(0) /* NDA_FDB_EXT_ATTRS */ @@ -879,6 +886,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, &fdb->flags))) clear_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + /* Clear locked flag when roaming to an + * unlocked port. + */ + if (unlikely(test_bit(BR_FDB_LOCKED, &fdb->flags))) + clear_bit(BR_FDB_LOCKED, &fdb->flags); } if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) @@ -1082,6 +1094,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + if (test_and_clear_bit(BR_FDB_LOCKED, &fdb->flags)) + modified = true; + if (fdb_handle_notify(fdb, notify)) modified = true; @@ -1150,6 +1165,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge_port *p = NULL; struct net_bridge_vlan *v; struct net_bridge *br = NULL; + u32 ext_flags = 0; int err = 0; trace_br_fdb_add(ndm, dev, addr, vid, nlh_flags); @@ -1178,6 +1194,14 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vg = nbp_vlan_group(p); } + if (tb[NDA_FLAGS_EXT]) + ext_flags = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext_flags & NTF_EXT_LOCKED) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add FDB entry with \"locked\" flag set"); + return -EINVAL; + } + if (tb[NDA_FDB_EXT_ATTRS]) { attr = tb[NDA_FDB_EXT_ATTRS]; err = nla_parse_nested(nfea_tb, NFEA_MAX, attr, diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 68b3e850bcb9..d04d2205ad4e 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -109,9 +109,26 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_fdb_entry *fdb_src = br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); - if (!fdb_src || READ_ONCE(fdb_src->dst) != p || - test_bit(BR_FDB_LOCAL, &fdb_src->flags)) + if (!fdb_src) { + /* FDB miss. Create locked FDB entry if MAB is enabled + * and drop the packet. + */ + if (p->flags & BR_PORT_MAB) + br_fdb_update(br, p, eth_hdr(skb)->h_source, + vid, BIT(BR_FDB_LOCKED)); goto drop; + } else if (READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) { + /* FDB mismatch. Drop the packet without roaming. */ + goto drop; + } else if test_bit(BR_FDB_LOCKED, &fdb_src->flags) { + /* FDB match, but entry is locked. Refresh it and drop + * the packet. + */ + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, + BIT(BR_FDB_LOCKED)); + goto drop; + } } nbp_switchdev_frame_mark(p, skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d087fd4c784a..4316cc82ae17 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -188,6 +188,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -274,7 +275,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || - nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED))) + nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || + nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -876,6 +878,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, + [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; @@ -943,6 +946,22 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); + br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); + + if ((p->flags & BR_PORT_MAB) && + (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { + NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); + p->flags = old_flags; + return -EINVAL; + } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { + struct net_bridge_fdb_flush_desc desc = { + .flags = BIT(BR_FDB_LOCKED), + .flags_mask = BIT(BR_FDB_LOCKED), + .port_ifindex = p->dev->ifindex, + }; + + br_fdb_flush(p->br, &desc); + } changed_mask = old_flags ^ p->flags; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa431..4ce8b8e5ae0b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -251,7 +251,8 @@ enum { BR_FDB_ADDED_BY_EXT_LEARN, BR_FDB_OFFLOADED, BR_FDB_NOTIFY, - BR_FDB_NOTIFY_INACTIVE + BR_FDB_NOTIFY_INACTIVE, + BR_FDB_LOCKED, }; struct net_bridge_fdb_key { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d2f27548fc0b..b64fffeb3844 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4051,6 +4051,11 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, return err; } + if (tb[NDA_FLAGS_EXT]) { + netdev_info(dev, "invalid flags given to default FDB implementation\n"); + return err; + } + if (vid) { netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; -- cgit v1.2.3 From 3830c5719af66fac9849cf5fb04b03d4e4bb46ff Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:01:59 +0100 Subject: net: devlink: convert devlink port type-specific pointers to union Instead of storing type_dev as a void pointer, convert it to union and use it to store either struct net_device or struct ib_device pointer. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 13 ++++++++++--- net/core/devlink.c | 17 +++++++++++++---- 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index ba6b8b094943..6c55aabaedf1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -121,12 +121,19 @@ struct devlink_port { struct list_head region_list; struct devlink *devlink; unsigned int index; - spinlock_t type_lock; /* Protects type and type_dev - * pointer consistency. + spinlock_t type_lock; /* Protects type and type_eth/ib + * structures consistency. */ enum devlink_port_type type; enum devlink_port_type desired_type; - void *type_dev; + union { + struct { + struct net_device *netdev; + } type_eth; + struct { + struct ib_device *ibdev; + } type_ib; + }; struct devlink_port_attrs attrs; u8 attrs_set:1, switch_port:1, diff --git a/net/core/devlink.c b/net/core/devlink.c index 0a16ad45520e..868d04c2164f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1303,7 +1303,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { struct net *net = devlink_net(devlink_port->devlink); - struct net_device *netdev = devlink_port->type_dev; + struct net_device *netdev = devlink_port->type_eth.netdev; if (netdev && net_eq(net, dev_net(netdev)) && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, @@ -1313,7 +1313,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { - struct ib_device *ibdev = devlink_port->type_dev; + struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, @@ -10003,7 +10003,16 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, devlink_port_type_warn_cancel(devlink_port); spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; - devlink_port->type_dev = type_dev; + switch (type) { + case DEVLINK_PORT_TYPE_ETH: + devlink_port->type_eth.netdev = type_dev; + break; + case DEVLINK_PORT_TYPE_IB: + devlink_port->type_ib.ibdev = type_dev; + break; + default: + break; + } spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } @@ -12016,7 +12025,7 @@ devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - metadata->input_dev = in_devlink_port->type_dev; + metadata->input_dev = in_devlink_port->type_eth.netdev; spin_unlock(&in_devlink_port->type_lock); } -- cgit v1.2.3 From 02a68a47eadedf95748facfca6ced31fb0181d52 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:03 +0100 Subject: net: devlink: track netdev with devlink_port assigned Currently, ethernet drivers are using devlink_port_type_eth_set() and devlink_port_type_clear() to set devlink port type and link to related netdev. Instead of calling them directly, let the driver use SET_NETDEV_DEVLINK_PORT macro to assign devlink_port pointer and let devlink to track it. Note the devlink port pointer is static during the time netdevice is registered. In devlink code, use per-namespace netdev notifier to track the netdevices with devlink_port assigned and change the internal devlink_port type and related type pointer accordingly. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 19 ++++++++++++ net/core/dev.c | 14 +++++---- net/core/devlink.c | 75 ++++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 99 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4b5052db978f..f048a30ea10b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1999,6 +1999,11 @@ enum netdev_ml_priv_type { * registered * @offload_xstats_l3: L3 HW stats for this netdevice. * + * @devlink_port: Pointer to related devlink port structure. + * Assigned by a driver before netdev registration using + * SET_NETDEV_DEVLINK_PORT macro. This pointer is static + * during the time netdevice is registered. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2349,9 +2354,22 @@ struct net_device { netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; struct rtnl_hw_stats64 *offload_xstats_l3; + + struct devlink_port *devlink_port; }; #define to_net_dev(d) container_of(d, struct net_device, dev) +/* + * Driver should use this to assign devlink port instance to a netdevice + * before it registers the netdevice. Therefore devlink_port is static + * during the netdev lifetime after it is registered. + */ +#define SET_NETDEV_DEVLINK_PORT(dev, port) \ +({ \ + WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \ + ((dev)->devlink_port = (port)); \ +}) + static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) @@ -2785,6 +2803,7 @@ enum netdev_cmd { NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, + NETDEV_PRE_UNINIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, diff --git a/net/core/dev.c b/net/core/dev.c index 2e4f1c97b59e..3bacee3bee78 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1621,10 +1621,10 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) - N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) - N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) - N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) - N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) + N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) + N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) + N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) + N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) @@ -10060,7 +10060,7 @@ int register_netdevice(struct net_device *dev) dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; write_unlock(&dev_base_lock); if (ret) - goto err_uninit; + goto err_uninit_notify; __netdev_update_features(dev); @@ -10107,6 +10107,8 @@ int register_netdevice(struct net_device *dev) out: return ret; +err_uninit_notify: + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10856,6 +10858,8 @@ void unregister_netdevice_many_notify(struct list_head *head, netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 3387dfbb80c5..6f06c05c7b1a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -71,6 +71,7 @@ struct devlink { refcount_t refcount; struct completion comp; struct rcu_head rcu; + struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; @@ -9615,6 +9616,9 @@ void devlink_set_features(struct devlink *devlink, u64 features) } EXPORT_SYMBOL_GPL(devlink_set_features); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr); + /** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace @@ -9645,10 +9649,13 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, &last_id, GFP_KERNEL); - if (ret < 0) { - kfree(devlink); - return NULL; - } + if (ret < 0) + goto err_xa_alloc; + + devlink->netdevice_nb.notifier_call = devlink_netdevice_event; + ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + if (ret) + goto err_register_netdevice_notifier; devlink->dev = dev; devlink->ops = ops; @@ -9675,6 +9682,12 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, init_completion(&devlink->comp); return devlink; + +err_register_netdevice_notifier: + xa_erase(&devlinks, devlink->index); +err_xa_alloc: + kfree(devlink); + return NULL; } EXPORT_SYMBOL_GPL(devlink_alloc_ns); @@ -9828,6 +9841,10 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); + + unregister_netdevice_notifier_net(devlink_net(devlink), + &devlink->netdevice_nb); + xa_erase(&devlinks, devlink->index); kfree(devlink); @@ -10121,6 +10138,56 @@ void devlink_port_type_clear(struct devlink_port *devlink_port) } EXPORT_SYMBOL_GPL(devlink_port_type_clear); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct devlink_port *devlink_port = netdev->devlink_port; + struct devlink *devlink; + + devlink = container_of(nb, struct devlink, netdevice_nb); + + if (!devlink_port || devlink_port->devlink != devlink) + return NOTIFY_OK; + + switch (event) { + case NETDEV_POST_INIT: + /* Set the type but not netdev pointer. It is going to be set + * later on by NETDEV_REGISTER event. Happens once during + * netdevice register + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, + NULL, true); + break; + case NETDEV_REGISTER: + /* Set the netdev on top of previously set type. Note this + * event happens also during net namespace change so here + * we take into account netdev pointer appearing in this + * namespace. + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, + netdev, true); + break; + case NETDEV_UNREGISTER: + /* Clear netdev pointer, but not the type. This event happens + * also during net namespace change so we need to clear + * pointer to netdev that is going to another net namespace. + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, + NULL, true); + break; + case NETDEV_PRE_UNINIT: + /* Clear the type and the netdev pointer. Happens one during + * netdevice unregister. + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, + NULL, true); + break; + } + + return NOTIFY_OK; +} + static int __devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour) { -- cgit v1.2.3 From c80965784dbf2fd624be654c1e73c24beada7441 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:05 +0100 Subject: net: devlink: remove netdev arg from devlink_port_type_eth_set() Since devlink_port_type_eth_set() should no longer be called by any driver with netdev pointer as it should rather use SET_NETDEV_DEVLINK_PORT, remove the netdev arg. Add a warn to type_clear() Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx4/main.c | 2 +- include/net/devlink.h | 3 +-- net/core/devlink.c | 23 ++++++++++++++--------- 3 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d3fc86cd3c1d..3ae246391549 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3043,7 +3043,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) */ if (!IS_ENABLED(CONFIG_MLX4_EN) && dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) - devlink_port_type_eth_set(&info->devlink_port, NULL); + devlink_port_type_eth_set(&info->devlink_port); else if (!IS_ENABLED(CONFIG_MLX4_INFINIBAND) && dev->caps.port_type[port] == MLX4_PORT_TYPE_IB) devlink_port_type_ib_set(&info->devlink_port, NULL); diff --git a/include/net/devlink.h b/include/net/devlink.h index 6c55aabaedf1..b1582b32183a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1582,8 +1582,7 @@ int devlink_port_register(struct devlink *devlink, unsigned int port_index); void devl_port_unregister(struct devlink_port *devlink_port); void devlink_port_unregister(struct devlink_port *devlink_port); -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev); +void devlink_port_type_eth_set(struct devlink_port *devlink_port); void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev); void devlink_port_type_clear(struct devlink_port *devlink_port); diff --git a/net/core/devlink.c b/net/core/devlink.c index 6f06c05c7b1a..70a374c828ae 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -10097,17 +10097,15 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port - * @netdev: related netdevice + * + * If driver is calling this, most likely it is doing something wrong. */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +void devlink_port_type_eth_set(struct devlink_port *devlink_port) { - if (!netdev) - dev_warn(devlink_port->devlink->dev, - "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", - devlink_port->index); - - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev, + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL, false); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -10130,9 +10128,16 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port + * + * If driver is calling this for clearing Ethernet type, most likely + * it is doing something wrong. */ void devlink_port_type_clear(struct devlink_port *devlink_port) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL, false); } -- cgit v1.2.3 From 31265c1e29eb28f17df50d04ee421b5b6369fefd Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:07 +0100 Subject: net: devlink: store copy netdevice ifindex and ifname to allow port_fill() without RTNL held To avoid a need to take RTNL mutex in port_fill() function, benefit from the introduce infrastructure that tracks netdevice notifier events. Store the ifindex and ifname upon register and change name events. Remove the rtnl_held bool propagated down to port_fill() function as it is no longer needed. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 2 ++ net/core/devlink.c | 68 ++++++++++++++++++++------------------------------- 2 files changed, 29 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index b1582b32183a..7befad57afd4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -129,6 +129,8 @@ struct devlink_port { union { struct { struct net_device *netdev; + int ifindex; + char ifname[IFNAMSIZ]; } type_eth; struct { struct ib_device *ibdev; diff --git a/net/core/devlink.c b/net/core/devlink.c index d948bb2fdd5f..38de3a1dff36 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1279,8 +1279,7 @@ out: static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, u32 seq, - int flags, struct netlink_ext_ack *extack, - bool rtnl_held) + int flags, struct netlink_ext_ack *extack) { struct devlink *devlink = devlink_port->devlink; void *hdr; @@ -1294,9 +1293,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; - /* Hold rtnl lock while accessing port's netdev attributes. */ - if (!rtnl_held) - rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -1305,13 +1301,11 @@ static int devlink_nl_port_fill(struct sk_buff *msg, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { - struct net_device *netdev = devlink_port->type_eth.netdev; - - if (netdev && + if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, - netdev->ifindex) || + devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, - netdev->name))) + devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { @@ -1323,8 +1317,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); - if (!rtnl_held) - rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -1339,15 +1331,13 @@ static int devlink_nl_port_fill(struct sk_buff *msg, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); - if (!rtnl_held) - rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } -static void __devlink_port_notify(struct devlink_port *devlink_port, - enum devlink_command cmd, bool rtnl_held) +static void devlink_port_notify(struct devlink_port *devlink_port, + enum devlink_command cmd) { struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; @@ -1362,8 +1352,7 @@ static void __devlink_port_notify(struct devlink_port *devlink_port, if (!msg) return; - err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL, - rtnl_held); + err = devlink_nl_port_fill(msg, devlink_port, cmd, 0, 0, 0, NULL); if (err) { nlmsg_free(msg); return; @@ -1373,12 +1362,6 @@ static void __devlink_port_notify(struct devlink_port *devlink_port, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } -static void devlink_port_notify(struct devlink_port *devlink_port, - enum devlink_command cmd) -{ - __devlink_port_notify(devlink_port, cmd, false); -} - static void devlink_rate_notify(struct devlink_rate *devlink_rate, enum devlink_command cmd) { @@ -1542,7 +1525,7 @@ static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0, - info->extack, false); + info->extack); if (err) { nlmsg_free(msg); return err; @@ -1572,8 +1555,7 @@ static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI, cb->extack, - false); + NLM_F_MULTI, cb->extack); if (err) { devl_unlock(devlink); devlink_put(devlink); @@ -1785,8 +1767,7 @@ static int devlink_port_new_notify(struct devlink *devlink, } err = devlink_nl_port_fill(msg, devlink_port, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0, NULL, - false); + info->snd_portid, info->snd_seq, 0, NULL); if (err) goto out; @@ -10062,7 +10043,7 @@ static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, - void *type_dev, bool rtnl_held) + void *type_dev) { struct net_device *netdev = type_dev; @@ -10081,6 +10062,13 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, switch (type) { case DEVLINK_PORT_TYPE_ETH: devlink_port->type_eth.netdev = netdev; + if (netdev) { + ASSERT_RTNL(); + devlink_port->type_eth.ifindex = netdev->ifindex; + BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != + sizeof(netdev->name)); + strcpy(devlink_port->type_eth.ifname, netdev->name); + } break; case DEVLINK_PORT_TYPE_IB: devlink_port->type_ib.ibdev = type_dev; @@ -10089,7 +10077,7 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, break; } spin_unlock_bh(&devlink_port->type_lock); - __devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW, rtnl_held); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } /** @@ -10104,8 +10092,7 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port) dev_warn(devlink_port->devlink->dev, "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL, - false); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -10118,8 +10105,7 @@ EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev) { - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev, - false); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); } EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); @@ -10137,8 +10123,7 @@ void devlink_port_type_clear(struct devlink_port *devlink_port) dev_warn(devlink_port->devlink->dev, "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", devlink_port->index); - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL, - false); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); @@ -10161,16 +10146,17 @@ static int devlink_netdevice_event(struct notifier_block *nb, * netdevice register */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, - NULL, true); + NULL); break; case NETDEV_REGISTER: + case NETDEV_CHANGENAME: /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this * namespace. */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, - netdev, true); + netdev); break; case NETDEV_UNREGISTER: /* Clear netdev pointer, but not the type. This event happens @@ -10178,14 +10164,14 @@ static int devlink_netdevice_event(struct notifier_block *nb, * pointer to netdev that is going to another net namespace. */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, - NULL, true); + NULL); break; case NETDEV_PRE_UNINIT: /* Clear the type and the netdev pointer. Happens one during * netdevice unregister. */ __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, - NULL, true); + NULL); break; } -- cgit v1.2.3 From 77df1db80da384c565106321f5934967690da7dd Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:10 +0100 Subject: net: remove unused ndo_get_devlink_port Remove ndo_get_devlink_port which is no longer used alongside with the implementations in drivers. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 -------- drivers/net/ethernet/fungible/funeth/funeth_main.c | 8 -------- drivers/net/ethernet/intel/ice/ice_main.c | 15 --------------- drivers/net/ethernet/intel/ice/ice_repr.c | 9 --------- drivers/net/ethernet/marvell/prestera/prestera_devlink.c | 7 ------- drivers/net/ethernet/marvell/prestera/prestera_devlink.h | 2 -- drivers/net/ethernet/marvell/prestera/prestera_main.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c | 10 ---------- drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h | 1 - drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 10 ---------- drivers/net/ethernet/mellanox/mlxsw/minimal.c | 11 ----------- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 11 ----------- drivers/net/ethernet/mscc/ocelot_net.c | 10 ---------- drivers/net/ethernet/netronome/nfp/nfp_app.h | 2 -- drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 11 ----------- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 -- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 1 - drivers/net/ethernet/ti/am65-cpsw-nuss.c | 8 -------- drivers/net/netdevsim/netdev.c | 9 --------- include/linux/netdevice.h | 5 ----- net/dsa/slave.c | 8 -------- 22 files changed, 150 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9604294b67aa..03272aa48511 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -13073,13 +13073,6 @@ int bnxt_get_port_parent_id(struct net_device *dev, return 0; } -static struct devlink_port *bnxt_get_devlink_port(struct net_device *dev) -{ - struct bnxt *bp = netdev_priv(dev); - - return &bp->dl_port; -} - static const struct net_device_ops bnxt_netdev_ops = { .ndo_open = bnxt_open, .ndo_start_xmit = bnxt_start_xmit, @@ -13111,7 +13104,6 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_xdp_xmit = bnxt_xdp_xmit, .ndo_bridge_getlink = bnxt_bridge_getlink, .ndo_bridge_setlink = bnxt_bridge_setlink, - .ndo_get_devlink_port = bnxt_get_devlink_port, }; static void bnxt_remove_one(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c index 208dc89f4972..b4cce30e526a 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_main.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c @@ -1178,13 +1178,6 @@ static int fun_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static struct devlink_port *fun_get_devlink_port(struct net_device *netdev) -{ - struct funeth_priv *fp = netdev_priv(netdev); - - return &fp->dl_port; -} - static int fun_init_vports(struct fun_ethdev *ed, unsigned int n) { if (ed->num_vports) @@ -1350,7 +1343,6 @@ static const struct net_device_ops fun_netdev_ops = { .ndo_set_vf_vlan = fun_set_vf_vlan, .ndo_set_vf_rate = fun_set_vf_rate, .ndo_get_vf_config = fun_get_vf_config, - .ndo_get_devlink_port = fun_get_devlink_port, }; #define GSO_ENCAP_FLAGS (NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | \ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 74d25fda11bd..a9fc89aebebe 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -298,20 +298,6 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) return status; } -/** - * ice_get_devlink_port - Get devlink port from netdev - * @netdev: the netdevice structure - */ -static struct devlink_port *ice_get_devlink_port(struct net_device *netdev) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - - if (!ice_is_switchdev_running(pf)) - return NULL; - - return &pf->devlink_port; -} - /** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI @@ -9107,5 +9093,4 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_bpf = ice_xdp, .ndo_xdp_xmit = ice_xdp_xmit, .ndo_xsk_wakeup = ice_xsk_wakeup, - .ndo_get_devlink_port = ice_get_devlink_port, }; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index 663a7a0e1814..0483eb14c288 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -134,14 +134,6 @@ static int ice_repr_stop(struct net_device *netdev) return 0; } -static struct devlink_port * -ice_repr_get_devlink_port(struct net_device *netdev) -{ - struct ice_repr *repr = ice_netdev_to_repr(netdev); - - return &repr->vf->devlink_port; -} - /** * ice_repr_sp_stats64 - get slow path stats for port representor * @dev: network interface device structure @@ -250,7 +242,6 @@ static const struct net_device_ops ice_repr_netdev_ops = { .ndo_open = ice_repr_open, .ndo_stop = ice_repr_stop, .ndo_start_xmit = ice_eswitch_port_start_xmit, - .ndo_get_devlink_port = ice_repr_get_devlink_port, .ndo_setup_tc = ice_repr_setup_tc, .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, .ndo_get_offload_stats = ice_repr_ndo_get_offload_stats, diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 637b8fee65e7..84ad05c9f12d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -445,13 +445,6 @@ void prestera_devlink_port_unregister(struct prestera_port *port) devlink_port_unregister(&port->dl_port); } -struct devlink_port *prestera_devlink_get_port(struct net_device *dev) -{ - struct prestera_port *port = netdev_priv(dev); - - return &port->dl_port; -} - int prestera_devlink_traps_register(struct prestera_switch *sw) { const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h index 04e8556f748a..bf84ad6fd87e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h @@ -15,8 +15,6 @@ void prestera_devlink_unregister(struct prestera_switch *sw); int prestera_devlink_port_register(struct prestera_port *port); void prestera_devlink_port_unregister(struct prestera_port *port); -struct devlink_port *prestera_devlink_get_port(struct net_device *dev); - void prestera_devlink_trap_report(struct prestera_port *port, struct sk_buff *skb, u8 cpu_code); int prestera_devlink_traps_register(struct prestera_switch *sw); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index a76bf3606aa6..edbdda8f958d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -569,7 +569,6 @@ static const struct net_device_ops prestera_netdev_ops = { .ndo_change_mtu = prestera_port_change_mtu, .ndo_get_stats64 = prestera_port_get_stats64, .ndo_set_mac_address = prestera_port_set_mac_address, - .ndo_get_devlink_port = prestera_devlink_get_port, }; int prestera_port_autoneg_set(struct prestera_port *port, u64 link_modes) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index ce0e56f856d6..83adaabf59f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -62,13 +62,3 @@ void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) devl_unlock(devlink); } - -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - - if (!netif_device_present(dev)) - return NULL; - - return mlx5e_devlink_get_dl_port(priv); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h index 1c203257ac30..4f238d4fff55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h @@ -9,7 +9,6 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv); void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv); -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev); static inline struct devlink_port * mlx5e_devlink_get_dl_port(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 97e876472a06..78d34c039fa7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4897,7 +4897,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, #endif - .ndo_get_devlink_port = mlx5e_get_devlink_port, }; static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 5412633b9c8c..1b53e8852c86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -607,15 +607,6 @@ static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) return mlx5e_change_mtu(netdev, new_mtu, NULL); } -static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *netdev) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_core_dev *dev = priv->mdev; - - return mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); -} - static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -644,7 +635,6 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_setup_tc = mlx5e_rep_setup_tc, - .ndo_get_devlink_port = mlx5e_rep_get_devlink_port, .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 177cf7e4db34..6b56eadd736e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -81,20 +81,9 @@ static int mlxsw_m_port_stop(struct net_device *dev) return 0; } -static struct devlink_port * -mlxsw_m_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); - struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; - - return mlxsw_core_port_devlink_port_get(mlxsw_m->core, - mlxsw_m_port->local_port); -} - static const struct net_device_ops mlxsw_m_port_netdev_ops = { .ndo_open = mlxsw_m_port_open, .ndo_stop = mlxsw_m_port_stop, - .ndo_get_devlink_port = mlxsw_m_port_get_devlink_port, }; static void mlxsw_m_module_get_drvinfo(struct net_device *dev, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b13739e1f8f3..04dc79da6024 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1259,16 +1259,6 @@ static int mlxsw_sp_set_features(struct net_device *dev, return 0; } -static struct devlink_port * -mlxsw_sp_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - - return mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - mlxsw_sp_port->local_port); -} - static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, struct ifreq *ifr) { @@ -1342,7 +1332,6 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid, .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_set_features = mlxsw_sp_set_features, - .ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port, .ndo_eth_ioctl = mlxsw_sp_port_ioctl, }; diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 5efc07751c8d..f50dada2bb8e 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -194,15 +194,6 @@ void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port) devlink_port_unregister(dlp); } -static struct devlink_port *ocelot_get_devlink_port(struct net_device *dev) -{ - struct ocelot_port_private *priv = netdev_priv(dev); - struct ocelot *ocelot = priv->port.ocelot; - int port = priv->port.index; - - return &ocelot->devlink_ports[port]; -} - int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv, struct flow_cls_offload *f, bool ingress) @@ -925,7 +916,6 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_set_features = ocelot_set_features, .ndo_setup_tc = ocelot_setup_tc, .ndo_eth_ioctl = ocelot_ioctl, - .ndo_get_devlink_port = ocelot_get_devlink_port, }; struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index dd56207df246..90707346a4ef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -445,6 +445,4 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, struct nfp_net *nn, unsigned int id); -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev); - #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index f3f0f11d8b52..8bfd48d50ef0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -362,14 +362,3 @@ void nfp_devlink_port_unregister(struct nfp_port *port) { devl_port_unregister(&port->dl_port); } - -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev) -{ - struct nfp_port *port; - - port = nfp_port_from_netdev(netdev); - if (!port) - return NULL; - - return &port->dl_port; -} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a5ca5c4a7896..8c1a870bc0e5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2013,7 +2013,6 @@ const struct net_device_ops nfp_nfd3_netdev_ops = { .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, .ndo_xsk_wakeup = nfp_net_xsk_wakeup, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; @@ -2044,7 +2043,6 @@ const struct net_device_ops nfp_nfdk_netdev_ops = { .ndo_features_check = nfp_net_features_check, .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index a6b6ca1fd55e..3af1229a3f08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -275,7 +275,6 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_set_features = nfp_port_set_features, .ndo_set_mac_address = eth_mac_addr, .ndo_get_port_parent_id = nfp_port_get_port_parent_id, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, }; void diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index b2a08f3f0e93..0dbdce4dc077 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1380,13 +1380,6 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } -static struct devlink_port *am65_cpsw_ndo_get_devlink_port(struct net_device *ndev) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - - return &port->devlink_port; -} - static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, @@ -1400,7 +1393,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, .ndo_eth_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, - .ndo_get_devlink_port = am65_cpsw_ndo_get_devlink_port, }; static void am65_cpsw_nuss_mac_config(struct phylink_config *config, unsigned int mode, diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index e7cbae743e86..6db6a75ff9b9 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -238,13 +238,6 @@ nsim_set_features(struct net_device *dev, netdev_features_t features) return 0; } -static struct devlink_port *nsim_get_devlink_port(struct net_device *dev) -{ - struct netdevsim *ns = netdev_priv(dev); - - return &ns->nsim_dev_port->devlink_port; -} - static const struct net_device_ops nsim_netdev_ops = { .ndo_start_xmit = nsim_start_xmit, .ndo_set_rx_mode = nsim_set_rx_mode, @@ -263,7 +256,6 @@ static const struct net_device_ops nsim_netdev_ops = { .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, .ndo_bpf = nsim_bpf, - .ndo_get_devlink_port = nsim_get_devlink_port, }; static const struct net_device_ops nsim_vf_netdev_ops = { @@ -275,7 +267,6 @@ static const struct net_device_ops nsim_vf_netdev_ops = { .ndo_get_stats64 = nsim_get_stats64, .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, - .ndo_get_devlink_port = nsim_get_devlink_port, }; static void nsim_setup(struct net_device *dev) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f048a30ea10b..d45713a06568 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1366,10 +1366,6 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); - * Get devlink port instance associated with a given netdev. - * Called with a reference on the netdevice and devlink locks only, - * rtnl_lock is not held. * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. @@ -1600,7 +1596,6 @@ struct net_device_ops { struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); - struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 158bb3f1aa0b..4176482cd03f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2165,13 +2165,6 @@ static const struct dcbnl_rtnl_ops __maybe_unused dsa_slave_dcbnl_ops = { .ieee_delapp = dsa_slave_dcbnl_ieee_delapp, }; -static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return &dp->devlink_port; -} - static void dsa_slave_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { @@ -2219,7 +2212,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_stats64 = dsa_slave_get_stats64, .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_get_devlink_port = dsa_slave_get_devlink_port, .ndo_change_mtu = dsa_slave_change_mtu, .ndo_fill_forward_path = dsa_slave_fill_forward_path, }; -- cgit v1.2.3 From dca56c3038c34a3e5acfe0aadb1f2bc9d724ae79 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:11 +0100 Subject: net: expose devlink port over rtnetlink Expose devlink port handle related to netdev over rtnetlink. Introduce a new nested IFLA attribute to carry the info. Call into devlink code to fill-up the nest with existing devlink attributes that are used over devlink netlink. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 14 ++++++++++++++ include/uapi/linux/if_link.h | 2 ++ net/core/devlink.c | 18 ++++++++++++++++++ net/core/rtnetlink.c | 39 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 73 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7befad57afd4..fa6e936af1a5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1873,6 +1873,9 @@ int devlink_compat_phys_port_name_get(struct net_device *dev, int devlink_compat_switch_id_get(struct net_device *dev, struct netdev_phys_item_id *ppid); +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port); +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port); + #else static inline struct devlink *devlink_try_get(struct devlink *devlink) @@ -1909,6 +1912,17 @@ devlink_compat_switch_id_get(struct net_device *dev, return -EOPNOTSUPP; } +static inline int +devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + return 0; +} + +static inline size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + return 0; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d92b3f79eba3..1021a7e47a86 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -372,6 +372,8 @@ enum { IFLA_TSO_MAX_SEGS, IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */ + IFLA_DEVLINK_PORT, + __IFLA_MAX }; diff --git a/net/core/devlink.c b/net/core/devlink.c index 3a454d0045e5..2dcf2bcc3527 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -880,6 +880,24 @@ nla_put_failure: return -EMSGSIZE; } +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + if (devlink_nl_put_handle(msg, devlink_port->devlink)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + return -EMSGSIZE; + return 0; +} + +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + struct devlink *devlink = devlink_port->devlink; + + return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ +} + struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b64fffeb3844..64289bc98887 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -53,6 +53,7 @@ #include #include #include +#include #include "dev.h" @@ -1038,6 +1039,16 @@ static size_t rtnl_proto_down_size(const struct net_device *dev) return size; } +static size_t rtnl_devlink_port_size(const struct net_device *dev) +{ + size_t size = nla_total_size(0); /* nest IFLA_DEVLINK_PORT */ + + if (dev->devlink_port) + size += devlink_nl_port_handle_size(dev->devlink_port); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1091,6 +1102,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + + rtnl_devlink_port_size(dev) + 0; } @@ -1728,6 +1740,30 @@ nla_put_failure: return -EMSGSIZE; } +static int rtnl_fill_devlink_port(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *devlink_port_nest; + int ret; + + devlink_port_nest = nla_nest_start(skb, IFLA_DEVLINK_PORT); + if (!devlink_port_nest) + return -EMSGSIZE; + + if (dev->devlink_port) { + ret = devlink_nl_port_handle_fill(skb, dev->devlink_port); + if (ret < 0) + goto nest_cancel; + } + + nla_nest_end(skb, devlink_port_nest); + return 0; + +nest_cancel: + nla_nest_cancel(skb, devlink_port_nest); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1865,6 +1901,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, dev->dev.parent->bus->name)) goto nla_put_failure; + if (rtnl_fill_devlink_port(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; -- cgit v1.2.3 From aa3496accc412b3d975e4ee5d06076d73394d8b5 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:55 +0530 Subject: bpf: Refactor kptr_off_tab into btf_record To prepare the BPF verifier to handle special fields in both map values and program allocated types coming from program BTF, we need to refactor the kptr_off_tab handling code into something more generic and reusable across both cases to avoid code duplication. Later patches also require passing this data to helpers at runtime, so that they can work on user defined types, initialize them, destruct them, etc. The main observation is that both map values and such allocated types point to a type in program BTF, hence they can be handled similarly. We can prepare a field metadata table for both cases and store them in struct bpf_map or struct btf depending on the use case. Hence, refactor the code into generic btf_record and btf_field member structs. The btf_record represents the fields of a specific btf_type in user BTF. The cnt indicates the number of special fields we successfully recognized, and field_mask is a bitmask of fields that were found, to enable quick determination of availability of a certain field. Subsequently, refactor the rest of the code to work with these generic types, remove assumptions about kptr and kptr_off_tab, rename variables to more meaningful names, etc. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 125 +++++++++++++++-------- include/linux/btf.h | 3 +- kernel/bpf/arraymap.c | 13 ++- kernel/bpf/btf.c | 67 ++++++------ kernel/bpf/hashtab.c | 14 ++- kernel/bpf/map_in_map.c | 14 ++- kernel/bpf/syscall.c | 263 +++++++++++++++++++++++++++--------------------- kernel/bpf/verifier.c | 96 +++++++++--------- 8 files changed, 332 insertions(+), 263 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8d948bfcb984..5f2a42033a37 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -165,35 +165,41 @@ struct bpf_map_ops { }; enum { - /* Support at most 8 pointers in a BPF map value */ - BPF_MAP_VALUE_OFF_MAX = 8, - BPF_MAP_OFF_ARR_MAX = BPF_MAP_VALUE_OFF_MAX + + /* Support at most 8 pointers in a BTF type */ + BTF_FIELDS_MAX = 8, + BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX + 1 + /* for bpf_spin_lock */ 1, /* for bpf_timer */ }; -enum bpf_kptr_type { - BPF_KPTR_UNREF, - BPF_KPTR_REF, +enum btf_field_type { + BPF_KPTR_UNREF = (1 << 2), + BPF_KPTR_REF = (1 << 3), + BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, }; -struct bpf_map_value_off_desc { +struct btf_field_kptr { + struct btf *btf; + struct module *module; + btf_dtor_kfunc_t dtor; + u32 btf_id; +}; + +struct btf_field { u32 offset; - enum bpf_kptr_type type; - struct { - struct btf *btf; - struct module *module; - btf_dtor_kfunc_t dtor; - u32 btf_id; - } kptr; + enum btf_field_type type; + union { + struct btf_field_kptr kptr; + }; }; -struct bpf_map_value_off { - u32 nr_off; - struct bpf_map_value_off_desc off[]; +struct btf_record { + u32 cnt; + u32 field_mask; + struct btf_field fields[]; }; -struct bpf_map_off_arr { +struct btf_field_offs { u32 cnt; u32 field_off[BPF_MAP_OFF_ARR_MAX]; u8 field_sz[BPF_MAP_OFF_ARR_MAX]; @@ -215,7 +221,7 @@ struct bpf_map { u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ - struct bpf_map_value_off *kptr_off_tab; + struct btf_record *record; int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; @@ -227,7 +233,7 @@ struct bpf_map { struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; - struct bpf_map_off_arr *off_arr; + struct btf_field_offs *field_offs; /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ @@ -251,6 +257,37 @@ struct bpf_map { bool frozen; /* write-once; write-protected by freeze_mutex */ }; +static inline u32 btf_field_type_size(enum btf_field_type type) +{ + switch (type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return sizeof(u64); + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static inline u32 btf_field_type_align(enum btf_field_type type) +{ + switch (type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return __alignof__(u64); + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) +{ + if (IS_ERR_OR_NULL(rec)) + return false; + return rec->field_mask & type; +} + static inline bool map_value_has_spin_lock(const struct bpf_map *map) { return map->spin_lock_off >= 0; @@ -261,23 +298,19 @@ static inline bool map_value_has_timer(const struct bpf_map *map) return map->timer_off >= 0; } -static inline bool map_value_has_kptrs(const struct bpf_map *map) -{ - return !IS_ERR_OR_NULL(map->kptr_off_tab); -} - static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); - if (unlikely(map_value_has_kptrs(map))) { - struct bpf_map_value_off *tab = map->kptr_off_tab; + if (!IS_ERR_OR_NULL(map->record)) { + struct btf_field *fields = map->record->fields; + u32 cnt = map->record->cnt; int i; - for (i = 0; i < tab->nr_off; i++) - *(u64 *)(dst + tab->off[i].offset) = 0; + for (i = 0; i < cnt; i++) + memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type)); } } @@ -303,7 +336,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b u32 curr_off = 0; int i; - if (likely(!map->off_arr)) { + if (likely(!map->field_offs)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); else @@ -311,11 +344,12 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b return; } - for (i = 0; i < map->off_arr->cnt; i++) { - u32 next_off = map->off_arr->field_off[i]; + for (i = 0; i < map->field_offs->cnt; i++) { + u32 next_off = map->field_offs->field_off[i]; + u32 sz = next_off - curr_off; - memcpy(dst + curr_off, src + curr_off, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + memcpy(dst + curr_off, src + curr_off, sz); + curr_off += map->field_offs->field_sz[i]; } memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); } @@ -335,16 +369,17 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) u32 curr_off = 0; int i; - if (likely(!map->off_arr)) { + if (likely(!map->field_offs)) { memset(dst, 0, map->value_size); return; } - for (i = 0; i < map->off_arr->cnt; i++) { - u32 next_off = map->off_arr->field_off[i]; + for (i = 0; i < map->field_offs->cnt; i++) { + u32 next_off = map->field_offs->field_off[i]; + u32 sz = next_off - curr_off; - memset(dst + curr_off, 0, next_off - curr_off); - curr_off += map->off_arr->field_sz[i]; + memset(dst + curr_off, 0, sz); + curr_off += map->field_offs->field_sz[i]; } memset(dst + curr_off, 0, map->value_size - curr_off); } @@ -1699,11 +1734,13 @@ void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); -struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset); -void bpf_map_free_kptr_off_tab(struct bpf_map *map); -struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map); -bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b); -void bpf_map_free_kptrs(struct bpf_map *map, void *map_value); +struct btf_field *btf_record_find(const struct btf_record *rec, + u32 offset, enum btf_field_type type); +void btf_record_free(struct btf_record *rec); +void bpf_map_free_record(struct bpf_map *map); +struct btf_record *btf_record_dup(const struct btf_record *rec); +bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); +void bpf_obj_free_fields(const struct btf_record *rec, void *obj); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index 86aad9b2ce02..9e62717cdc7a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -163,8 +163,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); -struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, - const struct btf_type *t); +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 832b2659e96e..417f84342e98 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -310,8 +310,7 @@ static void check_and_free_fields(struct bpf_array *arr, void *val) { if (map_value_has_timer(&arr->map)) bpf_timer_cancel_and_free(val + arr->map.timer_off); - if (map_value_has_kptrs(&arr->map)) - bpf_map_free_kptrs(&arr->map, val); + bpf_obj_free_fields(arr->map.record, val); } /* Called from syscall or from eBPF program */ @@ -409,7 +408,7 @@ static void array_map_free_timers(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - /* We don't reset or free kptr on uref dropping to zero. */ + /* We don't reset or free fields other than timer on uref dropping to zero. */ if (!map_value_has_timer(map)) return; @@ -423,22 +422,22 @@ static void array_map_free(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - if (map_value_has_kptrs(map)) { + if (!IS_ERR_OR_NULL(map->record)) { if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { for (i = 0; i < array->map.max_entries; i++) { void __percpu *pptr = array->pptrs[i & array->index_mask]; int cpu; for_each_possible_cpu(cpu) { - bpf_map_free_kptrs(map, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(map->record, per_cpu_ptr(pptr, cpu)); cond_resched(); } } } else { for (i = 0; i < array->map.max_entries; i++) - bpf_map_free_kptrs(map, array_map_elem_ptr(array, i)); + bpf_obj_free_fields(map->record, array_map_elem_ptr(array, i)); } - bpf_map_free_kptr_off_tab(map); + bpf_map_free_record(map); } if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f4d21eef6ebd..8391a77138ee 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3191,7 +3191,7 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } -enum btf_field_type { +enum btf_field_info_type { BTF_FIELD_SPIN_LOCK, BTF_FIELD_TIMER, BTF_FIELD_KPTR, @@ -3203,9 +3203,9 @@ enum { }; struct btf_field_info { - u32 type_id; + enum btf_field_type type; u32 off; - enum bpf_kptr_type type; + u32 type_id; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, @@ -3222,7 +3222,7 @@ static int btf_find_struct(const struct btf *btf, const struct btf_type *t, static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, u32 off, int sz, struct btf_field_info *info) { - enum bpf_kptr_type type; + enum btf_field_type type; u32 res_id; /* Permit modifiers on the pointer itself */ @@ -3259,7 +3259,7 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_member *member; @@ -3311,7 +3311,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, const char *name, int sz, int align, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const struct btf_var_secinfo *vsi; @@ -3360,7 +3360,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, } static int btf_find_field(const struct btf *btf, const struct btf_type *t, - enum btf_field_type field_type, + enum btf_field_info_type field_type, struct btf_field_info *info, int info_cnt) { const char *name; @@ -3423,14 +3423,13 @@ int btf_find_timer(const struct btf *btf, const struct btf_type *t) return info.off; } -struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, - const struct btf_type *t) +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t) { - struct btf_field_info info_arr[BPF_MAP_VALUE_OFF_MAX]; - struct bpf_map_value_off *tab; + struct btf_field_info info_arr[BTF_FIELDS_MAX]; struct btf *kernel_btf = NULL; struct module *mod = NULL; - int ret, i, nr_off; + struct btf_record *rec; + int ret, i, cnt; ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) @@ -3438,12 +3437,12 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, if (!ret) return NULL; - nr_off = ret; - tab = kzalloc(offsetof(struct bpf_map_value_off, off[nr_off]), GFP_KERNEL | __GFP_NOWARN); - if (!tab) + cnt = ret; + rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); + if (!rec) return ERR_PTR(-ENOMEM); - - for (i = 0; i < nr_off; i++) { + rec->cnt = 0; + for (i = 0; i < cnt; i++) { const struct btf_type *t; s32 id; @@ -3500,28 +3499,24 @@ struct bpf_map_value_off *btf_parse_kptrs(const struct btf *btf, ret = -EINVAL; goto end_mod; } - tab->off[i].kptr.dtor = (void *)addr; + rec->fields[i].kptr.dtor = (void *)addr; } - tab->off[i].offset = info_arr[i].off; - tab->off[i].type = info_arr[i].type; - tab->off[i].kptr.btf_id = id; - tab->off[i].kptr.btf = kernel_btf; - tab->off[i].kptr.module = mod; + rec->field_mask |= info_arr[i].type; + rec->fields[i].offset = info_arr[i].off; + rec->fields[i].type = info_arr[i].type; + rec->fields[i].kptr.btf_id = id; + rec->fields[i].kptr.btf = kernel_btf; + rec->fields[i].kptr.module = mod; + rec->cnt++; } - tab->nr_off = nr_off; - return tab; + return rec; end_mod: module_put(mod); end_btf: btf_put(kernel_btf); end: - while (i--) { - btf_put(tab->off[i].kptr.btf); - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - } - kfree(tab); + btf_record_free(rec); return ERR_PTR(ret); } @@ -6370,7 +6365,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, /* kptr_get is only true for kfunc */ if (i == 0 && kptr_get) { - struct bpf_map_value_off_desc *off_desc; + struct btf_field *kptr_field; if (reg->type != PTR_TO_MAP_VALUE) { bpf_log(log, "arg#0 expected pointer to map value\n"); @@ -6386,8 +6381,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - off_desc = bpf_map_kptr_off_contains(reg->map_ptr, reg->off + reg->var_off.value); - if (!off_desc || off_desc->type != BPF_KPTR_REF) { + kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); + if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", reg->off + reg->var_off.value); return -EINVAL; @@ -6406,8 +6401,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; } - if (!btf_struct_ids_match(log, btf, ref_id, 0, off_desc->kptr.btf, - off_desc->kptr.btf_id, true)) { + if (!btf_struct_ids_match(log, btf, ref_id, 0, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, true)) { bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", func_name, i, btf_type_str(ref_t), ref_tname); return -EINVAL; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index f39ee3e05589..c5ea8f9bb7a9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -238,21 +238,20 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) } } -static void htab_free_prealloced_kptrs(struct bpf_htab *htab) +static void htab_free_prealloced_fields(struct bpf_htab *htab) { u32 num_entries = htab->map.max_entries; int i; - if (!map_value_has_kptrs(&htab->map)) + if (IS_ERR_OR_NULL(htab->map.record)) return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); - for (i = 0; i < num_entries; i++) { struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_map_free_kptrs(&htab->map, elem->key + round_up(htab->map.key_size, 8)); + bpf_obj_free_fields(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -766,8 +765,7 @@ static void check_and_free_fields(struct bpf_htab *htab, if (map_value_has_timer(&htab->map)) bpf_timer_cancel_and_free(map_value + htab->map.timer_off); - if (map_value_has_kptrs(&htab->map)) - bpf_map_free_kptrs(&htab->map, map_value); + bpf_obj_free_fields(htab->map.record, map_value); } /* It is called from the bpf_lru_list when the LRU needs to delete @@ -1517,11 +1515,11 @@ static void htab_map_free(struct bpf_map *map) if (!htab_is_prealloc(htab)) { delete_all_elements(htab); } else { - htab_free_prealloced_kptrs(htab); + htab_free_prealloced_fields(htab); prealloc_destroy(htab); } - bpf_map_free_kptr_off_tab(map); + bpf_map_free_record(map); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); bpf_mem_alloc_destroy(&htab->pcpu_ma); diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 135205d0d560..d6c662183f88 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -52,7 +52,15 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->max_entries = inner_map->max_entries; inner_map_meta->spin_lock_off = inner_map->spin_lock_off; inner_map_meta->timer_off = inner_map->timer_off; - inner_map_meta->kptr_off_tab = bpf_map_copy_kptr_off_tab(inner_map); + inner_map_meta->record = btf_record_dup(inner_map->record); + if (IS_ERR(inner_map_meta->record)) { + /* btf_record_dup returns NULL or valid pointer in case of + * invalid/empty/valid, but ERR_PTR in case of errors. During + * equality NULL or IS_ERR is equivalent. + */ + fdput(f); + return ERR_CAST(inner_map_meta->record); + } if (inner_map->btf) { btf_get(inner_map->btf); inner_map_meta->btf = inner_map->btf; @@ -72,7 +80,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) void bpf_map_meta_free(struct bpf_map *map_meta) { - bpf_map_free_kptr_off_tab(map_meta); + bpf_map_free_record(map_meta); btf_put(map_meta->btf); kfree(map_meta); } @@ -86,7 +94,7 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, meta0->value_size == meta1->value_size && meta0->timer_off == meta1->timer_off && meta0->map_flags == meta1->map_flags && - bpf_map_equal_kptr_off_tab(meta0, meta1); + btf_record_equal(meta0->record, meta1->record); } void *bpf_map_fd_get_ptr(struct bpf_map *map, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5887592eeb93..b80c0e2eb73f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -495,114 +495,134 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif -static int bpf_map_kptr_off_cmp(const void *a, const void *b) +static int btf_field_cmp(const void *a, const void *b) { - const struct bpf_map_value_off_desc *off_desc1 = a, *off_desc2 = b; + const struct btf_field *f1 = a, *f2 = b; - if (off_desc1->offset < off_desc2->offset) + if (f1->offset < f2->offset) return -1; - else if (off_desc1->offset > off_desc2->offset) + else if (f1->offset > f2->offset) return 1; return 0; } -struct bpf_map_value_off_desc *bpf_map_kptr_off_contains(struct bpf_map *map, u32 offset) +struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, + enum btf_field_type type) { - /* Since members are iterated in btf_find_field in increasing order, - * offsets appended to kptr_off_tab are in increasing order, so we can - * do bsearch to find exact match. - */ - struct bpf_map_value_off *tab; + struct btf_field *field; - if (!map_value_has_kptrs(map)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & type)) + return NULL; + field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); + if (!field || !(field->type & type)) return NULL; - tab = map->kptr_off_tab; - return bsearch(&offset, tab->off, tab->nr_off, sizeof(tab->off[0]), bpf_map_kptr_off_cmp); + return field; } -void bpf_map_free_kptr_off_tab(struct bpf_map *map) +void btf_record_free(struct btf_record *rec) { - struct bpf_map_value_off *tab = map->kptr_off_tab; int i; - if (!map_value_has_kptrs(map)) + if (IS_ERR_OR_NULL(rec)) return; - for (i = 0; i < tab->nr_off; i++) { - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - btf_put(tab->off[i].kptr.btf); + for (i = 0; i < rec->cnt; i++) { + switch (rec->fields[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + if (rec->fields[i].kptr.module) + module_put(rec->fields[i].kptr.module); + btf_put(rec->fields[i].kptr.btf); + break; + default: + WARN_ON_ONCE(1); + continue; + } } - kfree(tab); - map->kptr_off_tab = NULL; + kfree(rec); +} + +void bpf_map_free_record(struct bpf_map *map) +{ + btf_record_free(map->record); + map->record = NULL; } -struct bpf_map_value_off *bpf_map_copy_kptr_off_tab(const struct bpf_map *map) +struct btf_record *btf_record_dup(const struct btf_record *rec) { - struct bpf_map_value_off *tab = map->kptr_off_tab, *new_tab; - int size, i; + const struct btf_field *fields; + struct btf_record *new_rec; + int ret, size, i; - if (!map_value_has_kptrs(map)) - return ERR_PTR(-ENOENT); - size = offsetof(struct bpf_map_value_off, off[tab->nr_off]); - new_tab = kmemdup(tab, size, GFP_KERNEL | __GFP_NOWARN); - if (!new_tab) + if (IS_ERR_OR_NULL(rec)) + return NULL; + size = offsetof(struct btf_record, fields[rec->cnt]); + new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); + if (!new_rec) return ERR_PTR(-ENOMEM); - /* Do a deep copy of the kptr_off_tab */ - for (i = 0; i < tab->nr_off; i++) { - btf_get(tab->off[i].kptr.btf); - if (tab->off[i].kptr.module && !try_module_get(tab->off[i].kptr.module)) { - while (i--) { - if (tab->off[i].kptr.module) - module_put(tab->off[i].kptr.module); - btf_put(tab->off[i].kptr.btf); + /* Do a deep copy of the btf_record */ + fields = rec->fields; + new_rec->cnt = 0; + for (i = 0; i < rec->cnt; i++) { + switch (fields[i].type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + btf_get(fields[i].kptr.btf); + if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { + ret = -ENXIO; + goto free; } - kfree(new_tab); - return ERR_PTR(-ENXIO); + break; + default: + ret = -EFAULT; + WARN_ON_ONCE(1); + goto free; } + new_rec->cnt++; } - return new_tab; + return new_rec; +free: + btf_record_free(new_rec); + return ERR_PTR(ret); } -bool bpf_map_equal_kptr_off_tab(const struct bpf_map *map_a, const struct bpf_map *map_b) +bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { - struct bpf_map_value_off *tab_a = map_a->kptr_off_tab, *tab_b = map_b->kptr_off_tab; - bool a_has_kptr = map_value_has_kptrs(map_a), b_has_kptr = map_value_has_kptrs(map_b); + bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; - if (!a_has_kptr && !b_has_kptr) + if (!a_has_fields && !b_has_fields) return true; - if (a_has_kptr != b_has_kptr) + if (a_has_fields != b_has_fields) return false; - if (tab_a->nr_off != tab_b->nr_off) + if (rec_a->cnt != rec_b->cnt) return false; - size = offsetof(struct bpf_map_value_off, off[tab_a->nr_off]); - return !memcmp(tab_a, tab_b, size); + size = offsetof(struct btf_record, fields[rec_a->cnt]); + return !memcmp(rec_a, rec_b, size); } -/* Caller must ensure map_value_has_kptrs is true. Note that this function can - * be called on a map value while the map_value is visible to BPF programs, as - * it ensures the correct synchronization, and we already enforce the same using - * the bpf_kptr_xchg helper on the BPF program side for referenced kptrs. - */ -void bpf_map_free_kptrs(struct bpf_map *map, void *map_value) +void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - unsigned long *btf_id_ptr; + const struct btf_field *fields; int i; - for (i = 0; i < tab->nr_off; i++) { - struct bpf_map_value_off_desc *off_desc = &tab->off[i]; - unsigned long old_ptr; - - btf_id_ptr = map_value + off_desc->offset; - if (off_desc->type == BPF_KPTR_UNREF) { - u64 *p = (u64 *)btf_id_ptr; - - WRITE_ONCE(*p, 0); + if (IS_ERR_OR_NULL(rec)) + return; + fields = rec->fields; + for (i = 0; i < rec->cnt; i++) { + const struct btf_field *field = &fields[i]; + void *field_ptr = obj + field->offset; + + switch (fields[i].type) { + case BPF_KPTR_UNREF: + WRITE_ONCE(*(u64 *)field_ptr, 0); + break; + case BPF_KPTR_REF: + field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); + break; + default: + WARN_ON_ONCE(1); continue; } - old_ptr = xchg(btf_id_ptr, 0); - off_desc->kptr.dtor((void *)old_ptr); } } @@ -612,10 +632,10 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); - kfree(map->off_arr); + kfree(map->field_offs); bpf_map_release_memcg(map); /* implementation dependent freeing, map_free callback also does - * bpf_map_free_kptr_off_tab, if needed. + * bpf_map_free_record, if needed. */ map->ops->map_free(map); } @@ -779,7 +799,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) int err; if (!map->ops->map_mmap || map_value_has_spin_lock(map) || - map_value_has_timer(map) || map_value_has_kptrs(map)) + map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -906,7 +926,7 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) +static int map_field_offs_cmp(const void *_a, const void *_b, const void *priv) { const u32 a = *(const u32 *)_a; const u32 b = *(const u32 *)_b; @@ -918,15 +938,15 @@ static int map_off_arr_cmp(const void *_a, const void *_b, const void *priv) return 0; } -static void map_off_arr_swap(void *_a, void *_b, int size, const void *priv) +static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) { struct bpf_map *map = (struct bpf_map *)priv; - u32 *off_base = map->off_arr->field_off; + u32 *off_base = map->field_offs->field_off; u32 *a = _a, *b = _b; u8 *sz_a, *sz_b; - sz_a = map->off_arr->field_sz + (a - off_base); - sz_b = map->off_arr->field_sz + (b - off_base); + sz_a = map->field_offs->field_sz + (a - off_base); + sz_b = map->field_offs->field_sz + (b - off_base); swap(*a, *b); swap(*sz_a, *sz_b); @@ -936,51 +956,51 @@ static int bpf_map_alloc_off_arr(struct bpf_map *map) { bool has_spin_lock = map_value_has_spin_lock(map); bool has_timer = map_value_has_timer(map); - bool has_kptrs = map_value_has_kptrs(map); - struct bpf_map_off_arr *off_arr; + bool has_fields = !IS_ERR_OR_NULL(map->record); + struct btf_field_offs *fo; u32 i; - if (!has_spin_lock && !has_timer && !has_kptrs) { - map->off_arr = NULL; + if (!has_spin_lock && !has_timer && !has_fields) { + map->field_offs = NULL; return 0; } - off_arr = kmalloc(sizeof(*map->off_arr), GFP_KERNEL | __GFP_NOWARN); - if (!off_arr) + fo = kmalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); + if (!fo) return -ENOMEM; - map->off_arr = off_arr; + map->field_offs = fo; - off_arr->cnt = 0; + fo->cnt = 0; if (has_spin_lock) { - i = off_arr->cnt; + i = fo->cnt; - off_arr->field_off[i] = map->spin_lock_off; - off_arr->field_sz[i] = sizeof(struct bpf_spin_lock); - off_arr->cnt++; + fo->field_off[i] = map->spin_lock_off; + fo->field_sz[i] = sizeof(struct bpf_spin_lock); + fo->cnt++; } if (has_timer) { - i = off_arr->cnt; + i = fo->cnt; - off_arr->field_off[i] = map->timer_off; - off_arr->field_sz[i] = sizeof(struct bpf_timer); - off_arr->cnt++; + fo->field_off[i] = map->timer_off; + fo->field_sz[i] = sizeof(struct bpf_timer); + fo->cnt++; } - if (has_kptrs) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - u32 *off = &off_arr->field_off[off_arr->cnt]; - u8 *sz = &off_arr->field_sz[off_arr->cnt]; + if (has_fields) { + struct btf_record *rec = map->record; + u32 *off = &fo->field_off[fo->cnt]; + u8 *sz = &fo->field_sz[fo->cnt]; - for (i = 0; i < tab->nr_off; i++) { - *off++ = tab->off[i].offset; - *sz++ = sizeof(u64); + for (i = 0; i < rec->cnt; i++) { + *off++ = rec->fields[i].offset; + *sz++ = btf_field_type_size(rec->fields[i].type); } - off_arr->cnt += tab->nr_off; + fo->cnt += rec->cnt; } - if (off_arr->cnt == 1) + if (fo->cnt == 1) return 0; - sort_r(off_arr->field_off, off_arr->cnt, sizeof(off_arr->field_off[0]), - map_off_arr_cmp, map_off_arr_swap, map); + sort_r(fo->field_off, fo->cnt, sizeof(fo->field_off[0]), + map_field_offs_cmp, map_field_offs_swap, map); return 0; } @@ -1038,8 +1058,10 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EOPNOTSUPP; } - map->kptr_off_tab = btf_parse_kptrs(btf, value_type); - if (map_value_has_kptrs(map)) { + map->record = btf_parse_fields(btf, value_type); + if (!IS_ERR_OR_NULL(map->record)) { + int i; + if (!bpf_capable()) { ret = -EPERM; goto free_map_tab; @@ -1048,12 +1070,25 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, ret = -EACCES; goto free_map_tab; } - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_LRU_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { - ret = -EOPNOTSUPP; - goto free_map_tab; + for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { + switch (map->record->field_mask & (1 << i)) { + case 0: + continue; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + default: + /* Fail if map_type checks are missing for a field type */ + ret = -EOPNOTSUPP; + goto free_map_tab; + } } } @@ -1065,7 +1100,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; free_map_tab: - bpf_map_free_kptr_off_tab(map); + bpf_map_free_record(map); return ret; } @@ -1186,7 +1221,7 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); free_map_off_arr: - kfree(map->off_arr); + kfree(map->field_offs); free_map: btf_put(map->btf); map->ops->map_free(map); @@ -1883,7 +1918,7 @@ static int map_freeze(const union bpf_attr *attr) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || - map_value_has_timer(map) || map_value_has_kptrs(map)) { + map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) { fdput(f); return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 14d350a25d5d..5ce5364ce898 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -262,7 +262,7 @@ struct bpf_call_arg_meta { struct btf *ret_btf; u32 ret_btf_id; u32 subprogno; - struct bpf_map_value_off_desc *kptr_off_desc; + struct btf_field *kptr_field; u8 uninit_dynptr_regno; }; @@ -3674,15 +3674,15 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, } static int map_kptr_match_type(struct bpf_verifier_env *env, - struct bpf_map_value_off_desc *off_desc, + struct btf_field *kptr_field, struct bpf_reg_state *reg, u32 regno) { - const char *targ_name = kernel_type_name(off_desc->kptr.btf, off_desc->kptr.btf_id); + const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); int perm_flags = PTR_MAYBE_NULL; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ - if (off_desc->type == BPF_KPTR_UNREF) + if (kptr_field->type == BPF_KPTR_UNREF) perm_flags |= PTR_UNTRUSTED; if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags)) @@ -3729,15 +3729,15 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, * strict mode to true for type match. */ if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, - off_desc->kptr.btf, off_desc->kptr.btf_id, - off_desc->type == BPF_KPTR_REF)) + kptr_field->kptr.btf, kptr_field->kptr.btf_id, + kptr_field->type == BPF_KPTR_REF)) goto bad_type; return 0; bad_type: verbose(env, "invalid kptr access, R%d type=%s%s ", regno, reg_type_str(env, reg->type), reg_name); verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name); - if (off_desc->type == BPF_KPTR_UNREF) + if (kptr_field->type == BPF_KPTR_UNREF) verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED), targ_name); else @@ -3747,7 +3747,7 @@ bad_type: static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, int value_regno, int insn_idx, - struct bpf_map_value_off_desc *off_desc) + struct btf_field *kptr_field) { struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; int class = BPF_CLASS(insn->code); @@ -3757,7 +3757,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, * - Reject cases where variable offset may touch kptr * - size of access (must be BPF_DW) * - tnum_is_const(reg->var_off) - * - off_desc->offset == off + reg->var_off.value + * - kptr_field->offset == off + reg->var_off.value */ /* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */ if (BPF_MODE(insn->code) != BPF_MEM) { @@ -3768,7 +3768,7 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, /* We only allow loading referenced kptr, since it will be marked as * untrusted, similar to unreferenced kptr. */ - if (class != BPF_LDX && off_desc->type == BPF_KPTR_REF) { + if (class != BPF_LDX && kptr_field->type == BPF_KPTR_REF) { verbose(env, "store to referenced kptr disallowed\n"); return -EACCES; } @@ -3778,19 +3778,19 @@ static int check_map_kptr_access(struct bpf_verifier_env *env, u32 regno, /* We can simply mark the value_regno receiving the pointer * value from map as PTR_TO_BTF_ID, with the correct type. */ - mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, off_desc->kptr.btf, - off_desc->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); + mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, PTR_MAYBE_NULL | PTR_UNTRUSTED); /* For mark_ptr_or_null_reg */ val_reg->id = ++env->id_gen; } else if (class == BPF_STX) { val_reg = reg_state(env, value_regno); if (!register_is_null(val_reg) && - map_kptr_match_type(env, off_desc, val_reg, value_regno)) + map_kptr_match_type(env, kptr_field, val_reg, value_regno)) return -EACCES; } else if (class == BPF_ST) { if (insn->imm) { verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n", - off_desc->offset); + kptr_field->offset); return -EACCES; } } else { @@ -3809,7 +3809,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_reg_state *reg = &state->regs[regno]; struct bpf_map *map = reg->map_ptr; - int err; + struct btf_record *rec; + int err, i; err = check_mem_region_access(env, regno, off, size, map->value_size, zero_size_allowed); @@ -3839,15 +3840,18 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } } - if (map_value_has_kptrs(map)) { - struct bpf_map_value_off *tab = map->kptr_off_tab; - int i; - - for (i = 0; i < tab->nr_off; i++) { - u32 p = tab->off[i].offset; - - if (reg->smin_value + off < p + sizeof(u64) && - p < reg->umax_value + off + size) { + if (IS_ERR_OR_NULL(map->record)) + return 0; + rec = map->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 p = field->offset; + + if (reg->smin_value + off < p + btf_field_type_size(field->type) && + p < reg->umax_value + off + size) { + switch (field->type) { + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: if (src != ACCESS_DIRECT) { verbose(env, "kptr cannot be accessed indirectly by helper\n"); return -EACCES; @@ -3866,10 +3870,13 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, return -EACCES; } break; + default: + verbose(env, "field cannot be accessed directly by load/store\n"); + return -EACCES; } } } - return err; + return 0; } #define MAX_PACKET_OFF 0xffff @@ -4742,7 +4749,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_MAP_VALUE) { - struct bpf_map_value_off_desc *kptr_off_desc = NULL; + struct btf_field *kptr_field = NULL; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { @@ -4756,11 +4763,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err) return err; if (tnum_is_const(reg->var_off)) - kptr_off_desc = bpf_map_kptr_off_contains(reg->map_ptr, - off + reg->var_off.value); - if (kptr_off_desc) { - err = check_map_kptr_access(env, regno, value_regno, insn_idx, - kptr_off_desc); + kptr_field = btf_record_find(reg->map_ptr->record, + off + reg->var_off.value, BPF_KPTR); + if (kptr_field) { + err = check_map_kptr_access(env, regno, value_regno, insn_idx, kptr_field); } else if (t == BPF_READ && value_regno >= 0) { struct bpf_map *map = reg->map_ptr; @@ -5527,10 +5533,9 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - struct bpf_map_value_off_desc *off_desc; struct bpf_map *map_ptr = reg->map_ptr; + struct btf_field *kptr_field; u32 kptr_off; - int ret; if (!tnum_is_const(reg->var_off)) { verbose(env, @@ -5543,30 +5548,23 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, map_ptr->name); return -EINVAL; } - if (!map_value_has_kptrs(map_ptr)) { - ret = PTR_ERR_OR_ZERO(map_ptr->kptr_off_tab); - if (ret == -E2BIG) - verbose(env, "map '%s' has more than %d kptr\n", map_ptr->name, - BPF_MAP_VALUE_OFF_MAX); - else if (ret == -EEXIST) - verbose(env, "map '%s' has repeating kptr BTF tags\n", map_ptr->name); - else - verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); + if (!btf_record_has_field(map_ptr->record, BPF_KPTR)) { + verbose(env, "map '%s' has no valid kptr\n", map_ptr->name); return -EINVAL; } meta->map_ptr = map_ptr; kptr_off = reg->off + reg->var_off.value; - off_desc = bpf_map_kptr_off_contains(map_ptr, kptr_off); - if (!off_desc) { + kptr_field = btf_record_find(map_ptr->record, kptr_off, BPF_KPTR); + if (!kptr_field) { verbose(env, "off=%d doesn't point to kptr\n", kptr_off); return -EACCES; } - if (off_desc->type != BPF_KPTR_REF) { + if (kptr_field->type != BPF_KPTR_REF) { verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off); return -EACCES; } - meta->kptr_off_desc = off_desc; + meta->kptr_field = kptr_field; return 0; } @@ -5788,7 +5786,7 @@ found: } if (meta->func_id == BPF_FUNC_kptr_xchg) { - if (map_kptr_match_type(env, meta->kptr_off_desc, reg, regno)) + if (map_kptr_match_type(env, meta->kptr_field, reg, regno)) return -EACCES; } else { if (arg_btf_id == BPF_PTR_POISON) { @@ -7536,8 +7534,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; if (func_id == BPF_FUNC_kptr_xchg) { - ret_btf = meta.kptr_off_desc->kptr.btf; - ret_btf_id = meta.kptr_off_desc->kptr.btf_id; + ret_btf = meta.kptr_field->kptr.btf; + ret_btf_id = meta.kptr_field->kptr.btf_id; } else { if (fn->ret_btf_id == BPF_PTR_POISON) { verbose(env, "verifier internal error:"); -- cgit v1.2.3 From db559117828d2448fe81ada051c60bcf39f822e9 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:56 +0530 Subject: bpf: Consolidate spin_lock, timer management into btf_record Now that kptr_off_tab has been refactored into btf_record, and can hold more than one specific field type, accomodate bpf_spin_lock and bpf_timer as well. While they don't require any more metadata than offset, having all special fields in one place allows us to share the same code for allocated user defined types and handle both map values and these allocated objects in a similar fashion. As an optimization, we still keep spin_lock_off and timer_off offsets in the btf_record structure, just to avoid having to find the btf_field struct each time their offset is needed. This is mostly needed to manipulate such objects in a map value at runtime. It's ok to hardcode just one offset as more than one field is disallowed. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 53 ++++--- include/linux/btf.h | 3 +- kernel/bpf/arraymap.c | 19 +-- kernel/bpf/bpf_local_storage.c | 2 +- kernel/bpf/btf.c | 323 ++++++++++++++++++++++------------------- kernel/bpf/hashtab.c | 24 +-- kernel/bpf/helpers.c | 6 +- kernel/bpf/local_storage.c | 2 +- kernel/bpf/map_in_map.c | 5 +- kernel/bpf/syscall.c | 135 ++++++++--------- kernel/bpf/verifier.c | 82 +++-------- net/core/bpf_sk_storage.c | 4 +- 12 files changed, 314 insertions(+), 344 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 5f2a42033a37..aae85019abde 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -166,13 +166,13 @@ struct bpf_map_ops { enum { /* Support at most 8 pointers in a BTF type */ - BTF_FIELDS_MAX = 8, - BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX + - 1 + /* for bpf_spin_lock */ - 1, /* for bpf_timer */ + BTF_FIELDS_MAX = 10, + BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX, }; enum btf_field_type { + BPF_SPIN_LOCK = (1 << 0), + BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, @@ -196,6 +196,8 @@ struct btf_field { struct btf_record { u32 cnt; u32 field_mask; + int spin_lock_off; + int timer_off; struct btf_field fields[]; }; @@ -220,10 +222,8 @@ struct bpf_map { u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; - int spin_lock_off; /* >=0 valid offset, <0 error */ - struct btf_record *record; - int timer_off; /* >=0 valid offset, <0 error */ u32 id; + struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; @@ -257,9 +257,29 @@ struct bpf_map { bool frozen; /* write-once; write-protected by freeze_mutex */ }; +static inline const char *btf_field_type_name(enum btf_field_type type) +{ + switch (type) { + case BPF_SPIN_LOCK: + return "bpf_spin_lock"; + case BPF_TIMER: + return "bpf_timer"; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + return "kptr"; + default: + WARN_ON_ONCE(1); + return "unknown"; + } +} + static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { + case BPF_SPIN_LOCK: + return sizeof(struct bpf_spin_lock); + case BPF_TIMER: + return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: return sizeof(u64); @@ -272,6 +292,10 @@ static inline u32 btf_field_type_size(enum btf_field_type type) static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { + case BPF_SPIN_LOCK: + return __alignof__(struct bpf_spin_lock); + case BPF_TIMER: + return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: return __alignof__(u64); @@ -288,22 +312,8 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline bool map_value_has_spin_lock(const struct bpf_map *map) -{ - return map->spin_lock_off >= 0; -} - -static inline bool map_value_has_timer(const struct bpf_map *map) -{ - return map->timer_off >= 0; -} - static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { - if (unlikely(map_value_has_spin_lock(map))) - memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); - if (unlikely(map_value_has_timer(map))) - memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); if (!IS_ERR_OR_NULL(map->record)) { struct btf_field *fields = map->record->fields; u32 cnt = map->record->cnt; @@ -1740,6 +1750,7 @@ void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); +void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); struct bpf_map *bpf_map_get(u32 ufd); diff --git a/include/linux/btf.h b/include/linux/btf.h index 9e62717cdc7a..282006abd062 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -163,7 +163,8 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, u32 expected_offset, u32 expected_size); int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); -struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t); +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, + u32 field_mask, u32 value_size); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 417f84342e98..672eb17ac421 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -306,13 +306,6 @@ static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key return 0; } -static void check_and_free_fields(struct bpf_array *arr, void *val) -{ - if (map_value_has_timer(&arr->map)) - bpf_timer_cancel_and_free(val + arr->map.timer_off); - bpf_obj_free_fields(arr->map.record, val); -} - /* Called from syscall or from eBPF program */ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) @@ -334,13 +327,13 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { val = this_cpu_ptr(array->pptrs[index & array->index_mask]); copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } else { val = array->value + (u64)array->elem_size * (index & array->index_mask); @@ -348,7 +341,7 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, copy_map_value_locked(map, val, value, false); else copy_map_value(map, val, value); - check_and_free_fields(array, val); + bpf_obj_free_fields(array->map.record, val); } return 0; } @@ -385,7 +378,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { copy_map_value_long(map, per_cpu_ptr(pptr, cpu), value + off); - check_and_free_fields(array, per_cpu_ptr(pptr, cpu)); + bpf_obj_free_fields(array->map.record, per_cpu_ptr(pptr, cpu)); off += size; } rcu_read_unlock(); @@ -409,11 +402,11 @@ static void array_map_free_timers(struct bpf_map *map) int i; /* We don't reset or free fields other than timer on uref dropping to zero. */ - if (!map_value_has_timer(map)) + if (!btf_record_has_field(map->record, BPF_TIMER)) return; for (i = 0; i < array->map.max_entries; i++) - bpf_timer_cancel_and_free(array_map_elem_ptr(array, i) + map->timer_off); + bpf_obj_free_timer(map->record, array_map_elem_ptr(array, i)); } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 93d9b1b17bc8..37020078d1c1 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -382,7 +382,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(&smap->map))) + !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 8391a77138ee..3dad828db13c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3205,16 +3205,20 @@ enum { struct btf_field_info { enum btf_field_type type; u32 off; - u32 type_id; + struct { + u32 type_id; + } kptr; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, - u32 off, int sz, struct btf_field_info *info) + u32 off, int sz, enum btf_field_type field_type, + struct btf_field_info *info) { if (!__btf_type_is_struct(t)) return BTF_FIELD_IGNORE; if (t->size != sz) return BTF_FIELD_IGNORE; + info->type = field_type; info->off = off; return BTF_FIELD_FOUND; } @@ -3251,28 +3255,66 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, if (!__btf_type_is_struct(t)) return -EINVAL; - info->type_id = res_id; - info->off = off; info->type = type; + info->off = off; + info->kptr.type_id = res_id; return BTF_FIELD_FOUND; } -static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align, - enum btf_field_info_type field_type, +static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, + int *align, int *sz) +{ + int type = 0; + + if (field_mask & BPF_SPIN_LOCK) { + if (!strcmp(name, "bpf_spin_lock")) { + if (*seen_mask & BPF_SPIN_LOCK) + return -E2BIG; + *seen_mask |= BPF_SPIN_LOCK; + type = BPF_SPIN_LOCK; + goto end; + } + } + if (field_mask & BPF_TIMER) { + if (!strcmp(name, "bpf_timer")) { + if (*seen_mask & BPF_TIMER) + return -E2BIG; + *seen_mask |= BPF_TIMER; + type = BPF_TIMER; + goto end; + } + } + /* Only return BPF_KPTR when all other types with matchable names fail */ + if (field_mask & BPF_KPTR) { + type = BPF_KPTR_REF; + goto end; + } + return 0; +end: + *sz = btf_field_type_size(type); + *align = btf_field_type_align(type); + return type; +} + +static int btf_find_struct_field(const struct btf *btf, + const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt) { + int ret, idx = 0, align, sz, field_type; const struct btf_member *member; struct btf_field_info tmp; - int ret, idx = 0; - u32 i, off; + u32 i, off, seen_mask = 0; for_each_member(i, t, member) { const struct btf_type *member_type = btf_type_by_id(btf, member->type); - if (name && strcmp(__btf_name_by_offset(btf, member_type->name_off), name)) + field_type = btf_get_field_type(__btf_name_by_offset(btf, member_type->name_off), + field_mask, &seen_mask, &align, &sz); + if (field_type == 0) continue; + if (field_type < 0) + return field_type; off = __btf_member_bit_offset(t, member); if (off % 8) @@ -3280,17 +3322,18 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t return -EINVAL; off /= 8; if (off % align) - return -EINVAL; + continue; switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - case BTF_FIELD_TIMER: - ret = btf_find_struct(btf, member_type, off, sz, + case BPF_SPIN_LOCK: + case BPF_TIMER: + ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; - case BTF_FIELD_KPTR: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: ret = btf_find_kptr(btf, member_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3310,37 +3353,41 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t } static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, - const char *name, int sz, int align, - enum btf_field_info_type field_type, - struct btf_field_info *info, int info_cnt) + u32 field_mask, struct btf_field_info *info, + int info_cnt) { + int ret, idx = 0, align, sz, field_type; const struct btf_var_secinfo *vsi; struct btf_field_info tmp; - int ret, idx = 0; - u32 i, off; + u32 i, off, seen_mask = 0; for_each_vsi(i, t, vsi) { const struct btf_type *var = btf_type_by_id(btf, vsi->type); const struct btf_type *var_type = btf_type_by_id(btf, var->type); - off = vsi->offset; - - if (name && strcmp(__btf_name_by_offset(btf, var_type->name_off), name)) + field_type = btf_get_field_type(__btf_name_by_offset(btf, var_type->name_off), + field_mask, &seen_mask, &align, &sz); + if (field_type == 0) continue; + if (field_type < 0) + return field_type; + + off = vsi->offset; if (vsi->size != sz) continue; if (off % align) - return -EINVAL; + continue; switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - case BTF_FIELD_TIMER: - ret = btf_find_struct(btf, var_type, off, sz, + case BPF_SPIN_LOCK: + case BPF_TIMER: + ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) return ret; break; - case BTF_FIELD_KPTR: + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: ret = btf_find_kptr(btf, var_type, off, sz, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3360,78 +3407,98 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, } static int btf_find_field(const struct btf *btf, const struct btf_type *t, - enum btf_field_info_type field_type, - struct btf_field_info *info, int info_cnt) + u32 field_mask, struct btf_field_info *info, + int info_cnt) { - const char *name; - int sz, align; - - switch (field_type) { - case BTF_FIELD_SPIN_LOCK: - name = "bpf_spin_lock"; - sz = sizeof(struct bpf_spin_lock); - align = __alignof__(struct bpf_spin_lock); - break; - case BTF_FIELD_TIMER: - name = "bpf_timer"; - sz = sizeof(struct bpf_timer); - align = __alignof__(struct bpf_timer); - break; - case BTF_FIELD_KPTR: - name = NULL; - sz = sizeof(u64); - align = 8; - break; - default: - return -EFAULT; - } - if (__btf_type_is_struct(t)) - return btf_find_struct_field(btf, t, name, sz, align, field_type, info, info_cnt); + return btf_find_struct_field(btf, t, field_mask, info, info_cnt); else if (btf_type_is_datasec(t)) - return btf_find_datasec_var(btf, t, name, sz, align, field_type, info, info_cnt); + return btf_find_datasec_var(btf, t, field_mask, info, info_cnt); return -EINVAL; } -/* find 'struct bpf_spin_lock' in map value. - * return >= 0 offset if found - * and < 0 in case of error - */ -int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +static int btf_parse_kptr(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) { - struct btf_field_info info; + struct module *mod = NULL; + const struct btf_type *t; + struct btf *kernel_btf; int ret; + s32 id; - ret = btf_find_field(btf, t, BTF_FIELD_SPIN_LOCK, &info, 1); - if (ret < 0) - return ret; - if (!ret) - return -ENOENT; - return info.off; -} + /* Find type in map BTF, and use it to look up the matching type + * in vmlinux or module BTFs, by name and kind. + */ + t = btf_type_by_id(btf, info->kptr.type_id); + id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), + &kernel_btf); + if (id < 0) + return id; + + /* Find and stash the function pointer for the destruction function that + * needs to be eventually invoked from the map free path. + */ + if (info->type == BPF_KPTR_REF) { + const struct btf_type *dtor_func; + const char *dtor_func_name; + unsigned long addr; + s32 dtor_btf_id; + + /* This call also serves as a whitelist of allowed objects that + * can be used as a referenced pointer and be stored in a map at + * the same time. + */ + dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); + if (dtor_btf_id < 0) { + ret = dtor_btf_id; + goto end_btf; + } -int btf_find_timer(const struct btf *btf, const struct btf_type *t) -{ - struct btf_field_info info; - int ret; + dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); + if (!dtor_func) { + ret = -ENOENT; + goto end_btf; + } - ret = btf_find_field(btf, t, BTF_FIELD_TIMER, &info, 1); - if (ret < 0) - return ret; - if (!ret) - return -ENOENT; - return info.off; + if (btf_is_module(kernel_btf)) { + mod = btf_try_get_module(kernel_btf); + if (!mod) { + ret = -ENXIO; + goto end_btf; + } + } + + /* We already verified dtor_func to be btf_type_is_func + * in register_btf_id_dtor_kfuncs. + */ + dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); + addr = kallsyms_lookup_name(dtor_func_name); + if (!addr) { + ret = -EINVAL; + goto end_mod; + } + field->kptr.dtor = (void *)addr; + } + + field->kptr.btf_id = id; + field->kptr.btf = kernel_btf; + field->kptr.module = mod; + return 0; +end_mod: + module_put(mod); +end_btf: + btf_put(kernel_btf); + return ret; } -struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t) +struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, + u32 field_mask, u32 value_size) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; - struct btf *kernel_btf = NULL; - struct module *mod = NULL; struct btf_record *rec; int ret, i, cnt; - ret = btf_find_field(btf, t, BTF_FIELD_KPTR, info_arr, ARRAY_SIZE(info_arr)); + ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); if (ret < 0) return ERR_PTR(ret); if (!ret) @@ -3441,80 +3508,44 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec = kzalloc(offsetof(struct btf_record, fields[cnt]), GFP_KERNEL | __GFP_NOWARN); if (!rec) return ERR_PTR(-ENOMEM); - rec->cnt = 0; - for (i = 0; i < cnt; i++) { - const struct btf_type *t; - s32 id; - /* Find type in map BTF, and use it to look up the matching type - * in vmlinux or module BTFs, by name and kind. - */ - t = btf_type_by_id(btf, info_arr[i].type_id); - id = bpf_find_btf_id(__btf_name_by_offset(btf, t->name_off), BTF_INFO_KIND(t->info), - &kernel_btf); - if (id < 0) { - ret = id; + rec->spin_lock_off = -EINVAL; + rec->timer_off = -EINVAL; + for (i = 0; i < cnt; i++) { + if (info_arr[i].off + btf_field_type_size(info_arr[i].type) > value_size) { + WARN_ONCE(1, "verifier bug off %d size %d", info_arr[i].off, value_size); + ret = -EFAULT; goto end; } - /* Find and stash the function pointer for the destruction function that - * needs to be eventually invoked from the map free path. - */ - if (info_arr[i].type == BPF_KPTR_REF) { - const struct btf_type *dtor_func; - const char *dtor_func_name; - unsigned long addr; - s32 dtor_btf_id; - - /* This call also serves as a whitelist of allowed objects that - * can be used as a referenced pointer and be stored in a map at - * the same time. - */ - dtor_btf_id = btf_find_dtor_kfunc(kernel_btf, id); - if (dtor_btf_id < 0) { - ret = dtor_btf_id; - goto end_btf; - } - - dtor_func = btf_type_by_id(kernel_btf, dtor_btf_id); - if (!dtor_func) { - ret = -ENOENT; - goto end_btf; - } - - if (btf_is_module(kernel_btf)) { - mod = btf_try_get_module(kernel_btf); - if (!mod) { - ret = -ENXIO; - goto end_btf; - } - } - - /* We already verified dtor_func to be btf_type_is_func - * in register_btf_id_dtor_kfuncs. - */ - dtor_func_name = __btf_name_by_offset(kernel_btf, dtor_func->name_off); - addr = kallsyms_lookup_name(dtor_func_name); - if (!addr) { - ret = -EINVAL; - goto end_mod; - } - rec->fields[i].kptr.dtor = (void *)addr; - } - rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; rec->fields[i].type = info_arr[i].type; - rec->fields[i].kptr.btf_id = id; - rec->fields[i].kptr.btf = kernel_btf; - rec->fields[i].kptr.module = mod; + + switch (info_arr[i].type) { + case BPF_SPIN_LOCK: + WARN_ON_ONCE(rec->spin_lock_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->spin_lock_off = rec->fields[i].offset; + break; + case BPF_TIMER: + WARN_ON_ONCE(rec->timer_off >= 0); + /* Cache offset for faster lookup at runtime */ + rec->timer_off = rec->fields[i].offset; + break; + case BPF_KPTR_UNREF: + case BPF_KPTR_REF: + ret = btf_parse_kptr(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; + default: + ret = -EFAULT; + goto end; + } rec->cnt++; } return rec; -end_mod: - module_put(mod); -end_btf: - btf_put(kernel_btf); end: btf_record_free(rec); return ERR_PTR(ret); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index c5ea8f9bb7a9..50d254cd0709 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -222,7 +222,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) u32 num_entries = htab->map.max_entries; int i; - if (!map_value_has_timer(&htab->map)) + if (!btf_record_has_field(htab->map.record, BPF_TIMER)) return; if (htab_has_extra_elems(htab)) num_entries += num_possible_cpus(); @@ -231,9 +231,7 @@ static void htab_free_prealloced_timers(struct bpf_htab *htab) struct htab_elem *elem; elem = get_htab_elem(htab, i); - bpf_timer_cancel_and_free(elem->key + - round_up(htab->map.key_size, 8) + - htab->map.timer_off); + bpf_obj_free_timer(htab->map.record, elem->key + round_up(htab->map.key_size, 8)); cond_resched(); } } @@ -763,8 +761,6 @@ static void check_and_free_fields(struct bpf_htab *htab, { void *map_value = elem->key + round_up(htab->map.key_size, 8); - if (map_value_has_timer(&htab->map)) - bpf_timer_cancel_and_free(map_value + htab->map.timer_off); bpf_obj_free_fields(htab->map.record, map_value); } @@ -1089,7 +1085,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, head = &b->head; if (unlikely(map_flags & BPF_F_LOCK)) { - if (unlikely(!map_value_has_spin_lock(map))) + if (unlikely(!btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; /* find an element without taking the bucket lock */ l_old = lookup_nulls_elem_raw(head, hash, key, key_size, @@ -1472,12 +1468,8 @@ static void htab_free_malloced_timers(struct bpf_htab *htab) struct htab_elem *l; hlist_nulls_for_each_entry(l, n, head, hash_node) { - /* We don't reset or free kptr on uref dropping to zero, - * hence just free timer. - */ - bpf_timer_cancel_and_free(l->key + - round_up(htab->map.key_size, 8) + - htab->map.timer_off); + /* We only free timer on uref dropping to zero */ + bpf_obj_free_timer(htab->map.record, l->key + round_up(htab->map.key_size, 8)); } cond_resched_rcu(); } @@ -1488,8 +1480,8 @@ static void htab_map_free_timers(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - /* We don't reset or free kptr on uref dropping to zero. */ - if (!map_value_has_timer(&htab->map)) + /* We only free timer on uref dropping to zero */ + if (!btf_record_has_field(htab->map.record, BPF_TIMER)) return; if (!htab_is_prealloc(htab)) htab_free_malloced_timers(htab); @@ -1673,7 +1665,7 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, elem_map_flags = attr->batch.elem_flags; if ((elem_map_flags & ~BPF_F_LOCK) || - ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + ((elem_map_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; map_flags = attr->batch.flags; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 124fd199ce5c..283f55bbeb70 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -366,9 +366,9 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, struct bpf_spin_lock *lock; if (lock_src) - lock = src + map->spin_lock_off; + lock = src + map->record->spin_lock_off; else - lock = dst + map->spin_lock_off; + lock = dst + map->record->spin_lock_off; preempt_disable(); __bpf_spin_lock_irqsave(lock); copy_map_value(map, dst, src); @@ -1169,7 +1169,7 @@ BPF_CALL_3(bpf_timer_init, struct bpf_timer_kern *, timer, struct bpf_map *, map ret = -ENOMEM; goto out; } - t->value = (void *)timer - map->timer_off; + t->value = (void *)timer - map->record->timer_off; t->map = map; t->prog = NULL; rcu_assign_pointer(t->callback_fn, NULL); diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 098cf336fae6..e90d9f63edc5 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -151,7 +151,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return -EINVAL; if (unlikely((flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map))) + !btf_record_has_field(map->record, BPF_SPIN_LOCK))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index d6c662183f88..8ca0cca39d49 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -29,7 +29,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) return ERR_PTR(-ENOTSUPP); } - if (map_value_has_spin_lock(inner_map)) { + if (btf_record_has_field(inner_map->record, BPF_SPIN_LOCK)) { fdput(f); return ERR_PTR(-ENOTSUPP); } @@ -50,8 +50,6 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) inner_map_meta->value_size = inner_map->value_size; inner_map_meta->map_flags = inner_map->map_flags; inner_map_meta->max_entries = inner_map->max_entries; - inner_map_meta->spin_lock_off = inner_map->spin_lock_off; - inner_map_meta->timer_off = inner_map->timer_off; inner_map_meta->record = btf_record_dup(inner_map->record); if (IS_ERR(inner_map_meta->record)) { /* btf_record_dup returns NULL or valid pointer in case of @@ -92,7 +90,6 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, return meta0->map_type == meta1->map_type && meta0->key_size == meta1->key_size && meta0->value_size == meta1->value_size && - meta0->timer_off == meta1->timer_off && meta0->map_flags == meta1->map_flags && btf_record_equal(meta0->record, meta1->record); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b80c0e2eb73f..53d6dc5cf0e2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -527,6 +527,9 @@ void btf_record_free(struct btf_record *rec) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { + case BPF_SPIN_LOCK: + case BPF_TIMER: + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (rec->fields[i].kptr.module) @@ -564,6 +567,9 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { + case BPF_SPIN_LOCK: + case BPF_TIMER: + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: btf_get(fields[i].kptr.btf); @@ -600,6 +606,13 @@ bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *r return !memcmp(rec_a, rec_b, size); } +void bpf_obj_free_timer(const struct btf_record *rec, void *obj) +{ + if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) + return; + bpf_timer_cancel_and_free(obj + rec->timer_off); +} + void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -613,6 +626,11 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) void *field_ptr = obj + field->offset; switch (fields[i].type) { + case BPF_SPIN_LOCK: + break; + case BPF_TIMER: + bpf_timer_cancel_and_free(field_ptr); + break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; @@ -798,8 +816,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) struct bpf_map *map = filp->private_data; int err; - if (!map->ops->map_mmap || map_value_has_spin_lock(map) || - map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) + if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) @@ -954,48 +971,30 @@ static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) static int bpf_map_alloc_off_arr(struct bpf_map *map) { - bool has_spin_lock = map_value_has_spin_lock(map); - bool has_timer = map_value_has_timer(map); bool has_fields = !IS_ERR_OR_NULL(map->record); struct btf_field_offs *fo; - u32 i; + struct btf_record *rec; + u32 i, *off; + u8 *sz; - if (!has_spin_lock && !has_timer && !has_fields) { + if (!has_fields) { map->field_offs = NULL; return 0; } - fo = kmalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); + fo = kzalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); if (!fo) return -ENOMEM; map->field_offs = fo; - fo->cnt = 0; - if (has_spin_lock) { - i = fo->cnt; - - fo->field_off[i] = map->spin_lock_off; - fo->field_sz[i] = sizeof(struct bpf_spin_lock); - fo->cnt++; - } - if (has_timer) { - i = fo->cnt; - - fo->field_off[i] = map->timer_off; - fo->field_sz[i] = sizeof(struct bpf_timer); - fo->cnt++; - } - if (has_fields) { - struct btf_record *rec = map->record; - u32 *off = &fo->field_off[fo->cnt]; - u8 *sz = &fo->field_sz[fo->cnt]; - - for (i = 0; i < rec->cnt; i++) { - *off++ = rec->fields[i].offset; - *sz++ = btf_field_type_size(rec->fields[i].type); - } - fo->cnt += rec->cnt; + rec = map->record; + off = fo->field_off; + sz = fo->field_sz; + for (i = 0; i < rec->cnt; i++) { + *off++ = rec->fields[i].offset; + *sz++ = btf_field_type_size(rec->fields[i].type); } + fo->cnt = rec->cnt; if (fo->cnt == 1) return 0; @@ -1026,39 +1025,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; - map->spin_lock_off = btf_find_spin_lock(btf, value_type); - - if (map_value_has_spin_lock(map)) { - if (map->map_flags & BPF_F_RDONLY_PROG) - return -EACCES; - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY && - map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && - map->map_type != BPF_MAP_TYPE_SK_STORAGE && - map->map_type != BPF_MAP_TYPE_INODE_STORAGE && - map->map_type != BPF_MAP_TYPE_TASK_STORAGE && - map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) - return -ENOTSUPP; - if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > - map->value_size) { - WARN_ONCE(1, - "verifier bug spin_lock_off %d value_size %d\n", - map->spin_lock_off, map->value_size); - return -EFAULT; - } - } - - map->timer_off = btf_find_timer(btf, value_type); - if (map_value_has_timer(map)) { - if (map->map_flags & BPF_F_RDONLY_PROG) - return -EACCES; - if (map->map_type != BPF_MAP_TYPE_HASH && - map->map_type != BPF_MAP_TYPE_LRU_HASH && - map->map_type != BPF_MAP_TYPE_ARRAY) - return -EOPNOTSUPP; - } - - map->record = btf_parse_fields(btf, value_type); + map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR, + map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1074,6 +1042,26 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, switch (map->record->field_mask & (1 << i)) { case 0: continue; + case BPF_SPIN_LOCK: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_SK_STORAGE && + map->map_type != BPF_MAP_TYPE_INODE_STORAGE && + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; + case BPF_TIMER: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) { + return -EOPNOTSUPP; + goto free_map_tab; + } + break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (map->map_type != BPF_MAP_TYPE_HASH && @@ -1153,8 +1141,6 @@ static int map_create(union bpf_attr *attr) mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner.lock); - map->spin_lock_off = -EINVAL; - map->timer_off = -EINVAL; if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with @@ -1368,7 +1354,7 @@ static int map_lookup_elem(union bpf_attr *attr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1441,7 +1427,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1604,7 +1590,7 @@ int generic_map_delete_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1661,7 +1647,7 @@ int generic_map_update_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } @@ -1724,7 +1710,7 @@ int generic_map_lookup_batch(struct bpf_map *map, return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; value_size = bpf_map_value_size(map); @@ -1846,7 +1832,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) } if ((attr->flags & BPF_F_LOCK) && - !map_value_has_spin_lock(map)) { + !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } @@ -1917,8 +1903,7 @@ static int map_freeze(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || - map_value_has_timer(map) || !IS_ERR_OR_NULL(map->record)) { + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) { fdput(f); return -ENOTSUPP; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5ce5364ce898..73a3516f1a48 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -454,7 +454,7 @@ static bool reg_type_not_null(enum bpf_reg_type type) static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && - map_value_has_spin_lock(reg->map_ptr); + btf_record_has_field(reg->map_ptr->record, BPF_SPIN_LOCK); } static bool type_is_rdonly_mem(u32 type) @@ -1388,7 +1388,7 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - if (map_value_has_timer(map->inner_map_meta)) + if (btf_record_has_field(map->inner_map_meta->record, BPF_TIMER)) reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; @@ -3817,29 +3817,6 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, if (err) return err; - if (map_value_has_spin_lock(map)) { - u32 lock = map->spin_lock_off; - - /* if any part of struct bpf_spin_lock can be touched by - * load/store reject this program. - * To check that [x1, x2) overlaps with [y1, y2) - * it is sufficient to check x1 < y2 && y1 < x2. - */ - if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && - lock < reg->umax_value + off + size) { - verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); - return -EACCES; - } - } - if (map_value_has_timer(map)) { - u32 t = map->timer_off; - - if (reg->smin_value + off < t + sizeof(struct bpf_timer) && - t < reg->umax_value + off + size) { - verbose(env, "bpf_timer cannot be accessed directly by load/store\n"); - return -EACCES; - } - } if (IS_ERR_OR_NULL(map->record)) return 0; rec = map->record; @@ -3847,6 +3824,10 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, struct btf_field *field = &rec->fields[i]; u32 p = field->offset; + /* If any part of a field can be touched by load/store, reject + * this program. To check that [x1, x2) overlaps with [y1, y2), + * it is sufficient to check x1 < y2 && y1 < x2. + */ if (reg->smin_value + off < p + btf_field_type_size(field->type) && p < reg->umax_value + off + size) { switch (field->type) { @@ -3871,7 +3852,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, } break; default: - verbose(env, "field cannot be accessed directly by load/store\n"); + verbose(env, "%s cannot be accessed directly by load/store\n", + btf_field_type_name(field->type)); return -EACCES; } } @@ -5440,24 +5422,13 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, map->name); return -EINVAL; } - if (!map_value_has_spin_lock(map)) { - if (map->spin_lock_off == -E2BIG) - verbose(env, - "map '%s' has more than one 'struct bpf_spin_lock'\n", - map->name); - else if (map->spin_lock_off == -ENOENT) - verbose(env, - "map '%s' doesn't have 'struct bpf_spin_lock'\n", - map->name); - else - verbose(env, - "map '%s' is not a struct type or bpf_spin_lock is mangled\n", - map->name); + if (!btf_record_has_field(map->record, BPF_SPIN_LOCK)) { + verbose(env, "map '%s' has no valid bpf_spin_lock\n", map->name); return -EINVAL; } - if (map->spin_lock_off != val + reg->off) { - verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", - val + reg->off); + if (map->record->spin_lock_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock' that is at %d\n", + val + reg->off, map->record->spin_lock_off); return -EINVAL; } if (is_lock) { @@ -5500,24 +5471,13 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, map->name); return -EINVAL; } - if (!map_value_has_timer(map)) { - if (map->timer_off == -E2BIG) - verbose(env, - "map '%s' has more than one 'struct bpf_timer'\n", - map->name); - else if (map->timer_off == -ENOENT) - verbose(env, - "map '%s' doesn't have 'struct bpf_timer'\n", - map->name); - else - verbose(env, - "map '%s' is not a struct type or bpf_timer is mangled\n", - map->name); + if (!btf_record_has_field(map->record, BPF_TIMER)) { + verbose(env, "map '%s' has no valid bpf_timer\n", map->name); return -EINVAL; } - if (map->timer_off != val + reg->off) { + if (map->record->timer_off != val + reg->off) { verbose(env, "off %lld doesn't point to 'struct bpf_timer' that is at %d\n", - val + reg->off, map->timer_off); + val + reg->off, map->record->timer_off); return -EINVAL; } if (meta->map_ptr) { @@ -7470,7 +7430,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].map_uid = meta.map_uid; regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; if (!type_may_be_null(ret_type) && - map_value_has_spin_lock(meta.map_ptr)) { + btf_record_has_field(meta.map_ptr->record, BPF_SPIN_LOCK)) { regs[BPF_REG_0].id = ++env->id_gen; } break; @@ -10381,7 +10341,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; - if (map_value_has_spin_lock(map)) + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) dst_reg->id = ++env->id_gen; } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { @@ -12659,7 +12619,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); - if (map_value_has_spin_lock(map)) { + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); return -EINVAL; @@ -12676,7 +12636,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } - if (map_value_has_timer(map)) { + if (btf_record_has_field(map->record, BPF_TIMER)) { if (is_tracing_prog_type(prog_type)) { verbose(env, "tracing progs cannot use bpf_timer yet\n"); return -EINVAL; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 49884e7de080..9d2288c0736e 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -147,7 +147,7 @@ bpf_sk_storage_clone_elem(struct sock *newsk, if (!copy_selem) return NULL; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else @@ -566,7 +566,7 @@ static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) if (!nla_value) goto errout; - if (map_value_has_spin_lock(&smap->map)) + if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else -- cgit v1.2.3 From f71b2f64177a199d5b1d2047e155d45fd98f564a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 4 Nov 2022 00:39:57 +0530 Subject: bpf: Refactor map->off_arr handling Refactor map->off_arr handling into generic functions that can work on their own without hardcoding map specific code. The btf_fields_offs structure is now returned from btf_parse_field_offs, which can be reused later for types in program BTF. All functions like copy_map_value, zero_map_value call generic underlying functions so that they can also be reused later for copying to values allocated in programs which encode specific fields. Later, some helper functions will also require access to this btf_field_offs structure to be able to skip over special fields at runtime. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221103191013.1236066-9-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 41 +++++++++++++++++------------ include/linux/btf.h | 1 + kernel/bpf/btf.c | 55 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 73 +++++++--------------------------------------------- 4 files changed, 89 insertions(+), 81 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aae85019abde..798aec816970 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -341,57 +341,64 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ -static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, bool long_memcpy) +static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, + void *dst, void *src, u32 size, + bool long_memcpy) { u32 curr_off = 0; int i; - if (likely(!map->field_offs)) { + if (likely(!foffs)) { if (long_memcpy) - bpf_long_memcpy(dst, src, round_up(map->value_size, 8)); + bpf_long_memcpy(dst, src, round_up(size, 8)); else - memcpy(dst, src, map->value_size); + memcpy(dst, src, size); return; } - for (i = 0; i < map->field_offs->cnt; i++) { - u32 next_off = map->field_offs->field_off[i]; + for (i = 0; i < foffs->cnt; i++) { + u32 next_off = foffs->field_off[i]; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); - curr_off += map->field_offs->field_sz[i]; + curr_off += foffs->field_sz[i]; } - memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off); + memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { - __copy_map_value(map, dst, src, false); + bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { - __copy_map_value(map, dst, src, true); + bpf_obj_memcpy(map->field_offs, dst, src, map->value_size, true); } -static inline void zero_map_value(struct bpf_map *map, void *dst) +static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 size) { u32 curr_off = 0; int i; - if (likely(!map->field_offs)) { - memset(dst, 0, map->value_size); + if (likely(!foffs)) { + memset(dst, 0, size); return; } - for (i = 0; i < map->field_offs->cnt; i++) { - u32 next_off = map->field_offs->field_off[i]; + for (i = 0; i < foffs->cnt; i++) { + u32 next_off = foffs->field_off[i]; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); - curr_off += map->field_offs->field_sz[i]; + curr_off += foffs->field_sz[i]; } - memset(dst + curr_off, 0, map->value_size - curr_off); + memset(dst + curr_off, 0, size - curr_off); +} + +static inline void zero_map_value(struct bpf_map *map, void *dst) +{ + bpf_obj_memzero(map->field_offs, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, diff --git a/include/linux/btf.h b/include/linux/btf.h index 282006abd062..d80345fa566b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -165,6 +165,7 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); +struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3dad828db13c..5579ff3a5b54 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3551,6 +3551,61 @@ end: return ERR_PTR(ret); } +static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) +{ + const u32 a = *(const u32 *)_a; + const u32 b = *(const u32 *)_b; + + if (a < b) + return -1; + else if (a > b) + return 1; + return 0; +} + +static void btf_field_offs_swap(void *_a, void *_b, int size, const void *priv) +{ + struct btf_field_offs *foffs = (void *)priv; + u32 *off_base = foffs->field_off; + u32 *a = _a, *b = _b; + u8 *sz_a, *sz_b; + + sz_a = foffs->field_sz + (a - off_base); + sz_b = foffs->field_sz + (b - off_base); + + swap(*a, *b); + swap(*sz_a, *sz_b); +} + +struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec) +{ + struct btf_field_offs *foffs; + u32 i, *off; + u8 *sz; + + BUILD_BUG_ON(ARRAY_SIZE(foffs->field_off) != ARRAY_SIZE(foffs->field_sz)); + if (IS_ERR_OR_NULL(rec) || WARN_ON_ONCE(rec->cnt > sizeof(foffs->field_off))) + return NULL; + + foffs = kzalloc(sizeof(*foffs), GFP_KERNEL | __GFP_NOWARN); + if (!foffs) + return ERR_PTR(-ENOMEM); + + off = foffs->field_off; + sz = foffs->field_sz; + for (i = 0; i < rec->cnt; i++) { + off[i] = rec->fields[i].offset; + sz[i] = btf_field_type_size(rec->fields[i].type); + } + foffs->cnt = rec->cnt; + + if (foffs->cnt == 1) + return foffs; + sort_r(foffs->field_off, foffs->cnt, sizeof(foffs->field_off[0]), + btf_field_offs_cmp, btf_field_offs_swap, foffs); + return foffs; +} + static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct btf_show *show) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 53d6dc5cf0e2..85532d301124 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -943,66 +943,6 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_field_offs_cmp(const void *_a, const void *_b, const void *priv) -{ - const u32 a = *(const u32 *)_a; - const u32 b = *(const u32 *)_b; - - if (a < b) - return -1; - else if (a > b) - return 1; - return 0; -} - -static void map_field_offs_swap(void *_a, void *_b, int size, const void *priv) -{ - struct bpf_map *map = (struct bpf_map *)priv; - u32 *off_base = map->field_offs->field_off; - u32 *a = _a, *b = _b; - u8 *sz_a, *sz_b; - - sz_a = map->field_offs->field_sz + (a - off_base); - sz_b = map->field_offs->field_sz + (b - off_base); - - swap(*a, *b); - swap(*sz_a, *sz_b); -} - -static int bpf_map_alloc_off_arr(struct bpf_map *map) -{ - bool has_fields = !IS_ERR_OR_NULL(map->record); - struct btf_field_offs *fo; - struct btf_record *rec; - u32 i, *off; - u8 *sz; - - if (!has_fields) { - map->field_offs = NULL; - return 0; - } - - fo = kzalloc(sizeof(*map->field_offs), GFP_KERNEL | __GFP_NOWARN); - if (!fo) - return -ENOMEM; - map->field_offs = fo; - - rec = map->record; - off = fo->field_off; - sz = fo->field_sz; - for (i = 0; i < rec->cnt; i++) { - *off++ = rec->fields[i].offset; - *sz++ = btf_field_type_size(rec->fields[i].type); - } - fo->cnt = rec->cnt; - - if (fo->cnt == 1) - return 0; - sort_r(fo->field_off, fo->cnt, sizeof(fo->field_off[0]), - map_field_offs_cmp, map_field_offs_swap, map); - return 0; -} - static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { @@ -1097,6 +1037,7 @@ free_map_tab: static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); + struct btf_field_offs *foffs; struct bpf_map *map; int f_flags; int err; @@ -1176,13 +1117,17 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = bpf_map_alloc_off_arr(map); - if (err) + + foffs = btf_parse_field_offs(map->record); + if (IS_ERR(foffs)) { + err = PTR_ERR(foffs); goto free_map; + } + map->field_offs = foffs; err = security_bpf_map_alloc(map); if (err) - goto free_map_off_arr; + goto free_map_field_offs; err = bpf_map_alloc_id(map); if (err) @@ -1206,7 +1151,7 @@ static int map_create(union bpf_attr *attr) free_map_sec: security_bpf_map_free(map); -free_map_off_arr: +free_map_field_offs: kfree(map->field_offs); free_map: btf_put(map->btf); -- cgit v1.2.3 From 2b6c0e152868c9c5939a5c5094d5b2be61cf48e6 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Fri, 28 Oct 2022 11:23:32 +0200 Subject: bcma: Use the proper gpio include The is including the legacy header to obtain struct gpio_chip. Instead, include where this struct is defined. It turns out that the brcm80211 brcmsmac depends on this to bring in the symbol gpio_is_valid(). The driver looks up the BCMA parent GPIO driver and checks that this succeeds, but then it goes on to use the deprecated GPIO call gpio_is_valid() to check the consistency of the .base member of the BCMA GPIO struct. The whole check can be dropped because the bcma_gpio is initialized in the declarations: struct gpio_chip *bcma_gpio = &cc_drv->gpio; And this can never be NULL. Cc: Jonas Gorski Acked-by: Arend van Spriel Signed-off-by: Linus Walleij Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221028092332.238728-1-linus.walleij@linaro.org --- drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.c | 3 --- include/linux/bcma/bcma_driver_chipcommon.h | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.c index c1b9ac692d26..9540a05247c2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.c @@ -63,9 +63,6 @@ int brcms_led_register(struct brcms_info *wl) int hwnum = -1; enum gpio_lookup_flags lflags = GPIO_ACTIVE_HIGH; - if (!bcma_gpio || !gpio_is_valid(bcma_gpio->base)) - return -ENODEV; - /* find radio enabled LED */ for (i = 0; i < BRCMS_LED_NO; i++) { u8 led = *leds[i]; diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 2d94c30ed439..0cb6638b55e5 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -4,7 +4,7 @@ #include #include -#include +#include /** ChipCommon core registers. **/ #define BCMA_CC_ID 0x0000 -- cgit v1.2.3 From d08cb25556773c65efb21761b75f92c804ad0975 Mon Sep 17 00:00:00 2001 From: David Yang Date: Fri, 28 Oct 2022 10:01:01 +0800 Subject: net: mv643xx_eth: support MII/GMII/RGMII modes for Kirkwood Support mode switch properly, which is not available before. If SoC has two Ethernet controllers, by setting both of them into MII mode, the first controller enters GMII mode, while the second controller is effectively disabled. This requires configuring (and maybe enabling) the second controller in the device tree, even though it cannot be used. Signed-off-by: David Yang Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mv643xx_eth.c | 49 +++++++++++++++++++++++++----- include/linux/mv643xx_eth.h | 2 ++ 2 files changed, 44 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 707993b445d1..4389a33a2ea6 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -108,6 +108,7 @@ static char mv643xx_eth_driver_version[] = "1.4"; #define TXQ_COMMAND 0x0048 #define TXQ_FIX_PRIO_CONF 0x004c #define PORT_SERIAL_CONTROL1 0x004c +#define RGMII_EN 0x00000008 #define CLK125_BYPASS_EN 0x00000010 #define TX_BW_RATE 0x0050 #define TX_BW_MTU 0x0058 @@ -2761,6 +2762,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, mv643xx_eth_property(pnp, "rx-sram-addr", ppd.rx_sram_addr); mv643xx_eth_property(pnp, "rx-sram-size", ppd.rx_sram_size); + of_get_phy_mode(pnp, &ppd.interface); + ppd.phy_node = of_parse_phandle(pnp, "phy-handle", 0); if (!ppd.phy_node) { ppd.phy_addr = MV643XX_ETH_PHY_NONE; @@ -3092,6 +3095,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev) struct mv643xx_eth_private *mp; struct net_device *dev; struct phy_device *phydev = NULL; + u32 psc1r; int err, irq; pd = dev_get_platdata(&pdev->dev); @@ -3119,14 +3123,45 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->dev = dev; - /* Kirkwood resets some registers on gated clocks. Especially - * CLK125_BYPASS_EN must be cleared but is not available on - * all other SoCs/System Controllers using this driver. - */ if (of_device_is_compatible(pdev->dev.of_node, - "marvell,kirkwood-eth-port")) - wrlp(mp, PORT_SERIAL_CONTROL1, - rdlp(mp, PORT_SERIAL_CONTROL1) & ~CLK125_BYPASS_EN); + "marvell,kirkwood-eth-port")) { + psc1r = rdlp(mp, PORT_SERIAL_CONTROL1); + + /* Kirkwood resets some registers on gated clocks. Especially + * CLK125_BYPASS_EN must be cleared but is not available on + * all other SoCs/System Controllers using this driver. + */ + psc1r &= ~CLK125_BYPASS_EN; + + /* On Kirkwood with two Ethernet controllers, if both of them + * have RGMII_EN disabled, the first controller will be in GMII + * mode and the second one is effectively disabled, instead of + * two MII interfaces. + * + * To enable GMII in the first controller, the second one must + * also be configured (and may be enabled) with RGMII_EN + * disabled too, even though it cannot be used at all. + */ + switch (pd->interface) { + /* Use internal to denote second controller being disabled */ + case PHY_INTERFACE_MODE_INTERNAL: + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_GMII: + psc1r &= ~RGMII_EN; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + psc1r |= RGMII_EN; + break; + default: + /* Unknown; don't touch */ + break; + } + + wrlp(mp, PORT_SERIAL_CONTROL1, psc1r); + } /* * Start with a default rate, and if there is a clock, allow diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 3682ae75c7aa..145169be2ed8 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -8,6 +8,7 @@ #include #include +#include #define MV643XX_ETH_SHARED_NAME "mv643xx_eth" #define MV643XX_ETH_NAME "mv643xx_eth_port" @@ -59,6 +60,7 @@ struct mv643xx_eth_platform_data { */ int speed; int duplex; + phy_interface_t interface; /* * How many RX/TX queues to use. -- cgit v1.2.3 From 7c3eaa022261d79d273d73ac68ff02cbe2839c10 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Nov 2022 12:13:32 -0700 Subject: genetlink: move the private fields in struct genl_family Move the private fields down to form a "private section". Use the kdoc "private:" label comment thing to hide them from the main kdoc comment. Signed-off-by: Jakub Kicinski Reviewed-by: Johannes Berg Reviewed-by: Jacob Keller Signed-off-by: David S. Miller --- include/net/genetlink.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9f97f73615b6..81180fc6526a 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -23,7 +23,6 @@ struct genl_info; /** * struct genl_family - generic netlink family - * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version @@ -43,8 +42,6 @@ struct genl_info; * @resv_start_op: first operation for which reserved fields of the header * can be validated and policies are required (see below); * new families should leave this field at zero - * @mcgrp_offset: starting number of multicast group IDs in this family - * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family @@ -58,12 +55,10 @@ struct genl_info; * if policy is not provided core will reject all TLV attributes. */ struct genl_family { - int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; - unsigned int mcgrp_offset; /* private */ u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; @@ -81,6 +76,12 @@ struct genl_family { const struct genl_small_ops *small_ops; const struct genl_multicast_group *mcgrps; struct module *module; + +/* private: internal use only */ + /* protocol family identifier */ + int id; + /* starting number of multicast group IDs in this family */ + unsigned int mcgrp_offset; }; /** -- cgit v1.2.3 From 20b0b53aca436af9fece9428ca3ab7c7b9cf4583 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Nov 2022 12:13:33 -0700 Subject: genetlink: introduce split op representation We currently have two forms of operations - small ops and "full" ops (or just ops). The former does not have pointers for some of the less commonly used features (namely dump start/done and policy). The "full" ops, however, still don't contain all the necessary information. In particular the policy is per command ID, while do and dump often accept different attributes. It's also not possible to define different pre_doit and post_doit callbacks for different commands within the family. At the same time a lot of commands do not support dumping and therefore all the dump-related information is wasted space. Create a new command representation which can hold info about a do implementation or a dump implementation, but not both at the same time. Use this new representation on the command execution path (genl_family_rcv_msg) as we either run a do or a dump and don't have to create a "full" op there. Signed-off-by: Jakub Kicinski Reviewed-by: Jacob Keller Signed-off-by: David S. Miller --- include/net/genetlink.h | 60 ++++++++++++++++++++++++++++++++--- net/batman-adv/netlink.c | 6 ++-- net/core/devlink.c | 4 +-- net/core/drop_monitor.c | 4 +-- net/ieee802154/nl802154.c | 6 ++-- net/netlink/genetlink.c | 79 ++++++++++++++++++++++++++++++++++++++--------- net/wireless/nl80211.c | 6 ++-- 7 files changed, 136 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 81180fc6526a..4be7989c451b 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -18,7 +18,7 @@ struct genl_multicast_group { u8 flags; }; -struct genl_ops; +struct genl_split_ops; struct genl_info; /** @@ -66,10 +66,10 @@ struct genl_family { u8 n_mcgrps; u8 resv_start_op; const struct nla_policy *policy; - int (*pre_doit)(const struct genl_ops *ops, + int (*pre_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); - void (*post_doit)(const struct genl_ops *ops, + void (*post_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; @@ -182,6 +182,58 @@ struct genl_ops { u8 validate; }; +/** + * struct genl_split_ops - generic netlink operations (do/dump split version) + * @cmd: command identifier + * @internal_flags: flags used by the family + * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) + * @validate: validation flags from enum genl_validate_flags + * @policy: netlink policy (takes precedence over family policy) + * @maxattr: maximum number of attributes supported + * + * Do callbacks: + * @pre_doit: called before an operation's @doit callback, it may + * do additional, common, filtering and return an error + * @doit: standard command callback + * @post_doit: called after an operation's @doit callback, it may + * undo operations done by pre_doit, for example release locks + * + * Dump callbacks: + * @start: start callback for dumps + * @dumpit: callback for dumpers + * @done: completion callback for dumps + * + * Do callbacks can be used if %GENL_CMD_CAP_DO is set in @flags. + * Dump callbacks can be used if %GENL_CMD_CAP_DUMP is set in @flags. + * Exactly one of those flags must be set. + */ +struct genl_split_ops { + union { + struct { + int (*pre_doit)(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info); + int (*doit)(struct sk_buff *skb, + struct genl_info *info); + void (*post_doit)(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info); + }; + struct { + int (*start)(struct netlink_callback *cb); + int (*dumpit)(struct sk_buff *skb, + struct netlink_callback *cb); + int (*done)(struct netlink_callback *cb); + }; + }; + const struct nla_policy *policy; + unsigned int maxattr; + u8 cmd; + u8 internal_flags; + u8 flags; + u8 validate; +}; + /** * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage @@ -190,7 +242,7 @@ struct genl_ops { */ struct genl_dumpit_info { const struct genl_family *family; - struct genl_ops op; + struct genl_split_ops op; struct nlattr **attrs; }; diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..ad5714f737be 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1267,7 +1267,8 @@ batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, * * Return: 0 on success or negative error number in case of failure */ -static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int batadv_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); @@ -1332,7 +1333,8 @@ err_put_softif: * @skb: Netlink message with request data * @info: receiver information */ -static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void batadv_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; diff --git a/net/core/devlink.c b/net/core/devlink.c index 2dcf2bcc3527..40fcdded57e6 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -770,7 +770,7 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) #define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) #define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) -static int devlink_nl_pre_doit(const struct genl_ops *ops, +static int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; @@ -828,7 +828,7 @@ unlock: return err; } -static void devlink_nl_post_doit(const struct genl_ops *ops, +static void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 11aa6e8a3098..5a782d1d8fd3 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1620,7 +1620,7 @@ static const struct genl_small_ops dropmon_ops[] = { }, }; -static int net_dm_nl_pre_doit(const struct genl_ops *ops, +static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); @@ -1628,7 +1628,7 @@ static int net_dm_nl_pre_doit(const struct genl_ops *ops, return 0; } -static void net_dm_nl_post_doit(const struct genl_ops *ops, +static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 38c4f3cb010e..b33d1b5eda87 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2157,7 +2157,8 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 #define NL802154_FLAG_NEED_WPAN_DEV 0x10 -static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl802154_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev; @@ -2219,7 +2220,8 @@ static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, return 0; } -static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl802154_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { if (info->user_ptr[1]) { diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0a7a856e9ce0..c66299740c05 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -189,6 +189,51 @@ static int genl_get_cmd(u32 cmd, const struct genl_family *family, return genl_get_cmd_small(cmd, family, op); } +static void +genl_cmd_full_to_split(struct genl_split_ops *op, + const struct genl_family *family, + const struct genl_ops *full, u8 flags) +{ + if (flags & GENL_CMD_CAP_DUMP) { + op->start = full->start; + op->dumpit = full->dumpit; + op->done = full->done; + } else { + op->pre_doit = family->pre_doit; + op->doit = full->doit; + op->post_doit = family->post_doit; + } + + op->policy = full->policy; + op->maxattr = full->maxattr; + + op->cmd = full->cmd; + op->internal_flags = full->internal_flags; + op->flags = full->flags; + op->validate = full->validate; + + /* Make sure flags include the GENL_CMD_CAP_DO / GENL_CMD_CAP_DUMP */ + op->flags |= flags; +} + +static int +genl_get_cmd_split(u32 cmd, u8 flags, const struct genl_family *family, + struct genl_split_ops *op) +{ + struct genl_ops full; + int err; + + err = genl_get_cmd(cmd, family, &full); + if (err) { + memset(op, 0, sizeof(*op)); + return err; + } + + genl_cmd_full_to_split(op, family, &full, flags); + + return 0; +} + static void genl_get_cmd_by_index(unsigned int i, const struct genl_family *family, struct genl_ops *op) @@ -544,7 +589,7 @@ static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { @@ -580,18 +625,19 @@ struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; - const struct genl_ops *ops; + const struct genl_split_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; - const struct genl_ops *ops = ctx->ops; + const struct genl_split_ops *ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; + ops = ctx->ops; if (ops->validate & GENL_DONT_VALIDATE_DUMP) goto no_attrs; @@ -633,7 +679,7 @@ no_attrs: static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_ops *ops = &genl_dumpit_info(cb)->op; + const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); @@ -645,7 +691,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) { @@ -661,7 +707,7 @@ static int genl_lock_done(struct netlink_callback *cb) static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) @@ -675,7 +721,7 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; @@ -721,7 +767,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; @@ -747,16 +793,16 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); - if (family->pre_doit) { - err = family->pre_doit(ops, skb, &info); + if (ops->pre_doit) { + err = ops->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); - if (family->post_doit) - family->post_doit(ops, skb, &info); + if (ops->post_doit) + ops->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); @@ -801,8 +847,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); - struct genl_ops op; + struct genl_split_ops op; int hdrlen; + u8 flags; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) @@ -815,7 +862,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (genl_header_check(family, nlh, hdr, extack)) return -EINVAL; - if (genl_get_cmd(hdr->cmd, family, &op)) + flags = (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP ? + GENL_CMD_CAP_DUMP : GENL_CMD_CAP_DO; + if (genl_get_cmd_split(hdr->cmd, flags, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && @@ -826,7 +875,7 @@ static int genl_family_rcv_msg(const struct genl_family *family, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) + if (flags & GENL_CMD_CAP_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 148f66edb015..1ad0326ff4dc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16140,7 +16140,8 @@ static u32 nl80211_internal_flags[] = { #undef SELECTOR }; -static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl80211_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = NULL; @@ -16241,7 +16242,8 @@ out_unlock: return err; } -static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl80211_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { u32 internal_flags = nl80211_internal_flags[ops->internal_flags]; -- cgit v1.2.3 From b8fd60c36a44351f773432e24efd8bb92f8ba0c6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Nov 2022 12:13:42 -0700 Subject: genetlink: allow families to use split ops directly Let families to hook in the new split ops. They are more flexible and should not be much larger than full ops. Each split op is 40B while full op is 48B. Devlink for example has 54 dos and 19 dumps, 2 of the dumps do not have a do -> 56 full commands = 2688B. Split ops would have taken 2920B, so 9% more space while allowing individual per/post doit and per-type policies. Signed-off-by: Jakub Kicinski Reviewed-by: Jacob Keller Signed-off-by: David S. Miller --- include/net/genetlink.h | 5 ++ net/netlink/genetlink.c | 170 ++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 149 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 4be7989c451b..d21210709f84 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -46,6 +46,9 @@ struct genl_info; * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family + * @split_ops: the split do/dump form of operation definition + * @n_split_ops: number of entries in @split_ops, not that with split do/dump + * ops the number of entries is not the same as number of commands * * Attribute policies (the combination of @policy and @maxattr fields) * can be attached at the family level or at the operation level. @@ -63,6 +66,7 @@ struct genl_family { u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; + u8 n_split_ops; u8 n_mcgrps; u8 resv_start_op; const struct nla_policy *policy; @@ -74,6 +78,7 @@ struct genl_family { struct genl_info *info); const struct genl_ops * ops; const struct genl_small_ops *small_ops; + const struct genl_split_ops *split_ops; const struct genl_multicast_group *mcgrps; struct module *module; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 0a4f1470f442..90b0feb5eb73 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -101,6 +101,17 @@ genl_op_fill_in_reject_policy(const struct genl_family *family, op->maxattr = 1; } +static void +genl_op_fill_in_reject_policy_split(const struct genl_family *family, + struct genl_split_ops *op) +{ + if (op->policy) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); @@ -118,6 +129,16 @@ static const struct genl_family *genl_family_find_byname(char *name) return NULL; } +struct genl_op_iter { + const struct genl_family *family; + struct genl_split_ops doit; + struct genl_split_ops dumpit; + int cmd_idx; + int entry_idx; + u32 cmd; + u8 flags; +}; + static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) { @@ -176,6 +197,50 @@ static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, return -ENOENT; } +static void genl_op_from_split(struct genl_op_iter *iter) +{ + const struct genl_family *family = iter->family; + int i, cnt = 0; + + i = iter->entry_idx - family->n_ops - family->n_small_ops; + + if (family->split_ops[i + cnt].flags & GENL_CMD_CAP_DO) { + iter->doit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->doit); + cnt++; + } else { + memset(&iter->doit, 0, sizeof(iter->doit)); + } + + if (i + cnt < family->n_split_ops && + family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) { + iter->dumpit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->dumpit); + cnt++; + } else { + memset(&iter->dumpit, 0, sizeof(iter->dumpit)); + } + + WARN_ON(!cnt); + iter->entry_idx += cnt; +} + +static int +genl_get_cmd_split(u32 cmd, u8 flag, const struct genl_family *family, + struct genl_split_ops *op) +{ + int i; + + for (i = 0; i < family->n_split_ops; i++) + if (family->split_ops[i].cmd == cmd && + family->split_ops[i].flags & flag) { + *op = family->split_ops[i]; + return 0; + } + + return -ENOENT; +} + static int genl_cmd_full_to_split(struct genl_split_ops *op, const struct genl_family *family, @@ -227,50 +292,60 @@ genl_get_cmd(u32 cmd, u8 flags, const struct genl_family *family, err = genl_get_cmd_full(cmd, family, &full); if (err == -ENOENT) err = genl_get_cmd_small(cmd, family, &full); - if (err) { - memset(op, 0, sizeof(*op)); - return err; - } + /* Found one of legacy forms */ + if (err == 0) + return genl_cmd_full_to_split(op, family, &full, flags); - return genl_cmd_full_to_split(op, family, &full, flags); + err = genl_get_cmd_split(cmd, flags, family, op); + if (err) + memset(op, 0, sizeof(*op)); + return err; } -struct genl_op_iter { - const struct genl_family *family; - struct genl_split_ops doit; - struct genl_split_ops dumpit; - int i; - u32 cmd; - u8 flags; -}; - static bool genl_op_iter_init(const struct genl_family *family, struct genl_op_iter *iter) { iter->family = family; - iter->i = 0; + iter->cmd_idx = 0; + iter->entry_idx = 0; iter->flags = 0; - return iter->family->n_ops + iter->family->n_small_ops; + return iter->family->n_ops + + iter->family->n_small_ops + + iter->family->n_split_ops; } static bool genl_op_iter_next(struct genl_op_iter *iter) { const struct genl_family *family = iter->family; + bool legacy_op = true; struct genl_ops op; - if (iter->i < family->n_ops) - genl_op_from_full(family, iter->i, &op); - else if (iter->i < family->n_ops + family->n_small_ops) - genl_op_from_small(family, iter->i - family->n_ops, &op); - else + if (iter->entry_idx < family->n_ops) { + genl_op_from_full(family, iter->entry_idx, &op); + } else if (iter->entry_idx < family->n_ops + family->n_small_ops) { + genl_op_from_small(family, iter->entry_idx - family->n_ops, + &op); + } else if (iter->entry_idx < + family->n_ops + family->n_small_ops + family->n_split_ops) { + legacy_op = false; + /* updates entry_idx */ + genl_op_from_split(iter); + } else { return false; + } - iter->i++; + iter->cmd_idx++; - genl_cmd_full_to_split(&iter->doit, family, &op, GENL_CMD_CAP_DO); - genl_cmd_full_to_split(&iter->dumpit, family, &op, GENL_CMD_CAP_DUMP); + if (legacy_op) { + iter->entry_idx++; + + genl_cmd_full_to_split(&iter->doit, family, + &op, GENL_CMD_CAP_DO); + genl_cmd_full_to_split(&iter->dumpit, family, + &op, GENL_CMD_CAP_DUMP); + } iter->cmd = iter->doit.cmd | iter->dumpit.cmd; iter->flags = iter->doit.flags | iter->dumpit.flags; @@ -286,7 +361,7 @@ genl_op_iter_copy(struct genl_op_iter *dst, struct genl_op_iter *src) static unsigned int genl_op_iter_idx(struct genl_op_iter *iter) { - return iter->i; + return iter->cmd_idx; } static int genl_allocate_reserve_groups(int n_groups, int *first_id) @@ -454,12 +529,22 @@ static void genl_unregister_mc_groups(const struct genl_family *family) } } +static bool genl_split_op_check(const struct genl_split_ops *op) +{ + if (WARN_ON(hweight8(op->flags & (GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP)) != 1)) + return true; + return false; +} + static int genl_validate_ops(const struct genl_family *family) { struct genl_op_iter i, j; + unsigned int s; if (WARN_ON(family->n_ops && !family->ops) || - WARN_ON(family->n_small_ops && !family->small_ops)) + WARN_ON(family->n_small_ops && !family->small_ops) || + WARN_ON(family->n_split_ops && !family->split_ops)) return -EINVAL; for (genl_op_iter_init(family, &i); genl_op_iter_next(&i); ) { @@ -477,6 +562,39 @@ static int genl_validate_ops(const struct genl_family *family) } } + if (family->n_split_ops) { + if (genl_split_op_check(&family->split_ops[0])) + return -EINVAL; + } + + for (s = 1; s < family->n_split_ops; s++) { + const struct genl_split_ops *a, *b; + + a = &family->split_ops[s - 1]; + b = &family->split_ops[s]; + + if (genl_split_op_check(b)) + return -EINVAL; + + /* Check sort order */ + if (a->cmd < b->cmd) + continue; + + if (a->internal_flags != b->internal_flags || + ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP))) { + WARN_ON(1); + return -EINVAL; + } + + if ((a->flags & GENL_CMD_CAP_DO) && + (b->flags & GENL_CMD_CAP_DUMP)) + continue; + + WARN_ON(1); + return -EINVAL; + } + return 0; } -- cgit v1.2.3 From e1f4ecab19338ec7079830e8700e4869f991fd45 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 4 Nov 2022 17:13:01 +0000 Subject: net: remove explicit phylink_generic_validate() references Virtually all conventional network drivers are now converted to use phylink_generic_validate() - only DSA drivers and fman_memac remain, so lets remove the necessity for network drivers to explicitly set this member, and default to phylink_generic_validate() when unset. This is possible as .validate must currently be set. Any remaining instances that have not been addressed by this patch can be fixed up later. Signed-off-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/E1or0FZ-001tRa-DI@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/altera/altera_tse_main.c | 1 - drivers/net/ethernet/atheros/ag71xx.c | 1 - drivers/net/ethernet/cadence/macb_main.c | 1 - drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c | 1 - drivers/net/ethernet/freescale/enetc/enetc_pf.c | 1 - drivers/net/ethernet/freescale/fman/fman_dtsec.c | 1 - drivers/net/ethernet/freescale/fman/fman_tgec.c | 1 - drivers/net/ethernet/marvell/mvneta.c | 1 - drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 - drivers/net/ethernet/marvell/prestera/prestera_main.c | 1 - drivers/net/ethernet/mediatek/mtk_eth_soc.c | 1 - drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c | 1 - drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c | 1 - drivers/net/ethernet/mscc/ocelot_net.c | 1 - drivers/net/ethernet/renesas/rswitch.c | 1 - drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 - drivers/net/ethernet/ti/am65-cpsw-nuss.c | 1 - drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 1 - drivers/net/phy/phylink.c | 5 ++++- drivers/net/usb/asix_devices.c | 1 - include/linux/phylink.h | 5 +++++ 21 files changed, 9 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7633b227b2ca..28b5cae60eb5 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -1095,7 +1095,6 @@ static struct phylink_pcs *alt_tse_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops alt_tse_phylink_ops = { - .validate = phylink_generic_validate, .mac_an_restart = alt_tse_mac_an_restart, .mac_config = alt_tse_mac_config, .mac_link_down = alt_tse_mac_link_down, diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index cc932b3cf873..a5de1bd8538c 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1086,7 +1086,6 @@ static void ag71xx_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ag71xx_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = ag71xx_mac_config, .mac_link_down = ag71xx_mac_link_down, .mac_link_up = ag71xx_mac_link_up, diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4f63f1ba3161..5d618814bb12 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -742,7 +742,6 @@ static struct phylink_pcs *macb_mac_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops macb_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = macb_mac_select_pcs, .mac_config = macb_mac_config, .mac_link_down = macb_mac_link_down, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 2bbab28f763d..51c9da8e1be2 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -236,7 +236,6 @@ static void dpaa2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = dpaa2_mac_select_pcs, .mac_config = dpaa2_mac_config, .mac_link_up = dpaa2_mac_link_up, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index bdf94335ee99..9f6c4f5c0a6c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1111,7 +1111,6 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops enetc_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = enetc_pl_mac_select_pcs, .mac_config = enetc_pl_mac_config, .mac_link_up = enetc_pl_mac_link_up, diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 3c87820ca202..d00bae15a901 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -986,7 +986,6 @@ static void dtsec_link_down(struct phylink_config *config, unsigned int mode, } static const struct phylink_mac_ops dtsec_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = dtsec_select_pcs, .mac_config = dtsec_mac_config, .mac_link_up = dtsec_link_up, diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index c265b7f19a4d..c2261d26db5b 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -469,7 +469,6 @@ static void tgec_link_down(struct phylink_config *config, unsigned int mode, } static const struct phylink_mac_ops tgec_mac_ops = { - .validate = phylink_generic_validate, .mac_config = tgec_mac_config, .mac_link_up = tgec_link_up, .mac_link_down = tgec_link_down, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 05ff3c58087e..c2cb98d24f5c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4228,7 +4228,6 @@ static void mvneta_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mvneta_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvneta_mac_select_pcs, .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 116e53172072..d98f7e9a480e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6603,7 +6603,6 @@ static void mvpp2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops mvpp2_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, .mac_config = mvpp2_mac_config, diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index edbdda8f958d..f8deaee84398 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -360,7 +360,6 @@ static void prestera_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_mac_ops prestera_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = prestera_mac_select_pcs, .mac_config = prestera_mac_config, .mac_link_down = prestera_mac_link_down, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 789268b15106..1cf76fd7afbc 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -653,7 +653,6 @@ static void mtk_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mtk_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mtk_mac_select_pcs, .mac_pcs_get_state = mtk_mac_pcs_get_state, .mac_config = mtk_mac_config, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index f9579a2ae676..c5f9803e6e63 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -124,7 +124,6 @@ static void lan966x_pcs_aneg_restart(struct phylink_pcs *pcs) } const struct phylink_mac_ops lan966x_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = lan966x_phylink_mac_select, .mac_config = lan966x_phylink_mac_config, .mac_prepare = lan966x_phylink_mac_prepare, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 830da0e5ff27..bb97d27a1da4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -138,7 +138,6 @@ const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { }; const struct phylink_mac_ops sparx5_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = sparx5_phylink_mac_select_pcs, .mac_config = sparx5_phylink_mac_config, .mac_link_down = sparx5_phylink_mac_link_down, diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index f50dada2bb8e..ca4bde861397 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1727,7 +1727,6 @@ static void vsc7514_phylink_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ocelot_phylink_ops = { - .validate = phylink_generic_validate, .mac_config = vsc7514_phylink_mac_config, .mac_link_down = vsc7514_phylink_mac_link_down, .mac_link_up = vsc7514_phylink_mac_link_up, diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index f0168fedfef9..4f7af6393c9e 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1190,7 +1190,6 @@ static void rswitch_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops rswitch_phylink_ops = { - .validate = phylink_generic_validate, .mac_config = rswitch_mac_config, .mac_link_down = rswitch_mac_link_down, .mac_link_up = rswitch_mac_link_up, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8273e6a175c8..2fea8785aaf4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1080,7 +1080,6 @@ static void stmmac_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index c785e01d025f..75429ff0c200 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1520,7 +1520,6 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy } static const struct phylink_mac_ops am65_cpsw_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = am65_cpsw_nuss_mac_config, .mac_link_down = am65_cpsw_nuss_mac_link_down, .mac_link_up = am65_cpsw_nuss_mac_link_up, diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index d082f2b10f4d..3e310b55bce2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1736,7 +1736,6 @@ static void axienet_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops axienet_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = axienet_mac_select_pcs, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 88f60e98b760..25feab1802ee 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -649,7 +649,10 @@ static int phylink_validate_mac_and_pcs(struct phylink *pl, } /* Then validate the link parameters with the MAC */ - pl->mac_ops->validate(pl->config, supported, state); + if (pl->mac_ops->validate) + pl->mac_ops->validate(pl->config, supported, state); + else + phylink_generic_validate(pl->config, supported, state); return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 02941d97d034..0fe3773c5bca 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -773,7 +773,6 @@ static void ax88772_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ax88772_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = ax88772_mac_config, .mac_link_down = ax88772_mac_link_down, .mac_link_up = ax88772_mac_link_up, diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 1df3e5e316e8..c492c26202b5 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -207,6 +207,11 @@ struct phylink_mac_ops { * * If the @state->interface mode is not supported, then the @supported * mask must be cleared. + * + * This member is optional; if not set, the generic validator will be + * used making use of @config->mac_capabilities and + * @config->supported_interfaces to determine which link modes are + * supported. */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); -- cgit v1.2.3 From 9a0f830f80265bd1ef816e1541ac24bee80e9a3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Nov 2022 12:01:25 -0700 Subject: ethtool: linkstate: add a statistic for PHY down events The previous attempt to augment carrier_down (see Link) was not met with much enthusiasm so let's do the simple thing of exposing what some devices already maintain. Add a common ethtool statistic for link going down. Currently users have to maintain per-driver mapping to extract the right stat from the vendor-specific ethtool -S stats. carrier_down does not fit the bill because it counts a lot of software related false positives. Add the statistic to the extended link state API to steer vendors towards implementing all of it. Implement for bnxt and all Linux-controlled PHYs. mlx5 and (possibly) enic also have a counter for this but I leave the implementation to their maintainers. Link: https://lore.kernel.org/r/20220520004500.2250674-1-kuba@kernel.org Reviewed-by: Florian Fainelli Reviewed-by: Michael Chan Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20221104190125.684910-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- Documentation/networking/ethtool-netlink.rst | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 15 ++++++++++++++ drivers/net/phy/phy.c | 1 + include/linux/ethtool.h | 17 ++++++++++++++++ include/linux/phy.h | 3 +++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/linkstate.c | 24 ++++++++++++++++++++++- 7 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d578b8bcd8a4..bede24ef44fd 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -491,6 +491,7 @@ Kernel response contents: ``ETHTOOL_A_LINKSTATE_SQI_MAX`` u32 Max support SQI value ``ETHTOOL_A_LINKSTATE_EXT_STATE`` u8 link extended state ``ETHTOOL_A_LINKSTATE_EXT_SUBSTATE`` u8 link extended substate + ``ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT`` u32 count of link down events ==================================== ====== ============================ For most NIC drivers, the value of ``ETHTOOL_A_LINKSTATE_LINK`` returns diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index cc89e5eabcb9..d8f0351df954 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -4112,6 +4112,20 @@ static void bnxt_get_rmon_stats(struct net_device *dev, *ranges = bnxt_rmon_ranges; } +static void bnxt_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats) +{ + struct bnxt *bp = netdev_priv(dev); + u64 *rx; + + if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) + return; + + rx = bp->rx_port_stats_ext.sw_stats; + stats->link_down_events = + *(rx + BNXT_RX_STATS_EXT_OFFSET(link_down_events)); +} + void bnxt_ethtool_free(struct bnxt *bp) { kfree(bp->test_info); @@ -4161,6 +4175,7 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_eeprom = bnxt_get_eeprom, .set_eeprom = bnxt_set_eeprom, .get_link = bnxt_get_link, + .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, .get_module_info = bnxt_get_module_info, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e741d8aebffe..e5b6cb1a77f9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -67,6 +67,7 @@ static void phy_link_down(struct phy_device *phydev) { phydev->phy_link_change(phydev, false); phy_led_trigger_change_speed(phydev); + WRITE_ONCE(phydev->link_down_events, phydev->link_down_events + 1); } static const char *phy_pause_str(struct phy_device *phydev) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 99dc7bfbcd3c..5c51c7fda32a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -125,6 +125,20 @@ struct ethtool_link_ext_state_info { }; }; +struct ethtool_link_ext_stats { + /* Custom Linux statistic for PHY level link down events. + * In a simpler world it should be equal to netdev->carrier_down_count + * unfortunately netdev also counts local reconfigurations which don't + * actually take the physical link down, not to mention NC-SI which, + * if present, keeps the link up regardless of host state. + * This statistic counts when PHY _actually_ went down, or lost link. + * + * Note that we need u64 for ethtool_stats_init() and comparisons + * to ETHTOOL_STAT_NOT_SET, but only u32 is exposed to the user. + */ + u64 link_down_events; +}; + /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table @@ -481,6 +495,7 @@ struct ethtool_module_power_mode_params { * do not attach ext_substate attribute to netlink message). If link_ext_state * and link_ext_substate are unknown, return -ENODATA. If not implemented, * link_ext_state and link_ext_substate will not be sent to userspace. + * @get_link_ext_stats: Read extra link-related counters. * @get_eeprom_len: Read range of EEPROM addresses for validation of * @get_eeprom and @set_eeprom requests. * Returns 0 if device does not support EEPROM access. @@ -652,6 +667,8 @@ struct ethtool_ops { u32 (*get_link)(struct net_device *); int (*get_link_ext_state)(struct net_device *, struct ethtool_link_ext_state_info *); + void (*get_link_ext_stats)(struct net_device *dev, + struct ethtool_link_ext_stats *stats); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); diff --git a/include/linux/phy.h b/include/linux/phy.h index ddf66198f751..9a3752c0c444 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -600,6 +600,7 @@ struct macsec_ops; * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine + * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * @@ -723,6 +724,8 @@ struct phy_device { int pma_extable; + unsigned int link_down_events; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index bb57084ac524..aaf7c6963d61 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -262,6 +262,7 @@ enum { ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ ETHTOOL_A_LINKSTATE_EXT_STATE, /* u8 */ ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, /* u8 */ + ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKSTATE_CNT, diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index fb676f349455..2158c17a0b32 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -13,6 +13,7 @@ struct linkstate_reply_data { int link; int sqi; int sqi_max; + struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; @@ -22,7 +23,7 @@ struct linkstate_reply_data { const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct net_device *dev) @@ -107,6 +108,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, goto out; } + ethtool_stats_init((u64 *)&data->link_stats, + sizeof(data->link_stats) / 8); + + if (req_base->flags & ETHTOOL_FLAG_STATS) { + if (dev->phydev) + data->link_stats.link_down_events = + READ_ONCE(dev->phydev->link_down_events); + + if (dev->ethtool_ops->get_link_ext_stats) + dev->ethtool_ops->get_link_ext_stats(dev, + &data->link_stats); + } + ret = 0; out: ethnl_ops_complete(dev); @@ -134,6 +148,9 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + len += nla_total_size(sizeof(u32)); + return len; } @@ -166,6 +183,11 @@ static int linkstate_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, + data->link_stats.link_down_events)) + return -EMSGSIZE; + return 0; } -- cgit v1.2.3 From ca71277f36e0781db663aedeb5fc1e26e7c144c4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 6 Nov 2022 15:34:14 -0500 Subject: net: move the ct helper function to nf_conntrack_helper for ovs and tc Move ovs_ct_helper from openvswitch to nf_conntrack_helper and rename as nf_ct_helper so that it can be used in TC act_ct in the next patch. Note that it also adds the checks for the family and proto, as in TC act_ct, the packets with correct family and proto are not guaranteed. Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: Paolo Abeni --- include/net/netfilter/nf_conntrack_helper.h | 3 ++ net/netfilter/nf_conntrack_helper.c | 69 +++++++++++++++++++++++++++++ net/openvswitch/conntrack.c | 61 +------------------------ 3 files changed, 73 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 9939c366f720..b6676249eeeb 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -115,6 +115,9 @@ struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags); +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto); + void nf_ct_helper_destroy(struct nf_conn *ct); static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ff737a76052e..88039eedadea 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -26,7 +26,9 @@ #include #include #include +#include #include +#include static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; @@ -240,6 +242,73 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..18f54fa38e8f 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -434,65 +434,6 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* 'skb' should already be pulled to nh_ofs. */ -static int ovs_ct_helper(struct sk_buff *skb, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - enum ip_conntrack_info ctinfo; - unsigned int protoff; - struct nf_conn *ct; - int err; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1038,7 +979,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : info->commit) && - ovs_ct_helper(skb, info->family) != NF_ACCEPT) { + nf_ct_helper(skb, ct, ctinfo, info->family) != NF_ACCEPT) { return -EINVAL; } -- cgit v1.2.3 From f96cba2eb923c025014fe74a50e104b7c5234feb Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 6 Nov 2022 15:34:15 -0500 Subject: net: move add ct helper function to nf_conntrack_helper for ovs and tc Move ovs_ct_add_helper from openvswitch to nf_conntrack_helper and rename as nf_ct_add_helper, so that it can be used in TC act_ct in the next patch. Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: Paolo Abeni --- include/net/netfilter/nf_conntrack_helper.h | 2 ++ net/netfilter/nf_conntrack_helper.c | 31 ++++++++++++++++++++ net/openvswitch/conntrack.c | 44 ++++------------------------- 3 files changed, 38 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index b6676249eeeb..f30b1694b690 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -117,6 +117,8 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, u16 proto); +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp); void nf_ct_helper_destroy(struct nf_conn *ct); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 88039eedadea..48ea6d0264b5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -309,6 +309,37 @@ int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, } EXPORT_SYMBOL_GPL(nf_ct_helper); +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 18f54fa38e8f..4348321856af 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1291,43 +1291,6 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) return 0; } -static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, - const struct sw_flow_key *key, bool log) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, info->family, - key->ip.proto); - if (!helper) { - OVS_NLERR(log, "Unknown helper \"%s\"", name); - return -EINVAL; - } - - help = nf_ct_helper_ext_add(info->ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } - -#if IS_ENABLED(CONFIG_NF_NAT) - if (info->nat) { - ret = nf_nat_helper_try_module_get(name, info->family, - key->ip.proto); - if (ret) { - nf_conntrack_helper_put(helper); - OVS_NLERR(log, "Failed to load \"%s\" NAT helper, error: %d", - name, ret); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - info->helper = helper; - return ret; -} - #if IS_ENABLED(CONFIG_NF_NAT) static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log) @@ -1661,9 +1624,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, } if (helper) { - err = ovs_ct_add_helper(&ct_info, helper, key, log); - if (err) + err = nf_ct_add_helper(ct_info.ct, helper, ct_info.family, + key->ip.proto, ct_info.nat, &ct_info.helper); + if (err) { + OVS_NLERR(log, "Failed to add %s helper %d", helper, err); goto err_free_ct; + } } err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, -- cgit v1.2.3 From a21b06e7319129994f339ed47f512bbe57b77f5b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 6 Nov 2022 15:34:17 -0500 Subject: net: sched: add helper support in act_ct This patch is to add helper support in act_ct for OVS actions=ct(alg=xxx) offloading, which is corresponding to Commit cae3a2627520 ("openvswitch: Allow attaching helpers to ct action") in OVS kernel part. The difference is when adding TC actions family and proto cannot be got from the filter/match, other than helper name in tb[TCA_CT_HELPER_NAME], we also need to send the family in tb[TCA_CT_HELPER_FAMILY] and the proto in tb[TCA_CT_HELPER_PROTO] to kernel. Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: Paolo Abeni --- include/net/tc_act/tc_ct.h | 1 + include/uapi/linux/tc_act/tc_ct.h | 3 ++ net/sched/act_ct.c | 89 +++++++++++++++++++++++++++++++++++---- 3 files changed, 85 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 8250d6f0a462..b24ea2d9400b 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -10,6 +10,7 @@ #include struct tcf_ct_params { + struct nf_conntrack_helper *helper; struct nf_conn *tmpl; u16 zone; diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h index 5fb1d7ac1027..6c5200f0ed38 100644 --- a/include/uapi/linux/tc_act/tc_ct.h +++ b/include/uapi/linux/tc_act/tc_ct.h @@ -22,6 +22,9 @@ enum { TCA_CT_NAT_PORT_MIN, /* be16 */ TCA_CT_NAT_PORT_MAX, /* be16 */ TCA_CT_PAD, + TCA_CT_HELPER_NAME, /* string */ + TCA_CT_HELPER_FAMILY, /* u8 */ + TCA_CT_HELPER_PROTO, /* u8 */ __TCA_CT_MAX }; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 193a460a9d7f..da0b7f665277 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -33,6 +33,7 @@ #include #include #include +#include #include static struct workqueue_struct *act_ct_wq; @@ -655,7 +656,7 @@ struct tc_ct_action_net { /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, - u16 zone_id, bool force) + struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -665,11 +666,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; - if (nf_ct_zone(ct)->id != zone_id) + if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; + if (p->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != p->helper) + goto drop_ct; + } /* Force conntrack entry direction. */ - if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + if ((p->ct_action & TCA_CT_ACT_FORCE) && + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); @@ -832,6 +841,13 @@ out_free: static void tcf_ct_params_free(struct tcf_ct_params *params) { + if (params->helper) { +#if IS_ENABLED(CONFIG_NF_NAT) + if (params->ct_action & TCA_CT_ACT_NAT) + nf_nat_helper_put(params->helper); +#endif + nf_conntrack_helper_put(params->helper); + } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) @@ -1026,13 +1042,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); - bool cached, commit, clear, force; enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; + bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; + bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1043,7 +1060,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; - force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); @@ -1086,7 +1102,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, * actually run the packet through conntrack twice unless it's for a * different zone. */ - cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); + cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; @@ -1119,6 +1135,22 @@ do_nat: if (err != NF_ACCEPT) goto drop; + if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { + err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); + if (err) + goto drop; + add_helper = true; + if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { + if (!nfct_seqadj_ext_add(ct)) + goto drop; + } + } + + if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { + if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) + goto drop; + } + if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); @@ -1167,6 +1199,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, + [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, + [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, + [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, @@ -1256,8 +1291,9 @@ static int tcf_ct_fill_params(struct net *net, { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; + int err, family, proto, len; struct nf_conn *tmpl; - int err; + char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; @@ -1318,10 +1354,31 @@ static int tcf_ct_fill_params(struct net *net, NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); p->tmpl = tmpl; + if (tb[TCA_CT_HELPER_NAME]) { + name = nla_data(tb[TCA_CT_HELPER_NAME]); + len = nla_len(tb[TCA_CT_HELPER_NAME]); + if (len > 16 || name[len - 1] != '\0') { + NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); + err = -EINVAL; + goto err; + } + family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; + proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; + err = nf_ct_add_helper(tmpl, name, family, proto, + p->ct_action & TCA_CT_ACT_NAT, &p->helper); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); + goto err; + } + } + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; +err: + nf_ct_put(p->tmpl); + p->tmpl = NULL; + return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, @@ -1490,6 +1547,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) return 0; } +static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) +{ + if (!helper) + return 0; + + if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || + nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || + nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) + return -1; + + return 0; +} + static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -1542,6 +1612,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; + if (tcf_ct_dump_helper(skb, p->helper)) + goto nla_put_failure; + skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; -- cgit v1.2.3 From c3d96f690a790074b508fe183a41e36a00cd7ddd Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 3 Oct 2022 07:34:21 +0100 Subject: net, proc: Provide PROC_FS=n fallback for proc_create_net_single_write() Provide a CONFIG_PROC_FS=n fallback for proc_create_net_single_write(). Also provide a fallback for proc_create_net_data_write(). Fixes: 564def71765c ("proc: Add a way to make network proc files writable") Reported-by: kernel test robot Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org --- include/linux/proc_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 81d6e4ec2294..0260f5ea98fe 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -208,8 +208,10 @@ static inline void proc_remove(struct proc_dir_entry *de) {} static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } #define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) +#define proc_create_net_data_write(name, mode, parent, ops, write, state_size, data) ({NULL;}) #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) #define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) +#define proc_create_net_single_write(name, mode, parent, show, write, data) ({NULL;}) static inline struct pid *tgid_pidfd_to_pid(const struct file *file) { -- cgit v1.2.3 From 4d843be56ba6a8c0e566afd58775742d9e721505 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Apr 2022 21:48:48 +0100 Subject: rxrpc: Trace setting of the request-ack flag Add a tracepoint to log why the request-ack flag is set on an outgoing DATA packet, allowing debugging as to why. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 36 ++++++++++++++++++++++++++++++++++++ net/rxrpc/output.c | 32 +++++++++++++++++++++++--------- 2 files changed, 59 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d20bf4aa0204..4c501c660123 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -242,6 +242,16 @@ EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +#define rxrpc_req_ack_traces \ + EM(rxrpc_reqack_ack_lost, "ACK-LOST ") \ + EM(rxrpc_reqack_already_on, "ALREADY-ON") \ + EM(rxrpc_reqack_more_rtt, "MORE-RTT ") \ + EM(rxrpc_reqack_no_srv_last, "NO-SRVLAST") \ + EM(rxrpc_reqack_old_rtt, "OLD-RTT ") \ + EM(rxrpc_reqack_retrans, "RETRANS ") \ + EM(rxrpc_reqack_slow_start, "SLOW-START") \ + E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") + /* * Generate enums for tracing information. */ @@ -263,6 +273,7 @@ enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); +enum rxrpc_req_ack_trace { rxrpc_req_ack_traces } __mode(byte); enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); @@ -290,6 +301,7 @@ rxrpc_propose_ack_outcomes; rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; +rxrpc_req_ack_traces; rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_skb_traces; @@ -1395,6 +1407,30 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +TRACE_EVENT(rxrpc_req_ack, + TP_PROTO(unsigned int call_debug_id, rxrpc_seq_t seq, + enum rxrpc_req_ack_trace why), + + TP_ARGS(call_debug_id, seq, why), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(enum rxrpc_req_ack_trace, why ) + ), + + TP_fast_assign( + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->why = why; + ), + + TP_printk("c=%08x q=%08x REQ-%s", + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->why, rxrpc_req_ack_traces)) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 9683617db704..2922c10bd500 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -350,6 +350,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, bool retrans) { + enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; struct rxrpc_wire_header whdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -405,16 +406,29 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) || - rxrpc_to_server(sp) - ) && - (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || - retrans || - call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_count < 3 && sp->hdr.seq & 1) || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), - ktime_get_real()))) + if (whdr.flags & RXRPC_REQUEST_ACK) + why = rxrpc_reqack_already_on; + else if ((whdr.flags & RXRPC_LAST_PACKET) && rxrpc_to_client(sp)) + why = rxrpc_reqack_no_srv_last; + else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) + why = rxrpc_reqack_ack_lost; + else if (retrans) + why = rxrpc_reqack_retrans; + else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) + why = rxrpc_reqack_slow_start; + else if (call->tx_winsize <= 2) + why = rxrpc_reqack_small_txwin; + else if (call->peer->rtt_count < 3 && sp->hdr.seq & 1) + why = rxrpc_reqack_more_rtt; + else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) + why = rxrpc_reqack_old_rtt; + else + goto dont_set_request_ack; + + trace_rxrpc_req_ack(call->debug_id, sp->hdr.seq, why); + if (why != rxrpc_reqack_no_srv_last) whdr.flags |= RXRPC_REQUEST_ACK; +dont_set_request_ack: if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; -- cgit v1.2.3 From 334dfbfc5a7187c99761df2392dd4cc49c453bea Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Apr 2022 00:20:49 +0100 Subject: rxrpc: Split call timer-expiration from call timer-set tracepoint Split the tracepoint for call timer-set to separate out the call timer-expiration event Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 42 +++++++++++++++++++++++++++++++++++++++++- net/rxrpc/call_object.c | 2 +- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4c501c660123..a72f04e3d264 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -133,7 +133,6 @@ #define rxrpc_timer_traces \ EM(rxrpc_timer_begin, "Begin ") \ - EM(rxrpc_timer_expired, "*EXPR*") \ EM(rxrpc_timer_exp_ack, "ExpAck") \ EM(rxrpc_timer_exp_hard, "ExpHrd") \ EM(rxrpc_timer_exp_idle, "ExpIdl") \ @@ -1019,6 +1018,47 @@ TRACE_EVENT(rxrpc_timer, __entry->timer - __entry->now) ); +TRACE_EVENT(rxrpc_timer_expired, + TP_PROTO(struct rxrpc_call *call, unsigned long now), + + TP_ARGS(call, now), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(long, now ) + __field(long, ack_at ) + __field(long, ack_lost_at ) + __field(long, resend_at ) + __field(long, ping_at ) + __field(long, expect_rx_by ) + __field(long, expect_req_by ) + __field(long, expect_term_by ) + __field(long, timer ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->now = now; + __entry->ack_at = call->ack_at; + __entry->ack_lost_at = call->ack_lost_at; + __entry->resend_at = call->resend_at; + __entry->expect_rx_by = call->expect_rx_by; + __entry->expect_req_by = call->expect_req_by; + __entry->expect_term_by = call->expect_term_by; + __entry->timer = call->timer.expires; + ), + + TP_printk("c=%08x EXPIRED a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", + __entry->call, + __entry->ack_at - __entry->now, + __entry->ack_lost_at - __entry->now, + __entry->resend_at - __entry->now, + __entry->expect_rx_by - __entry->now, + __entry->expect_req_by - __entry->now, + __entry->expect_term_by - __entry->now, + __entry->timer - __entry->now) + ); + TRACE_EVENT(rxrpc_rx_lose, TP_PROTO(struct rxrpc_skb_priv *sp), diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6401cdf7a624..a75861a0c477 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -52,7 +52,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (call->state < RXRPC_CALL_COMPLETE) { - trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies); + trace_rxrpc_timer_expired(call, jiffies); __rxrpc_queue_call(call); } else { rxrpc_put_call(call, rxrpc_call_put); -- cgit v1.2.3 From f7fa52421f76309c574f2575701660bc3ea3a705 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 18 Aug 2022 11:52:36 +0100 Subject: rxrpc: Record stats for why the REQUEST-ACK flag is being set Record stats for why the REQUEST-ACK flag is being set. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 2 ++ net/rxrpc/output.c | 1 + net/rxrpc/proc.c | 14 ++++++++++++++ 4 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a72f04e3d264..794523d15321 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -250,6 +250,7 @@ EM(rxrpc_reqack_retrans, "RETRANS ") \ EM(rxrpc_reqack_slow_start, "SLOW-START") \ E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") +/* ---- Must update size of stat_why_req_ack[] if more are added! */ /* * Generate enums for tracing information. diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 8ed707a11d43..436a1e8d0abd 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -107,6 +107,8 @@ struct rxrpc_net { atomic_t stat_tx_ack_skip; atomic_t stat_tx_acks[256]; atomic_t stat_rx_acks[256]; + + atomic_t stat_why_req_ack[8]; }; /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f350d39e3a60..77ed46ab33c5 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -430,6 +430,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else goto dont_set_request_ack; + rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, sp->hdr.seq, why); if (why != rxrpc_reqack_no_srv_last) whdr.flags |= RXRPC_REQUEST_ACK; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 488c403f1d33..9bd357f39c39 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -445,6 +445,18 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING_RESPONSE]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DELAY]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Why-Req-A: acklost=%u already=%u mrtt=%u ortt=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_already_on]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt])); + seq_printf(seq, + "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_retrans]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, "Buffers : txb=%u rxb=%u\n", atomic_read(&rxrpc_n_tx_skbs), @@ -476,5 +488,7 @@ int rxrpc_stats_clear(struct file *file, char *buf, size_t size) atomic_set(&rxnet->stat_tx_ack_skip, 0); memset(&rxnet->stat_tx_acks, 0, sizeof(rxnet->stat_tx_acks)); memset(&rxnet->stat_rx_acks, 0, sizeof(rxnet->stat_rx_acks)); + + memset(&rxnet->stat_why_req_ack, 0, sizeof(rxnet->stat_why_req_ack)); return size; } -- cgit v1.2.3 From 42fb06b391ace2aec5cdb1ebb8ff668f0a34332f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 12 Oct 2022 08:49:29 +0100 Subject: net: Change the udp encap_err_rcv to allow use of {ip,ipv6}_icmp_error() Change the udp encap_err_rcv signature to match ip_icmp_error() and ipv6_icmp_error() so that those can be used from the called function and export them. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: netdev@vger.kernel.org --- include/linux/udp.h | 3 +- include/net/udp_tunnel.h | 4 +-- net/ipv4/ip_sockglue.c | 1 + net/ipv4/udp.c | 3 +- net/ipv6/datagram.c | 1 + net/ipv6/udp.c | 3 +- net/rxrpc/ar-internal.h | 2 +- net/rxrpc/peer_event.c | 71 ++++++++++++------------------------------------ 8 files changed, 28 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/udp.h b/include/linux/udp.h index 5cdba00a904a..dea57aa37df6 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -70,7 +70,8 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); - void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); + void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 72394f441dad..0ca9b7a11baf 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -68,8 +68,8 @@ typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, - struct sk_buff *skb, - unsigned int udp_offset); + struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f16807d3235..9f92ae35bb01 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -433,6 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, } kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 89accc3c8bb3..b859d6c8298e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -784,7 +784,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info, + (u8 *)(uh+1)); goto out; } if (!inet->recverr) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df7e032ce87d..7c7155b48f17 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -334,6 +334,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ipv6_icmp_error); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 297f7cc06044..4bc3fc27ec78 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -631,7 +631,8 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Tunnels don't have an application socket: don't pass errors back */ if (tunnel) { if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, offset); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, + ntohl(info), (u8 *)(uh+1)); goto out; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 436a1e8d0abd..51270b2e49c3 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -998,7 +998,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); +void rxrpc_encap_err_rcv(struct sock *, struct sk_buff *, int, __be16, u32, u8 *); void rxrpc_error_report(struct sock *); void rxrpc_peer_keepalive_worker(struct work_struct *); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 32561e9567fe..d7d6d7aff985 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -29,20 +29,16 @@ static void rxrpc_distribute_error(struct rxrpc_peer *, int, */ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, + __be16 udp_port, struct sockaddr_rxrpc *srx) { struct iphdr *ip, *ip0 = ip_hdr(skb); struct icmphdr *icmp = icmp_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); _enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code); switch (icmp->type) { case ICMP_DEST_UNREACH: - *info = ntohs(icmp->un.frag.mtu); - fallthrough; case ICMP_TIME_EXCEEDED: case ICMP_PARAMETERPROB: ip = (struct iphdr *)((void *)icmp + 8); @@ -63,7 +59,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, case AF_INET: srx->transport_len = sizeof(srx->transport.sin); srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; + srx->transport.sin.sin_port = udp_port; memcpy(&srx->transport.sin.sin_addr, &ip->daddr, sizeof(struct in_addr)); break; @@ -72,7 +68,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, case AF_INET6: srx->transport_len = sizeof(srx->transport.sin); srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; + srx->transport.sin.sin_port = udp_port; memcpy(&srx->transport.sin.sin_addr, &ip->daddr, sizeof(struct in_addr)); break; @@ -93,20 +89,16 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, */ static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, + __be16 udp_port, struct sockaddr_rxrpc *srx) { struct icmp6hdr *icmp = icmp6_hdr(skb); struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); _enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code); switch (icmp->icmp6_type) { case ICMPV6_DEST_UNREACH: - *info = ntohl(icmp->icmp6_mtu); - fallthrough; case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: @@ -129,13 +121,13 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, _net("Rx ICMP6 on v4 sock"); srx->transport_len = sizeof(srx->transport.sin); srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; + srx->transport.sin.sin_port = udp_port; memcpy(&srx->transport.sin.sin_addr, &ip->daddr.s6_addr32[3], sizeof(struct in_addr)); break; case AF_INET6: _net("Rx ICMP6"); - srx->transport.sin.sin_port = udp->dest; + srx->transport.sin.sin_port = udp_port; memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr, sizeof(struct in6_addr)); break; @@ -152,15 +144,13 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, /* * Handle an error received on the local endpoint as a tunnel. */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, - unsigned int udp_offset) +void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) { struct sock_extended_err ee; struct sockaddr_rxrpc srx; struct rxrpc_local *local; struct rxrpc_peer *peer; - unsigned int info = 0; - int err; u8 version = ip_hdr(skb)->version; u8 type = icmp_hdr(skb)->type; u8 code = icmp_hdr(skb)->code; @@ -176,13 +166,11 @@ void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, switch (ip_hdr(skb)->version) { case IPVERSION: - peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset, - &info, &srx); + peer = rxrpc_lookup_peer_icmp_rcu(local, skb, port, &srx); break; #ifdef CONFIG_AF_RXRPC_IPV6 case 6: - peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset, - &info, &srx); + peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, port, &srx); break; #endif default: @@ -201,34 +189,12 @@ void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, switch (version) { case IPVERSION: - switch (type) { - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_FRAG_NEEDED: - rxrpc_adjust_mtu(peer, info); - rcu_read_unlock(); - rxrpc_put_peer(peer); - return; - default: - break; - } - - err = EHOSTUNREACH; - if (code <= NR_ICMP_UNREACH) { - /* Might want to do something different with - * non-fatal errors - */ - //harderr = icmp_err_convert[code].fatal; - err = icmp_err_convert[code].errno; - } - break; - - case ICMP_TIME_EXCEEDED: - err = EHOSTUNREACH; - break; - default: - err = EPROTO; - break; + if (type == ICMP_DEST_UNREACH && + code == ICMP_FRAG_NEEDED) { + rxrpc_adjust_mtu(peer, info); + rcu_read_unlock(); + rxrpc_put_peer(peer); + return; } ee.ee_origin = SO_EE_ORIGIN_ICMP; @@ -239,16 +205,13 @@ void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_AF_RXRPC_IPV6 case 6: - switch (type) { - case ICMPV6_PKT_TOOBIG: + if (type == ICMPV6_PKT_TOOBIG) { rxrpc_adjust_mtu(peer, info); rcu_read_unlock(); rxrpc_put_peer(peer); return; } - icmpv6_err_convert(type, code, &err); - if (err == EACCES) err = EHOSTUNREACH; -- cgit v1.2.3 From 27f699ccb89d65165175525254fec3d9d6b8d500 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 13:52:06 +0100 Subject: rxrpc: Remove the flags from the rxrpc_skb tracepoint Remove the flags from the rxrpc_skb tracepoint as we're no longer going to be using this for the transmission buffers and so marking which are transmission buffers isn't going to be necessary. Note that this also remove the rxrpc skb flag that indicates if this is a transmission buffer and so the count is not updated for the moment. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 9 +++------ net/rxrpc/ar-internal.h | 1 - net/rxrpc/sendmsg.c | 1 - net/rxrpc/skbuff.c | 20 +++++++------------- 4 files changed, 10 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 794523d15321..484c8d032ab8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -461,14 +461,13 @@ TRACE_EVENT(rxrpc_call, TRACE_EVENT(rxrpc_skb, TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op, - int usage, int mod_count, u8 flags, const void *where), + int usage, int mod_count, const void *where), - TP_ARGS(skb, op, usage, mod_count, flags, where), + TP_ARGS(skb, op, usage, mod_count, where), TP_STRUCT__entry( __field(struct sk_buff *, skb ) __field(enum rxrpc_skb_trace, op ) - __field(u8, flags ) __field(int, usage ) __field(int, mod_count ) __field(const void *, where ) @@ -476,16 +475,14 @@ TRACE_EVENT(rxrpc_skb, TP_fast_assign( __entry->skb = skb; - __entry->flags = flags; __entry->op = op; __entry->usage = usage; __entry->mod_count = mod_count; __entry->where = where; ), - TP_printk("s=%p %cx %s u=%d m=%d p=%pSR", + TP_printk("s=%p Rx %s u=%d m=%d p=%pSR", __entry->skb, - __entry->flags & RXRPC_SKB_TX_BUFFER ? 'T' : 'R', __print_symbolic(__entry->op, rxrpc_skb_traces), __entry->usage, __entry->mod_count, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ba0ee5d1c723..92f20b6c23ca 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,7 +198,6 @@ struct rxrpc_skb_priv { u8 nr_subpackets; /* Number of subpackets */ u8 rx_flags; /* Received packet flags */ #define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ -#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ union { int remain; /* amount of space remaining for next write */ diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index ad6f2cd08916..b2d28aa12e10 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -363,7 +363,6 @@ reload: goto maybe_error; sp = rxrpc_skb(skb); - sp->rx_flags |= RXRPC_SKB_TX_BUFFER; rxrpc_new_skb(skb, rxrpc_skb_new); _debug("ALLOC SEND %p", skb); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 580a5acffee7..0c827d5bb2b8 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,8 +14,7 @@ #include #include "ar-internal.h" -#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) -#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -24,8 +23,7 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } /* @@ -36,8 +34,7 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } } @@ -48,8 +45,7 @@ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); skb_get(skb); } @@ -60,7 +56,7 @@ void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, 0, here); + trace_rxrpc_skb(skb, op, 0, n, here); } /* @@ -72,8 +68,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -88,8 +83,7 @@ void rxrpc_purge_queue(struct sk_buff_head *list) while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + refcount_read(&skb->users), n, here); kfree_skb(skb); } } -- cgit v1.2.3 From 02a1935640f8f8539b8f2dbd6eeb539de93b2ce4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Apr 2022 21:16:32 +0100 Subject: rxrpc: Define rxrpc_txbuf struct to carry data to be transmitted Define a struct, rxrpc_txbuf, to carry data to be transmitted instead of a socket buffer so that it can be placed onto multiple queues at once. This also allows the data buffer to be in the same allocation as the internal data. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 45 +++++++++++++++++++ net/rxrpc/Makefile | 1 + net/rxrpc/ar-internal.h | 53 +++++++++++++++++++++++ net/rxrpc/proc.c | 3 +- net/rxrpc/txbuf.c | 100 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 201 insertions(+), 1 deletion(-) create mode 100644 net/rxrpc/txbuf.c (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 484c8d032ab8..47b157b1d32b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -252,6 +252,18 @@ E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") /* ---- Must update size of stat_why_req_ack[] if more are added! */ +#define rxrpc_txbuf_traces \ + EM(rxrpc_txbuf_alloc_ack, "ALLOC ACK ") \ + EM(rxrpc_txbuf_alloc_data, "ALLOC DATA ") \ + EM(rxrpc_txbuf_free, "FREE ") \ + EM(rxrpc_txbuf_get_trans, "GET TRANS ") \ + EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ + EM(rxrpc_txbuf_put_cleaned, "PUT CLEANED") \ + EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ + EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ + EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ + E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") + /* * Generate enums for tracing information. */ @@ -280,6 +292,7 @@ enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); +enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -308,6 +321,7 @@ rxrpc_skb_traces; rxrpc_timer_traces; rxrpc_transmit_traces; rxrpc_tx_points; +rxrpc_txbuf_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -1469,6 +1483,37 @@ TRACE_EVENT(rxrpc_req_ack, __print_symbolic(__entry->why, rxrpc_req_ack_traces)) ); +TRACE_EVENT(rxrpc_txbuf, + TP_PROTO(unsigned int debug_id, + unsigned int call_debug_id, rxrpc_seq_t seq, + int ref, enum rxrpc_txbuf_trace what), + + TP_ARGS(debug_id, call_debug_id, seq, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(int, ref ) + __field(enum rxrpc_txbuf_trace, what ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("B=%08x c=%08x q=%08x %s r=%d", + __entry->debug_id, + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->what, rxrpc_txbuf_traces), + __entry->ref) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index b11281bed2a4..fdeba488fc6e 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -30,6 +30,7 @@ rxrpc-y := \ sendmsg.o \ server_key.o \ skbuff.o \ + txbuf.o \ utils.o rxrpc-$(CONFIG_PROC_FS) += proc.o diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 282cb986f8a7..49e90614d5e5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -29,6 +29,7 @@ struct rxrpc_crypt { struct key_preparsed_payload; struct rxrpc_connection; +struct rxrpc_txbuf; /* * Mark applied to socket buffers in skb->mark. skb->priority is used @@ -759,6 +760,48 @@ struct rxrpc_send_params { bool upgrade; /* If the connection is upgradeable */ }; +/* + * Buffer of data to be output as a packet. + */ +struct rxrpc_txbuf { + struct rcu_head rcu; + struct list_head call_link; /* Link in call->tx_queue */ + struct list_head tx_link; /* Link in live Enc queue or Tx queue */ + struct rxrpc_call *call; /* Call to which belongs */ + ktime_t last_sent; /* Time at which last transmitted */ + refcount_t ref; + rxrpc_seq_t seq; /* Sequence number of this packet */ + unsigned int call_debug_id; + unsigned int debug_id; + unsigned int len; /* Amount of data in buffer */ + unsigned int space; /* Remaining data space */ + unsigned int offset; /* Offset of fill point */ + unsigned long flags; +#define RXRPC_TXBUF_ACKED 0 /* Set if ACK'd */ +#define RXRPC_TXBUF_NACKED 1 /* Set if NAK'd */ +#define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ +#define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ + struct { + /* The packet for encrypting and DMA'ing. We align it such + * that data[] aligns correctly for any crypto blocksize. + */ + u8 pad[64 - sizeof(struct rxrpc_wire_header)]; + struct rxrpc_wire_header wire; /* Network-ready header */ + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + } __aligned(64); +}; + +static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) +{ + return txb->wire.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) +{ + return !rxrpc_sending_to_server(txb); +} + #include /* @@ -1125,6 +1168,16 @@ static inline int __init rxrpc_sysctl_init(void) { return 0; } static inline void rxrpc_sysctl_exit(void) {} #endif +/* + * txbuf.c + */ +extern atomic_t rxrpc_nr_txbuf; +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp); +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); + /* * utils.c */ diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 9bd357f39c39..3877afd23598 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -458,7 +458,8 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, - "Buffers : txb=%u rxb=%u\n", + "Buffers : txb=%u,%u rxb=%u\n", + atomic_read(&rxrpc_nr_txbuf), atomic_read(&rxrpc_n_tx_skbs), atomic_read(&rxrpc_n_rx_skbs)); return 0; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c new file mode 100644 index 000000000000..66d922ad65d0 --- /dev/null +++ b/net/rxrpc/txbuf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* RxRPC Tx data buffering. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include "ar-internal.h" + +static atomic_t rxrpc_txbuf_debug_ids; +atomic_t rxrpc_nr_txbuf; + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp) +{ + struct rxrpc_txbuf *txb; + + txb = kmalloc(sizeof(*txb), gfp); + if (txb) { + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call = call; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = sizeof(txb->data); + txb->len = 0; + txb->offset = 0; + txb->flags = 0; + txb->seq = call->tx_top + 1; + txb->wire.epoch = htonl(call->conn->proto.epoch); + txb->wire.cid = htonl(call->cid); + txb->wire.callNumber = htonl(call->call_id); + txb->wire.seq = htonl(txb->seq); + txb->wire.type = packet_type; + txb->wire.flags = call->conn->out_clientflag; + txb->wire.userStatus = 0; + txb->wire.securityIndex = call->security_ix; + txb->wire._rsvd = 0; + txb->wire.serviceId = htons(call->service_id); + + trace_rxrpc_txbuf(txb->debug_id, + txb->call_debug_id, txb->seq, 1, + packet_type == RXRPC_PACKET_TYPE_DATA ? + rxrpc_txbuf_alloc_data : + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); + } + + return txb; +} + +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r; + + __refcount_inc(&txb->ref, &r); + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r + 1, what); +} + +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r = refcount_read(&txb->ref); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); +} + +static void rxrpc_free_txbuf(struct rcu_head *rcu) +{ + struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, + rxrpc_txbuf_free); + kfree(txb); + atomic_dec(&rxrpc_nr_txbuf); +} + +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + unsigned int debug_id, call_debug_id; + rxrpc_seq_t seq; + bool dead; + int r; + + if (txb) { + debug_id = txb->debug_id; + call_debug_id = txb->call_debug_id; + seq = txb->seq; + dead = __refcount_dec_and_test(&txb->ref, &r); + trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); + if (dead) + call_rcu(&txb->rcu, rxrpc_free_txbuf); + } +} -- cgit v1.2.3 From 72f0c6fb057971864fe4d42b289b8e6ede836ef1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:13 +0000 Subject: rxrpc: Allocate ACK records at proposal and queue for transmission Allocate rxrpc_txbuf records for ACKs and put onto a queue for the transmitter thread to dispatch. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 47 ++++++++--- net/rxrpc/ar-internal.h | 21 +++-- net/rxrpc/call_accept.c | 5 +- net/rxrpc/call_event.c | 189 ++++++++++++++++++++++++------------------- net/rxrpc/input.c | 89 +++++++++----------- net/rxrpc/local_object.c | 7 ++ net/rxrpc/output.c | 157 +++++++++++++++++------------------ net/rxrpc/recvmsg.c | 33 +++----- net/rxrpc/sendmsg.c | 4 +- net/rxrpc/txbuf.c | 1 + 10 files changed, 285 insertions(+), 268 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 47b157b1d32b..1597ff7ad97e 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -34,7 +34,8 @@ EM(rxrpc_local_new, "NEW") \ EM(rxrpc_local_processing, "PRO") \ EM(rxrpc_local_put, "PUT") \ - E_(rxrpc_local_queued, "QUE") + EM(rxrpc_local_queued, "QUE") \ + E_(rxrpc_local_tx_ack, "TAK") #define rxrpc_peer_traces \ EM(rxrpc_peer_got, "GOT") \ @@ -258,7 +259,9 @@ EM(rxrpc_txbuf_free, "FREE ") \ EM(rxrpc_txbuf_get_trans, "GET TRANS ") \ EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ + EM(rxrpc_txbuf_put_ack_tx, "PUT ACK TX ") \ EM(rxrpc_txbuf_put_cleaned, "PUT CLEANED") \ + EM(rxrpc_txbuf_put_nomem, "PUT NOMEM ") \ EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ @@ -1095,19 +1098,16 @@ TRACE_EVENT(rxrpc_rx_lose, TRACE_EVENT(rxrpc_propose_ack, TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, - u8 ack_reason, rxrpc_serial_t serial, bool immediate, - bool background, enum rxrpc_propose_ack_outcome outcome), + u8 ack_reason, rxrpc_serial_t serial, + enum rxrpc_propose_ack_outcome outcome), - TP_ARGS(call, why, ack_reason, serial, immediate, background, - outcome), + TP_ARGS(call, why, ack_reason, serial, outcome), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_propose_ack_trace, why ) __field(rxrpc_serial_t, serial ) __field(u8, ack_reason ) - __field(bool, immediate ) - __field(bool, background ) __field(enum rxrpc_propose_ack_outcome, outcome ) ), @@ -1116,21 +1116,44 @@ TRACE_EVENT(rxrpc_propose_ack, __entry->why = why; __entry->serial = serial; __entry->ack_reason = ack_reason; - __entry->immediate = immediate; - __entry->background = background; __entry->outcome = outcome; ), - TP_printk("c=%08x %s %s r=%08x i=%u b=%u%s", + TP_printk("c=%08x %s %s r=%08x%s", __entry->call, __print_symbolic(__entry->why, rxrpc_propose_ack_traces), __print_symbolic(__entry->ack_reason, rxrpc_ack_names), __entry->serial, - __entry->immediate, - __entry->background, __print_symbolic(__entry->outcome, rxrpc_propose_ack_outcomes)) ); +TRACE_EVENT(rxrpc_send_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial), + + TP_ARGS(call, why, ack_reason, serial), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + ), + + TP_printk("c=%08x %s %s r=%08x", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial) + ); + TRACE_EVENT(rxrpc_retransmit, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, s64 expiry), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 49e90614d5e5..802a8f372af2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -292,6 +292,8 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; + struct list_head ack_tx_queue; /* List of ACKs that need sending */ + spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ @@ -520,10 +522,8 @@ enum rxrpc_call_flag { * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ACK, /* need to generate ACK */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_PING, /* Ping send required */ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ }; @@ -782,13 +782,20 @@ struct rxrpc_txbuf { #define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ #define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ #define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ + u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ struct { /* The packet for encrypting and DMA'ing. We align it such * that data[] aligns correctly for any crypto blocksize. */ u8 pad[64 - sizeof(struct rxrpc_wire_header)]; struct rxrpc_wire_header wire; /* Network-ready header */ - u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + union { + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + struct { + struct rxrpc_ackpacket ack; + u8 acks[0]; + }; + }; } __aligned(64); }; @@ -824,8 +831,10 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, - enum rxrpc_propose_ack_trace); +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why); +void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1030,7 +1039,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); +void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); void rxrpc_reject_packets(struct rxrpc_local *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 99e10eea3732..d8db277d5ebe 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -248,9 +248,8 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) if (call->peer->rtt_count < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); + rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ack_ping_for_params); } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 70f70a0393f7..67b54ad914a1 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -20,46 +20,39 @@ /* * Propose a PING ACK be sent. */ -static void rxrpc_propose_ping(struct rxrpc_call *call, - bool immediate, bool background) +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why) { - if (immediate) { - if (background && - !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; + unsigned long now = jiffies; + unsigned long ping_at = now + rxrpc_idle_ack_delay; - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - } + spin_lock_bh(&call->lock); + + if (time_before(ping_at, call->ping_at)) { + rxrpc_inc_stat(call->rxnet, stat_tx_acks[RXRPC_ACK_PING]); + WRITE_ONCE(call->ping_at, ping_at); + rxrpc_reduce_call_timer(call, ping_at, now, + rxrpc_timer_set_for_ping); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial, + rxrpc_propose_ack_use); } + + spin_unlock_bh(&call->lock); } /* * propose an ACK be sent */ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) + u32 serial, enum rxrpc_propose_ack_trace why) { enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; + unsigned long now = jiffies, ack_at; s8 prior = rxrpc_ack_priority[ack_reason]; rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - /* Pings are handled specially because we don't want to accidentally - * lose a ping response by subsuming it into a ping. - */ - if (ack_reason == RXRPC_ACK_PING) { - rxrpc_propose_ping(call, immediate, background); - goto trace; - } - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial * numbers, but we don't alter the timeout. */ @@ -71,8 +64,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, outcome = rxrpc_propose_ack_update; call->ackr_serial = serial; } - if (!immediate) - goto trace; } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { call->ackr_reason = ack_reason; call->ackr_serial = serial; @@ -84,8 +75,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, case RXRPC_ACK_REQUESTED: if (rxrpc_requested_ack_delay < expiry) expiry = rxrpc_requested_ack_delay; - if (serial == 1) - immediate = false; break; case RXRPC_ACK_DELAY: @@ -99,52 +88,89 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, break; default: - immediate = true; - break; + WARN_ON(1); + return; } - if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { - _debug("already scheduled"); - } else if (immediate || expiry == 0) { - _debug("immediate ACK %lx", call->events); - if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) && - background) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies, ack_at; - - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + + if (call->peer->srtt_us != 0) + ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); + else + ack_at = expiry; + + ack_at += READ_ONCE(call->tx_backoff); + ack_at += now; + if (time_before(ack_at, call->ack_at)) { + WRITE_ONCE(call->ack_at, ack_at); + rxrpc_reduce_call_timer(call, ack_at, now, + rxrpc_timer_set_for_ack); } -trace: - trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate, - background, outcome); + trace_rxrpc_propose_ack(call, why, ack_reason, serial, outcome); } /* * propose an ACK be sent, locking the call structure */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, +void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, u32 serial, enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, - immediate, background, why); + __rxrpc_propose_ACK(call, ack_reason, serial, why); spin_unlock_bh(&call->lock); } +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_local *local = call->conn->params.local; + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, + in_softirq() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); + if (!txb) { + kleave(" = -ENOMEM"); + return; + } + + txb->ack_why = why; + txb->wire.seq = 0; + txb->wire.type = RXRPC_PACKET_TYPE_ACK; + txb->wire.flags |= RXRPC_SLOW_START_OK; + txb->ack.bufferSpace = 0; + txb->ack.maxSkew = 0; + txb->ack.firstPacket = 0; + txb->ack.previousPacket = 0; + txb->ack.serial = htonl(serial); + txb->ack.reason = ack_reason; + txb->ack.nAcks = 0; + + if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); + return; + } + + spin_lock_bh(&local->ack_tx_lock); + list_add_tail(&txb->tx_link, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + trace_rxrpc_send_ack(call, why, ack_reason, serial); + + if (in_task()) { + rxrpc_transmit_ack_packets(call->peer->local); + } else { + rxrpc_get_local(local); + rxrpc_queue_local(local); + } +} + /* * Handle congestion being detected by the retransmit timeout. */ @@ -230,9 +256,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_ack_packet(call, true, NULL); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); goto out; } @@ -291,9 +316,10 @@ void rxrpc_process_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - rxrpc_serial_t *send_ack; unsigned long now, next, t; unsigned int iterations = 0; + rxrpc_serial_t ackr_serial; + u8 ackr_reason; rxrpc_see_call(call); @@ -342,7 +368,15 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_ACK, &call->events); + spin_lock_bh(&call->lock); + ackr_reason = call->ackr_reason; + ackr_serial = call->ackr_serial; + call->ackr_reason = 0; + call->ackr_serial = 0; + spin_unlock_bh(&call->lock); + if (ackr_reason) + rxrpc_send_ACK(call, ackr_reason, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -356,16 +390,16 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, - rxrpc_propose_ack_ping_for_keepalive); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->ping_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->resend_at); @@ -388,25 +422,10 @@ recheck_state: goto recheck_state; } - send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - send_ack = &call->acks_lost_ping; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) || - send_ack) { - if (call->ackr_reason) { - rxrpc_send_ack_packet(call, false, send_ack); - goto recheck_state; - } - } - - if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { - rxrpc_send_ack_packet(call, true, NULL); - goto recheck_state; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); } if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0cb23ba79e3b..e23f66ef8c06 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -398,8 +398,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) unsigned int j, nr_subpackets, nr_unacked = 0; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false; - u8 ack = 0; + bool jumbo_bad = false; _enter("{%u,%u},{%u,%u}", call->rx_hard_ack, call->rx_top, skb->len, seq0); @@ -447,9 +446,9 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) nr_subpackets = sp->nr_subpackets; if (nr_subpackets > 1) { if (call->nr_jumbo_bad > 3) { - ack = RXRPC_ACK_NOSPACE; - ack_serial = serial; - goto ack; + rxrpc_send_ACK(call, RXRPC_ACK_NOSPACE, serial, + rxrpc_propose_ack_input_data); + goto unlock; } } @@ -459,6 +458,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; bool terminal = (j == nr_subpackets - 1); bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); + bool acked = false; u8 flags, annotation = j; _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", @@ -488,25 +488,22 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); continue; } if (call->rxtx_buffer[ix]) { rxrpc_input_dup_data(call, seq, nr_subpackets > 1, &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - } - immediate_ack = true; + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); continue; } if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, + rxrpc_propose_ack_input_data); if (flags & RXRPC_JUMBO_PACKET) { if (!jumbo_bad) { call->nr_jumbo_bad++; @@ -514,12 +511,13 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } } - goto ack; + goto unlock; } - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; + if (flags & RXRPC_REQUEST_ACK) { + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, + rxrpc_propose_ack_input_data); + acked = true; } if (after(seq0, call->ackr_highest_seq)) @@ -542,11 +540,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) smp_store_release(&call->rx_top, seq); } else if (before(seq, call->rx_top)) { /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; + if (!acked) { + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, + rxrpc_propose_ack_input_data); + acked = true; } - immediate_ack = true; } if (terminal) { @@ -558,14 +556,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) sp = NULL; } - nr_unacked++; - if (last) { set_bit(RXRPC_CALL_RX_LAST, &call->flags); - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); } else { trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); @@ -574,32 +566,30 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (after_eq(seq, call->rx_expect_next)) { if (after(seq, call->rx_expect_next)) { _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, + rxrpc_propose_ack_input_data); + acked = true; } call->rx_expect_next = seq + 1; } - if (!ack) + + if (!acked) { + nr_unacked++; ack_serial = serial; + } } -ack: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2 && !ack) - ack = RXRPC_ACK_IDLE; - - if (ack) - rxrpc_propose_ACK(call, ack, ack_serial, - immediate_ack, true, - rxrpc_propose_ack_input_data); +unlock: + if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, + rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, ack_serial, rxrpc_propose_ack_input_data); trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); -unlock: spin_unlock(&call->input_lock); rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); @@ -893,13 +883,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (buf.ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ping); + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ack); + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably @@ -1011,9 +999,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, - false, true, - rxrpc_propose_ack_ping_for_lost_reply); + rxrpc_propose_ping(call, ack_serial, + rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); out: diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index e95e75e785fb..a178f71e5082 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -97,6 +97,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); + INIT_LIST_HEAD(&local->ack_tx_queue); + spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); @@ -432,6 +434,11 @@ static void rxrpc_local_processor(struct work_struct *work) break; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + again = true; + } + if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); again = true; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 71885d741987..1edbc678e8be 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -16,14 +16,6 @@ #include #include "ar-internal.h" -struct rxrpc_ack_buffer { - struct rxrpc_wire_header whdr; - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - struct rxrpc_ackinfo ackinfo; -}; - extern int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); static ssize_t do_udp_sendmsg(struct socket *sk, struct msghdr *msg, size_t len) @@ -82,22 +74,21 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_ack_buffer *pkt, + struct rxrpc_txbuf *txb, rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top, - u8 reason) + rxrpc_seq_t *_top) { - rxrpc_serial_t serial; + struct rxrpc_ackinfo ackinfo; unsigned int tmp; rxrpc_seq_t hard_ack, top, seq; int ix; u32 mtu, jmax; - u8 *ackp = pkt->acks; + u8 *ackp = txb->acks; tmp = atomic_xchg(&call->ackr_nr_unacked, 0); tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (reason == RXRPC_ACK_DELAY || - reason == RXRPC_ACK_IDLE)) { + if (!tmp && (txb->ack.reason == RXRPC_ACK_DELAY || + txb->ack.reason == RXRPC_ACK_IDLE)) { rxrpc_inc_stat(call->rxnet, stat_tx_ack_skip); return 0; } @@ -105,24 +96,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - serial = call->ackr_serial; hard_ack = READ_ONCE(call->rx_hard_ack); top = smp_load_acquire(&call->rx_top); *_hard_ack = hard_ack; *_top = top; - pkt->ack.bufferSpace = htons(0); - pkt->ack.maxSkew = htons(0); - pkt->ack.firstPacket = htonl(hard_ack + 1); - pkt->ack.previousPacket = htonl(call->ackr_highest_seq); - pkt->ack.serial = htonl(serial); - pkt->ack.reason = reason; - pkt->ack.nAcks = top - hard_ack; - - if (reason == RXRPC_ACK_PING) - pkt->whdr.flags |= RXRPC_REQUEST_ACK; + txb->ack.firstPacket = htonl(hard_ack + 1); + txb->ack.previousPacket = htonl(call->ackr_highest_seq); + txb->ack.nAcks = top - hard_ack; - if (after(top, hard_ack)) { + if (txb->ack.nAcks) { seq = hard_ack + 1; do { ix = seq & RXRPC_RXTX_BUFF_MASK; @@ -137,15 +120,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; - pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - pkt->ackinfo.maxMTU = htonl(mtu); - pkt->ackinfo.rwind = htonl(call->rx_winsize); - pkt->ackinfo.jumbo_max = htonl(jmax); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.maxMTU = htonl(mtu); + ackinfo.rwind = htonl(call->rx_winsize); + ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; - return top - hard_ack + 3; + memcpy(ackp, &ackinfo, sizeof(ackinfo)); + return top - hard_ack + 3 + sizeof(ackinfo); } /* @@ -194,26 +178,21 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, /* * Send an ACK call packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, - rxrpc_serial_t *_serial) +static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; struct rxrpc_ack_buffer *pkt; + struct rxrpc_call *call = txb->call; struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; - u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - conn = call->conn; msg.msg_name = &call->peer->srx.transport; @@ -222,85 +201,93 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, msg.msg_controllen = 0; msg.msg_flags = 0; - pkt->whdr.epoch = htonl(conn->proto.epoch); - pkt->whdr.cid = htonl(call->cid); - pkt->whdr.callNumber = htonl(call->call_id); - pkt->whdr.seq = 0; - pkt->whdr.type = RXRPC_PACKET_TYPE_ACK; - pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag; - pkt->whdr.userStatus = 0; - pkt->whdr.securityIndex = call->security_ix; - pkt->whdr._rsvd = 0; - pkt->whdr.serviceId = htons(call->service_id); + if (txb->ack.reason == RXRPC_ACK_PING) + txb->wire.flags |= RXRPC_REQUEST_ACK; spin_lock_bh(&call->lock); - if (ping) { - reason = RXRPC_ACK_PING; - } else { - reason = call->ackr_reason; - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; - } - call->ackr_reason = 0; - } - n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason); - + n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); spin_unlock_bh(&call->lock); if (n == 0) { kfree(pkt); return 0; } - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; + len = iov[0].iov_len; serial = atomic_inc_return(&conn->serial); - pkt->whdr.serial = htonl(serial); + txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - if (_serial) - *_serial = serial; + ntohl(txb->ack.firstPacket), + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) + call->acks_lost_ping = serial; - if (ping) + if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); else - trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { - if (ret < 0) { + if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_propose_ACK(call, pkt->ack.reason, - ntohl(pkt->ack.serial), - false, true, - rxrpc_propose_ack_retry_tx); - } - rxrpc_set_keepalive(call); } -out: kfree(pkt); return ret; } +/* + * ACK transmitter for a local endpoint. The UDP socket locks around each + * transmission, so we can only transmit one packet at a time, ACK, DATA or + * otherwise. + */ +void rxrpc_transmit_ack_packets(struct rxrpc_local *local) +{ + LIST_HEAD(queue); + int ret; + + trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, + refcount_read(&local->ref), NULL); + + if (list_empty(&local->ack_tx_queue)) + return; + + spin_lock_bh(&local->ack_tx_lock); + list_splice_tail_init(&local->ack_tx_queue, &queue); + spin_unlock_bh(&local->ack_tx_lock); + + while (!list_empty(&queue)) { + struct rxrpc_txbuf *txb = + list_entry(queue.next, struct rxrpc_txbuf, tx_link); + + ret = rxrpc_send_ack_packet(local, txb); + if (ret < 0 && ret != -ECONNRESET) { + spin_lock_bh(&local->ack_tx_lock); + list_splice_init(&queue, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + break; + } + + list_del_init(&txb->tx_link); + rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + } +} + /* * Send an ABORT call packet. */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a378e7a672a8..104dd4a29f05 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -189,7 +189,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, rxrpc_propose_ack_terminal_ack); //rxrpc_send_ack_packet(call, false, NULL); } @@ -206,7 +206,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, rxrpc_propose_ack_processing_op); break; default: @@ -259,12 +259,11 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - true, false, - rxrpc_propose_ack_rotate_rx); - if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) - rxrpc_send_ack_packet(call, false, NULL); + if (atomic_inc_return(&call->ackr_nr_consumed) > 2) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); + } } } @@ -363,10 +362,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; - if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) && - call->ackr_reason) - rxrpc_send_ack_packet(call, false, NULL); - rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; rx_pkt_last = call->rx_pkt_last; @@ -389,6 +384,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (!skb) { trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, rx_pkt_offset, rx_pkt_len, 0); + rxrpc_transmit_ack_packets(call->peer->local); break; } smp_rmb(); @@ -604,6 +600,7 @@ try_again: if (ret == -EAGAIN) ret = 0; + rxrpc_transmit_ack_packets(call->peer->local); if (after(call->rx_top, call->rx_hard_ack) && call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) rxrpc_notify_socket(call); @@ -734,17 +731,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - switch (call->ackr_reason) { - case RXRPC_ACK_IDLE: - break; - case RXRPC_ACK_DELAY: - if (ret != -EAGAIN) - break; - fallthrough; - default: - rxrpc_send_ack_packet(call, false, NULL); - } - + rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index b2d28aa12e10..ef4949259020 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -332,9 +332,7 @@ reload: rxrpc_see_skb(skb, rxrpc_skb_seen); do { - /* Check to see if there's a ping ACK to reply to. */ - if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_ack_packet(call, false, NULL); + rxrpc_transmit_ack_packets(call->peer->local); if (!skb) { size_t remain, bufsize, chunk, offset; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 66d922ad65d0..45a7b48a5e10 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -33,6 +33,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->len = 0; txb->offset = 0; txb->flags = 0; + txb->ack_why = 0; txb->seq = call->tx_top + 1; txb->wire.epoch = htonl(call->conn->proto.epoch); txb->wire.cid = htonl(call->cid); -- cgit v1.2.3 From 530403d9ba1c3f51c721a394f642e56309072295 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:14 +0000 Subject: rxrpc: Clean up ACK handling Clean up the rxrpc_propose_ACK() function. If deferred PING ACK proposal is split out, it's only really needed for deferred DELAY ACKs. All other ACKs, bar terminal IDLE ACK are sent immediately. The deferred IDLE ACK submission can be handled by conversion of a DELAY ACK into an IDLE ACK if there's nothing to be SACK'd. Also, because there's a delay between an ACK being generated and being transmitted, it's possible that other ACKs of the same type will be generated during that interval. Apart from the ACK time and the serial number responded to, most of the ACK body, including window and SACK parameters, are not filled out till the point of transmission - so we can avoid generating a new ACK if there's one pending that will cover the SACK data we need to convey. Therefore, don't propose a new DELAY or IDLE ACK for a call if there's one already pending. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 52 ++++++++++++++++-------- net/rxrpc/ar-internal.h | 10 ++--- net/rxrpc/call_event.c | 95 ++++++++++++-------------------------------- net/rxrpc/call_object.c | 2 +- net/rxrpc/input.c | 8 ++-- net/rxrpc/misc.c | 18 --------- net/rxrpc/output.c | 7 ++++ net/rxrpc/protocol.h | 7 ---- net/rxrpc/recvmsg.c | 14 +++---- net/rxrpc/sendmsg.c | 2 +- net/rxrpc/sysctl.c | 9 ----- 11 files changed, 86 insertions(+), 138 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 1597ff7ad97e..d32e9858c682 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -158,6 +158,7 @@ #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ + EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ EM(rxrpc_propose_ack_ping_for_check_life, "ChkLife") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ @@ -170,11 +171,6 @@ EM(rxrpc_propose_ack_rotate_rx, "RxAck ") \ E_(rxrpc_propose_ack_terminal_ack, "ClTerm ") -#define rxrpc_propose_ack_outcomes \ - EM(rxrpc_propose_ack_subsume, " Subsume") \ - EM(rxrpc_propose_ack_update, " Update") \ - E_(rxrpc_propose_ack_use, " New") - #define rxrpc_congest_modes \ EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ EM(RXRPC_CALL_FAST_RETRANSMIT, "FastReTx ") \ @@ -313,7 +309,6 @@ rxrpc_congest_changes; rxrpc_congest_modes; rxrpc_conn_traces; rxrpc_local_traces; -rxrpc_propose_ack_outcomes; rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; @@ -1012,7 +1007,7 @@ TRACE_EVENT(rxrpc_timer, __entry->call = call->debug_id; __entry->why = why; __entry->now = now; - __entry->ack_at = call->ack_at; + __entry->ack_at = call->delay_ack_at; __entry->ack_lost_at = call->ack_lost_at; __entry->resend_at = call->resend_at; __entry->expect_rx_by = call->expect_rx_by; @@ -1054,7 +1049,7 @@ TRACE_EVENT(rxrpc_timer_expired, TP_fast_assign( __entry->call = call->debug_id; __entry->now = now; - __entry->ack_at = call->ack_at; + __entry->ack_at = call->delay_ack_at; __entry->ack_lost_at = call->ack_lost_at; __entry->resend_at = call->resend_at; __entry->expect_rx_by = call->expect_rx_by; @@ -1098,17 +1093,15 @@ TRACE_EVENT(rxrpc_rx_lose, TRACE_EVENT(rxrpc_propose_ack, TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, - u8 ack_reason, rxrpc_serial_t serial, - enum rxrpc_propose_ack_outcome outcome), + u8 ack_reason, rxrpc_serial_t serial), - TP_ARGS(call, why, ack_reason, serial, outcome), + TP_ARGS(call, why, ack_reason, serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_propose_ack_trace, why ) __field(rxrpc_serial_t, serial ) __field(u8, ack_reason ) - __field(enum rxrpc_propose_ack_outcome, outcome ) ), TP_fast_assign( @@ -1116,15 +1109,13 @@ TRACE_EVENT(rxrpc_propose_ack, __entry->why = why; __entry->serial = serial; __entry->ack_reason = ack_reason; - __entry->outcome = outcome; ), - TP_printk("c=%08x %s %s r=%08x%s", + TP_printk("c=%08x %s %s r=%08x", __entry->call, __print_symbolic(__entry->why, rxrpc_propose_ack_traces), __print_symbolic(__entry->ack_reason, rxrpc_ack_names), - __entry->serial, - __print_symbolic(__entry->outcome, rxrpc_propose_ack_outcomes)) + __entry->serial) ); TRACE_EVENT(rxrpc_send_ack, @@ -1154,6 +1145,35 @@ TRACE_EVENT(rxrpc_send_ack, __entry->serial) ); +TRACE_EVENT(rxrpc_drop_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial, bool nobuf), + + TP_ARGS(call, why, ack_reason, serial, nobuf), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + __field(bool, nobuf ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + __entry->nobuf = nobuf; + ), + + TP_printk("c=%08x %s %s r=%08x nbf=%u", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial, __entry->nobuf) + ); + TRACE_EVENT(rxrpc_retransmit, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, s64 expiry), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 802a8f372af2..5a81545a58d5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -516,6 +516,8 @@ enum rxrpc_call_flag { RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ + RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ + RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ }; /* @@ -582,7 +584,7 @@ struct rxrpc_call { struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ - unsigned long ack_at; /* When deferred ACK needs to happen */ + unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ unsigned long ping_at; /* When next to send a ping */ @@ -834,7 +836,8 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, enum rxrpc_propose_ack_trace); +void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, + enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1016,15 +1019,12 @@ static inline bool __rxrpc_use_local(struct rxrpc_local *local) * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; -extern unsigned long rxrpc_requested_ack_delay; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; -extern const s8 rxrpc_ack_priority[]; - /* * net_ns.c */ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 67b54ad914a1..36f60ac1d95d 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -29,70 +29,29 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, spin_lock_bh(&call->lock); if (time_before(ping_at, call->ping_at)) { - rxrpc_inc_stat(call->rxnet, stat_tx_acks[RXRPC_ACK_PING]); WRITE_ONCE(call->ping_at, ping_at); rxrpc_reduce_call_timer(call, ping_at, now, rxrpc_timer_set_for_ping); - trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial, - rxrpc_propose_ack_use); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); } spin_unlock_bh(&call->lock); } /* - * propose an ACK be sent + * Propose a DELAY ACK be sent in the future. */ -static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, enum rxrpc_propose_ack_trace why) +static void __rxrpc_propose_delay_ACK(struct rxrpc_call *call, + rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { - enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; unsigned long now = jiffies, ack_at; - s8 prior = rxrpc_ack_priority[ack_reason]; - - rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial - * numbers, but we don't alter the timeout. - */ - _debug("prior %u %u vs %u %u", - ack_reason, prior, - call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]); - if (ack_reason == call->ackr_reason) { - if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { - outcome = rxrpc_propose_ack_update; - call->ackr_serial = serial; - } - } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { - call->ackr_reason = ack_reason; - call->ackr_serial = serial; - } else { - outcome = rxrpc_propose_ack_subsume; - } - - switch (ack_reason) { - case RXRPC_ACK_REQUESTED: - if (rxrpc_requested_ack_delay < expiry) - expiry = rxrpc_requested_ack_delay; - break; - - case RXRPC_ACK_DELAY: - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - break; - - case RXRPC_ACK_IDLE: - if (rxrpc_idle_ack_delay < expiry) - expiry = rxrpc_idle_ack_delay; - break; - - default: - WARN_ON(1); - return; - } + call->ackr_serial = serial; + if (rxrpc_soft_ack_delay < expiry) + expiry = rxrpc_soft_ack_delay; if (call->peer->srtt_us != 0) ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); else @@ -100,23 +59,23 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, ack_at += READ_ONCE(call->tx_backoff); ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); + if (time_before(ack_at, call->delay_ack_at)) { + WRITE_ONCE(call->delay_ack_at, ack_at); rxrpc_reduce_call_timer(call, ack_at, now, rxrpc_timer_set_for_ack); } - trace_rxrpc_propose_ack(call, why, ack_reason, serial, outcome); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); } /* - * propose an ACK be sent, locking the call structure + * Propose a DELAY ACK be sent, locking the call structure */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, u32 serial, - enum rxrpc_propose_ack_trace why) +void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, why); + __rxrpc_propose_delay_ACK(call, serial, why); spin_unlock_bh(&call->lock); } @@ -131,6 +90,11 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return; + if (ack_reason == RXRPC_ACK_DELAY && + test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { + trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); + return; + } rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); @@ -319,7 +283,6 @@ void rxrpc_process_call(struct work_struct *work) unsigned long now, next, t; unsigned int iterations = 0; rxrpc_serial_t ackr_serial; - u8 ackr_reason; rxrpc_see_call(call); @@ -364,19 +327,13 @@ recheck_state: set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); } - t = READ_ONCE(call->ack_at); + t = READ_ONCE(call->delay_ack_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - spin_lock_bh(&call->lock); - ackr_reason = call->ackr_reason; - ackr_serial = call->ackr_serial; - call->ackr_reason = 0; - call->ackr_serial = 0; - spin_unlock_bh(&call->lock); - if (ackr_reason) - rxrpc_send_ACK(call, ackr_reason, ackr_serial, - rxrpc_propose_ack_ping_for_lost_ack); + cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + ackr_serial = xchg(&call->ackr_serial, 0); + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -441,7 +398,7 @@ recheck_state: set(call->expect_req_by); set(call->expect_term_by); - set(call->ack_at); + set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8290d94e9233..8f9e88897197 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -222,7 +222,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; - call->ack_at = j; + call->delay_ack_at = j; call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index e23f66ef8c06..4df1bdc4de6c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -299,7 +299,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) now = jiffies; timo = now + MAX_JIFFY_OFFSET; WRITE_ONCE(call->resend_at, timo); - WRITE_ONCE(call->ack_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } @@ -542,7 +542,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) /* Send an immediate ACK if we fill in a hole */ if (!acked) { rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data); + rxrpc_propose_ack_input_data_hole); acked = true; } } @@ -584,8 +584,8 @@ unlock: rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, ack_serial, - rxrpc_propose_ack_input_data); + rxrpc_propose_delay_ACK(call, ack_serial, + rxrpc_propose_ack_input_data); trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index d4144fd86f84..f5f03f27bd6c 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -16,12 +16,6 @@ */ unsigned int rxrpc_max_backlog __read_mostly = 10; -/* - * How long to wait before scheduling ACK generation after seeing a - * packet with RXRPC_REQUEST_ACK set (in jiffies). - */ -unsigned long rxrpc_requested_ack_delay = 1; - /* * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). * @@ -62,15 +56,3 @@ unsigned int rxrpc_rx_mtu = 5692; * sender that we're willing to handle. */ unsigned int rxrpc_rx_jumbo_max = 4; - -const s8 rxrpc_ack_priority[] = { - [0] = 0, - [RXRPC_ACK_DELAY] = 1, - [RXRPC_ACK_REQUESTED] = 2, - [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_DUPLICATE] = 4, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 5, - [RXRPC_ACK_EXCEEDS_WINDOW] = 6, - [RXRPC_ACK_NOSPACE] = 7, - [RXRPC_ACK_PING_RESPONSE] = 8, -}; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 1edbc678e8be..d35657b659ad 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -115,6 +115,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *ackp++ = RXRPC_ACK_TYPE_NACK; seq++; } while (before_eq(seq, top)); + } else if (txb->ack.reason == RXRPC_ACK_DELAY) { + txb->ack.reason = RXRPC_ACK_IDLE; } mtu = conn->params.peer->if_mtu; @@ -204,6 +206,11 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; + if (txb->ack.reason == RXRPC_ACK_DELAY) + clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); + if (txb->ack.reason == RXRPC_ACK_IDLE) + clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + spin_lock_bh(&call->lock); n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); spin_unlock_bh(&call->lock); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index d2cf8e1d218f..f3d4e2700901 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -132,13 +132,6 @@ struct rxrpc_ackpacket { } __packed; -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - /* * ACK packets can have a further piece of information tagged on the end */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 104dd4a29f05..46e784edc0f4 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -188,11 +188,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_terminal_ack); - //rxrpc_send_ack_packet(call, false, NULL); - } + if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); write_lock_bh(&call->state_lock); @@ -206,8 +203,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_processing_op); + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_processing_op); break; default: write_unlock_bh(&call->state_lock); @@ -259,7 +256,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) { + if (atomic_inc_return(&call->ackr_nr_consumed) > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, rxrpc_propose_ack_rotate_rx); rxrpc_transmit_ack_packets(call->peer->local); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index ef4949259020..e32805a49324 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -234,7 +234,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; now = jiffies; - WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 555e0910786b..2bd987364e44 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -26,15 +26,6 @@ static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; */ static struct ctl_table rxrpc_sysctl_table[] = { /* Values measured in milliseconds but used in jiffies */ - { - .procname = "req_ack_delay", - .data = &rxrpc_requested_ack_delay, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, - }, { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, -- cgit v1.2.3 From faf92e8d53f5f03842da25af971a3f0ef88ffba2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 17:22:40 +0100 Subject: rxrpc: Split the rxrpc_recvmsg tracepoint Split the rxrpc_recvmsg tracepoint so that the tracepoints that are about data packet processing (and which have extra pieces of information) are separate from the tracepoint that shows the general flow of recvmsg(). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 24 ++++++++++++++++++++++++ net/rxrpc/recvmsg.c | 37 ++++++++++++++++++------------------- 2 files changed, 42 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d32e9858c682..84464b29e54a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -885,6 +885,30 @@ TRACE_EVENT(rxrpc_receive, ); TRACE_EVENT(rxrpc_recvmsg, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, + int ret), + + TP_ARGS(call, why, ret), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_recvmsg_trace, why ) + __field(int, ret ) + ), + + TP_fast_assign( + __entry->call = call ? call->debug_id : 0; + __entry->why = why; + __entry->ret = ret; + ), + + TP_printk("c=%08x %s ret=%d", + __entry->call, + __print_symbolic(__entry->why, rxrpc_recvmsg_traces), + __entry->ret) + ); + +TRACE_EVENT(rxrpc_recvdata, TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, rxrpc_seq_t seq, unsigned int offset, unsigned int len, int ret), diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 46e784edc0f4..77cde6311559 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,8 +173,8 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, - call->rx_pkt_offset, call->rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, + call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -380,8 +380,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ix = seq & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; if (!skb) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_hole, seq, + rx_pkt_offset, rx_pkt_len, 0); rxrpc_transmit_ack_packets(call->peer->local); break; } @@ -404,15 +404,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, &call->rxtx_annotations[ix], &rx_pkt_offset, &rx_pkt_len, &rx_pkt_last); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, + rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { ret = ret2; goto out; } } else { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, + rx_pkt_offset, rx_pkt_len, 0); } /* We have to handle short, empty and used-up DATA packets. */ @@ -435,8 +435,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } if (rx_pkt_len > 0) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_full, seq, + rx_pkt_offset, rx_pkt_len, 0); ASSERTCMP(*_offset, ==, len); ret = 0; break; @@ -464,8 +464,8 @@ out: call->rx_pkt_last = rx_pkt_last; } done: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, - rx_pkt_offset, rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, + rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); return ret; @@ -488,7 +488,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, DEFINE_WAIT(wait); - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0); if (flags & (MSG_OOB | MSG_TRUNC)) return -EOPNOTSUPP; @@ -525,8 +525,7 @@ try_again: if (list_empty(&rx->recvmsg_q)) { if (signal_pending(current)) goto wait_interrupted; - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, - 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0); timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(&rx->sk), &wait); @@ -545,7 +544,7 @@ try_again: rxrpc_get_call(call, rxrpc_call_got); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); /* We're going to drop the socket lock, so we need to lock the call * against interference by sendmsg. @@ -630,7 +629,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; error_requeue_call: @@ -638,14 +637,14 @@ error_requeue_call: write_lock_bh(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put); } error_no_call: release_sock(&rx->sk); error_trace: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; wait_interrupted: -- cgit v1.2.3 From d4d02d8bb5c412d977af7ea7c7ea91977a6a64dc Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 17:44:39 +0100 Subject: rxrpc: Clone received jumbo subpackets and queue separately Split up received jumbo packets into separate skbuffs by cloning the original skbuff for each subpacket and setting the offset and length of the data in that subpacket in the skbuff's private data. The subpackets are then placed on the recvmsg queue separately. The security class then gets to revise the offset and length to remove its metadata. If we fail to clone a packet, we just drop it and let the peer resend it. The original packet gets used for the final subpacket. This should make it easier to handle parallel decryption of the subpackets. It also simplifies the handling of lost or misordered packets in the queuing/buffering loop as the possibility of overlapping jumbo packets no longer needs to be considered. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 12 +- net/rxrpc/ar-internal.h | 32 +--- net/rxrpc/input.c | 401 ++++++++++++++++++++----------------------- net/rxrpc/insecure.c | 13 +- net/rxrpc/output.c | 2 +- net/rxrpc/protocol.h | 2 +- net/rxrpc/recvmsg.c | 104 ++--------- net/rxrpc/rxkad.c | 96 +++-------- 8 files changed, 245 insertions(+), 417 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 84464b29e54a..03a984e661bc 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -18,6 +18,7 @@ */ #define rxrpc_skb_traces \ EM(rxrpc_skb_cleaned, "CLN") \ + EM(rxrpc_skb_cloned_jumbo, "CLJ") \ EM(rxrpc_skb_freed, "FRE") \ EM(rxrpc_skb_got, "GOT") \ EM(rxrpc_skb_lost, "*L*") \ @@ -630,16 +631,15 @@ TRACE_EVENT(rxrpc_transmit, TRACE_EVENT(rxrpc_rx_data, TP_PROTO(unsigned int call, rxrpc_seq_t seq, - rxrpc_serial_t serial, u8 flags, u8 anno), + rxrpc_serial_t serial, u8 flags), - TP_ARGS(call, seq, serial, flags, anno), + TP_ARGS(call, seq, serial, flags), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) __field(rxrpc_serial_t, serial ) __field(u8, flags ) - __field(u8, anno ) ), TP_fast_assign( @@ -647,15 +647,13 @@ TRACE_EVENT(rxrpc_rx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->anno = anno; ), - TP_printk("c=%08x DATA %08x q=%08x fl=%02x a=%02x", + TP_printk("c=%08x DATA %08x q=%08x fl=%02x", __entry->call, __entry->serial, __entry->seq, - __entry->flags, - __entry->anno) + __entry->flags) ); TRACE_EVENT(rxrpc_rx_ack, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5a81545a58d5..e93ed18816b1 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -195,19 +195,14 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - atomic_t nr_ring_pins; /* Number of rxtx ring pins */ - u8 nr_subpackets; /* Number of subpackets */ - u8 rx_flags; /* Received packet flags */ -#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ - union { - int remain; /* amount of space remaining for next write */ - - /* List of requested ACKs on subpackets */ - unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / - BITS_PER_LONG]; - }; - - struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ + u16 remain; + u16 offset; /* Offset of data */ + u16 len; /* Length of data */ + u8 rx_flags; /* Received packet flags */ + u8 flags; +#define RXRPC_RX_VERIFIED 0x01 + + struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) @@ -252,16 +247,11 @@ struct rxrpc_security { int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); /* verify the security on a received packet */ - int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, - unsigned int, unsigned int, rxrpc_seq_t, u16); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); - /* Locate the data in a received packet that has been verified. */ - void (*locate_data)(struct rxrpc_call *, struct sk_buff *, - unsigned int *, unsigned int *); - /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -628,7 +618,6 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ - bool rx_pkt_last; /* Current recvmsg packet is last */ /* Rx/Tx circular buffer, depending on phase. * @@ -652,8 +641,6 @@ struct rxrpc_call { #define RXRPC_TX_ANNO_LAST 0x04 #define RXRPC_TX_ANNO_RESENT 0x08 -#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ -#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. */ @@ -681,7 +668,6 @@ struct rxrpc_call { rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ u8 tx_winsize; /* Maximum size of Tx window */ - u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ spinlock_t input_lock; /* Lock for packet input to this call */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 4df1bdc4de6c..0e7545ed0128 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -313,78 +313,178 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) } /* - * Scan a data packet to validate its structure and to work out how many - * subpackets it contains. - * - * A jumbo packet is a collection of consecutive packets glued together with - * little headers between that indicate how to change the initial header for - * each subpacket. - * - * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but - * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any - * size. + * Process a DATA packet, adding the packet to the Rx ring. The caller's + * packet ref must be passed on or discarded. */ -static bool rxrpc_validate_data(struct sk_buff *skb) +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len; - u8 flags = sp->hdr.flags; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq = sp->hdr.seq, hard_ack; + unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + bool acked = false; - for (;;) { - if (flags & RXRPC_REQUEST_ACK) - __set_bit(sp->nr_subpackets, sp->rx_req_ack); - sp->nr_subpackets++; + rxrpc_inc_stat(call->rxnet, stat_rx_data); + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); + if (sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - if (!(flags & RXRPC_JUMBO_PACKET)) - break; + hard_ack = READ_ONCE(call->rx_hard_ack); - if (len - offset < RXRPC_JUMBO_SUBPKTLEN) - goto protocol_error; - if (flags & RXRPC_LAST_PACKET) - goto protocol_error; - offset += RXRPC_JUMBO_DATALEN; - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - goto protocol_error; - offset += sizeof(struct rxrpc_jumbo_header); + _proto("Rx DATA %%%u { #%x l=%u }", serial, seq, last); + + if (last) { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto out; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto out; + } } - if (flags & RXRPC_LAST_PACKET) - sp->rx_flags |= RXRPC_SKB_INCL_LAST; - return true; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); -protocol_error: - return false; + if (before_eq(seq, hard_ack)) { + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (call->rxtx_buffer[ix]) { + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (after(seq, hard_ack + call->rx_winsize)) { + rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (sp->hdr.flags & RXRPC_REQUEST_ACK) { + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, + rxrpc_propose_ack_input_data); + acked = true; + } + + if (after(seq, call->ackr_highest_seq)) + call->ackr_highest_seq = seq; + + /* Queue the packet. We use a couple of memory barriers here as need + * to make sure that rx_top is perceived to be set after the buffer + * pointer and that the buffer pointer is set after the annotation and + * the skb data. + * + * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() + * and also rxrpc_fill_out_ack(). + */ + call->rxtx_annotations[ix] = 1; + smp_wmb(); + call->rxtx_buffer[ix] = skb; + if (after(seq, call->rx_top)) { + smp_store_release(&call->rx_top, seq); + } else if (before(seq, call->rx_top)) { + /* Send an immediate ACK if we fill in a hole */ + if (!acked) { + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, + rxrpc_propose_ack_input_data_hole); + acked = true; + } + } + + /* From this point on, we're not allowed to touch the packet any longer + * as its ref now belongs to the Rx ring. + */ + skb = NULL; + sp = NULL; + + if (last) { + set_bit(RXRPC_CALL_RX_LAST, &call->flags); + trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + } else { + trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + } + + if (after_eq(seq, call->rx_expect_next)) { + if (after(seq, call->rx_expect_next)) { + _net("OOS %u > %u", seq, call->rx_expect_next); + rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, + rxrpc_propose_ack_input_data); + acked = true; + } + call->rx_expect_next = seq + 1; + } + +out: + if (!acked && + atomic_inc_return(&call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_input_data); + else + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_input_data); + + trace_rxrpc_notify_socket(call->debug_id, serial); + rxrpc_notify_socket(call); + + rxrpc_free_skb(skb, rxrpc_skb_freed); + _leave(" [queued]"); } /* - * Handle reception of a duplicate packet. - * - * We have to take care to avoid an attack here whereby we're given a series of - * jumbograms, each with a sequence number one before the preceding one and - * filled up to maximum UDP size. If they never send us the first packet in - * the sequence, they can cause us to have to hold on to around 2MiB of kernel - * space until the call times out. - * - * We limit the space usage by only accepting three duplicate jumbo packets per - * call. After that, we tell the other side we're no longer accepting jumbos - * (that information is encoded in the ACK packet). + * Split a jumbo packet and file the bits separately. */ -static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - bool is_jumbo, bool *_jumbo_bad) +static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb) { - /* Discard normal packets that are duplicates. */ - if (is_jumbo) - return; + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; + struct sk_buff *jskb; + unsigned int offset = sizeof(struct rxrpc_wire_header); + unsigned int len = skb->len - offset; - /* Skip jumbo subpackets that are duplicates. When we've had three or - * more partially duplicate jumbo packets, we refuse to take any more - * jumbos for this call. - */ - if (!*_jumbo_bad) { - call->nr_jumbo_bad++; - *_jumbo_bad = true; + while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { + if (len < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (sp->hdr.flags & RXRPC_LAST_PACKET) + goto protocol_error; + if (skb_copy_bits(skb, offset + RXRPC_JUMBO_DATALEN, + &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; + + jskb = skb_clone(skb, GFP_ATOMIC); + if (!jskb) { + kdebug("couldn't clone"); + return false; + } + rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + jsp = rxrpc_skb(jskb); + jsp->offset = offset; + jsp->len = RXRPC_JUMBO_DATALEN; + rxrpc_input_data_one(call, jskb); + + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + sp->hdr.seq++; + sp->hdr.serial++; + offset += RXRPC_JUMBO_SUBPKTLEN; + len -= RXRPC_JUMBO_SUBPKTLEN; } + + sp->offset = offset; + sp->len = len; + rxrpc_input_data_one(call, skb); + return true; + +protocol_error: + return false; } /* @@ -395,16 +495,14 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int j, nr_subpackets, nr_unacked = 0; - rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; - rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool jumbo_bad = false; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq0 = sp->hdr.seq; _enter("{%u,%u},{%u,%u}", call->rx_hard_ack, call->rx_top, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x n=%u }", - sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); + _proto("Rx DATA %%%u { #%u f=%02x }", + sp->hdr.serial, seq0, sp->hdr.flags); state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { @@ -412,6 +510,24 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) return; } + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + return; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + skb = nskb; + rxrpc_new_skb(skb, rxrpc_skb_unshared); + sp = rxrpc_skb(skb); + } + } + if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -425,12 +541,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } } - rxrpc_inc_stat(call->rxnet, stat_rx_data); - if (sp->hdr.flags & RXRPC_REQUEST_ACK) - rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); - if (sp->hdr.flags & RXRPC_JUMBO_PACKET) - rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - spin_lock(&call->input_lock); /* Received data implicitly ACKs all of the request packets we sent @@ -439,154 +549,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto unlock; - - hard_ack = READ_ONCE(call->rx_hard_ack); - - nr_subpackets = sp->nr_subpackets; - if (nr_subpackets > 1) { - if (call->nr_jumbo_bad > 3) { - rxrpc_send_ACK(call, RXRPC_ACK_NOSPACE, serial, - rxrpc_propose_ack_input_data); - goto unlock; - } - } - - for (j = 0; j < nr_subpackets; j++) { - rxrpc_serial_t serial = sp->hdr.serial + j; - rxrpc_seq_t seq = seq0 + j; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; - bool terminal = (j == nr_subpackets - 1); - bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); - bool acked = false; - u8 flags, annotation = j; - - _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", - j, serial, seq, terminal, last); - - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; - } - } - - flags = 0; - if (last) - flags |= RXRPC_LAST_PACKET; - if (!terminal) - flags |= RXRPC_JUMBO_PACKET; - if (test_bit(j, sp->rx_req_ack)) - flags |= RXRPC_REQUEST_ACK; - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - - if (before_eq(seq, hard_ack)) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - continue; - } - - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, nr_subpackets > 1, - &jumbo_bad); - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - continue; - } - - if (after(seq, hard_ack + call->rx_winsize)) { - rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, - rxrpc_propose_ack_input_data); - if (flags & RXRPC_JUMBO_PACKET) { - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; - } - } - - goto unlock; - } - - if (flags & RXRPC_REQUEST_ACK) { - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, - rxrpc_propose_ack_input_data); - acked = true; - } - - if (after(seq0, call->ackr_highest_seq)) - call->ackr_highest_seq = seq0; - - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - if (!terminal) - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!acked) { - rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data_hole); - acked = true; - } - } - - if (terminal) { - /* From this point on, we're not allowed to touch the - * packet any longer as its ref now belongs to the Rx - * ring. - */ - skb = NULL; - sp = NULL; - } - - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } - - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, - rxrpc_propose_ack_input_data); - acked = true; - } - call->rx_expect_next = seq + 1; - } + goto out; - if (!acked) { - nr_unacked++; - ack_serial = serial; - } + if (!rxrpc_input_split_jumbo(call, skb)) { + rxrpc_proto_abort("VLD", call, sp->hdr.seq); + goto out; } + skb = NULL; -unlock: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2) - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_delay_ACK(call, ack_serial, - rxrpc_propose_ack_input_data); - +out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); @@ -1288,8 +1259,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (!rxrpc_validate_data(skb)) - goto bad_message; /* Unshare the packet so that it can be modified for in-place * decryption. @@ -1403,7 +1372,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) trace_rxrpc_rx_data(chan->call_debug_id, sp->hdr.seq, sp->hdr.serial, - sp->hdr.flags, 0); + sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); goto out; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 9aae99d67833..fd68f0e3af27 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -31,10 +31,11 @@ static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, return 0; } -static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + sp->flags |= RXRPC_RX_VERIFIED; return 0; } @@ -42,11 +43,6 @@ static void none_free_call_crypto(struct rxrpc_call *call) { } -static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ -} - static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) @@ -95,7 +91,6 @@ const struct rxrpc_security rxrpc_no_security = { .how_much_data = none_how_much_data, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, - .locate_data = none_locate_data, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index d35657b659ad..f7bb792c8aa1 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -121,7 +121,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; - jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; + jmax = rxrpc_rx_jumbo_max; ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(call->rx_winsize); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index f3d4e2700901..6760cb99c6d6 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -84,7 +84,7 @@ struct rxrpc_jumbo_header { __be16 _rsvd; /* reserved */ __be16 cksum; /* kerberos security checksum */ }; -}; +} __packed; #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 77cde6311559..401aae687830 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -222,7 +222,6 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; bool last = false; - u8 subpacket; int ix; _enter("%d", call->debug_id); @@ -237,11 +236,9 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_see_skb(skb, rxrpc_skb_rotated); sp = rxrpc_skb(skb); - subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - serial = sp->hdr.serial + subpacket; + serial = sp->hdr.serial; - if (subpacket == sp->nr_subpackets - 1 && - sp->rx_flags & RXRPC_SKB_INCL_LAST) + if (sp->hdr.flags & RXRPC_LAST_PACKET) last = true; call->rxtx_buffer[ix] = NULL; @@ -266,80 +263,15 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) } /* - * Decrypt and verify a (sub)packet. The packet's length may be changed due to - * padding, but if this is the case, the packet length will be resident in the - * socket buffer. Note that we can't modify the master skb info as the skb may - * be the home to multiple subpackets. + * Decrypt and verify a DATA packet. */ -static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - u8 annotation, - unsigned int offset, unsigned int len) +static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_seq_t seq = sp->hdr.seq; - u16 cksum = sp->hdr.cksum; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - _enter(""); - - /* For all but the head jumbo subpacket, the security checksum is in a - * jumbo header immediately prior to the data. - */ - if (subpacket > 0) { - __be16 tmp; - if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) - BUG(); - cksum = ntohs(tmp); - seq += subpacket; - } - - return call->security->verify_packet(call, skb, offset, len, - seq, cksum); -} - -/* - * Locate the data within a packet. This is complicated by: - * - * (1) An skb may contain a jumbo packet - so we have to find the appropriate - * subpacket. - * - * (2) The (sub)packets may be encrypted and, if so, the encrypted portion - * contains an extra header which includes the true length of the data, - * excluding any encrypted padding. - */ -static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - u8 *_annotation, - unsigned int *_offset, unsigned int *_len, - bool *_last) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len; - bool last = false; - int ret; - u8 annotation = *_annotation; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - - /* Locate the subpacket */ - offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; - len = skb->len - offset; - if (subpacket < sp->nr_subpackets - 1) - len = RXRPC_JUMBO_DATALEN; - else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; - - if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { - ret = rxrpc_verify_packet(call, skb, annotation, offset, len); - if (ret < 0) - return ret; - *_annotation |= RXRPC_RX_ANNO_VERIFIED; - } - - *_offset = offset; - *_len = len; - *_last = last; - call->security->locate_data(call, skb, _offset, _len); - return 0; + if (sp->flags & RXRPC_RX_VERIFIED) + return 0; + return call->security->verify_packet(call, skb); } /* @@ -356,13 +288,11 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; - bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { seq = call->rx_hard_ack; @@ -391,7 +321,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (!(flags & MSG_PEEK)) { serial = sp->hdr.serial; - serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; trace_rxrpc_receive(call, rxrpc_receive_front, serial, seq); } @@ -400,10 +329,9 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, sock_recv_timestamp(msg, sock->sk, skb); if (rx_pkt_offset == 0) { - ret2 = rxrpc_locate_data(call, skb, - &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len, - &rx_pkt_last); + ret2 = rxrpc_verify_data(call, skb); + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { @@ -443,16 +371,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } /* The whole packet has been transferred. */ - if (!(flags & MSG_PEEK)) - rxrpc_rotate_rx_window(call); + if (sp->hdr.flags & RXRPC_LAST_PACKET) + ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; - if (rx_pkt_last) { - ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); - ret = 1; - goto out; - } + if (!(flags & MSG_PEEK)) + rxrpc_rotate_rx_window(call); seq++; } @@ -461,7 +386,6 @@ out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; - call->rx_pkt_last = rx_pkt_last; } done: trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 78fa0524156f..b19937776aa9 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -439,11 +439,11 @@ static int rxkad_secure_packet(struct rxrpc_call *call, * decrypt partial encryption on a packet (level 1 security) */ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { struct rxkad_level1_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; bool aborted; @@ -453,9 +453,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, _enter(""); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); + RXKADSEALEDINCON); goto protocol_error; } @@ -463,7 +463,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, * directly into the target buffer. */ sg_init_table(sg, ARRAY_SIZE(sg)); - ret = skb_to_sgvec(skb, sg, offset, 8); + ret = skb_to_sgvec(skb, sg, sp->offset, 8); if (unlikely(ret < 0)) return ret; @@ -477,12 +477,13 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -496,11 +497,12 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -515,12 +517,12 @@ protocol_error: * wholly decrypt a packet (level 2 security) */ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; bool aborted; @@ -528,9 +530,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, u16 check; int nsg, ret; - _enter(",{%d}", skb->len); + _enter(",{%d}", sp->len); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", RXKADSEALEDINCON); goto protocol_error; @@ -550,7 +552,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } sg_init_table(sg, nsg); - ret = skb_to_sgvec(skb, sg, offset, len); + ret = skb_to_sgvec(skb, sg, sp->offset, sp->len); if (unlikely(ret < 0)) { if (sg != _sg) kfree(sg); @@ -563,19 +565,20 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, len, iv.x); + skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -589,12 +592,13 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -609,16 +613,15 @@ nomem: } /* - * Verify the security on a received packet or subpacket (if part of a - * jumbo packet). + * Verify the security on a received packet and the subpackets therein. */ -static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + rxrpc_seq_t seq = sp->hdr.seq; bool aborted; u16 cksum; u32 x, y; @@ -654,7 +657,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ - if (cksum != expected_cksum) { + if (cksum != sp->hdr.cksum) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", RXKADSEALEDINCON); goto protocol_error; @@ -664,9 +667,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, case RXRPC_SECURITY_PLAIN: return 0; case RXRPC_SECURITY_AUTH: - return rxkad_verify_packet_1(call, skb, offset, len, seq, req); + return rxkad_verify_packet_1(call, skb, seq, req); case RXRPC_SECURITY_ENCRYPT: - return rxkad_verify_packet_2(call, skb, offset, len, seq, req); + return rxkad_verify_packet_2(call, skb, seq, req); default: return -ENOANO; } @@ -677,52 +680,6 @@ protocol_error: return -EPROTO; } -/* - * Locate the data contained in a packet that was partially encrypted. - */ -static void rxkad_locate_data_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level1_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in a packet that was completely encrypted. - */ -static void rxkad_locate_data_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level2_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in an already decrypted packet. - */ -static void rxkad_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - switch (call->conn->params.security_level) { - case RXRPC_SECURITY_AUTH: - rxkad_locate_data_1(call, skb, _offset, _len); - return; - case RXRPC_SECURITY_ENCRYPT: - rxkad_locate_data_2(call, skb, _offset, _len); - return; - default: - return; - } -} - /* * issue a challenge */ @@ -1397,7 +1354,6 @@ const struct rxrpc_security rxkad = { .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, - .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, -- cgit v1.2.3 From 5d7edbc9231ec6b60f9c5b7e7980e9a1cd92e6bb Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 27 Aug 2022 14:27:56 +0100 Subject: rxrpc: Get rid of the Rx ring Get rid of the Rx ring and replace it with a pair of queues instead. One queue gets the packets that are in-sequence and are ready for processing by recvmsg(); the other queue gets the out-of-sequence packets for addition to the first queue as the holes get filled. The annotation ring is removed and replaced with a SACK table. The SACK table has the bits set that correspond exactly to the sequence number of the packet being acked. The SACK ring is copied when an ACK packet is being assembled and rotated so that the first ACK is in byte 0. Flow control handling is altered so that packets that are moved to the in-sequence queue are hard-ACK'd even before they're consumed - and then the Rx window size in the ACK packet (rsize) is shrunk down to compensate (even going to 0 if the window is full). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 19 ++-- net/rxrpc/ar-internal.h | 29 +++--- net/rxrpc/call_object.c | 7 +- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 213 ++++++++++++++++++++++++++----------------- net/rxrpc/misc.c | 5 +- net/rxrpc/output.c | 95 +++++++++++-------- net/rxrpc/proc.c | 7 +- net/rxrpc/recvmsg.c | 117 ++++++++++++------------ net/rxrpc/rxkad.c | 1 - net/rxrpc/sysctl.c | 2 +- 11 files changed, 290 insertions(+), 207 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 03a984e661bc..284a1560b0a8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -104,7 +104,12 @@ EM(rxrpc_receive_incoming, "INC") \ EM(rxrpc_receive_queue, "QUE") \ EM(rxrpc_receive_queue_last, "QLS") \ - E_(rxrpc_receive_rotate, "ROT") + EM(rxrpc_receive_queue_oos, "QUO") \ + EM(rxrpc_receive_queue_oos_last, "QOL") \ + EM(rxrpc_receive_oos, "OOS") \ + EM(rxrpc_receive_oos_last, "OSL") \ + EM(rxrpc_receive_rotate, "ROT") \ + E_(rxrpc_receive_rotate_last, "RLS") #define rxrpc_recvmsg_traces \ EM(rxrpc_recvmsg_cont, "CONT") \ @@ -860,8 +865,7 @@ TRACE_EVENT(rxrpc_receive, __field(enum rxrpc_receive_trace, why ) __field(rxrpc_serial_t, serial ) __field(rxrpc_seq_t, seq ) - __field(rxrpc_seq_t, hard_ack ) - __field(rxrpc_seq_t, top ) + __field(u64, window ) ), TP_fast_assign( @@ -869,8 +873,7 @@ TRACE_EVENT(rxrpc_receive, __entry->why = why; __entry->serial = serial; __entry->seq = seq; - __entry->hard_ack = call->rx_hard_ack; - __entry->top = call->rx_top; + __entry->window = atomic64_read(&call->ackr_window); ), TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x", @@ -878,8 +881,8 @@ TRACE_EVENT(rxrpc_receive, __print_symbolic(__entry->why, rxrpc_receive_traces), __entry->serial, __entry->seq, - __entry->hard_ack, - __entry->top) + lower_32_bits(__entry->window), + upper_32_bits(__entry->window)) ); TRACE_EVENT(rxrpc_recvmsg, @@ -1459,7 +1462,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->rx_hard_ack; + __entry->rx_seq = call->rx_highest_seq; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e93ed18816b1..c6c5bb3d3688 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,7 +198,6 @@ struct rxrpc_skb_priv { u16 remain; u16 offset; /* Offset of data */ u16 len; /* Length of data */ - u8 rx_flags; /* Received packet flags */ u8 flags; #define RXRPC_RX_VERIFIED 0x01 @@ -644,8 +643,20 @@ struct rxrpc_call { rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. */ + + /* Transmitted data tracking. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ + u8 tx_winsize; /* Maximum size of Tx window */ + + /* Received data tracking */ + struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ + struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ + + rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ + rxrpc_seq_t rx_consumed; /* Highest packet consumed */ + rxrpc_serial_t rx_serial; /* Highest serial received for this call */ + u8 rx_winsize; /* Size of Rx window */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -660,23 +671,19 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not - * consumed packet follows this. - */ - rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ - rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ - rxrpc_serial_t rx_serial; /* Highest serial received for this call */ - u8 rx_winsize; /* Size of Rx window */ - u8 tx_winsize; /* Maximum size of Tx window */ - spinlock_t input_lock; /* Lock for packet input to this call */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - rxrpc_seq_t ackr_highest_seq; /* Higest sequence number received */ + atomic64_t ackr_window; /* Base (in LSW) and top (in MSW) of SACK window */ atomic_t ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ + struct { +#define RXRPC_SACK_SIZE 256 + /* SACK table for soft-acked packets */ + u8 ackr_sack_table[RXRPC_SACK_SIZE]; + } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8f9e88897197..4d8601c6a32d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -155,6 +155,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + skb_queue_head_init(&call->recvmsg_queue); + skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); @@ -165,13 +167,12 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; + atomic64_set(&call->ackr_window, 0x100000001ULL); memset(&call->sock_node, 0xed, sizeof(call->sock_node)); - /* Leave space in the ring to handle a maxed-out jumbo packet */ call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->rx_expect_next = 1; call->cong_cwnd = 2; call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; @@ -519,6 +520,8 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); call->rxtx_buffer[i] = NULL; } + skb_queue_purge(&call->recvmsg_queue); + skb_queue_purge(&call->rx_oos_queue); } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 22089e37e97f..f7ea71ae6159 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -175,7 +175,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: - chan->last_seq = call->rx_hard_ack; + chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0e7545ed0128..947e7196e2be 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -312,18 +312,43 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) return rxrpc_end_tx_phase(call, true, "ETD"); } +static void rxrpc_input_update_ack_window(struct rxrpc_call *call, + rxrpc_seq_t window, rxrpc_seq_t wtop) +{ + atomic64_set_release(&call->ackr_window, ((u64)wtop) << 32 | window); +} + /* - * Process a DATA packet, adding the packet to the Rx ring. The caller's - * packet ref must be passed on or discarded. + * Push a DATA packet onto the Rx queue. + */ +static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, + rxrpc_seq_t window, rxrpc_seq_t wtop, + enum rxrpc_receive_trace why) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + + __skb_queue_tail(&call->recvmsg_queue, skb); + rxrpc_input_update_ack_window(call, window, wtop); + + trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); +} + +/* + * Process a DATA packet. */ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sk_buff *oos; rxrpc_serial_t serial = sp->hdr.serial; - rxrpc_seq_t seq = sp->hdr.seq, hard_ack; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + u64 win = atomic64_read(&call->ackr_window); + rxrpc_seq_t window = lower_32_bits(win); + rxrpc_seq_t wtop = upper_32_bits(win); + rxrpc_seq_t wlimit = window + call->rx_winsize - 1; + rxrpc_seq_t seq = sp->hdr.seq; bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - bool acked = false; + int ack_reason = -1; rxrpc_inc_stat(call->rxnet, stat_rx_data); if (sp->hdr.flags & RXRPC_REQUEST_ACK) @@ -331,112 +356,135 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (sp->hdr.flags & RXRPC_JUMBO_PACKET) rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - hard_ack = READ_ONCE(call->rx_hard_ack); - - _proto("Rx DATA %%%u { #%x l=%u }", serial, seq, last); - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { + if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq + 1 != wtop) { rxrpc_proto_abort("LSN", call, seq); - goto out; + goto err_free; } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { + after_eq(seq, wtop)) { + pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", + call->debug_id, seq, window, wtop, wlimit); rxrpc_proto_abort("LSA", call, seq); - goto out; + goto err_free; } } + if (after(seq, call->rx_highest_seq)) + call->rx_highest_seq = seq; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); - if (before_eq(seq, hard_ack)) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - goto out; + if (before(seq, window)) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; } - - if (call->rxtx_buffer[ix]) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - goto out; + if (after(seq, wlimit)) { + ack_reason = RXRPC_ACK_EXCEEDS_WINDOW; + goto send_ack; } - if (after(seq, hard_ack + call->rx_winsize)) { - rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, - rxrpc_propose_ack_input_data); - goto out; - } + /* Queue the packet. */ + if (seq == window) { + rxrpc_seq_t reset_from; + bool reset_sack = false; - if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, - rxrpc_propose_ack_input_data); - acked = true; - } + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + ack_reason = RXRPC_ACK_REQUESTED; + /* Send an immediate ACK if we fill in a hole */ + else if (!skb_queue_empty(&call->rx_oos_queue)) + ack_reason = RXRPC_ACK_DELAY; - if (after(seq, call->ackr_highest_seq)) - call->ackr_highest_seq = seq; + window++; + if (after(window, wtop)) + wtop = window; - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - call->rxtx_annotations[ix] = 1; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!acked) { - rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data_hole); - acked = true; + spin_lock(&call->recvmsg_queue.lock); + rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); + skb = NULL; + + while ((oos = skb_peek(&call->rx_oos_queue))) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, window)) + break; + + __skb_unlink(oos, &call->rx_oos_queue); + last = osp->hdr.flags & RXRPC_LAST_PACKET; + seq = osp->hdr.seq; + if (!reset_sack) { + reset_from = seq; + reset_sack = true; + } + + window++; + rxrpc_input_queue_data(call, oos, window, wtop, + rxrpc_receive_queue_oos); } - } - /* From this point on, we're not allowed to touch the packet any longer - * as its ref now belongs to the Rx ring. - */ - skb = NULL; - sp = NULL; + spin_unlock(&call->recvmsg_queue.lock); - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + if (reset_sack) { + do { + call->ackr_sack_table[reset_from % RXRPC_SACK_SIZE] = 0; + } while (reset_from++, before(reset_from, window)); + } } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } + bool keep = false; + + ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; + + if (!call->ackr_sack_table[seq % RXRPC_SACK_SIZE]) { + call->ackr_sack_table[seq % RXRPC_SACK_SIZE] = 1; + keep = 1; + } + + if (after(seq + 1, wtop)) { + wtop = seq + 1; + rxrpc_input_update_ack_window(call, window, wtop); + } + + if (!keep) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + + skb_queue_walk(&call->rx_oos_queue, oos) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, - rxrpc_propose_ack_input_data); - acked = true; + if (after(osp->hdr.seq, seq)) { + __skb_queue_before(&call->rx_oos_queue, oos, skb); + goto oos_queued; + } } - call->rx_expect_next = seq + 1; + + __skb_queue_tail(&call->rx_oos_queue, skb); + oos_queued: + trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, + sp->hdr.serial, sp->hdr.seq); + skb = NULL; } -out: - if (!acked && - atomic_inc_return(&call->ackr_nr_unacked) > 2) - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, +send_ack: + if (ack_reason < 0 && + atomic_inc_return(&call->ackr_nr_unacked) > 2 && + test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + ack_reason = RXRPC_ACK_IDLE; + } else if (ack_reason >= 0) { + set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + } + + if (ack_reason >= 0) + rxrpc_send_ACK(call, ack_reason, serial, rxrpc_propose_ack_input_data); else rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_input_data); - trace_rxrpc_notify_socket(call->debug_id, serial); - rxrpc_notify_socket(call); - +err_free: rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" [queued]"); } /* @@ -498,8 +546,9 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_serial_t serial = sp->hdr.serial; rxrpc_seq_t seq0 = sp->hdr.seq; - _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq0); + _enter("{%llx,%x},{%u,%x}", + atomic64_read(&call->ackr_window), call->rx_highest_seq, + skb->len, seq0); _proto("Rx DATA %%%u { #%u f=%02x }", sp->hdr.serial, seq0, sp->hdr.flags); diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index f5f03f27bd6c..056c428d8bf3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -40,10 +40,7 @@ unsigned long rxrpc_idle_ack_delay = HZ / 2; * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further * packets. */ -unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE; -#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE -#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE -#endif +unsigned int rxrpc_rx_window_size = 255; /* * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f7bb792c8aa1..0a4f37d7b6b5 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -74,47 +74,64 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top) + struct rxrpc_txbuf *txb) { struct rxrpc_ackinfo ackinfo; - unsigned int tmp; - rxrpc_seq_t hard_ack, top, seq; - int ix; + unsigned int qsize; + rxrpc_seq_t window, wtop, wrap_point, ix, first; + int rsize; + u64 wtmp; u32 mtu, jmax; u8 *ackp = txb->acks; + u8 sack_buffer[sizeof(call->ackr_sack_table)] __aligned(8); - tmp = atomic_xchg(&call->ackr_nr_unacked, 0); - tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (txb->ack.reason == RXRPC_ACK_DELAY || - txb->ack.reason == RXRPC_ACK_IDLE)) { - rxrpc_inc_stat(call->rxnet, stat_tx_ack_skip); - return 0; - } - + atomic_set(&call->ackr_nr_unacked, 0); + atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - hard_ack = READ_ONCE(call->rx_hard_ack); - top = smp_load_acquire(&call->rx_top); - *_hard_ack = hard_ack; - *_top = top; - - txb->ack.firstPacket = htonl(hard_ack + 1); - txb->ack.previousPacket = htonl(call->ackr_highest_seq); - txb->ack.nAcks = top - hard_ack; - - if (txb->ack.nAcks) { - seq = hard_ack + 1; - do { - ix = seq & RXRPC_RXTX_BUFF_MASK; - if (call->rxtx_buffer[ix]) - *ackp++ = RXRPC_ACK_TYPE_ACK; - else - *ackp++ = RXRPC_ACK_TYPE_NACK; - seq++; - } while (before_eq(seq, top)); +retry: + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + txb->ack.firstPacket = htonl(window); + txb->ack.nAcks = 0; + + if (after(wtop, window)) { + /* Try to copy the SACK ring locklessly. We can use the copy, + * only if the now-current top of the window didn't go past the + * previously read base - otherwise we can't know whether we + * have old data or new data. + */ + memcpy(sack_buffer, call->ackr_sack_table, sizeof(sack_buffer)); + wrap_point = window + RXRPC_SACK_SIZE - 1; + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + if (after(wtop, wrap_point)) { + cond_resched(); + goto retry; + } + + /* The buffer is maintained as a ring with an invariant mapping + * between bit position and sequence number, so we'll probably + * need to rotate it. + */ + txb->ack.nAcks = wtop - window; + ix = window % RXRPC_SACK_SIZE; + first = sizeof(sack_buffer) - ix; + + if (ix + txb->ack.nAcks <= RXRPC_SACK_SIZE) { + memcpy(txb->acks, sack_buffer + ix, txb->ack.nAcks); + } else { + memcpy(txb->acks, sack_buffer + ix, first); + memcpy(txb->acks + first, sack_buffer, + txb->ack.nAcks - first); + } + + ackp += txb->ack.nAcks; + } else if (before(wtop, window)) { + pr_warn("ack window backward %x %x", window, wtop); } else if (txb->ack.reason == RXRPC_ACK_DELAY) { txb->ack.reason = RXRPC_ACK_IDLE; } @@ -122,16 +139,18 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; jmax = rxrpc_rx_jumbo_max; + qsize = (window - 1) - call->rx_consumed; + rsize = max_t(int, call->rx_winsize - qsize, 0); ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(call->rx_winsize); + ackinfo.rwind = htonl(rsize); ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return top - hard_ack + 3 + sizeof(ackinfo); + return txb->ack.nAcks + 3 + sizeof(ackinfo); } /* @@ -188,7 +207,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * struct msghdr msg; struct kvec iov[1]; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; @@ -212,7 +230,7 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); spin_lock_bh(&call->lock); - n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); + n = rxrpc_fill_out_ack(conn, call, txb); spin_unlock_bh(&call->lock); if (n == 0) { kfree(pkt); @@ -236,6 +254,9 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); + /* Grab the highest received seq as late as possible */ + txb->ack.previousPacket = htonl(call->rx_highest_seq); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 3877afd23598..d48af0178866 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,8 +54,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack, rx_hard_ack; + rxrpc_seq_t tx_hard_ack; char lbuff[50], rbuff[50]; + u64 wtmp; if (v == &rxnet->calls) { seq_puts(seq, @@ -91,7 +92,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) } tx_hard_ack = READ_ONCE(call->tx_hard_ack); - rx_hard_ack = READ_ONCE(call->rx_hard_ack); + wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", @@ -106,7 +107,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->abort_code, call->debug_id, tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, - rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, + lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 401aae687830..efb85f983657 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,7 +173,8 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, + lower_32_bits(atomic64_read(&call->ackr_window)) - 1, call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -183,10 +184,11 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); - ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); @@ -220,45 +222,53 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct rxrpc_skb_priv *sp; struct sk_buff *skb; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; - bool last = false; - int ix; + rxrpc_seq_t old_consumed = call->rx_consumed, tseq; + bool last; + int acked; _enter("%d", call->debug_id); - hard_ack = call->rx_hard_ack; - top = smp_load_acquire(&call->rx_top); - ASSERT(before(hard_ack, top)); - - hard_ack++; - ix = hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; +further_rotation: + skb = skb_dequeue(&call->recvmsg_queue); rxrpc_see_skb(skb, rxrpc_skb_rotated); - sp = rxrpc_skb(skb); + sp = rxrpc_skb(skb); + tseq = sp->hdr.seq; serial = sp->hdr.serial; + last = sp->hdr.flags & RXRPC_LAST_PACKET; - if (sp->hdr.flags & RXRPC_LAST_PACKET) - last = true; - - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ - smp_store_release(&call->rx_hard_ack, hard_ack); + if (after(tseq, call->rx_consumed)) + smp_store_release(&call->rx_consumed, tseq); rxrpc_free_skb(skb, rxrpc_skb_freed); - trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); + trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, + serial, call->rx_consumed); if (last) { rxrpc_end_rx_phase(call, serial); - } else { - /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2 && - !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_rotate_rx); - rxrpc_transmit_ack_packets(call->peer->local); - } + return; + } + + /* The next packet on the queue might entirely overlap with the one we + * just consumed; if so, rotate that away also. + */ + skb = skb_peek(&call->recvmsg_queue); + if (skb) { + sp = rxrpc_skb(skb); + if (sp->hdr.seq != call->rx_consumed && + after_eq(call->rx_consumed, sp->hdr.seq)) + goto further_rotation; + } + + /* Check to see if there's an ACK that needs sending. */ + acked = atomic_add_return(call->rx_consumed - old_consumed, + &call->ackr_nr_consumed); + if (acked > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); } } @@ -285,46 +295,38 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; - rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top, seq; + rxrpc_seq_t seq = 0; size_t remain; unsigned int rx_pkt_offset, rx_pkt_len; - int ix, copy, ret = -EAGAIN, ret2; + int copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { - seq = call->rx_hard_ack; + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; } - /* Barriers against rxrpc_input_data(). */ - hard_ack = call->rx_hard_ack; - seq = hard_ack + 1; - - while (top = smp_load_acquire(&call->rx_top), - before_eq(seq, top) - ) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - if (!skb) { - trace_rxrpc_recvdata(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); - rxrpc_transmit_ack_packets(call->peer->local); - break; - } - smp_rmb(); + /* No one else can be removing stuff from the queue, so we shouldn't + * need the Rx lock to walk it. + */ + skb = skb_peek(&call->recvmsg_queue); + while (skb) { rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); + seq = sp->hdr.seq; - if (!(flags & MSG_PEEK)) { - serial = sp->hdr.serial; - trace_rxrpc_receive(call, rxrpc_receive_front, - serial, seq); + if (after_eq(call->rx_consumed, seq)) { + kdebug("obsolete %x %x", call->rx_consumed, seq); + goto skip_obsolete; } + if (!(flags & MSG_PEEK)) + trace_rxrpc_receive(call, rxrpc_receive_front, + sp->hdr.serial, seq); + if (msg) sock_recv_timestamp(msg, sock->sk, skb); @@ -338,6 +340,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ret = ret2; goto out; } + rxrpc_transmit_ack_packets(call->peer->local); } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -370,16 +373,17 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, break; } + skip_obsolete: /* The whole packet has been transferred. */ if (sp->hdr.flags & RXRPC_LAST_PACKET) ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; + skb = skb_peek_next(skb, &call->recvmsg_queue); + if (!(flags & MSG_PEEK)) rxrpc_rotate_rx_window(call); - - seq++; } out: @@ -522,8 +526,7 @@ try_again: ret = 0; rxrpc_transmit_ack_packets(call->peer->local); - if (after(call->rx_top, call->rx_hard_ack) && - call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) + if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; default: diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index b19937776aa9..d87c99b36e01 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1191,7 +1191,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), ticket, ticket_len) < 0) - goto protocol_error_free; ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 2bd987364e44..cde3224a5cd2 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; -static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; +static const unsigned int n_max_acks = 255; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; -- cgit v1.2.3 From a4ea4c47761943d90cd5d1688b3c3c65922ff2b1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 31 Mar 2022 23:55:08 +0100 Subject: rxrpc: Don't use a ring buffer for call Tx queue Change the way the Tx queueing works to make the following ends easier to achieve: (1) The filling of packets, the encryption of packets and the transmission of packets can be handled in parallel by separate threads, rather than rxrpc_sendmsg() allocating, filling, encrypting and transmitting each packet before moving onto the next one. (2) Get rid of the fixed-size ring which sets a hard limit on the number of packets that can be retained in the ring. This allows the number of packets to increase without having to allocate a very large ring or having variable-sized rings. [Note: the downside of this is that it's then less efficient to locate a packet for retransmission as we then have to step through a list and examine each buffer in the list.] (3) Allow the filler/encrypter to run ahead of the transmission window. (4) Make it easier to do zero copy UDP from the packet buffers. (5) Make it easier to do zero copy from userspace to the packet buffers - and thence to UDP (only if for unauthenticated connections). To that end, the following changes are made: (1) Use the new rxrpc_txbuf struct instead of sk_buff for keeping packets to be transmitted in. This allows them to be placed on multiple queues simultaneously. An sk_buff isn't really necessary as it's never passed on to lower-level networking code. (2) Keep the transmissable packets in a linked list on the call struct rather than in a ring. As a consequence, the annotation buffer isn't used either; rather a flag is set on the packet to indicate ackedness. (3) Use the RXRPC_CALL_TX_LAST flag to indicate that the last packet to be transmitted has been queued. Add RXRPC_CALL_TX_ALL_ACKED to indicate that all packets up to and including the last got hard acked. (4) Wire headers are now stored in the txbuf rather than being concocted on the stack and they're stored immediately before the data, thereby allowing zerocopy of a single span. (5) Don't bother with instant-resend on transmission failure; rather, leave it for a timer or an ACK packet to trigger. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 78 +++++++++--------- net/rxrpc/af_rxrpc.c | 5 +- net/rxrpc/ar-internal.h | 31 +++---- net/rxrpc/call_event.c | 111 +++++++++---------------- net/rxrpc/call_object.c | 15 +++- net/rxrpc/input.c | 145 ++++++++++++++------------------- net/rxrpc/insecure.c | 3 +- net/rxrpc/output.c | 89 +++++++++----------- net/rxrpc/proc.c | 9 +-- net/rxrpc/rxkad.c | 102 +++++++++-------------- net/rxrpc/sendmsg.c | 188 +++++++++++++++++-------------------------- net/rxrpc/txbuf.c | 34 ++++++++ 12 files changed, 349 insertions(+), 461 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 284a1560b0a8..71ca74e40ec8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -75,6 +75,7 @@ EM(rxrpc_call_got, "GOT") \ EM(rxrpc_call_got_kernel, "Gke") \ EM(rxrpc_call_got_timer, "GTM") \ + EM(rxrpc_call_got_tx, "Gtx") \ EM(rxrpc_call_got_userid, "Gus") \ EM(rxrpc_call_new_client, "NWc") \ EM(rxrpc_call_new_service, "NWs") \ @@ -83,20 +84,22 @@ EM(rxrpc_call_put_noqueue, "PnQ") \ EM(rxrpc_call_put_notimer, "PnT") \ EM(rxrpc_call_put_timer, "PTM") \ + EM(rxrpc_call_put_tx, "Ptx") \ EM(rxrpc_call_put_userid, "Pus") \ EM(rxrpc_call_queued, "QUE") \ EM(rxrpc_call_queued_ref, "QUR") \ EM(rxrpc_call_release, "RLS") \ E_(rxrpc_call_seen, "SEE") -#define rxrpc_transmit_traces \ - EM(rxrpc_transmit_await_reply, "AWR") \ - EM(rxrpc_transmit_end, "END") \ - EM(rxrpc_transmit_queue, "QUE") \ - EM(rxrpc_transmit_queue_last, "QLS") \ - EM(rxrpc_transmit_rotate, "ROT") \ - EM(rxrpc_transmit_rotate_last, "RLS") \ - E_(rxrpc_transmit_wait, "WAI") +#define rxrpc_txqueue_traces \ + EM(rxrpc_txqueue_await_reply, "AWR") \ + EM(rxrpc_txqueue_dequeue, "DEQ") \ + EM(rxrpc_txqueue_end, "END") \ + EM(rxrpc_txqueue_queue, "QUE") \ + EM(rxrpc_txqueue_queue_last, "QLS") \ + EM(rxrpc_txqueue_rotate, "ROT") \ + EM(rxrpc_txqueue_rotate_last, "RLS") \ + E_(rxrpc_txqueue_wait, "WAI") #define rxrpc_receive_traces \ EM(rxrpc_receive_end, "END") \ @@ -259,6 +262,7 @@ EM(rxrpc_txbuf_alloc_ack, "ALLOC ACK ") \ EM(rxrpc_txbuf_alloc_data, "ALLOC DATA ") \ EM(rxrpc_txbuf_free, "FREE ") \ + EM(rxrpc_txbuf_get_buffer, "GET BUFFER ") \ EM(rxrpc_txbuf_get_trans, "GET TRANS ") \ EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ EM(rxrpc_txbuf_put_ack_tx, "PUT ACK TX ") \ @@ -266,6 +270,7 @@ EM(rxrpc_txbuf_put_nomem, "PUT NOMEM ") \ EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ + EM(rxrpc_txbuf_put_trans, "PUT TRANS ") \ EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") @@ -295,9 +300,9 @@ enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); -enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); +enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -323,9 +328,9 @@ rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_transmit_traces; rxrpc_tx_points; rxrpc_txbuf_traces; +rxrpc_txqueue_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -605,15 +610,16 @@ TRACE_EVENT(rxrpc_call_complete, __entry->abort_code) ); -TRACE_EVENT(rxrpc_transmit, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_transmit_trace why), +TRACE_EVENT(rxrpc_txqueue, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_txqueue_trace why), TP_ARGS(call, why), TP_STRUCT__entry( __field(unsigned int, call ) - __field(enum rxrpc_transmit_trace, why ) - __field(rxrpc_seq_t, tx_hard_ack ) + __field(enum rxrpc_txqueue_trace, why ) + __field(rxrpc_seq_t, acks_hard_ack ) + __field(rxrpc_seq_t, tx_bottom ) __field(rxrpc_seq_t, tx_top ) __field(int, tx_winsize ) ), @@ -621,16 +627,19 @@ TRACE_EVENT(rxrpc_transmit, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->tx_hard_ack = call->tx_hard_ack; + __entry->acks_hard_ack = call->acks_hard_ack; + __entry->tx_bottom = call->tx_bottom; __entry->tx_top = call->tx_top; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x n=%u/%u", + TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u", __entry->call, - __print_symbolic(__entry->why, rxrpc_transmit_traces), - __entry->tx_hard_ack + 1, - __entry->tx_top - __entry->tx_hard_ack, + __print_symbolic(__entry->why, rxrpc_txqueue_traces), + __entry->tx_bottom, + __entry->acks_hard_ack, + __entry->tx_top - __entry->tx_bottom, + __entry->tx_top - __entry->acks_hard_ack, __entry->tx_winsize) ); @@ -1200,29 +1209,25 @@ TRACE_EVENT(rxrpc_drop_ack, ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, - s64 expiry), + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, s64 expiry), - TP_ARGS(call, seq, annotation, expiry), + TP_ARGS(call, seq, expiry), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) - __field(u8, annotation ) __field(s64, expiry ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->seq = seq; - __entry->annotation = annotation; __entry->expiry = expiry; ), - TP_printk("c=%08x q=%x a=%02x xp=%lld", + TP_printk("c=%08x q=%x xp=%lld", __entry->call, __entry->seq, - __entry->annotation, __entry->expiry) ); @@ -1245,14 +1250,14 @@ TRACE_EVENT(rxrpc_congest, TP_fast_assign( __entry->call = call->debug_id; __entry->change = change; - __entry->hard_ack = call->tx_hard_ack; + __entry->hard_ack = call->acks_hard_ack; __entry->top = call->tx_top; __entry->lowest_nak = call->acks_lowest_nak; __entry->ack_serial = ack_serial; memcpy(&__entry->sum, summary, sizeof(__entry->sum)); ), - TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s", + TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, __entry->ack_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), @@ -1362,26 +1367,23 @@ TRACE_EVENT(rxrpc_connect_call, ); TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call, int ix), + TP_PROTO(struct rxrpc_call *call), - TP_ARGS(call, ix), + TP_ARGS(call), TP_STRUCT__entry( __field(unsigned int, call ) - __field(int, ix ) - __array(u8, anno, 64 ) + __field(rxrpc_seq_t, seq ) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->ix = ix; - memcpy(__entry->anno, call->rxtx_annotations, 64); + __entry->seq = call->acks_hard_ack; ), - TP_printk("c=%08x ix=%u a=%64phN", + TP_printk("c=%08x q=%x", __entry->call, - __entry->ix, - __entry->anno) + __entry->seq) ); TRACE_EVENT(rxrpc_rx_icmp, @@ -1461,7 +1463,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_id = call->call_id; __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; - __entry->tx_seq = call->tx_hard_ack; + __entry->tx_seq = call->acks_hard_ack; __entry->rx_seq = call->rx_highest_seq; ), diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ceba28e9dce6..2f3991cf8715 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -39,7 +39,7 @@ atomic_t rxrpc_debug_id; EXPORT_SYMBOL(rxrpc_debug_id); /* count of skbs currently in use */ -atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +atomic_t rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; @@ -979,7 +979,7 @@ static int __init af_rxrpc_init(void) goto error_call_jar; } - rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); + rxrpc_workqueue = alloc_workqueue("krxrpcd", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!rxrpc_workqueue) { pr_notice("Failed to allocate work queue\n"); goto error_work_queue; @@ -1059,7 +1059,6 @@ static void __exit af_rxrpc_exit(void) sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); unregister_pernet_device(&rxrpc_net_ops); - ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); /* Make sure the local and peer records pinned by any dying connections diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c6c5bb3d3688..d7aebe82e17c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -195,7 +195,6 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - u16 remain; u16 offset; /* Offset of data */ u16 len; /* Length of data */ u8 flags; @@ -243,7 +242,7 @@ struct rxrpc_security { size_t *, size_t *, size_t *); /* impose security on a packet */ - int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); + int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); @@ -497,6 +496,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ @@ -594,7 +594,7 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ - struct sk_buff *tx_pending; /* Tx socket buffer being filled */ + struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ @@ -632,22 +632,16 @@ struct rxrpc_call { #define RXRPC_INIT_RX_WINDOW_SIZE 63 struct sk_buff **rxtx_buffer; u8 *rxtx_annotations; -#define RXRPC_TX_ANNO_ACK 0 -#define RXRPC_TX_ANNO_UNACK 1 -#define RXRPC_TX_ANNO_NAK 2 -#define RXRPC_TX_ANNO_RETRANS 3 -#define RXRPC_TX_ANNO_MASK 0x03 -#define RXRPC_TX_ANNO_LAST 0x04 -#define RXRPC_TX_ANNO_RESENT 0x08 - - rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but - * not hard-ACK'd packet follows this. - */ /* Transmitted data tracking. */ + spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_buffer; /* Buffer of transmissible packets */ + rxrpc_seq_t tx_bottom; /* First packet in buffer */ + rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ +#define RXRPC_TX_MAX_WINDOW 128 /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ @@ -657,6 +651,7 @@ struct rxrpc_call { rxrpc_seq_t rx_consumed; /* Highest packet consumed */ rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ + spinlock_t input_lock; /* Lock for packet input to this call */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -671,8 +666,6 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - spinlock_t input_lock; /* Lock for packet input to this call */ - /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ @@ -697,6 +690,7 @@ struct rxrpc_call { ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ + rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ @@ -809,7 +803,7 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) /* * af_rxrpc.c */ -extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* @@ -831,6 +825,7 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1034,7 +1029,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) */ void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); +int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 36f60ac1d95d..3c37b280eb20 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -148,62 +148,52 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { - struct sk_buff *skb; + struct rxrpc_txbuf *txb; unsigned long resend_at; - rxrpc_seq_t cursor, seq, top; + rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; - int ix; - u8 annotation, anno_type, retrans = 0, unacked = 0; + bool unacked = false; + LIST_HEAD(retrans_queue); - _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); + _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); - spin_lock_bh(&call->lock); - - cursor = call->tx_hard_ack; - top = call->tx_top; - ASSERT(before_eq(cursor, top)); - if (cursor == top) - goto out_unlock; + spin_lock(&call->tx_lock); /* Scan the packet list without dropping the lock and decide which of * the packets in the Tx buffer we're going to resend and what the new * resend timeout will be. */ - trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK); + trace_rxrpc_resend(call); oldest = now; - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_ACK) + list_for_each_entry(txb, &call->tx_buffer, call_link) { + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; + if (after(txb->seq, transmitted)) + break; - skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - if (anno_type == RXRPC_TX_ANNO_UNACK) { - if (ktime_after(skb->tstamp, max_age)) { - if (ktime_before(skb->tstamp, oldest)) - oldest = skb->tstamp; + if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) { + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; continue; } - if (!(annotation & RXRPC_TX_ANNO_RESENT)) - unacked++; + unacked = true; } - /* Okay, we need to retransmit a packet. */ - call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation; - retrans++; - trace_rxrpc_retransmit(call, seq, annotation | anno_type, - ktime_to_ns(ktime_sub(skb->tstamp, max_age))); + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_move_tail(&txb->tx_link, &retrans_queue); } + spin_unlock(&call->tx_lock); + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, + !list_empty(&retrans_queue)); WRITE_ONCE(call->resend_at, resend_at); if (unacked) @@ -213,7 +203,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (!retrans) { + if (list_empty(&retrans_queue)) { + spin_lock_bh(&call->lock); rxrpc_reduce_call_timer(call, resend_at, now_j, rxrpc_timer_set_for_resend); spin_unlock_bh(&call->lock); @@ -225,50 +216,19 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) goto out; } - /* Now go through the Tx window and perform the retransmissions. We - * have to drop the lock for each send. If an ACK comes in whilst the - * lock is dropped, it may clear some of the retransmission markers for - * packets that it soft-ACKs. - */ - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type != RXRPC_TX_ANNO_RETRANS) - continue; - - /* We need to reset the retransmission state, but we need to do - * so before we drop the lock as a new ACK/NAK may come in and - * confuse things - */ - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; - - rxrpc_get_skb(skb, rxrpc_skb_got); - spin_unlock_bh(&call->lock); - + while ((txb = list_first_entry_or_null(&retrans_queue, + struct rxrpc_txbuf, tx_link))) { + list_del_init(&txb->tx_link); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - } + rxrpc_send_data_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - rxrpc_free_skb(skb, rxrpc_skb_freed); - spin_lock_bh(&call->lock); - if (after(call->tx_hard_ack, seq)) - seq = call->tx_hard_ack; + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); } -out_unlock: - spin_unlock_bh(&call->lock); out: _leave(""); } @@ -301,6 +261,9 @@ recheck_state: goto recheck_state; } + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + if (call->state == RXRPC_CALL_COMPLETE) { rxrpc_delete_call_timer(call); goto out_put; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 4d8601c6a32d..ed5f6f0e4286 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -155,11 +155,13 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); @@ -175,7 +177,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->tx_winsize = 16; call->cong_cwnd = 2; - call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; + call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; @@ -510,7 +512,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Clean up the RxTx skb ring. + * Clean up the Rx skb ring. */ static void rxrpc_cleanup_ring(struct rxrpc_call *call) { @@ -686,6 +688,8 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { + struct rxrpc_txbuf *txb; + _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -694,7 +698,12 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); rxrpc_cleanup_ring(call); - rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 947e7196e2be..b1f7debd4f3e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -32,7 +32,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, bool resend = false; summary->flight_size = - (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + (call->tx_top - call->acks_hard_ack) - summary->nr_acks; if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; @@ -150,8 +150,8 @@ resume_normality: out: cumulative_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) - cwnd = RXRPC_RXTX_BUFF_SIZE - 1; + if (cwnd >= RXRPC_TX_MAX_WINDOW) + cwnd = RXRPC_TX_MAX_WINDOW; call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); @@ -169,9 +169,8 @@ send_extra_data: /* Send some previously unsent DATA if we have some to advance the ACK * state. */ - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST || - summary->nr_acks != call->tx_top - call->tx_hard_ack) { + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || + summary->nr_acks != call->tx_top - call->acks_hard_ack) { call->cong_extra++; wake_up(&call->waitq); } @@ -184,53 +183,40 @@ send_extra_data: static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct sk_buff *skb, *list = NULL; + struct rxrpc_txbuf *txb; bool rot_last = false; - int ix; - u8 annotation; - if (call->acks_lowest_nak == call->tx_hard_ack) { - call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { - summary->new_low_nack = true; - call->acks_lowest_nak = to; - } - - spin_lock(&call->lock); - - while (before(call->tx_hard_ack, to)) { - call->tx_hard_ack++; - ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rotated); - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; - skb->next = list; - list = skb; - - if (annotation & RXRPC_TX_ANNO_LAST) { + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before_eq(txb->seq, call->acks_hard_ack)) + continue; + if (!test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) + summary->nr_rot_new_acks++; + if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) - summary->nr_rot_new_acks++; + if (txb->seq == to) + break; } - spin_unlock(&call->lock); + if (rot_last) + set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); - trace_rxrpc_transmit(call, (rot_last ? - rxrpc_transmit_rotate_last : - rxrpc_transmit_rotate)); - wake_up(&call->waitq); + _enter("%x,%x,%x,%d", to, call->acks_hard_ack, call->tx_top, rot_last); - while (list) { - skb = list; - list = skb->next; - skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_freed); + if (call->acks_lowest_nak == call->acks_hard_ack) { + call->acks_lowest_nak = to; + } else if (before_eq(call->acks_lowest_nak, to)) { + summary->new_low_nack = true; + call->acks_lowest_nak = to; } + smp_store_release(&call->acks_hard_ack, to); + + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + wake_up(&call->waitq); return rot_last; } @@ -270,9 +256,9 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, write_unlock(&call->state_lock); if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); else - trace_rxrpc_transmit(call, rxrpc_transmit_end); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); _leave(" = ok"); return true; @@ -678,30 +664,21 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - rxrpc_seq_t top, bottom, seq; + struct rxrpc_txbuf *txb; + rxrpc_seq_t top, bottom; bool resend = false; - spin_lock_bh(&call->lock); - - bottom = call->tx_hard_ack + 1; - top = call->acks_lost_top; + bottom = READ_ONCE(call->acks_hard_ack) + 1; + top = READ_ONCE(call->acks_lost_top); if (before(bottom, top)) { - for (seq = bottom; before_eq(seq, top); seq++) { - int ix = seq & RXRPC_RXTX_BUFF_MASK; - u8 annotation = call->rxtx_annotations[ix]; - u8 anno_type = annotation & RXRPC_TX_ANNO_MASK; - - if (anno_type != RXRPC_TX_ANNO_UNACK) + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RETRANS; - call->rxtx_annotations[ix] = annotation; + set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); resend = true; } } - spin_unlock_bh(&call->lock); - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -735,8 +712,8 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > RXRPC_TX_MAX_WINDOW) + rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { if (rwind > call->tx_winsize) wake = true; @@ -775,22 +752,24 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - int ix; - u8 annotation, anno_type; - - for (; nr_acks > 0; nr_acks--, seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - switch (*acks++) { + struct rxrpc_txbuf *txb; + + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before(txb->seq, seq)) + continue; + if (after_eq(txb->seq, seq + nr_acks)) + break; + switch (acks[txb->seq - seq]) { case RXRPC_ACK_TYPE_ACK: summary->nr_acks++; - if (anno_type == RXRPC_TX_ANNO_ACK) + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; + /* A lot of the time the packet is going to + * have been ACK.'d already. + */ + clear_bit(RXRPC_TXBUF_NACKED, &txb->flags); + set_bit(RXRPC_TXBUF_ACKED, &txb->flags); summary->nr_new_acks++; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_ACK | annotation; break; case RXRPC_ACK_TYPE_NACK: if (!summary->nr_nacks && @@ -799,13 +778,12 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, summary->new_low_nack = true; } summary->nr_nacks++; - if (anno_type == RXRPC_TX_ANNO_NAK) + if (test_bit(RXRPC_TXBUF_NACKED, &txb->flags)) continue; summary->nr_new_nacks++; - if (anno_type == RXRPC_TX_ANNO_RETRANS) - continue; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_NAK | annotation; + clear_bit(RXRPC_TXBUF_ACKED, &txb->flags); + set_bit(RXRPC_TXBUF_NACKED, &txb->flags); + set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); break; default: return rxrpc_proto_abort("SFT", call, 0); @@ -930,7 +908,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && - call->tx_hard_ack == 0 && + call->acks_hard_ack == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); @@ -989,7 +967,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (before(hard_ack, call->tx_hard_ack) || + if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) { rxrpc_proto_abort("AKW", call, 0); goto out; @@ -999,7 +977,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (after(hard_ack, call->tx_hard_ack)) { + if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); goto out; @@ -1015,8 +993,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) &summary); } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST && + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) rxrpc_propose_ping(call, ack_serial, diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index fd68f0e3af27..0eb8471bfc53 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -25,8 +25,7 @@ static int none_how_much_data(struct rxrpc_call *call, size_t remain, return 0; } -static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, - size_t data_size) +static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { return 0; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 0a4f37d7b6b5..e2f501cef040 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -335,7 +335,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) * channel instead, thereby closing off this call. */ if (rxrpc_is_client_call(call) && - test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) return 0; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -383,20 +383,17 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) /* * send a packet through the transport endpoint */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, - bool retrans) +int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; size_t len; int ret, rtt_slot = -1; - _enter(",{%d}", skb->len); + _enter("%x,{%d}", txb->seq, txb->len); if (hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); @@ -406,29 +403,16 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(call->cid); - whdr.callNumber = htonl(call->call_id); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = htonl(serial); - whdr.type = RXRPC_PACKET_TYPE_DATA; - whdr.flags = sp->hdr.flags; - whdr.userStatus = 0; - whdr.securityIndex = call->security_ix; - whdr._rsvd = htons(sp->hdr._rsvd); - whdr.serviceId = htons(call->service_id); + txb->wire.serial = htonl(serial); if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && - sp->hdr.seq == 1) - whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + txb->seq == 1) + txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = skb->head; - iov[1].iov_len = skb->len; - len = iov[0].iov_len + iov[1].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + txb->len; + len = iov[0].iov_len; + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -443,19 +427,19 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (whdr.flags & RXRPC_REQUEST_ACK) + if (txb->wire.flags & RXRPC_REQUEST_ACK) why = rxrpc_reqack_already_on; - else if ((whdr.flags & RXRPC_LAST_PACKET) && rxrpc_to_client(sp)) + else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; - else if (retrans) + else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) why = rxrpc_reqack_retrans; else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) why = rxrpc_reqack_slow_start; else if (call->tx_winsize <= 2) why = rxrpc_reqack_small_txwin; - else if (call->peer->rtt_count < 3 && sp->hdr.seq & 1) + else if (call->peer->rtt_count < 3 && txb->seq & 1) why = rxrpc_reqack_more_rtt; else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) why = rxrpc_reqack_old_rtt; @@ -463,35 +447,36 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, goto dont_set_request_ack; rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); - trace_rxrpc_req_ack(call->debug_id, sp->hdr.seq, why); + trace_rxrpc_req_ack(call->debug_id, txb->seq, why); if (why != rxrpc_reqack_no_srv_last) - whdr.flags |= RXRPC_REQUEST_ACK; + txb->wire.flags |= RXRPC_REQUEST_ACK; dont_set_request_ack: if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, - whdr.flags, retrans, true); + trace_rxrpc_tx_data(call, txb->seq, serial, + txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), + true); goto done; } } - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, - false); + trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (iov[1].iov_len >= call->peer->maxdata) + if (txb->len >= call->peer->maxdata) goto send_fragmentable; down_read(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP @@ -510,7 +495,7 @@ dont_set_request_ack: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_nofrag); } @@ -520,8 +505,8 @@ dont_set_request_ack: done: if (ret >= 0) { - if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = skb->tstamp; + if (txb->wire.flags & RXRPC_REQUEST_ACK) { + call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -533,7 +518,7 @@ done: } } - if (sp->hdr.seq == 1 && + if (txb->seq == 1 && !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { unsigned long nowj = jiffies, expect_rx_by; @@ -565,23 +550,21 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: case AF_INET: ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DONT); + IP_PMTUDISC_DONT); rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DO); + IP_PMTUDISC_DO); break; default: @@ -593,7 +576,7 @@ send_fragmentable: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_frag); } rxrpc_tx_backoff(call, ret); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d48af0178866..0807753ec2dc 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,7 +54,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack; + rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; u64 wtmp; @@ -91,7 +91,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) timeout -= jiffies; } - tx_hard_ack = READ_ONCE(call->tx_hard_ack); + acks_hard_ack = READ_ONCE(call->acks_hard_ack); wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" @@ -106,7 +106,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rxrpc_call_states[call->state], call->abort_code, call->debug_id, - tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, + acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); @@ -459,9 +459,8 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, - "Buffers : txb=%u,%u rxb=%u\n", + "Buffers : txb=%u rxb=%u\n", atomic_read(&rxrpc_nr_txbuf), - atomic_read(&rxrpc_n_tx_skbs), atomic_read(&rxrpc_n_rx_skbs)); return 0; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index d87c99b36e01..8fc055587f0e 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -259,11 +259,10 @@ static void rxkad_free_call_crypto(struct rxrpc_call *call) * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, - struct sk_buff *skb, u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxkad_level1_hdr hdr; + struct rxkad_level1_hdr *hdr = (void *)txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -271,22 +270,22 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ call->call_id; - data_size |= (u32)check << 16; - - hdr.data_size = htonl(data_size); - memcpy(skb->head, &hdr, sizeof(hdr)); + check = txb->seq ^ ntohl(txb->wire.callNumber); + hdr->data_size = htonl((u32)check << 16 | txb->len); - pad = sizeof(struct rxkad_level1_hdr) + data_size; + txb->len += sizeof(struct rxkad_level1_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, skb->head, 8); + sg_init_one(&sg, txb->data, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -301,87 +300,60 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, * wholly encrypt a packet (level 2 security) */ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr rxkhdr; - struct rxrpc_skb_priv *sp; + struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; struct rxrpc_crypt iv; - struct scatterlist sg[16]; - unsigned int len; + struct scatterlist sg; size_t pad; u16 check; - int err; - - sp = rxrpc_skb(skb); + int ret; _enter(""); - check = sp->hdr.seq ^ call->call_id; + check = txb->seq ^ ntohl(txb->wire.callNumber); - rxkhdr.data_size = htonl(data_size | (u32)check << 16); - rxkhdr.checksum = 0; - memcpy(skb->head, &rxkhdr, sizeof(rxkhdr)); + rxkhdr->data_size = htonl(txb->len | (u32)check << 16); + rxkhdr->checksum = 0; - pad = sizeof(struct rxkad_level2_hdr) + data_size; + txb->len += sizeof(struct rxkad_level2_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* encrypt from the session key */ token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg[0], skb->head, sizeof(rxkhdr)); + sg_init_one(&sg, txb->data, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x); - crypto_skcipher_encrypt(req); - - /* we want to encrypt the skbuff in-place */ - err = -EMSGSIZE; - if (skb_shinfo(skb)->nr_frags > 16) - goto out; - - len = round_up(data_size, RXKAD_ALIGN); - - sg_init_table(sg, ARRAY_SIZE(sg)); - err = skb_to_sgvec(skb, sg, 8, len); - if (unlikely(err < 0)) - goto out; - skcipher_request_set_crypt(req, sg, sg, len, iv.x); - crypto_skcipher_encrypt(req); - - _leave(" = 0"); - err = 0; - -out: + skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); - return err; + return ret; } /* * checksum an RxRPC packet header */ -static int rxkad_secure_packet(struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size) +static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - struct rxrpc_skb_priv *sp; struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; u32 x, y; int ret; - sp = rxrpc_skb(skb); - - _enter("{%d{%x}},{#%u},%zu,", + _enter("{%d{%x}},{#%u},%u,", call->debug_id, key_serial(call->conn->params.key), - sp->hdr.seq, data_size); + txb->seq, txb->len); if (!call->conn->rxkad.cipher) return 0; @@ -398,9 +370,9 @@ static int rxkad_secure_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); - x |= sp->hdr.seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); + x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x |= txb->seq & 0x3fffffff; + call->crypto_buf[0] = txb->wire.callNumber; call->crypto_buf[1] = htonl(x); sg_init_one(&sg, call->crypto_buf, 8); @@ -414,17 +386,17 @@ static int rxkad_secure_packet(struct rxrpc_call *call, y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - sp->hdr.cksum = y; + txb->wire.cksum = htons(y); switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; case RXRPC_SECURITY_AUTH: - ret = rxkad_secure_packet_auth(call, skb, data_size, req); + ret = rxkad_secure_packet_auth(call, txb, req); break; case RXRPC_SECURITY_ENCRYPT: - ret = rxkad_secure_packet_encrypt(call, skb, data_size, req); + ret = rxkad_secure_packet_encrypt(call, txb, req); break; default: ret = -EPERM; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index e32805a49324..a96ae7f58148 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -25,7 +25,7 @@ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) unsigned int win_size = min_t(unsigned int, call->tx_winsize, call->cong_cwnd + call->cong_extra); - rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); if (_tx_win) *_tx_win = tx_win; @@ -50,7 +50,12 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -71,12 +76,11 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, rtt = 2; timeout = rtt; - tx_start = READ_ONCE(call->tx_hard_ack); + tx_start = smp_load_acquire(&call->acks_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - tx_win = READ_ONCE(call->tx_hard_ack); if (rxrpc_check_tx_space(call, &tx_win)) return 0; @@ -87,12 +91,17 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; } - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); timeout = schedule_timeout(timeout); } } @@ -112,7 +121,12 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -129,8 +143,8 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%u,%u,%u}", - call->tx_hard_ack, call->tx_top, call->tx_winsize); + _enter(",{%u,%u,%u,%u}", + call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); @@ -154,24 +168,6 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, return ret; } -/* - * Schedule an instant Tx resend. - */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) -{ - spin_lock_bh(&call->lock); - - if (call->state < RXRPC_CALL_COMPLETE) { - call->rxtx_annotations[ix] = - (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) | - RXRPC_TX_ANNO_RETRANS; - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - } - - spin_unlock_bh(&call->lock); -} - /* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. @@ -188,40 +184,35 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, * the packet immediately. Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */ -static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + rxrpc_notify_end_tx_t notify_end_tx) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; - rxrpc_seq_t seq = sp->hdr.seq; - int ret, ix; - u8 annotation = RXRPC_TX_ANNO_UNACK; - - _net("queue skb %p [%d]", skb, seq); + rxrpc_seq_t seq = txb->seq; + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + int ret; rxrpc_inc_stat(call->rxnet, stat_tx_data); ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) - annotation |= RXRPC_TX_ANNO_LAST; - /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ - skb->tstamp = ktime_get_real(); + txb->last_sent = ktime_get_real(); - ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; + /* Add the packet to the call's output buffer */ + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_buffer); call->tx_top = seq; + spin_unlock(&call->tx_lock); + if (last) - trace_rxrpc_transmit(call, rxrpc_transmit_queue_last); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else - trace_rxrpc_transmit(call, rxrpc_transmit_queue); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); @@ -254,7 +245,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (seq == 1 && rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - ret = rxrpc_send_data_packet(call, skb, false); + ret = rxrpc_send_data_packet(call, txb); if (ret < 0) { switch (ret) { case -ENETUNREACH: @@ -264,8 +255,6 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, 0, ret); goto out; } - _debug("need instant resend %d", ret); - rxrpc_instant_resend(call, ix); } else { unsigned long now = jiffies; unsigned long resend_at = now + call->peer->rto_j; @@ -276,9 +265,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" = %d", ret); - return ret; + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); } /* @@ -292,8 +279,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, rxrpc_notify_end_tx_t notify_end_tx, bool *_dropped_lock) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + struct rxrpc_txbuf *txb; struct sock *sk = &rx->sk; enum rxrpc_call_state state; long timeo; @@ -327,14 +313,15 @@ reload: goto maybe_error; } - skb = call->tx_pending; + txb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_seen); + if (txb) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { rxrpc_transmit_ack_packets(call->peer->local); - if (!skb) { + if (!txb) { size_t remain, bufsize, chunk, offset; _debug("alloc"); @@ -355,52 +342,31 @@ reload: _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); /* create a buffer that we can retain until it's ACK'd */ - skb = sock_alloc_send_skb( - sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret); - if (!skb) + ret = -ENOMEM; + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, + GFP_KERNEL); + if (!txb) goto maybe_error; - sp = rxrpc_skb(skb); - rxrpc_new_skb(skb, rxrpc_skb_new); - - _debug("ALLOC SEND %p", skb); - - ASSERTCMP(skb->mark, ==, 0); - - __skb_put(skb, offset); - - sp->remain = chunk; - if (sp->remain > skb_tailroom(skb)) - sp->remain = skb_tailroom(skb); - - _net("skb: hr %d, tr %d, hl %d, rm %d", - skb_headroom(skb), - skb_tailroom(skb), - skb_headlen(skb), - sp->remain); - - skb->ip_summed = CHECKSUM_UNNECESSARY; + txb->offset = offset; + txb->space -= offset; + txb->space = min_t(size_t, chunk, txb->space); } _debug("append"); - sp = rxrpc_skb(skb); /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { - int copy = skb_tailroom(skb); - ASSERTCMP(copy, >, 0); - if (copy > msg_data_left(msg)) - copy = msg_data_left(msg); - if (copy > sp->remain) - copy = sp->remain; - - _debug("add"); - ret = skb_add_data(skb, &msg->msg_iter, copy); - _debug("added"); - if (ret < 0) + size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); + + _debug("add %zu", copy); + if (!copy_from_iter_full(txb->data + txb->offset, copy, + &msg->msg_iter)) goto efault; - sp->remain -= copy; - skb->mark += copy; + _debug("added"); + txb->space -= copy; + txb->len += copy; + txb->offset += copy; copied += copy; if (call->tx_total_len != -1) call->tx_total_len -= copy; @@ -412,32 +378,22 @@ reload: goto call_terminated; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || + if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - struct rxrpc_connection *conn = call->conn; - uint32_t seq; - - seq = call->tx_top + 1; - - sp->hdr.seq = seq; - sp->hdr._rsvd = 0; - sp->hdr.flags = conn->out_clientflag; - - if (msg_data_left(msg) == 0 && !more) - sp->hdr.flags |= RXRPC_LAST_PACKET; - else if (call->tx_top - call->tx_hard_ack < + if (msg_data_left(msg) == 0 && !more) { + txb->wire.flags |= RXRPC_LAST_PACKET; + __set_bit(RXRPC_TXBUF_LAST, &txb->flags); + } + else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - sp->hdr.flags |= RXRPC_MORE_PACKETS; + txb->wire.flags |= RXRPC_MORE_PACKETS; - ret = call->security->secure_packet(call, skb, skb->mark); + ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; - ret = rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); - /* Should check for failure here */ - skb = NULL; + rxrpc_queue_packet(rx, call, txb, notify_end_tx); + txb = NULL; } } while (msg_data_left(msg) > 0); @@ -450,12 +406,12 @@ success: read_unlock_bh(&call->state_lock); } out: - call->tx_pending = skb; + call->tx_pending = txb; _leave(" = %d", ret); return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted); _leave(" = %d", call->error); return call->error; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 45a7b48a5e10..96bfee89927b 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -99,3 +99,37 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) call_rcu(&txb->rcu, rxrpc_free_txbuf); } } + +/* + * Shrink the transmit buffer. + */ +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + + _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); + + for (;;) { + spin_lock(&call->tx_lock); + txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link); + if (!txb) + break; + hard_ack = smp_load_acquire(&call->acks_hard_ack); + if (before(hard_ack, txb->seq)) + break; + + ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); + call->tx_bottom++; + list_del_rcu(&txb->call_link); + + trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); + + spin_unlock(&call->tx_lock); + + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + } + + spin_unlock(&call->tx_lock); +} -- cgit v1.2.3 From d57a3a151660902091491ac2633134e1be92557f Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 7 May 2022 10:06:13 +0100 Subject: rxrpc: Save last ACK's SACK table rather than marking txbufs Improve the tracking of which packets need to be transmitted by saving the last ACK packet that we receive that has a populated soft-ACK table rather than marking packets. Then we can step through the soft-ACK table and look at the packets we've transmitted beyond that to determine which packets we might want to retransmit. We also look at the highest serial number that has been acked to try and guess which packets we've transmitted the peer is likely to have seen. If necessary, we send a ping to retrieve that number. One downside that might be a problem is that we can't then compare the previous acked/unacked state so easily in rxrpc_input_soft_acks() - which is a potential problem for the slow-start algorithm. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 7 +- net/core/skbuff.c | 1 + net/rxrpc/ar-internal.h | 12 ++-- net/rxrpc/call_event.c | 117 ++++++++++++++++++++++++------ net/rxrpc/call_object.c | 2 + net/rxrpc/input.c | 164 ++++++++++++++++++++----------------------- net/rxrpc/sendmsg.c | 1 - 7 files changed, 185 insertions(+), 119 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 71ca74e40ec8..a11de55c3c14 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,6 +17,7 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_skb_traces \ + EM(rxrpc_skb_ack, "ACK") \ EM(rxrpc_skb_cleaned, "CLN") \ EM(rxrpc_skb_cloned_jumbo, "CLJ") \ EM(rxrpc_skb_freed, "FRE") \ @@ -1257,7 +1258,7 @@ TRACE_EVENT(rxrpc_congest, memcpy(&__entry->sum, summary, sizeof(__entry->sum)); ), - TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s", + TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, __entry->ack_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), @@ -1265,8 +1266,8 @@ TRACE_EVENT(rxrpc_congest, __print_symbolic(__entry->sum.mode, rxrpc_congest_modes), __entry->sum.cwnd, __entry->sum.ssthresh, - __entry->sum.nr_acks, __entry->sum.nr_nacks, - __entry->sum.nr_new_acks, __entry->sum.nr_new_nacks, + __entry->sum.nr_acks, __entry->sum.saw_nacks, + __entry->sum.nr_new_acks, __entry->sum.nr_rot_new_acks, __entry->top - __entry->hard_ack, __entry->sum.cumulative_acks, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d84a17eada5..2143244e8ec3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6431,6 +6431,7 @@ void skb_condense(struct sk_buff *skb) */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } +EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5ec30e84360b..168d03b56ada 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -694,6 +694,8 @@ struct rxrpc_call { rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ + struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ + spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* @@ -702,10 +704,9 @@ struct rxrpc_call { struct rxrpc_ack_summary { u8 ack_reason; u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_nacks; /* Number of NACKs in packet */ u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_new_nacks; /* Number of new NACKs in packet */ u8 nr_rot_new_acks; /* Number of rotated new ACKs */ + bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ @@ -765,11 +766,8 @@ struct rxrpc_txbuf { unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ unsigned long flags; -#define RXRPC_TXBUF_ACKED 0 /* Set if ACK'd */ -#define RXRPC_TXBUF_NACKED 1 /* Set if NAK'd */ -#define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ -#define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ -#define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ +#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ struct { /* The packet for encrypting and DMA'ing. We align it such diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index dbfaf8170929..1e21a708390e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -132,48 +132,127 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { + struct rxrpc_ackpacket *ack = NULL; struct rxrpc_txbuf *txb; + struct sk_buff *ack_skb = NULL; unsigned long resend_at; rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; bool unacked = false; + unsigned int i; LIST_HEAD(retrans_queue); _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); + oldest = now; + + /* See if there's an ACK saved with a soft-ACK table in it. */ + if (call->acks_soft_tbl) { + spin_lock_bh(&call->acks_ack_lock); + ack_skb = call->acks_soft_tbl; + if (ack_skb) { + rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + } + spin_unlock_bh(&call->acks_ack_lock); + } + + if (list_empty(&call->tx_buffer)) + goto no_resend; spin_lock(&call->tx_lock); - /* Scan the packet list without dropping the lock and decide which of - * the packets in the Tx buffer we're going to resend and what the new - * resend timeout will be. - */ + if (list_empty(&call->tx_buffer)) + goto no_further_resend; + trace_rxrpc_resend(call); - oldest = now; - list_for_each_entry(txb, &call->tx_buffer, call_link) { - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - if (after(txb->seq, transmitted)) - break; + txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); - rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + /* Scan the soft ACK table without dropping the lock and resend any + * explicitly NAK'd packets. + */ + if (ack) { + for (i = 0; i < ack->nAcks; i++) { + rxrpc_seq_t seq; - if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) { - if (ktime_after(txb->last_sent, max_age)) { - if (ktime_before(txb->last_sent, oldest)) - oldest = txb->last_sent; + if (ack->acks[i] & 1) continue; + seq = ntohl(ack->firstPacket) + i; + if (after(txb->seq, transmitted)) + break; + if (after(txb->seq, seq)) + continue; /* A new hard ACK probably came in */ + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (txb->seq == seq) + goto found_txb; + } + goto no_further_resend; + + found_txb: + if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + continue; /* Ack point not yet reached */ + + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + rxrpc_get_call(call, rxrpc_call_got_tx); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } - unacked = true; + + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); + + if (list_is_last(&txb->call_link, &call->tx_buffer)) + goto no_further_resend; + txb = list_next_entry(txb, call_link); } + } - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); - list_move_tail(&txb->tx_link, &retrans_queue); + /* Fast-forward through the Tx queue to the point the peer says it has + * seen. Anything between the soft-ACK table and that point will get + * ACK'd or NACK'd in due course, so don't worry about it here; here we + * need to consider retransmitting anything beyond that point. + * + * Note that ACK for a packet can beat the update of tx_transmitted. + */ + if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + goto no_further_resend; + + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + continue; + if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + break; /* Not transmitted yet */ + + if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && + before(ntohl(txb->wire.serial), ntohl(ack->serial))) + goto do_resend; /* Wasn't accounted for by a more recent ping. */ + + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; + continue; + } + + do_resend: + unacked = true; + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + } } +no_further_resend: spin_unlock(&call->tx_lock); +no_resend: + rxrpc_free_skb(ack_skb, rxrpc_skb_freed); resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, @@ -201,8 +280,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) while ((txb = list_first_entry_or_null(&retrans_queue, struct rxrpc_txbuf, tx_link))) { list_del_init(&txb->tx_link); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); rxrpc_send_data_packet(call, txb); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index a3ae2ab45f9e..91771031ad3c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -162,6 +162,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); + spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; @@ -701,6 +702,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index e6e1267915de..5c17fed4b60f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -60,7 +60,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; if (summary->cumulative_acks > 0) cwnd += 1; @@ -71,7 +71,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; /* We analyse the number of packets that get ACK'd per RTT @@ -90,7 +90,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_PACKET_LOSS: - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; if (summary->new_low_nack) { @@ -128,7 +128,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } else { change = rxrpc_cong_progress; cwnd = call->cong_ssthresh; - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; } goto out; @@ -189,8 +189,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - if (!test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - summary->nr_rot_new_acks++; + summary->nr_rot_new_acks++; if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; @@ -661,22 +660,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - struct rxrpc_txbuf *txb; - rxrpc_seq_t top, bottom; - bool resend = false; - - bottom = READ_ONCE(call->acks_hard_ack) + 1; - top = READ_ONCE(call->acks_lost_top); - if (before(bottom, top)) { - list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); - resend = true; - } - } - - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) + if (after(call->acks_lost_top, call->acks_prev_seq) && + !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -749,41 +734,19 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - struct rxrpc_txbuf *txb; + unsigned int i; - list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { - if (before(txb->seq, seq)) - continue; - if (after_eq(txb->seq, seq + nr_acks)) - break; - switch (acks[txb->seq - seq]) { - case RXRPC_ACK_TYPE_ACK: + for (i = 0; i < nr_acks; i++) { + if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - /* A lot of the time the packet is going to - * have been ACK.'d already. - */ - clear_bit(RXRPC_TXBUF_NACKED, &txb->flags); - set_bit(RXRPC_TXBUF_ACKED, &txb->flags); summary->nr_new_acks++; - break; - case RXRPC_ACK_TYPE_NACK: - if (!summary->nr_nacks && - call->acks_lowest_nak != seq) { - call->acks_lowest_nak = seq; + } else { + if (!summary->saw_nacks && + call->acks_lowest_nak != seq + i) { + call->acks_lowest_nak = seq + i; summary->new_low_nack = true; } - summary->nr_nacks++; - if (test_bit(RXRPC_TXBUF_NACKED, &txb->flags)) - continue; - summary->nr_new_nacks++; - clear_bit(RXRPC_TXBUF_ACKED, &txb->flags); - set_bit(RXRPC_TXBUF_NACKED, &txb->flags); - set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); - break; - default: - return rxrpc_proto_abort("SFT", call, 0); + summary->saw_nacks = true; } } } @@ -825,12 +788,10 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - union { - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo info; - u8 acks[RXRPC_MAXACKS]; - } buf; + struct rxrpc_ackinfo info; + struct sk_buff *skb_old = NULL, *skb_put = skb; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -838,30 +799,28 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) { - _debug("extraction failure"); - return rxrpc_proto_abort("XAK", call, 0); + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { + rxrpc_proto_abort("XAK", call, 0); + goto out_not_locked; } - offset += sizeof(buf.ack); + offset += sizeof(ack); ack_serial = sp->hdr.serial; - acked_serial = ntohl(buf.ack.serial); - first_soft_ack = ntohl(buf.ack.firstPacket); - prev_pkt = ntohl(buf.ack.previousPacket); + acked_serial = ntohl(ack.serial); + first_soft_ack = ntohl(ack.firstPacket); + prev_pkt = ntohl(ack.previousPacket); hard_ack = first_soft_ack - 1; - nr_acks = buf.ack.nAcks; - summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? - buf.ack.reason : RXRPC_ACK__INVALID); + nr_acks = ack.nAcks; + summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? + ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - rxrpc_inc_stat(call->rxnet, stat_rx_acks[buf.ack.reason]); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (buf.ack.reason) { + switch (ack.reason) { case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); break; @@ -876,7 +835,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) break; } - if (buf.ack.reason == RXRPC_ACK_PING) { + if (ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); @@ -889,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -902,7 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && call->acks_hard_ack == 0 && @@ -917,14 +876,19 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - return; + goto out_not_locked; } - buf.info.rxMTU = 0; + info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info) && - skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(info) && + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { + rxrpc_proto_abort("XAI", call, 0); + goto out_not_locked; + } + + if (nr_acks > 0) + skb_condense(skb); spin_lock(&call->input_lock); @@ -940,13 +904,22 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; - if (buf.ack.reason != RXRPC_ACK_PING && - after(acked_serial, call->acks_highest_serial)) - call->acks_highest_serial = acked_serial; + switch (ack.reason) { + case RXRPC_ACK_PING: + break; + case RXRPC_ACK_PING_RESPONSE: + rxrpc_input_ping_response(call, skb->tstamp, acked_serial, + ack_serial); + fallthrough; + default: + if (after(acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = acked_serial; + break; + } /* Parse rwind and mtu sizes if provided. */ - if (buf.info.rxMTU) - rxrpc_input_ackinfo(call, skb, &buf.info); + if (info.rxMTU) + rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) { rxrpc_proto_abort("AK0", call, 0); @@ -982,12 +955,24 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + if (offset > (int)skb->len - nr_acks) { rxrpc_proto_abort("XSA", call, 0); goto out; } - rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, - &summary); + + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = skb; + spin_unlock(&call->acks_ack_lock); + + rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, + nr_acks, &summary); + skb_put = NULL; + } else if (call->acks_soft_tbl) { + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = NULL; + spin_unlock(&call->acks_ack_lock); } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && @@ -999,6 +984,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); out: spin_unlock(&call->input_lock); +out_not_locked: + rxrpc_free_skb(skb_put, rxrpc_skb_freed); + rxrpc_free_skb(skb_old, rxrpc_skb_freed); } /* @@ -1071,7 +1059,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - break; + goto no_free; case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a96ae7f58148..9b567aff3e84 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -600,7 +600,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) - __releases(&call->user_mutex) { enum rxrpc_call_state state; struct rxrpc_call *call; -- cgit v1.2.3 From 1fc4fa2ac93dcf3542f2dc6f7ff88fb022da5116 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 3 Oct 2022 18:49:11 +0100 Subject: rxrpc: Fix congestion management rxrpc has a problem in its congestion management in that it saves the congestion window size (cwnd) from one call to another, but if this is 0 at the time is saved, then the next call may not actually manage to ever transmit anything. To this end: (1) Don't save cwnd between calls, but rather reset back down to the initial cwnd and re-enter slow-start if data transmission is idle for more than an RTT. (2) Preserve ssthresh instead, as that is a handy estimate of pipe capacity. Knowing roughly when to stop slow start and enter congestion avoidance can reduce the tendency to overshoot and drop larger amounts of packets when probing. In future, cwind growth also needs to be constrained when the window isn't being filled due to being application limited. Reported-by: Simon Wilkinson cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 9 +++++---- net/rxrpc/call_accept.c | 3 ++- net/rxrpc/call_object.c | 7 ++++++- net/rxrpc/conn_client.c | 3 ++- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 21 ++++++++++++++++++++- net/rxrpc/output.c | 1 + net/rxrpc/peer_object.c | 7 +------ net/rxrpc/proc.c | 4 ++-- net/rxrpc/sendmsg.c | 22 +++++++++++++++++++--- 11 files changed, 60 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a11de55c3c14..b9886d1df825 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -193,6 +193,7 @@ EM(rxrpc_cong_new_low_nack, " NewLowN") \ EM(rxrpc_cong_no_change, " -") \ EM(rxrpc_cong_progress, " Progres") \ + EM(rxrpc_cong_idle_reset, " IdleRes") \ EM(rxrpc_cong_retransmit_again, " ReTxAgn") \ EM(rxrpc_cong_rtt_window_end, " RttWinE") \ E_(rxrpc_cong_saw_nack, " SawNack") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 775eb91aabb2..6bbe28ecf583 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -332,7 +332,7 @@ struct rxrpc_peer { u32 rto_j; /* Retransmission timeout in jiffies */ u8 backoff; /* Backoff timeout */ - u8 cong_cwnd; /* Congestion window size */ + u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* @@ -626,6 +626,7 @@ struct rxrpc_call { u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 + ktime_t tx_last_sent; /* Last time a transmission occurred */ /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ @@ -687,10 +688,10 @@ struct rxrpc_call { * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { + u16 nr_acks; /* Number of ACKs in packet */ + u16 nr_new_acks; /* Number of new ACKs in packet */ + u16 nr_rot_new_acks; /* Number of rotated new ACKs */ u8 ack_reason; - u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_rot_new_acks; /* Number of rotated new ACKs */ bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index d8db277d5ebe..48790ee77019 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -324,7 +324,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); - call->cong_cwnd = call->peer->cong_cwnd; + call->cong_ssthresh = call->peer->cong_ssthresh; + call->tx_last_sent = ktime_get_real(); return call; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index aa19daaa487b..1befe22cd301 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -166,7 +166,12 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->cong_cwnd = 2; + if (RXRPC_TX_SMSS > 2190) + call->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + call->cong_cwnd = 3; + else + call->cong_cwnd = 4; call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..f020f308ed9e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -363,7 +363,8 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, if (!cp->peer) goto error; - call->cong_cwnd = cp->peer->cong_cwnd; + call->tx_last_sent = ktime_get_real(); + call->cong_ssthresh = cp->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; else diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index f7ea71ae6159..156bd26daf74 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -207,7 +207,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - call->peer->cong_cwnd = call->cong_cwnd; + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 5c17fed4b60f..bdf70b81addc 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -58,6 +58,25 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, summary->cumulative_acks = cumulative_acks; summary->dup_acks = call->cong_dup_acks; + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if ((call->cong_mode == RXRPC_CALL_SLOW_START || + call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && + ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real()) + ) { + change = rxrpc_cong_idle_reset; + summary->mode = RXRPC_CALL_SLOW_START; + if (RXRPC_TX_SMSS > 2190) + summary->cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + summary->cwnd = 3; + else + summary->cwnd = 4; + } + switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: if (summary->saw_nacks) @@ -205,7 +224,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, if (call->acks_lowest_nak == call->acks_hard_ack) { call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { + } else if (after(to, call->acks_lowest_nak)) { summary->new_low_nack = true; call->acks_lowest_nak = to; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 2c3f7e4e30d7..46432e70a16b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -501,6 +501,7 @@ dont_set_request_ack: done: if (ret >= 0) { + call->tx_last_sent = txb->last_sent; if (txb->wire.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 26d2ae9baaf2..041a51225c5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -227,12 +227,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); - if (RXRPC_TX_SMSS > 2190) - peer->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - peer->cong_cwnd = 3; - else - peer->cong_cwnd = 4; + peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 0807753ec2dc..fae22a8b38d6 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -217,7 +217,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " Use CW MTU LastUse RTT RTO\n" + " Use SST MTU LastUse RTT RTO\n" ); return 0; } @@ -235,7 +235,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) lbuff, rbuff, refcount_read(&peer->ref), - peer->cong_cwnd, + peer->cong_ssthresh, peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 9b567aff3e84..e5fd8a95bf71 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,11 +22,27 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size = - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); + unsigned int win_size; rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if (ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real())) { + if (RXRPC_TX_SMSS > 2190) + win_size = 2; + else if (RXRPC_TX_SMSS > 1095) + win_size = 3; + else + win_size = 4; + win_size += call->cong_extra; + } else { + win_size = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + } + if (_tx_win) *_tx_win = tx_win; return call->tx_top - tx_win < win_size; -- cgit v1.2.3 From bd039b5ea2a91ea707ee8539df26456bd5be80af Mon Sep 17 00:00:00 2001 From: Andy Ren Date: Mon, 7 Nov 2022 09:42:42 -0800 Subject: net/core: Allow live renaming when an interface is up Allow a network interface to be renamed when the interface is up. As described in the netconsole documentation [1], when netconsole is used as a built-in, it will bring up the specified interface as soon as possible. As a result, user space will not be able to rename the interface since the kernel disallows renaming of interfaces that are administratively up unless the 'IFF_LIVE_RENAME_OK' private flag was set by the kernel. The original solution [2] to this problem was to add a new parameter to the netconsole configuration parameters that allows renaming of the interface used by netconsole while it is administratively up. However, during the discussion that followed, it became apparent that we have no reason to keep the current restriction and instead we should allow user space to rename interfaces regardless of their administrative state: 1. The restriction was put in place over 20 years ago when renaming was only possible via IOCTL and before rtnetlink started notifying user space about such changes like it does today. 2. The 'IFF_LIVE_RENAME_OK' flag was added over 3 years ago in version 5.2 and no regressions were reported. 3. In-kernel listeners to 'NETDEV_CHANGENAME' do not seem to care about the administrative state of interface. Therefore, allow user space to rename running interfaces by removing the restriction and the associated 'IFF_LIVE_RENAME_OK' flag. Help in possible triage by emitting a message to the kernel log that an interface was renamed while UP. [1] https://www.kernel.org/doc/Documentation/networking/netconsole.rst [2] https://lore.kernel.org/netdev/20221102002420.2613004-1-andy.ren@getcruise.com/ Signed-off-by: Andy Ren Reviewed-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 +--- net/core/dev.c | 19 ++----------------- net/core/failover.c | 6 +++--- 3 files changed, 6 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d45713a06568..4be87b89e481 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1650,7 +1650,6 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device - * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN @@ -1686,7 +1685,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, - IFF_LIVE_RENAME_OK = 1<<30, + /* was IFF_LIVE_RENAME_OK */ IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; @@ -1721,7 +1720,6 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK #define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR /* Specifies the type of the struct net_device::ml_priv pointer */ diff --git a/net/core/dev.c b/net/core/dev.c index 3bacee3bee78..707de6b841d0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,22 +1163,6 @@ int dev_change_name(struct net_device *dev, const char *newname) net = dev_net(dev); - /* Some auto-enslaved devices e.g. failover slaves are - * special, as userspace might rename the device after - * the interface had been brought up and running since - * the point kernel initiated auto-enslavement. Allow - * live name change even when these slave devices are - * up and running. - * - * Typically, users of these auto-enslaving devices - * don't actually care about slave name change, as - * they are supposed to operate on master interface - * directly. - */ - if (dev->flags & IFF_UP && - likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) - return -EBUSY; - down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { @@ -1195,7 +1179,8 @@ int dev_change_name(struct net_device *dev, const char *newname) } if (oldname[0] && !strchr(oldname, '%')) - netdev_info(dev, "renamed from %s\n", oldname); + netdev_info(dev, "renamed from %s%s\n", oldname, + dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; dev->name_assign_type = NET_NAME_RENAMED; diff --git a/net/core/failover.c b/net/core/failover.c index 864d2d83eff4..655411c4ca51 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) -- cgit v1.2.3 From 3e52fba03a20234abc65a656cef063a1045d9723 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 8 Nov 2022 14:22:06 +0100 Subject: net: introduce a helper to move notifier block to different namespace Currently, net_dev() netdev notifier variant follows the netdev with per-net notifier from namespace to namespace. This is implemented by move_netdevice_notifiers_dev_net() helper. For devlink it is needed to re-register per-net notifier during devlink reload. Introduce a new helper called move_netdevice_notifier_net() and share the unregister/register code with existing move_netdevice_notifiers_dev_net() helper. Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ net/core/dev.c | 22 ++++++++++++++++++---- 2 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4be87b89e481..02a2318da7c7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2826,6 +2826,8 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); diff --git a/net/core/dev.c b/net/core/dev.c index 707de6b841d0..117e830cabb0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1861,6 +1861,22 @@ int unregister_netdevice_notifier_net(struct net *net, } EXPORT_SYMBOL(unregister_netdevice_notifier_net); +static void __move_netdevice_notifier_net(struct net *src_net, + struct net *dst_net, + struct notifier_block *nb) +{ + __unregister_netdevice_notifier_net(src_net, nb); + __register_netdevice_notifier_net(dst_net, nb, true); +} + +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb) +{ + rtnl_lock(); + __move_netdevice_notifier_net(src_net, dst_net, nb); + rtnl_unlock(); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -1897,10 +1913,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev, { struct netdev_net_notifier *nn; - list_for_each_entry(nn, &dev->net_notifier_list, list) { - __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); - __register_netdevice_notifier_net(net, nn->nb, true); - } + list_for_each_entry(nn, &dev->net_notifier_list, list) + __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** -- cgit v1.2.3 From 27fabd02abf30a9df9899f92d467591c7eabb1ba Mon Sep 17 00:00:00 2001 From: "Hans J. Schultz" Date: Tue, 8 Nov 2022 11:47:08 +0100 Subject: bridge: switchdev: Allow device drivers to install locked FDB entries When the bridge is offloaded to hardware, FDB entries are learned and aged-out by the hardware. Some device drivers synchronize the hardware and software FDBs by generating switchdev events towards the bridge. When a port is locked, the hardware must not learn autonomously, as otherwise any host will blindly gain authorization. Instead, the hardware should generate events regarding hosts that are trying to gain authorization and their MAC addresses should be notified by the device driver as locked FDB entries towards the bridge driver. Allow device drivers to notify the bridge driver about such entries by extending the 'switchdev_notifier_fdb_info' structure with the 'locked' bit. The bit can only be set by device drivers and not by the bridge driver. Prevent a locked entry from being installed if MAB is not enabled on the bridge port. If an entry already exists in the bridge driver, reject the locked entry if the current entry does not have the "locked" flag set or if it points to a different port. The same semantics are implemented in the software data path. Signed-off-by: Hans J. Schultz Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Reviewed-by: Vladimir Oltean Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/net/switchdev.h | 1 + net/bridge/br.c | 3 ++- net/bridge/br_fdb.c | 22 ++++++++++++++++++++-- net/bridge/br_private.h | 2 +- net/bridge/br_switchdev.c | 4 ++++ 5 files changed, 28 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 7dcdc97c0bc3..ca0312b78294 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -248,6 +248,7 @@ struct switchdev_notifier_fdb_info { u16 vid; u8 added_by_user:1, is_local:1, + locked:1, offloaded:1; }; diff --git a/net/bridge/br.c b/net/bridge/br.c index 145999b8c355..4f5098d33a46 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,7 +166,8 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, false); + fdb_info->vid, + fdb_info->locked, false); if (err) { err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 3b83af4458b8..e69a872bfc1d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1139,7 +1139,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, "FDB entry towards bridge must be permanent"); return -EINVAL; } - err = br_fdb_external_learn_add(br, p, addr, vid, true); + err = br_fdb_external_learn_add(br, p, addr, vid, false, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1377,7 +1377,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, + const unsigned char *addr, u16 vid, bool locked, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1386,6 +1386,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, trace_br_fdb_external_learn_add(br, p, addr, vid); + if (locked && (!p || !(p->flags & BR_PORT_MAB))) + return -EINVAL; + spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); @@ -1398,6 +1401,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (!p) flags |= BIT(BR_FDB_LOCAL); + if (locked) + flags |= BIT(BR_FDB_LOCKED); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1405,6 +1411,13 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { + if (locked && + (!test_bit(BR_FDB_LOCKED, &fdb->flags) || + READ_ONCE(fdb->dst) != p)) { + err = -EINVAL; + goto err_unlock; + } + fdb->updated = jiffies; if (READ_ONCE(fdb->dst) != p) { @@ -1421,6 +1434,11 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (locked != test_bit(BR_FDB_LOCKED, &fdb->flags)) { + change_bit(BR_FDB_LOCKED, &fdb->flags); + modified = true; + } + if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 4ce8b8e5ae0b..4c4fda930068 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -811,7 +811,7 @@ int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, - bool swdev_notify); + bool locked, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool swdev_notify); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8f3d76c751dd..8a0abe35137d 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -136,6 +136,7 @@ static void br_switchdev_fdb_populate(struct net_bridge *br, item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); + item->locked = false; item->info.dev = (!p || item->is_local) ? br->dev : p->dev; item->info.ctx = ctx; } @@ -146,6 +147,9 @@ br_switchdev_fdb_notify(struct net_bridge *br, { struct switchdev_notifier_fdb_info item; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { -- cgit v1.2.3 From 2640a82bbc08393c846c7b55178079bb8ca31a8c Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Tue, 8 Nov 2022 11:47:10 +0100 Subject: devlink: Add packet traps for 802.1X operation Add packet traps for 802.1X operation. The "eapol" control trap is used to trap EAPOL packets and is required for the correct operation of the control plane. The "locked_port" drop trap can be enabled to gain visibility into packets that were dropped by the device due to the locked bridge port check. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-trap.rst | 13 +++++++++++++ include/net/devlink.h | 9 +++++++++ net/core/devlink.c | 3 +++ 3 files changed, 25 insertions(+) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 90d1381b88de..2c14dfe69b3a 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -485,6 +485,16 @@ be added to the following table: - Traps incoming packets that the device decided to drop because the destination MAC is not configured in the MAC table and the interface is not in promiscuous mode + * - ``eapol`` + - ``control`` + - Traps "Extensible Authentication Protocol over LAN" (EAPOL) packets + specified in IEEE 802.1X + * - ``locked_port`` + - ``drop`` + - Traps packets that the device decided to drop because they failed the + locked bridge port check. That is, packets that were received via a + locked port and whose {SMAC, VID} does not correspond to an FDB entry + pointing to the port Driver-specific Packet Traps ============================ @@ -589,6 +599,9 @@ narrow. The description of these groups must be added to the following table: * - ``parser_error_drops`` - Contains packet traps for packets that were marked by the device during parsing as erroneous + * - ``eapol`` + - Contains packet traps for "Extensible Authentication Protocol over LAN" + (EAPOL) packets specified in IEEE 802.1X Packet Trap Policers ==================== diff --git a/include/net/devlink.h b/include/net/devlink.h index fa6e936af1a5..611a23a3deb2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -894,6 +894,8 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_NEXTHOP, DEVLINK_TRAP_GENERIC_ID_DMAC_FILTER, + DEVLINK_TRAP_GENERIC_ID_EAPOL, + DEVLINK_TRAP_GENERIC_ID_LOCKED_PORT, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -930,6 +932,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP, DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_EAPOL, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -1121,6 +1124,10 @@ enum devlink_trap_group_generic_id { "blackhole_nexthop" #define DEVLINK_TRAP_GENERIC_NAME_DMAC_FILTER \ "dmac_filter" +#define DEVLINK_TRAP_GENERIC_NAME_EAPOL \ + "eapol" +#define DEVLINK_TRAP_GENERIC_NAME_LOCKED_PORT \ + "locked_port" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -1174,6 +1181,8 @@ enum devlink_trap_group_generic_id { "acl_trap" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \ "parser_error_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EAPOL \ + "eapol" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \ _metadata_cap) \ diff --git a/net/core/devlink.c b/net/core/devlink.c index ea0b319385fc..6bbe230c4ec5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -11734,6 +11734,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), DEVLINK_TRAP(DMAC_FILTER, DROP), + DEVLINK_TRAP(EAPOL, CONTROL), + DEVLINK_TRAP(LOCKED_PORT, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -11769,6 +11771,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), + DEVLINK_TRAP_GROUP(EAPOL), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) -- cgit v1.2.3 From f6479ea4e5990e17b9690d66474198dcdba1b2c1 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 8 Nov 2022 14:25:56 +0000 Subject: net: mdio: add mdiodev_c45_(read|write) Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski --- include/linux/mdio.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 00177567cfef..f7fbbf3069e7 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -488,6 +488,19 @@ static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); } +static inline int mdiodev_c45_read(struct mdio_device *mdiodev, int devad, + u16 regnum) +{ + return mdiobus_c45_read(mdiodev->bus, mdiodev->addr, devad, regnum); +} + +static inline int mdiodev_c45_write(struct mdio_device *mdiodev, u32 devad, + u16 regnum, u16 val) +{ + return mdiobus_c45_write(mdiodev->bus, mdiodev->addr, devad, regnum, + val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); -- cgit v1.2.3 From fd325cd648f15eb9a8b32a68de3bafc72bcfe753 Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:25 -0700 Subject: net: mana: Move header files to a common location In preparation to add MANA RDMA driver, move all the required header files to a common location for use by both Ethernet and RDMA drivers. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-8-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- MAINTAINERS | 1 + drivers/net/ethernet/microsoft/mana/gdma.h | 689 --------------------- drivers/net/ethernet/microsoft/mana/gdma_main.c | 2 +- drivers/net/ethernet/microsoft/mana/hw_channel.c | 4 +- drivers/net/ethernet/microsoft/mana/hw_channel.h | 195 ------ drivers/net/ethernet/microsoft/mana/mana.h | 650 ------------------- .../net/ethernet/microsoft/mana/mana_auxiliary.h | 10 - drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +- drivers/net/ethernet/microsoft/mana/mana_en.c | 4 +- drivers/net/ethernet/microsoft/mana/mana_ethtool.c | 2 +- drivers/net/ethernet/microsoft/mana/shm_channel.c | 2 +- drivers/net/ethernet/microsoft/mana/shm_channel.h | 21 - include/net/mana/gdma.h | 689 +++++++++++++++++++++ include/net/mana/hw_channel.h | 195 ++++++ include/net/mana/mana.h | 650 +++++++++++++++++++ include/net/mana/mana_auxiliary.h | 10 + include/net/mana/shm_channel.h | 21 + 17 files changed, 1574 insertions(+), 1573 deletions(-) delete mode 100644 drivers/net/ethernet/microsoft/mana/gdma.h delete mode 100644 drivers/net/ethernet/microsoft/mana/hw_channel.h delete mode 100644 drivers/net/ethernet/microsoft/mana/mana.h delete mode 100644 drivers/net/ethernet/microsoft/mana/mana_auxiliary.h delete mode 100644 drivers/net/ethernet/microsoft/mana/shm_channel.h create mode 100644 include/net/mana/gdma.h create mode 100644 include/net/mana/hw_channel.h create mode 100644 include/net/mana/mana.h create mode 100644 include/net/mana/mana_auxiliary.h create mode 100644 include/net/mana/shm_channel.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 379945f82a64..441a65d41eb4 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9541,6 +9541,7 @@ F: include/asm-generic/hyperv-tlfs.h F: include/asm-generic/mshyperv.h F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h +F: include/net/mana F: include/uapi/linux/hyperv.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/ diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h deleted file mode 100644 index 72eaec2470c0..000000000000 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ /dev/null @@ -1,689 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _GDMA_H -#define _GDMA_H - -#include -#include - -#include "shm_channel.h" - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -enum gdma_request_type { - GDMA_VERIFY_VF_DRIVER_VERSION = 1, - GDMA_QUERY_MAX_RESOURCES = 2, - GDMA_LIST_DEVICES = 3, - GDMA_REGISTER_DEVICE = 4, - GDMA_DEREGISTER_DEVICE = 5, - GDMA_GENERATE_TEST_EQE = 10, - GDMA_CREATE_QUEUE = 12, - GDMA_DISABLE_QUEUE = 13, - GDMA_CREATE_DMA_REGION = 25, - GDMA_DMA_REGION_ADD_PAGES = 26, - GDMA_DESTROY_DMA_REGION = 27, -}; - -enum gdma_queue_type { - GDMA_INVALID_QUEUE, - GDMA_SQ, - GDMA_RQ, - GDMA_CQ, - GDMA_EQ, -}; - -enum gdma_work_request_flags { - GDMA_WR_NONE = 0, - GDMA_WR_OOB_IN_SGL = BIT(0), - GDMA_WR_PAD_BY_SGE0 = BIT(1), -}; - -enum gdma_eqe_type { - GDMA_EQE_COMPLETION = 3, - GDMA_EQE_TEST_EVENT = 64, - GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, - GDMA_EQE_HWC_INIT_DATA = 130, - GDMA_EQE_HWC_INIT_DONE = 131, -}; - -enum { - GDMA_DEVICE_NONE = 0, - GDMA_DEVICE_HWC = 1, - GDMA_DEVICE_MANA = 2, -}; - -struct gdma_resource { - /* Protect the bitmap */ - spinlock_t lock; - - /* The bitmap size in bits. */ - u32 size; - - /* The bitmap tracks the resources. */ - unsigned long *map; -}; - -union gdma_doorbell_entry { - u64 as_uint64; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 31; - u64 arm : 1; - } cq; - - struct { - u64 id : 24; - u64 wqe_cnt : 8; - u64 tail_ptr : 32; - } rq; - - struct { - u64 id : 24; - u64 reserved : 8; - u64 tail_ptr : 32; - } sq; - - struct { - u64 id : 16; - u64 reserved : 16; - u64 tail_ptr : 31; - u64 arm : 1; - } eq; -}; /* HW DATA */ - -struct gdma_msg_hdr { - u32 hdr_type; - u32 msg_type; - u16 msg_version; - u16 hwc_msg_id; - u32 msg_size; -}; /* HW DATA */ - -struct gdma_dev_id { - union { - struct { - u16 type; - u16 instance; - }; - - u32 as_uint32; - }; -}; /* HW DATA */ - -struct gdma_req_hdr { - struct gdma_msg_hdr req; - struct gdma_msg_hdr resp; /* The expected response */ - struct gdma_dev_id dev_id; - u32 activity_id; -}; /* HW DATA */ - -struct gdma_resp_hdr { - struct gdma_msg_hdr response; - struct gdma_dev_id dev_id; - u32 activity_id; - u32 status; - u32 reserved; -}; /* HW DATA */ - -struct gdma_general_req { - struct gdma_req_hdr hdr; -}; /* HW DATA */ - -#define GDMA_MESSAGE_V1 1 - -struct gdma_general_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define GDMA_STANDARD_HEADER_TYPE 0 - -static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code, - u32 req_size, u32 resp_size) -{ - hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->req.msg_type = code; - hdr->req.msg_version = GDMA_MESSAGE_V1; - hdr->req.msg_size = req_size; - - hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE; - hdr->resp.msg_type = code; - hdr->resp.msg_version = GDMA_MESSAGE_V1; - hdr->resp.msg_size = resp_size; -} - -/* The 16-byte struct is part of the GDMA work queue entry (WQE). */ -struct gdma_sge { - u64 address; - u32 mem_key; - u32 size; -}; /* HW DATA */ - -struct gdma_wqe_request { - struct gdma_sge *sgl; - u32 num_sge; - - u32 inline_oob_size; - const void *inline_oob_data; - - u32 flags; - u32 client_data_unit; -}; - -enum gdma_page_type { - GDMA_PAGE_TYPE_4K, -}; - -#define GDMA_INVALID_DMA_REGION 0 - -struct gdma_mem_info { - struct device *dev; - - dma_addr_t dma_handle; - void *virt_addr; - u64 length; - - /* Allocated by the PF driver */ - u64 gdma_region; -}; - -#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 - -struct gdma_dev { - struct gdma_context *gdma_context; - - struct gdma_dev_id dev_id; - - u32 pdid; - u32 doorbell; - u32 gpa_mkey; - - /* GDMA driver specific pointer */ - void *driver_data; - - struct auxiliary_device *adev; -}; - -#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE - -#define GDMA_CQE_SIZE 64 -#define GDMA_EQE_SIZE 16 -#define GDMA_MAX_SQE_SIZE 512 -#define GDMA_MAX_RQE_SIZE 256 - -#define GDMA_COMP_DATA_SIZE 0x3C - -#define GDMA_EVENT_DATA_SIZE 0xC - -/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */ -#define GDMA_WQE_BU_SIZE 32 - -#define INVALID_PDID UINT_MAX -#define INVALID_DOORBELL UINT_MAX -#define INVALID_MEM_KEY UINT_MAX -#define INVALID_QUEUE_ID UINT_MAX -#define INVALID_PCI_MSIX_INDEX UINT_MAX - -struct gdma_comp { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - u32 wq_num; - bool is_sq; -}; - -struct gdma_event { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u8 type; -}; - -struct gdma_queue; - -struct mana_eq { - struct gdma_queue *eq; -}; - -typedef void gdma_eq_callback(void *context, struct gdma_queue *q, - struct gdma_event *e); - -typedef void gdma_cq_callback(void *context, struct gdma_queue *q); - -/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE - * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the - * driver increases the 'head' in BUs rather than in bytes, and notifies - * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track - * the HW head, and increases the 'head' by 1 for every processed EQE/CQE. - * - * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is - * processed, the driver increases the 'tail' to indicate that WQEs have - * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ. - * - * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures - * that the EQ/CQ is big enough so they can't overflow, and the driver uses - * the owner bits mechanism to detect if the queue has become empty. - */ -struct gdma_queue { - struct gdma_dev *gdma_dev; - - enum gdma_queue_type type; - u32 id; - - struct gdma_mem_info mem_info; - - void *queue_mem_ptr; - u32 queue_size; - - bool monitor_avl_buf; - - u32 head; - u32 tail; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - bool disable_needed; - - gdma_eq_callback *callback; - void *context; - - unsigned int msix_index; - - u32 log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent; /* For CQ/EQ relationship */ - } cq; - }; -}; - -struct gdma_queue_spec { - enum gdma_queue_type type; - bool monitor_avl_buf; - unsigned int queue_size; - - /* Extra fields specific to EQ/CQ. */ - union { - struct { - gdma_eq_callback *callback; - void *context; - - unsigned long log2_throttle_limit; - } eq; - - struct { - gdma_cq_callback *callback; - void *context; - - struct gdma_queue *parent_eq; - - } cq; - }; -}; - -struct gdma_irq_context { - void (*handler)(void *arg); - void *arg; -}; - -struct gdma_context { - struct device *dev; - - /* Per-vPort max number of queues */ - unsigned int max_num_queues; - unsigned int max_num_msix; - unsigned int num_msix_usable; - struct gdma_resource msix_resource; - struct gdma_irq_context *irq_contexts; - - /* This maps a CQ index to the queue structure. */ - unsigned int max_num_cqs; - struct gdma_queue **cq_table; - - /* Protect eq_test_event and test_event_eq_id */ - struct mutex eq_test_event_mutex; - struct completion eq_test_event; - u32 test_event_eq_id; - - bool is_pf; - phys_addr_t bar0_pa; - void __iomem *bar0_va; - void __iomem *shm_base; - void __iomem *db_page_base; - phys_addr_t phys_db_page_base; - u32 db_page_size; - - /* Shared memory chanenl (used to bootstrap HWC) */ - struct shm_channel shm_channel; - - /* Hardware communication channel (HWC) */ - struct gdma_dev hwc; - - /* Azure network adapter */ - struct gdma_dev mana; -}; - -#define MAX_NUM_GDMA_DEVICES 4 - -static inline bool mana_gd_is_mana(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_MANA; -} - -static inline bool mana_gd_is_hwc(struct gdma_dev *gd) -{ - return gd->dev_id.type == GDMA_DEVICE_HWC; -} - -u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset); -u32 mana_gd_wq_avail_space(struct gdma_queue *wq); - -int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq); - -int mana_gd_create_hwc_queue(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_eq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, - const struct gdma_queue_spec *spec, - struct gdma_queue **queue_ptr); - -void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); - -int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); - -void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); - -struct gdma_wqe { - u32 reserved :24; - u32 last_vbytes :8; - - union { - u32 flags; - - struct { - u32 num_sge :8; - u32 inline_oob_size_div4:3; - u32 client_oob_in_sgl :1; - u32 reserved1 :4; - u32 client_data_unit :14; - u32 reserved2 :2; - }; - }; -}; /* HW DATA */ - -#define INLINE_OOB_SMALL_SIZE 8 -#define INLINE_OOB_LARGE_SIZE 24 - -#define MAX_TX_WQE_SIZE 512 -#define MAX_RX_WQE_SIZE 256 - -struct gdma_cqe { - u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; - - union { - u32 as_uint32; - - struct { - u32 wq_num : 24; - u32 is_sq : 1; - u32 reserved : 4; - u32 owner_bits : 3; - }; - } cqe_info; -}; /* HW DATA */ - -#define GDMA_CQE_OWNER_BITS 3 - -#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1) - -#define SET_ARM_BIT 1 - -#define GDMA_EQE_OWNER_BITS 3 - -union gdma_eqe_info { - u32 as_uint32; - - struct { - u32 type : 8; - u32 reserved1 : 8; - u32 client_id : 2; - u32 reserved2 : 11; - u32 owner_bits : 3; - }; -}; /* HW DATA */ - -#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1) -#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries)) - -struct gdma_eqe { - u32 details[GDMA_EVENT_DATA_SIZE / 4]; - u32 eqe_info; -}; /* HW DATA */ - -#define GDMA_REG_DB_PAGE_OFFSET 8 -#define GDMA_REG_DB_PAGE_SIZE 0x10 -#define GDMA_REG_SHM_OFFSET 0x18 - -#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 -#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 -#define GDMA_PF_REG_SHM_OFF 0x70 - -#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 - -#define MANA_PF_DEVICE_ID 0x00B9 -#define MANA_VF_DEVICE_ID 0x00BA - -struct gdma_posted_wqe_info { - u32 wqe_size_in_bu; -}; - -/* GDMA_GENERATE_TEST_EQE */ -struct gdma_generate_test_event_req { - struct gdma_req_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_VERIFY_VF_DRIVER_VERSION */ -enum { - GDMA_PROTOCOL_V1 = 1, - GDMA_PROTOCOL_FIRST = GDMA_PROTOCOL_V1, - GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, -}; - -#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) - -#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT - -#define GDMA_DRV_CAP_FLAGS2 0 - -#define GDMA_DRV_CAP_FLAGS3 0 - -#define GDMA_DRV_CAP_FLAGS4 0 - -struct gdma_verify_ver_req { - struct gdma_req_hdr hdr; - - /* Mandatory fields required for protocol establishment */ - u64 protocol_ver_min; - u64 protocol_ver_max; - - /* Gdma Driver Capability Flags */ - u64 gd_drv_cap_flags1; - u64 gd_drv_cap_flags2; - u64 gd_drv_cap_flags3; - u64 gd_drv_cap_flags4; - - /* Advisory fields */ - u64 drv_ver; - u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */ - u32 reserved; - u32 os_ver_major; - u32 os_ver_minor; - u32 os_ver_build; - u32 os_ver_platform; - u64 reserved_2; - u8 os_ver_str1[128]; - u8 os_ver_str2[128]; - u8 os_ver_str3[128]; - u8 os_ver_str4[128]; -}; /* HW DATA */ - -struct gdma_verify_ver_resp { - struct gdma_resp_hdr hdr; - u64 gdma_protocol_ver; - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; -}; /* HW DATA */ - -/* GDMA_QUERY_MAX_RESOURCES */ -struct gdma_query_max_resources_resp { - struct gdma_resp_hdr hdr; - u32 status; - u32 max_sq; - u32 max_rq; - u32 max_cq; - u32 max_eq; - u32 max_db; - u32 max_mst; - u32 max_cq_mod_ctx; - u32 max_mod_cq; - u32 max_msix; -}; /* HW DATA */ - -/* GDMA_LIST_DEVICES */ -struct gdma_list_devices_resp { - struct gdma_resp_hdr hdr; - u32 num_of_devs; - u32 reserved; - struct gdma_dev_id devs[64]; -}; /* HW DATA */ - -/* GDMA_REGISTER_DEVICE */ -struct gdma_register_device_resp { - struct gdma_resp_hdr hdr; - u32 pdid; - u32 gpa_mkey; - u32 db_id; -}; /* HW DATA */ - -/* GDMA_CREATE_QUEUE */ -struct gdma_create_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 reserved1; - u32 pdid; - u32 doolbell_id; - u64 gdma_region; - u32 reserved2; - u32 queue_size; - u32 log2_throttle_limit; - u32 eq_pci_msix_index; - u32 cq_mod_ctx_id; - u32 cq_parent_eq_id; - u8 rq_drop_on_overrun; - u8 rq_err_on_wqe_overflow; - u8 rq_chain_rec_wqes; - u8 sq_hw_db; - u32 reserved3; -}; /* HW DATA */ - -struct gdma_create_queue_resp { - struct gdma_resp_hdr hdr; - u32 queue_index; -}; /* HW DATA */ - -/* GDMA_DISABLE_QUEUE */ -struct gdma_disable_queue_req { - struct gdma_req_hdr hdr; - u32 type; - u32 queue_index; - u32 alloc_res_id_on_creation; -}; /* HW DATA */ - -/* GDMA_CREATE_DMA_REGION */ -struct gdma_create_dma_region_req { - struct gdma_req_hdr hdr; - - /* The total size of the DMA region */ - u64 length; - - /* The offset in the first page */ - u32 offset_in_page; - - /* enum gdma_page_type */ - u32 gdma_page_type; - - /* The total number of pages */ - u32 page_count; - - /* If page_addr_list_len is smaller than page_count, - * the remaining page addresses will be added via the - * message GDMA_DMA_REGION_ADD_PAGES. - */ - u32 page_addr_list_len; - u64 page_addr_list[]; -}; /* HW DATA */ - -struct gdma_create_dma_region_resp { - struct gdma_resp_hdr hdr; - u64 gdma_region; -}; /* HW DATA */ - -/* GDMA_DMA_REGION_ADD_PAGES */ -struct gdma_dma_region_add_pages_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; - - u32 page_addr_list_len; - u32 reserved3; - - u64 page_addr_list[]; -}; /* HW DATA */ - -/* GDMA_DESTROY_DMA_REGION */ -struct gdma_destroy_dma_region_req { - struct gdma_req_hdr hdr; - - u64 gdma_region; -}; /* HW DATA */ - -int mana_gd_verify_vf_version(struct pci_dev *pdev); - -int mana_gd_register_device(struct gdma_dev *gd); -int mana_gd_deregister_device(struct gdma_dev *gd); - -int mana_gd_post_work_request(struct gdma_queue *wq, - const struct gdma_wqe_request *wqe_req, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_post_and_ring(struct gdma_queue *queue, - const struct gdma_wqe_request *wqe, - struct gdma_posted_wqe_info *wqe_info); - -int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r); -void mana_gd_free_res_map(struct gdma_resource *r); - -void mana_gd_wq_ring_doorbell(struct gdma_context *gc, - struct gdma_queue *queue); - -int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, - struct gdma_mem_info *gmi); - -void mana_gd_free_memory(struct gdma_mem_info *gmi); - -int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, - u32 resp_len, void *resp); -#endif /* _GDMA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index f0e22954d5c0..69795bc679e7 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,7 +6,7 @@ #include #include -#include "mana.h" +#include static u32 mana_gd_r32(struct gdma_context *g, u64 offset) { diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 543a5d5c304f..76829ab43d40 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Copyright (c) 2021, Microsoft Corporation. */ -#include "gdma.h" -#include "hw_channel.h" +#include +#include static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) { diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/drivers/net/ethernet/microsoft/mana/hw_channel.h deleted file mode 100644 index 6a757a6e2732..000000000000 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.h +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _HW_CHANNEL_H -#define _HW_CHANNEL_H - -#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4 - -#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000 -#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000 - -#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1 - -#define HWC_INIT_DATA_CQID 1 -#define HWC_INIT_DATA_RQID 2 -#define HWC_INIT_DATA_SQID 3 -#define HWC_INIT_DATA_QUEUE_DEPTH 4 -#define HWC_INIT_DATA_MAX_REQUEST 5 -#define HWC_INIT_DATA_MAX_RESPONSE 6 -#define HWC_INIT_DATA_MAX_NUM_CQS 7 -#define HWC_INIT_DATA_PDID 8 -#define HWC_INIT_DATA_GPA_MKEY 9 -#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 -#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 - -/* Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -union hwc_init_eq_id_db { - u32 as_uint32; - - struct { - u32 eq_id : 16; - u32 doorbell : 16; - }; -}; /* HW DATA */ - -union hwc_init_type_data { - u32 as_uint32; - - struct { - u32 value : 24; - u32 type : 8; - }; -}; /* HW DATA */ - -struct hwc_rx_oob { - u32 type : 6; - u32 eom : 1; - u32 som : 1; - u32 vendor_err : 8; - u32 reserved1 : 16; - - u32 src_virt_wq : 24; - u32 src_vfid : 8; - - u32 reserved2; - - union { - u32 wqe_addr_low; - u32 wqe_offset; - }; - - u32 wqe_addr_high; - - u32 client_data_unit : 14; - u32 reserved3 : 18; - - u32 tx_oob_data_size; - - u32 chunk_offset : 21; - u32 reserved4 : 11; -}; /* HW DATA */ - -struct hwc_tx_oob { - u32 reserved1; - - u32 reserved2; - - u32 vrq_id : 24; - u32 dest_vfid : 8; - - u32 vrcq_id : 24; - u32 reserved3 : 8; - - u32 vscq_id : 24; - u32 loopback : 1; - u32 lso_override: 1; - u32 dest_pf : 1; - u32 reserved4 : 5; - - u32 vsq_id : 24; - u32 reserved5 : 8; -}; /* HW DATA */ - -struct hwc_work_request { - void *buf_va; - void *buf_sge_addr; - u32 buf_len; - u32 msg_size; - - struct gdma_wqe_request wqe_req; - struct hwc_tx_oob tx_oob; - - struct gdma_sge sge; -}; - -/* hwc_dma_buf represents the array of in-flight WQEs. - * mem_info as know as the GDMA mapped memory is partitioned and used by - * in-flight WQEs. - * The number of WQEs is determined by the number of in-flight messages. - */ -struct hwc_dma_buf { - struct gdma_mem_info mem_info; - - u32 gpa_mkey; - - u32 num_reqs; - struct hwc_work_request reqs[]; -}; - -typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id, - const struct hwc_rx_oob *rx_oob); - -typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id, - const struct hwc_rx_oob *rx_oob); - -struct hwc_cq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_cq; - struct gdma_queue *gdma_eq; - struct gdma_comp *comp_buf; - u16 queue_depth; - - hwc_rx_event_handler_t *rx_event_handler; - void *rx_event_ctx; - - hwc_tx_event_handler_t *tx_event_handler; - void *tx_event_ctx; -}; - -struct hwc_wq { - struct hw_channel_context *hwc; - - struct gdma_queue *gdma_wq; - struct hwc_dma_buf *msg_buf; - u16 queue_depth; - - struct hwc_cq *hwc_cq; -}; - -struct hwc_caller_ctx { - struct completion comp_event; - void *output_buf; - u32 output_buflen; - - u32 error; /* Linux error code */ - u32 status_code; -}; - -struct hw_channel_context { - struct gdma_dev *gdma_dev; - struct device *dev; - - u16 num_inflight_msg; - u32 max_req_msg_size; - - u16 hwc_init_q_depth_max; - u32 hwc_init_max_req_msg_size; - u32 hwc_init_max_resp_msg_size; - - struct completion hwc_init_eqe_comp; - - struct hwc_wq *rxq; - struct hwc_wq *txq; - struct hwc_cq *cq; - - struct semaphore sema; - struct gdma_resource inflight_msg_res; - - u32 pf_dest_vrq_id; - u32 pf_dest_vrcq_id; - - struct hwc_caller_ctx *caller_ctx; -}; - -int mana_hwc_create_channel(struct gdma_context *gc); -void mana_hwc_destroy_channel(struct gdma_context *gc); - -int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, - const void *req, u32 resp_len, void *resp); - -#endif /* _HW_CHANNEL_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h deleted file mode 100644 index 6e9e86fb4c02..000000000000 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ /dev/null @@ -1,650 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _MANA_H -#define _MANA_H - -#include "gdma.h" -#include "hw_channel.h" - -/* Microsoft Azure Network Adapter (MANA)'s definitions - * - * Structures labeled with "HW DATA" are exchanged with the hardware. All of - * them are naturally aligned and hence don't need __packed. - */ - -/* MANA protocol version */ -#define MANA_MAJOR_VERSION 0 -#define MANA_MINOR_VERSION 1 -#define MANA_MICRO_VERSION 1 - -typedef u64 mana_handle_t; -#define INVALID_MANA_HANDLE ((mana_handle_t)-1) - -enum TRI_STATE { - TRI_STATE_UNKNOWN = -1, - TRI_STATE_FALSE = 0, - TRI_STATE_TRUE = 1 -}; - -/* Number of entries for hardware indirection table must be in power of 2 */ -#define MANA_INDIRECT_TABLE_SIZE 64 -#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) - -/* The Toeplitz hash key's length in bytes: should be multiple of 8 */ -#define MANA_HASH_KEY_SIZE 40 - -#define COMP_ENTRY_SIZE 64 - -#define ADAPTER_MTU_SIZE 1500 -#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) - -#define RX_BUFFERS_PER_QUEUE 512 - -#define MAX_SEND_BUFFERS_PER_QUEUE 256 - -#define EQ_SIZE (8 * PAGE_SIZE) -#define LOG2_EQ_THROTTLE 3 - -#define MAX_PORTS_IN_MANA_DEV 256 - -struct mana_stats_rx { - u64 packets; - u64 bytes; - u64 xdp_drop; - u64 xdp_tx; - u64 xdp_redirect; - struct u64_stats_sync syncp; -}; - -struct mana_stats_tx { - u64 packets; - u64 bytes; - u64 xdp_xmit; - struct u64_stats_sync syncp; -}; - -struct mana_txq { - struct gdma_queue *gdma_sq; - - union { - u32 gdma_txq_id; - struct { - u32 reserved1 : 10; - u32 vsq_frame : 14; - u32 reserved2 : 8; - }; - }; - - u16 vp_offset; - - struct net_device *ndev; - - /* The SKBs are sent to the HW and we are waiting for the CQEs. */ - struct sk_buff_head pending_skbs; - struct netdev_queue *net_txq; - - atomic_t pending_sends; - - struct mana_stats_tx stats; -}; - -/* skb data and frags dma mappings */ -struct mana_skb_head { - dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; - - u32 size[MAX_SKB_FRAGS + 1]; -}; - -#define MANA_HEADROOM sizeof(struct mana_skb_head) - -enum mana_tx_pkt_format { - MANA_SHORT_PKT_FMT = 0, - MANA_LONG_PKT_FMT = 1, -}; - -struct mana_tx_short_oob { - u32 pkt_fmt : 2; - u32 is_outer_ipv4 : 1; - u32 is_outer_ipv6 : 1; - u32 comp_iphdr_csum : 1; - u32 comp_tcp_csum : 1; - u32 comp_udp_csum : 1; - u32 supress_txcqe_gen : 1; - u32 vcq_num : 24; - - u32 trans_off : 10; /* Transport header offset */ - u32 vsq_frame : 14; - u32 short_vp_offset : 8; -}; /* HW DATA */ - -struct mana_tx_long_oob { - u32 is_encap : 1; - u32 inner_is_ipv6 : 1; - u32 inner_tcp_opt : 1; - u32 inject_vlan_pri_tag : 1; - u32 reserved1 : 12; - u32 pcp : 3; /* 802.1Q */ - u32 dei : 1; /* 802.1Q */ - u32 vlan_id : 12; /* 802.1Q */ - - u32 inner_frame_offset : 10; - u32 inner_ip_rel_offset : 6; - u32 long_vp_offset : 12; - u32 reserved2 : 4; - - u32 reserved3; - u32 reserved4; -}; /* HW DATA */ - -struct mana_tx_oob { - struct mana_tx_short_oob s_oob; - struct mana_tx_long_oob l_oob; -}; /* HW DATA */ - -enum mana_cq_type { - MANA_CQ_TYPE_RX, - MANA_CQ_TYPE_TX, -}; - -enum mana_cqe_type { - CQE_INVALID = 0, - CQE_RX_OKAY = 1, - CQE_RX_COALESCED_4 = 2, - CQE_RX_OBJECT_FENCE = 3, - CQE_RX_TRUNCATED = 4, - - CQE_TX_OKAY = 32, - CQE_TX_SA_DROP = 33, - CQE_TX_MTU_DROP = 34, - CQE_TX_INVALID_OOB = 35, - CQE_TX_INVALID_ETH_TYPE = 36, - CQE_TX_HDR_PROCESSING_ERROR = 37, - CQE_TX_VF_DISABLED = 38, - CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39, - CQE_TX_VPORT_DISABLED = 40, - CQE_TX_VLAN_TAGGING_VIOLATION = 41, -}; - -#define MANA_CQE_COMPLETION 1 - -struct mana_cqe_header { - u32 cqe_type : 6; - u32 client_type : 2; - u32 vendor_err : 24; -}; /* HW DATA */ - -/* NDIS HASH Types */ -#define NDIS_HASH_IPV4 BIT(0) -#define NDIS_HASH_TCP_IPV4 BIT(1) -#define NDIS_HASH_UDP_IPV4 BIT(2) -#define NDIS_HASH_IPV6 BIT(3) -#define NDIS_HASH_TCP_IPV6 BIT(4) -#define NDIS_HASH_UDP_IPV6 BIT(5) -#define NDIS_HASH_IPV6_EX BIT(6) -#define NDIS_HASH_TCP_IPV6_EX BIT(7) -#define NDIS_HASH_UDP_IPV6_EX BIT(8) - -#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX) -#define MANA_HASH_L4 \ - (NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 | \ - NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX) - -struct mana_rxcomp_perpkt_info { - u32 pkt_len : 16; - u32 reserved1 : 16; - u32 reserved2; - u32 pkt_hash; -}; /* HW DATA */ - -#define MANA_RXCOMP_OOB_NUM_PPI 4 - -/* Receive completion OOB */ -struct mana_rxcomp_oob { - struct mana_cqe_header cqe_hdr; - - u32 rx_vlan_id : 12; - u32 rx_vlantag_present : 1; - u32 rx_outer_iphdr_csum_succeed : 1; - u32 rx_outer_iphdr_csum_fail : 1; - u32 reserved1 : 1; - u32 rx_hashtype : 9; - u32 rx_iphdr_csum_succeed : 1; - u32 rx_iphdr_csum_fail : 1; - u32 rx_tcp_csum_succeed : 1; - u32 rx_tcp_csum_fail : 1; - u32 rx_udp_csum_succeed : 1; - u32 rx_udp_csum_fail : 1; - u32 reserved2 : 1; - - struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI]; - - u32 rx_wqe_offset; -}; /* HW DATA */ - -struct mana_tx_comp_oob { - struct mana_cqe_header cqe_hdr; - - u32 tx_data_offset; - - u32 tx_sgl_offset : 5; - u32 tx_wqe_offset : 27; - - u32 reserved[12]; -}; /* HW DATA */ - -struct mana_rxq; - -#define CQE_POLLING_BUFFER 512 - -struct mana_cq { - struct gdma_queue *gdma_cq; - - /* Cache the CQ id (used to verify if each CQE comes to the right CQ. */ - u32 gdma_id; - - /* Type of the CQ: TX or RX */ - enum mana_cq_type type; - - /* Pointer to the mana_rxq that is pushing RX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_RX. - */ - struct mana_rxq *rxq; - - /* Pointer to the mana_txq that is pushing TX CQEs to the queue. - * Only and must be non-NULL if type is MANA_CQ_TYPE_TX. - */ - struct mana_txq *txq; - - /* Buffer which the CQ handler can copy the CQE's into. */ - struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; - - /* NAPI data */ - struct napi_struct napi; - int work_done; - int budget; -}; - -#define GDMA_MAX_RQE_SGES 15 - -struct mana_recv_buf_oob { - /* A valid GDMA work request representing the data buffer. */ - struct gdma_wqe_request wqe_req; - - void *buf_va; - dma_addr_t buf_dma_addr; - - /* SGL of the buffer going to be sent has part of the work request. */ - u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; - - /* Required to store the result of mana_gd_post_work_request. - * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the - * work queue when the WQE is consumed. - */ - struct gdma_posted_wqe_info wqe_inf; -}; - -struct mana_rxq { - struct gdma_queue *gdma_rq; - /* Cache the gdma receive queue id */ - u32 gdma_id; - - /* Index of RQ in the vPort, not gdma receive queue id */ - u32 rxq_idx; - - u32 datasize; - - mana_handle_t rxobj; - - struct mana_cq rx_cq; - - struct completion fence_event; - - struct net_device *ndev; - - /* Total number of receive buffers to be allocated */ - u32 num_rx_buf; - - u32 buf_index; - - struct mana_stats_rx stats; - - struct bpf_prog __rcu *bpf_prog; - struct xdp_rxq_info xdp_rxq; - struct page *xdp_save_page; - bool xdp_flush; - int xdp_rc; /* XDP redirect return code */ - - /* MUST BE THE LAST MEMBER: - * Each receive buffer has an associated mana_recv_buf_oob. - */ - struct mana_recv_buf_oob rx_oobs[]; -}; - -struct mana_tx_qp { - struct mana_txq txq; - - struct mana_cq tx_cq; - - mana_handle_t tx_object; -}; - -struct mana_ethtool_stats { - u64 stop_queue; - u64 wake_queue; -}; - -struct mana_context { - struct gdma_dev *gdma_dev; - - u16 num_ports; - - struct mana_eq *eqs; - - struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; -}; - -struct mana_port_context { - struct mana_context *ac; - struct net_device *ndev; - - u8 mac_addr[ETH_ALEN]; - - enum TRI_STATE rss_state; - - mana_handle_t default_rxobj; - bool tx_shortform_allowed; - u16 tx_vp_offset; - - struct mana_tx_qp *tx_qp; - - /* Indirection Table for RX & TX. The values are queue indexes */ - u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Indirection table containing RxObject Handles */ - mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; - - /* Hash key used by the NIC */ - u8 hashkey[MANA_HASH_KEY_SIZE]; - - /* This points to an array of num_queues of RQ pointers. */ - struct mana_rxq **rxqs; - - struct bpf_prog *bpf_prog; - - /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ - unsigned int max_queues; - unsigned int num_queues; - - mana_handle_t port_handle; - mana_handle_t pf_filter_handle; - - /* Mutex for sharing access to vport_use_count */ - struct mutex vport_mutex; - int vport_use_count; - - u16 port_idx; - - bool port_is_up; - bool port_st_save; /* Saved port state */ - - struct mana_ethtool_stats eth_stats; -}; - -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); -int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, - bool update_hash, bool update_tab); - -int mana_alloc_queues(struct net_device *ndev); -int mana_attach(struct net_device *ndev); -int mana_detach(struct net_device *ndev, bool from_close); - -int mana_probe(struct gdma_dev *gd, bool resuming); -void mana_remove(struct gdma_dev *gd, bool suspending); - -void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); -int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, - u32 flags); -u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, - struct xdp_buff *xdp, void *buf_va, uint pkt_len); -struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); -void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); -int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); - -extern const struct ethtool_ops mana_ethtool_ops; - -struct mana_obj_spec { - u32 queue_index; - u64 gdma_region; - u32 queue_size; - u32 attached_eq; - u32 modr_ctx_id; -}; - -enum mana_command_code { - MANA_QUERY_DEV_CONFIG = 0x20001, - MANA_QUERY_GF_STAT = 0x20002, - MANA_CONFIG_VPORT_TX = 0x20003, - MANA_CREATE_WQ_OBJ = 0x20004, - MANA_DESTROY_WQ_OBJ = 0x20005, - MANA_FENCE_RQ = 0x20006, - MANA_CONFIG_VPORT_RX = 0x20007, - MANA_QUERY_VPORT_CONFIG = 0x20008, - - /* Privileged commands for the PF mode */ - MANA_REGISTER_FILTER = 0x28000, - MANA_DEREGISTER_FILTER = 0x28001, - MANA_REGISTER_HW_PORT = 0x28003, - MANA_DEREGISTER_HW_PORT = 0x28004, -}; - -/* Query Device Configuration */ -struct mana_query_device_cfg_req { - struct gdma_req_hdr hdr; - - /* MANA Nic Driver Capability flags */ - u64 mn_drv_cap_flags1; - u64 mn_drv_cap_flags2; - u64 mn_drv_cap_flags3; - u64 mn_drv_cap_flags4; - - u32 proto_major_ver; - u32 proto_minor_ver; - u32 proto_micro_ver; - - u32 reserved; -}; /* HW DATA */ - -struct mana_query_device_cfg_resp { - struct gdma_resp_hdr hdr; - - u64 pf_cap_flags1; - u64 pf_cap_flags2; - u64 pf_cap_flags3; - u64 pf_cap_flags4; - - u16 max_num_vports; - u16 reserved; - u32 max_num_eqs; -}; /* HW DATA */ - -/* Query vPort Configuration */ -struct mana_query_vport_cfg_req { - struct gdma_req_hdr hdr; - u32 vport_index; -}; /* HW DATA */ - -struct mana_query_vport_cfg_resp { - struct gdma_resp_hdr hdr; - u32 max_num_sq; - u32 max_num_rq; - u32 num_indirection_ent; - u32 reserved1; - u8 mac_addr[6]; - u8 reserved2[2]; - mana_handle_t vport; -}; /* HW DATA */ - -/* Configure vPort */ -struct mana_config_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 pdid; - u32 doorbell_pageid; -}; /* HW DATA */ - -struct mana_config_vport_resp { - struct gdma_resp_hdr hdr; - u16 tx_vport_offset; - u8 short_form_allowed; - u8 reserved; -}; /* HW DATA */ - -/* Create WQ Object */ -struct mana_create_wqobj_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u32 wq_type; - u32 reserved; - u64 wq_gdma_region; - u64 cq_gdma_region; - u32 wq_size; - u32 cq_size; - u32 cq_moderation_ctx_id; - u32 cq_parent_qid; -}; /* HW DATA */ - -struct mana_create_wqobj_resp { - struct gdma_resp_hdr hdr; - u32 wq_id; - u32 cq_id; - mana_handle_t wq_obj; -}; /* HW DATA */ - -/* Destroy WQ Object */ -struct mana_destroy_wqobj_req { - struct gdma_req_hdr hdr; - u32 wq_type; - u32 reserved; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_destroy_wqobj_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Fence RQ */ -struct mana_fence_rq_req { - struct gdma_req_hdr hdr; - mana_handle_t wq_obj_handle; -}; /* HW DATA */ - -struct mana_fence_rq_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Configure vPort Rx Steering */ -struct mana_cfg_rx_steer_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u16 num_indir_entries; - u16 indir_tab_offset; - u32 rx_enable; - u32 rss_enable; - u8 update_default_rxobj; - u8 update_hashkey; - u8 update_indir_tab; - u8 reserved; - mana_handle_t default_rxobj; - u8 hashkey[MANA_HASH_KEY_SIZE]; -}; /* HW DATA */ - -struct mana_cfg_rx_steer_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register HW vPort */ -struct mana_register_hw_vport_req { - struct gdma_req_hdr hdr; - u16 attached_gfid; - u8 is_pf_default_vport; - u8 reserved1; - u8 allow_all_ether_types; - u8 reserved2; - u8 reserved3; - u8 reserved4; -}; /* HW DATA */ - -struct mana_register_hw_vport_resp { - struct gdma_resp_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -/* Deregister HW vPort */ -struct mana_deregister_hw_vport_req { - struct gdma_req_hdr hdr; - mana_handle_t hw_vport_handle; -}; /* HW DATA */ - -struct mana_deregister_hw_vport_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -/* Register filter */ -struct mana_register_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t vport; - u8 mac_addr[6]; - u8 reserved1; - u8 reserved2; - u8 reserved3; - u8 reserved4; - u16 reserved5; - u32 reserved6; - u32 reserved7; - u32 reserved8; -}; /* HW DATA */ - -struct mana_register_filter_resp { - struct gdma_resp_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -/* Deregister filter */ -struct mana_deregister_filter_req { - struct gdma_req_hdr hdr; - mana_handle_t filter_handle; -}; /* HW DATA */ - -struct mana_deregister_filter_resp { - struct gdma_resp_hdr hdr; -}; /* HW DATA */ - -#define MANA_MAX_NUM_QUEUES 64 - -#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) - -struct mana_tx_package { - struct gdma_wqe_request wqe_req; - struct gdma_sge sgl_array[5]; - struct gdma_sge *sgl_ptr; - - struct mana_tx_oob tx_oob; - - struct gdma_posted_wqe_info wqe_info; -}; - -int mana_create_wq_obj(struct mana_port_context *apc, - mana_handle_t vport, - u32 wq_type, struct mana_obj_spec *wq_spec, - struct mana_obj_spec *cq_spec, - mana_handle_t *wq_obj); - -void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, - mana_handle_t wq_obj); - -int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, - u32 doorbell_pg_id); -void mana_uncfg_vport(struct mana_port_context *apc); -#endif /* _MANA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h b/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h deleted file mode 100644 index 373d59756846..000000000000 --- a/drivers/net/ethernet/microsoft/mana/mana_auxiliary.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2022, Microsoft Corporation. */ - -#include "mana.h" -#include - -struct mana_adev { - struct auxiliary_device adev; - struct gdma_dev *mdev; -}; diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 421fd39ff3a8..3caea631229c 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -8,7 +8,7 @@ #include #include -#include "mana.h" +#include void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index b6303a43fa7c..ffa2a0e2c213 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -12,8 +12,8 @@ #include #include -#include "mana.h" -#include "mana_auxiliary.h" +#include +#include static DEFINE_IDA(mana_adev_ida); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index c530db76880f..6f98de6d7440 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -5,7 +5,7 @@ #include #include -#include "mana.h" +#include static const struct { char name[ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index da255da62176..5553af9c8085 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -6,7 +6,7 @@ #include #include -#include "shm_channel.h" +#include #define PAGE_FRAME_L48_WIDTH_BYTES 6 #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8) diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.h b/drivers/net/ethernet/microsoft/mana/shm_channel.h deleted file mode 100644 index 5199b41497ff..000000000000 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright (c) 2021, Microsoft Corporation. */ - -#ifndef _SHM_CHANNEL_H -#define _SHM_CHANNEL_H - -struct shm_channel { - struct device *dev; - void __iomem *base; -}; - -void mana_smc_init(struct shm_channel *sc, struct device *dev, - void __iomem *base); - -int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, - u64 cq_addr, u64 rq_addr, u64 sq_addr, - u32 eq_msix_index); - -int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); - -#endif /* _SHM_CHANNEL_H */ diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h new file mode 100644 index 000000000000..72eaec2470c0 --- /dev/null +++ b/include/net/mana/gdma.h @@ -0,0 +1,689 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _GDMA_H +#define _GDMA_H + +#include +#include + +#include "shm_channel.h" + +/* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +enum gdma_request_type { + GDMA_VERIFY_VF_DRIVER_VERSION = 1, + GDMA_QUERY_MAX_RESOURCES = 2, + GDMA_LIST_DEVICES = 3, + GDMA_REGISTER_DEVICE = 4, + GDMA_DEREGISTER_DEVICE = 5, + GDMA_GENERATE_TEST_EQE = 10, + GDMA_CREATE_QUEUE = 12, + GDMA_DISABLE_QUEUE = 13, + GDMA_CREATE_DMA_REGION = 25, + GDMA_DMA_REGION_ADD_PAGES = 26, + GDMA_DESTROY_DMA_REGION = 27, +}; + +enum gdma_queue_type { + GDMA_INVALID_QUEUE, + GDMA_SQ, + GDMA_RQ, + GDMA_CQ, + GDMA_EQ, +}; + +enum gdma_work_request_flags { + GDMA_WR_NONE = 0, + GDMA_WR_OOB_IN_SGL = BIT(0), + GDMA_WR_PAD_BY_SGE0 = BIT(1), +}; + +enum gdma_eqe_type { + GDMA_EQE_COMPLETION = 3, + GDMA_EQE_TEST_EVENT = 64, + GDMA_EQE_HWC_INIT_EQ_ID_DB = 129, + GDMA_EQE_HWC_INIT_DATA = 130, + GDMA_EQE_HWC_INIT_DONE = 131, +}; + +enum { + GDMA_DEVICE_NONE = 0, + GDMA_DEVICE_HWC = 1, + GDMA_DEVICE_MANA = 2, +}; + +struct gdma_resource { + /* Protect the bitmap */ + spinlock_t lock; + + /* The bitmap size in bits. */ + u32 size; + + /* The bitmap tracks the resources. */ + unsigned long *map; +}; + +union gdma_doorbell_entry { + u64 as_uint64; + + struct { + u64 id : 24; + u64 reserved : 8; + u64 tail_ptr : 31; + u64 arm : 1; + } cq; + + struct { + u64 id : 24; + u64 wqe_cnt : 8; + u64 tail_ptr : 32; + } rq; + + struct { + u64 id : 24; + u64 reserved : 8; + u64 tail_ptr : 32; + } sq; + + struct { + u64 id : 16; + u64 reserved : 16; + u64 tail_ptr : 31; + u64 arm : 1; + } eq; +}; /* HW DATA */ + +struct gdma_msg_hdr { + u32 hdr_type; + u32 msg_type; + u16 msg_version; + u16 hwc_msg_id; + u32 msg_size; +}; /* HW DATA */ + +struct gdma_dev_id { + union { + struct { + u16 type; + u16 instance; + }; + + u32 as_uint32; + }; +}; /* HW DATA */ + +struct gdma_req_hdr { + struct gdma_msg_hdr req; + struct gdma_msg_hdr resp; /* The expected response */ + struct gdma_dev_id dev_id; + u32 activity_id; +}; /* HW DATA */ + +struct gdma_resp_hdr { + struct gdma_msg_hdr response; + struct gdma_dev_id dev_id; + u32 activity_id; + u32 status; + u32 reserved; +}; /* HW DATA */ + +struct gdma_general_req { + struct gdma_req_hdr hdr; +}; /* HW DATA */ + +#define GDMA_MESSAGE_V1 1 + +struct gdma_general_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +#define GDMA_STANDARD_HEADER_TYPE 0 + +static inline void mana_gd_init_req_hdr(struct gdma_req_hdr *hdr, u32 code, + u32 req_size, u32 resp_size) +{ + hdr->req.hdr_type = GDMA_STANDARD_HEADER_TYPE; + hdr->req.msg_type = code; + hdr->req.msg_version = GDMA_MESSAGE_V1; + hdr->req.msg_size = req_size; + + hdr->resp.hdr_type = GDMA_STANDARD_HEADER_TYPE; + hdr->resp.msg_type = code; + hdr->resp.msg_version = GDMA_MESSAGE_V1; + hdr->resp.msg_size = resp_size; +} + +/* The 16-byte struct is part of the GDMA work queue entry (WQE). */ +struct gdma_sge { + u64 address; + u32 mem_key; + u32 size; +}; /* HW DATA */ + +struct gdma_wqe_request { + struct gdma_sge *sgl; + u32 num_sge; + + u32 inline_oob_size; + const void *inline_oob_data; + + u32 flags; + u32 client_data_unit; +}; + +enum gdma_page_type { + GDMA_PAGE_TYPE_4K, +}; + +#define GDMA_INVALID_DMA_REGION 0 + +struct gdma_mem_info { + struct device *dev; + + dma_addr_t dma_handle; + void *virt_addr; + u64 length; + + /* Allocated by the PF driver */ + u64 gdma_region; +}; + +#define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 + +struct gdma_dev { + struct gdma_context *gdma_context; + + struct gdma_dev_id dev_id; + + u32 pdid; + u32 doorbell; + u32 gpa_mkey; + + /* GDMA driver specific pointer */ + void *driver_data; + + struct auxiliary_device *adev; +}; + +#define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE + +#define GDMA_CQE_SIZE 64 +#define GDMA_EQE_SIZE 16 +#define GDMA_MAX_SQE_SIZE 512 +#define GDMA_MAX_RQE_SIZE 256 + +#define GDMA_COMP_DATA_SIZE 0x3C + +#define GDMA_EVENT_DATA_SIZE 0xC + +/* The WQE size must be a multiple of the Basic Unit, which is 32 bytes. */ +#define GDMA_WQE_BU_SIZE 32 + +#define INVALID_PDID UINT_MAX +#define INVALID_DOORBELL UINT_MAX +#define INVALID_MEM_KEY UINT_MAX +#define INVALID_QUEUE_ID UINT_MAX +#define INVALID_PCI_MSIX_INDEX UINT_MAX + +struct gdma_comp { + u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; + u32 wq_num; + bool is_sq; +}; + +struct gdma_event { + u32 details[GDMA_EVENT_DATA_SIZE / 4]; + u8 type; +}; + +struct gdma_queue; + +struct mana_eq { + struct gdma_queue *eq; +}; + +typedef void gdma_eq_callback(void *context, struct gdma_queue *q, + struct gdma_event *e); + +typedef void gdma_cq_callback(void *context, struct gdma_queue *q); + +/* The 'head' is the producer index. For SQ/RQ, when the driver posts a WQE + * (Note: the WQE size must be a multiple of the 32-byte Basic Unit), the + * driver increases the 'head' in BUs rather than in bytes, and notifies + * the HW of the updated head. For EQ/CQ, the driver uses the 'head' to track + * the HW head, and increases the 'head' by 1 for every processed EQE/CQE. + * + * The 'tail' is the consumer index for SQ/RQ. After the CQE of the SQ/RQ is + * processed, the driver increases the 'tail' to indicate that WQEs have + * been consumed by the HW, so the driver can post new WQEs into the SQ/RQ. + * + * The driver doesn't use the 'tail' for EQ/CQ, because the driver ensures + * that the EQ/CQ is big enough so they can't overflow, and the driver uses + * the owner bits mechanism to detect if the queue has become empty. + */ +struct gdma_queue { + struct gdma_dev *gdma_dev; + + enum gdma_queue_type type; + u32 id; + + struct gdma_mem_info mem_info; + + void *queue_mem_ptr; + u32 queue_size; + + bool monitor_avl_buf; + + u32 head; + u32 tail; + + /* Extra fields specific to EQ/CQ. */ + union { + struct { + bool disable_needed; + + gdma_eq_callback *callback; + void *context; + + unsigned int msix_index; + + u32 log2_throttle_limit; + } eq; + + struct { + gdma_cq_callback *callback; + void *context; + + struct gdma_queue *parent; /* For CQ/EQ relationship */ + } cq; + }; +}; + +struct gdma_queue_spec { + enum gdma_queue_type type; + bool monitor_avl_buf; + unsigned int queue_size; + + /* Extra fields specific to EQ/CQ. */ + union { + struct { + gdma_eq_callback *callback; + void *context; + + unsigned long log2_throttle_limit; + } eq; + + struct { + gdma_cq_callback *callback; + void *context; + + struct gdma_queue *parent_eq; + + } cq; + }; +}; + +struct gdma_irq_context { + void (*handler)(void *arg); + void *arg; +}; + +struct gdma_context { + struct device *dev; + + /* Per-vPort max number of queues */ + unsigned int max_num_queues; + unsigned int max_num_msix; + unsigned int num_msix_usable; + struct gdma_resource msix_resource; + struct gdma_irq_context *irq_contexts; + + /* This maps a CQ index to the queue structure. */ + unsigned int max_num_cqs; + struct gdma_queue **cq_table; + + /* Protect eq_test_event and test_event_eq_id */ + struct mutex eq_test_event_mutex; + struct completion eq_test_event; + u32 test_event_eq_id; + + bool is_pf; + phys_addr_t bar0_pa; + void __iomem *bar0_va; + void __iomem *shm_base; + void __iomem *db_page_base; + phys_addr_t phys_db_page_base; + u32 db_page_size; + + /* Shared memory chanenl (used to bootstrap HWC) */ + struct shm_channel shm_channel; + + /* Hardware communication channel (HWC) */ + struct gdma_dev hwc; + + /* Azure network adapter */ + struct gdma_dev mana; +}; + +#define MAX_NUM_GDMA_DEVICES 4 + +static inline bool mana_gd_is_mana(struct gdma_dev *gd) +{ + return gd->dev_id.type == GDMA_DEVICE_MANA; +} + +static inline bool mana_gd_is_hwc(struct gdma_dev *gd) +{ + return gd->dev_id.type == GDMA_DEVICE_HWC; +} + +u8 *mana_gd_get_wqe_ptr(const struct gdma_queue *wq, u32 wqe_offset); +u32 mana_gd_wq_avail_space(struct gdma_queue *wq); + +int mana_gd_test_eq(struct gdma_context *gc, struct gdma_queue *eq); + +int mana_gd_create_hwc_queue(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +int mana_gd_create_mana_eq(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, + const struct gdma_queue_spec *spec, + struct gdma_queue **queue_ptr); + +void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); + +int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); + +void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); + +struct gdma_wqe { + u32 reserved :24; + u32 last_vbytes :8; + + union { + u32 flags; + + struct { + u32 num_sge :8; + u32 inline_oob_size_div4:3; + u32 client_oob_in_sgl :1; + u32 reserved1 :4; + u32 client_data_unit :14; + u32 reserved2 :2; + }; + }; +}; /* HW DATA */ + +#define INLINE_OOB_SMALL_SIZE 8 +#define INLINE_OOB_LARGE_SIZE 24 + +#define MAX_TX_WQE_SIZE 512 +#define MAX_RX_WQE_SIZE 256 + +struct gdma_cqe { + u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; + + union { + u32 as_uint32; + + struct { + u32 wq_num : 24; + u32 is_sq : 1; + u32 reserved : 4; + u32 owner_bits : 3; + }; + } cqe_info; +}; /* HW DATA */ + +#define GDMA_CQE_OWNER_BITS 3 + +#define GDMA_CQE_OWNER_MASK ((1 << GDMA_CQE_OWNER_BITS) - 1) + +#define SET_ARM_BIT 1 + +#define GDMA_EQE_OWNER_BITS 3 + +union gdma_eqe_info { + u32 as_uint32; + + struct { + u32 type : 8; + u32 reserved1 : 8; + u32 client_id : 2; + u32 reserved2 : 11; + u32 owner_bits : 3; + }; +}; /* HW DATA */ + +#define GDMA_EQE_OWNER_MASK ((1 << GDMA_EQE_OWNER_BITS) - 1) +#define INITIALIZED_OWNER_BIT(log2_num_entries) (1UL << (log2_num_entries)) + +struct gdma_eqe { + u32 details[GDMA_EVENT_DATA_SIZE / 4]; + u32 eqe_info; +}; /* HW DATA */ + +#define GDMA_REG_DB_PAGE_OFFSET 8 +#define GDMA_REG_DB_PAGE_SIZE 0x10 +#define GDMA_REG_SHM_OFFSET 0x18 + +#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 +#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 +#define GDMA_PF_REG_SHM_OFF 0x70 + +#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 + +#define MANA_PF_DEVICE_ID 0x00B9 +#define MANA_VF_DEVICE_ID 0x00BA + +struct gdma_posted_wqe_info { + u32 wqe_size_in_bu; +}; + +/* GDMA_GENERATE_TEST_EQE */ +struct gdma_generate_test_event_req { + struct gdma_req_hdr hdr; + u32 queue_index; +}; /* HW DATA */ + +/* GDMA_VERIFY_VF_DRIVER_VERSION */ +enum { + GDMA_PROTOCOL_V1 = 1, + GDMA_PROTOCOL_FIRST = GDMA_PROTOCOL_V1, + GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, +}; + +#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) + +#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT + +#define GDMA_DRV_CAP_FLAGS2 0 + +#define GDMA_DRV_CAP_FLAGS3 0 + +#define GDMA_DRV_CAP_FLAGS4 0 + +struct gdma_verify_ver_req { + struct gdma_req_hdr hdr; + + /* Mandatory fields required for protocol establishment */ + u64 protocol_ver_min; + u64 protocol_ver_max; + + /* Gdma Driver Capability Flags */ + u64 gd_drv_cap_flags1; + u64 gd_drv_cap_flags2; + u64 gd_drv_cap_flags3; + u64 gd_drv_cap_flags4; + + /* Advisory fields */ + u64 drv_ver; + u32 os_type; /* Linux = 0x10; Windows = 0x20; Other = 0x30 */ + u32 reserved; + u32 os_ver_major; + u32 os_ver_minor; + u32 os_ver_build; + u32 os_ver_platform; + u64 reserved_2; + u8 os_ver_str1[128]; + u8 os_ver_str2[128]; + u8 os_ver_str3[128]; + u8 os_ver_str4[128]; +}; /* HW DATA */ + +struct gdma_verify_ver_resp { + struct gdma_resp_hdr hdr; + u64 gdma_protocol_ver; + u64 pf_cap_flags1; + u64 pf_cap_flags2; + u64 pf_cap_flags3; + u64 pf_cap_flags4; +}; /* HW DATA */ + +/* GDMA_QUERY_MAX_RESOURCES */ +struct gdma_query_max_resources_resp { + struct gdma_resp_hdr hdr; + u32 status; + u32 max_sq; + u32 max_rq; + u32 max_cq; + u32 max_eq; + u32 max_db; + u32 max_mst; + u32 max_cq_mod_ctx; + u32 max_mod_cq; + u32 max_msix; +}; /* HW DATA */ + +/* GDMA_LIST_DEVICES */ +struct gdma_list_devices_resp { + struct gdma_resp_hdr hdr; + u32 num_of_devs; + u32 reserved; + struct gdma_dev_id devs[64]; +}; /* HW DATA */ + +/* GDMA_REGISTER_DEVICE */ +struct gdma_register_device_resp { + struct gdma_resp_hdr hdr; + u32 pdid; + u32 gpa_mkey; + u32 db_id; +}; /* HW DATA */ + +/* GDMA_CREATE_QUEUE */ +struct gdma_create_queue_req { + struct gdma_req_hdr hdr; + u32 type; + u32 reserved1; + u32 pdid; + u32 doolbell_id; + u64 gdma_region; + u32 reserved2; + u32 queue_size; + u32 log2_throttle_limit; + u32 eq_pci_msix_index; + u32 cq_mod_ctx_id; + u32 cq_parent_eq_id; + u8 rq_drop_on_overrun; + u8 rq_err_on_wqe_overflow; + u8 rq_chain_rec_wqes; + u8 sq_hw_db; + u32 reserved3; +}; /* HW DATA */ + +struct gdma_create_queue_resp { + struct gdma_resp_hdr hdr; + u32 queue_index; +}; /* HW DATA */ + +/* GDMA_DISABLE_QUEUE */ +struct gdma_disable_queue_req { + struct gdma_req_hdr hdr; + u32 type; + u32 queue_index; + u32 alloc_res_id_on_creation; +}; /* HW DATA */ + +/* GDMA_CREATE_DMA_REGION */ +struct gdma_create_dma_region_req { + struct gdma_req_hdr hdr; + + /* The total size of the DMA region */ + u64 length; + + /* The offset in the first page */ + u32 offset_in_page; + + /* enum gdma_page_type */ + u32 gdma_page_type; + + /* The total number of pages */ + u32 page_count; + + /* If page_addr_list_len is smaller than page_count, + * the remaining page addresses will be added via the + * message GDMA_DMA_REGION_ADD_PAGES. + */ + u32 page_addr_list_len; + u64 page_addr_list[]; +}; /* HW DATA */ + +struct gdma_create_dma_region_resp { + struct gdma_resp_hdr hdr; + u64 gdma_region; +}; /* HW DATA */ + +/* GDMA_DMA_REGION_ADD_PAGES */ +struct gdma_dma_region_add_pages_req { + struct gdma_req_hdr hdr; + + u64 gdma_region; + + u32 page_addr_list_len; + u32 reserved3; + + u64 page_addr_list[]; +}; /* HW DATA */ + +/* GDMA_DESTROY_DMA_REGION */ +struct gdma_destroy_dma_region_req { + struct gdma_req_hdr hdr; + + u64 gdma_region; +}; /* HW DATA */ + +int mana_gd_verify_vf_version(struct pci_dev *pdev); + +int mana_gd_register_device(struct gdma_dev *gd); +int mana_gd_deregister_device(struct gdma_dev *gd); + +int mana_gd_post_work_request(struct gdma_queue *wq, + const struct gdma_wqe_request *wqe_req, + struct gdma_posted_wqe_info *wqe_info); + +int mana_gd_post_and_ring(struct gdma_queue *queue, + const struct gdma_wqe_request *wqe, + struct gdma_posted_wqe_info *wqe_info); + +int mana_gd_alloc_res_map(u32 res_avail, struct gdma_resource *r); +void mana_gd_free_res_map(struct gdma_resource *r); + +void mana_gd_wq_ring_doorbell(struct gdma_context *gc, + struct gdma_queue *queue); + +int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, + struct gdma_mem_info *gmi); + +void mana_gd_free_memory(struct gdma_mem_info *gmi); + +int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, + u32 resp_len, void *resp); +#endif /* _GDMA_H */ diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h new file mode 100644 index 000000000000..6a757a6e2732 --- /dev/null +++ b/include/net/mana/hw_channel.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _HW_CHANNEL_H +#define _HW_CHANNEL_H + +#define DEFAULT_LOG2_THROTTLING_FOR_ERROR_EQ 4 + +#define HW_CHANNEL_MAX_REQUEST_SIZE 0x1000 +#define HW_CHANNEL_MAX_RESPONSE_SIZE 0x1000 + +#define HW_CHANNEL_VF_BOOTSTRAP_QUEUE_DEPTH 1 + +#define HWC_INIT_DATA_CQID 1 +#define HWC_INIT_DATA_RQID 2 +#define HWC_INIT_DATA_SQID 3 +#define HWC_INIT_DATA_QUEUE_DEPTH 4 +#define HWC_INIT_DATA_MAX_REQUEST 5 +#define HWC_INIT_DATA_MAX_RESPONSE 6 +#define HWC_INIT_DATA_MAX_NUM_CQS 7 +#define HWC_INIT_DATA_PDID 8 +#define HWC_INIT_DATA_GPA_MKEY 9 +#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 +#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 + +/* Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +union hwc_init_eq_id_db { + u32 as_uint32; + + struct { + u32 eq_id : 16; + u32 doorbell : 16; + }; +}; /* HW DATA */ + +union hwc_init_type_data { + u32 as_uint32; + + struct { + u32 value : 24; + u32 type : 8; + }; +}; /* HW DATA */ + +struct hwc_rx_oob { + u32 type : 6; + u32 eom : 1; + u32 som : 1; + u32 vendor_err : 8; + u32 reserved1 : 16; + + u32 src_virt_wq : 24; + u32 src_vfid : 8; + + u32 reserved2; + + union { + u32 wqe_addr_low; + u32 wqe_offset; + }; + + u32 wqe_addr_high; + + u32 client_data_unit : 14; + u32 reserved3 : 18; + + u32 tx_oob_data_size; + + u32 chunk_offset : 21; + u32 reserved4 : 11; +}; /* HW DATA */ + +struct hwc_tx_oob { + u32 reserved1; + + u32 reserved2; + + u32 vrq_id : 24; + u32 dest_vfid : 8; + + u32 vrcq_id : 24; + u32 reserved3 : 8; + + u32 vscq_id : 24; + u32 loopback : 1; + u32 lso_override: 1; + u32 dest_pf : 1; + u32 reserved4 : 5; + + u32 vsq_id : 24; + u32 reserved5 : 8; +}; /* HW DATA */ + +struct hwc_work_request { + void *buf_va; + void *buf_sge_addr; + u32 buf_len; + u32 msg_size; + + struct gdma_wqe_request wqe_req; + struct hwc_tx_oob tx_oob; + + struct gdma_sge sge; +}; + +/* hwc_dma_buf represents the array of in-flight WQEs. + * mem_info as know as the GDMA mapped memory is partitioned and used by + * in-flight WQEs. + * The number of WQEs is determined by the number of in-flight messages. + */ +struct hwc_dma_buf { + struct gdma_mem_info mem_info; + + u32 gpa_mkey; + + u32 num_reqs; + struct hwc_work_request reqs[]; +}; + +typedef void hwc_rx_event_handler_t(void *ctx, u32 gdma_rxq_id, + const struct hwc_rx_oob *rx_oob); + +typedef void hwc_tx_event_handler_t(void *ctx, u32 gdma_txq_id, + const struct hwc_rx_oob *rx_oob); + +struct hwc_cq { + struct hw_channel_context *hwc; + + struct gdma_queue *gdma_cq; + struct gdma_queue *gdma_eq; + struct gdma_comp *comp_buf; + u16 queue_depth; + + hwc_rx_event_handler_t *rx_event_handler; + void *rx_event_ctx; + + hwc_tx_event_handler_t *tx_event_handler; + void *tx_event_ctx; +}; + +struct hwc_wq { + struct hw_channel_context *hwc; + + struct gdma_queue *gdma_wq; + struct hwc_dma_buf *msg_buf; + u16 queue_depth; + + struct hwc_cq *hwc_cq; +}; + +struct hwc_caller_ctx { + struct completion comp_event; + void *output_buf; + u32 output_buflen; + + u32 error; /* Linux error code */ + u32 status_code; +}; + +struct hw_channel_context { + struct gdma_dev *gdma_dev; + struct device *dev; + + u16 num_inflight_msg; + u32 max_req_msg_size; + + u16 hwc_init_q_depth_max; + u32 hwc_init_max_req_msg_size; + u32 hwc_init_max_resp_msg_size; + + struct completion hwc_init_eqe_comp; + + struct hwc_wq *rxq; + struct hwc_wq *txq; + struct hwc_cq *cq; + + struct semaphore sema; + struct gdma_resource inflight_msg_res; + + u32 pf_dest_vrq_id; + u32 pf_dest_vrcq_id; + + struct hwc_caller_ctx *caller_ctx; +}; + +int mana_hwc_create_channel(struct gdma_context *gc); +void mana_hwc_destroy_channel(struct gdma_context *gc); + +int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, + const void *req, u32 resp_len, void *resp); + +#endif /* _HW_CHANNEL_H */ diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h new file mode 100644 index 000000000000..6e9e86fb4c02 --- /dev/null +++ b/include/net/mana/mana.h @@ -0,0 +1,650 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _MANA_H +#define _MANA_H + +#include "gdma.h" +#include "hw_channel.h" + +/* Microsoft Azure Network Adapter (MANA)'s definitions + * + * Structures labeled with "HW DATA" are exchanged with the hardware. All of + * them are naturally aligned and hence don't need __packed. + */ + +/* MANA protocol version */ +#define MANA_MAJOR_VERSION 0 +#define MANA_MINOR_VERSION 1 +#define MANA_MICRO_VERSION 1 + +typedef u64 mana_handle_t; +#define INVALID_MANA_HANDLE ((mana_handle_t)-1) + +enum TRI_STATE { + TRI_STATE_UNKNOWN = -1, + TRI_STATE_FALSE = 0, + TRI_STATE_TRUE = 1 +}; + +/* Number of entries for hardware indirection table must be in power of 2 */ +#define MANA_INDIRECT_TABLE_SIZE 64 +#define MANA_INDIRECT_TABLE_MASK (MANA_INDIRECT_TABLE_SIZE - 1) + +/* The Toeplitz hash key's length in bytes: should be multiple of 8 */ +#define MANA_HASH_KEY_SIZE 40 + +#define COMP_ENTRY_SIZE 64 + +#define ADAPTER_MTU_SIZE 1500 +#define MAX_FRAME_SIZE (ADAPTER_MTU_SIZE + 14) + +#define RX_BUFFERS_PER_QUEUE 512 + +#define MAX_SEND_BUFFERS_PER_QUEUE 256 + +#define EQ_SIZE (8 * PAGE_SIZE) +#define LOG2_EQ_THROTTLE 3 + +#define MAX_PORTS_IN_MANA_DEV 256 + +struct mana_stats_rx { + u64 packets; + u64 bytes; + u64 xdp_drop; + u64 xdp_tx; + u64 xdp_redirect; + struct u64_stats_sync syncp; +}; + +struct mana_stats_tx { + u64 packets; + u64 bytes; + u64 xdp_xmit; + struct u64_stats_sync syncp; +}; + +struct mana_txq { + struct gdma_queue *gdma_sq; + + union { + u32 gdma_txq_id; + struct { + u32 reserved1 : 10; + u32 vsq_frame : 14; + u32 reserved2 : 8; + }; + }; + + u16 vp_offset; + + struct net_device *ndev; + + /* The SKBs are sent to the HW and we are waiting for the CQEs. */ + struct sk_buff_head pending_skbs; + struct netdev_queue *net_txq; + + atomic_t pending_sends; + + struct mana_stats_tx stats; +}; + +/* skb data and frags dma mappings */ +struct mana_skb_head { + dma_addr_t dma_handle[MAX_SKB_FRAGS + 1]; + + u32 size[MAX_SKB_FRAGS + 1]; +}; + +#define MANA_HEADROOM sizeof(struct mana_skb_head) + +enum mana_tx_pkt_format { + MANA_SHORT_PKT_FMT = 0, + MANA_LONG_PKT_FMT = 1, +}; + +struct mana_tx_short_oob { + u32 pkt_fmt : 2; + u32 is_outer_ipv4 : 1; + u32 is_outer_ipv6 : 1; + u32 comp_iphdr_csum : 1; + u32 comp_tcp_csum : 1; + u32 comp_udp_csum : 1; + u32 supress_txcqe_gen : 1; + u32 vcq_num : 24; + + u32 trans_off : 10; /* Transport header offset */ + u32 vsq_frame : 14; + u32 short_vp_offset : 8; +}; /* HW DATA */ + +struct mana_tx_long_oob { + u32 is_encap : 1; + u32 inner_is_ipv6 : 1; + u32 inner_tcp_opt : 1; + u32 inject_vlan_pri_tag : 1; + u32 reserved1 : 12; + u32 pcp : 3; /* 802.1Q */ + u32 dei : 1; /* 802.1Q */ + u32 vlan_id : 12; /* 802.1Q */ + + u32 inner_frame_offset : 10; + u32 inner_ip_rel_offset : 6; + u32 long_vp_offset : 12; + u32 reserved2 : 4; + + u32 reserved3; + u32 reserved4; +}; /* HW DATA */ + +struct mana_tx_oob { + struct mana_tx_short_oob s_oob; + struct mana_tx_long_oob l_oob; +}; /* HW DATA */ + +enum mana_cq_type { + MANA_CQ_TYPE_RX, + MANA_CQ_TYPE_TX, +}; + +enum mana_cqe_type { + CQE_INVALID = 0, + CQE_RX_OKAY = 1, + CQE_RX_COALESCED_4 = 2, + CQE_RX_OBJECT_FENCE = 3, + CQE_RX_TRUNCATED = 4, + + CQE_TX_OKAY = 32, + CQE_TX_SA_DROP = 33, + CQE_TX_MTU_DROP = 34, + CQE_TX_INVALID_OOB = 35, + CQE_TX_INVALID_ETH_TYPE = 36, + CQE_TX_HDR_PROCESSING_ERROR = 37, + CQE_TX_VF_DISABLED = 38, + CQE_TX_VPORT_IDX_OUT_OF_RANGE = 39, + CQE_TX_VPORT_DISABLED = 40, + CQE_TX_VLAN_TAGGING_VIOLATION = 41, +}; + +#define MANA_CQE_COMPLETION 1 + +struct mana_cqe_header { + u32 cqe_type : 6; + u32 client_type : 2; + u32 vendor_err : 24; +}; /* HW DATA */ + +/* NDIS HASH Types */ +#define NDIS_HASH_IPV4 BIT(0) +#define NDIS_HASH_TCP_IPV4 BIT(1) +#define NDIS_HASH_UDP_IPV4 BIT(2) +#define NDIS_HASH_IPV6 BIT(3) +#define NDIS_HASH_TCP_IPV6 BIT(4) +#define NDIS_HASH_UDP_IPV6 BIT(5) +#define NDIS_HASH_IPV6_EX BIT(6) +#define NDIS_HASH_TCP_IPV6_EX BIT(7) +#define NDIS_HASH_UDP_IPV6_EX BIT(8) + +#define MANA_HASH_L3 (NDIS_HASH_IPV4 | NDIS_HASH_IPV6 | NDIS_HASH_IPV6_EX) +#define MANA_HASH_L4 \ + (NDIS_HASH_TCP_IPV4 | NDIS_HASH_UDP_IPV4 | NDIS_HASH_TCP_IPV6 | \ + NDIS_HASH_UDP_IPV6 | NDIS_HASH_TCP_IPV6_EX | NDIS_HASH_UDP_IPV6_EX) + +struct mana_rxcomp_perpkt_info { + u32 pkt_len : 16; + u32 reserved1 : 16; + u32 reserved2; + u32 pkt_hash; +}; /* HW DATA */ + +#define MANA_RXCOMP_OOB_NUM_PPI 4 + +/* Receive completion OOB */ +struct mana_rxcomp_oob { + struct mana_cqe_header cqe_hdr; + + u32 rx_vlan_id : 12; + u32 rx_vlantag_present : 1; + u32 rx_outer_iphdr_csum_succeed : 1; + u32 rx_outer_iphdr_csum_fail : 1; + u32 reserved1 : 1; + u32 rx_hashtype : 9; + u32 rx_iphdr_csum_succeed : 1; + u32 rx_iphdr_csum_fail : 1; + u32 rx_tcp_csum_succeed : 1; + u32 rx_tcp_csum_fail : 1; + u32 rx_udp_csum_succeed : 1; + u32 rx_udp_csum_fail : 1; + u32 reserved2 : 1; + + struct mana_rxcomp_perpkt_info ppi[MANA_RXCOMP_OOB_NUM_PPI]; + + u32 rx_wqe_offset; +}; /* HW DATA */ + +struct mana_tx_comp_oob { + struct mana_cqe_header cqe_hdr; + + u32 tx_data_offset; + + u32 tx_sgl_offset : 5; + u32 tx_wqe_offset : 27; + + u32 reserved[12]; +}; /* HW DATA */ + +struct mana_rxq; + +#define CQE_POLLING_BUFFER 512 + +struct mana_cq { + struct gdma_queue *gdma_cq; + + /* Cache the CQ id (used to verify if each CQE comes to the right CQ. */ + u32 gdma_id; + + /* Type of the CQ: TX or RX */ + enum mana_cq_type type; + + /* Pointer to the mana_rxq that is pushing RX CQEs to the queue. + * Only and must be non-NULL if type is MANA_CQ_TYPE_RX. + */ + struct mana_rxq *rxq; + + /* Pointer to the mana_txq that is pushing TX CQEs to the queue. + * Only and must be non-NULL if type is MANA_CQ_TYPE_TX. + */ + struct mana_txq *txq; + + /* Buffer which the CQ handler can copy the CQE's into. */ + struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; + + /* NAPI data */ + struct napi_struct napi; + int work_done; + int budget; +}; + +#define GDMA_MAX_RQE_SGES 15 + +struct mana_recv_buf_oob { + /* A valid GDMA work request representing the data buffer. */ + struct gdma_wqe_request wqe_req; + + void *buf_va; + dma_addr_t buf_dma_addr; + + /* SGL of the buffer going to be sent has part of the work request. */ + u32 num_sge; + struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; + + /* Required to store the result of mana_gd_post_work_request. + * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the + * work queue when the WQE is consumed. + */ + struct gdma_posted_wqe_info wqe_inf; +}; + +struct mana_rxq { + struct gdma_queue *gdma_rq; + /* Cache the gdma receive queue id */ + u32 gdma_id; + + /* Index of RQ in the vPort, not gdma receive queue id */ + u32 rxq_idx; + + u32 datasize; + + mana_handle_t rxobj; + + struct mana_cq rx_cq; + + struct completion fence_event; + + struct net_device *ndev; + + /* Total number of receive buffers to be allocated */ + u32 num_rx_buf; + + u32 buf_index; + + struct mana_stats_rx stats; + + struct bpf_prog __rcu *bpf_prog; + struct xdp_rxq_info xdp_rxq; + struct page *xdp_save_page; + bool xdp_flush; + int xdp_rc; /* XDP redirect return code */ + + /* MUST BE THE LAST MEMBER: + * Each receive buffer has an associated mana_recv_buf_oob. + */ + struct mana_recv_buf_oob rx_oobs[]; +}; + +struct mana_tx_qp { + struct mana_txq txq; + + struct mana_cq tx_cq; + + mana_handle_t tx_object; +}; + +struct mana_ethtool_stats { + u64 stop_queue; + u64 wake_queue; +}; + +struct mana_context { + struct gdma_dev *gdma_dev; + + u16 num_ports; + + struct mana_eq *eqs; + + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; +}; + +struct mana_port_context { + struct mana_context *ac; + struct net_device *ndev; + + u8 mac_addr[ETH_ALEN]; + + enum TRI_STATE rss_state; + + mana_handle_t default_rxobj; + bool tx_shortform_allowed; + u16 tx_vp_offset; + + struct mana_tx_qp *tx_qp; + + /* Indirection Table for RX & TX. The values are queue indexes */ + u32 indir_table[MANA_INDIRECT_TABLE_SIZE]; + + /* Indirection table containing RxObject Handles */ + mana_handle_t rxobj_table[MANA_INDIRECT_TABLE_SIZE]; + + /* Hash key used by the NIC */ + u8 hashkey[MANA_HASH_KEY_SIZE]; + + /* This points to an array of num_queues of RQ pointers. */ + struct mana_rxq **rxqs; + + struct bpf_prog *bpf_prog; + + /* Create num_queues EQs, SQs, SQ-CQs, RQs and RQ-CQs, respectively. */ + unsigned int max_queues; + unsigned int num_queues; + + mana_handle_t port_handle; + mana_handle_t pf_filter_handle; + + /* Mutex for sharing access to vport_use_count */ + struct mutex vport_mutex; + int vport_use_count; + + u16 port_idx; + + bool port_is_up; + bool port_st_save; /* Saved port state */ + + struct mana_ethtool_stats eth_stats; +}; + +int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); +int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, + bool update_hash, bool update_tab); + +int mana_alloc_queues(struct net_device *ndev); +int mana_attach(struct net_device *ndev); +int mana_detach(struct net_device *ndev, bool from_close); + +int mana_probe(struct gdma_dev *gd, bool resuming); +void mana_remove(struct gdma_dev *gd, bool suspending); + +void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); +int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, + u32 flags); +u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, + struct xdp_buff *xdp, void *buf_va, uint pkt_len); +struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); +void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); +int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); + +extern const struct ethtool_ops mana_ethtool_ops; + +struct mana_obj_spec { + u32 queue_index; + u64 gdma_region; + u32 queue_size; + u32 attached_eq; + u32 modr_ctx_id; +}; + +enum mana_command_code { + MANA_QUERY_DEV_CONFIG = 0x20001, + MANA_QUERY_GF_STAT = 0x20002, + MANA_CONFIG_VPORT_TX = 0x20003, + MANA_CREATE_WQ_OBJ = 0x20004, + MANA_DESTROY_WQ_OBJ = 0x20005, + MANA_FENCE_RQ = 0x20006, + MANA_CONFIG_VPORT_RX = 0x20007, + MANA_QUERY_VPORT_CONFIG = 0x20008, + + /* Privileged commands for the PF mode */ + MANA_REGISTER_FILTER = 0x28000, + MANA_DEREGISTER_FILTER = 0x28001, + MANA_REGISTER_HW_PORT = 0x28003, + MANA_DEREGISTER_HW_PORT = 0x28004, +}; + +/* Query Device Configuration */ +struct mana_query_device_cfg_req { + struct gdma_req_hdr hdr; + + /* MANA Nic Driver Capability flags */ + u64 mn_drv_cap_flags1; + u64 mn_drv_cap_flags2; + u64 mn_drv_cap_flags3; + u64 mn_drv_cap_flags4; + + u32 proto_major_ver; + u32 proto_minor_ver; + u32 proto_micro_ver; + + u32 reserved; +}; /* HW DATA */ + +struct mana_query_device_cfg_resp { + struct gdma_resp_hdr hdr; + + u64 pf_cap_flags1; + u64 pf_cap_flags2; + u64 pf_cap_flags3; + u64 pf_cap_flags4; + + u16 max_num_vports; + u16 reserved; + u32 max_num_eqs; +}; /* HW DATA */ + +/* Query vPort Configuration */ +struct mana_query_vport_cfg_req { + struct gdma_req_hdr hdr; + u32 vport_index; +}; /* HW DATA */ + +struct mana_query_vport_cfg_resp { + struct gdma_resp_hdr hdr; + u32 max_num_sq; + u32 max_num_rq; + u32 num_indirection_ent; + u32 reserved1; + u8 mac_addr[6]; + u8 reserved2[2]; + mana_handle_t vport; +}; /* HW DATA */ + +/* Configure vPort */ +struct mana_config_vport_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u32 pdid; + u32 doorbell_pageid; +}; /* HW DATA */ + +struct mana_config_vport_resp { + struct gdma_resp_hdr hdr; + u16 tx_vport_offset; + u8 short_form_allowed; + u8 reserved; +}; /* HW DATA */ + +/* Create WQ Object */ +struct mana_create_wqobj_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u32 wq_type; + u32 reserved; + u64 wq_gdma_region; + u64 cq_gdma_region; + u32 wq_size; + u32 cq_size; + u32 cq_moderation_ctx_id; + u32 cq_parent_qid; +}; /* HW DATA */ + +struct mana_create_wqobj_resp { + struct gdma_resp_hdr hdr; + u32 wq_id; + u32 cq_id; + mana_handle_t wq_obj; +}; /* HW DATA */ + +/* Destroy WQ Object */ +struct mana_destroy_wqobj_req { + struct gdma_req_hdr hdr; + u32 wq_type; + u32 reserved; + mana_handle_t wq_obj_handle; +}; /* HW DATA */ + +struct mana_destroy_wqobj_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Fence RQ */ +struct mana_fence_rq_req { + struct gdma_req_hdr hdr; + mana_handle_t wq_obj_handle; +}; /* HW DATA */ + +struct mana_fence_rq_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Configure vPort Rx Steering */ +struct mana_cfg_rx_steer_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u16 num_indir_entries; + u16 indir_tab_offset; + u32 rx_enable; + u32 rss_enable; + u8 update_default_rxobj; + u8 update_hashkey; + u8 update_indir_tab; + u8 reserved; + mana_handle_t default_rxobj; + u8 hashkey[MANA_HASH_KEY_SIZE]; +}; /* HW DATA */ + +struct mana_cfg_rx_steer_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Register HW vPort */ +struct mana_register_hw_vport_req { + struct gdma_req_hdr hdr; + u16 attached_gfid; + u8 is_pf_default_vport; + u8 reserved1; + u8 allow_all_ether_types; + u8 reserved2; + u8 reserved3; + u8 reserved4; +}; /* HW DATA */ + +struct mana_register_hw_vport_resp { + struct gdma_resp_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +/* Deregister HW vPort */ +struct mana_deregister_hw_vport_req { + struct gdma_req_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +struct mana_deregister_hw_vport_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Register filter */ +struct mana_register_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u8 mac_addr[6]; + u8 reserved1; + u8 reserved2; + u8 reserved3; + u8 reserved4; + u16 reserved5; + u32 reserved6; + u32 reserved7; + u32 reserved8; +}; /* HW DATA */ + +struct mana_register_filter_resp { + struct gdma_resp_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +/* Deregister filter */ +struct mana_deregister_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +struct mana_deregister_filter_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +#define MANA_MAX_NUM_QUEUES 64 + +#define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) + +struct mana_tx_package { + struct gdma_wqe_request wqe_req; + struct gdma_sge sgl_array[5]; + struct gdma_sge *sgl_ptr; + + struct mana_tx_oob tx_oob; + + struct gdma_posted_wqe_info wqe_info; +}; + +int mana_create_wq_obj(struct mana_port_context *apc, + mana_handle_t vport, + u32 wq_type, struct mana_obj_spec *wq_spec, + struct mana_obj_spec *cq_spec, + mana_handle_t *wq_obj); + +void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + mana_handle_t wq_obj); + +int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id); +void mana_uncfg_vport(struct mana_port_context *apc); +#endif /* _MANA_H */ diff --git a/include/net/mana/mana_auxiliary.h b/include/net/mana/mana_auxiliary.h new file mode 100644 index 000000000000..373d59756846 --- /dev/null +++ b/include/net/mana/mana_auxiliary.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022, Microsoft Corporation. */ + +#include "mana.h" +#include + +struct mana_adev { + struct auxiliary_device adev; + struct gdma_dev *mdev; +}; diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h new file mode 100644 index 000000000000..5199b41497ff --- /dev/null +++ b/include/net/mana/shm_channel.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* Copyright (c) 2021, Microsoft Corporation. */ + +#ifndef _SHM_CHANNEL_H +#define _SHM_CHANNEL_H + +struct shm_channel { + struct device *dev; + void __iomem *base; +}; + +void mana_smc_init(struct shm_channel *sc, struct device *dev, + void __iomem *base); + +int mana_smc_setup_hwc(struct shm_channel *sc, bool reset_vf, u64 eq_addr, + u64 cq_addr, u64 rq_addr, u64 sq_addr, + u32 eq_msix_index); + +int mana_smc_teardown_hwc(struct shm_channel *sc, bool reset_vf); + +#endif /* _SHM_CHANNEL_H */ -- cgit v1.2.3 From aa56549792fb348892fbbae67f6f0c71bb750b65 Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:26 -0700 Subject: net: mana: Define max values for SGL entries The number of maximum SGl entries should be computed from the maximum WQE size for the intended queue type and the corresponding OOB data size. This guarantees the hardware queue can successfully queue requests up to the queue depth exposed to the upper layer. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-9-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- include/net/mana/gdma.h | 7 +++++++ include/net/mana/mana.h | 4 +--- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index ffa2a0e2c213..f6bcd0cc6cda 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -189,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > 30); + WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 72eaec2470c0..0b0c0cd0b6bd 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -427,6 +427,13 @@ struct gdma_wqe { #define MAX_TX_WQE_SIZE 512 #define MAX_RX_WQE_SIZE 256 +#define MAX_TX_WQE_SGL_ENTRIES ((GDMA_MAX_SQE_SIZE - \ + sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \ + sizeof(struct gdma_sge)) + +#define MAX_RX_WQE_SGL_ENTRIES ((GDMA_MAX_RQE_SIZE - \ + sizeof(struct gdma_sge)) / sizeof(struct gdma_sge)) + struct gdma_cqe { u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 6e9e86fb4c02..713a8f8cca9a 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -265,8 +265,6 @@ struct mana_cq { int budget; }; -#define GDMA_MAX_RQE_SGES 15 - struct mana_recv_buf_oob { /* A valid GDMA work request representing the data buffer. */ struct gdma_wqe_request wqe_req; @@ -276,7 +274,7 @@ struct mana_recv_buf_oob { /* SGL of the buffer going to be sent has part of the work request. */ u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; + struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; /* Required to store the result of mana_gd_post_work_request. * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the -- cgit v1.2.3 From de372f2a9ca7ada2698ecac7df8f02407cd98fa0 Mon Sep 17 00:00:00 2001 From: Ajay Sharma Date: Thu, 3 Nov 2022 12:16:27 -0700 Subject: net: mana: Define and process GDMA response code GDMA_STATUS_MORE_ENTRIES When doing memory registration, the PF may respond with GDMA_STATUS_MORE_ENTRIES to indicate a follow request is needed. This is not an error and should be processed as expected. Signed-off-by: Ajay Sharma Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-10-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/hw_channel.c | 2 +- include/net/mana/gdma.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 76829ab43d40..9d1507eba5b9 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (ctx->status_code) { + if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", ctx->status_code); err = -EPROTO; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 0b0c0cd0b6bd..a9b7930dfbf8 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -9,6 +9,8 @@ #include "shm_channel.h" +#define GDMA_STATUS_MORE_ENTRIES 0x00000105 + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */ -- cgit v1.2.3 From f72ececfc197e9b0bbb5595294908a950cf444fa Mon Sep 17 00:00:00 2001 From: Long Li Date: Thu, 3 Nov 2022 12:16:28 -0700 Subject: net: mana: Define data structures for allocating doorbell page from GDMA The RDMA device needs to allocate doorbell pages for each user context. Define the GDMA data structures for use by the RDMA driver. Reviewed-by: Dexuan Cui Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-11-git-send-email-longli@linuxonhyperv.com Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- include/net/mana/gdma.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include') diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index a9b7930dfbf8..055408a5baf3 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -24,11 +24,15 @@ enum gdma_request_type { GDMA_GENERATE_TEST_EQE = 10, GDMA_CREATE_QUEUE = 12, GDMA_DISABLE_QUEUE = 13, + GDMA_ALLOCATE_RESOURCE_RANGE = 22, + GDMA_DESTROY_RESOURCE_RANGE = 24, GDMA_CREATE_DMA_REGION = 25, GDMA_DMA_REGION_ADD_PAGES = 26, GDMA_DESTROY_DMA_REGION = 27, }; +#define GDMA_RESOURCE_DOORBELL_PAGE 27 + enum gdma_queue_type { GDMA_INVALID_QUEUE, GDMA_SQ, @@ -587,6 +591,26 @@ struct gdma_register_device_resp { u32 db_id; }; /* HW DATA */ +struct gdma_allocate_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 alignment; + u32 allocated_resources; +}; + +struct gdma_allocate_resource_range_resp { + struct gdma_resp_hdr hdr; + u32 allocated_resources; +}; + +struct gdma_destroy_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 allocated_resources; +}; + /* GDMA_CREATE_QUEUE */ struct gdma_create_queue_req { struct gdma_req_hdr hdr; -- cgit v1.2.3 From 28c66cfa45388af1126985d1114e0ed762eb2abd Mon Sep 17 00:00:00 2001 From: Ajay Sharma Date: Thu, 3 Nov 2022 12:16:29 -0700 Subject: net: mana: Define data structures for protection domain and memory registration The MANA hardware support protection domain and memory registration for use in RDMA environment. Add those definitions and expose them for use by the RDMA driver. Signed-off-by: Ajay Sharma Signed-off-by: Long Li Link: https://lore.kernel.org/r/1667502990-2559-12-git-send-email-longli@linuxonhyperv.com Reviewed-by: Dexuan Cui Acked-by: Haiyang Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/microsoft/mana/gdma_main.c | 27 ++++-- drivers/net/ethernet/microsoft/mana/mana_en.c | 18 ++-- include/net/mana/gdma.h | 121 +++++++++++++++++++++++- 3 files changed, 143 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 69795bc679e7..46a7d1e6ece9 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -198,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, req.type = queue->type; req.pdid = queue->gdma_dev->pdid; req.doolbell_id = queue->gdma_dev->doorbell; - req.gdma_region = queue->mem_info.gdma_region; + req.gdma_region = queue->mem_info.dma_region_handle; req.queue_size = queue->queue_size; req.log2_throttle_limit = queue->eq.log2_throttle_limit; req.eq_pci_msix_index = queue->eq.msix_index; @@ -212,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, queue->id = resp.queue_index; queue->eq.disable_needed = true; - queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; return 0; } @@ -671,24 +671,30 @@ free_q: return err; } -static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region) +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle) { struct gdma_destroy_dma_region_req req = {}; struct gdma_general_resp resp = {}; int err; - if (gdma_region == GDMA_INVALID_DMA_REGION) - return; + if (dma_region_handle == GDMA_INVALID_DMA_REGION) + return 0; mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req), sizeof(resp)); - req.gdma_region = gdma_region; + req.dma_region_handle = dma_region_handle; err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); - if (err || resp.hdr.status) + if (err || resp.hdr.status) { dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", err, resp.hdr.status); + return -EPROTO; + } + + return 0; } +EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_mem_info *gmi) @@ -733,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, if (err) goto out; - if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) { + if (resp.hdr.status || + resp.dma_region_handle == GDMA_INVALID_DMA_REGION) { dev_err(gc->dev, "Failed to create DMA region: 0x%x\n", resp.hdr.status); err = -EPROTO; goto out; } - gmi->gdma_region = resp.gdma_region; + gmi->dma_region_handle = resp.dma_region_handle; out: kfree(req); return err; @@ -863,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue) return; } - mana_gd_destroy_dma_region(gc, gmi->gdma_region); + mana_gd_destroy_dma_region(gc, gmi->dma_region_handle); mana_gd_free_memory(gmi); kfree(queue); } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index f6bcd0cc6cda..1c59502d34b5 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1523,10 +1523,10 @@ static int mana_create_txq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; + wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; wq_spec.queue_size = txq->gdma_sq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1541,8 +1541,10 @@ static int mana_create_txq(struct mana_port_context *apc, txq->gdma_sq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + txq->gdma_sq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; txq->gdma_txq_id = txq->gdma_sq->id; @@ -1753,10 +1755,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; + wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; wq_spec.queue_size = rxq->gdma_rq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1769,8 +1771,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->gdma_rq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; rxq->gdma_id = rxq->gdma_rq->id; cq->gdma_id = cq->gdma_cq->id; diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 055408a5baf3..221adc96340c 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -29,6 +29,10 @@ enum gdma_request_type { GDMA_CREATE_DMA_REGION = 25, GDMA_DMA_REGION_ADD_PAGES = 26, GDMA_DESTROY_DMA_REGION = 27, + GDMA_CREATE_PD = 29, + GDMA_DESTROY_PD = 30, + GDMA_CREATE_MR = 31, + GDMA_DESTROY_MR = 32, }; #define GDMA_RESOURCE_DOORBELL_PAGE 27 @@ -61,6 +65,8 @@ enum { GDMA_DEVICE_MANA = 2, }; +typedef u64 gdma_obj_handle_t; + struct gdma_resource { /* Protect the bitmap */ spinlock_t lock; @@ -194,7 +200,7 @@ struct gdma_mem_info { u64 length; /* Allocated by the PF driver */ - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; #define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 @@ -618,7 +624,7 @@ struct gdma_create_queue_req { u32 reserved1; u32 pdid; u32 doolbell_id; - u64 gdma_region; + gdma_obj_handle_t gdma_region; u32 reserved2; u32 queue_size; u32 log2_throttle_limit; @@ -645,6 +651,28 @@ struct gdma_disable_queue_req { u32 alloc_res_id_on_creation; }; /* HW DATA */ +enum atb_page_size { + ATB_PAGE_SIZE_4K, + ATB_PAGE_SIZE_8K, + ATB_PAGE_SIZE_16K, + ATB_PAGE_SIZE_32K, + ATB_PAGE_SIZE_64K, + ATB_PAGE_SIZE_128K, + ATB_PAGE_SIZE_256K, + ATB_PAGE_SIZE_512K, + ATB_PAGE_SIZE_1M, + ATB_PAGE_SIZE_2M, + ATB_PAGE_SIZE_MAX, +}; + +enum gdma_mr_access_flags { + GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0), + GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1), + GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2), + GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3), + GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4), +}; + /* GDMA_CREATE_DMA_REGION */ struct gdma_create_dma_region_req { struct gdma_req_hdr hdr; @@ -671,14 +699,14 @@ struct gdma_create_dma_region_req { struct gdma_create_dma_region_resp { struct gdma_resp_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ /* GDMA_DMA_REGION_ADD_PAGES */ struct gdma_dma_region_add_pages_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; u32 page_addr_list_len; u32 reserved3; @@ -690,9 +718,88 @@ struct gdma_dma_region_add_pages_req { struct gdma_destroy_dma_region_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ +enum gdma_pd_flags { + GDMA_PD_FLAG_INVALID = 0, +}; + +struct gdma_create_pd_req { + struct gdma_req_hdr hdr; + enum gdma_pd_flags flags; + u32 reserved; +};/* HW DATA */ + +struct gdma_create_pd_resp { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t pd_handle; + u32 pd_id; + u32 reserved; +};/* HW DATA */ + +struct gdma_destroy_pd_req { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; +};/* HW DATA */ + +struct gdma_destory_pd_resp { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + +enum gdma_mr_type { + /* Guest Virtual Address - MRs of this type allow access + * to memory mapped by PTEs associated with this MR using a virtual + * address that is set up in the MST + */ + GDMA_MR_TYPE_GVA = 2, +}; + +struct gdma_create_mr_params { + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + }; +}; + +struct gdma_create_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + u32 reserved_1; + + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + + }; + u32 reserved_2; +};/* HW DATA */ + +struct gdma_create_mr_response { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t mr_handle; + u32 lkey; + u32 rkey; +};/* HW DATA */ + +struct gdma_destroy_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t mr_handle; +};/* HW DATA */ + +struct gdma_destroy_mr_response { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + int mana_gd_verify_vf_version(struct pci_dev *pdev); int mana_gd_register_device(struct gdma_dev *gd); @@ -719,4 +826,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi); int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, u32 resp_len, void *resp); + +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle); + #endif /* _GDMA_H */ -- cgit v1.2.3 From cc514101a97e3fb48f8617c8f291db798d10d831 Mon Sep 17 00:00:00 2001 From: Sujuan Chen Date: Sat, 5 Nov 2022 23:36:18 +0100 Subject: net: ethernet: mtk_wed: introduce wed mcu support Introduce WED mcu support used to configure WED WO chip. This is a preliminary patch in order to add RX Wireless Ethernet Dispatch available on MT7986 SoC. Tested-by: Daniel Golle Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Sujuan Chen Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/Makefile | 2 +- drivers/net/ethernet/mediatek/mtk_wed_mcu.c | 359 +++++++++++++++++++++++++++ drivers/net/ethernet/mediatek/mtk_wed_regs.h | 1 + drivers/net/ethernet/mediatek/mtk_wed_wo.h | 150 +++++++++++ include/linux/soc/mediatek/mtk_wed.h | 29 +++ 5 files changed, 540 insertions(+), 1 deletion(-) create mode 100644 drivers/net/ethernet/mediatek/mtk_wed_mcu.c create mode 100644 drivers/net/ethernet/mediatek/mtk_wed_wo.h (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile index 45ba0970504a..d4bdefa77159 100644 --- a/drivers/net/ethernet/mediatek/Makefile +++ b/drivers/net/ethernet/mediatek/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_ppe.o mtk_ppe_debugfs.o mtk_ppe_offload.o -mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o +mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o mtk_wed_mcu.o ifdef CONFIG_DEBUG_FS mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o endif diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c new file mode 100644 index 000000000000..ce40d58000a0 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2022 MediaTek Inc. + * + * Author: Lorenzo Bianconi + * Sujuan Chen + */ + +#include +#include +#include +#include +#include + +#include "mtk_wed_regs.h" +#include "mtk_wed_wo.h" +#include "mtk_wed.h" + +static u32 wo_r32(struct mtk_wed_wo *wo, u32 reg) +{ + return readl(wo->boot.addr + reg); +} + +static void wo_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +{ + writel(val, wo->boot.addr + reg); +} + +static struct sk_buff * +mtk_wed_mcu_msg_alloc(const void *data, int data_len) +{ + int length = sizeof(struct mtk_wed_mcu_hdr) + data_len; + struct sk_buff *skb; + + skb = alloc_skb(length, GFP_KERNEL); + if (!skb) + return NULL; + + memset(skb->head, 0, length); + skb_reserve(skb, sizeof(struct mtk_wed_mcu_hdr)); + if (data && data_len) + skb_put_data(skb, data, data_len); + + return skb; +} + +static struct sk_buff * +mtk_wed_mcu_get_response(struct mtk_wed_wo *wo, unsigned long expires) +{ + if (!time_is_after_jiffies(expires)) + return NULL; + + wait_event_timeout(wo->mcu.wait, !skb_queue_empty(&wo->mcu.res_q), + expires - jiffies); + return skb_dequeue(&wo->mcu.res_q); +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + skb_queue_tail(&wo->mcu.res_q, skb); + wake_up(&wo->mcu.wait); +} + +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + switch (hdr->cmd) { + case MTK_WED_WO_EVT_LOG_DUMP: { + const char *msg = (const char *)(skb->data + sizeof(*hdr)); + + dev_notice(wo->hw->dev, "%s\n", msg); + break; + } + case MTK_WED_WO_EVT_PROFILING: { + struct mtk_wed_wo_log_info *info; + u32 count = (skb->len - sizeof(*hdr)) / sizeof(*info); + int i; + + info = (struct mtk_wed_wo_log_info *)(skb->data + sizeof(*hdr)); + for (i = 0 ; i < count ; i++) + dev_notice(wo->hw->dev, + "SN:%u latency: total=%u, rro:%u, mod:%u\n", + le32_to_cpu(info[i].sn), + le32_to_cpu(info[i].total), + le32_to_cpu(info[i].rro), + le32_to_cpu(info[i].mod)); + break; + } + case MTK_WED_WO_EVT_RXCNT_INFO: + break; + default: + break; + } + + dev_kfree_skb(skb); +} + +static int +mtk_wed_mcu_skb_send_msg(struct mtk_wed_wo *wo, struct sk_buff *skb, + int id, int cmd, u16 *wait_seq, bool wait_resp) +{ + struct mtk_wed_mcu_hdr *hdr; + + /* TODO: make it dynamic based on cmd */ + wo->mcu.timeout = 20 * HZ; + + hdr = (struct mtk_wed_mcu_hdr *)skb_push(skb, sizeof(*hdr)); + hdr->cmd = cmd; + hdr->length = cpu_to_le16(skb->len); + + if (wait_resp && wait_seq) { + u16 seq = ++wo->mcu.seq; + + if (!seq) + seq = ++wo->mcu.seq; + *wait_seq = seq; + + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_NEED_RSP); + hdr->seq = cpu_to_le16(seq); + } + if (id == MTK_WED_MODULE_ID_WO) + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_FROM_TO_WO); + + dev_kfree_skb(skb); + return 0; +} + +static int +mtk_wed_mcu_parse_response(struct mtk_wed_wo *wo, struct sk_buff *skb, + int cmd, int seq) +{ + struct mtk_wed_mcu_hdr *hdr; + + if (!skb) { + dev_err(wo->hw->dev, "Message %08x (seq %d) timeout\n", + cmd, seq); + return -ETIMEDOUT; + } + + hdr = (struct mtk_wed_mcu_hdr *)skb->data; + if (le16_to_cpu(hdr->seq) != seq) + return -EAGAIN; + + skb_pull(skb, sizeof(*hdr)); + switch (cmd) { + case MTK_WED_WO_CMD_RXCNT_INFO: + default: + break; + } + + return 0; +} + +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp) +{ + unsigned long expires; + struct sk_buff *skb; + u16 seq; + int ret; + + skb = mtk_wed_mcu_msg_alloc(data, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&wo->mcu.mutex); + + ret = mtk_wed_mcu_skb_send_msg(wo, skb, id, cmd, &seq, wait_resp); + if (ret || !wait_resp) + goto unlock; + + expires = jiffies + wo->mcu.timeout; + do { + skb = mtk_wed_mcu_get_response(wo, expires); + ret = mtk_wed_mcu_parse_response(wo, skb, cmd, seq); + dev_kfree_skb(skb); + } while (ret == -EAGAIN); + +unlock: + mutex_unlock(&wo->mcu.mutex); + + return ret; +} + +static int +mtk_wed_get_memory_region(struct mtk_wed_wo *wo, + struct mtk_wed_wo_memory_region *region) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(wo->hw->node, "memory-region-names", + region->name); + if (index < 0) + return index; + + np = of_parse_phandle(wo->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + region->phy_addr = rmem->base; + region->size = rmem->size; + region->addr = devm_ioremap(wo->hw->dev, region->phy_addr, region->size); + + return !region->addr ? -EINVAL : 0; +} + +static int +mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw, + struct mtk_wed_wo_memory_region *region) +{ + const u8 *first_region_ptr, *region_ptr, *trailer_ptr, *ptr = fw->data; + const struct mtk_wed_fw_trailer *trailer; + const struct mtk_wed_fw_region *fw_region; + + trailer_ptr = fw->data + fw->size - sizeof(*trailer); + trailer = (const struct mtk_wed_fw_trailer *)trailer_ptr; + region_ptr = trailer_ptr - trailer->num_region * sizeof(*fw_region); + first_region_ptr = region_ptr; + + while (region_ptr < trailer_ptr) { + u32 length; + + fw_region = (const struct mtk_wed_fw_region *)region_ptr; + length = le32_to_cpu(fw_region->len); + + if (region->phy_addr != le32_to_cpu(fw_region->addr)) + goto next; + + if (region->size < length) + goto next; + + if (first_region_ptr < ptr + length) + goto next; + + if (region->shared && region->consumed) + return 0; + + if (!region->shared || !region->consumed) { + memcpy_toio(region->addr, ptr, length); + region->consumed = true; + return 0; + } +next: + region_ptr += sizeof(*fw_region); + ptr += length; + } + + return -EINVAL; +} + +static int +mtk_wed_mcu_load_firmware(struct mtk_wed_wo *wo) +{ + static struct mtk_wed_wo_memory_region mem_region[] = { + [MTK_WED_WO_REGION_EMI] = { + .name = "wo-emi", + }, + [MTK_WED_WO_REGION_ILM] = { + .name = "wo-ilm", + }, + [MTK_WED_WO_REGION_DATA] = { + .name = "wo-data", + .shared = true, + }, + }; + const struct mtk_wed_fw_trailer *trailer; + const struct firmware *fw; + const char *fw_name; + u32 val, boot_cr; + int ret, i; + + /* load firmware region metadata */ + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_get_memory_region(wo, &mem_region[i]); + if (ret) + return ret; + } + + wo->boot.name = "wo-boot"; + ret = mtk_wed_get_memory_region(wo, &wo->boot); + if (ret) + return ret; + + /* set dummy cr */ + wed_w32(wo->hw->wed_dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL, + wo->hw->index + 1); + + /* load firmware */ + fw_name = wo->hw->index ? MT7986_FIRMWARE_WO1 : MT7986_FIRMWARE_WO0; + ret = request_firmware(&fw, fw_name, wo->hw->dev); + if (ret) + return ret; + + trailer = (void *)(fw->data + fw->size - + sizeof(struct mtk_wed_fw_trailer)); + dev_info(wo->hw->dev, + "MTK WED WO Firmware Version: %.10s, Build Time: %.15s\n", + trailer->fw_ver, trailer->build_date); + dev_info(wo->hw->dev, "MTK WED WO Chip ID %02x Region %d\n", + trailer->chip_id, trailer->num_region); + + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_mcu_run_firmware(wo, fw, &mem_region[i]); + if (ret) + goto out; + } + + /* set the start address */ + boot_cr = wo->hw->index ? MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR + : MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR; + wo_w32(wo, boot_cr, mem_region[MTK_WED_WO_REGION_EMI].phy_addr >> 16); + /* wo firmware reset */ + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR, 0xc00); + + val = wo_r32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR); + val |= wo->hw->index ? MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK + : MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK; + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR, val); +out: + release_firmware(fw); + + return ret; +} + +static u32 +mtk_wed_mcu_read_fw_dl(struct mtk_wed_wo *wo) +{ + return wed_r32(wo->hw->wed_dev, + MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL); +} + +int mtk_wed_mcu_init(struct mtk_wed_wo *wo) +{ + u32 val; + int ret; + + skb_queue_head_init(&wo->mcu.res_q); + init_waitqueue_head(&wo->mcu.wait); + mutex_init(&wo->mcu.mutex); + + ret = mtk_wed_mcu_load_firmware(wo); + if (ret) + return ret; + + return readx_poll_timeout(mtk_wed_mcu_read_fw_dl, wo, val, !val, + 100, MTK_FW_DL_TIMEOUT); +} + +MODULE_FIRMWARE(MT7986_FIRMWARE_WO0); +MODULE_FIRMWARE(MT7986_FIRMWARE_WO1); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h index e270fb336143..c940b3bb215b 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h @@ -152,6 +152,7 @@ struct mtk_wdma_desc { #define MTK_WED_RING_RX(_n) (0x400 + (_n) * 0x10) +#define MTK_WED_SCR0 0x3c0 #define MTK_WED_WPDMA_INT_TRIGGER 0x504 #define MTK_WED_WPDMA_INT_TRIGGER_RX_DONE BIT(1) #define MTK_WED_WPDMA_INT_TRIGGER_TX_DONE GENMASK(5, 4) diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h new file mode 100644 index 000000000000..5413a2308084 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2022 Lorenzo Bianconi */ + +#ifndef __MTK_WED_WO_H +#define __MTK_WED_WO_H + +#include +#include + +struct mtk_wed_hw; + +struct mtk_wed_mcu_hdr { + /* DW0 */ + u8 version; + u8 cmd; + __le16 length; + + /* DW1 */ + __le16 seq; + __le16 flag; + + /* DW2 */ + __le32 status; + + /* DW3 */ + u8 rsv[20]; +}; + +struct mtk_wed_wo_log_info { + __le32 sn; + __le32 total; + __le32 rro; + __le32 mod; +}; + +enum mtk_wed_wo_event { + MTK_WED_WO_EVT_LOG_DUMP = 0x1, + MTK_WED_WO_EVT_PROFILING = 0x2, + MTK_WED_WO_EVT_RXCNT_INFO = 0x3, +}; + +#define MTK_WED_MODULE_ID_WO 1 +#define MTK_FW_DL_TIMEOUT 4000000 /* us */ +#define MTK_WOCPU_TIMEOUT 2000000 /* us */ + +enum { + MTK_WED_WARP_CMD_FLAG_RSP = BIT(0), + MTK_WED_WARP_CMD_FLAG_NEED_RSP = BIT(1), + MTK_WED_WARP_CMD_FLAG_FROM_TO_WO = BIT(2), +}; + +enum { + MTK_WED_WO_REGION_EMI, + MTK_WED_WO_REGION_ILM, + MTK_WED_WO_REGION_DATA, + MTK_WED_WO_REGION_BOOT, + __MTK_WED_WO_REGION_MAX, +}; + +enum mtk_wed_dummy_cr_idx { + MTK_WED_DUMMY_CR_FWDL, + MTK_WED_DUMMY_CR_WO_STATUS, +}; + +#define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin" +#define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin" + +#define MTK_WO_MCU_CFG_LS_BASE 0 +#define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000) +#define MTK_WO_MCU_CFG_LS_FW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x004) +#define MTK_WO_MCU_CFG_LS_CFG_DBG1_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x00c) +#define MTK_WO_MCU_CFG_LS_CFG_DBG2_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x010) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x014) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_SET_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x018) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x01c) +#define MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x050) +#define MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x060) +#define MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x064) + +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK BIT(5) +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK BIT(0) + +struct mtk_wed_wo_memory_region { + const char *name; + void __iomem *addr; + phys_addr_t phy_addr; + u32 size; + bool shared:1; + bool consumed:1; +}; + +struct mtk_wed_fw_region { + __le32 decomp_crc; + __le32 decomp_len; + __le32 decomp_blk_sz; + u8 rsv0[4]; + __le32 addr; + __le32 len; + u8 feature_set; + u8 rsv1[15]; +} __packed; + +struct mtk_wed_fw_trailer { + u8 chip_id; + u8 eco_code; + u8 num_region; + u8 format_ver; + u8 format_flag; + u8 rsv[2]; + char fw_ver[10]; + char build_date[15]; + u32 crc; +}; + +struct mtk_wed_wo { + struct mtk_wed_hw *hw; + struct mtk_wed_wo_memory_region boot; + + struct { + struct mutex mutex; + int timeout; + u16 seq; + + struct sk_buff_head res_q; + wait_queue_head_t wait; + } mcu; +}; + +static inline int +mtk_wed_mcu_check_msg(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + if (hdr->version) + return -EINVAL; + + if (skb->len < sizeof(*hdr) || skb->len != le16_to_cpu(hdr->length)) + return -EINVAL; + + return 0; +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb); +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb); +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp); +int mtk_wed_mcu_init(struct mtk_wed_wo *wo); + +#endif /* __MTK_WED_WO_H */ diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 4450c8b7a1cb..2cc2f1e43ba9 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -11,6 +11,35 @@ struct mtk_wed_hw; struct mtk_wdma_desc; +enum mtk_wed_wo_cmd { + MTK_WED_WO_CMD_WED_CFG, + MTK_WED_WO_CMD_WED_RX_STAT, + MTK_WED_WO_CMD_RRO_SER, + MTK_WED_WO_CMD_DBG_INFO, + MTK_WED_WO_CMD_DEV_INFO, + MTK_WED_WO_CMD_BSS_INFO, + MTK_WED_WO_CMD_STA_REC, + MTK_WED_WO_CMD_DEV_INFO_DUMP, + MTK_WED_WO_CMD_BSS_INFO_DUMP, + MTK_WED_WO_CMD_STA_REC_DUMP, + MTK_WED_WO_CMD_BA_INFO_DUMP, + MTK_WED_WO_CMD_FBCMD_Q_DUMP, + MTK_WED_WO_CMD_FW_LOG_CTRL, + MTK_WED_WO_CMD_LOG_FLUSH, + MTK_WED_WO_CMD_CHANGE_STATE, + MTK_WED_WO_CMD_CPU_STATS_ENABLE, + MTK_WED_WO_CMD_CPU_STATS_DUMP, + MTK_WED_WO_CMD_EXCEPTION_INIT, + MTK_WED_WO_CMD_PROF_CTRL, + MTK_WED_WO_CMD_STA_BA_DUMP, + MTK_WED_WO_CMD_BA_CTRL_DUMP, + MTK_WED_WO_CMD_RXCNT_CTRL, + MTK_WED_WO_CMD_RXCNT_INFO, + MTK_WED_WO_CMD_SET_CAP, + MTK_WED_WO_CMD_CCIF_RING_DUMP, + MTK_WED_WO_CMD_WED_END +}; + enum mtk_wed_bus_tye { MTK_WED_BUS_PCIE, MTK_WED_BUS_AXI, -- cgit v1.2.3 From 084d60ce0c6cef96024d53a58b92d7ff2d8b9318 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 5 Nov 2022 23:36:20 +0100 Subject: net: ethernet: mtk_wed: rename tx_wdma array in rx_wdma Rename tx_wdma queue array in rx_wdma since this is rx side of wdma soc. Moreover rename mtk_wed_wdma_ring_setup routine in mtk_wed_wdma_rx_ring_setup() Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 16 ++++++++-------- include/linux/soc/mediatek/mtk_wed.h | 3 ++- 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 9c9dd17332b6..e904596e67de 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -253,8 +253,8 @@ mtk_wed_free_tx_rings(struct mtk_wed_device *dev) for (i = 0; i < ARRAY_SIZE(dev->tx_ring); i++) mtk_wed_free_ring(dev, &dev->tx_ring[i]); - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - mtk_wed_free_ring(dev, &dev->tx_wdma[i]); + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + mtk_wed_free_ring(dev, &dev->rx_wdma[i]); } static void @@ -688,10 +688,10 @@ mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, } static int -mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size) +mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; - struct mtk_wed_ring *wdma = &dev->tx_wdma[idx]; + struct mtk_wed_ring *wdma = &dev->rx_wdma[idx]; if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size)) return -ENOMEM; @@ -805,9 +805,9 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) { int i; - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - if (!dev->tx_wdma[i].desc) - mtk_wed_wdma_ring_setup(dev, i, 16); + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + if (!dev->rx_wdma[i].desc) + mtk_wed_wdma_rx_ring_setup(dev, i, 16); mtk_wed_hw_init(dev); mtk_wed_configure_irq(dev, irq_mask); @@ -916,7 +916,7 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) sizeof(*ring->desc))) return -ENOMEM; - if (mtk_wed_wdma_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) return -ENOMEM; ring->reg_base = MTK_WED_RING_TX(idx); diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 2cc2f1e43ba9..956978320f8b 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -7,6 +7,7 @@ #include #define MTK_WED_TX_QUEUES 2 +#define MTK_WED_RX_QUEUES 2 struct mtk_wed_hw; struct mtk_wdma_desc; @@ -66,7 +67,7 @@ struct mtk_wed_device { struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; struct mtk_wed_ring txfree_ring; - struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES]; struct { int size; -- cgit v1.2.3 From 4c5de09eb0d05fc9e73ff8f0e052622f1f3df6d8 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Sat, 5 Nov 2022 23:36:21 +0100 Subject: net: ethernet: mtk_wed: add configure wed wo support Enable RX Wireless Ethernet Dispatch available on MT7986 Soc. Tested-by: Daniel Golle Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 600 +++++++++++++++++++++++++-- drivers/net/ethernet/mediatek/mtk_wed.h | 19 + drivers/net/ethernet/mediatek/mtk_wed_mcu.c | 45 +- drivers/net/ethernet/mediatek/mtk_wed_regs.h | 128 +++++- drivers/net/ethernet/mediatek/mtk_wed_wo.h | 28 ++ include/linux/soc/mediatek/mtk_wed.h | 76 +++- 6 files changed, 842 insertions(+), 54 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index e904596e67de..7d8842378c2b 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -23,6 +24,7 @@ #define MTK_WED_PKT_SIZE 1900 #define MTK_WED_BUF_SIZE 2048 #define MTK_WED_BUF_PER_PAGE (PAGE_SIZE / 2048) +#define MTK_WED_RX_RING_SIZE 1536 #define MTK_WED_TX_RING_SIZE 2048 #define MTK_WED_WDMA_RING_SIZE 1024 @@ -31,6 +33,10 @@ #define MTK_WED_PER_GROUP_PKT 128 #define MTK_WED_FBUF_SIZE 128 +#define MTK_WED_MIOD_CNT 16 +#define MTK_WED_FB_CMD_CNT 1024 +#define MTK_WED_RRO_QUE_CNT 8192 +#define MTK_WED_MIOD_ENTRY_CNT 128 static struct mtk_wed_hw *hw_list[2]; static DEFINE_MUTEX(hw_lock); @@ -65,12 +71,76 @@ wdma_set(struct mtk_wed_device *dev, u32 reg, u32 mask) wdma_m32(dev, reg, 0, mask); } +static void +wdma_clr(struct mtk_wed_device *dev, u32 reg, u32 mask) +{ + wdma_m32(dev, reg, mask, 0); +} + +static u32 +wifi_r32(struct mtk_wed_device *dev, u32 reg) +{ + return readl(dev->wlan.base + reg); +} + +static void +wifi_w32(struct mtk_wed_device *dev, u32 reg, u32 val) +{ + writel(val, dev->wlan.base + reg); +} + static u32 mtk_wed_read_reset(struct mtk_wed_device *dev) { return wed_r32(dev, MTK_WED_RESET); } +static u32 +mtk_wdma_read_reset(struct mtk_wed_device *dev) +{ + return wdma_r32(dev, MTK_WDMA_GLO_CFG); +} + +static void +mtk_wdma_rx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_RX_DMA_BUSY; + int i; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_DMA_EN); + if (readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 1000)) + dev_err(dev->hw->dev, "rx reset failed\n"); + + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) { + if (dev->rx_wdma[i].desc) + continue; + + wdma_w32(dev, + MTK_WDMA_RING_RX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); + } +} + +static void +mtk_wdma_tx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_TX_DMA_BUSY; + int i; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN); + if (readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 1000)) + dev_err(dev->hw->dev, "tx reset failed\n"); + + for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) { + if (dev->tx_wdma[i].desc) + continue; + + wdma_w32(dev, + MTK_WDMA_RING_TX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); + } +} + static void mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) { @@ -82,6 +152,54 @@ mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) WARN_ON_ONCE(1); } +static u32 +mtk_wed_wo_read_status(struct mtk_wed_device *dev) +{ + return wed_r32(dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_WO_STATUS); +} + +static void +mtk_wed_wo_reset(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + u8 state = MTK_WED_WO_STATE_DISABLE; + void __iomem *reg; + u32 val; + + mtk_wdma_tx_reset(dev); + mtk_wed_reset(dev, MTK_WED_RESET_WED); + + mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_CHANGE_STATE, &state, + sizeof(state), false); + + if (readx_poll_timeout(mtk_wed_wo_read_status, dev, val, + val == MTK_WED_WOIF_DISABLE_DONE, + 100, MTK_WOCPU_TIMEOUT)) + dev_err(dev->hw->dev, "failed to disable wed-wo\n"); + + reg = ioremap(MTK_WED_WO_CPU_MCUSYS_RESET_ADDR, 4); + + val = readl(reg); + switch (dev->hw->index) { + case 0: + val |= MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + break; + case 1: + val |= MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + break; + default: + break; + } + iounmap(reg); +} + static struct mtk_wed_hw * mtk_wed_assign(struct mtk_wed_device *dev) { @@ -116,7 +234,7 @@ out: } static int -mtk_wed_buffer_alloc(struct mtk_wed_device *dev) +mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev) { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; @@ -133,16 +251,16 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) if (!page_list) return -ENOMEM; - dev->buf_ring.size = ring_size; - dev->buf_ring.pages = page_list; + dev->tx_buf_ring.size = ring_size; + dev->tx_buf_ring.pages = page_list; desc = dma_alloc_coherent(dev->hw->dev, ring_size * sizeof(*desc), &desc_phys, GFP_KERNEL); if (!desc) return -ENOMEM; - dev->buf_ring.desc = desc; - dev->buf_ring.desc_phys = desc_phys; + dev->tx_buf_ring.desc = desc; + dev->tx_buf_ring.desc_phys = desc_phys; for (i = 0, page_idx = 0; i < ring_size; i += MTK_WED_BUF_PER_PAGE) { dma_addr_t page_phys, buf_phys; @@ -203,10 +321,10 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) } static void -mtk_wed_free_buffer(struct mtk_wed_device *dev) +mtk_wed_free_tx_buffer(struct mtk_wed_device *dev) { - struct mtk_wdma_desc *desc = dev->buf_ring.desc; - void **page_list = dev->buf_ring.pages; + struct mtk_wdma_desc *desc = dev->tx_buf_ring.desc; + void **page_list = dev->tx_buf_ring.pages; int page_idx; int i; @@ -216,7 +334,8 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) if (!desc) goto free_pagelist; - for (i = 0, page_idx = 0; i < dev->buf_ring.size; i += MTK_WED_BUF_PER_PAGE) { + for (i = 0, page_idx = 0; i < dev->tx_buf_ring.size; + i += MTK_WED_BUF_PER_PAGE) { void *page = page_list[page_idx++]; dma_addr_t buf_addr; @@ -229,13 +348,59 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) __free_page(page); } - dma_free_coherent(dev->hw->dev, dev->buf_ring.size * sizeof(*desc), - desc, dev->buf_ring.desc_phys); + dma_free_coherent(dev->hw->dev, dev->tx_buf_ring.size * sizeof(*desc), + desc, dev->tx_buf_ring.desc_phys); free_pagelist: kfree(page_list); } +static int +mtk_wed_rx_buffer_alloc(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc; + dma_addr_t desc_phys; + + dev->rx_buf_ring.size = dev->wlan.rx_nbuf; + desc = dma_alloc_coherent(dev->hw->dev, + dev->wlan.rx_nbuf * sizeof(*desc), + &desc_phys, GFP_KERNEL); + if (!desc) + return -ENOMEM; + + dev->rx_buf_ring.desc = desc; + dev->rx_buf_ring.desc_phys = desc_phys; + dev->wlan.init_rx_buf(dev, dev->wlan.rx_npkt); + + return 0; +} + +static void +mtk_wed_free_rx_buffer(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc = dev->rx_buf_ring.desc; + + if (!desc) + return; + + dev->wlan.release_rx_buf(dev); + dma_free_coherent(dev->hw->dev, dev->rx_buf_ring.size * sizeof(*desc), + desc, dev->rx_buf_ring.desc_phys); +} + +static void +mtk_wed_rx_buffer_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RX_BM_RX_DMAD, + FIELD_PREP(MTK_WED_RX_BM_RX_DMAD_SDL0, dev->wlan.rx_size)); + wed_w32(dev, MTK_WED_RX_BM_BASE, dev->rx_buf_ring.desc_phys); + wed_w32(dev, MTK_WED_RX_BM_INIT_PTR, MTK_WED_RX_BM_INIT_SW_TAIL | + FIELD_PREP(MTK_WED_RX_BM_SW_TAIL, dev->wlan.rx_npkt)); + wed_w32(dev, MTK_WED_RX_BM_DYN_ALLOC_TH, + FIELD_PREP(MTK_WED_RX_BM_DYN_ALLOC_TH_H, 0xffff)); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); +} + static void mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) { @@ -246,6 +411,13 @@ mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) ring->desc, ring->desc_phys); } +static void +mtk_wed_free_rx_rings(struct mtk_wed_device *dev) +{ + mtk_wed_free_rx_buffer(dev); + mtk_wed_free_ring(dev, &dev->rro.ring); +} + static void mtk_wed_free_tx_rings(struct mtk_wed_device *dev) { @@ -291,6 +463,38 @@ mtk_wed_set_512_support(struct mtk_wed_device *dev, bool enable) } } +#define MTK_WFMDA_RX_DMA_EN BIT(2) +static void +mtk_wed_check_wfdma_rx_fill(struct mtk_wed_device *dev, int idx) +{ + u32 val; + int i; + + if (!(dev->rx_ring[idx].flags & MTK_WED_RING_CONFIGURED)) + return; /* queue is not configured by mt76 */ + + for (i = 0; i < 3; i++) { + u32 cur_idx; + + cur_idx = wed_r32(dev, + MTK_WED_WPDMA_RING_RX_DATA(idx) + + MTK_WED_RING_OFS_CPU_IDX); + if (cur_idx == MTK_WED_RX_RING_SIZE - 1) + break; + + usleep_range(100000, 200000); + } + + if (i == 3) { + dev_err(dev->hw->dev, "rx dma enable failed\n"); + return; + } + + val = wifi_r32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base) | + MTK_WFMDA_RX_DMA_EN; + wifi_w32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base, val); +} + static void mtk_wed_dma_disable(struct mtk_wed_device *dev) { @@ -304,20 +508,25 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) MTK_WED_GLO_CFG_TX_DMA_EN | MTK_WED_GLO_CFG_RX_DMA_EN); - wdma_m32(dev, MTK_WDMA_GLO_CFG, + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN | MTK_WDMA_GLO_CFG_RX_INFO1_PRERES | - MTK_WDMA_GLO_CFG_RX_INFO2_PRERES, 0); + MTK_WDMA_GLO_CFG_RX_INFO2_PRERES); if (dev->hw->version == 1) { regmap_write(dev->hw->mirror, dev->hw->index * 4, 0); - wdma_m32(dev, MTK_WDMA_GLO_CFG, - MTK_WDMA_GLO_CFG_RX_INFO3_PRERES, 0); + wdma_clr(dev, MTK_WDMA_GLO_CFG, + MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); + wed_clr(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN); + wed_clr(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); + mtk_wed_set_512_support(dev, false); } } @@ -338,6 +547,13 @@ mtk_wed_stop(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); + + if (dev->hw->version == 1) + return; + + wed_w32(dev, MTK_WED_EXT_INT_MASK1, 0); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, 0); + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); } static void @@ -353,11 +569,21 @@ mtk_wed_detach(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); mtk_wed_reset(dev, MTK_WED_RESET_WED); + if (mtk_wed_get_rx_capa(dev)) { + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN); + wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_TX); + wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + } - mtk_wed_free_buffer(dev); + mtk_wed_free_tx_buffer(dev); mtk_wed_free_tx_rings(dev); - if (hw->version != 1) + + if (mtk_wed_get_rx_capa(dev)) { + mtk_wed_wo_reset(dev); + mtk_wed_free_rx_rings(dev); mtk_wed_wo_deinit(hw); + mtk_wdma_rx_reset(dev); + } if (dev->wlan.bus_type == MTK_WED_BUS_PCIE) { struct device_node *wlan_node; @@ -434,10 +660,12 @@ mtk_wed_set_wpdma(struct mtk_wed_device *dev) } else { mtk_wed_bus_init(dev); - wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); - wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); + wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_RX_GLO_CFG, dev->wlan.wpdma_rx_glo); + wed_w32(dev, MTK_WED_WPDMA_RX_RING, dev->wlan.wpdma_rx); } } @@ -487,6 +715,132 @@ mtk_wed_hw_init_early(struct mtk_wed_device *dev) } } +static int +mtk_wed_rro_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, + int size) +{ + ring->desc = dma_alloc_coherent(dev->hw->dev, + size * sizeof(*ring->desc), + &ring->desc_phys, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_size = sizeof(*ring->desc); + ring->size = size; + memset(ring->desc, 0, size); + + return 0; +} + +#define MTK_WED_MIOD_COUNT (MTK_WED_MIOD_ENTRY_CNT * MTK_WED_MIOD_CNT) +static int +mtk_wed_rro_alloc(struct mtk_wed_device *dev) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(dev->hw->node, "memory-region-names", + "wo-dlm"); + if (index < 0) + return index; + + np = of_parse_phandle(dev->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + dev->rro.miod_phys = rmem->base; + dev->rro.fdbk_phys = MTK_WED_MIOD_COUNT + dev->rro.miod_phys; + + return mtk_wed_rro_ring_alloc(dev, &dev->rro.ring, + MTK_WED_RRO_QUE_CNT); +} + +static int +mtk_wed_rro_cfg(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + struct { + struct { + __le32 base; + __le32 cnt; + __le32 unit; + } ring[2]; + __le32 wed; + u8 version; + } req = { + .ring[0] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE), + .cnt = cpu_to_le32(MTK_WED_MIOD_CNT), + .unit = cpu_to_le32(MTK_WED_MIOD_ENTRY_CNT), + }, + .ring[1] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE + + MTK_WED_MIOD_COUNT), + .cnt = cpu_to_le32(MTK_WED_FB_CMD_CNT), + .unit = cpu_to_le32(4), + }, + }; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_WED_CFG, + &req, sizeof(req), true); +} + +static void +mtk_wed_rro_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RROQM_MIOD_CFG, + FIELD_PREP(MTK_WED_RROQM_MIOD_MID_DW, 0x70 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_MOD_DW, 0x10 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_ENTRY_DW, + MTK_WED_MIOD_ENTRY_CNT >> 2)); + + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL0, dev->rro.miod_phys); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL1, + FIELD_PREP(MTK_WED_RROQM_MIOD_CNT, MTK_WED_MIOD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL0, dev->rro.fdbk_phys); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL1, + FIELD_PREP(MTK_WED_RROQM_FDBK_CNT, MTK_WED_FB_CMD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL2, 0); + wed_w32(dev, MTK_WED_RROQ_BASE_L, dev->rro.ring.desc_phys); + + wed_set(dev, MTK_WED_RROQM_RST_IDX, + MTK_WED_RROQM_RST_IDX_MIOD | + MTK_WED_RROQM_RST_IDX_FDBK); + + wed_w32(dev, MTK_WED_RROQM_RST_IDX, 0); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL2, MTK_WED_MIOD_CNT - 1); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_RRO_QM_EN); +} + +static void +mtk_wed_route_qm_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RESET, MTK_WED_RESET_RX_ROUTE_QM); + + for (;;) { + usleep_range(100, 200); + if (!(wed_r32(dev, MTK_WED_RESET) & MTK_WED_RESET_RX_ROUTE_QM)) + break; + } + + /* configure RX_ROUTE_QM */ + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_TXDMAD_FPORT); + wed_set(dev, MTK_WED_RTQM_GLO_CFG, + FIELD_PREP(MTK_WED_RTQM_TXDMAD_FPORT, 0x3 + dev->hw->index)); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + /* enable RX_ROUTE_QM */ + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_ROUTE_QM_EN); +} + static void mtk_wed_hw_init(struct mtk_wed_device *dev) { @@ -498,11 +852,11 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_BM_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_BM_CTRL_RSV_GRP_NUM, MTK_WED_TX_RING_SIZE / 256)); - wed_w32(dev, MTK_WED_TX_BM_BASE, dev->buf_ring.desc_phys); + wed_w32(dev, MTK_WED_TX_BM_BASE, dev->tx_buf_ring.desc_phys); wed_w32(dev, MTK_WED_TX_BM_BUF_LEN, MTK_WED_PKT_SIZE); @@ -529,9 +883,9 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_TKID_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_TKID_CTRL_RSV_GRP_NUM, - dev->buf_ring.size / 128)); + dev->tx_buf_ring.size / 128)); wed_w32(dev, MTK_WED_TX_TKID_DYN_THR, FIELD_PREP(MTK_WED_TX_TKID_DYN_THR_LO, 0) | MTK_WED_TX_TKID_DYN_THR_HI); @@ -539,18 +893,28 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) mtk_wed_reset(dev, MTK_WED_RESET_TX_BM); - if (dev->hw->version == 1) + if (dev->hw->version == 1) { wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_TX_BM_EN | MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); - else + } else { wed_clr(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE); + /* rx hw init */ + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, + MTK_WED_WPDMA_RX_D_RST_CRX_IDX | + MTK_WED_WPDMA_RX_D_RST_DRV_IDX); + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, 0); + + mtk_wed_rx_buffer_hw_init(dev); + mtk_wed_rro_hw_init(dev); + mtk_wed_route_qm_hw_init(dev); + } wed_clr(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE); } static void -mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) +mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size, bool tx) { void *head = (void *)ring->desc; int i; @@ -560,7 +924,10 @@ mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) desc = (struct mtk_wdma_desc *)(head + i * ring->desc_size); desc->buf0 = 0; - desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + if (tx) + desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + else + desc->ctrl = cpu_to_le32(MTK_WFDMA_DESC_CTRL_TO_HOST); desc->buf1 = 0; desc->info = 0; } @@ -616,7 +983,8 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) if (!dev->tx_ring[i].desc) continue; - mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE); + mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE, + true); } if (mtk_wed_poll_busy(dev)) @@ -634,6 +1002,9 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX); wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + if (mtk_wed_get_rx_capa(dev)) + mtk_wdma_rx_reset(dev); + if (busy) { mtk_wed_reset(dev, MTK_WED_RESET_WDMA_INT_AGENT); mtk_wed_reset(dev, MTK_WED_RESET_WDMA_RX_DRV); @@ -668,12 +1039,11 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) MTK_WED_WPDMA_RESET_IDX_RX); wed_w32(dev, MTK_WED_WPDMA_RESET_IDX, 0); } - } static int mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, - int size, u32 desc_size) + int size, u32 desc_size, bool tx) { ring->desc = dma_alloc_coherent(dev->hw->dev, size * desc_size, &ring->desc_phys, GFP_KERNEL); @@ -682,7 +1052,7 @@ mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, ring->desc_size = desc_size; ring->size = size; - mtk_wed_ring_reset(ring, size); + mtk_wed_ring_reset(ring, size, tx); return 0; } @@ -691,9 +1061,14 @@ static int mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; - struct mtk_wed_ring *wdma = &dev->rx_wdma[idx]; + struct mtk_wed_ring *wdma; - if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size)) + if (idx >= ARRAY_SIZE(dev->rx_wdma)) + return -EINVAL; + + wdma = &dev->rx_wdma[idx]; + if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, + true)) return -ENOMEM; wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE, @@ -710,6 +1085,60 @@ mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) return 0; } +static int +mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size) +{ + u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; + struct mtk_wed_ring *wdma; + + if (idx >= ARRAY_SIZE(dev->tx_wdma)) + return -EINVAL; + + wdma = &dev->tx_wdma[idx]; + if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, + true)) + return -ENOMEM; + + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_COUNT, + size); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_DMA_IDX, 0); + + if (!idx) { + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_COUNT, + size); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_CPU_IDX, + 0); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_DMA_IDX, + 0); + } + + return 0; +} + +static void +mtk_wed_ppe_check(struct mtk_wed_device *dev, struct sk_buff *skb, + u32 reason, u32 hash) +{ + struct mtk_eth *eth = dev->hw->eth; + struct ethhdr *eh; + + if (!skb) + return; + + if (reason != MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) + return; + + skb_set_mac_header(skb, 0); + eh = eth_hdr(skb); + skb->protocol = eh->h_proto; + mtk_ppe_check_skb(eth->ppe[dev->hw->index], skb, hash); +} + static void mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) { @@ -732,6 +1161,8 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) wed_clr(dev, MTK_WED_WDMA_INT_CTRL, wdma_mask); } else { + wdma_mask |= FIELD_PREP(MTK_WDMA_INT_MASK_TX_DONE, + GENMASK(1, 0)); /* initail tx interrupt trigger */ wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX, MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN | @@ -750,6 +1181,16 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_TRIG, dev->wlan.txfree_tbit)); + wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_RX, + MTK_WED_WPDMA_INT_CTRL_RX0_EN | + MTK_WED_WPDMA_INT_CTRL_RX0_CLR | + MTK_WED_WPDMA_INT_CTRL_RX1_EN | + MTK_WED_WPDMA_INT_CTRL_RX1_CLR | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG, + dev->wlan.rx_tbit[0]) | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG, + dev->wlan.rx_tbit[1])); + wed_w32(dev, MTK_WED_WDMA_INT_CLR, wdma_mask); wed_set(dev, MTK_WED_WDMA_INT_CTRL, FIELD_PREP(MTK_WED_WDMA_INT_CTRL_POLL_SRC_SEL, @@ -787,9 +1228,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { + int i; + wed_set(dev, MTK_WED_WPDMA_CTRL, MTK_WED_WPDMA_CTRL_SDL1_FIXED); + wed_set(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DRV_EN | + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); + wed_set(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); @@ -797,6 +1244,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_TX_TKID_KEEP | MTK_WED_WPDMA_GLO_CFG_TX_DMAD_DW3_PREV); + + wed_set(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN | + FIELD_PREP(MTK_WED_WPDMA_RX_D_RXD_READ_LEN, 0x18) | + FIELD_PREP(MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL, + 0x2)); + + for (i = 0; i < MTK_WED_RX_QUEUES; i++) + mtk_wed_check_wfdma_rx_fill(dev, i); } } @@ -822,7 +1278,19 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) val |= BIT(0) | (BIT(1) * !!dev->hw->index); regmap_write(dev->hw->mirror, dev->hw->index * 4, val); } else { - mtk_wed_set_512_support(dev, true); + /* driver set mid ready and only once */ + wed_w32(dev, MTK_WED_EXT_INT_MASK1, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + + wed_r32(dev, MTK_WED_EXT_INT_MASK1); + wed_r32(dev, MTK_WED_EXT_INT_MASK2); + + if (mtk_wed_rro_cfg(dev)) + return; + + mtk_wed_set_512_support(dev, dev->wlan.wcid_512); } mtk_wed_dma_enable(dev); @@ -856,7 +1324,7 @@ mtk_wed_attach(struct mtk_wed_device *dev) if (!hw) { module_put(THIS_MODULE); ret = -ENODEV; - goto out; + goto unlock; } device = dev->wlan.bus_type == MTK_WED_BUS_PCIE @@ -869,15 +1337,24 @@ mtk_wed_attach(struct mtk_wed_device *dev) dev->dev = hw->dev; dev->irq = hw->irq; dev->wdma_idx = hw->index; + dev->version = hw->version; if (hw->eth->dma_dev == hw->eth->dev && of_dma_is_coherent(hw->eth->dev->of_node)) mtk_eth_set_dma_device(hw->eth, hw->dev); - ret = mtk_wed_buffer_alloc(dev); - if (ret) { - mtk_wed_detach(dev); + ret = mtk_wed_tx_buffer_alloc(dev); + if (ret) goto out; + + if (mtk_wed_get_rx_capa(dev)) { + ret = mtk_wed_rx_buffer_alloc(dev); + if (ret) + goto out; + + ret = mtk_wed_rro_alloc(dev); + if (ret) + goto out; } mtk_wed_hw_init_early(dev); @@ -886,8 +1363,10 @@ mtk_wed_attach(struct mtk_wed_device *dev) BIT(hw->index), 0); else ret = mtk_wed_wo_init(hw); - out: + if (ret) + mtk_wed_detach(dev); +unlock: mutex_unlock(&hw_lock); return ret; @@ -910,10 +1389,11 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) * WDMA RX. */ - BUG_ON(idx >= ARRAY_SIZE(dev->tx_ring)); + if (WARN_ON(idx >= ARRAY_SIZE(dev->tx_ring))) + return -EINVAL; if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, - sizeof(*ring->desc))) + sizeof(*ring->desc), true)) return -ENOMEM; if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) @@ -960,6 +1440,37 @@ mtk_wed_txfree_ring_setup(struct mtk_wed_device *dev, void __iomem *regs) return 0; } +static int +mtk_wed_rx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) +{ + struct mtk_wed_ring *ring = &dev->rx_ring[idx]; + + if (WARN_ON(idx >= ARRAY_SIZE(dev->rx_ring))) + return -EINVAL; + + if (mtk_wed_ring_alloc(dev, ring, MTK_WED_RX_RING_SIZE, + sizeof(*ring->desc), false)) + return -ENOMEM; + + if (mtk_wed_wdma_tx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + return -ENOMEM; + + ring->reg_base = MTK_WED_RING_RX_DATA(idx); + ring->wpdma = regs; + ring->flags |= MTK_WED_RING_CONFIGURED; + + /* WPDMA -> WED */ + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_BASE, ring->desc_phys); + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_COUNT, MTK_WED_RX_RING_SIZE); + + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_BASE, + ring->desc_phys); + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_COUNT, + MTK_WED_RX_RING_SIZE); + + return 0; +} + static u32 mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) { @@ -1056,7 +1567,9 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, static const struct mtk_wed_ops wed_ops = { .attach = mtk_wed_attach, .tx_ring_setup = mtk_wed_tx_ring_setup, + .rx_ring_setup = mtk_wed_rx_ring_setup, .txfree_ring_setup = mtk_wed_txfree_ring_setup, + .msg_update = mtk_wed_mcu_msg_update, .start = mtk_wed_start, .stop = mtk_wed_stop, .reset_dma = mtk_wed_reset_dma, @@ -1065,6 +1578,7 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, .irq_get = mtk_wed_irq_get, .irq_set_mask = mtk_wed_irq_set_mask, .detach = mtk_wed_detach, + .ppe_check = mtk_wed_ppe_check, }; struct device_node *eth_np = eth->dev->of_node; struct platform_device *pdev; diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h index af656fd31ff9..e012b8a82133 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.h +++ b/drivers/net/ethernet/mediatek/mtk_wed.h @@ -86,6 +86,24 @@ wpdma_tx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) writel(val, dev->tx_ring[ring].wpdma + reg); } +static inline u32 +wpdma_rx_r32(struct mtk_wed_device *dev, int ring, u32 reg) +{ + if (!dev->rx_ring[ring].wpdma) + return 0; + + return readl(dev->rx_ring[ring].wpdma + reg); +} + +static inline void +wpdma_rx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) +{ + if (!dev->rx_ring[ring].wpdma) + return; + + writel(val, dev->rx_ring[ring].wpdma + reg); +} + static inline u32 wpdma_txfree_r32(struct mtk_wed_device *dev, u32 reg) { @@ -128,6 +146,7 @@ static inline int mtk_wed_flow_add(int index) static inline void mtk_wed_flow_remove(int index) { } + #endif #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c index b657328a1d9d..f9539e6233c9 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "mtk_wed_regs.h" #include "mtk_wed_wo.h" @@ -60,24 +61,37 @@ void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb) wake_up(&wo->mcu.wait); } +static void +mtk_wed_update_rx_stats(struct mtk_wed_device *wed, struct sk_buff *skb) +{ + u32 count = get_unaligned_le32(skb->data); + struct mtk_wed_wo_rx_stats *stats; + int i; + + if (count * sizeof(*stats) > skb->len - sizeof(u32)) + return; + + stats = (struct mtk_wed_wo_rx_stats *)(skb->data + sizeof(u32)); + for (i = 0 ; i < count ; i++) + wed->wlan.update_wo_rx_stats(wed, &stats[i]); +} + void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, struct sk_buff *skb) { struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; - switch (hdr->cmd) { - case MTK_WED_WO_EVT_LOG_DUMP: { - const char *msg = (const char *)(skb->data + sizeof(*hdr)); + skb_pull(skb, sizeof(*hdr)); - dev_notice(wo->hw->dev, "%s\n", msg); + switch (hdr->cmd) { + case MTK_WED_WO_EVT_LOG_DUMP: + dev_notice(wo->hw->dev, "%s\n", skb->data); break; - } case MTK_WED_WO_EVT_PROFILING: { - struct mtk_wed_wo_log_info *info; - u32 count = (skb->len - sizeof(*hdr)) / sizeof(*info); + struct mtk_wed_wo_log_info *info = (void *)skb->data; + u32 count = skb->len / sizeof(*info); int i; - info = (struct mtk_wed_wo_log_info *)(skb->data + sizeof(*hdr)); for (i = 0 ; i < count ; i++) dev_notice(wo->hw->dev, "SN:%u latency: total=%u, rro:%u, mod:%u\n", @@ -88,6 +102,7 @@ void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, break; } case MTK_WED_WO_EVT_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); break; default: break; @@ -144,6 +159,8 @@ mtk_wed_mcu_parse_response(struct mtk_wed_wo *wo, struct sk_buff *skb, skb_pull(skb, sizeof(*hdr)); switch (cmd) { case MTK_WED_WO_CMD_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); + break; default: break; } @@ -182,6 +199,18 @@ unlock: return ret; } +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + + if (dev->hw->version == 1) + return 0; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, id, data, len, + true); +} + static int mtk_wed_get_memory_region(struct mtk_wed_wo *wo, struct mtk_wed_wo_memory_region *region) diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h index c940b3bb215b..9e39dace95eb 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h @@ -4,6 +4,7 @@ #ifndef __MTK_WED_REGS_H #define __MTK_WED_REGS_H +#define MTK_WFDMA_DESC_CTRL_TO_HOST BIT(8) #define MTK_WDMA_DESC_CTRL_LEN1 GENMASK(14, 0) #define MTK_WDMA_DESC_CTRL_LEN1_V2 GENMASK(13, 0) #define MTK_WDMA_DESC_CTRL_LAST_SEG1 BIT(15) @@ -28,6 +29,8 @@ struct mtk_wdma_desc { #define MTK_WED_RESET_WED_TX_DMA BIT(12) #define MTK_WED_RESET_WDMA_RX_DRV BIT(17) #define MTK_WED_RESET_WDMA_INT_AGENT BIT(19) +#define MTK_WED_RESET_RX_RRO_QM BIT(20) +#define MTK_WED_RESET_RX_ROUTE_QM BIT(21) #define MTK_WED_RESET_WED BIT(31) #define MTK_WED_CTRL 0x00c @@ -39,8 +42,12 @@ struct mtk_wdma_desc { #define MTK_WED_CTRL_WED_TX_BM_BUSY BIT(9) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_EN BIT(10) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY BIT(11) -#define MTK_WED_CTRL_RESERVE_EN BIT(12) -#define MTK_WED_CTRL_RESERVE_BUSY BIT(13) +#define MTK_WED_CTRL_WED_RX_BM_EN BIT(12) +#define MTK_WED_CTRL_WED_RX_BM_BUSY BIT(13) +#define MTK_WED_CTRL_RX_RRO_QM_EN BIT(14) +#define MTK_WED_CTRL_RX_RRO_QM_BUSY BIT(15) +#define MTK_WED_CTRL_RX_ROUTE_QM_EN BIT(16) +#define MTK_WED_CTRL_RX_ROUTE_QM_BUSY BIT(17) #define MTK_WED_CTRL_FINAL_DIDX_READ BIT(24) #define MTK_WED_CTRL_ETH_DMAD_FMT BIT(25) #define MTK_WED_CTRL_MIB_READ_CLEAR BIT(28) @@ -62,6 +69,9 @@ struct mtk_wdma_desc { #define MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR BIT(22) #define MTK_WED_EXT_INT_STATUS_TX_DMA_W_RESP_ERR BIT(23) #define MTK_WED_EXT_INT_STATUS_RX_DRV_DMA_RECYCLE BIT(24) +#define MTK_WED_EXT_INT_STATUS_RX_DRV_GET_BM_DMAD_SKIP BIT(25) +#define MTK_WED_EXT_INT_STATUS_WPDMA_RX_D_DRV_ERR BIT(26) +#define MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY BIT(27) #define MTK_WED_EXT_INT_STATUS_ERROR_MASK (MTK_WED_EXT_INT_STATUS_TF_LEN_ERR | \ MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD | \ MTK_WED_EXT_INT_STATUS_TKID_TITO_INVALID | \ @@ -71,6 +81,8 @@ struct mtk_wdma_desc { MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR) #define MTK_WED_EXT_INT_MASK 0x028 +#define MTK_WED_EXT_INT_MASK1 0x02c +#define MTK_WED_EXT_INT_MASK2 0x030 #define MTK_WED_STATUS 0x060 #define MTK_WED_STATUS_TX GENMASK(15, 8) @@ -151,6 +163,7 @@ struct mtk_wdma_desc { #define MTK_WED_RING_TX(_n) (0x300 + (_n) * 0x10) #define MTK_WED_RING_RX(_n) (0x400 + (_n) * 0x10) +#define MTK_WED_RING_RX_DATA(_n) (0x420 + (_n) * 0x10) #define MTK_WED_SCR0 0x3c0 #define MTK_WED_WPDMA_INT_TRIGGER 0x504 @@ -213,6 +226,12 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_RX 0x534 +#define MTK_WED_WPDMA_INT_CTRL_RX0_EN BIT(0) +#define MTK_WED_WPDMA_INT_CTRL_RX0_CLR BIT(1) +#define MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG GENMASK(6, 2) +#define MTK_WED_WPDMA_INT_CTRL_RX1_EN BIT(8) +#define MTK_WED_WPDMA_INT_CTRL_RX1_CLR BIT(9) +#define MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_TX_FREE 0x538 #define MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN BIT(0) @@ -242,11 +261,34 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_RING_TX(_n) (0x600 + (_n) * 0x10) #define MTK_WED_WPDMA_RING_RX(_n) (0x700 + (_n) * 0x10) +#define MTK_WED_WPDMA_RING_RX_DATA(_n) (0x730 + (_n) * 0x10) + +#define MTK_WED_WPDMA_RX_D_GLO_CFG 0x75c +#define MTK_WED_WPDMA_RX_D_RX_DRV_EN BIT(0) +#define MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL GENMASK(11, 7) +#define MTK_WED_WPDMA_RX_D_RXD_READ_LEN GENMASK(31, 24) + +#define MTK_WED_WPDMA_RX_D_RST_IDX 0x760 +#define MTK_WED_WPDMA_RX_D_RST_CRX_IDX GENMASK(17, 16) +#define MTK_WED_WPDMA_RX_D_RST_DRV_IDX GENMASK(25, 24) + +#define MTK_WED_WPDMA_RX_GLO_CFG 0x76c +#define MTK_WED_WPDMA_RX_RING 0x770 + +#define MTK_WED_WPDMA_RX_D_MIB(_n) (0x774 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_PROCESSED_MIB(_n) (0x784 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_COHERENT_MIB 0x78c + +#define MTK_WED_WDMA_RING_TX 0x800 + +#define MTK_WED_WDMA_TX_MIB 0x810 + #define MTK_WED_WDMA_RING_RX(_n) (0x900 + (_n) * 0x10) #define MTK_WED_WDMA_RX_THRES(_n) (0x940 + (_n) * 0x4) #define MTK_WED_WDMA_GLO_CFG 0xa04 #define MTK_WED_WDMA_GLO_CFG_TX_DRV_EN BIT(0) +#define MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK BIT(1) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_EN BIT(2) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY BIT(3) #define MTK_WED_WDMA_GLO_CFG_BT_SIZE GENMASK(5, 4) @@ -291,6 +333,20 @@ struct mtk_wdma_desc { #define MTK_WED_WDMA_RX_RECYCLE_MIB(_n) (0xae8 + (_n) * 4) #define MTK_WED_WDMA_RX_PROCESSED_MIB(_n) (0xaf0 + (_n) * 4) +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_RX_DMAD_SDL0 GENMASK(13, 0) + +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_SW_TAIL GENMASK(15, 0) +#define MTK_WED_RX_BM_INIT_SW_TAIL BIT(16) + +#define MTK_WED_RX_PTR 0xd8c + +#define MTK_WED_RX_BM_DYN_ALLOC_TH 0xdb4 +#define MTK_WED_RX_BM_DYN_ALLOC_TH_H GENMASK(31, 16) +#define MTK_WED_RX_BM_DYN_ALLOC_TH_L GENMASK(15, 0) + #define MTK_WED_RING_OFS_BASE 0x00 #define MTK_WED_RING_OFS_COUNT 0x04 #define MTK_WED_RING_OFS_CPU_IDX 0x08 @@ -301,7 +357,9 @@ struct mtk_wdma_desc { #define MTK_WDMA_GLO_CFG 0x204 #define MTK_WDMA_GLO_CFG_TX_DMA_EN BIT(0) +#define MTK_WDMA_GLO_CFG_TX_DMA_BUSY BIT(1) #define MTK_WDMA_GLO_CFG_RX_DMA_EN BIT(2) +#define MTK_WDMA_GLO_CFG_RX_DMA_BUSY BIT(3) #define MTK_WDMA_GLO_CFG_RX_INFO3_PRERES BIT(26) #define MTK_WDMA_GLO_CFG_RX_INFO2_PRERES BIT(27) #define MTK_WDMA_GLO_CFG_RX_INFO1_PRERES BIT(28) @@ -330,4 +388,70 @@ struct mtk_wdma_desc { /* DMA channel mapping */ #define HIFSYS_DMA_AG_MAP 0x008 +#define MTK_WED_RTQM_GLO_CFG 0xb00 +#define MTK_WED_RTQM_BUSY BIT(1) +#define MTK_WED_RTQM_Q_RST BIT(2) +#define MTK_WED_RTQM_Q_DBG_BYPASS BIT(5) +#define MTK_WED_RTQM_TXDMAD_FPORT GENMASK(23, 20) + +#define MTK_WED_RTQM_R2H_MIB(_n) (0xb70 + (_n) * 0x4) +#define MTK_WED_RTQM_R2Q_MIB(_n) (0xb78 + (_n) * 0x4) +#define MTK_WED_RTQM_Q2N_MIB 0xb80 +#define MTK_WED_RTQM_Q2H_MIB(_n) (0xb84 + (_n) * 0x4) + +#define MTK_WED_RTQM_Q2B_MIB 0xb8c +#define MTK_WED_RTQM_PFDBK_MIB 0xb90 + +#define MTK_WED_RROQM_GLO_CFG 0xc04 +#define MTK_WED_RROQM_RST_IDX 0xc08 +#define MTK_WED_RROQM_RST_IDX_MIOD BIT(0) +#define MTK_WED_RROQM_RST_IDX_FDBK BIT(4) + +#define MTK_WED_RROQM_MIOD_CTRL0 0xc40 +#define MTK_WED_RROQM_MIOD_CTRL1 0xc44 +#define MTK_WED_RROQM_MIOD_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_MIOD_CTRL2 0xc48 +#define MTK_WED_RROQM_MIOD_CTRL3 0xc4c + +#define MTK_WED_RROQM_FDBK_CTRL0 0xc50 +#define MTK_WED_RROQM_FDBK_CTRL1 0xc54 +#define MTK_WED_RROQM_FDBK_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_FDBK_CTRL2 0xc58 + +#define MTK_WED_RROQ_BASE_L 0xc80 +#define MTK_WED_RROQ_BASE_H 0xc84 + +#define MTK_WED_RROQM_MIOD_CFG 0xc8c +#define MTK_WED_RROQM_MIOD_MID_DW GENMASK(5, 0) +#define MTK_WED_RROQM_MIOD_MOD_DW GENMASK(13, 8) +#define MTK_WED_RROQM_MIOD_ENTRY_DW GENMASK(22, 16) + +#define MTK_WED_RROQM_MID_MIB 0xcc0 +#define MTK_WED_RROQM_MOD_MIB 0xcc4 +#define MTK_WED_RROQM_MOD_COHERENT_MIB 0xcc8 +#define MTK_WED_RROQM_FDBK_MIB 0xcd0 +#define MTK_WED_RROQM_FDBK_COHERENT_MIB 0xcd4 +#define MTK_WED_RROQM_FDBK_IND_MIB 0xce0 +#define MTK_WED_RROQM_FDBK_ENQ_MIB 0xce4 +#define MTK_WED_RROQM_FDBK_ANC_MIB 0xce8 +#define MTK_WED_RROQM_FDBK_ANC2H_MIB 0xcec + +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_PTR 0xd8c +#define MTK_WED_RX_BM_PTR_HEAD GENMASK(32, 16) +#define MTK_WED_RX_BM_PTR_TAIL GENMASK(15, 0) + +#define MTK_WED_RX_BM_BLEN 0xd90 +#define MTK_WED_RX_BM_STS 0xd94 +#define MTK_WED_RX_BM_INTF2 0xd98 +#define MTK_WED_RX_BM_INTF 0xd9c +#define MTK_WED_RX_BM_ERR_STS 0xda8 + +#define MTK_WED_WOCPU_VIEW_MIOD_BASE 0x8000 +#define MTK_WED_PCIE_INT_MASK 0x0 + #endif diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h index ed7e69d420dc..c8fb85795864 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -49,6 +49,10 @@ enum { MTK_WED_WARP_CMD_FLAG_FROM_TO_WO = BIT(2), }; +#define MTK_WED_WO_CPU_MCUSYS_RESET_ADDR 0x15194050 +#define MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK 0x20 +#define MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK 0x1 + enum { MTK_WED_WO_REGION_EMI, MTK_WED_WO_REGION_ILM, @@ -57,6 +61,28 @@ enum { __MTK_WED_WO_REGION_MAX, }; +enum mtk_wed_wo_state { + MTK_WED_WO_STATE_UNDEFINED, + MTK_WED_WO_STATE_INIT, + MTK_WED_WO_STATE_ENABLE, + MTK_WED_WO_STATE_DISABLE, + MTK_WED_WO_STATE_HALT, + MTK_WED_WO_STATE_GATING, + MTK_WED_WO_STATE_SER_RESET, + MTK_WED_WO_STATE_WF_RESET, +}; + +enum mtk_wed_wo_done_state { + MTK_WED_WOIF_UNDEFINED, + MTK_WED_WOIF_DISABLE_DONE, + MTK_WED_WOIF_TRIGGER_ENABLE, + MTK_WED_WOIF_ENABLE_DONE, + MTK_WED_WOIF_TRIGGER_GATING, + MTK_WED_WOIF_GATING_DONE, + MTK_WED_WOIF_TRIGGER_HALT, + MTK_WED_WOIF_HALT_DONE, +}; + enum mtk_wed_dummy_cr_idx { MTK_WED_DUMMY_CR_FWDL, MTK_WED_DUMMY_CR_WO_STATUS, @@ -245,6 +271,8 @@ void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, struct sk_buff *skb); int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, const void *data, int len, bool wait_resp); +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len); int mtk_wed_mcu_init(struct mtk_wed_wo *wo); int mtk_wed_wo_init(struct mtk_wed_hw *hw); void mtk_wed_wo_deinit(struct mtk_wed_hw *hw); diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 956978320f8b..8294978f4bca 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -5,10 +5,13 @@ #include #include #include +#include #define MTK_WED_TX_QUEUES 2 #define MTK_WED_RX_QUEUES 2 +#define WED_WO_STA_REC 0x6 + struct mtk_wed_hw; struct mtk_wdma_desc; @@ -41,21 +44,37 @@ enum mtk_wed_wo_cmd { MTK_WED_WO_CMD_WED_END }; +struct mtk_rxbm_desc { + __le32 buf0; + __le32 token; +} __packed __aligned(4); + enum mtk_wed_bus_tye { MTK_WED_BUS_PCIE, MTK_WED_BUS_AXI, }; +#define MTK_WED_RING_CONFIGURED BIT(0) struct mtk_wed_ring { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; u32 desc_size; int size; + u32 flags; u32 reg_base; void __iomem *wpdma; }; +struct mtk_wed_wo_rx_stats { + __le16 wlan_idx; + __le16 tid; + __le32 rx_pkt_cnt; + __le32 rx_byte_cnt; + __le32 rx_err_cnt; + __le32 rx_drop_cnt; +}; + struct mtk_wed_device { #ifdef CONFIG_NET_MEDIATEK_SOC_WED const struct mtk_wed_ops *ops; @@ -64,9 +83,12 @@ struct mtk_wed_device { bool init_done, running; int wdma_idx; int irq; + u8 version; struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring rx_ring[MTK_WED_RX_QUEUES]; struct mtk_wed_ring txfree_ring; + struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES]; struct { @@ -74,7 +96,20 @@ struct mtk_wed_device { void **pages; struct mtk_wdma_desc *desc; dma_addr_t desc_phys; - } buf_ring; + } tx_buf_ring; + + struct { + int size; + struct page_frag_cache rx_page; + struct mtk_rxbm_desc *desc; + dma_addr_t desc_phys; + } rx_buf_ring; + + struct { + struct mtk_wed_ring ring; + dma_addr_t miod_phys; + dma_addr_t fdbk_phys; + } rro; /* filled by driver: */ struct { @@ -83,22 +118,36 @@ struct mtk_wed_device { struct pci_dev *pci_dev; }; enum mtk_wed_bus_tye bus_type; + void __iomem *base; + u32 phy_base; u32 wpdma_phys; u32 wpdma_int; u32 wpdma_mask; u32 wpdma_tx; u32 wpdma_txfree; + u32 wpdma_rx_glo; + u32 wpdma_rx; + + bool wcid_512; u16 token_start; unsigned int nbuf; + unsigned int rx_nbuf; + unsigned int rx_npkt; + unsigned int rx_size; u8 tx_tbit[MTK_WED_TX_QUEUES]; + u8 rx_tbit[MTK_WED_RX_QUEUES]; u8 txfree_tbit; u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); int (*offload_enable)(struct mtk_wed_device *wed); void (*offload_disable)(struct mtk_wed_device *wed); + u32 (*init_rx_buf)(struct mtk_wed_device *wed, int size); + void (*release_rx_buf)(struct mtk_wed_device *wed); + void (*update_wo_rx_stats)(struct mtk_wed_device *wed, + struct mtk_wed_wo_rx_stats *stats); } wlan; #endif }; @@ -107,9 +156,15 @@ struct mtk_wed_ops { int (*attach)(struct mtk_wed_device *dev); int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, void __iomem *regs); + int (*rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); int (*txfree_ring_setup)(struct mtk_wed_device *dev, void __iomem *regs); + int (*msg_update)(struct mtk_wed_device *dev, int cmd_id, + void *data, int len); void (*detach)(struct mtk_wed_device *dev); + void (*ppe_check)(struct mtk_wed_device *dev, struct sk_buff *skb, + u32 reason, u32 hash); void (*stop)(struct mtk_wed_device *dev); void (*start)(struct mtk_wed_device *dev, u32 irq_mask); @@ -144,6 +199,16 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) return ret; } +static inline bool +mtk_wed_get_rx_capa(struct mtk_wed_device *dev) +{ +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + return dev->version != 1; +#else + return false; +#endif +} + #ifdef CONFIG_NET_MEDIATEK_SOC_WED #define mtk_wed_device_active(_dev) !!(_dev)->ops #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) @@ -160,6 +225,12 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) (_dev)->ops->irq_get(_dev, _mask) #define mtk_wed_device_irq_set_mask(_dev, _mask) \ (_dev)->ops->irq_set_mask(_dev, _mask) +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) \ + (_dev)->ops->ppe_check(_dev, _skb, _reason, _hash) +#define mtk_wed_device_update_msg(_dev, _id, _msg, _len) \ + (_dev)->ops->msg_update(_dev, _id, _msg, _len) #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -173,6 +244,9 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) #define mtk_wed_device_irq_get(_dev, _mask) 0 #define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) do {} while (0) +#define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV #endif #endif -- cgit v1.2.3 From 75ab70ec5cefade915a999886e4863fe6a38f8b5 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Wed, 9 Nov 2022 15:09:45 -0800 Subject: ptp: remove the .adjfreq interface function Now that all drivers have been converted to .adjfine, we can remove the .adjfreq from the interface structure. Signed-off-by: Jacob Keller Cc: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_clock.c | 5 +---- include/linux/ptp_clock_kernel.h | 7 ------- 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 51cae72bb6db..62d4d29e7c05 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -131,10 +131,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) long ppb = scaled_ppm_to_ppb(tx->freq); if (ppb > ops->max_adj || ppb < -ops->max_adj) return -ERANGE; - if (ops->adjfine) - err = ops->adjfine(ops, tx->freq); - else - err = ops->adjfreq(ops, ppb); + err = ops->adjfine(ops, tx->freq); ptp->dialed_frequency = tx->freq; } else if (tx->modes & ADJ_OFFSET) { if (ops->adjphase) { diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index f4781c5766d6..fdffa6a98d79 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -77,12 +77,6 @@ struct ptp_system_timestamp { * nominal frequency in parts per million, but with a * 16 bit binary fractional field. * - * @adjfreq: Adjusts the frequency of the hardware clock. - * This method is deprecated. New drivers should implement - * the @adjfine method instead. - * parameter delta: Desired frequency offset from nominal frequency - * in parts per billion - * * @adjphase: Adjusts the phase offset of the hardware clock. * parameter delta: Desired change in nanoseconds. * @@ -174,7 +168,6 @@ struct ptp_clock_info { int pps; struct ptp_pin_desc *pin_config; int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); - int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjphase)(struct ptp_clock_info *ptp, s32 phase); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); -- cgit v1.2.3 From 9bb053490f1a5a0914eb9f7b4116a0e4a95d4f8e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 7 Nov 2022 15:04:18 -0800 Subject: bpf: Add hwtstamp field for the sockops prog The bpf-tc prog has already been able to access the skb_hwtstamps(skb)->hwtstamp. This patch extends the same hwtstamp access to the sockops prog. In sockops, the skb is also available to the bpf prog during the BPF_SOCK_OPS_PARSE_HDR_OPT_CB event. There is a use case that the hwtstamp will be useful to the sockops prog to better measure the one-way-delay when the sender has put the tx timestamp in the tcp header option. Signed-off-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20221107230420.4192307-2-martin.lau@linux.dev --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 39 +++++++++++++++++++++++++++++++-------- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 33 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 94659f6b3395..fb4c911d2a03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6445,6 +6445,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ diff --git a/net/core/filter.c b/net/core/filter.c index cb3b635e35be..cd667cdbdb26 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8925,6 +8925,10 @@ static bool sock_ops_is_valid_access(int off, int size, bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case offsetof(struct bpf_sock_ops, skb_hwtstamp): + if (size != sizeof(__u64)) + return false; + break; default: if (size != size_default) return false; @@ -9108,21 +9112,21 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, return insn; } -static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, +static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - BPF_REG_AX, si->src_reg, + BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, head)); - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif @@ -9515,7 +9519,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, gso_segs): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9523,7 +9527,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, gso_size): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9550,7 +9554,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -10400,6 +10404,25 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, tcp_flags), si->dst_reg, si->dst_reg, off); break; + case offsetof(struct bpf_sock_ops, skb_hwtstamp): { + struct bpf_insn *jmp_on_null_skb; + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + /* Reserve one insn to test skb == NULL */ + jmp_on_null_skb = insn++; + insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, + insn - jmp_on_null_skb - 1); + break; + } } return insn - insn_buf; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 94659f6b3395..fb4c911d2a03 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6445,6 +6445,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ -- cgit v1.2.3 From 354259fa73e2aac92ae5e19522adb69a92c15b49 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Nov 2022 09:57:58 +0000 Subject: net: remove skb->vlan_present skb->vlan_present seems redundant. We can instead derive it from this boolean expression: vlan_present = skb->vlan_proto != 0 || skb->vlan_tci != 0 Add a new union, to access both fields in a single load/store when possible. union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; This allows following patch to remove a conditional test in GRO stack. Note: We move remcsum_offload to keep TC_AT_INGRESS_MASK and SKB_MONO_DELIVERY_TIME_MASK unchanged. Signed-off-by: Eric Dumazet Acked-by: Yonghong Song Acked-by: Martin KaFai Lau Signed-off-by: Jakub Kicinski --- arch/sparc/net/bpf_jit_comp_32.c | 10 +++++----- .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 +- include/linux/if_vlan.h | 9 +++------ include/linux/skbuff.h | 18 ++++++++++-------- lib/test_bpf.c | 1 - net/core/filter.c | 22 ++++++++++------------ 6 files changed, 29 insertions(+), 33 deletions(-) (limited to 'include') diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index b1dbf2fa8c0a..a74e5004c6c8 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -555,11 +555,11 @@ void bpf_jit_compile(struct bpf_prog *fp) emit_skb_load16(vlan_tci, r_A); break; case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: - __emit_skb_load8(__pkt_vlan_present_offset, r_A); - if (PKT_VLAN_PRESENT_BIT) - emit_alu_K(SRL, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - emit_andi(r_A, 1, r_A); + emit_skb_load32(vlan_all, r_A); + emit_cmpi(r_A, 0); + emit_branch_off(BE, 12); + emit_nop(); + emit_loadimm(1, r_A); break; case BPF_LD | BPF_W | BPF_LEN: emit_skb_load32(len, r_A); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 303930499a4c..c1ea60bc2630 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1973,7 +1973,7 @@ static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, #endif #ifdef CONFIG_DCB - if (!skb->vlan_present) + if (!skb_vlan_tag_present(skb)) goto pick_tx; vlan_prio = skb->vlan_tci >> 13; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index e00c4ee81ff7..6864b89ef868 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -76,7 +76,7 @@ static inline bool is_vlan_dev(const struct net_device *dev) return dev->priv_flags & IFF_802_1Q_VLAN; } -#define skb_vlan_tag_present(__skb) ((__skb)->vlan_present) +#define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) @@ -471,7 +471,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { - skb->vlan_present = 0; + skb->vlan_all = 0; } /** @@ -483,9 +483,7 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { - dst->vlan_present = src->vlan_present; - dst->vlan_proto = src->vlan_proto; - dst->vlan_tci = src->vlan_tci; + dst->vlan_all = src->vlan_all; } /* @@ -519,7 +517,6 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; - skb->vlan_present = 1; } /** diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 59c9fd55699d..4e464a27adaf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -818,7 +818,7 @@ typedef unsigned char *sk_buff_data_t; * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff - * @vlan_present: VLAN tag is present + * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) @@ -951,7 +951,7 @@ struct sk_buff { /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ - __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ + __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 dst_pending_confirm:1; @@ -966,7 +966,6 @@ struct sk_buff { __u8 ipvs_property:1; __u8 inner_protocol_type:1; - __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; @@ -999,8 +998,13 @@ struct sk_buff { __u32 priority; int skb_iif; __u32 hash; - __be16 vlan_proto; - __u16 vlan_tci; + union { + u32 vlan_all; + struct { + __be16 vlan_proto; + __u16 vlan_tci; + }; + }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; @@ -1059,15 +1063,13 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time +/* if you move tc_at_ingress or mono_delivery_time * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define PKT_VLAN_PRESENT_BIT 7 #define TC_AT_INGRESS_MASK (1 << 0) #define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) #else -#define PKT_VLAN_PRESENT_BIT 0 #define TC_AT_INGRESS_MASK (1 << 7) #define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 5820704165a6..ade9ac672adb 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14346,7 +14346,6 @@ static struct sk_buff *populate_skb(char *buf, int size) skb->hash = SKB_HASH; skb->queue_mapping = SKB_QUEUE_MAP; skb->vlan_tci = SKB_VLAN_TCI; - skb->vlan_present = SKB_VLAN_PRESENT; skb->vlan_proto = htons(ETH_P_IP); dev_net_set(&dev, &init_net); skb->dev = &dev; diff --git a/net/core/filter.c b/net/core/filter.c index bb0136e7a8e4..358d5e70671a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -325,11 +325,11 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: - *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_all)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } @@ -9290,13 +9290,11 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, vlan_present): - *target_size = 1; - *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, - PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, + vlan_all, 4, target_size)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): -- cgit v1.2.3 From 2c925db0a7d69b404d6bfe4c037935c2d367913d Mon Sep 17 00:00:00 2001 From: Ofer Levi Date: Tue, 9 Feb 2021 17:48:11 +0200 Subject: net/mlx5e: Support enhanced CQE compression CQE compression feature improves performance by reducing PCI bandwidth bottleneck on CQEs write. Enhanced CQE compression introduced in ConnectX-6 and it aims to reduce CPU utilization of SW side packets decompression by eliminating the need to rewrite ownership bit, which is likely to cost a cache-miss, is replaced by validity byte handled solely by HW. Another advantage of the enhanced feature is that session packets are available to SW as soon as a single CQE slot is filled, instead of waiting for session to close, this improves packet latency from NIC to host. Performance: Following are tested scenarios and reults comparing basic and enahnced CQE compression. setup: IXIA 100GbE connected directly to port 0 and port 1 of ConnectX-6 Dx 100GbE dual port. Case #1 RX only, single flow goes to single queue: IRQ rate reduced by ~ 30%, CPU utilization improved by 2%. Case #2 IP forwarding from port 1 to port 0 single flow goes to single queue: Avg latency improved from 60us to 21us, frame loss improved from 0.5% to 0.0%. Case #3 IP forwarding from port 1 to port 0 Max Throughput IXIA sends 100%, 8192 UDP flows, goes to 24 queues: Enhanced is equal or slightly better than basic. Testing the basic compression feature with this patch shows there is no perfrormance degradation of the basic compression feature. Signed-off-by: Ofer Levi Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 + .../net/ethernet/mellanox/mlx5/core/en/params.c | 10 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 8 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 150 ++++++++++++++++++--- drivers/net/ethernet/mellanox/mlx5/core/wq.h | 17 +++ include/linux/mlx5/device.h | 6 + 6 files changed, 170 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 26a23047f1f3..ff5b302531d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -344,6 +344,7 @@ enum { MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */ MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, /* set when mini_cqe_resp_stride_index cap is used */ MLX5E_RQ_STATE_SHAMPO, /* set when SHAMPO cap is used */ + MLX5E_RQ_STATE_MINI_CQE_ENHANCED, /* set when enhanced mini_cqe_cap is used */ }; struct mlx5e_cq { @@ -370,6 +371,7 @@ struct mlx5e_cq_decomp { u8 mini_arr_idx; u16 left; u16 wqe_counter; + bool last_cqe_title; } ____cacheline_aligned_in_smp; enum mlx5e_dma_map_type { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 29dd3a04c154..1a2de9bc6538 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -608,13 +608,15 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE; - mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n", + mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d %s)\n", params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? BIT(mlx5e_mpwqe_get_log_rq_size(mdev, params, NULL)) : BIT(params->log_rq_mtu_frames), BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)), - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); + MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS), + MLX5_CAP_GEN(mdev, enhanced_cqe_compression) ? + "enhanced" : "basic"); } void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params) @@ -852,6 +854,10 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { MLX5_SET(cqc, cqc, mini_cqe_res_format, hw_stridx ? MLX5_CQE_FORMAT_CSUM_STRIDX : MLX5_CQE_FORMAT_CSUM); + MLX5_SET(cqc, cqc, cqe_compression_layout, + MLX5_CAP_GEN(mdev, enhanced_cqe_compression) ? + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED : + MLX5_CQE_COMPRESS_LAYOUT_BASIC); MLX5_SET(cqc, cqc, cqe_comp_en, 1); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1669c7d7f285..c462b76743b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1205,6 +1205,13 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, MLX5_CAP_GEN(mdev, mini_cqe_resp_stride_index)) __set_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state); + /* For enhanced CQE compression packet processing. decompress + * session according to the enhanced layout. + */ + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) && + MLX5_CAP_GEN(mdev, enhanced_cqe_compression)) + __set_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state); + return 0; err_destroy_rq: @@ -1895,6 +1902,7 @@ static int mlx5e_alloc_cq_common(struct mlx5e_priv *priv, struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, i); cqe->op_own = 0xf1; + cqe->validity_iteration_count = 0xff; } cq->mdev = mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index a61a43fc8d5c..b1ea0b995d9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -89,6 +89,25 @@ static inline void mlx5e_read_cqe_slot(struct mlx5_cqwq *wq, memcpy(data, mlx5_cqwq_get_wqe(wq, ci), sizeof(struct mlx5_cqe64)); } +static void mlx5e_read_enhanced_title_slot(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe) +{ + struct mlx5e_cq_decomp *cqd = &rq->cqd; + struct mlx5_cqe64 *title = &cqd->title; + + memcpy(title, cqe, sizeof(struct mlx5_cqe64)); + + if (likely(test_bit(MLX5E_RQ_STATE_MINI_CQE_HW_STRIDX, &rq->state))) + return; + + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + cqd->wqe_counter = mpwrq_get_cqe_stride_index(title) + + mpwrq_get_cqe_consumed_strides(title); + else + cqd->wqe_counter = + mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, be16_to_cpu(title->wqe_counter) + 1); +} + static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq, struct mlx5_cqwq *wq, u32 cqcc) @@ -175,6 +194,38 @@ static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq, cqd->title.rss_hash_result = 0; } +static u32 mlx5e_decompress_enhanced_cqe(struct mlx5e_rq *rq, + struct mlx5_cqwq *wq, + struct mlx5_cqe64 *cqe, + int budget_rem) +{ + struct mlx5e_cq_decomp *cqd = &rq->cqd; + u32 cqcc, left; + u32 i; + + left = get_cqe_enhanced_num_mini_cqes(cqe); + /* Here we avoid breaking the cqe compression session in the middle + * in case budget is not sufficient to handle all of it. In this case + * we return work_done == budget_rem to give 'busy' napi indication. + */ + if (unlikely(left > budget_rem)) + return budget_rem; + + cqcc = wq->cc; + cqd->mini_arr_idx = 0; + memcpy(cqd->mini_arr, cqe, sizeof(struct mlx5_cqe64)); + for (i = 0; i < left; i++, cqd->mini_arr_idx++, cqcc++) { + mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, &cqd->title); + } + wq->cc = cqcc; + rq->stats->cqe_compress_pkts += left; + + return left; +} + static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, struct mlx5_cqwq *wq, int update_owner_only, @@ -220,7 +271,7 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, rq, &cqd->title); cqd->mini_arr_idx++; - return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; + return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem); } static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, struct page *page) @@ -2211,45 +2262,102 @@ mpwrq_cqe_out: mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); } -int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) +static int mlx5e_rx_cq_process_enhanced_cqe_comp(struct mlx5e_rq *rq, + struct mlx5_cqwq *cqwq, + int budget_rem) { - struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); - struct mlx5_cqwq *cqwq = &cq->wq; - struct mlx5_cqe64 *cqe; + struct mlx5_cqe64 *cqe, *title_cqe = NULL; + struct mlx5e_cq_decomp *cqd = &rq->cqd; int work_done = 0; - if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) - return 0; + cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq); + if (!cqe) + return work_done; - if (rq->cqd.left) { - work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget); - if (work_done >= budget) - goto out; + if (cqd->last_cqe_title && + (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED)) { + rq->stats->cqe_compress_blks++; + cqd->last_cqe_title = false; } - cqe = mlx5_cqwq_get_cqe(cqwq); - if (!cqe) { - if (unlikely(work_done)) - goto out; - return 0; + do { + if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { + if (title_cqe) { + mlx5e_read_enhanced_title_slot(rq, title_cqe); + title_cqe = NULL; + rq->stats->cqe_compress_blks++; + } + work_done += + mlx5e_decompress_enhanced_cqe(rq, cqwq, cqe, + budget_rem - work_done); + continue; + } + title_cqe = cqe; + mlx5_cqwq_pop(cqwq); + + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, cqe); + work_done++; + } while (work_done < budget_rem && + (cqe = mlx5_cqwq_get_cqe_enahnced_comp(cqwq))); + + /* last cqe might be title on next poll bulk */ + if (title_cqe) { + mlx5e_read_enhanced_title_slot(rq, title_cqe); + cqd->last_cqe_title = true; } - do { + return work_done; +} + +static int mlx5e_rx_cq_process_basic_cqe_comp(struct mlx5e_rq *rq, + struct mlx5_cqwq *cqwq, + int budget_rem) +{ + struct mlx5_cqe64 *cqe; + int work_done = 0; + + if (rq->cqd.left) + work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget_rem); + + while (work_done < budget_rem && (cqe = mlx5_cqwq_get_cqe(cqwq))) { if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { work_done += mlx5e_decompress_cqes_start(rq, cqwq, - budget - work_done); + budget_rem - work_done); continue; } mlx5_cqwq_pop(cqwq); - INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, rq, cqe); - } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); + work_done++; + } + + return work_done; +} + +int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) +{ + struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); + struct mlx5_cqwq *cqwq = &cq->wq; + int work_done; + + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) + return 0; + + if (test_bit(MLX5E_RQ_STATE_MINI_CQE_ENHANCED, &rq->state)) + work_done = mlx5e_rx_cq_process_enhanced_cqe_comp(rq, cqwq, + budget); + else + work_done = mlx5e_rx_cq_process_basic_cqe_comp(rq, cqwq, + budget); + + if (work_done == 0) + return 0; -out: if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state) && rq->hw_gro_data->skb) mlx5e_shampo_flush_skb(rq, NULL, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 4d629e5ddbc7..e4ef1d24a3ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -243,6 +243,23 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq) return cqe; } +static inline +struct mlx5_cqe64 *mlx5_cqwq_get_cqe_enahnced_comp(struct mlx5_cqwq *wq) +{ + u8 sw_validity_iteration_count = mlx5_cqwq_get_wrap_cnt(wq) & 0xff; + u32 ci = mlx5_cqwq_get_ci(wq); + struct mlx5_cqe64 *cqe; + + cqe = mlx5_cqwq_get_wqe(wq, ci); + if (cqe->validity_iteration_count != sw_validity_iteration_count) + return NULL; + + /* ensure cqe content is read after cqe ownership bit/validity byte */ + dma_rmb(); + + return cqe; +} + static inline u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) { return (u32)wq->fbc.sz_m1 + 1; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 1ff91cb79ded..eb3fac30488b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -882,6 +882,12 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } +static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) +{ + /* num_of_mini_cqes is zero based */ + return get_cqe_opcode(cqe) + 1; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; -- cgit v1.2.3 From 92125c3a602454824d70edb1b2abb382811cab4f Mon Sep 17 00:00:00 2001 From: Nick Child Date: Thu, 10 Nov 2022 15:32:17 -0600 Subject: ibmvnic: Add hotpluggable CPU callbacks to reassign affinity hints When CPU's are added and removed, ibmvnic devices will reassign hint values. Introduce a new cpu hotplug state CPUHP_IBMVNIC_DEAD to signal to ibmvnic devices that the CPU has been removed and it is time to reset affinity hint assignments. On the other hand, when CPU's are being added, add a state instance to CPUHP_AP_ONLINE_DYN which will trigger a reassignment of affinity hints once the new CPU's are online. This implementation is based on the virtio_net driver. Signed-off-by: Thomas Falcon Signed-off-by: Dany Madden Signed-off-by: Nick Child Reviewed-by: Rick Lindsley Reviewed-by: Haren Myneni Signed-off-by: David S. Miller --- drivers/net/ethernet/ibm/ibmvnic.c | 89 +++++++++++++++++++++++++++++++++++++- drivers/net/ethernet/ibm/ibmvnic.h | 4 ++ include/linux/cpuhotplug.h | 1 + 3 files changed, 93 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 0c969bdaf94d..2fc0d50dbb86 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -298,6 +298,57 @@ out: } } +static int ibmvnic_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node); + ibmvnic_set_affinity(adapter); + return 0; +} + +static int ibmvnic_cpu_dead(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node_dead); + ibmvnic_set_affinity(adapter); + return 0; +} + +static int ibmvnic_cpu_down_prep(unsigned int cpu, struct hlist_node *node) +{ + struct ibmvnic_adapter *adapter; + + adapter = hlist_entry_safe(node, struct ibmvnic_adapter, node); + ibmvnic_clean_affinity(adapter); + return 0; +} + +static enum cpuhp_state ibmvnic_online; + +static int ibmvnic_cpu_notif_add(struct ibmvnic_adapter *adapter) +{ + int ret; + + ret = cpuhp_state_add_instance_nocalls(ibmvnic_online, &adapter->node); + if (ret) + return ret; + ret = cpuhp_state_add_instance_nocalls(CPUHP_IBMVNIC_DEAD, + &adapter->node_dead); + if (!ret) + return ret; + cpuhp_state_remove_instance_nocalls(ibmvnic_online, &adapter->node); + return ret; +} + +static void ibmvnic_cpu_notif_remove(struct ibmvnic_adapter *adapter) +{ + cpuhp_state_remove_instance_nocalls(ibmvnic_online, &adapter->node); + cpuhp_state_remove_instance_nocalls(CPUHP_IBMVNIC_DEAD, + &adapter->node_dead); +} + static long h_reg_sub_crq(unsigned long unit_address, unsigned long token, unsigned long length, unsigned long *number, unsigned long *irq) @@ -6292,10 +6343,19 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } dev_info(&dev->dev, "ibmvnic registered\n"); + rc = ibmvnic_cpu_notif_add(adapter); + if (rc) { + netdev_err(netdev, "Registering cpu notifier failed\n"); + goto cpu_notif_add_failed; + } + complete(&adapter->probe_done); return 0; +cpu_notif_add_failed: + unregister_netdev(netdev); + ibmvnic_register_fail: device_remove_file(&dev->dev, &dev_attr_failover); @@ -6346,6 +6406,8 @@ static void ibmvnic_remove(struct vio_dev *dev) spin_unlock_irqrestore(&adapter->state_lock, flags); + ibmvnic_cpu_notif_remove(adapter); + flush_work(&adapter->ibmvnic_reset); flush_delayed_work(&adapter->ibmvnic_delayed_reset); @@ -6476,15 +6538,40 @@ static struct vio_driver ibmvnic_driver = { /* module functions */ static int __init ibmvnic_module_init(void) { + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/ibmvnic:online", + ibmvnic_cpu_online, + ibmvnic_cpu_down_prep); + if (ret < 0) + goto out; + ibmvnic_online = ret; + ret = cpuhp_setup_state_multi(CPUHP_IBMVNIC_DEAD, "net/ibmvnic:dead", + NULL, ibmvnic_cpu_dead); + if (ret) + goto err_dead; + + ret = vio_register_driver(&ibmvnic_driver); + if (ret) + goto err_vio_register; + pr_info("%s: %s %s\n", ibmvnic_driver_name, ibmvnic_driver_string, IBMVNIC_DRIVER_VERSION); - return vio_register_driver(&ibmvnic_driver); + return 0; +err_vio_register: + cpuhp_remove_multi_state(CPUHP_IBMVNIC_DEAD); +err_dead: + cpuhp_remove_multi_state(ibmvnic_online); +out: + return ret; } static void __exit ibmvnic_module_exit(void) { vio_unregister_driver(&ibmvnic_driver); + cpuhp_remove_multi_state(CPUHP_IBMVNIC_DEAD); + cpuhp_remove_multi_state(ibmvnic_online); } module_init(ibmvnic_module_init); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 6720fec1ae67..b35c9b6f913b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -984,6 +984,10 @@ struct ibmvnic_adapter { int reset_done_rc; bool wait_for_reset; + /* CPU hotplug instances for online & dead */ + struct hlist_node node; + struct hlist_node node_dead; + /* partner capabilities */ u64 min_tx_queues; u64 min_rx_queues; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index f61447913db9..c8bc85a87b1e 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -69,6 +69,7 @@ enum cpuhp_state { CPUHP_X86_APB_DEAD, CPUHP_X86_MCE_DEAD, CPUHP_VIRT_NET_DEAD, + CPUHP_IBMVNIC_DEAD, CPUHP_SLUB_DEAD, CPUHP_DEBUG_OBJ_DEAD, CPUHP_MM_WRITEBACK_DEAD, -- cgit v1.2.3 From 70ea86a0dfed10e00ee2666dadeb563bab00efea Mon Sep 17 00:00:00 2001 From: Steen Hegelund Date: Fri, 11 Nov 2022 14:05:14 +0100 Subject: net: flow_offload: add support for ARP frame matching This adds a new flow_rule_match_arp function that allows drivers to be able to dissect ARP frames. Signed-off-by: Steen Hegelund Signed-off-by: David S. Miller --- include/net/flow_offload.h | 6 ++++++ net/core/flow_offload.c | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 7a60bc6d72c9..0400a0ac8a29 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -32,6 +32,10 @@ struct flow_match_vlan { struct flow_dissector_key_vlan *key, *mask; }; +struct flow_match_arp { + struct flow_dissector_key_arp *key, *mask; +}; + struct flow_match_ipv4_addrs { struct flow_dissector_key_ipv4_addrs *key, *mask; }; @@ -98,6 +102,8 @@ void flow_rule_match_vlan(const struct flow_rule *rule, struct flow_match_vlan *out); void flow_rule_match_cvlan(const struct flow_rule *rule, struct flow_match_vlan *out); +void flow_rule_match_arp(const struct flow_rule *rule, + struct flow_match_arp *out); void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out); void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index abe423fd5736..acfc1f88ea79 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -97,6 +97,13 @@ void flow_rule_match_cvlan(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_cvlan); +void flow_rule_match_arp(const struct flow_rule *rule, + struct flow_match_arp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ARP, out); +} +EXPORT_SYMBOL(flow_rule_match_arp); + void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, struct flow_match_ipv4_addrs *out) { -- cgit v1.2.3 From 2d577252579b3efb9e934b68948a2edfa9920110 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:23 +0530 Subject: bpf: Remove BPF_MAP_OFF_ARR_MAX In f71b2f64177a ("bpf: Refactor map->off_arr handling"), map->off_arr was refactored to be btf_field_offs. The number of field offsets is equal to maximum possible fields limited by BTF_FIELDS_MAX. Hence, reuse BTF_FIELDS_MAX as spin_lock and timer no longer are to be handled specially for offset sorting, fix the comment, and remove incorrect WARN_ON as its rec->cnt can never exceed this value. The reason to keep separate constant was the it was always more 2 more than total kptrs. This is no longer the case. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 9 ++++----- kernel/bpf/btf.c | 2 +- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 798aec816970..1a66a1df1af1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -165,9 +165,8 @@ struct bpf_map_ops { }; enum { - /* Support at most 8 pointers in a BTF type */ - BTF_FIELDS_MAX = 10, - BPF_MAP_OFF_ARR_MAX = BTF_FIELDS_MAX, + /* Support at most 10 fields in a BTF type */ + BTF_FIELDS_MAX = 10, }; enum btf_field_type { @@ -203,8 +202,8 @@ struct btf_record { struct btf_field_offs { u32 cnt; - u32 field_off[BPF_MAP_OFF_ARR_MAX]; - u8 field_sz[BPF_MAP_OFF_ARR_MAX]; + u32 field_off[BTF_FIELDS_MAX]; + u8 field_sz[BTF_FIELDS_MAX]; }; struct bpf_map { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5579ff3a5b54..12361d7b2498 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3584,7 +3584,7 @@ struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec) u8 *sz; BUILD_BUG_ON(ARRAY_SIZE(foffs->field_off) != ARRAY_SIZE(foffs->field_sz)); - if (IS_ERR_OR_NULL(rec) || WARN_ON_ONCE(rec->cnt > sizeof(foffs->field_off))) + if (IS_ERR_OR_NULL(rec)) return NULL; foffs = kzalloc(sizeof(*foffs), GFP_KERNEL | __GFP_NOWARN); -- cgit v1.2.3 From e5feed0f64f73e167ef70755d3dc2db959d8fd5c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:24 +0530 Subject: bpf: Fix copy_map_value, zero_map_value The current offset needs to also skip over the already copied region in addition to the size of the next field. This case manifests where there are gaps between adjacent special fields. It was observed that for a map value with size 48, having fields at: off: 0, 16, 32 size: 4, 16, 16 The current code does: memcpy(dst + 0, src + 0, 0) memcpy(dst + 4, src + 4, 12) memcpy(dst + 20, src + 20, 12) memcpy(dst + 36, src + 36, 12) With the fix, it is done correctly as: memcpy(dst + 0, src + 0, 0) memcpy(dst + 4, src + 4, 12) memcpy(dst + 32, src + 32, 0) memcpy(dst + 48, src + 48, 0) Fixes: 4d7d7f69f4b1 ("bpf: Adapt copy_map_value for multiple offset case") Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1a66a1df1af1..f08eb2d27de0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -360,7 +360,7 @@ static inline void bpf_obj_memcpy(struct btf_field_offs *foffs, u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); - curr_off += foffs->field_sz[i]; + curr_off += foffs->field_sz[i] + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } @@ -390,7 +390,7 @@ static inline void bpf_obj_memzero(struct btf_field_offs *foffs, void *dst, u32 u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); - curr_off += foffs->field_sz[i]; + curr_off += foffs->field_sz[i] + sz; } memset(dst + curr_off, 0, size - curr_off); } -- cgit v1.2.3 From f0c5941ff5b255413d31425bb327c2aec3625673 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:25 +0530 Subject: bpf: Support bpf_list_head in map values Add the support on the map side to parse, recognize, verify, and build metadata table for a new special field of the type struct bpf_list_head. To parameterize the bpf_list_head for a certain value type and the list_node member it will accept in that value type, we use BTF declaration tags. The definition of bpf_list_head in a map value will be done as follows: struct foo { struct bpf_list_node node; int data; }; struct map_value { struct bpf_list_head head __contains(foo, node); }; Then, the bpf_list_head only allows adding to the list 'head' using the bpf_list_node 'node' for the type struct foo. The 'contains' annotation is a BTF declaration tag composed of four parts, "contains:name:node" where the name is then used to look up the type in the map BTF, with its kind hardcoded to BTF_KIND_STRUCT during the lookup. The node defines name of the member in this type that has the type struct bpf_list_node, which is actually used for linking into the linked list. For now, 'kind' part is hardcoded as struct. This allows building intrusive linked lists in BPF, using container_of to obtain pointer to entry, while being completely type safe from the perspective of the verifier. The verifier knows exactly the type of the nodes, and knows that list helpers return that type at some fixed offset where the bpf_list_node member used for this list exists. The verifier also uses this information to disallow adding types that are not accepted by a certain list. For now, no elements can be added to such lists. Support for that is coming in future patches, hence draining and freeing items is done with a TODO that will be resolved in a future patch. Note that the bpf_list_head_free function moves the list out to a local variable under the lock and releases it, doing the actual draining of the list items outside the lock. While this helps with not holding the lock for too long pessimizing other concurrent list operations, it is also necessary for deadlock prevention: unless every function called in the critical section would be notrace, a fentry/fexit program could attach and call bpf_map_update_elem again on the map, leading to the same lock being acquired if the key matches and lead to a deadlock. While this requires some special effort on part of the BPF programmer to trigger and is highly unlikely to occur in practice, it is always better if we can avoid such a condition. While notrace would prevent this, doing the draining outside the lock has advantages of its own, hence it is used to also fix the deadlock related problem. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 17 +++++ include/uapi/linux/bpf.h | 10 +++ kernel/bpf/btf.c | 145 ++++++++++++++++++++++++++++++++++++++++- kernel/bpf/helpers.c | 32 +++++++++ kernel/bpf/syscall.c | 22 ++++++- kernel/bpf/verifier.c | 7 ++ tools/include/uapi/linux/bpf.h | 10 +++ 7 files changed, 239 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f08eb2d27de0..05f98e9e5c48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -175,6 +175,7 @@ enum btf_field_type { BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, + BPF_LIST_HEAD = (1 << 4), }; struct btf_field_kptr { @@ -184,11 +185,18 @@ struct btf_field_kptr { u32 btf_id; }; +struct btf_field_list_head { + struct btf *btf; + u32 value_btf_id; + u32 node_offset; +}; + struct btf_field { u32 offset; enum btf_field_type type; union { struct btf_field_kptr kptr; + struct btf_field_list_head list_head; }; }; @@ -266,6 +274,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; + case BPF_LIST_HEAD: + return "bpf_list_head"; default: WARN_ON_ONCE(1); return "unknown"; @@ -282,6 +292,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return sizeof(u64); + case BPF_LIST_HEAD: + return sizeof(struct bpf_list_head); default: WARN_ON_ONCE(1); return 0; @@ -298,6 +310,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return __alignof__(u64); + case BPF_LIST_HEAD: + return __alignof__(struct bpf_list_head); default: WARN_ON_ONCE(1); return 0; @@ -403,6 +417,9 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_list_head_free(const struct btf_field *field, void *list_head, + struct bpf_spin_lock *spin_lock); + int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fb4c911d2a03..6580448e9f77 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6888,6 +6888,16 @@ struct bpf_dynptr { __u64 :64; } __attribute__((aligned(8))); +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 12361d7b2498..c0d73d71c539 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3205,9 +3205,15 @@ enum { struct btf_field_info { enum btf_field_type type; u32 off; - struct { - u32 type_id; - } kptr; + union { + struct { + u32 type_id; + } kptr; + struct { + const char *node_name; + u32 value_btf_id; + } list_head; + }; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, @@ -3261,6 +3267,63 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } +static const char *btf_find_decl_tag_value(const struct btf *btf, + const struct btf_type *pt, + int comp_idx, const char *tag_key) +{ + int i; + + for (i = 1; i < btf_nr_types(btf); i++) { + const struct btf_type *t = btf_type_by_id(btf, i); + int len = strlen(tag_key); + + if (!btf_type_is_decl_tag(t)) + continue; + if (pt != btf_type_by_id(btf, t->type) || + btf_type_decl_tag(t)->component_idx != comp_idx) + continue; + if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) + continue; + return __btf_name_by_offset(btf, t->name_off) + len; + } + return NULL; +} + +static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, + const struct btf_type *t, int comp_idx, + u32 off, int sz, struct btf_field_info *info) +{ + const char *value_type; + const char *list_node; + s32 id; + + if (!__btf_type_is_struct(t)) + return BTF_FIELD_IGNORE; + if (t->size != sz) + return BTF_FIELD_IGNORE; + value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); + if (!value_type) + return -EINVAL; + list_node = strstr(value_type, ":"); + if (!list_node) + return -EINVAL; + value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN); + if (!value_type) + return -ENOMEM; + id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); + kfree(value_type); + if (id < 0) + return id; + list_node++; + if (str_is_empty(list_node)) + return -EINVAL; + info->type = BPF_LIST_HEAD; + info->off = off; + info->list_head.value_btf_id = id; + info->list_head.node_name = list_node; + return BTF_FIELD_FOUND; +} + static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, int *align, int *sz) { @@ -3284,6 +3347,12 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_LIST_HEAD) { + if (!strcmp(name, "bpf_list_head")) { + type = BPF_LIST_HEAD; + goto end; + } + } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3339,6 +3408,12 @@ static int btf_find_struct_field(const struct btf *btf, if (ret < 0) return ret; break; + case BPF_LIST_HEAD: + ret = btf_find_list_head(btf, t, member_type, i, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; default: return -EFAULT; } @@ -3393,6 +3468,12 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, if (ret < 0) return ret; break; + case BPF_LIST_HEAD: + ret = btf_find_list_head(btf, var, var_type, -1, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; default: return -EFAULT; } @@ -3491,11 +3572,52 @@ end_btf: return ret; } +static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + const struct btf_type *t, *n = NULL; + const struct btf_member *member; + u32 offset; + int i; + + t = btf_type_by_id(btf, info->list_head.value_btf_id); + /* We've already checked that value_btf_id is a struct type. We + * just need to figure out the offset of the list_node, and + * verify its type. + */ + for_each_member(i, t, member) { + if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off))) + continue; + /* Invalid BTF, two members with same name */ + if (n) + return -EINVAL; + n = btf_type_by_id(btf, member->type); + if (!__btf_type_is_struct(n)) + return -EINVAL; + if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off))) + return -EINVAL; + offset = __btf_member_bit_offset(n, member); + if (offset % 8) + return -EINVAL; + offset /= 8; + if (offset % __alignof__(struct bpf_list_node)) + return -EINVAL; + + field->list_head.btf = (struct btf *)btf; + field->list_head.value_btf_id = info->list_head.value_btf_id; + field->list_head.node_offset = offset; + } + if (!n) + return -ENOENT; + return 0; +} + struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; struct btf_record *rec; + u32 next_off = 0; int ret, i, cnt; ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); @@ -3517,6 +3639,11 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type ret = -EFAULT; goto end; } + if (info_arr[i].off < next_off) { + ret = -EEXIST; + goto end; + } + next_off = info_arr[i].off + btf_field_type_size(info_arr[i].type); rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; @@ -3539,12 +3666,24 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_LIST_HEAD: + ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; default: ret = -EFAULT; goto end; } rec->cnt++; } + + /* bpf_list_head requires bpf_spin_lock */ + if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) { + ret = -EINVAL; + goto end; + } + return rec; end: btf_record_free(rec); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 283f55bbeb70..7bc71995f17c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1706,6 +1706,38 @@ bpf_base_func_proto(enum bpf_func_id func_id) } } +void bpf_list_head_free(const struct btf_field *field, void *list_head, + struct bpf_spin_lock *spin_lock) +{ + struct list_head *head = list_head, *orig_head = list_head; + + BUILD_BUG_ON(sizeof(struct list_head) > sizeof(struct bpf_list_head)); + BUILD_BUG_ON(__alignof__(struct list_head) > __alignof__(struct bpf_list_head)); + + /* Do the actual list draining outside the lock to not hold the lock for + * too long, and also prevent deadlocks if tracing programs end up + * executing on entry/exit of functions called inside the critical + * section, and end up doing map ops that call bpf_list_head_free for + * the same map value again. + */ + __bpf_spin_lock_irqsave(spin_lock); + if (!head->next || list_empty(head)) + goto unlock; + head = head->next; +unlock: + INIT_LIST_HEAD(orig_head); + __bpf_spin_unlock_irqrestore(spin_lock); + + while (head != orig_head) { + void *obj = head; + + obj -= field->list_head.node_offset; + head = head->next; + /* TODO: Rework later */ + kfree(obj); + } +} + BTF_SET8_START(tracing_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 85532d301124..fdbae52f463f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -536,6 +536,9 @@ void btf_record_free(struct btf_record *rec) module_put(rec->fields[i].kptr.module); btf_put(rec->fields[i].kptr.btf); break; + case BPF_LIST_HEAD: + /* Nothing to release for bpf_list_head */ + break; default: WARN_ON_ONCE(1); continue; @@ -578,6 +581,9 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) goto free; } break; + case BPF_LIST_HEAD: + /* Nothing to acquire for bpf_list_head */ + break; default: ret = -EFAULT; WARN_ON_ONCE(1); @@ -637,6 +643,11 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) case BPF_KPTR_REF: field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); break; + case BPF_LIST_HEAD: + if (WARN_ON_ONCE(rec->spin_lock_off < 0)) + continue; + bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); + break; default: WARN_ON_ONCE(1); continue; @@ -965,7 +976,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; - map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR, + map->record = btf_parse_fields(btf, value_type, + BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1012,6 +1024,14 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, goto free_map_tab; } break; + case BPF_LIST_HEAD: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 07c0259dfc1a..a50018e2d4a0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12814,6 +12814,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); + if (btf_record_has_field(map->record, BPF_LIST_HEAD)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_list_head yet\n"); + return -EINVAL; + } + } + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fb4c911d2a03..6580448e9f77 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6888,6 +6888,16 @@ struct bpf_dynptr { __u64 :64; } __attribute__((aligned(8))); +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. -- cgit v1.2.3 From 2de2669b4e52b2ae2f118bfc310004f50b47f0f5 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:26 +0530 Subject: bpf: Rename RET_PTR_TO_ALLOC_MEM Currently, the verifier has two return types, RET_PTR_TO_ALLOC_MEM, and RET_PTR_TO_ALLOC_MEM_OR_NULL, however the former is confusingly named to imply that it carries MEM_ALLOC, while only the latter does. This causes confusion during code review leading to conclusions like that the return value of RET_PTR_TO_DYNPTR_MEM_OR_NULL (which is RET_PTR_TO_ALLOC_MEM | PTR_MAYBE_NULL) may be consumable by bpf_ringbuf_{submit,commit}. Rename it to make it clear MEM_ALLOC needs to be tacked on top of RET_PTR_TO_MEM. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 6 +++--- kernel/bpf/verifier.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 05f98e9e5c48..2fe3ec620d54 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -607,7 +607,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ - RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */ + RET_PTR_TO_MEM, /* returns a pointer to memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, @@ -617,8 +617,8 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, - RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, - RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_MEM, + RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a50018e2d4a0..c88da7e3ca74 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7630,7 +7630,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; break; - case RET_PTR_TO_ALLOC_MEM: + case RET_PTR_TO_MEM: mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; -- cgit v1.2.3 From 894f2a8b1673a355a1a7507a4dfa6a3c836d07c1 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:27 +0530 Subject: bpf: Rename MEM_ALLOC to MEM_RINGBUF Currently, verifier uses MEM_ALLOC type tag to specially tag memory returned from bpf_ringbuf_reserve helper. However, this is currently only used for this purpose and there is an implicit assumption that it only refers to ringbuf memory (e.g. the check for ARG_PTR_TO_ALLOC_MEM in check_func_arg_reg_off). Hence, rename MEM_ALLOC to MEM_RINGBUF to indicate this special relationship and instead open the use of MEM_ALLOC for more generic allocations made for user types. Also, since ARG_PTR_TO_ALLOC_MEM_OR_NULL is unused, simply drop it. Finally, update selftests using 'alloc_' verifier string to 'ringbuf_'. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 ++++------- kernel/bpf/ringbuf.c | 6 +++--- kernel/bpf/verifier.c | 14 +++++++------- tools/testing/selftests/bpf/prog_tests/dynptr.c | 2 +- tools/testing/selftests/bpf/verifier/ringbuf.c | 2 +- tools/testing/selftests/bpf/verifier/spill_fill.c | 2 +- 6 files changed, 17 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2fe3ec620d54..afc1c51b59ff 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -488,10 +488,8 @@ enum bpf_type_flag { */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), - /* MEM was "allocated" from a different helper, and cannot be mixed - * with regular non-MEM_ALLOC'ed MEM types. - */ - MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), + /* MEM points to BPF ring buffer reservation. */ + MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS), /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), @@ -565,7 +563,7 @@ enum bpf_arg_type { ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ - ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ + ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ @@ -582,7 +580,6 @@ enum bpf_arg_type { ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, - ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* pointer to memory does not need to be initialized, helper function must fill @@ -617,7 +614,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, - RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_MEM, + RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 9e832acf4692..80f4b4d88aaf 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -447,7 +447,7 @@ BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags) const struct bpf_func_proto bpf_ringbuf_reserve_proto = { .func = bpf_ringbuf_reserve, - .ret_type = RET_PTR_TO_ALLOC_MEM_OR_NULL, + .ret_type = RET_PTR_TO_RINGBUF_MEM_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, @@ -490,7 +490,7 @@ BPF_CALL_2(bpf_ringbuf_submit, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_submit_proto = { .func = bpf_ringbuf_submit, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; @@ -503,7 +503,7 @@ BPF_CALL_2(bpf_ringbuf_discard, void *, sample, u64, flags) const struct bpf_func_proto bpf_ringbuf_discard_proto = { .func = bpf_ringbuf_discard, .ret_type = RET_VOID, - .arg1_type = ARG_PTR_TO_ALLOC_MEM | OBJ_RELEASE, + .arg1_type = ARG_PTR_TO_RINGBUF_MEM | OBJ_RELEASE, .arg2_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c88da7e3ca74..c588e5483540 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -577,8 +577,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env, if (type & MEM_RDONLY) strncpy(prefix, "rdonly_", 32); - if (type & MEM_ALLOC) - strncpy(prefix, "alloc_", 32); + if (type & MEM_RINGBUF) + strncpy(prefix, "ringbuf_", 32); if (type & MEM_USER) strncpy(prefix, "user_", 32); if (type & MEM_PERCPU) @@ -5785,7 +5785,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, - PTR_TO_MEM | MEM_ALLOC, + PTR_TO_MEM | MEM_RINGBUF, PTR_TO_BUF, }, }; @@ -5803,7 +5803,7 @@ static const struct bpf_reg_types int_ptr_types = { static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; -static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } }; +static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5836,7 +5836,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, - [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, + [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, @@ -5957,14 +5957,14 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_MEM | MEM_RDONLY: - case PTR_TO_MEM | MEM_ALLOC: + case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case SCALAR_VALUE: /* Some of the argument types nevertheless require a * zero register offset. */ - if (base_type(arg_type) != ARG_PTR_TO_ALLOC_MEM) + if (base_type(arg_type) != ARG_PTR_TO_RINGBUF_MEM) return 0; break; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index 8fc4e6c02bfd..b0c06f821cb8 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -17,7 +17,7 @@ static struct { {"ringbuf_missing_release2", "Unreleased reference id=2"}, {"ringbuf_missing_release_callback", "Unreleased reference id"}, {"use_after_invalid", "Expected an initialized dynptr as arg #3"}, - {"ringbuf_invalid_api", "type=mem expected=alloc_mem"}, + {"ringbuf_invalid_api", "type=mem expected=ringbuf_mem"}, {"add_dynptr_to_map1", "invalid indirect read from stack"}, {"add_dynptr_to_map2", "invalid indirect read from stack"}, {"data_slice_out_of_bounds_ringbuf", "value is outside of the allowed memory range"}, diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c index b64d33e4833c..84838feba47f 100644 --- a/tools/testing/selftests/bpf/verifier/ringbuf.c +++ b/tools/testing/selftests/bpf/verifier/ringbuf.c @@ -28,7 +28,7 @@ }, .fixup_map_ringbuf = { 1 }, .result = REJECT, - .errstr = "dereference of modified alloc_mem ptr R1", + .errstr = "dereference of modified ringbuf_mem ptr R1", }, { "ringbuf: invalid reservation offset 2", diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index e23f07175e1b..9bb302dade23 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -84,7 +84,7 @@ }, .fixup_map_ringbuf = { 1 }, .result = REJECT, - .errstr = "R0 pointer arithmetic on alloc_mem_or_null prohibited", + .errstr = "R0 pointer arithmetic on ringbuf_mem_or_null prohibited", }, { "check corrupted spill/fill", -- cgit v1.2.3 From 6728aea7216c0c06c98e2e58d753a5e8b2ae1c6f Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:28 +0530 Subject: bpf: Refactor btf_struct_access Instead of having to pass multiple arguments that describe the register, pass the bpf_reg_state into the btf_struct_access callback. Currently, all call sites simply reuse the btf and btf_id of the reg they want to check the access of. The only exception to this pattern is the callsite in check_ptr_to_map_access, hence for that case create a dummy reg to simulate PTR_TO_BTF_ID access. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 17 ++++++++--------- include/linux/filter.h | 8 ++++---- kernel/bpf/btf.c | 11 +++++++---- kernel/bpf/verifier.c | 12 +++++++----- net/bpf/bpf_dummy_struct_ops.c | 14 +++++++------- net/core/filter.c | 34 ++++++++++++++-------------------- net/ipv4/bpf_tcp_ca.c | 13 ++++++------- net/netfilter/nf_conntrack_bpf.c | 17 +++++++---------- 8 files changed, 60 insertions(+), 66 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index afc1c51b59ff..49f9d2bec401 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -771,6 +771,7 @@ struct bpf_prog_ops { union bpf_attr __user *uattr); }; +struct bpf_reg_state; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * @@ -792,9 +793,8 @@ struct bpf_verifier_ops { struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag); }; @@ -2080,9 +2080,9 @@ static inline bool bpf_tracing_btf_ctx_access(int off, int size, return btf_ctx_access(off, size, type, prog, info); } -int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, +int btf_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, @@ -2333,9 +2333,8 @@ static inline struct bpf_prog *bpf_prog_by_id(u32 id) } static inline int btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag) { return -EACCES; diff --git a/include/linux/filter.h b/include/linux/filter.h index efc42a6e3aed..787d35dbf5b0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -568,10 +568,10 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; -extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, u32 *next_btf_id, - enum bpf_type_flag *flag); +extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c0d73d71c539..875355ff3718 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6017,15 +6017,18 @@ error: return -EINVAL; } -int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype __maybe_unused, +int btf_struct_access(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype __maybe_unused, u32 *next_btf_id, enum bpf_type_flag *flag) { + const struct btf *btf = reg->btf; enum bpf_type_flag tmp_flag = 0; + const struct btf_type *t; + u32 id = reg->btf_id; int err; - u32 id; + t = btf_type_by_id(btf, id); do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c588e5483540..5e74f460dfd0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4688,16 +4688,14 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, } if (env->ops->btf_struct_access) { - ret = env->ops->btf_struct_access(&env->log, reg->btf, t, - off, size, atype, &btf_id, &flag); + ret = env->ops->btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); return -EACCES; } - ret = btf_struct_access(&env->log, reg->btf, t, off, size, - atype, &btf_id, &flag); + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } if (ret < 0) @@ -4723,6 +4721,7 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, { struct bpf_reg_state *reg = regs + regno; struct bpf_map *map = reg->map_ptr; + struct bpf_reg_state map_reg; enum bpf_type_flag flag = 0; const struct btf_type *t; const char *tname; @@ -4761,7 +4760,10 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, return -EACCES; } - ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id, &flag); + /* Simulate access to a PTR_TO_BTF_ID */ + memset(&map_reg, 0, sizeof(map_reg)); + mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID, btf_vmlinux, *map->ops->map_btf_id, 0); + ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag); if (ret < 0) return ret; diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index e78dadfc5829..2d434c1f4617 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -156,29 +156,29 @@ static bool bpf_dummy_ops_is_valid_access(int off, int size, } static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag) { const struct btf_type *state; + const struct btf_type *t; s32 type_id; int err; - type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state", + type_id = btf_find_by_name_kind(reg->btf, "bpf_dummy_ops_state", BTF_KIND_STRUCT); if (type_id < 0) return -EINVAL; - state = btf_type_by_id(btf, type_id); + t = btf_type_by_id(reg->btf, reg->btf_id); + state = btf_type_by_id(reg->btf, type_id); if (t != state) { bpf_log(log, "only access to bpf_dummy_ops_state is supported\n"); return -EACCES; } - err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + err = btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); if (err < 0) return err; diff --git a/net/core/filter.c b/net/core/filter.c index 6dd2baf5eeb2..37fad5a9b752 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8651,28 +8651,25 @@ static bool tc_cls_act_is_valid_access(int off, int size, DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); -int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, int off, int size, - enum bpf_access_type atype, u32 *next_btf_id, - enum bpf_type_flag *flag); +int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { int ret = -EACCES; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_unlock(&nf_conn_btf_access_lock); return ret; @@ -8738,21 +8735,18 @@ void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { int ret = -EACCES; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) - ret = nfct_btf_struct_access(log, btf, t, off, size, atype, next_btf_id, flag); + ret = nfct_btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); mutex_unlock(&nf_conn_btf_access_lock); return ret; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 6da16ae6a962..d15c91de995f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -69,18 +69,17 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { + const struct btf_type *t; size_t end; if (atype == BPF_READ) - return btf_struct_access(log, btf, t, off, size, atype, next_btf_id, - flag); + return btf_struct_access(log, reg, off, size, atype, next_btf_id, flag); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); return -EACCES; diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 8639e7efd0e2..24002bc61e07 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -191,19 +191,16 @@ BTF_ID(struct, nf_conn___init) /* Check writes into `struct nf_conn` */ static int _nf_conntrack_btf_struct_access(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int off, - int size, enum bpf_access_type atype, - u32 *next_btf_id, - enum bpf_type_flag *flag) + const struct bpf_reg_state *reg, + int off, int size, enum bpf_access_type atype, + u32 *next_btf_id, enum bpf_type_flag *flag) { - const struct btf_type *ncit; - const struct btf_type *nct; + const struct btf_type *ncit, *nct, *t; size_t end; - ncit = btf_type_by_id(btf, btf_nf_conn_ids[1]); - nct = btf_type_by_id(btf, btf_nf_conn_ids[0]); - + ncit = btf_type_by_id(reg->btf, btf_nf_conn_ids[1]); + nct = btf_type_by_id(reg->btf, btf_nf_conn_ids[0]); + t = btf_type_by_id(reg->btf, reg->btf_id); if (t != nct && t != ncit) { bpf_log(log, "only read is supported\n"); return -EACCES; -- cgit v1.2.3 From 7d34aa3e03b6a56306296bd98b26c6a1710cd57b Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 14 Oct 2022 23:45:58 +0200 Subject: netfilter: nf_tables: Extend nft_expr_ops::dump callback parameters Add a 'reset' flag just like with nft_object_ops::dump. This will be useful to reset "anonymous stateful objects", e.g. simple rule counters. No functional change intended. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 3 ++- include/net/netfilter/nft_fib.h | 2 +- include/net/netfilter/nft_meta.h | 4 ++-- include/net/netfilter/nft_reject.h | 3 ++- net/ipv4/netfilter/nft_dup_ipv4.c | 3 ++- net/ipv6/netfilter/nft_dup_ipv6.c | 3 ++- net/netfilter/nf_tables_api.c | 2 +- net/netfilter/nft_bitwise.c | 6 ++++-- net/netfilter/nft_byteorder.c | 3 ++- net/netfilter/nft_cmp.c | 9 ++++++--- net/netfilter/nft_compat.c | 9 ++++++--- net/netfilter/nft_connlimit.c | 3 ++- net/netfilter/nft_counter.c | 3 ++- net/netfilter/nft_ct.c | 6 ++++-- net/netfilter/nft_dup_netdev.c | 3 ++- net/netfilter/nft_dynset.c | 3 ++- net/netfilter/nft_exthdr.c | 9 ++++++--- net/netfilter/nft_fib.c | 2 +- net/netfilter/nft_flow_offload.c | 3 ++- net/netfilter/nft_fwd_netdev.c | 6 ++++-- net/netfilter/nft_hash.c | 4 ++-- net/netfilter/nft_immediate.c | 3 ++- net/netfilter/nft_inner.c | 3 ++- net/netfilter/nft_last.c | 3 ++- net/netfilter/nft_limit.c | 5 +++-- net/netfilter/nft_log.c | 3 ++- net/netfilter/nft_lookup.c | 3 ++- net/netfilter/nft_masq.c | 3 ++- net/netfilter/nft_meta.c | 5 +++-- net/netfilter/nft_nat.c | 3 ++- net/netfilter/nft_numgen.c | 6 ++++-- net/netfilter/nft_objref.c | 6 ++++-- net/netfilter/nft_osf.c | 3 ++- net/netfilter/nft_payload.c | 6 ++++-- net/netfilter/nft_queue.c | 6 ++++-- net/netfilter/nft_quota.c | 3 ++- net/netfilter/nft_range.c | 3 ++- net/netfilter/nft_redir.c | 3 ++- net/netfilter/nft_reject.c | 3 ++- net/netfilter/nft_rt.c | 2 +- net/netfilter/nft_socket.c | 2 +- net/netfilter/nft_synproxy.c | 3 ++- net/netfilter/nft_tproxy.c | 2 +- net/netfilter/nft_tunnel.c | 2 +- net/netfilter/nft_xfrm.c | 2 +- 45 files changed, 110 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 38e2b396e38a..c557a57fb0f1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -927,7 +927,8 @@ struct nft_expr_ops { void (*destroy_clone)(const struct nft_ctx *ctx, const struct nft_expr *expr); int (*dump)(struct sk_buff *skb, - const struct nft_expr *expr); + const struct nft_expr *expr, + bool reset); int (*validate)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data); diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index eed099eae672..167640b843ef 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -18,7 +18,7 @@ nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } -int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h index f3a5285a511c..ba1238f12a48 100644 --- a/include/net/netfilter/nft_meta.h +++ b/include/net/netfilter/nft_meta.h @@ -24,10 +24,10 @@ int nft_meta_set_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]); int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr); + const struct nft_expr *expr, bool reset); int nft_meta_set_dump(struct sk_buff *skb, - const struct nft_expr *expr); + const struct nft_expr *expr, bool reset); void nft_meta_get_eval(const struct nft_expr *expr, struct nft_regs *regs, diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h index 56b123a42220..6d9ba62efd75 100644 --- a/include/net/netfilter/nft_reject.h +++ b/include/net/netfilter/nft_reject.h @@ -22,7 +22,8 @@ int nft_reject_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); -int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr); +int nft_reject_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset); int nft_reject_icmp_code(u8 code); int nft_reject_icmpv6_code(u8 code); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index 0bcd6aee6000..a522c3a3be52 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -52,7 +52,8 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, return err; } -static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_ipv4_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 70a405b4006f..c82f3fdd4a65 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -50,7 +50,8 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, return err; } -static int nft_dup_ipv6_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_ipv6_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_ipv6 *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 62da204eed41..741a0e386406 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2769,7 +2769,7 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; - if (expr->ops->dump(skb, expr) < 0) + if (expr->ops->dump(skb, expr, false) < 0) goto nla_put_failure; nla_nest_end(skb, data); } diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index e6e402b247d0..84eae7cabc67 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -232,7 +232,8 @@ static int nft_bitwise_dump_shift(struct sk_buff *skb, return 0; } -static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_bitwise_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_bitwise *priv = nft_expr_priv(expr); int err = 0; @@ -393,7 +394,8 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, } static int -nft_bitwise_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +nft_bitwise_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); struct nft_data data; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index f952a80275a8..b66647a5a171 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -148,7 +148,8 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, priv->len); } -static int nft_byteorder_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_byteorder_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_byteorder *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 963cf831799c..6eb21a4f5698 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -92,7 +92,8 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return 0; } -static int nft_cmp_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); @@ -253,7 +254,8 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx, return __nft_cmp_offload(ctx, flow, &cmp); } -static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; @@ -347,7 +349,8 @@ static int nft_cmp16_fast_offload(struct nft_offload_ctx *ctx, return __nft_cmp_offload(ctx, flow, &cmp); } -static int nft_cmp16_fast_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_cmp16_fast_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index c16172427622..5284cd2ad532 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -324,7 +324,8 @@ static int nft_extension_dump_info(struct sk_buff *skb, int attr, return 0; } -static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_target_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); @@ -572,12 +573,14 @@ nla_put_failure: return -1; } -static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_match_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { return __nft_match_dump(skb, expr, nft_expr_priv(expr)); } -static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e) +static int nft_match_large_dump(struct sk_buff *skb, + const struct nft_expr *e, bool reset) { struct nft_xt_match_priv *priv = nft_expr_priv(e); diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index d657f999a11b..de9d1980df69 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -185,7 +185,8 @@ static void nft_connlimit_eval(const struct nft_expr *expr, nft_connlimit_do_eval(priv, regs, pkt, NULL); } -static int nft_connlimit_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_connlimit_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_connlimit *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index f4d3573e8782..06482fb9c145 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -201,7 +201,8 @@ void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, nft_counter_do_eval(priv, regs, pkt); } -static int nft_counter_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_counter_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..a0696d7ea10c 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -641,7 +641,8 @@ static void nft_ct_set_destroy(const struct nft_ctx *ctx, nf_ct_netns_put(ctx->net, ctx->family); } -static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ct_get_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ct *priv = nft_expr_priv(expr); @@ -703,7 +704,8 @@ static bool nft_ct_get_reduce(struct nft_regs_track *track, return nft_expr_reduce_bitwise(track, expr); } -static int nft_ct_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ct_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ct *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index 63507402716d..e5739a59ebf1 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -44,7 +44,8 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, sizeof(int)); } -static int nft_dup_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dup_netdev_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_dup_netdev *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 6983e6ddeef9..01c61e090639 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -357,7 +357,8 @@ static void nft_dynset_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_dynset_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_dynset *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index a67ea9c3ae57..ed929d0d37ce 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -576,7 +576,8 @@ nla_put_failure: return -1; } -static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); @@ -586,7 +587,8 @@ static int nft_exthdr_dump(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump_set(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); @@ -596,7 +598,8 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static int nft_exthdr_dump_strip(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_exthdr_dump_strip(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_exthdr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 1f12d7ade606..6e049fd48760 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -118,7 +118,7 @@ int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, } EXPORT_SYMBOL_GPL(nft_fib_init); -int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_fib *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a25c88bc8b75..e860d8fe0e5e 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -433,7 +433,8 @@ static void nft_flow_offload_destroy(const struct nft_ctx *ctx, nf_ct_netns_put(ctx->net, ctx->family); } -static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_flow_offload_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 7c5876dc9ff2..7b9d4d1bd17c 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -56,7 +56,8 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, sizeof(int)); } -static int nft_fwd_netdev_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_fwd_netdev_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_fwd_netdev *priv = nft_expr_priv(expr); @@ -186,7 +187,8 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, addr_len); } -static int nft_fwd_neigh_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_fwd_neigh_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_fwd_neigh *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index e5631e88b285..ee8d487b69c0 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -139,7 +139,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx, } static int nft_jhash_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_jhash *priv = nft_expr_priv(expr); @@ -176,7 +176,7 @@ static bool nft_jhash_reduce(struct nft_regs_track *track, } static int nft_symhash_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_symhash *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 5f28b21abc7d..c9d2f7c29f53 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -147,7 +147,8 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, } } -static int nft_immediate_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_immediate_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 809f0d0787ec..6d96b826db4e 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -347,7 +347,8 @@ static int nft_inner_init(const struct nft_ctx *ctx, return 0; } -static int nft_inner_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_inner_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_inner *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index bb15a55dad5c..7f2bda6641bd 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -65,7 +65,8 @@ static void nft_last_eval(const struct nft_expr *expr, WRITE_ONCE(last->set, 1); } -static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_last_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_last_priv *priv = nft_expr_priv(expr); struct nft_last *last = priv->last; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 981addb2d051..145dc62c6247 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -193,7 +193,8 @@ static int nft_limit_pkts_init(const struct nft_ctx *ctx, return 0; } -static int nft_limit_pkts_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_limit_pkts_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_limit_priv_pkts *priv = nft_expr_priv(expr); @@ -251,7 +252,7 @@ static int nft_limit_bytes_init(const struct nft_ctx *ctx, } static int nft_limit_bytes_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_limit_priv *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 0e13c003f0c1..5defe6e4fd98 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -241,7 +241,8 @@ static void nft_log_destroy(const struct nft_ctx *ctx, nf_logger_put(ctx->family, li->type); } -static int nft_log_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_log_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_log *priv = nft_expr_priv(expr); const struct nf_loginfo *li = &priv->loginfo; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index dfae12759c7c..cae5a6724163 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -178,7 +178,8 @@ static void nft_lookup_destroy(const struct nft_ctx *ctx, nf_tables_destroy_set(ctx, priv->set); } -static int nft_lookup_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_lookup_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_lookup *priv = nft_expr_priv(expr); u32 flags = priv->invert ? NFT_LOOKUP_F_INV : 0; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 2a0adc497bbb..e55e455275c4 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -73,7 +73,8 @@ static int nft_masq_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -static int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_masq_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_masq *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 8c39adeebb5c..e384e0de7a54 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -669,7 +669,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, EXPORT_SYMBOL_GPL(nft_meta_set_init); int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -684,7 +684,8 @@ nla_put_failure: } EXPORT_SYMBOL_GPL(nft_meta_get_dump); -int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_meta_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_meta *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index e5fd6995e4bf..047999150390 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -255,7 +255,8 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return nf_ct_netns_get(ctx->net, family); } -static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_nat_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_nat *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 45d3dc9e96f2..7d29db7c2ac0 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -112,7 +112,8 @@ nla_put_failure: return -1; } -static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ng_inc_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ng_inc *priv = nft_expr_priv(expr); @@ -168,7 +169,8 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NULL, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_ng_random_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_ng_random *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 74e0eea4abac..7b01aa2ef653 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -47,7 +47,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return 0; } -static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_objref_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_object *obj = nft_objref_priv(expr); @@ -155,7 +156,8 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, return 0; } -static int nft_objref_map_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_objref_map_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_objref_map *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index adacf95b6e2b..70820c66b591 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -92,7 +92,8 @@ static int nft_osf_init(const struct nft_ctx *ctx, return 0; } -static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_osf_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_osf *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 53e64d8aa01f..336ac668cae3 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -231,7 +231,8 @@ static int nft_payload_init(const struct nft_ctx *ctx, priv->len); } -static int nft_payload_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_payload_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_payload *priv = nft_expr_priv(expr); @@ -919,7 +920,8 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, priv->len); } -static int nft_payload_set_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_payload_set_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_payload_set *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index da29e92c03e2..b2b8127c8d43 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -152,7 +152,8 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, return 0; } -static int nft_queue_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_queue_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_queue *priv = nft_expr_priv(expr); @@ -168,7 +169,8 @@ nla_put_failure: } static int -nft_queue_sreg_dump(struct sk_buff *skb, const struct nft_expr *expr) +nft_queue_sreg_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_queue *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index e6b0df68feea..b1a1217bca4c 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -217,7 +217,8 @@ static int nft_quota_init(const struct nft_ctx *ctx, return nft_quota_do_init(tb, priv); } -static int nft_quota_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_quota_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_quota *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 832f0d725a9e..0566d6aaf1e5 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -111,7 +111,8 @@ err1: return err; } -static int nft_range_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_range_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_range_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 5086adfe731c..5f7739987559 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -75,7 +75,8 @@ static int nft_redir_init(const struct nft_ctx *ctx, return nf_ct_netns_get(ctx->net, ctx->family); } -static int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_redir_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_redir *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 927ff8459bd9..f2addc844dd2 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -69,7 +69,8 @@ int nft_reject_init(const struct nft_ctx *ctx, } EXPORT_SYMBOL_GPL(nft_reject_init); -int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_reject_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { const struct nft_reject *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 71931ec91721..5990fdd7b3cc 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -146,7 +146,7 @@ static int nft_rt_get_init(const struct nft_ctx *ctx, } static int nft_rt_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_rt *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 49a5348a6a14..85f8df87efda 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -199,7 +199,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, } static int nft_socket_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_socket *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 6cf9a04fbfe2..13da882669a4 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -272,7 +272,8 @@ static void nft_synproxy_destroy(const struct nft_ctx *ctx, nft_synproxy_do_destroy(ctx); } -static int nft_synproxy_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_synproxy_dump(struct sk_buff *skb, + const struct nft_expr *expr, bool reset) { struct nft_synproxy *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 62da25ad264b..ea83f661417e 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -294,7 +294,7 @@ static void nft_tproxy_destroy(const struct nft_ctx *ctx, } static int nft_tproxy_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_tproxy *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 983ade4be3b3..b059aa541798 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -108,7 +108,7 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, } static int nft_tunnel_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_tunnel *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 1c5343c936a8..c88fd078a9ae 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -212,7 +212,7 @@ static void nft_xfrm_get_eval(const struct nft_expr *expr, } static int nft_xfrm_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { const struct nft_xfrm *priv = nft_expr_priv(expr); -- cgit v1.2.3 From 8daa8fde3fc3f069ff0b5c87079a5c1df7743113 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 14 Oct 2022 23:45:59 +0200 Subject: netfilter: nf_tables: Introduce NFT_MSG_GETRULE_RESET Analogous to NFT_MSG_GETOBJ_RESET, but for rules: Reset stateful expressions like counters or quotas. The latter two are the only consumers, adjust their 'dump' callbacks to respect the parameter introduced earlier. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 49 +++++++++++++++++++++----------- net/netfilter/nft_counter.c | 2 +- net/netfilter/nft_dynset.c | 4 +-- net/netfilter/nft_inner.c | 2 +- net/netfilter/nft_quota.c | 2 +- 7 files changed, 41 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c557a57fb0f1..e69ce23566ea 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -383,7 +383,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_expr *expr); + const struct nft_expr *expr, bool reset); bool nft_expr_reduce_bitwise(struct nft_regs_track *track, const struct nft_expr *expr); diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e4b739d57480..cfa844da1ce6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -97,6 +97,7 @@ enum nft_verdicts { * @NFT_MSG_NEWFLOWTABLE: add new flow table (enum nft_flowtable_attributes) * @NFT_MSG_GETFLOWTABLE: get flow table (enum nft_flowtable_attributes) * @NFT_MSG_DELFLOWTABLE: delete flow table (enum nft_flowtable_attributes) + * @NFT_MSG_GETRULE_RESET: get rules and reset stateful expressions (enum nft_obj_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -124,6 +125,7 @@ enum nf_tables_msg_types { NFT_MSG_NEWFLOWTABLE, NFT_MSG_GETFLOWTABLE, NFT_MSG_DELFLOWTABLE, + NFT_MSG_GETRULE_RESET, NFT_MSG_MAX, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 741a0e386406..80e613405f6f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2759,7 +2759,7 @@ static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { }; static int nf_tables_fill_expr_info(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name)) goto nla_put_failure; @@ -2769,7 +2769,7 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; - if (expr->ops->dump(skb, expr, false) < 0) + if (expr->ops->dump(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, data); } @@ -2781,14 +2781,14 @@ nla_put_failure: }; int nft_expr_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; - if (nf_tables_fill_expr_info(skb, expr) < 0) + if (nf_tables_fill_expr_info(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -3034,7 +3034,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, u64 handle) + const struct nft_rule *rule, u64 handle, + bool reset) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; @@ -3067,7 +3068,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, list); @@ -3118,7 +3119,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, - ctx->chain, rule, handle); + ctx->chain, rule, handle, false); if (err < 0) { kfree_skb(skb); goto err; @@ -3139,7 +3140,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, unsigned int *idx, struct netlink_callback *cb, const struct nft_table *table, - const struct nft_chain *chain) + const struct nft_chain *chain, + bool reset) { struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; @@ -3166,7 +3168,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle) < 0) + table, chain, rule, handle, reset) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3189,6 +3191,10 @@ static int nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + bool reset = false; + + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; rcu_read_lock(); nft_net = nft_pernet(net); @@ -3213,14 +3219,15 @@ static int nf_tables_dump_rules(struct sk_buff *skb, if (!nft_is_active(net, chain)) continue; __nf_tables_dump_rules(skb, &idx, - cb, table, chain); + cb, table, chain, reset); break; } goto done; } list_for_each_entry_rcu(chain, &table->chains, list) { - if (__nf_tables_dump_rules(skb, &idx, cb, table, chain)) + if (__nf_tables_dump_rules(skb, &idx, + cb, table, chain, reset)) goto done; } @@ -3291,6 +3298,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; + bool reset = false; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { @@ -3327,9 +3335,12 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, if (!skb2) return -ENOMEM; + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; + err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, 0); + family, table, chain, rule, 0, reset); if (err < 0) goto err_fill_rule_info; @@ -4104,7 +4115,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); - if (nf_tables_fill_expr_info(skb, set->exprs[0]) < 0) + if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) goto nla_put_failure; nla_nest_end(skb, nest); @@ -4115,7 +4126,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, for (i = 0; i < set->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - set->exprs[i]) < 0) + set->exprs[i], false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -4946,7 +4957,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); - if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr) < 0) + if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, false) < 0) return -1; return 0; @@ -4957,7 +4968,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -8311,6 +8322,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, + [NFT_MSG_GETRULE_RESET] = { + .call = nf_tables_getrule, + .type = NFNL_CB_RCU, + .attr_count = NFTA_RULE_MAX, + .policy = nft_rule_policy, + }, [NFT_MSG_DELRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 06482fb9c145..dccc68a5135a 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -206,7 +206,7 @@ static int nft_counter_dump(struct sk_buff *skb, { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - return nft_counter_do_dump(skb, priv, false); + return nft_counter_do_dump(skb, priv, reset); } static int nft_counter_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 01c61e090639..274579b1696e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -380,7 +380,7 @@ static int nft_dynset_dump(struct sk_buff *skb, if (priv->set->num_exprs == 0) { if (priv->num_exprs == 1) { if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, - priv->expr_array[0])) + priv->expr_array[0], reset)) goto nla_put_failure; } else if (priv->num_exprs > 1) { struct nlattr *nest; @@ -391,7 +391,7 @@ static int nft_dynset_dump(struct sk_buff *skb, for (i = 0; i < priv->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - priv->expr_array[i])) + priv->expr_array[i], reset)) goto nla_put_failure; } nla_nest_end(skb, nest); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 6d96b826db4e..28e2873ba24e 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -359,7 +359,7 @@ static int nft_inner_dump(struct sk_buff *skb, goto nla_put_failure; if (nft_expr_dump(skb, NFTA_INNER_EXPR, - (struct nft_expr *)&priv->expr) < 0) + (struct nft_expr *)&priv->expr, reset) < 0) goto nla_put_failure; return 0; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index b1a1217bca4c..123578e28917 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -222,7 +222,7 @@ static int nft_quota_dump(struct sk_buff *skb, { struct nft_quota *priv = nft_expr_priv(expr); - return nft_quota_do_dump(skb, priv, false); + return nft_quota_do_dump(skb, priv, reset); } static void nft_quota_destroy(const struct nft_ctx *ctx, -- cgit v1.2.3 From 14d898f3c1b3bf9c4375ee3255ec9e9b89a35578 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 8 Nov 2022 15:05:59 +0100 Subject: dev: Move received_rps counter next to RPS members in softnet data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the received_rps counter value next to the other RPS-related members in softnet_data. This closes two four-byte holes in the structure, making room for another pointer in the first two cache lines without bumping the xmit struct to its own line. Acked-by: Song Liu Reviewed-by: Stanislav Fomichev Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221108140601.149971-2-toke@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02a2318da7c7..ddc59ef98500 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3128,7 +3128,6 @@ struct softnet_data { /* stats */ unsigned int processed; unsigned int time_squeeze; - unsigned int received_rps; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif @@ -3161,6 +3160,7 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif + unsigned int received_rps; unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; -- cgit v1.2.3 From 32637e33003f36e75e9147788cc0e2f21706ef99 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 8 Nov 2022 15:06:00 +0100 Subject: bpf: Expand map key argument of bpf_redirect_map to u64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For queueing packets in XDP we want to add a new redirect map type with support for 64-bit indexes. To prepare fore this, expand the width of the 'key' argument to the bpf_redirect_map() helper. Since BPF registers are always 64-bit, this should be safe to do after the fact. Acked-by: Song Liu Reviewed-by: Stanislav Fomichev Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221108140601.149971-3-toke@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- include/linux/filter.h | 12 ++++++------ include/uapi/linux/bpf.h | 2 +- kernel/bpf/cpumap.c | 4 ++-- kernel/bpf/devmap.c | 4 ++-- kernel/bpf/verifier.c | 2 +- net/core/filter.c | 4 ++-- net/xdp/xskmap.c | 4 ++-- 8 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 49f9d2bec401..54462dd28824 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -135,7 +135,7 @@ struct bpf_map_ops { struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ - int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags); + int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure diff --git a/include/linux/filter.h b/include/linux/filter.h index 787d35dbf5b0..bf701976056e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -643,13 +643,13 @@ struct bpf_nh_params { }; struct bpf_redirect_info { - u32 flags; - u32 tgt_index; + u64 tgt_index; void *tgt_value; struct bpf_map *map; + u32 flags; + u32 kern_flags; u32 map_id; enum bpf_map_type map_type; - u32 kern_flags; struct bpf_nh_params nh; }; @@ -1504,7 +1504,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { @@ -1515,7 +1515,7 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; - ri->tgt_value = lookup_elem(map, ifindex); + ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program @@ -1527,7 +1527,7 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind return flags & action_mask; } - ri->tgt_index = ifindex; + ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6580448e9f77..ab86145df760 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2647,7 +2647,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 6b6a78c04b90..e0b2d016f0bf 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -667,9 +667,9 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + return __bpf_xdp_redirect_map(map, index, flags, 0, __cpu_map_lookup_elem); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index f9a87dcc5535..d01e4c55b376 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -992,14 +992,14 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, map, key, value, map_flags); } -static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } -static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5e74f460dfd0..be24774961ab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14384,7 +14384,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, - (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL)); + (int (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, (int (*)(struct bpf_map *map, bpf_callback_t callback_fn, diff --git a/net/core/filter.c b/net/core/filter.c index 37fad5a9b752..754dd01354d8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4414,10 +4414,10 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, +BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { - return map->ops->map_redirect(map, ifindex, flags); + return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index acc8e52a4f5f..771d0fa90ef5 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -231,9 +231,9 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + return __bpf_xdp_redirect_map(map, index, flags, 0, __xsk_map_lookup_elem); } -- cgit v1.2.3 From 53d04b9811107633f25be02a5d981a6070d09e6e Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 14 Nov 2022 19:07:30 +0200 Subject: net: dsa: remove phylink_validate() method As of now, no DSA driver uses a custom link mode validation procedure anymore. So remove this DSA operation and let phylink determine what is supported based on config->mac_capabilities (if provided by the driver). Leave a comment why we left the code that we did, and that there is more work to do. Signed-off-by: Vladimir Oltean Reviewed-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 3 --- net/dsa/port.c | 18 ++++++++---------- 2 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index ee369670e20e..dde364688739 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -880,9 +880,6 @@ struct dsa_switch_ops { */ void (*phylink_get_caps)(struct dsa_switch *ds, int port, struct phylink_config *config); - void (*phylink_validate)(struct dsa_switch *ds, int port, - unsigned long *supported, - struct phylink_link_state *state); struct phylink_pcs *(*phylink_mac_select_pcs)(struct dsa_switch *ds, int port, phy_interface_t iface); diff --git a/net/dsa/port.c b/net/dsa/port.c index 208168276995..48c9eaa74aee 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1536,16 +1536,14 @@ static void dsa_port_phylink_validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->phylink_validate) { - if (config->mac_capabilities) - phylink_generic_validate(config, supported, state); - return; - } - - ds->ops->phylink_validate(ds, dp->index, supported, state); + /* Skip call for drivers which don't yet set mac_capabilities, + * since validating in that case would mean their PHY will advertise + * nothing. In turn, skipping validation makes them advertise + * everything that the PHY supports, so those drivers should be + * converted ASAP. + */ + if (config->mac_capabilities) + phylink_generic_validate(config, supported, state); } static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, -- cgit v1.2.3 From 02ae6a7034d7b2e3d89e33d73da10a1f156789a0 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Tue, 8 Nov 2022 14:23:55 -0600 Subject: wifi: cfg80211: Avoid clashing function prototypes When built with Control Flow Integrity, function prototypes between caller and function declaration must match. These mismatches are visible at compile time with the new -Wcast-function-type-strict in Clang[1]. Fix a total of 73 warnings like these: drivers/net/wireless/intersil/orinoco/wext.c:1379:27: warning: cast from 'int (*)(struct net_device *, struct iw_request_info *, struct iw_param *, char *)' to 'iw_handler' (aka 'int (*)(struct net_device *, struct iw_request_info *, union iwreq_data *, char *)') converts to incompatible function type [-Wcast-function-type-strict] IW_HANDLER(SIOCGIWPOWER, (iw_handler)orinoco_ioctl_getpower), ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../net/wireless/wext-compat.c:1607:33: warning: cast from 'int (*)(struct net_device *, struct iw_request_info *, struct iw_point *, char *)' to 'iw_handler' (aka 'int (*)(struct net_device *, struct iw_request_info *, union iwreq_data *, char *)') converts to incompatible function type [-Wcast-function-type-strict] [IW_IOCTL_IDX(SIOCSIWGENIE)] = (iw_handler) cfg80211_wext_siwgenie, ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ../drivers/net/wireless/intersil/orinoco/wext.c:1390:27: error: incompatible function pointer types initializing 'const iw_handler' (aka 'int (*const)(struct net_device *, struct iw_request_info *, union iwreq_data *, char *)') with an expression of type 'int (struct net_device *, struct iw_request_info *, struct iw_param *, char *)' [-Wincompatible-function-pointer-types] IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), ^~~~~~~~~~~~~~~~~~~~~~ The cfg80211 Wireless Extension handler callbacks (iw_handler) use a union for the data argument. Actually use the union and perform explicit member selection in the function body instead of having a function prototype mismatch. There are no resulting binary differences before/after changes. These changes were made partly manually and partly with the help of Coccinelle. Link: https://github.com/KSPP/linux/issues/234 Link: https://reviews.llvm.org/D134831 [1] Signed-off-by: Gustavo A. R. Silva Reviewed-by: Kees Cook Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/a68822bf8dd587988131bb6a295280cb4293f05d.1667934775.git.gustavoars@kernel.org --- drivers/net/wireless/intel/ipw2x00/ipw2200.c | 2 +- drivers/net/wireless/intersil/orinoco/wext.c | 22 ++-- include/net/cfg80211-wext.h | 20 +-- net/wireless/scan.c | 3 +- net/wireless/wext-compat.c | 180 ++++++++++++--------------- net/wireless/wext-compat.h | 8 +- net/wireless/wext-sme.c | 5 +- 7 files changed, 113 insertions(+), 127 deletions(-) (limited to 'include') diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c index 79d5c09757d4..ca802af8cddc 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c @@ -9856,7 +9856,7 @@ static int ipw_wx_sw_reset(struct net_device *dev, /* Rebase the WE IOCTLs to zero for the handler array */ static iw_handler ipw_wx_handlers[] = { - IW_HANDLER(SIOCGIWNAME, (iw_handler)cfg80211_wext_giwname), + IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), IW_HANDLER(SIOCSIWFREQ, ipw_wx_set_freq), IW_HANDLER(SIOCGIWFREQ, ipw_wx_get_freq), IW_HANDLER(SIOCSIWMODE, ipw_wx_set_mode), diff --git a/drivers/net/wireless/intersil/orinoco/wext.c b/drivers/net/wireless/intersil/orinoco/wext.c index b8eb5d60192f..dea1ff044342 100644 --- a/drivers/net/wireless/intersil/orinoco/wext.c +++ b/drivers/net/wireless/intersil/orinoco/wext.c @@ -1363,31 +1363,31 @@ static const struct iw_priv_args orinoco_privtab[] = { static const iw_handler orinoco_handler[] = { IW_HANDLER(SIOCSIWCOMMIT, orinoco_ioctl_commit), - IW_HANDLER(SIOCGIWNAME, (iw_handler)cfg80211_wext_giwname), + IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), IW_HANDLER(SIOCSIWFREQ, orinoco_ioctl_setfreq), IW_HANDLER(SIOCGIWFREQ, orinoco_ioctl_getfreq), - IW_HANDLER(SIOCSIWMODE, (iw_handler)cfg80211_wext_siwmode), - IW_HANDLER(SIOCGIWMODE, (iw_handler)cfg80211_wext_giwmode), + IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), + IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), IW_HANDLER(SIOCSIWSENS, orinoco_ioctl_setsens), IW_HANDLER(SIOCGIWSENS, orinoco_ioctl_getsens), - IW_HANDLER(SIOCGIWRANGE, (iw_handler)cfg80211_wext_giwrange), + IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), IW_HANDLER(SIOCSIWSPY, iw_handler_set_spy), IW_HANDLER(SIOCGIWSPY, iw_handler_get_spy), IW_HANDLER(SIOCSIWTHRSPY, iw_handler_set_thrspy), IW_HANDLER(SIOCGIWTHRSPY, iw_handler_get_thrspy), IW_HANDLER(SIOCSIWAP, orinoco_ioctl_setwap), IW_HANDLER(SIOCGIWAP, orinoco_ioctl_getwap), - IW_HANDLER(SIOCSIWSCAN, (iw_handler)cfg80211_wext_siwscan), - IW_HANDLER(SIOCGIWSCAN, (iw_handler)cfg80211_wext_giwscan), + IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), + IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), IW_HANDLER(SIOCSIWESSID, orinoco_ioctl_setessid), IW_HANDLER(SIOCGIWESSID, orinoco_ioctl_getessid), IW_HANDLER(SIOCSIWRATE, orinoco_ioctl_setrate), IW_HANDLER(SIOCGIWRATE, orinoco_ioctl_getrate), - IW_HANDLER(SIOCSIWRTS, (iw_handler)cfg80211_wext_siwrts), - IW_HANDLER(SIOCGIWRTS, (iw_handler)cfg80211_wext_giwrts), - IW_HANDLER(SIOCSIWFRAG, (iw_handler)cfg80211_wext_siwfrag), - IW_HANDLER(SIOCGIWFRAG, (iw_handler)cfg80211_wext_giwfrag), - IW_HANDLER(SIOCGIWRETRY, (iw_handler)cfg80211_wext_giwretry), + IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), + IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), + IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), + IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), + IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), IW_HANDLER(SIOCSIWENCODE, orinoco_ioctl_setiwencode), IW_HANDLER(SIOCGIWENCODE, orinoco_ioctl_getiwencode), IW_HANDLER(SIOCSIWPOWER, orinoco_ioctl_setpower), diff --git a/include/net/cfg80211-wext.h b/include/net/cfg80211-wext.h index ad77caf2ffde..0ee36d97e068 100644 --- a/include/net/cfg80211-wext.h +++ b/include/net/cfg80211-wext.h @@ -19,34 +19,34 @@ */ int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, - char *name, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwscan(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwscan(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, - struct iw_param *retry, char *extra); + union iwreq_data *wrqu, char *extra); #endif /* __NET_CFG80211_WEXT_H */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 806a5f1330ff..853619bc0f1a 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3229,8 +3229,9 @@ static int ieee80211_scan_results(struct cfg80211_registered_device *rdev, int cfg80211_wext_giwscan(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct cfg80211_registered_device *rdev; int res; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index ddf340bfa07a..8a24dfca75af 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -25,16 +25,17 @@ int cfg80211_wext_giwname(struct net_device *dev, struct iw_request_info *info, - char *name, char *extra) + union iwreq_data *wrqu, char *extra) { - strcpy(name, "IEEE 802.11"); + strcpy(wrqu->name, "IEEE 802.11"); return 0; } EXPORT_WEXT_HANDLER(cfg80211_wext_giwname); int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra) + union iwreq_data *wrqu, char *extra) { + __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev; struct vif_params vifparams; @@ -71,8 +72,9 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info, EXPORT_WEXT_HANDLER(cfg80211_wext_siwmode); int cfg80211_wext_giwmode(struct net_device *dev, struct iw_request_info *info, - u32 *mode, char *extra) + union iwreq_data *wrqu, char *extra) { + __u32 *mode = &wrqu->mode; struct wireless_dev *wdev = dev->ieee80211_ptr; if (!wdev) @@ -108,8 +110,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwmode); int cfg80211_wext_giwrange(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_range *range = (struct iw_range *) extra; enum nl80211_band band; @@ -251,8 +254,9 @@ int cfg80211_wext_freq(struct iw_freq *freq) int cfg80211_wext_siwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 orts = wdev->wiphy->rts_threshold; @@ -281,8 +285,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_siwrts); int cfg80211_wext_giwrts(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rts, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rts = &wrqu->rts; struct wireless_dev *wdev = dev->ieee80211_ptr; rts->value = wdev->wiphy->rts_threshold; @@ -295,8 +300,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwrts); int cfg80211_wext_siwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 ofrag = wdev->wiphy->frag_threshold; @@ -325,8 +331,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_siwfrag); int cfg80211_wext_giwfrag(struct net_device *dev, struct iw_request_info *info, - struct iw_param *frag, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *frag = &wrqu->frag; struct wireless_dev *wdev = dev->ieee80211_ptr; frag->value = wdev->wiphy->frag_threshold; @@ -339,8 +346,9 @@ EXPORT_WEXT_HANDLER(cfg80211_wext_giwfrag); static int cfg80211_wext_siwretry(struct net_device *dev, struct iw_request_info *info, - struct iw_param *retry, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u32 changed = 0; @@ -378,8 +386,9 @@ static int cfg80211_wext_siwretry(struct net_device *dev, int cfg80211_wext_giwretry(struct net_device *dev, struct iw_request_info *info, - struct iw_param *retry, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *retry = &wrqu->retry; struct wireless_dev *wdev = dev->ieee80211_ptr; retry->disabled = 0; @@ -588,8 +597,9 @@ static int cfg80211_set_encryption(struct cfg80211_registered_device *rdev, static int cfg80211_wext_siwencode(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *keybuf) + union iwreq_data *wrqu, char *keybuf) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int idx, err; @@ -664,8 +674,9 @@ out: static int cfg80211_wext_siwencodeext(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct iw_encode_ext *ext = (struct iw_encode_ext *) extra; @@ -767,8 +778,9 @@ static int cfg80211_wext_siwencodeext(struct net_device *dev, static int cfg80211_wext_giwencode(struct net_device *dev, struct iw_request_info *info, - struct iw_point *erq, char *keybuf) + union iwreq_data *wrqu, char *keybuf) { + struct iw_point *erq = &wrqu->encoding; struct wireless_dev *wdev = dev->ieee80211_ptr; int idx; @@ -804,8 +816,9 @@ static int cfg80211_wext_giwencode(struct net_device *dev, static int cfg80211_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *wextfreq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_freq *wextfreq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = { @@ -870,8 +883,9 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, static int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_freq *freq = &wrqu->freq; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_chan_def chandef = {}; @@ -1147,8 +1161,9 @@ static int cfg80211_set_key_mgt(struct wireless_dev *wdev, u32 key_mgt) static int cfg80211_wext_siwauth(struct net_device *dev, struct iw_request_info *info, - struct iw_param *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *data = &wrqu->param; struct wireless_dev *wdev = dev->ieee80211_ptr; if (wdev->iftype != NL80211_IFTYPE_STATION) @@ -1180,7 +1195,7 @@ static int cfg80211_wext_siwauth(struct net_device *dev, static int cfg80211_wext_giwauth(struct net_device *dev, struct iw_request_info *info, - struct iw_param *data, char *extra) + union iwreq_data *wrqu, char *extra) { /* XXX: what do we need? */ @@ -1189,8 +1204,9 @@ static int cfg80211_wext_giwauth(struct net_device *dev, static int cfg80211_wext_siwpower(struct net_device *dev, struct iw_request_info *info, - struct iw_param *wrq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); bool ps; @@ -1238,8 +1254,9 @@ static int cfg80211_wext_siwpower(struct net_device *dev, static int cfg80211_wext_giwpower(struct net_device *dev, struct iw_request_info *info, - struct iw_param *wrq, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *wrq = &wrqu->power; struct wireless_dev *wdev = dev->ieee80211_ptr; wrq->disabled = !wdev->ps; @@ -1249,8 +1266,9 @@ static int cfg80211_wext_giwpower(struct net_device *dev, static int cfg80211_wext_siwrate(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rate, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bitrate_mask mask; @@ -1307,8 +1325,9 @@ static int cfg80211_wext_siwrate(struct net_device *dev, static int cfg80211_wext_giwrate(struct net_device *dev, struct iw_request_info *info, - struct iw_param *rate, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_param *rate = &wrqu->bitrate; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct station_info sinfo = {}; @@ -1430,8 +1449,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) static int cfg80211_wext_siwap(struct net_device *dev, struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) + union iwreq_data *wrqu, char *extra) { + struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1455,8 +1475,9 @@ static int cfg80211_wext_siwap(struct net_device *dev, static int cfg80211_wext_giwap(struct net_device *dev, struct iw_request_info *info, - struct sockaddr *ap_addr, char *extra) + union iwreq_data *wrqu, char *extra) { + struct sockaddr *ap_addr = &wrqu->ap_addr; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1480,8 +1501,9 @@ static int cfg80211_wext_giwap(struct net_device *dev, static int cfg80211_wext_siwessid(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *ssid) + union iwreq_data *wrqu, char *ssid) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1505,8 +1527,9 @@ static int cfg80211_wext_siwessid(struct net_device *dev, static int cfg80211_wext_giwessid(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *ssid) + union iwreq_data *wrqu, char *ssid) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ret; @@ -1533,7 +1556,7 @@ static int cfg80211_wext_giwessid(struct net_device *dev, static int cfg80211_wext_siwpmksa(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -1584,78 +1607,39 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev, return ret; } -#define DEFINE_WEXT_COMPAT_STUB(func, type) \ - static int __ ## func(struct net_device *dev, \ - struct iw_request_info *info, \ - union iwreq_data *wrqu, \ - char *extra) \ - { \ - return func(dev, info, (type *)wrqu, extra); \ - } - -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwname, char) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfreq, struct iw_freq) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfreq, struct iw_freq) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmode, u32) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwmode, u32) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrange, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwap, struct sockaddr) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwap, struct sockaddr) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmlme, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwscan, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwessid, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwessid, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrate, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrate, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrts, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrts, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfrag, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfrag, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwretry, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwretry, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencode, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwencode, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwpower, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpower, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwgenie, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwauth, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwauth, struct iw_param) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencodeext, struct iw_point) -DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpmksa, struct iw_point) - static const iw_handler cfg80211_handlers[] = { - [IW_IOCTL_IDX(SIOCGIWNAME)] = __cfg80211_wext_giwname, - [IW_IOCTL_IDX(SIOCSIWFREQ)] = __cfg80211_wext_siwfreq, - [IW_IOCTL_IDX(SIOCGIWFREQ)] = __cfg80211_wext_giwfreq, - [IW_IOCTL_IDX(SIOCSIWMODE)] = __cfg80211_wext_siwmode, - [IW_IOCTL_IDX(SIOCGIWMODE)] = __cfg80211_wext_giwmode, - [IW_IOCTL_IDX(SIOCGIWRANGE)] = __cfg80211_wext_giwrange, - [IW_IOCTL_IDX(SIOCSIWAP)] = __cfg80211_wext_siwap, - [IW_IOCTL_IDX(SIOCGIWAP)] = __cfg80211_wext_giwap, - [IW_IOCTL_IDX(SIOCSIWMLME)] = __cfg80211_wext_siwmlme, - [IW_IOCTL_IDX(SIOCSIWSCAN)] = cfg80211_wext_siwscan, - [IW_IOCTL_IDX(SIOCGIWSCAN)] = __cfg80211_wext_giwscan, - [IW_IOCTL_IDX(SIOCSIWESSID)] = __cfg80211_wext_siwessid, - [IW_IOCTL_IDX(SIOCGIWESSID)] = __cfg80211_wext_giwessid, - [IW_IOCTL_IDX(SIOCSIWRATE)] = __cfg80211_wext_siwrate, - [IW_IOCTL_IDX(SIOCGIWRATE)] = __cfg80211_wext_giwrate, - [IW_IOCTL_IDX(SIOCSIWRTS)] = __cfg80211_wext_siwrts, - [IW_IOCTL_IDX(SIOCGIWRTS)] = __cfg80211_wext_giwrts, - [IW_IOCTL_IDX(SIOCSIWFRAG)] = __cfg80211_wext_siwfrag, - [IW_IOCTL_IDX(SIOCGIWFRAG)] = __cfg80211_wext_giwfrag, - [IW_IOCTL_IDX(SIOCSIWTXPOW)] = cfg80211_wext_siwtxpower, - [IW_IOCTL_IDX(SIOCGIWTXPOW)] = cfg80211_wext_giwtxpower, - [IW_IOCTL_IDX(SIOCSIWRETRY)] = __cfg80211_wext_siwretry, - [IW_IOCTL_IDX(SIOCGIWRETRY)] = __cfg80211_wext_giwretry, - [IW_IOCTL_IDX(SIOCSIWENCODE)] = __cfg80211_wext_siwencode, - [IW_IOCTL_IDX(SIOCGIWENCODE)] = __cfg80211_wext_giwencode, - [IW_IOCTL_IDX(SIOCSIWPOWER)] = __cfg80211_wext_siwpower, - [IW_IOCTL_IDX(SIOCGIWPOWER)] = __cfg80211_wext_giwpower, - [IW_IOCTL_IDX(SIOCSIWGENIE)] = __cfg80211_wext_siwgenie, - [IW_IOCTL_IDX(SIOCSIWAUTH)] = __cfg80211_wext_siwauth, - [IW_IOCTL_IDX(SIOCGIWAUTH)] = __cfg80211_wext_giwauth, - [IW_IOCTL_IDX(SIOCSIWENCODEEXT)]= __cfg80211_wext_siwencodeext, - [IW_IOCTL_IDX(SIOCSIWPMKSA)] = __cfg80211_wext_siwpmksa, + IW_HANDLER(SIOCGIWNAME, cfg80211_wext_giwname), + IW_HANDLER(SIOCSIWFREQ, cfg80211_wext_siwfreq), + IW_HANDLER(SIOCGIWFREQ, cfg80211_wext_giwfreq), + IW_HANDLER(SIOCSIWMODE, cfg80211_wext_siwmode), + IW_HANDLER(SIOCGIWMODE, cfg80211_wext_giwmode), + IW_HANDLER(SIOCGIWRANGE, cfg80211_wext_giwrange), + IW_HANDLER(SIOCSIWAP, cfg80211_wext_siwap), + IW_HANDLER(SIOCGIWAP, cfg80211_wext_giwap), + IW_HANDLER(SIOCSIWMLME, cfg80211_wext_siwmlme), + IW_HANDLER(SIOCSIWSCAN, cfg80211_wext_siwscan), + IW_HANDLER(SIOCGIWSCAN, cfg80211_wext_giwscan), + IW_HANDLER(SIOCSIWESSID, cfg80211_wext_siwessid), + IW_HANDLER(SIOCGIWESSID, cfg80211_wext_giwessid), + IW_HANDLER(SIOCSIWRATE, cfg80211_wext_siwrate), + IW_HANDLER(SIOCGIWRATE, cfg80211_wext_giwrate), + IW_HANDLER(SIOCSIWRTS, cfg80211_wext_siwrts), + IW_HANDLER(SIOCGIWRTS, cfg80211_wext_giwrts), + IW_HANDLER(SIOCSIWFRAG, cfg80211_wext_siwfrag), + IW_HANDLER(SIOCGIWFRAG, cfg80211_wext_giwfrag), + IW_HANDLER(SIOCSIWTXPOW, cfg80211_wext_siwtxpower), + IW_HANDLER(SIOCGIWTXPOW, cfg80211_wext_giwtxpower), + IW_HANDLER(SIOCSIWRETRY, cfg80211_wext_siwretry), + IW_HANDLER(SIOCGIWRETRY, cfg80211_wext_giwretry), + IW_HANDLER(SIOCSIWENCODE, cfg80211_wext_siwencode), + IW_HANDLER(SIOCGIWENCODE, cfg80211_wext_giwencode), + IW_HANDLER(SIOCSIWPOWER, cfg80211_wext_siwpower), + IW_HANDLER(SIOCGIWPOWER, cfg80211_wext_giwpower), + IW_HANDLER(SIOCSIWGENIE, cfg80211_wext_siwgenie), + IW_HANDLER(SIOCSIWAUTH, cfg80211_wext_siwauth), + IW_HANDLER(SIOCGIWAUTH, cfg80211_wext_giwauth), + IW_HANDLER(SIOCSIWENCODEEXT, cfg80211_wext_siwencodeext), + IW_HANDLER(SIOCSIWPMKSA, cfg80211_wext_siwpmksa), }; const struct iw_handler_def cfg80211_wext_handler = { diff --git a/net/wireless/wext-compat.h b/net/wireless/wext-compat.h index 8d3cc1552e2f..c02eb789e676 100644 --- a/net/wireless/wext-compat.h +++ b/net/wireless/wext-compat.h @@ -13,7 +13,7 @@ int cfg80211_ibss_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra); + struct iw_freq *wextfreq, char *extra); int cfg80211_ibss_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra); @@ -32,7 +32,7 @@ int cfg80211_ibss_wext_giwessid(struct net_device *dev, int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, - struct iw_freq *freq, char *extra); + struct iw_freq *wextfreq, char *extra); int cfg80211_mgd_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra); @@ -51,10 +51,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra); + union iwreq_data *wrqu, char *extra); int cfg80211_wext_freq(struct iw_freq *freq); diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 68f45afc352d..191c6d98c700 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -324,8 +324,9 @@ int cfg80211_mgd_wext_giwap(struct net_device *dev, int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { + struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *ie = extra; @@ -374,7 +375,7 @@ int cfg80211_wext_siwgenie(struct net_device *dev, int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, - struct iw_point *data, char *extra) + union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; -- cgit v1.2.3 From 06463f6e98df34908c26aa8e7a31a279646b1f51 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 9 Nov 2022 14:42:49 -0800 Subject: wifi: wl1251: drop support for platform data Remove support for configuring the device via platform data because there are no users of wl1251_platform_data left in the mainline kernel. Signed-off-by: Dmitry Torokhov Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20221109224250.2885119-2-dmitry.torokhov@gmail.com --- MAINTAINERS | 1 - drivers/net/wireless/ti/Kconfig | 8 ----- drivers/net/wireless/ti/wilink_platform_data.c | 35 -------------------- drivers/net/wireless/ti/wl1251/sdio.c | 8 +---- drivers/net/wireless/ti/wl1251/spi.c | 15 ++------- drivers/net/wireless/ti/wlcore/spi.c | 1 - include/linux/wl12xx.h | 44 -------------------------- 7 files changed, 4 insertions(+), 108 deletions(-) delete mode 100644 drivers/net/wireless/ti/wilink_platform_data.c delete mode 100644 include/linux/wl12xx.h (limited to 'include') diff --git a/MAINTAINERS b/MAINTAINERS index 377aedb3808b..56764f76752b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20665,7 +20665,6 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/wl12xx W: https://wireless.wiki.kernel.org/en/users/Drivers/wl1251 T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git F: drivers/net/wireless/ti/ -F: include/linux/wl12xx.h TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz diff --git a/drivers/net/wireless/ti/Kconfig b/drivers/net/wireless/ti/Kconfig index 7c0b17a76fe2..3fcd9e395f72 100644 --- a/drivers/net/wireless/ti/Kconfig +++ b/drivers/net/wireless/ti/Kconfig @@ -18,12 +18,4 @@ source "drivers/net/wireless/ti/wl18xx/Kconfig" # keep last for automatic dependencies source "drivers/net/wireless/ti/wlcore/Kconfig" -config WILINK_PLATFORM_DATA - bool "TI WiLink platform data" - depends on WLCORE_SDIO || WL1251_SDIO - default y - help - Small platform data bit needed to pass data to the sdio modules. - - endif # WLAN_VENDOR_TI diff --git a/drivers/net/wireless/ti/wilink_platform_data.c b/drivers/net/wireless/ti/wilink_platform_data.c deleted file mode 100644 index 1de6a62d526f..000000000000 --- a/drivers/net/wireless/ti/wilink_platform_data.c +++ /dev/null @@ -1,35 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * This file is part of wl12xx - * - * Copyright (C) 2010-2011 Texas Instruments, Inc. - */ - -#include -#include -#include - -static struct wl1251_platform_data *wl1251_platform_data; - -int __init wl1251_set_platform_data(const struct wl1251_platform_data *data) -{ - if (wl1251_platform_data) - return -EBUSY; - if (!data) - return -EINVAL; - - wl1251_platform_data = kmemdup(data, sizeof(*data), GFP_KERNEL); - if (!wl1251_platform_data) - return -ENOMEM; - - return 0; -} - -struct wl1251_platform_data *wl1251_get_platform_data(void) -{ - if (!wl1251_platform_data) - return ERR_PTR(-ENODEV); - - return wl1251_platform_data; -} -EXPORT_SYMBOL(wl1251_get_platform_data); diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c index c9a4e9a43400..301bd0043a43 100644 --- a/drivers/net/wireless/ti/wl1251/sdio.c +++ b/drivers/net/wireless/ti/wl1251/sdio.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -197,7 +196,6 @@ static int wl1251_sdio_probe(struct sdio_func *func, struct wl1251 *wl; struct ieee80211_hw *hw; struct wl1251_sdio *wl_sdio; - const struct wl1251_platform_data *wl1251_board_data; struct device_node *np = func->dev.of_node; hw = wl1251_alloc_hw(); @@ -225,11 +223,7 @@ static int wl1251_sdio_probe(struct sdio_func *func, wl->if_priv = wl_sdio; wl->if_ops = &wl1251_sdio_ops; - wl1251_board_data = wl1251_get_platform_data(); - if (!IS_ERR(wl1251_board_data)) { - wl->irq = wl1251_board_data->irq; - wl->use_eeprom = wl1251_board_data->use_eeprom; - } else if (np) { + if (np) { wl->use_eeprom = of_property_read_bool(np, "ti,wl1251-has-eeprom"); wl->irq = of_irq_get(np, 0); if (wl->irq == -EPROBE_DEFER) { diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c index 9df38726e8b0..08d9814b49c1 100644 --- a/drivers/net/wireless/ti/wl1251/spi.c +++ b/drivers/net/wireless/ti/wl1251/spi.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -226,16 +225,13 @@ static const struct wl1251_if_operations wl1251_spi_ops = { static int wl1251_spi_probe(struct spi_device *spi) { - struct wl1251_platform_data *pdata = dev_get_platdata(&spi->dev); struct device_node *np = spi->dev.of_node; struct ieee80211_hw *hw; struct wl1251 *wl; int ret; - if (!np && !pdata) { - wl1251_error("no platform data"); + if (!np) return -ENODEV; - } hw = wl1251_alloc_hw(); if (IS_ERR(hw)) @@ -259,14 +255,9 @@ static int wl1251_spi_probe(struct spi_device *spi) goto out_free; } - if (np) { - wl->use_eeprom = of_property_read_bool(np, "ti,wl1251-has-eeprom"); - wl->power_gpio = of_get_named_gpio(np, "ti,power-gpio", 0); - } else if (pdata) { - wl->power_gpio = pdata->power_gpio; - wl->use_eeprom = pdata->use_eeprom; - } + wl->use_eeprom = of_property_read_bool(np, "ti,wl1251-has-eeprom"); + wl->power_gpio = of_get_named_gpio(np, "ti,power-gpio", 0); if (wl->power_gpio == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto out_free; diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c index 7eae1ec2eb2b..2d2edddc77bd 100644 --- a/drivers/net/wireless/ti/wlcore/spi.c +++ b/drivers/net/wireless/ti/wlcore/spi.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h deleted file mode 100644 index 03d61f1d23ab..000000000000 --- a/include/linux/wl12xx.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * This file is part of wl12xx - * - * Copyright (C) 2009 Nokia Corporation - * - * Contact: Luciano Coelho - */ - -#ifndef _LINUX_WL12XX_H -#define _LINUX_WL12XX_H - -#include - -struct wl1251_platform_data { - int power_gpio; - /* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */ - int irq; - bool use_eeprom; -}; - -#ifdef CONFIG_WILINK_PLATFORM_DATA - -int wl1251_set_platform_data(const struct wl1251_platform_data *data); - -struct wl1251_platform_data *wl1251_get_platform_data(void); - -#else - -static inline -int wl1251_set_platform_data(const struct wl1251_platform_data *data) -{ - return -ENOSYS; -} - -static inline -struct wl1251_platform_data *wl1251_get_platform_data(void) -{ - return ERR_PTR(-ENODATA); -} - -#endif - -#endif -- cgit v1.2.3 From 67fb43308f4b354f13aabcc66dd5d99bfbb7e838 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 14 Nov 2022 13:57:54 -0800 Subject: udp: Set NULL to sk->sk_prot->h.udp_table. We will soon introduce an optional per-netns hash table for UDP. This means we cannot use the global sk->sk_prot->h.udp_table to fetch a UDP hash table. Instead, set NULL to sk->sk_prot->h.udp_table for UDP and get a proper table from net->ipv4.udp_table. Note that we still need sk->sk_prot->h.udp_table for UDP LITE. Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 + net/ipv4/udp.c | 15 +++++++++++---- net/ipv6/udp.c | 2 +- 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 25f90bba4889..e4cc4d3cacc4 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,6 +43,7 @@ struct tcp_fastopen_context; struct netns_ipv4 { struct inet_timewait_death_row tcp_death_row; + struct udp_table *udp_table; #ifdef CONFIG_SYSCTL struct ctl_table_header *forw_hdr; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a34de263e9ce..6206c27a1659 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -131,6 +131,11 @@ EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) +static struct udp_table *udp_get_table_prot(struct sock *sk) +{ + return sk->sk_prot->h.udp_table ? : sock_net(sk)->ipv4.udp_table; +} + static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, @@ -232,7 +237,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) int udp_lib_get_port(struct sock *sk, unsigned short snum, unsigned int hash2_nulladdr) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; struct net *net = sock_net(sk); int error = 1; @@ -1999,7 +2004,7 @@ EXPORT_SYMBOL(udp_disconnect); void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; hslot = udp_hashslot(udptable, sock_net(sk), @@ -2030,7 +2035,7 @@ EXPORT_SYMBOL(udp_lib_unhash); void udp_lib_rehash(struct sock *sk, u16 newhash) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); @@ -2967,7 +2972,7 @@ struct proto udp_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp_sock), - .h.udp_table = &udp_table, + .h.udp_table = NULL, .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -3280,6 +3285,8 @@ EXPORT_SYMBOL(udp_flow_hashrnd); static int __net_init udp_sysctl_init(struct net *net) { + net->ipv4.udp_table = &udp_table; + net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 727de67e4c90..bbd6dc398f3b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1774,7 +1774,7 @@ struct proto udpv6_prot = { .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), .obj_size = sizeof(struct udp6_sock), - .h.udp_table = &udp_table, + .h.udp_table = NULL, .diag_destroy = udp_abort, }; -- cgit v1.2.3 From 9804985bf27f8fbcf0d96c7435b5ad94a2a6ea20 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Mon, 14 Nov 2022 13:57:57 -0800 Subject: udp: Introduce optional per-netns hash table. The maximum hash table size is 64K due to the nature of the protocol. [0] It's smaller than TCP, and fewer sockets can cause a performance drop. On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in different netns, creating 32Mi sockets without data transfer in the root netns causes regression for the iperf3's connection. uhash_entries sockets length Gbps 64K 1 1 5.69 1Mi 16 5.27 2Mi 32 4.90 4Mi 64 4.09 8Mi 128 2.96 16Mi 256 2.06 32Mi 512 1.12 The per-netns hash table breaks the lengthy lists into shorter ones. It is useful on a multi-tenant system with thousands of netns. With smaller hash tables, we can look up sockets faster, isolate noisy neighbours, and reduce lock contention. The max size of the per-netns table is 64K as well. This is because the possible hash range by udp_hashfn() always fits in 64K within the same netns and we cannot make full use of the whole buckets larger than 64K. /* 0 < num < 64K -> X < hash < X + 64K */ (num + net_hash_mix(net)) & mask; Also, the min size is 128. We use a bitmap to search for an available port in udp_lib_get_port(). To keep the bitmap on the stack and not fire the CONFIG_FRAME_WARN error at build time, we round up the table size to 128. The sysctl usage is the same with TCP: $ dmesg | cut -d ' ' -f 6- | grep "UDP hash" UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc) # sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 65536 # can be changed by uhash_entries # sysctl net.ipv4.udp_child_hash_entries net.ipv4.udp_child_hash_entries = 0 # disabled by default # ip netns add test1 # ip netns exec test1 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = -65536 # share the global table # sysctl -w net.ipv4.udp_child_hash_entries=100 net.ipv4.udp_child_hash_entries = 100 # ip netns add test2 # ip netns exec test2 sysctl net.ipv4.udp_hash_entries net.ipv4.udp_hash_entries = 128 # own a per-netns table with 2^n buckets We could optimise the hash table lookup/iteration further by removing the netns comparison for the per-netns one in the future. Also, we could optimise the sparse udp_hslot layout by putting it in udp_table. [0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/ Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.rst | 27 +++++++++ include/linux/udp.h | 2 + include/net/netns/ipv4.h | 2 + net/ipv4/sysctl_net_ipv4.c | 40 +++++++++++++ net/ipv4/udp.c | 101 +++++++++++++++++++++++++++++++-- 5 files changed, 166 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 815efc89ad73..727b25cc7ec4 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1177,6 +1177,33 @@ udp_rmem_min - INTEGER udp_wmem_min - INTEGER UDP does not have tx memory accounting and this tunable has no effect. +udp_hash_entries - INTEGER + Show the number of hash buckets for UDP sockets in the current + networking namespace. + + A negative value means the networking namespace does not own its + hash buckets and shares the initial networking namespace's one. + +udp_child_ehash_entries - INTEGER + Control the number of hash buckets for UDP sockets in the child + networking namespace, which must be set before clone() or unshare(). + + If the value is not 0, the kernel uses a value rounded up to 2^n + as the actual hash bucket size. 0 is a special value, meaning + the child networking namespace will share the initial networking + namespace's hash buckets. + + Note that the child will use the global one in case the kernel + fails to allocate enough memory. In addition, the global hash + buckets are spread over available NUMA nodes, but the allocation + of the child hash table depends on the current process's NUMA + policy, which could result in performance differences. + + Possible values: 0, 2^n (n: 7 (128) - 16 (64K)) + + Default: 0 + + RAW variables ============= diff --git a/include/linux/udp.h b/include/linux/udp.h index dea57aa37df6..a2892e151644 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -23,7 +23,9 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) return (struct udphdr *)skb_transport_header(skb); } +#define UDP_HTABLE_SIZE_MIN_PERNET 128 #define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) +#define UDP_HTABLE_SIZE_MAX 65536 static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index e4cc4d3cacc4..db762e35aca9 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -208,6 +208,8 @@ struct netns_ipv4 { atomic_t dev_addr_genid; + unsigned int sysctl_udp_child_hash_entries; + #ifdef CONFIG_SYSCTL unsigned long *sysctl_local_reserved_ports; int sysctl_ip_prot_sock; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0af28cedd071..0d0cc4ef2b85 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -40,6 +40,7 @@ static int one_day_secs = 24 * 3600; static u32 fib_multipath_hash_fields_all_mask __maybe_unused = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024; +static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; @@ -402,12 +403,36 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write, if (!net_eq(net, &init_net) && !hinfo->pernet) tcp_ehash_entries *= -1; + memset(&tbl, 0, sizeof(tbl)); tbl.data = &tcp_ehash_entries; tbl.maxlen = sizeof(int); return proc_dointvec(&tbl, write, buffer, lenp, ppos); } +static int proc_udp_hash_entries(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = container_of(table->data, struct net, + ipv4.sysctl_udp_child_hash_entries); + int udp_hash_entries; + struct ctl_table tbl; + + udp_hash_entries = net->ipv4.udp_table->mask + 1; + + /* A negative number indicates that the child netns + * shares the global udp_table. + */ + if (!net_eq(net, &init_net) && net->ipv4.udp_table == &udp_table) + udp_hash_entries *= -1; + + memset(&tbl, 0, sizeof(tbl)); + tbl.data = &udp_hash_entries; + tbl.maxlen = sizeof(int); + + return proc_dointvec(&tbl, write, buffer, lenp, ppos); +} + #ifdef CONFIG_IP_ROUTE_MULTIPATH static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, @@ -1361,6 +1386,21 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = &tcp_child_ehash_entries_max, }, + { + .procname = "udp_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .mode = 0444, + .proc_handler = proc_udp_hash_entries, + }, + { + .procname = "udp_child_hash_entries", + .data = &init_net.ipv4.sysctl_udp_child_hash_entries, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_child_hash_entries_max, + }, { .procname = "udp_rmem_min", .data = &init_net.ipv4.sysctl_udp_rmem_min, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 37e79158d145..1fb7d1ed1cb1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -129,7 +129,7 @@ DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 -#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN_PERNET) static struct udp_table *udp_get_table_prot(struct sock *sk) { @@ -3277,7 +3277,7 @@ void __init udp_table_init(struct udp_table *table, const char *name) &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, - 64 * 1024); + UDP_HTABLE_SIZE_MAX); table->hash2 = table->hash + (table->mask + 1); for (i = 0; i <= table->mask; i++) { @@ -3302,22 +3302,111 @@ u32 udp_flow_hashrnd(void) } EXPORT_SYMBOL(udp_flow_hashrnd); -static int __net_init udp_sysctl_init(struct net *net) +static void __net_init udp_sysctl_init(struct net *net) { - net->ipv4.udp_table = &udp_table; - net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif +} + +static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries) +{ + struct udp_table *udptable; + int i; + + udptable = kmalloc(sizeof(*udptable), GFP_KERNEL); + if (!udptable) + goto out; + + udptable->hash = vmalloc_huge(hash_entries * 2 * sizeof(struct udp_hslot), + GFP_KERNEL_ACCOUNT); + if (!udptable->hash) + goto free_table; + + udptable->hash2 = udptable->hash + hash_entries; + udptable->mask = hash_entries - 1; + udptable->log = ilog2(hash_entries); + + for (i = 0; i < hash_entries; i++) { + INIT_HLIST_HEAD(&udptable->hash[i].head); + udptable->hash[i].count = 0; + spin_lock_init(&udptable->hash[i].lock); + + INIT_HLIST_HEAD(&udptable->hash2[i].head); + udptable->hash2[i].count = 0; + spin_lock_init(&udptable->hash2[i].lock); + } + + return udptable; + +free_table: + kfree(udptable); +out: + return NULL; +} + +static void __net_exit udp_pernet_table_free(struct net *net) +{ + struct udp_table *udptable = net->ipv4.udp_table; + + if (udptable == &udp_table) + return; + + kvfree(udptable->hash); + kfree(udptable); +} + +static void __net_init udp_set_table(struct net *net) +{ + struct udp_table *udptable; + unsigned int hash_entries; + struct net *old_net; + + if (net_eq(net, &init_net)) + goto fallback; + + old_net = current->nsproxy->net_ns; + hash_entries = READ_ONCE(old_net->ipv4.sysctl_udp_child_hash_entries); + if (!hash_entries) + goto fallback; + + /* Set min to keep the bitmap on stack in udp_lib_get_port() */ + if (hash_entries < UDP_HTABLE_SIZE_MIN_PERNET) + hash_entries = UDP_HTABLE_SIZE_MIN_PERNET; + else + hash_entries = roundup_pow_of_two(hash_entries); + + udptable = udp_pernet_table_alloc(hash_entries); + if (udptable) { + net->ipv4.udp_table = udptable; + } else { + pr_warn("Failed to allocate UDP hash table (entries: %u) " + "for a netns, fallback to the global one\n", + hash_entries); +fallback: + net->ipv4.udp_table = &udp_table; + } +} + +static int __net_init udp_pernet_init(struct net *net) +{ + udp_sysctl_init(net); + udp_set_table(net); return 0; } +static void __net_exit udp_pernet_exit(struct net *net) +{ + udp_pernet_table_free(net); +} + static struct pernet_operations __net_initdata udp_sysctl_ops = { - .init = udp_sysctl_init, + .init = udp_pernet_init, + .exit = udp_pernet_exit, }; #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) -- cgit v1.2.3 From 6c1c5097781f563b70a81683ea6fdac21637573b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 15 Nov 2022 08:53:55 +0000 Subject: net: add atomic_long_t to net_device_stats fields Long standing KCSAN issues are caused by data-race around some dev->stats changes. Most performance critical paths already use per-cpu variables, or per-queue ones. It is reasonable (and more correct) to use atomic operations for the slow paths. This patch adds an union for each field of net_device_stats, so that we can convert paths that are not yet protected by a spinlock or a mutex. netdev_stats_to_stats64() no longer has an #if BITS_PER_LONG==64 Note that the memcpy() we were using on 64bit arches had no provision to avoid load-tearing, while atomic_long_read() is providing the needed protection at no cost. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 58 ++++++++++++++++++++++++++++------------------- include/net/dst.h | 5 ++-- net/core/dev.c | 14 +++--------- 3 files changed, 40 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 02a2318da7c7..23b3903b0678 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -171,31 +171,38 @@ static inline bool dev_xmit_complete(int rc) * (unsigned long) so they can be read and written atomically. */ +#define NET_DEV_STAT(FIELD) \ + union { \ + unsigned long FIELD; \ + atomic_long_t __##FIELD; \ + } + struct net_device_stats { - unsigned long rx_packets; - unsigned long tx_packets; - unsigned long rx_bytes; - unsigned long tx_bytes; - unsigned long rx_errors; - unsigned long tx_errors; - unsigned long rx_dropped; - unsigned long tx_dropped; - unsigned long multicast; - unsigned long collisions; - unsigned long rx_length_errors; - unsigned long rx_over_errors; - unsigned long rx_crc_errors; - unsigned long rx_frame_errors; - unsigned long rx_fifo_errors; - unsigned long rx_missed_errors; - unsigned long tx_aborted_errors; - unsigned long tx_carrier_errors; - unsigned long tx_fifo_errors; - unsigned long tx_heartbeat_errors; - unsigned long tx_window_errors; - unsigned long rx_compressed; - unsigned long tx_compressed; + NET_DEV_STAT(rx_packets); + NET_DEV_STAT(tx_packets); + NET_DEV_STAT(rx_bytes); + NET_DEV_STAT(tx_bytes); + NET_DEV_STAT(rx_errors); + NET_DEV_STAT(tx_errors); + NET_DEV_STAT(rx_dropped); + NET_DEV_STAT(tx_dropped); + NET_DEV_STAT(multicast); + NET_DEV_STAT(collisions); + NET_DEV_STAT(rx_length_errors); + NET_DEV_STAT(rx_over_errors); + NET_DEV_STAT(rx_crc_errors); + NET_DEV_STAT(rx_frame_errors); + NET_DEV_STAT(rx_fifo_errors); + NET_DEV_STAT(rx_missed_errors); + NET_DEV_STAT(tx_aborted_errors); + NET_DEV_STAT(tx_carrier_errors); + NET_DEV_STAT(tx_fifo_errors); + NET_DEV_STAT(tx_heartbeat_errors); + NET_DEV_STAT(tx_window_errors); + NET_DEV_STAT(rx_compressed); + NET_DEV_STAT(tx_compressed); }; +#undef NET_DEV_STAT /* per-cpu stats, allocated on demand. * Try to fit them in a single cache line, for dev_get_stats() sake. @@ -5171,4 +5178,9 @@ extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; +/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ +#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) +#define DEV_STATS_ADD(DEV, FIELD, VAL) \ + atomic_long_add((VAL), &(DEV)->stats.__##FIELD) + #endif /* _LINUX_NETDEVICE_H */ diff --git a/include/net/dst.h b/include/net/dst.h index 00b479ce6b99..d67fda89cd0f 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -356,9 +356,8 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, struct net *net) { - /* TODO : stats should be SMP safe */ - dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + DEV_STATS_INC(dev, rx_packets); + DEV_STATS_ADD(dev, rx_bytes, skb->len); __skb_tunnel_rx(skb, dev, net); } diff --git a/net/core/dev.c b/net/core/dev.c index fb943dad9651..d0fb4af9a126 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10369,24 +10369,16 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { -#if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); - /* zero out counters that only exist in rtnl_link_stats64 */ - memset((char *)stats64 + sizeof(*netdev_stats), 0, - sizeof(*stats64) - sizeof(*netdev_stats)); -#else - size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); - const unsigned long *src = (const unsigned long *)netdev_stats; + size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); + const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = src[i]; + dst[i] = atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); -#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); -- cgit v1.2.3 From 3af43ba4c6019b29c048921eb8147eb010165329 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Wed, 16 Nov 2022 15:50:58 +0800 Subject: bpf: Pass map file to .map_update_batch directly Currently bpf_map_do_batch() first invokes fdget(batch.map_fd) to get the target map file, then it invokes generic_map_update_batch() to do batch update. generic_map_update_batch() will get the target map file by using fdget(batch.map_fd) again and pass it to bpf_map_update_value(). The problem is map file returned by the second fdget() may be NULL or a totally different file compared by map file in bpf_map_do_batch(). The reason is that the first fdget() only guarantees the liveness of struct file instead of file descriptor and the file description may be released by concurrent close() through pick_file(). It doesn't incur any problem as for now, because maps with batch update support don't use map file in .map_fd_get_ptr() ops. But it is better to fix the potential access of an invalid map file. Using __bpf_map_get() again in generic_map_update_batch() can not fix the problem, because batch.map_fd may be closed and reopened, and the returned map file may be different with map file got in bpf_map_do_batch(), so just passing the map file directly to .map_update_batch() in bpf_map_do_batch(). Signed-off-by: Hou Tao Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20221116075059.1551277-1-houtao@huaweicloud.com --- include/linux/bpf.h | 5 +++-- kernel/bpf/syscall.c | 32 ++++++++++++++------------------ 2 files changed, 17 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 54462dd28824..e60a5c052473 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -85,7 +85,8 @@ struct bpf_map_ops { int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); - int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr, + int (*map_update_batch)(struct bpf_map *map, struct file *map_file, + const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -1789,7 +1790,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); -int generic_map_update_batch(struct bpf_map *map, +int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fdbae52f463f..b078965999e6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -175,8 +175,8 @@ static void maybe_wait_bpf_programs(struct bpf_map *map) synchronize_rcu(); } -static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, - void *value, __u64 flags) +static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, + void *key, void *value, __u64 flags) { int err; @@ -190,7 +190,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { - return bpf_fd_array_map_update_elem(map, f.file, key, value, + return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } @@ -205,12 +205,12 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); - err = bpf_fd_array_map_update_elem(map, f.file, key, value, + err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { rcu_read_lock(); - err = bpf_fd_htab_map_update_elem(map, f.file, key, value, + err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); rcu_read_unlock(); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { @@ -1410,7 +1410,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) goto free_key; } - err = bpf_map_update_value(map, f, key, value, attr->flags); + err = bpf_map_update_value(map, f.file, key, value, attr->flags); kvfree(value); free_key: @@ -1596,16 +1596,14 @@ int generic_map_delete_batch(struct bpf_map *map, return err; } -int generic_map_update_batch(struct bpf_map *map, +int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; - int ufd = attr->batch.map_fd; void *key, *value; - struct fd f; int err = 0; if (attr->batch.elem_flags & ~BPF_F_LOCK) @@ -1632,7 +1630,6 @@ int generic_map_update_batch(struct bpf_map *map, return -ENOMEM; } - f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */ for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, @@ -1640,7 +1637,7 @@ int generic_map_update_batch(struct bpf_map *map, copy_from_user(value, values + cp * value_size, value_size)) break; - err = bpf_map_update_value(map, f, key, value, + err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) @@ -1653,7 +1650,6 @@ int generic_map_update_batch(struct bpf_map *map, kvfree(value); kvfree(key); - fdput(f); return err; } @@ -4446,13 +4442,13 @@ put_file: #define BPF_MAP_BATCH_LAST_FIELD batch.flags -#define BPF_DO_BATCH(fn) \ +#define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ - err = fn(map, attr, uattr); \ + err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, @@ -4486,13 +4482,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, } if (cmd == BPF_MAP_LOOKUP_BATCH) - BPF_DO_BATCH(map->ops->map_lookup_batch); + BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) - BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch); + BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) - BPF_DO_BATCH(map->ops->map_update_batch); + BPF_DO_BATCH(map->ops->map_update_batch, map, f.file, attr, uattr); else - BPF_DO_BATCH(map->ops->map_delete_batch); + BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: if (has_write) bpf_map_write_active_dec(map); -- cgit v1.2.3 From 282de143ead96a5d53331e946f31c977b4610a74 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:55 +0530 Subject: bpf: Introduce allocated objects support Introduce support for representing pointers to objects allocated by the BPF program, i.e. PTR_TO_BTF_ID that point to a type in program BTF. This is indicated by the presence of MEM_ALLOC type flag in reg->type to avoid having to check btf_is_kernel when trying to match argument types in helpers. Whenever walking such types, any pointers being walked will always yield a SCALAR instead of pointer. In the future we might permit kptr inside such allocated objects (either kernel or program allocated), and it will then form a PTR_TO_BTF_ID of the respective type. For now, such allocated objects will always be referenced in verifier context, hence ref_obj_id == 0 for them is a bug. It is allowed to write to such objects, as long fields that are special are not touched (support for which will be added in subsequent patches). Note that once such a pointer is marked PTR_UNTRUSTED, it is no longer allowed to write to it. No PROBE_MEM handling is therefore done for loads into this type unless PTR_UNTRUSTED is part of the register type, since they can never be in an undefined state, and their lifetime will always be valid. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 +++++++++++ kernel/bpf/btf.c | 5 +++++ kernel/bpf/verifier.c | 25 +++++++++++++++++++++++-- 3 files changed, 39 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e60a5c052473..7440c20c4192 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -525,6 +525,11 @@ enum bpf_type_flag { /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), + /* MEM is of an allocated object of type in program BTF. This is used to + * tag PTR_TO_BTF_ID allocated using bpf_obj_new. + */ + MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -2792,4 +2797,10 @@ struct bpf_key { bool has_ref; }; #endif /* CONFIG_KEYS */ + +static inline bool type_is_alloc(u32 type) +{ + return type & MEM_ALLOC; +} + #endif /* _LINUX_BPF_H */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 875355ff3718..9a596f430558 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6034,6 +6034,11 @@ int btf_struct_access(struct bpf_verifier_log *log, switch (err) { case WALK_PTR: + /* For local types, the destination register cannot + * become a pointer again. + */ + if (type_is_alloc(reg->type)) + return SCALAR_VALUE; /* If we found the pointer or scalar on t+off, * we're done. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0312d9ce292f..49e08c1c2c61 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4687,14 +4687,27 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (env->ops->btf_struct_access) { + if (env->ops->btf_struct_access && !type_is_alloc(reg->type)) { + if (!btf_is_kernel(reg->btf)) { + verbose(env, "verifier internal error: reg->btf must be kernel btf\n"); + return -EFAULT; + } ret = env->ops->btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } else { - if (atype != BPF_READ) { + /* Writes are permitted with default btf_struct_access for + * program allocated objects (which always have ref_obj_id > 0), + * but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC. + */ + if (atype != BPF_READ && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "only read is supported\n"); return -EACCES; } + if (type_is_alloc(reg->type) && !reg->ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); + return -EFAULT; + } + ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag); } @@ -5973,6 +5986,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, * fixed offset. */ case PTR_TO_BTF_ID: + case PTR_TO_BTF_ID | MEM_ALLOC: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset * can be non-zero. @@ -13690,6 +13704,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: + /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike + * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot + * be said once it is marked PTR_UNTRUSTED, hence we must handle + * any faults for loads into such types. BPF_WRITE is disallowed + * for this case. + */ + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); -- cgit v1.2.3 From 8ffa5cc142137a59d6a10eb5273fa2ba5dcd4947 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:56 +0530 Subject: bpf: Recognize lock and list fields in allocated objects Allow specifying bpf_spin_lock, bpf_list_head, bpf_list_node fields in a allocated object. Also update btf_struct_access to reject direct access to these special fields. A bpf_list_head allows implementing map-in-map style use cases, where an allocated object with bpf_list_head is linked into a list in a map value. This would require embedding a bpf_list_node, support for which is also included. The bpf_spin_lock is used to protect the bpf_list_head and other data. While we strictly don't require to hold a bpf_spin_lock while touching the bpf_list_head in such objects, as when have access to it, we have complete ownership of the object, the locking constraint is still kept and may be conditionally lifted in the future. Note that the specification of such types can be done just like map values, e.g.: struct bar { struct bpf_list_node node; }; struct foo { struct bpf_spin_lock lock; struct bpf_list_head head __contains(bar, node); struct bpf_list_node node; }; struct map_value { struct bpf_spin_lock lock; struct bpf_list_head head __contains(foo, node); }; To recognize such types in user BTF, we build a btf_struct_metas array of metadata items corresponding to each BTF ID. This is done once during the btf_parse stage to avoid having to do it each time during the verification process's requirement to inspect the metadata. Moreover, the computed metadata needs to be passed to some helpers in future patches which requires allocating them and storing them in the BTF that is pinned by the program itself, so that valid access can be assumed to such data during program runtime. A key thing to note is that once a btf_struct_meta is available for a type, both the btf_record and btf_field_offs should be available. It is critical that btf_field_offs is available in case special fields are present, as we extensively rely on special fields being zeroed out in map values and allocated objects in later patches. The code ensures that by bailing out in case of errors and ensuring both are available together. If the record is not available, the special fields won't be recognized, so not having both is also fine (in terms of being a verification error and not a runtime bug). Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/btf.h | 35 +++++++++ kernel/bpf/btf.c | 197 ++++++++++++++++++++++++++++++++++++++++++++++----- kernel/bpf/syscall.c | 4 ++ 4 files changed, 225 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7440c20c4192..eb6ea53fa5a2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -177,6 +177,7 @@ enum btf_field_type { BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, BPF_LIST_HEAD = (1 << 4), + BPF_LIST_NODE = (1 << 5), }; struct btf_field_kptr { @@ -277,6 +278,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; + case BPF_LIST_NODE: + return "bpf_list_node"; default: WARN_ON_ONCE(1); return "unknown"; @@ -295,6 +298,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); + case BPF_LIST_NODE: + return sizeof(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; @@ -313,6 +318,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); + case BPF_LIST_NODE: + return __alignof__(struct bpf_list_node); default: WARN_ON_ONCE(1); return 0; diff --git a/include/linux/btf.h b/include/linux/btf.h index d80345fa566b..a01a8da20021 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -6,6 +6,8 @@ #include #include +#include +#include #include #include @@ -78,6 +80,17 @@ struct btf_id_dtor_kfunc { u32 kfunc_btf_id; }; +struct btf_struct_meta { + u32 btf_id; + struct btf_record *record; + struct btf_field_offs *field_offs; +}; + +struct btf_struct_metas { + u32 cnt; + struct btf_struct_meta types[]; +}; + typedef void (*btf_dtor_kfunc_t)(void *); extern const struct file_operations btf_fops; @@ -408,6 +421,23 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } +static inline int btf_id_cmp_func(const void *a, const void *b) +{ + const int *pa = a, *pb = b; + + return *pa - *pb; +} + +static inline bool btf_id_set_contains(const struct btf_id_set *set, u32 id) +{ + return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; +} + +static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) +{ + return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); +} + #ifdef CONFIG_BPF_SYSCALL struct bpf_prog; @@ -423,6 +453,7 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -454,6 +485,10 @@ static inline int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dt { return 0; } +static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + return NULL; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9a596f430558..a04e10477567 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -237,6 +237,7 @@ struct btf { struct rcu_head rcu; struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; + struct btf_struct_metas *struct_meta_tab; /* split BTF support */ struct btf *base_btf; @@ -1642,8 +1643,30 @@ static void btf_free_dtor_kfunc_tab(struct btf *btf) btf->dtor_kfunc_tab = NULL; } +static void btf_struct_metas_free(struct btf_struct_metas *tab) +{ + int i; + + if (!tab) + return; + for (i = 0; i < tab->cnt; i++) { + btf_record_free(tab->types[i].record); + kfree(tab->types[i].field_offs); + } + kfree(tab); +} + +static void btf_free_struct_meta_tab(struct btf *btf) +{ + struct btf_struct_metas *tab = btf->struct_meta_tab; + + btf_struct_metas_free(tab); + btf->struct_meta_tab = NULL; +} + static void btf_free(struct btf *btf) { + btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); kvfree(btf->types); @@ -3353,6 +3376,12 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_LIST_NODE) { + if (!strcmp(name, "bpf_list_node")) { + type = BPF_LIST_NODE; + goto end; + } + } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3396,6 +3425,7 @@ static int btf_find_struct_field(const struct btf *btf, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3456,6 +3486,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, switch (field_type) { case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_LIST_NODE: ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3671,6 +3702,8 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_LIST_NODE: + break; default: ret = -EFAULT; goto end; @@ -5141,6 +5174,119 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return btf_check_sec_info(env, btf_data_size); } +static const char *alloc_obj_fields[] = { + "bpf_spin_lock", + "bpf_list_head", + "bpf_list_node", +}; + +static struct btf_struct_metas * +btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) +{ + union { + struct btf_id_set set; + struct { + u32 _cnt; + u32 _ids[ARRAY_SIZE(alloc_obj_fields)]; + } _arr; + } aof; + struct btf_struct_metas *tab = NULL; + int i, n, id, ret; + + BUILD_BUG_ON(offsetof(struct btf_id_set, cnt) != 0); + BUILD_BUG_ON(sizeof(struct btf_id_set) != sizeof(u32)); + + memset(&aof, 0, sizeof(aof)); + for (i = 0; i < ARRAY_SIZE(alloc_obj_fields); i++) { + /* Try to find whether this special type exists in user BTF, and + * if so remember its ID so we can easily find it among members + * of structs that we iterate in the next loop. + */ + id = btf_find_by_name_kind(btf, alloc_obj_fields[i], BTF_KIND_STRUCT); + if (id < 0) + continue; + aof.set.ids[aof.set.cnt++] = id; + } + + if (!aof.set.cnt) + return NULL; + sort(&aof.set.ids, aof.set.cnt, sizeof(aof.set.ids[0]), btf_id_cmp_func, NULL); + + n = btf_nr_types(btf); + for (i = 1; i < n; i++) { + struct btf_struct_metas *new_tab; + const struct btf_member *member; + struct btf_field_offs *foffs; + struct btf_struct_meta *type; + struct btf_record *record; + const struct btf_type *t; + int j, tab_cnt; + + t = btf_type_by_id(btf, i); + if (!t) { + ret = -EINVAL; + goto free; + } + if (!__btf_type_is_struct(t)) + continue; + + cond_resched(); + + for_each_member(j, t, member) { + if (btf_id_set_contains(&aof.set, member->type)) + goto parse; + } + continue; + parse: + tab_cnt = tab ? tab->cnt : 0; + new_tab = krealloc(tab, offsetof(struct btf_struct_metas, types[tab_cnt + 1]), + GFP_KERNEL | __GFP_NOWARN); + if (!new_tab) { + ret = -ENOMEM; + goto free; + } + if (!tab) + new_tab->cnt = 0; + tab = new_tab; + + type = &tab->types[tab->cnt]; + type->btf_id = i; + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + /* The record cannot be unset, treat it as an error if so */ + if (IS_ERR_OR_NULL(record)) { + ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; + goto free; + } + foffs = btf_parse_field_offs(record); + /* We need the field_offs to be valid for a valid record, + * either both should be set or both should be unset. + */ + if (IS_ERR_OR_NULL(foffs)) { + btf_record_free(record); + ret = -EFAULT; + goto free; + } + type->record = record; + type->field_offs = foffs; + tab->cnt++; + } + return tab; +free: + btf_struct_metas_free(tab); + return ERR_PTR(ret); +} + +struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id) +{ + struct btf_struct_metas *tab; + + BUILD_BUG_ON(offsetof(struct btf_struct_meta, btf_id) != 0); + tab = btf->struct_meta_tab; + if (!tab) + return NULL; + return bsearch(&btf_id, tab->types, tab->cnt, sizeof(tab->types[0]), btf_id_cmp_func); +} + static int btf_check_type_tags(struct btf_verifier_env *env, struct btf *btf, int start_id) { @@ -5191,6 +5337,7 @@ static int btf_check_type_tags(struct btf_verifier_env *env, static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { + struct btf_struct_metas *struct_meta_tab; struct btf_verifier_env *env = NULL; struct bpf_verifier_log *log; struct btf *btf = NULL; @@ -5259,15 +5406,24 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, if (err) goto errout; + struct_meta_tab = btf_parse_struct_metas(log, btf); + if (IS_ERR(struct_meta_tab)) { + err = PTR_ERR(struct_meta_tab); + goto errout; + } + btf->struct_meta_tab = struct_meta_tab; + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; - goto errout; + goto errout_meta; } btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; +errout_meta: + btf_free_struct_meta_tab(btf); errout: btf_verifier_env_free(env); if (btf) @@ -6028,6 +6184,28 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 id = reg->btf_id; int err; + while (type_is_alloc(reg->type)) { + struct btf_struct_meta *meta; + struct btf_record *rec; + int i; + + meta = btf_find_struct_meta(btf, id); + if (!meta) + break; + rec = meta->record; + for (i = 0; i < rec->cnt; i++) { + struct btf_field *field = &rec->fields[i]; + u32 offset = field->offset; + if (off < offset + btf_field_type_size(field->type) && offset < off + size) { + bpf_log(log, + "direct access to %s is disallowed\n", + btf_field_type_name(field->type)); + return -EACCES; + } + } + break; + } + t = btf_type_by_id(btf, id); do { err = btf_struct_walk(log, btf, t, off, size, &id, &tmp_flag); @@ -7269,23 +7447,6 @@ bool btf_is_module(const struct btf *btf) return btf->kernel_btf && strcmp(btf->name, "vmlinux") != 0; } -static int btf_id_cmp_func(const void *a, const void *b) -{ - const int *pa = a, *pb = b; - - return *pa - *pb; -} - -bool btf_id_set_contains(const struct btf_id_set *set, u32 id) -{ - return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL; -} - -static void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) -{ - return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); -} - enum { BTF_MODULE_F_LIVE = (1 << 0), }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4c20dcbc6526..56ae97d490f4 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -537,6 +537,7 @@ void btf_record_free(struct btf_record *rec) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to release for bpf_list_head */ break; default: @@ -582,6 +583,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) } break; case BPF_LIST_HEAD: + case BPF_LIST_NODE: /* Nothing to acquire for bpf_list_head */ break; default: @@ -648,6 +650,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_LIST_NODE: + break; default: WARN_ON_ONCE(1); continue; -- cgit v1.2.3 From 865ce09a49d79d2b2c1d980f4c05ffc0b3517bdc Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:57 +0530 Subject: bpf: Verify ownership relationships for user BTF types Ensure that there can be no ownership cycles among different types by way of having owning objects that can hold some other type as their element. For instance, a map value can only hold allocated objects, but these are allowed to have another bpf_list_head. To prevent unbounded recursion while freeing resources, elements of bpf_list_head in local kptrs can never have a bpf_list_head which are part of list in a map value. Later patches will verify this by having dedicated BTF selftests. Also, to make runtime destruction easier, once btf_struct_metas is fully populated, we can stash the metadata of the value type directly in the metadata of the list_head fields, as that allows easier access to the value type's layout to destruct it at runtime from the btf_field entry of the list head itself. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-8-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/btf.h | 1 + kernel/bpf/btf.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 4 +++ 4 files changed, 77 insertions(+) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index eb6ea53fa5a2..323985a39ece 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -191,6 +191,7 @@ struct btf_field_list_head { struct btf *btf; u32 value_btf_id; u32 node_offset; + struct btf_record *value_rec; }; struct btf_field { diff --git a/include/linux/btf.h b/include/linux/btf.h index a01a8da20021..42d8f3730a8d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -178,6 +178,7 @@ int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); int btf_find_timer(const struct btf *btf, const struct btf_type *t); struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size); +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec); struct btf_field_offs *btf_parse_field_offs(struct btf_record *rec); bool btf_type_is_void(const struct btf_type *t); s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a04e10477567..91aa9c96621f 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3723,6 +3723,67 @@ end: return ERR_PTR(ret); } +int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) +{ + int i; + + /* There are two owning types, kptr_ref and bpf_list_head. The former + * only supports storing kernel types, which can never store references + * to program allocated local types, atleast not yet. Hence we only need + * to ensure that bpf_list_head ownership does not form cycles. + */ + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + return 0; + for (i = 0; i < rec->cnt; i++) { + struct btf_struct_meta *meta; + u32 btf_id; + + if (!(rec->fields[i].type & BPF_LIST_HEAD)) + continue; + btf_id = rec->fields[i].list_head.value_btf_id; + meta = btf_find_struct_meta(btf, btf_id); + if (!meta) + return -EFAULT; + rec->fields[i].list_head.value_rec = meta->record; + + if (!(rec->field_mask & BPF_LIST_NODE)) + continue; + + /* We need to ensure ownership acyclicity among all types. The + * proper way to do it would be to topologically sort all BTF + * IDs based on the ownership edges, since there can be multiple + * bpf_list_head in a type. Instead, we use the following + * reasoning: + * + * - A type can only be owned by another type in user BTF if it + * has a bpf_list_node. + * - A type can only _own_ another type in user BTF if it has a + * bpf_list_head. + * + * We ensure that if a type has both bpf_list_head and + * bpf_list_node, its element types cannot be owning types. + * + * To ensure acyclicity: + * + * When A only has bpf_list_head, ownership chain can be: + * A -> B -> C + * Where: + * - B has both bpf_list_head and bpf_list_node. + * - C only has bpf_list_node. + * + * When A has both bpf_list_head and bpf_list_node, some other + * type already owns it in the BTF domain, hence it can not own + * another owning type through any of the bpf_list_head edges. + * A -> B + * Where: + * - B only has bpf_list_node. + */ + if (meta->record->field_mask & BPF_LIST_HEAD) + return -ELOOP; + } + return 0; +} + static int btf_field_offs_cmp(const void *_a, const void *_b, const void *priv) { const u32 a = *(const u32 *)_a; @@ -5413,6 +5474,16 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, } btf->struct_meta_tab = struct_meta_tab; + if (struct_meta_tab) { + int i; + + for (i = 0; i < struct_meta_tab->cnt; i++) { + err = btf_check_and_fixup_fields(btf, struct_meta_tab->types[i].record); + if (err < 0) + goto errout_meta; + } + } + if (log->level && bpf_verifier_log_full(log)) { err = -ENOSPC; goto errout_meta; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 56ae97d490f4..6140cbc3ed8a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1054,6 +1054,10 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } } + ret = btf_check_and_fixup_fields(btf, map->record); + if (ret < 0) + goto free_map_tab; + if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) -- cgit v1.2.3 From d0d78c1df9b1dbfb5e172de473561ce09d5e9d39 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:25:59 +0530 Subject: bpf: Allow locking bpf_spin_lock global variables Global variables reside in maps accessible using direct_value_addr callbacks, so giving each load instruction's rewrite a unique reg->id disallows us from holding locks which are global. The reason for preserving reg->id as a unique value for registers that may point to spin lock is that two separate lookups are treated as two separate memory regions, and any possible aliasing is ignored for the purposes of spin lock correctness. This is not great especially for the global variable case, which are served from maps that have max_entries == 1, i.e. they always lead to map values pointing into the same map value. So refactor the active_spin_lock into a 'active_lock' structure which represents the lock identity, and instead of the reg->id, remember two fields, a pointer and the reg->id. The pointer will store reg->map_ptr or reg->btf. It's only necessary to distinguish for the id == 0 case of global variables, but always setting the pointer to a non-NULL value and using the pointer to check whether the lock is held simplifies code in the verifier. This is generic enough to allow it for global variables, map lookups, and allocated objects at the same time. Note that while whether a lock is held can be answered by just comparing active_lock.ptr to NULL, to determine whether the register is pointing to the same held lock requires comparing _both_ ptr and id. Finally, as a result of this refactoring, pseudo load instructions are not given a unique reg->id, as they are doing lookup for the same map value (max_entries is never greater than 1). Essentially, we consider that the tuple of (ptr, id) will always be unique for any kind of argument to bpf_spin_{lock,unlock}. Note that this can be extended in the future to also remember offset used for locking, so that we can introduce multiple bpf_spin_lock fields in the same allocation. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-10-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 16 +++++++++++++++- kernel/bpf/verifier.c | 41 ++++++++++++++++++++++++++++------------- 2 files changed, 43 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1a32baa78ce2..1db2b4dc7009 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -323,7 +323,21 @@ struct bpf_verifier_state { u32 branches; u32 insn_idx; u32 curframe; - u32 active_spin_lock; + /* For every reg representing a map value or allocated object pointer, + * we consider the tuple of (ptr, id) for them to be unique in verifier + * context and conside them to not alias each other for the purposes of + * tracking lock state. + */ + struct { + /* This can either be reg->map_ptr or reg->btf. If ptr is NULL, + * there's no active lock held, and other fields have no + * meaning. If non-NULL, it indicates that a lock is held and + * id member has the reg->id of the register which can be >= 0. + */ + void *ptr; + /* This will be reg->id */ + u32 id; + } active_lock; bool speculative; /* first and last insn idx of this verifier state */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 19467dda5dd9..c8f3abe9b08e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1221,7 +1221,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; - dst_state->active_spin_lock = src->active_spin_lock; + dst_state->active_lock.ptr = src->active_lock.ptr; + dst_state->active_lock.id = src->active_lock.id; dst_state->branches = src->branches; dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; @@ -5596,7 +5597,7 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state * Since only one bpf_spin_lock is allowed the checks are simpler than * reg_is_refcounted() logic. The verifier needs to remember only * one spin_lock instead of array of acquired_refs. - * cur_state->active_spin_lock remembers which map value element or allocated + * cur_state->active_lock remembers which map value element or allocated * object got locked and clears it after bpf_spin_unlock. */ static int process_spin_lock(struct bpf_verifier_env *env, int regno, @@ -5640,22 +5641,35 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, return -EINVAL; } if (is_lock) { - if (cur->active_spin_lock) { + if (cur->active_lock.ptr) { verbose(env, "Locking two bpf_spin_locks are not allowed\n"); return -EINVAL; } - cur->active_spin_lock = reg->id; + if (map) + cur->active_lock.ptr = map; + else + cur->active_lock.ptr = btf; + cur->active_lock.id = reg->id; } else { - if (!cur->active_spin_lock) { + void *ptr; + + if (map) + ptr = map; + else + ptr = btf; + + if (!cur->active_lock.ptr) { verbose(env, "bpf_spin_unlock without taking a lock\n"); return -EINVAL; } - if (cur->active_spin_lock != reg->id) { + if (cur->active_lock.ptr != ptr || + cur->active_lock.id != reg->id) { verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } - cur->active_spin_lock = 0; + cur->active_lock.ptr = NULL; + cur->active_lock.id = 0; } return 0; } @@ -10617,8 +10631,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; - if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) - dst_reg->id = ++env->id_gen; + WARN_ON_ONCE(map->max_entries != 1); + /* We want reg->id to be same (0) as map_value is not distinct */ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; @@ -10696,7 +10710,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); return -EINVAL; } @@ -11962,7 +11976,8 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; - if (old->active_spin_lock != cur->active_spin_lock) + if (old->active_lock.ptr != cur->active_lock.ptr || + old->active_lock.id != cur->active_lock.id) return false; /* for states to be equal callsites have to be the same @@ -12607,7 +12622,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock && + if (env->cur_state->active_lock.ptr && (insn->src_reg == BPF_PSEUDO_CALL || insn->imm != BPF_FUNC_spin_unlock)) { verbose(env, "function calls are not allowed while holding a lock\n"); @@ -12644,7 +12659,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_spin_lock) { + if (env->cur_state->active_lock.ptr) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } -- cgit v1.2.3 From 00b85860feb809852af9a88cb4ca8766d7dff6a3 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:01 +0530 Subject: bpf: Rewrite kfunc argument handling As we continue to add more features, argument types, kfunc flags, and different extensions to kfuncs, the code to verify the correctness of the kfunc prototype wrt the passed in registers has become ad-hoc and ugly to read. To make life easier, and make a very clear split between different stages of argument processing, move all the code into verifier.c and refactor into easier to read helpers and functions. This also makes sharing code within the verifier easier with kfunc argument processing. This will be more and more useful in later patches as we are now moving to implement very core BPF helpers as kfuncs, to keep them experimental before baking into UAPI. Remove all kfunc related bits now from btf_check_func_arg_match, as users have been converted away to refactored kfunc argument handling. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-12-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 11 - include/linux/bpf_verifier.h | 2 - include/linux/btf.h | 31 +- kernel/bpf/btf.c | 380 +------------- kernel/bpf/verifier.c | 545 ++++++++++++++++++++- .../selftests/bpf/prog_tests/kfunc_dynptr_param.c | 2 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../testing/selftests/bpf/verifier/ref_tracking.c | 4 +- 8 files changed, 573 insertions(+), 404 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 323985a39ece..0a74df731eb8 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2109,22 +2109,11 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, const char *func_name, struct btf_func_model *m); -struct bpf_kfunc_arg_meta { - u64 r0_size; - bool r0_rdonly; - int ref_obj_id; - u32 flags; -}; - struct bpf_reg_state; int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *reg); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1db2b4dc7009..fb146b0ce006 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -603,8 +603,6 @@ int check_ptr_off_reg(struct bpf_verifier_env *env, int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type); -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, diff --git a/include/linux/btf.h b/include/linux/btf.h index 42d8f3730a8d..d5b26380a60f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -338,6 +338,16 @@ static inline bool btf_type_is_struct(const struct btf_type *t) return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } +static inline bool __btf_type_is_struct(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; +} + +static inline bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + static inline u16 btf_type_vlen(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -439,9 +449,10 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id) return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func); } -#ifdef CONFIG_BPF_SYSCALL struct bpf_prog; +struct bpf_verifier_log; +#ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); @@ -455,6 +466,12 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); +const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg); +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) @@ -490,6 +507,18 @@ static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf { return NULL; } +static inline const struct btf_member * +btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) +{ + return NULL; +} +static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + return false; +} #endif static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 91aa9c96621f..4dcda4ae48c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -478,16 +478,6 @@ static bool btf_type_nosize_or_null(const struct btf_type *t) return !t || btf_type_nosize(t); } -static bool __btf_type_is_struct(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; -} - -static bool btf_type_is_array(const struct btf_type *t) -{ - return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; -} - static bool btf_type_is_datasec(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; @@ -5536,7 +5526,7 @@ static u8 bpf_ctx_convert_map[] = { #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE -static const struct btf_member * +const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg) @@ -6322,8 +6312,8 @@ int btf_struct_access(struct bpf_verifier_log *log, * end up with two different module BTFs, but IDs point to the common type in * vmlinux BTF. */ -static bool btf_types_are_same(const struct btf *btf1, u32 id1, - const struct btf *btf2, u32 id2) +bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) { if (id1 != id2) return false; @@ -6605,122 +6595,19 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr return btf_check_func_type_match(log, btf1, t1, btf2, t2); } -static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { -#ifdef CONFIG_NET - [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], - [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], - [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], -#endif -}; - -/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ -static bool __btf_type_is_scalar_struct(struct bpf_verifier_log *log, - const struct btf *btf, - const struct btf_type *t, int rec) -{ - const struct btf_type *member_type; - const struct btf_member *member; - u32 i; - - if (!btf_type_is_struct(t)) - return false; - - for_each_member(i, t, member) { - const struct btf_array *array; - - member_type = btf_type_skip_modifiers(btf, member->type, NULL); - if (btf_type_is_struct(member_type)) { - if (rec >= 3) { - bpf_log(log, "max struct nesting depth exceeded\n"); - return false; - } - if (!__btf_type_is_scalar_struct(log, btf, member_type, rec + 1)) - return false; - continue; - } - if (btf_type_is_array(member_type)) { - array = btf_type_array(member_type); - if (!array->nelems) - return false; - member_type = btf_type_skip_modifiers(btf, array->type, NULL); - if (!btf_type_is_scalar(member_type)) - return false; - continue; - } - if (!btf_type_is_scalar(member_type)) - return false; - } - return true; -} - -static bool is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg) -{ - int len, sfx_len = sizeof("__sz") - 1; - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < sfx_len) - return false; - param_name += len - sfx_len; - if (strncmp(param_name, "__sz", sfx_len)) - return false; - - return true; -} - -static bool btf_is_kfunc_arg_mem_size(const struct btf *btf, - const struct btf_param *arg, - const struct bpf_reg_state *reg, - const char *name) -{ - int len, target_len = strlen(name); - const struct btf_type *t; - const char *param_name; - - t = btf_type_skip_modifiers(btf, arg->type, NULL); - if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) - return false; - - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len != target_len) - return false; - if (strcmp(param_name, name)) - return false; - - return true; -} - static int btf_check_func_arg_match(struct bpf_verifier_env *env, const struct btf *btf, u32 func_id, struct bpf_reg_state *regs, bool ptr_to_mem_ok, - struct bpf_kfunc_arg_meta *kfunc_meta, bool processing_call) { enum bpf_prog_type prog_type = resolve_prog_type(env->prog); - bool rel = false, kptr_get = false, trusted_args = false; - bool sleepable = false; struct bpf_verifier_log *log = &env->log; - u32 i, nargs, ref_id, ref_obj_id = 0; - bool is_kfunc = btf_is_kernel(btf); const char *func_name, *ref_tname; const struct btf_type *t, *ref_t; const struct btf_param *args; - int ref_regno = 0, ret; + u32 i, nargs, ref_id; + int ret; t = btf_type_by_id(btf, func_id); if (!t || !btf_type_is_func(t)) { @@ -6746,14 +6633,6 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - if (is_kfunc && kfunc_meta) { - /* Only kfunc can be release func */ - rel = kfunc_meta->flags & KF_RELEASE; - kptr_get = kfunc_meta->flags & KF_KPTR_GET; - trusted_args = kfunc_meta->flags & KF_TRUSTED_ARGS; - sleepable = kfunc_meta->flags & KF_SLEEPABLE; - } - /* check that BTF function arguments match actual types that the * verifier sees. */ @@ -6761,42 +6640,9 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1; struct bpf_reg_state *reg = ®s[regno]; - bool obj_ptr = false; t = btf_type_skip_modifiers(btf, args[i].type, NULL); if (btf_type_is_scalar(t)) { - if (is_kfunc && kfunc_meta) { - bool is_buf_size = false; - - /* check for any const scalar parameter of name "rdonly_buf_size" - * or "rdwr_buf_size" - */ - if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdonly_buf_size")) { - kfunc_meta->r0_rdonly = true; - is_buf_size = true; - } else if (btf_is_kfunc_arg_mem_size(btf, &args[i], reg, - "rdwr_buf_size")) - is_buf_size = true; - - if (is_buf_size) { - if (kfunc_meta->r0_size) { - bpf_log(log, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); - return -EINVAL; - } - - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "R%d is not a const\n", regno); - return -EINVAL; - } - - kfunc_meta->r0_size = reg->var_off.value; - ret = mark_chain_precision(env, regno); - if (ret) - return ret; - } - } - if (reg->type == SCALAR_VALUE) continue; bpf_log(log, "R%d is not a scalar\n", regno); @@ -6809,88 +6655,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, return -EINVAL; } - /* These register types have special constraints wrt ref_obj_id - * and offset checks. The rest of trusted args don't. - */ - obj_ptr = reg->type == PTR_TO_CTX || reg->type == PTR_TO_BTF_ID || - reg2btf_ids[base_type(reg->type)]; - - /* Check if argument must be a referenced pointer, args + i has - * been verified to be a pointer (after skipping modifiers). - * PTR_TO_CTX is ok without having non-zero ref_obj_id. - */ - if (is_kfunc && trusted_args && (obj_ptr && reg->type != PTR_TO_CTX) && !reg->ref_obj_id) { - bpf_log(log, "R%d must be referenced\n", regno); - return -EINVAL; - } - ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); ref_tname = btf_name_by_offset(btf, ref_t->name_off); - /* Trusted args have the same offset checks as release arguments */ - if ((trusted_args && obj_ptr) || (rel && reg->ref_obj_id)) - arg_type |= OBJ_RELEASE; ret = check_func_arg_reg_off(env, reg, regno, arg_type); if (ret < 0) return ret; - if (is_kfunc && reg->ref_obj_id) { - /* Ensure only one argument is referenced PTR_TO_BTF_ID */ - if (ref_obj_id) { - bpf_log(log, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", - regno, reg->ref_obj_id, ref_obj_id); - return -EFAULT; - } - ref_regno = regno; - ref_obj_id = reg->ref_obj_id; - } - - /* kptr_get is only true for kfunc */ - if (i == 0 && kptr_get) { - struct btf_field *kptr_field; - - if (reg->type != PTR_TO_MAP_VALUE) { - bpf_log(log, "arg#0 expected pointer to map value\n"); - return -EINVAL; - } - - /* check_func_arg_reg_off allows var_off for - * PTR_TO_MAP_VALUE, but we need fixed offset to find - * off_desc. - */ - if (!tnum_is_const(reg->var_off)) { - bpf_log(log, "arg#0 must have constant offset\n"); - return -EINVAL; - } - - kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); - if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { - bpf_log(log, "arg#0 no referenced kptr at map value offset=%llu\n", - reg->off + reg->var_off.value); - return -EINVAL; - } - - if (!btf_type_is_ptr(ref_t)) { - bpf_log(log, "arg#0 BTF type must be a double pointer\n"); - return -EINVAL; - } - - ref_t = btf_type_skip_modifiers(btf, ref_t->type, &ref_id); - ref_tname = btf_name_by_offset(btf, ref_t->name_off); - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - if (!btf_struct_ids_match(log, btf, ref_id, 0, kptr_field->kptr.btf, - kptr_field->kptr.btf_id, true)) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s\n", - func_name, i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } - /* rest of the arguments can be anything, like normal kfunc */ - } else if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { /* If function expects ctx type in BTF check that caller * is passing PTR_TO_CTX. */ @@ -6900,109 +6672,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || - (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { - const struct btf_type *reg_ref_t; - const struct btf *reg_btf; - const char *reg_ref_tname; - u32 reg_ref_id; - - if (!btf_type_is_struct(ref_t)) { - bpf_log(log, "kernel function %s args#%d pointer type %s %s is not supported\n", - func_name, i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (reg->type == PTR_TO_BTF_ID) { - reg_btf = reg->btf; - reg_ref_id = reg->btf_id; - } else { - reg_btf = btf_vmlinux; - reg_ref_id = *reg2btf_ids[base_type(reg->type)]; - } - - reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, - ®_ref_id); - reg_ref_tname = btf_name_by_offset(reg_btf, - reg_ref_t->name_off); - if (!btf_struct_ids_match(log, reg_btf, reg_ref_id, - reg->off, btf, ref_id, - trusted_args || (rel && reg->ref_obj_id))) { - bpf_log(log, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", - func_name, i, - btf_type_str(ref_t), ref_tname, - regno, btf_type_str(reg_ref_t), - reg_ref_tname); - return -EINVAL; - } } else if (ptr_to_mem_ok && processing_call) { const struct btf_type *resolve_ret; u32 type_size; - if (is_kfunc) { - bool arg_mem_size = i + 1 < nargs && is_kfunc_arg_mem_size(btf, &args[i + 1], ®s[regno + 1]); - bool arg_dynptr = btf_type_is_struct(ref_t) && - !strcmp(ref_tname, - stringify_struct(bpf_dynptr_kern)); - - /* Permit pointer to mem, but only when argument - * type is pointer to scalar, or struct composed - * (recursively) of scalars. - * When arg_mem_size is true, the pointer can be - * void *. - * Also permit initialized local dynamic pointers. - */ - if (!btf_type_is_scalar(ref_t) && - !__btf_type_is_scalar_struct(log, btf, ref_t, 0) && - !arg_dynptr && - (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { - bpf_log(log, - "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", - i, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); - return -EINVAL; - } - - if (arg_dynptr) { - if (reg->type != PTR_TO_STACK) { - bpf_log(log, "arg#%d pointer type %s %s not to stack\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_reg_valid_init(env, reg)) { - bpf_log(log, - "arg#%d pointer type %s %s must be valid and initialized\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - if (!is_dynptr_type_expected(env, reg, - ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { - bpf_log(log, - "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", - i, btf_type_str(ref_t), - ref_tname); - return -EINVAL; - } - - continue; - } - - /* Check for mem, len pair */ - if (arg_mem_size) { - if (check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1)) { - bpf_log(log, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", - i, i + 1); - return -EINVAL; - } - i++; - continue; - } - } - resolve_ret = btf_resolve_size(btf, ref_t, &type_size); if (IS_ERR(resolve_ret)) { bpf_log(log, @@ -7015,36 +6688,13 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, if (check_mem_reg(env, reg, regno, type_size)) return -EINVAL; } else { - bpf_log(log, "reg type unsupported for arg#%d %sfunction %s#%d\n", i, - is_kfunc ? "kernel " : "", func_name, func_id); + bpf_log(log, "reg type unsupported for arg#%d function %s#%d\n", i, + func_name, func_id); return -EINVAL; } } - /* Either both are set, or neither */ - WARN_ON_ONCE((ref_obj_id && !ref_regno) || (!ref_obj_id && ref_regno)); - /* We already made sure ref_obj_id is set only for one argument. We do - * allow (!rel && ref_obj_id), so that passing such referenced - * PTR_TO_BTF_ID to other kfuncs works. Note that rel is only true when - * is_kfunc is true. - */ - if (rel && !ref_obj_id) { - bpf_log(log, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", - func_name); - return -EINVAL; - } - - if (sleepable && !env->prog->aux->sleepable) { - bpf_log(log, "kernel function %s is sleepable but the program is not\n", - func_name); - return -EINVAL; - } - - if (kfunc_meta && ref_obj_id) - kfunc_meta->ref_obj_id = ref_obj_id; - - /* returns argument register number > 0 in case of reference release kfunc */ - return rel ? ref_regno : 0; + return 0; } /* Compare BTF of a function declaration with given bpf_reg_state. @@ -7074,7 +6724,7 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, false); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, false); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -7117,7 +6767,7 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return -EINVAL; is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; - err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, NULL, true); + err = btf_check_func_arg_match(env, btf, btf_id, regs, is_global, true); /* Compiler optimizations can remove arguments from static functions * or mismatched type can be passed into a global function. @@ -7128,14 +6778,6 @@ int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, return err; } -int btf_check_kfunc_arg_match(struct bpf_verifier_env *env, - const struct btf *btf, u32 func_id, - struct bpf_reg_state *regs, - struct bpf_kfunc_arg_meta *meta) -{ - return btf_check_func_arg_match(env, btf, func_id, regs, true, meta, true); -} - /* Convert BTF of a function into bpf_reg_state if possible * Returns: * EFAULT - there is a verifier bug. Abort verification. diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8f3abe9b08e..7d7a91c54709 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5550,8 +5550,8 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, return err; } -int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, - u32 regno) +static int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + u32 regno) { struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); @@ -7863,19 +7863,517 @@ static void mark_btf_func_reg_size(struct bpf_verifier_env *env, u32 regno, } } +struct bpf_kfunc_call_arg_meta { + /* In parameters */ + struct btf *btf; + u32 func_id; + u32 kfunc_flags; + const struct btf_type *func_proto; + const char *func_name; + /* Out parameters */ + u32 ref_obj_id; + u8 release_regno; + bool r0_rdonly; + u64 r0_size; +}; + +static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_ACQUIRE; +} + +static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RET_NULL; +} + +static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RELEASE; +} + +static bool is_kfunc_trusted_args(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_TRUSTED_ARGS; +} + +static bool is_kfunc_sleepable(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_SLEEPABLE; +} + +static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_DESTRUCTIVE; +} + +static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) +{ + return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); +} + +static bool is_kfunc_arg_mem_size(const struct btf *btf, + const struct btf_param *arg, + const struct bpf_reg_state *reg) +{ + int len, sfx_len = sizeof("__sz") - 1; + const struct btf_type *t; + const char *param_name; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) + return false; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len < sfx_len) + return false; + param_name += len - sfx_len; + if (strncmp(param_name, "__sz", sfx_len)) + return false; + + return true; +} + +static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, + const struct btf_param *arg, + const char *name) +{ + int len, target_len = strlen(name); + const char *param_name; + + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len != target_len) + return false; + if (strcmp(param_name, name)) + return false; + + return true; +} + +enum { + KF_ARG_DYNPTR_ID, +}; + +BTF_ID_LIST(kf_arg_btf_ids) +BTF_ID(struct, bpf_dynptr_kern) + +static bool is_kfunc_arg_dynptr(const struct btf *btf, + const struct btf_param *arg) +{ + const struct btf_type *t; + u32 res_id; + + t = btf_type_skip_modifiers(btf, arg->type, NULL); + if (!t) + return false; + if (!btf_type_is_ptr(t)) + return false; + t = btf_type_skip_modifiers(btf, t->type, &res_id); + if (!t) + return false; + return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[KF_ARG_DYNPTR_ID]); +} + +/* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ +static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, + const struct btf *btf, + const struct btf_type *t, int rec) +{ + const struct btf_type *member_type; + const struct btf_member *member; + u32 i; + + if (!btf_type_is_struct(t)) + return false; + + for_each_member(i, t, member) { + const struct btf_array *array; + + member_type = btf_type_skip_modifiers(btf, member->type, NULL); + if (btf_type_is_struct(member_type)) { + if (rec >= 3) { + verbose(env, "max struct nesting depth exceeded\n"); + return false; + } + if (!__btf_type_is_scalar_struct(env, btf, member_type, rec + 1)) + return false; + continue; + } + if (btf_type_is_array(member_type)) { + array = btf_array(member_type); + if (!array->nelems) + return false; + member_type = btf_type_skip_modifiers(btf, array->type, NULL); + if (!btf_type_is_scalar(member_type)) + return false; + continue; + } + if (!btf_type_is_scalar(member_type)) + return false; + } + return true; +} + + +static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = { +#ifdef CONFIG_NET + [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK], + [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], + [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP], +#endif +}; + +enum kfunc_ptr_arg_type { + KF_ARG_PTR_TO_CTX, + KF_ARG_PTR_TO_KPTR, /* PTR_TO_KPTR but type specific */ + KF_ARG_PTR_TO_DYNPTR, + KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ + KF_ARG_PTR_TO_MEM, + KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ +}; + +static enum kfunc_ptr_arg_type +get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, + const struct btf_type *t, const struct btf_type *ref_t, + const char *ref_tname, const struct btf_param *args, + int argno, int nargs) +{ + u32 regno = argno + 1; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + bool arg_mem_size = false; + + /* In this function, we verify the kfunc's BTF as per the argument type, + * leaving the rest of the verification with respect to the register + * type to our caller. When a set of conditions hold in the BTF type of + * arguments, we resolve it to a known kfunc_ptr_arg_type. + */ + if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + return KF_ARG_PTR_TO_CTX; + + if (is_kfunc_arg_kptr_get(meta, argno)) { + if (!btf_type_is_ptr(ref_t)) { + verbose(env, "arg#0 BTF type must be a double pointer for kptr_get kfunc\n"); + return -EINVAL; + } + ref_t = btf_type_by_id(meta->btf, ref_t->type); + ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off); + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#0 pointer type %s %s is not supported\n", + meta->func_name, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_KPTR; + } + + if (is_kfunc_arg_dynptr(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_DYNPTR; + + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { + if (!btf_type_is_struct(ref_t)) { + verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return KF_ARG_PTR_TO_BTF_ID; + } + + if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) + arg_mem_size = true; + + /* This is the catch all argument type of register types supported by + * check_helper_mem_access. However, we only allow when argument type is + * pointer to scalar, or struct composed (recursively) of scalars. When + * arg_mem_size is true, the pointer can be void *. + */ + if (!btf_type_is_scalar(ref_t) && !__btf_type_is_scalar_struct(env, meta->btf, ref_t, 0) && + (arg_mem_size ? !btf_type_is_void(ref_t) : 1)) { + verbose(env, "arg#%d pointer type %s %s must point to %sscalar, or struct with scalar\n", + argno, btf_type_str(ref_t), ref_tname, arg_mem_size ? "void, " : ""); + return -EINVAL; + } + return arg_mem_size ? KF_ARG_PTR_TO_MEM_SIZE : KF_ARG_PTR_TO_MEM; +} + +static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, u32 ref_id, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + const struct btf_type *reg_ref_t; + bool strict_type_match = false; + const struct btf *reg_btf; + const char *reg_ref_tname; + u32 reg_ref_id; + + if (reg->type == PTR_TO_BTF_ID) { + reg_btf = reg->btf; + reg_ref_id = reg->btf_id; + } else { + reg_btf = btf_vmlinux; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; + } + + if (is_kfunc_trusted_args(meta) || (is_kfunc_release(meta) && reg->ref_obj_id)) + strict_type_match = true; + + reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); + reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); + if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s but R%d has a pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname, argno + 1, + btf_type_str(reg_ref_t), reg_ref_tname); + return -EINVAL; + } + return 0; +} + +static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + const struct btf_type *ref_t, + const char *ref_tname, + struct bpf_kfunc_call_arg_meta *meta, + int argno) +{ + struct btf_field *kptr_field; + + /* check_func_arg_reg_off allows var_off for + * PTR_TO_MAP_VALUE, but we need fixed offset to find + * off_desc. + */ + if (!tnum_is_const(reg->var_off)) { + verbose(env, "arg#0 must have constant offset\n"); + return -EINVAL; + } + + kptr_field = btf_record_find(reg->map_ptr->record, reg->off + reg->var_off.value, BPF_KPTR); + if (!kptr_field || kptr_field->type != BPF_KPTR_REF) { + verbose(env, "arg#0 no referenced kptr at map value offset=%llu\n", + reg->off + reg->var_off.value); + return -EINVAL; + } + + if (!btf_struct_ids_match(&env->log, meta->btf, ref_t->type, 0, kptr_field->kptr.btf, + kptr_field->kptr.btf_id, true)) { + verbose(env, "kernel function %s args#%d expected pointer to %s %s\n", + meta->func_name, argno, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + return 0; +} + +static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) +{ + const char *func_name = meta->func_name, *ref_tname; + const struct btf *btf = meta->btf; + const struct btf_param *args; + u32 i, nargs; + int ret; + + args = (const struct btf_param *)(meta->func_proto + 1); + nargs = btf_type_vlen(meta->func_proto); + if (nargs > MAX_BPF_FUNC_REG_ARGS) { + verbose(env, "Function %s has %d > %d args\n", func_name, nargs, + MAX_BPF_FUNC_REG_ARGS); + return -EINVAL; + } + + /* Check that BTF function arguments match actual types that the + * verifier sees. + */ + for (i = 0; i < nargs; i++) { + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[i + 1]; + const struct btf_type *t, *ref_t, *resolve_ret; + enum bpf_arg_type arg_type = ARG_DONTCARE; + u32 regno = i + 1, ref_id, type_size; + bool is_ret_buf_sz = false; + int kf_arg_type; + + t = btf_type_skip_modifiers(btf, args[i].type, NULL); + if (btf_type_is_scalar(t)) { + if (reg->type != SCALAR_VALUE) { + verbose(env, "R%d is not a scalar\n", regno); + return -EINVAL; + } + if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdonly_buf_size")) { + meta->r0_rdonly = true; + is_ret_buf_sz = true; + } else if (is_kfunc_arg_scalar_with_name(btf, &args[i], "rdwr_buf_size")) { + is_ret_buf_sz = true; + } + + if (is_ret_buf_sz) { + if (meta->r0_size) { + verbose(env, "2 or more rdonly/rdwr_buf_size parameters for kfunc"); + return -EINVAL; + } + + if (!tnum_is_const(reg->var_off)) { + verbose(env, "R%d is not a const\n", regno); + return -EINVAL; + } + + meta->r0_size = reg->var_off.value; + ret = mark_chain_precision(env, regno); + if (ret) + return ret; + } + continue; + } + + if (!btf_type_is_ptr(t)) { + verbose(env, "Unrecognized arg#%d type %s\n", i, btf_type_str(t)); + return -EINVAL; + } + + if (reg->ref_obj_id) { + if (is_kfunc_release(meta) && meta->ref_obj_id) { + verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", + regno, reg->ref_obj_id, + meta->ref_obj_id); + return -EFAULT; + } + meta->ref_obj_id = reg->ref_obj_id; + if (is_kfunc_release(meta)) + meta->release_regno = regno; + } + + ref_t = btf_type_skip_modifiers(btf, t->type, &ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + + kf_arg_type = get_kfunc_ptr_arg_type(env, meta, t, ref_t, ref_tname, args, i, nargs); + if (kf_arg_type < 0) + return kf_arg_type; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_BTF_ID: + if (!is_kfunc_trusted_args(meta)) + break; + if (!reg->ref_obj_id) { + verbose(env, "R%d must be referenced\n", regno); + return -EINVAL; + } + fallthrough; + case KF_ARG_PTR_TO_CTX: + /* Trusted arguments have the same offset checks as release arguments */ + arg_type |= OBJ_RELEASE; + break; + case KF_ARG_PTR_TO_KPTR: + case KF_ARG_PTR_TO_DYNPTR: + case KF_ARG_PTR_TO_MEM: + case KF_ARG_PTR_TO_MEM_SIZE: + /* Trusted by default */ + break; + default: + WARN_ON_ONCE(1); + return -EFAULT; + } + + if (is_kfunc_release(meta) && reg->ref_obj_id) + arg_type |= OBJ_RELEASE; + ret = check_func_arg_reg_off(env, reg, regno, arg_type); + if (ret < 0) + return ret; + + switch (kf_arg_type) { + case KF_ARG_PTR_TO_CTX: + if (reg->type != PTR_TO_CTX) { + verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_KPTR: + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "arg#0 expected pointer to map value\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_kptr(env, reg, ref_t, ref_tname, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_DYNPTR: + if (reg->type != PTR_TO_STACK) { + verbose(env, "arg#%d expected pointer to stack\n", i); + return -EINVAL; + } + + if (!is_dynptr_reg_valid_init(env, reg)) { + verbose(env, "arg#%d pointer type %s %s must be valid and initialized\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + + if (!is_dynptr_type_expected(env, reg, ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { + verbose(env, "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", + i, btf_type_str(ref_t), ref_tname); + return -EINVAL; + } + break; + case KF_ARG_PTR_TO_BTF_ID: + /* Only base_type is checked, further checks are done here */ + if (reg->type != PTR_TO_BTF_ID && + (!reg2btf_ids[base_type(reg->type)] || type_flag(reg->type))) { + verbose(env, "arg#%d expected pointer to btf or socket\n", i); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM: + resolve_ret = btf_resolve_size(btf, ref_t, &type_size); + if (IS_ERR(resolve_ret)) { + verbose(env, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", + i, btf_type_str(ref_t), ref_tname, PTR_ERR(resolve_ret)); + return -EINVAL; + } + ret = check_mem_reg(env, reg, regno, type_size); + if (ret < 0) + return ret; + break; + case KF_ARG_PTR_TO_MEM_SIZE: + ret = check_kfunc_mem_size_reg(env, ®s[regno + 1], regno + 1); + if (ret < 0) { + verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1); + return ret; + } + /* Skip next '__sz' argument */ + i++; + break; + } + } + + if (is_kfunc_release(meta) && !meta->release_regno) { + verbose(env, "release kernel function %s expects refcounted PTR_TO_BTF_ID\n", + func_name); + return -EINVAL; + } + + return 0; +} + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); - struct bpf_kfunc_arg_meta meta = { 0 }; const char *func_name, *ptr_type_name; + struct bpf_kfunc_call_arg_meta meta; u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; const struct btf_param *args; struct btf *desc_btf; u32 *kfunc_flags; - bool acq; /* skip for now, but return error when we find this in fixup_kfunc_call */ if (!insn->imm) @@ -7896,24 +8394,34 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, func_name); return -EACCES; } - if (*kfunc_flags & KF_DESTRUCTIVE && !capable(CAP_SYS_BOOT)) { - verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capabilities\n"); + + /* Prepare kfunc call metadata */ + memset(&meta, 0, sizeof(meta)); + meta.btf = desc_btf; + meta.func_id = func_id; + meta.kfunc_flags = *kfunc_flags; + meta.func_proto = func_proto; + meta.func_name = func_name; + + if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) { + verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n"); return -EACCES; } - acq = *kfunc_flags & KF_ACQUIRE; - - meta.flags = *kfunc_flags; + if (is_kfunc_sleepable(&meta) && !env->prog->aux->sleepable) { + verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); + return -EACCES; + } /* Check the arguments */ - err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs, &meta); + err = check_kfunc_args(env, &meta); if (err < 0) return err; /* In case of release function, we get register number of refcounted - * PTR_TO_BTF_ID back from btf_check_kfunc_arg_match, do the release now + * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ - if (err) { - err = release_reference(env, regs[err].ref_obj_id); + if (meta.release_regno) { + err = release_reference(env, regs[meta.release_regno].ref_obj_id); if (err) { verbose(env, "kfunc %s#%d reference has not been acquired before\n", func_name, func_id); @@ -7927,7 +8435,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* Check return type */ t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); - if (acq && !btf_type_is_struct_ptr(desc_btf, t)) { + if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); return -EINVAL; } @@ -7966,20 +8474,23 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } - if (*kfunc_flags & KF_RET_NULL) { + if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ regs[BPF_REG_0].id = ++env->id_gen; } mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); - if (acq) { + if (is_kfunc_acquire(&meta)) { int id = acquire_reference_state(env, insn_idx); if (id < 0) return id; - regs[BPF_REG_0].id = id; + if (is_kfunc_ret_null(&meta)) + regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; } + if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) + regs[BPF_REG_0].id = ++env->id_gen; } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ nargs = btf_type_vlen(func_proto); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index c210657d4d0a..55d641c1f126 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -22,7 +22,7 @@ static struct { "arg#0 pointer type STRUCT bpf_dynptr_kern points to unsupported dynamic pointer type", 0}, {"not_valid_dynptr", "arg#0 pointer type STRUCT bpf_dynptr_kern must be valid and initialized", 0}, - {"not_ptr_to_stack", "arg#0 pointer type STRUCT bpf_dynptr_kern not to stack", 0}, + {"not_ptr_to_stack", "arg#0 expected pointer to stack", 0}, {"dynptr_data_null", NULL, -EBADMSG}, }; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index e1a937277b54..86d6fef2e3b4 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -109,7 +109,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "arg#0 pointer type STRUCT prog_test_ref_kfunc must point", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 3 }, { "bpf_kfunc_call_test_release", 5 }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index fd683a32a276..55cba01c99d5 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -142,7 +142,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_user_key", 2 }, { "bpf_key_put", 4 }, @@ -163,7 +163,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar", + .errstr = "arg#0 expected pointer to btf or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_system_key", 1 }, { "bpf_key_put", 3 }, -- cgit v1.2.3 From 958cf2e273f0929c66169e0788031310e8118722 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:03 +0530 Subject: bpf: Introduce bpf_obj_new Introduce type safe memory allocator bpf_obj_new for BPF programs. The kernel side kfunc is named bpf_obj_new_impl, as passing hidden arguments to kfuncs still requires having them in prototype, unlike BPF helpers which always take 5 arguments and have them checked using bpf_func_proto in verifier, ignoring unset argument types. Introduce __ign suffix to ignore a specific kfunc argument during type checks, then use this to introduce support for passing type metadata to the bpf_obj_new_impl kfunc. The user passes BTF ID of the type it wants to allocates in program BTF, the verifier then rewrites the first argument as the size of this type, after performing some sanity checks (to ensure it exists and it is a struct type). The second argument is also fixed up and passed by the verifier. This is the btf_struct_meta for the type being allocated. It would be needed mostly for the offset array which is required for zero initializing special fields while leaving the rest of storage in unitialized state. It would also be needed in the next patch to perform proper destruction of the object's special fields. Under the hood, bpf_obj_new will call bpf_mem_alloc and bpf_mem_free, using the any context BPF memory allocator introduced recently. To this end, a global instance of the BPF memory allocator is initialized on boot to be used for this purpose. This 'bpf_global_ma' serves all allocations for bpf_obj_new. In the future, bpf_obj_new variants will allow specifying a custom allocator. Note that now that bpf_obj_new can be used to allocate objects that can be linked to BPF linked list (when future linked list helpers are available), we need to also free the elements using bpf_mem_free. However, since the draining of elements is done outside the bpf_spin_lock, we need to do migrate_disable around the call since bpf_list_head_free can be called from map free path where migration is enabled. Otherwise, when called from BPF programs migration is already disabled. A convenience macro is included in the bpf_experimental.h header to hide over the ugly details of the implementation, leading to user code looking similar to a language level extension which allocates and constructs fields of a user type. struct bar { struct bpf_list_node node; }; struct foo { struct bpf_spin_lock lock; struct bpf_list_head head __contains(bar, node); }; void prog(void) { struct foo *f; f = bpf_obj_new(typeof(*f)); if (!f) return; ... } A key piece of this story is still missing, i.e. the free function, which will come in the next patch. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-14-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 21 +++-- include/linux/bpf_verifier.h | 2 + kernel/bpf/core.c | 16 ++++ kernel/bpf/helpers.c | 47 ++++++++++-- kernel/bpf/verifier.c | 102 +++++++++++++++++++++++-- tools/testing/selftests/bpf/bpf_experimental.h | 25 ++++++ 6 files changed, 190 insertions(+), 23 deletions(-) create mode 100644 tools/testing/selftests/bpf/bpf_experimental.h (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0a74df731eb8..8b32376ce746 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -54,6 +54,8 @@ struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; +extern struct bpf_mem_alloc bpf_global_ma; +extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, @@ -334,16 +336,19 @@ static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_f return rec->field_mask & type; } -static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +static inline void bpf_obj_init(const struct btf_field_offs *foffs, void *obj) { - if (!IS_ERR_OR_NULL(map->record)) { - struct btf_field *fields = map->record->fields; - u32 cnt = map->record->cnt; - int i; + int i; - for (i = 0; i < cnt; i++) - memset(dst + fields[i].offset, 0, btf_field_type_size(fields[i].type)); - } + if (!foffs) + return; + for (i = 0; i < foffs->cnt; i++) + memset(obj + foffs->field_off[i], 0, foffs->field_sz[i]); +} + +static inline void check_and_init_map_value(struct bpf_map *map, void *dst) +{ + bpf_obj_init(map->field_offs, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index fb146b0ce006..3dc72d396dfc 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -433,6 +433,8 @@ struct bpf_insn_aux_data { */ struct bpf_loop_inline_state loop_inline_state; }; + u64 obj_new_size; /* remember the size of type passed to bpf_obj_new to rewrite R1 */ + struct btf_struct_meta *kptr_struct_meta; u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9c16338bcbe8..2e57fc839a5c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -60,6 +61,9 @@ #define CTX regs[BPF_REG_CTX] #define IMM insn->imm +struct bpf_mem_alloc bpf_global_ma; +bool bpf_global_ma_set; + /* No hurry in this branch * * Exported for the bpf jit load helper. @@ -2746,6 +2750,18 @@ int __weak bpf_arch_text_invalidate(void *dst, size_t len) return -ENOTSUPP; } +#ifdef CONFIG_BPF_SYSCALL +static int __init bpf_global_ma_init(void) +{ + int ret; + + ret = bpf_mem_alloc_init(&bpf_global_ma, 0, false); + bpf_global_ma_set = !ret; + return ret; +} +late_initcall(bpf_global_ma_init); +#endif + DEFINE_STATIC_KEY_FALSE(bpf_stats_enabled_key); EXPORT_SYMBOL(bpf_stats_enabled_key); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 5bc0b9f0f306..c4f1c22cc44c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "../../lib/kstrtox.h" @@ -1735,25 +1736,57 @@ unlock: obj -= field->list_head.node_offset; head = head->next; - /* TODO: Rework later */ - kfree(obj); + /* The contained type can also have resources, including a + * bpf_list_head which needs to be freed. + */ + bpf_obj_free_fields(field->list_head.value_rec, obj); + /* bpf_mem_free requires migrate_disable(), since we can be + * called from map free path as well apart from BPF program (as + * part of map ops doing bpf_obj_free_fields). + */ + migrate_disable(); + bpf_mem_free(&bpf_global_ma, obj); + migrate_enable(); } } -BTF_SET8_START(tracing_btf_ids) +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +{ + struct btf_struct_meta *meta = meta__ign; + u64 size = local_type_id__k; + void *p; + + if (unlikely(!bpf_global_ma_set)) + return NULL; + p = bpf_mem_alloc(&bpf_global_ma, size); + if (!p) + return NULL; + if (meta) + bpf_obj_init(meta->field_offs, p); + return p; +} + +__diag_pop(); + +BTF_SET8_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif -BTF_SET8_END(tracing_btf_ids) +BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL) +BTF_SET8_END(generic_btf_ids) -static const struct btf_kfunc_id_set tracing_kfunc_set = { +static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, - .set = &tracing_btf_ids, + .set = &generic_btf_ids, }; static int __init kfunc_init(void) { - return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &tracing_kfunc_set); + return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &generic_kfunc_set); } late_initcall(kfunc_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c8fcc2808d99..804f3bca6c08 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7952,6 +7952,11 @@ static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param return __kfunc_param_match_suffix(btf, arg, "__k"); } +static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__ign"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -8214,6 +8219,10 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); + + if (is_kfunc_arg_ignore(btf, &args[i])) + continue; + if (btf_type_is_scalar(t)) { if (reg->type != SCALAR_VALUE) { verbose(env, "R%d is not a scalar\n", regno); @@ -8391,6 +8400,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return 0; } +enum special_kfunc_type { + KF_bpf_obj_new_impl, +}; + +BTF_SET_START(special_kfunc_set) +BTF_ID(func, bpf_obj_new_impl) +BTF_SET_END(special_kfunc_set) + +BTF_ID_LIST(special_kfunc_list) +BTF_ID(func, bpf_obj_new_impl) + static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { @@ -8465,17 +8485,59 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) { - verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); - return -EINVAL; + /* Only exception is bpf_obj_new_impl */ + if (meta.btf != btf_vmlinux || meta.func_id != special_kfunc_list[KF_bpf_obj_new_impl]) { + verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n"); + return -EINVAL; + } } if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { - ptr_type = btf_type_skip_modifiers(desc_btf, t->type, - &ptr_type_id); - if (!btf_type_is_struct(ptr_type)) { + ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); + + if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) { + if (meta.func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + const struct btf_type *ret_t; + struct btf *ret_btf; + u32 ret_btf_id; + + if (((u64)(u32)meta.arg_constant.value) != meta.arg_constant.value) { + verbose(env, "local type ID argument must be in range [0, U32_MAX]\n"); + return -EINVAL; + } + + ret_btf = env->prog->aux->btf; + ret_btf_id = meta.arg_constant.value; + + /* This may be NULL due to user not supplying a BTF */ + if (!ret_btf) { + verbose(env, "bpf_obj_new requires prog BTF\n"); + return -EINVAL; + } + + ret_t = btf_type_by_id(ret_btf, ret_btf_id); + if (!ret_t || !__btf_type_is_struct(ret_t)) { + verbose(env, "bpf_obj_new type ID argument must be of a struct\n"); + return -EINVAL; + } + + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[BPF_REG_0].btf = ret_btf; + regs[BPF_REG_0].btf_id = ret_btf_id; + + env->insn_aux_data[insn_idx].obj_new_size = ret_t->size; + env->insn_aux_data[insn_idx].kptr_struct_meta = + btf_find_struct_meta(ret_btf, ret_btf_id); + } else { + verbose(env, "kernel function %s unhandled dynamic return type\n", + meta.func_name); + return -EFAULT; + } + } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); @@ -8503,6 +8565,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; } + if (is_kfunc_ret_null(&meta)) { regs[BPF_REG_0].type |= PTR_MAYBE_NULL; /* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */ @@ -14671,8 +14734,8 @@ static int fixup_call_args(struct bpf_verifier_env *env) return err; } -static int fixup_kfunc_call(struct bpf_verifier_env *env, - struct bpf_insn *insn) +static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + struct bpf_insn *insn_buf, int insn_idx, int *cnt) { const struct bpf_kfunc_desc *desc; @@ -14691,8 +14754,21 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, return -EFAULT; } + *cnt = 0; insn->imm = desc->imm; + if (insn->off) + return 0; + if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) { + struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta; + struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) }; + u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size; + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size); + insn_buf[1] = addr[0]; + insn_buf[2] = addr[1]; + insn_buf[3] = *insn; + *cnt = 4; + } return 0; } @@ -14834,9 +14910,19 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->src_reg == BPF_PSEUDO_CALL) continue; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { - ret = fixup_kfunc_call(env, insn); + ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; + if (cnt == 0) + continue; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; continue; } diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h new file mode 100644 index 000000000000..aeb6a7fcb7c4 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -0,0 +1,25 @@ +#ifndef __BPF_EXPERIMENTAL__ +#define __BPF_EXPERIMENTAL__ + +#include +#include +#include +#include + +/* Description + * Allocates an object of the type represented by 'local_type_id' in + * program BTF. User may use the bpf_core_type_id_local macro to pass the + * type ID of a struct in program BTF. + * + * The 'local_type_id' parameter must be a known constant. + * The 'meta' parameter is a hidden argument that is ignored. + * Returns + * A pointer to an object of the type corresponding to the passed in + * 'local_type_id', or NULL on failure. + */ +extern void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym; + +/* Convenience macro to wrap over bpf_obj_new_impl */ +#define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) + +#endif -- cgit v1.2.3 From 534e86bc6c66e1e0c798a1c0a6a680bb231c08db Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 18 Nov 2022 07:26:07 +0530 Subject: bpf: Add 'release on unlock' logic for bpf_list_push_{front,back} This commit implements the delayed release logic for bpf_list_push_front and bpf_list_push_back. Once a node has been added to the list, it's pointer changes to PTR_UNTRUSTED. However, it is only released once the lock protecting the list is unlocked. For such PTR_TO_BTF_ID | MEM_ALLOC with PTR_UNTRUSTED set but an active ref_obj_id, it is still permitted to read them as long as the lock is held. Writing to them is not allowed. This allows having read access to push items we no longer own until we release the lock guarding the list, allowing a little more flexibility when working with these APIs. Note that enabling write support has fairly tricky interactions with what happens inside the critical section. Just as an example, currently, bpf_obj_drop is not permitted, but if it were, being able to write to the PTR_UNTRUSTED pointer while the object gets released back to the memory allocator would violate safety properties we wish to guarantee (i.e. not crashing the kernel). The memory could be reused for a different type in the BPF program or even in the kernel as it gets eventually kfree'd. Not enabling bpf_obj_drop inside the critical section would appear to prevent all of the above, but that is more of an artifical limitation right now. Since the write support is tangled with how we handle potential aliasing of nodes inside the critical section that may or may not be part of the list anymore, it has been deferred to a future patch. Acked-by: Dave Marchevsky Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221118015614.2013203-18-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 5 ++++ kernel/bpf/verifier.c | 58 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3dc72d396dfc..23f30c685f28 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -223,6 +223,11 @@ struct bpf_reference_state { * exiting a callback function. */ int callback_ref; + /* Mark the reference state to release the registers sharing the same id + * on bpf_spin_unlock (for nodes that we will lose ownership to but are + * safe to access inside the critical section). + */ + bool release_on_unlock; }; /* state of the program: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1364df74129e..195d24316750 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5652,7 +5652,9 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, cur->active_lock.ptr = btf; cur->active_lock.id = reg->id; } else { + struct bpf_func_state *fstate = cur_func(env); void *ptr; + int i; if (map) ptr = map; @@ -5670,6 +5672,23 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, } cur->active_lock.ptr = NULL; cur->active_lock.id = 0; + + for (i = 0; i < fstate->acquired_refs; i++) { + int err; + + /* Complain on error because this reference state cannot + * be freed before this point, as bpf_spin_lock critical + * section does not allow functions that release the + * allocated object immediately. + */ + if (!fstate->refs[i].release_on_unlock) + continue; + err = release_reference(env, fstate->refs[i].id); + if (err) { + verbose(env, "failed to release release_on_unlock reference"); + return err; + } + } } return 0; } @@ -8260,6 +8279,42 @@ static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, return 0; } +static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_id) +{ + struct bpf_func_state *state = cur_func(env); + struct bpf_reg_state *reg; + int i; + + /* bpf_spin_lock only allows calling list_push and list_pop, no BPF + * subprogs, no global functions. This means that the references would + * not be released inside the critical section but they may be added to + * the reference state, and the acquired_refs are never copied out for a + * different frame as BPF to BPF calls don't work in bpf_spin_lock + * critical sections. + */ + if (!ref_obj_id) { + verbose(env, "verifier internal error: ref_obj_id is zero for release_on_unlock\n"); + return -EFAULT; + } + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ref_obj_id) { + if (state->refs[i].release_on_unlock) { + verbose(env, "verifier internal error: expected false release_on_unlock"); + return -EFAULT; + } + state->refs[i].release_on_unlock = true; + /* Now mark everyone sharing same ref_obj_id as untrusted */ + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->ref_obj_id == ref_obj_id) + reg->type |= PTR_UNTRUSTED; + })); + return 0; + } + } + verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); + return -EFAULT; +} + /* Implementation details: * * Each register points to some region of memory, which we define as an @@ -8433,7 +8488,8 @@ static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, btf_name_by_offset(field->list_head.btf, et->name_off)); return -EINVAL; } - return 0; + /* Set arg#1 for expiration after unlock */ + return ref_set_release_on_unlock(env, reg->ref_obj_id); } static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) -- cgit v1.2.3 From f20a0a0519f35a3a34236ed2d38b067c5cb22b9f Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Nov 2022 02:18:28 +0900 Subject: ethtool: doc: clarify what drivers can implement in their get_drvinfo() Many of the drivers which implement ethtool_ops::get_drvinfo() will prints the .driver, .version or .bus_info of struct ethtool_drvinfo. To have a glance of current state, do: $ git grep -W "get_drvinfo(struct" Printing in those three fields is useless because: - since [1], the driver version should be the kernel version (at least for upstream drivers). Arguably, out of tree drivers might still want to set a custom version, but out of tree is not our focus. - since [2], the core is able to provide default values for .driver and .bus_info. In summary, drivers may provide .fw_version and .erom_version, the rest is expected to be done by the core. In struct ethtool_ops doc from linux/ethtool: rephrase field get_drvinfo() doc to discourage developers from implementing this callback. In struct ethtool_drvinfo doc from uapi/linux/ethtool.h: remove the paragraph mentioning what drivers should do. Rationale: no need to repeat what is already written in struct ethtool_ops doc. But add a note that .fw_version and .erom_version are driver defined. Also update the dummy driver and simply remove the callback in order not to confuse the newcomers: most of the drivers will not need this callback function any more. [1] commit 6a7e25c7fb48 ("net/core: Replace driver version to be kernel version") Link: https://git.kernel.org/torvalds/linux/c/6a7e25c7fb48 [2] commit edaf5df22cb8 ("ethtool: ethtool_get_drvinfo: populate drvinfo fields even if callback exits") Link: https://git.kernel.org/netdev/net-next/c/edaf5df22cb8 Reviewed-by: Leon Romanovsky Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20221116171828.4093-1-mailhol.vincent@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/dummy.c | 7 ------- include/linux/ethtool.h | 8 ++++---- include/uapi/linux/ethtool.h | 10 ++++------ 3 files changed, 8 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index aa0fc00faecb..c4b1b0aa438a 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -99,14 +99,7 @@ static const struct net_device_ops dummy_netdev_ops = { .ndo_change_carrier = dummy_change_carrier, }; -static void dummy_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) -{ - strscpy(info->driver, DRV_NAME, sizeof(info->driver)); -} - static const struct ethtool_ops dummy_ethtool_ops = { - .get_drvinfo = dummy_get_drvinfo, .get_ts_info = ethtool_op_get_ts_info, }; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 5c51c7fda32a..9e0a76fc7de9 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -473,10 +473,10 @@ struct ethtool_module_power_mode_params { * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. - * @get_drvinfo: Report driver/device information. Should only set the - * @driver, @version, @fw_version and @bus_info fields. If not - * implemented, the @driver and @bus_info fields will be filled in - * according to the netdev's parent device. + * @get_drvinfo: Report driver/device information. Modern drivers no + * longer have to implement this callback. Most fields are + * correctly filled in by the core using system information, or + * populated using other driver operations. * @get_regs_len: Get buffer length required for @get_regs * @get_regs: Get device registers * @get_wol: Report whether Wake-on-Lan is enabled diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f341de2ae612..58e587ba0450 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -159,8 +159,10 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * in its bus driver structure (e.g. pci_driver::name). Must * not be an empty string. * @version: Driver version string; may be an empty string - * @fw_version: Firmware version string; may be an empty string - * @erom_version: Expansion ROM version string; may be an empty string + * @fw_version: Firmware version string; driver defined; may be an + * empty string + * @erom_version: Expansion ROM version string; driver defined; may be + * an empty string * @bus_info: Device bus address. This should match the dev_name() * string for the underlying bus device, if there is one. May be * an empty string. @@ -179,10 +181,6 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * * Users can use the %ETHTOOL_GSSET_INFO command to get the number of * strings in any string set (from Linux 2.6.34). - * - * Drivers should set at most @driver, @version, @fw_version and - * @bus_info in their get_drvinfo() implementation. The ethtool - * core fills in the other fields using other driver operations. */ struct ethtool_drvinfo { __u32 cmd; -- cgit v1.2.3 From 9999f85ba34651726018e0f50d4afdf6c8cc8096 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 15 Nov 2022 03:18:42 +0200 Subject: net: dsa: stop exposing tag proto module helpers to the world The DSA tagging protocol driver macros are in the public include/net/dsa.h probably because that's also where the DSA_TAG_PROTO_*_VALUE macros are (MODULE_ALIAS_DSA_TAG_DRIVER hinges on those macro definitions). But there is no reason to expose these helpers to . That header is shared between switch drivers (drivers/net/dsa/), tagging protocol drivers (net/dsa/tag_*.c), the DSA core (net/dsa/ sans tag_*.c), and the rest of the world (DSA master drivers, network stack, etc). Too much exposure. On the other hand, net/dsa/dsa_priv.h is included only by the DSA core and by DSA tagging protocol drivers (or IOW, "friend" modules). Also a bit too much exposure - I've contemplated creating a new header which is only included by tagging protocol drivers, but completely separating a new dsa_tag_proto.h from dsa_priv.h is not immediately trivial - for example dsa_slave_to_port() is used both from the fast path and from the control path. So for now, move these definitions to dsa_priv.h which at least hides them from the world. Signed-off-by: Vladimir Oltean Tested-by: Michael Walle Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 70 ------------------------------------------------------ net/dsa/dsa_priv.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+), 70 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index dde364688739..82da44561f4c 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -118,10 +118,6 @@ struct dsa_netdevice_ops { int cmd); }; -#define DSA_TAG_DRIVER_ALIAS "dsa_tag-" -#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ - MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) - struct dsa_lag { struct net_device *dev; unsigned int id; @@ -1400,70 +1396,4 @@ static inline bool dsa_slave_dev_check(const struct net_device *dev) netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); -struct dsa_tag_driver { - const struct dsa_device_ops *ops; - struct list_head list; - struct module *owner; -}; - -void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count, - struct module *owner); -void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count); - -#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ -static int __init dsa_tag_driver_module_init(void) \ -{ \ - dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ - THIS_MODULE); \ - return 0; \ -} \ -module_init(dsa_tag_driver_module_init); \ - \ -static void __exit dsa_tag_driver_module_exit(void) \ -{ \ - dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ -} \ -module_exit(dsa_tag_driver_module_exit) - -/** - * module_dsa_tag_drivers() - Helper macro for registering DSA tag - * drivers - * @__ops_array: Array of tag driver structures - * - * Helper macro for DSA tag drivers which do not do anything special - * in module init/exit. Each module may only use this macro once, and - * calling it replaces module_init() and module_exit(). - */ -#define module_dsa_tag_drivers(__ops_array) \ -dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) - -#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops - -/* Create a static structure we can build a linked list of dsa_tag - * drivers - */ -#define DSA_TAG_DRIVER(__ops) \ -static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ - .ops = &__ops, \ -} - -/** - * module_dsa_tag_driver() - Helper macro for registering a single DSA tag - * driver - * @__ops: Single tag driver structures - * - * Helper macro for DSA tag drivers which do not do anything special - * in module init/exit. Each module may only use this macro once, and - * calling it replaces module_init() and module_exit(). - */ -#define module_dsa_tag_driver(__ops) \ -DSA_TAG_DRIVER(__ops); \ - \ -static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ - &DSA_TAG_DRIVER_NAME(__ops) \ -}; \ -module_dsa_tag_drivers(dsa_tag_driver_array) #endif - diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 71e9707d11d4..23d2dfdbc1ab 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -17,6 +17,76 @@ #define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG +#define DSA_TAG_DRIVER_ALIAS "dsa_tag-" +#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) + +struct dsa_tag_driver { + const struct dsa_device_ops *ops; + struct list_head list; + struct module *owner; +}; + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, + struct module *owner); +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count); + +#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ +static int __init dsa_tag_driver_module_init(void) \ +{ \ + dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ + THIS_MODULE); \ + return 0; \ +} \ +module_init(dsa_tag_driver_module_init); \ + \ +static void __exit dsa_tag_driver_module_exit(void) \ +{ \ + dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ +} \ +module_exit(dsa_tag_driver_module_exit) + +/** + * module_dsa_tag_drivers() - Helper macro for registering DSA tag + * drivers + * @__ops_array: Array of tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_drivers(__ops_array) \ +dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) + +#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops + +/* Create a static structure we can build a linked list of dsa_tag + * drivers + */ +#define DSA_TAG_DRIVER(__ops) \ +static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ + .ops = &__ops, \ +} + +/** + * module_dsa_tag_driver() - Helper macro for registering a single DSA tag + * driver + * @__ops: Single tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_driver(__ops) \ +DSA_TAG_DRIVER(__ops); \ + \ +static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ + &DSA_TAG_DRIVER_NAME(__ops) \ +}; \ +module_dsa_tag_drivers(dsa_tag_driver_array) + enum { DSA_NOTIFIER_AGEING_TIME, DSA_NOTIFIER_BRIDGE_JOIN, -- cgit v1.2.3 From cd502236835b678738810ecd501c85a3a7a11150 Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:15 +0100 Subject: devlink: Introduce new attribute 'tx_priority' to devlink-rate To fully utilize offload capabilities of Intel 100G card QoS capabilities new attribute 'tx_priority' needs to be introduced. This attribute allows for usage of strict priority arbiter among siblings. This arbitration scheme attempts to schedule nodes based on their priority as long as the nodes remain within their bandwidth limit. Introduce new attribute in devlink-rate that will allow for configuration of strict priority. New attribute is optional. Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 6 ++++++ include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 31 +++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 611a23a3deb2..90d59d673cb1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -114,6 +114,8 @@ struct devlink_rate { refcount_t refcnt; }; }; + + u32 tx_priority; }; struct devlink_port { @@ -1511,10 +1513,14 @@ struct devlink_ops { u64 tx_share, struct netlink_ext_ack *extack); int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 2f24b53a87a5..1a9214d35ef5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -607,6 +607,7 @@ enum devlink_attr { DEVLINK_ATTR_SELFTESTS, /* nested */ + DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 7f789bbcbbd7..bf6d3a3c28bb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1203,6 +1203,9 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, devlink_rate->tx_max, DEVLINK_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY, + devlink_rate->tx_priority)) + goto nla_put_failure; if (devlink_rate->parent) if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, devlink_rate->parent->name)) @@ -1936,6 +1939,7 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, { struct nlattr *nla_parent, **attrs = info->attrs; int err = -EOPNOTSUPP; + u32 priority; u64 rate; if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { @@ -1964,6 +1968,20 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_max = rate; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]) { + priority = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + + if (err) + return err; + devlink_rate->tx_priority = priority; + } + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; if (nla_parent) { err = devlink_nl_rate_parent_node_set(devlink_rate, info, @@ -1995,6 +2013,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_leaf_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); @@ -2009,6 +2033,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_node_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; @@ -9187,6 +9217,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit v1.2.3 From 6e2d7e84fcfee62d70e62aa9e469d10b8b6a7dc7 Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:16 +0100 Subject: devlink: Introduce new attribute 'tx_weight' to devlink-rate To fully utilize offload capabilities of Intel 100G card QoS capabilities new attribute 'tx_weight' needs to be introduced. This attribute allows for usage of Weighted Fair Queuing arbitration scheme among siblings. This arbitration scheme can be used simultaneously with the strict priority. Introduce new attribute in devlink-rate that will allow for configuration of Weighted Fair Queueing. New attribute is optional. Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 5 +++++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 33 +++++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 90d59d673cb1..366b23d3f973 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -116,6 +116,7 @@ struct devlink_rate { }; u32 tx_priority; + u32 tx_weight; }; struct devlink_port { @@ -1515,12 +1516,16 @@ struct devlink_ops { u64 tx_max, struct netlink_ext_ack *extack); int (*rate_leaf_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_priority, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); int (*rate_node_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_priority, struct netlink_ext_ack *extack); + int (*rate_node_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1a9214d35ef5..498d0d5d0957 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -608,6 +608,8 @@ enum devlink_attr { DEVLINK_ATTR_SELFTESTS, /* nested */ DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ + DEVLINK_ATTR_RATE_TX_WEIGHT, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index bf6d3a3c28bb..525bdf426163 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1206,6 +1206,11 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY, devlink_rate->tx_priority)) goto nla_put_failure; + + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT, + devlink_rate->tx_weight)) + goto nla_put_failure; + if (devlink_rate->parent) if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, devlink_rate->parent->name)) @@ -1940,6 +1945,7 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, struct nlattr *nla_parent, **attrs = info->attrs; int err = -EOPNOTSUPP; u32 priority; + u32 weight; u64 rate; if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { @@ -1982,6 +1988,20 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_priority = priority; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]) { + weight = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + + if (err) + return err; + devlink_rate->tx_weight = weight; + } + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; if (nla_parent) { err = devlink_nl_rate_parent_node_set(devlink_rate, info, @@ -2019,6 +2039,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX priority set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_leaf_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); @@ -2039,6 +2065,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX priority set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_node_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; @@ -9218,6 +9250,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit v1.2.3 From caba177d7f4d7693a9157ece8c9a30944c949e34 Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:17 +0100 Subject: devlink: Enable creation of the devlink-rate nodes from the driver Intel 100G card internal firmware hierarchy for Hierarchicial QoS is very rigid and can't be easily removed. This requires an ability to export default hierarchy to allow user to modify it. Currently the driver is only able to create the 'leaf' nodes, which usually represent the vport. This is not enough for HQoS implemented in Intel hardware. Introduce new function devl_rate_node_create() that allows for creation of the devlink-rate nodes from the driver. Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 3 +++ net/core/devlink.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/net/devlink.h b/include/net/devlink.h index 366b23d3f973..339a2ed02d36 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1618,6 +1618,9 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); int devl_rate_leaf_create(struct devlink_port *port, void *priv); +struct devlink_rate * +devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name, + struct devlink_rate *parent); void devl_rate_leaf_destroy(struct devlink_port *devlink_port); void devl_rate_nodes_destroy(struct devlink *devlink); void devlink_port_linecard_set(struct devlink_port *devlink_port, diff --git a/net/core/devlink.c b/net/core/devlink.c index 525bdf426163..3dfee7cd9929 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -10384,6 +10384,51 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); +/** + * devl_rate_node_create - create devlink rate node + * @devlink: devlink instance + * @priv: driver private data + * @node_name: name of the resulting node + * @parent: parent devlink_rate struct + * + * Create devlink rate object of type node + */ +struct devlink_rate * +devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name, + struct devlink_rate *parent) +{ + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_by_name(devlink, node_name); + if (!IS_ERR(rate_node)) + return ERR_PTR(-EEXIST); + + rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); + if (!rate_node) + return ERR_PTR(-ENOMEM); + + if (parent) { + rate_node->parent = parent; + refcount_inc(&rate_node->parent->refcnt); + } + + rate_node->type = DEVLINK_RATE_TYPE_NODE; + rate_node->devlink = devlink; + rate_node->priv = priv; + + rate_node->name = kstrdup(node_name, GFP_KERNEL); + if (!rate_node->name) { + kfree(rate_node); + return ERR_PTR(-ENOMEM); + } + + refcount_set(&rate_node->refcnt, 1); + list_add(&rate_node->list, &devlink->rate_list); + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + return rate_node; +} +EXPORT_SYMBOL_GPL(devl_rate_node_create); + /** * devl_rate_leaf_create - create devlink rate leaf * @devlink_port: devlink port object to create rate object on -- cgit v1.2.3 From f2fc15e271f2d17f2bee2c5a3b3e50252a7ba91f Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:19 +0100 Subject: devlink: Allow to set up parent in devl_rate_leaf_create() Currently the driver is able to create leaf nodes for the devlink-rate, but is unable to set parent for them. This wasn't as issue before the possibility to export hierarchy from the driver. After adding the export feature, in order for the driver to supply correct hierarchy, it's necessary for it to be able to supply a parent name to devl_rate_leaf_create(). Introduce a new parameter 'parent_name' in devl_rate_leaf_create(). Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 ++-- drivers/net/netdevsim/dev.c | 2 +- include/net/devlink.h | 4 +++- net/core/devlink.c | 9 ++++++++- 4 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 9bc7be95db54..084a910bb4e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -91,7 +91,7 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_ if (err) goto reg_err; - err = devl_rate_leaf_create(dl_port, vport); + err = devl_rate_leaf_create(dl_port, vport, NULL); if (err) goto rate_err; @@ -160,7 +160,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (err) return err; - err = devl_rate_leaf_create(dl_port, vport); + err = devl_rate_leaf_create(dl_port, vport, NULL); if (err) goto rate_err; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 705872eb7564..e14686594a71 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1401,7 +1401,7 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_typ if (nsim_dev_port_is_vf(nsim_dev_port)) { err = devl_rate_leaf_create(&nsim_dev_port->devlink_port, - nsim_dev_port); + nsim_dev_port, NULL); if (err) goto err_nsim_destroy; } diff --git a/include/net/devlink.h b/include/net/devlink.h index 339a2ed02d36..074a79b8933f 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1617,10 +1617,12 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); -int devl_rate_leaf_create(struct devlink_port *port, void *priv); struct devlink_rate * devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name, struct devlink_rate *parent); +int +devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv, + struct devlink_rate *parent); void devl_rate_leaf_destroy(struct devlink_port *devlink_port); void devl_rate_nodes_destroy(struct devlink *devlink); void devlink_port_linecard_set(struct devlink_port *devlink_port, diff --git a/net/core/devlink.c b/net/core/devlink.c index 61d431578f5f..d93bc95cd7cb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -10435,10 +10435,12 @@ EXPORT_SYMBOL_GPL(devl_rate_node_create); * devl_rate_leaf_create - create devlink rate leaf * @devlink_port: devlink port object to create rate object on * @priv: driver private data + * @parent: parent devlink_rate struct * * Create devlink rate object of type leaf on provided @devlink_port. */ -int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) +int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv, + struct devlink_rate *parent) { struct devlink *devlink = devlink_port->devlink; struct devlink_rate *devlink_rate; @@ -10452,6 +10454,11 @@ int devl_rate_leaf_create(struct devlink_port *devlink_port, void *priv) if (!devlink_rate) return -ENOMEM; + if (parent) { + devlink_rate->parent = parent; + refcount_inc(&devlink_rate->parent->refcnt); + } + devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; devlink_rate->devlink = devlink; devlink_rate->devlink_port = devlink_port; -- cgit v1.2.3 From b78c4162823dddc621649edae704b14c5973298c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 15 Nov 2022 10:39:53 -0500 Subject: sctp: change to include linux/sctp.h in net/sctp/checksum.h Currently "net/sctp/checksum.h" including "net/sctp/sctp.h" is included in quite some places in netfilter and openswitch and net/sched. It's not necessary to include "net/sctp/sctp.h" if a module does not have dependence on SCTP, "linux/sctp.h" is the right one to include. Signed-off-by: Xin Long Reviewed-by: Saeed Mahameed Link: https://lore.kernel.org/r/ca7ea96d62a26732f0491153c3979dc1c0d8d34a.1668526793.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sctp/checksum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 5a9bb09f32b6..f514a0aa849e 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -24,7 +24,7 @@ #define __sctp_checksum_h__ #include -#include +#include #include #include -- cgit v1.2.3 From 647541ea06a7bbbcf941e501c726b3e26328c102 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 15 Nov 2022 10:40:21 -0500 Subject: sctp: move SCTP_PAD4 and SCTP_TRUNC4 to linux/sctp.h Move these two macros from net/sctp/sctp.h to linux/sctp.h, so that it will be enough to include only linux/sctp.h in nft_exthdr.c and xt_sctp.c. It should not include "net/sctp/sctp.h" if a module does not have a dependence on SCTP module. Signed-off-by: Xin Long Reviewed-by: Saeed Mahameed Link: https://lore.kernel.org/r/ef6468a687f36da06f575c2131cd4612f6b7be88.1668526821.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/sctp.h | 5 +++++ include/net/sctp/sctp.h | 5 ----- net/netfilter/nft_exthdr.c | 1 - net/netfilter/xt_sctp.c | 1 - 4 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index a86e852507b3..358dc08e0831 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -820,4 +820,9 @@ struct sctp_new_encap_port_hdr { __be16 new_port; }; +/* Round an int up to the next multiple of 4. */ +#define SCTP_PAD4(s) (((s)+3)&~3) +/* Truncate to the previous multiple of 4. */ +#define SCTP_TRUNC4(s) ((s)&~3) + #endif /* __LINUX_SCTP_H__ */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a04999ee99b0..01d904b34cf0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -67,11 +67,6 @@ #define SCTP_PROTOSW_FLAG INET_PROTOSW_PERMANENT #endif -/* Round an int up to the next multiple of 4. */ -#define SCTP_PAD4(s) (((s)+3)&~3) -/* Truncate to the previous multiple of 4. */ -#define SCTP_TRUNC4(s) ((s)&~3) - /* * Function declarations. */ diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ed929d0d37ce..a54a7f772cec 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -13,7 +13,6 @@ #include #include #include -#include #include struct nft_exthdr { diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c index 680015ba7cb6..e8961094a282 100644 --- a/net/netfilter/xt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From 33e93ed2209d5971043bed41dd194bc583b57ef3 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 16 Nov 2022 15:01:19 -0500 Subject: sctp: add skb_sdif in struct sctp_af Add skb_sdif function in struct sctp_af to get the enslaved device for both ipv4 and ipv6 when adding SCTP VRF support in sctp_rcv in the next patch. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 1 + net/sctp/ipv6.c | 8 +++++++- net/sctp/protocol.c | 6 ++++++ 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 350f250b0dc7..7b4884c63b26 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -477,6 +477,7 @@ struct sctp_af { int (*available) (union sctp_addr *, struct sctp_sock *); int (*skb_iif) (const struct sk_buff *sk); + int (*skb_sdif)(const struct sk_buff *sk); int (*is_ce) (const struct sk_buff *sk); void (*seq_dump_addr)(struct seq_file *seq, union sctp_addr *addr); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e6274cdbdf6c..097bd60ce964 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -842,7 +842,12 @@ static int sctp_v6_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) /* Where did this skb come from? */ static int sctp_v6_skb_iif(const struct sk_buff *skb) { - return IP6CB(skb)->iif; + return inet6_iif(skb); +} + +static int sctp_v6_skb_sdif(const struct sk_buff *skb) +{ + return inet6_sdif(skb); } /* Was this packet marked by Explicit Congestion Notification? */ @@ -1142,6 +1147,7 @@ static struct sctp_af sctp_af_inet6 = { .is_any = sctp_v6_is_any, .available = sctp_v6_available, .skb_iif = sctp_v6_skb_iif, + .skb_sdif = sctp_v6_skb_sdif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, .ecn_capable = sctp_v6_ecn_capable, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index dbfe7d1000c2..a18cf0471a8d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -567,6 +567,11 @@ static int sctp_v4_skb_iif(const struct sk_buff *skb) return inet_iif(skb); } +static int sctp_v4_skb_sdif(const struct sk_buff *skb) +{ + return inet_sdif(skb); +} + /* Was this packet marked by Explicit Congestion Notification? */ static int sctp_v4_is_ce(const struct sk_buff *skb) { @@ -1185,6 +1190,7 @@ static struct sctp_af sctp_af_inet = { .available = sctp_v4_available, .scope = sctp_v4_scope, .skb_iif = sctp_v4_skb_iif, + .skb_sdif = sctp_v4_skb_sdif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, .ecn_capable = sctp_v4_ecn_capable, -- cgit v1.2.3 From 0af03170637f47fb5cc6501d4b2dcbf1c14772a9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 16 Nov 2022 15:01:20 -0500 Subject: sctp: add dif and sdif check in asoc and ep lookup This patch at first adds a pernet global l3mdev_accept to decide if it accepts the packets from a l3mdev when a SCTP socket doesn't bind to any interface. It's set to 1 to avoid any possible incompatible issue, and in next patch, a sysctl will be introduced to allow to change it. Then similar to inet/udp_sk_bound_dev_eq(), sctp_sk_bound_dev_eq() is added to check either dif or sdif is equal to sk_bound_dev_if, and to check sid is 0 or l3mdev_accept is 1 if sk_bound_dev_if is not set. This function is used to match a association or a endpoint, namely called by sctp_addrs_lookup_transport() and sctp_endpoint_is_match(). All functions that needs updating are: sctp_rcv(): asoc: __sctp_rcv_lookup() __sctp_lookup_association() -> sctp_addrs_lookup_transport() __sctp_rcv_lookup_harder() __sctp_rcv_init_lookup() __sctp_lookup_association() -> sctp_addrs_lookup_transport() __sctp_rcv_walk_lookup() __sctp_rcv_asconf_lookup() __sctp_lookup_association() -> sctp_addrs_lookup_transport() ep: __sctp_rcv_lookup_endpoint() -> sctp_endpoint_is_match() sctp_connect(): sctp_endpoint_is_peeled_off() __sctp_lookup_association() sctp_has_association() sctp_lookup_association() __sctp_lookup_association() -> sctp_addrs_lookup_transport() sctp_diag_dump_one(): sctp_transport_lookup_process() -> sctp_addrs_lookup_transport() Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/netns/sctp.h | 4 ++ include/net/sctp/sctp.h | 6 ++- include/net/sctp/structs.h | 8 ++-- net/sctp/diag.c | 3 +- net/sctp/endpointola.c | 13 ++++-- net/sctp/input.c | 108 +++++++++++++++++++++++++-------------------- net/sctp/protocol.c | 4 ++ net/sctp/socket.c | 4 +- 8 files changed, 89 insertions(+), 61 deletions(-) (limited to 'include') diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index a681147aecd8..7eff3d981b89 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -175,6 +175,10 @@ struct netns_sctp { /* Threshold for autoclose timeout, in seconds. */ unsigned long max_autoclose; + +#ifdef CONFIG_NET_L3_MASTER_DEV + int l3mdev_accept; +#endif }; #endif /* __NETNS_SCTP_H__ */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 01d904b34cf0..c335dd01a597 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -109,7 +109,7 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos); int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr, void *p); + const union sctp_addr *paddr, void *p, int dif); int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done, struct net *net, int *pos, void *p); int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p); @@ -157,10 +157,12 @@ void sctp_unhash_transport(struct sctp_transport *t); struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr); + const union sctp_addr *paddr, + int dif, int sdif); struct sctp_transport *sctp_epaddr_lookup_transport( const struct sctp_endpoint *ep, const union sctp_addr *paddr); +bool sctp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif); /* * sctp/proc.c diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 7b4884c63b26..afa3781e3ca2 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1379,10 +1379,12 @@ struct sctp_association *sctp_endpoint_lookup_assoc( struct sctp_transport **); bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr); -struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *, - struct net *, const union sctp_addr *); +struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, + struct net *net, + const union sctp_addr *laddr, + int dif, int sdif); bool sctp_has_association(struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr); + const union sctp_addr *paddr, int dif, int sdif); int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, diff --git a/net/sctp/diag.c b/net/sctp/diag.c index d9c6d8f30f09..a557009e9832 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -426,6 +426,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb, struct net *net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; union sctp_addr laddr, paddr; + int dif = req->id.idiag_if; struct sctp_comm_param commp = { .skb = skb, .r = req, @@ -454,7 +455,7 @@ static int sctp_diag_dump_one(struct netlink_callback *cb, } return sctp_transport_lookup_process(sctp_sock_dump_one, - net, &laddr, &paddr, &commp); + net, &laddr, &paddr, &commp, dif); } static void sctp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index efffde7f2328..7e77b450697c 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -246,12 +246,15 @@ void sctp_endpoint_put(struct sctp_endpoint *ep) /* Is this the endpoint we are looking for? */ struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, struct net *net, - const union sctp_addr *laddr) + const union sctp_addr *laddr, + int dif, int sdif) { + int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if); struct sctp_endpoint *retval = NULL; - if ((htons(ep->base.bind_addr.port) == laddr->v4.sin_port) && - net_eq(ep->base.net, net)) { + if (net_eq(ep->base.net, net) && + sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && + (htons(ep->base.bind_addr.port) == laddr->v4.sin_port)) { if (sctp_bind_addr_match(&ep->base.bind_addr, laddr, sctp_sk(ep->base.sk))) retval = ep; @@ -298,6 +301,7 @@ out: bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr) { + int bound_dev_if = READ_ONCE(ep->base.sk->sk_bound_dev_if); struct sctp_sockaddr_entry *addr; struct net *net = ep->base.net; struct sctp_bind_addr *bp; @@ -307,7 +311,8 @@ bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, * so the address_list can not change. */ list_for_each_entry(addr, &bp->address_list, list) { - if (sctp_has_association(net, &addr->a, paddr)) + if (sctp_has_association(net, &addr->a, paddr, + bound_dev_if, bound_dev_if)) return true; } diff --git a/net/sctp/input.c b/net/sctp/input.c index 4f43afa8678f..bf70371301ff 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -50,16 +50,19 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, - struct sctp_transport **transportp); + struct sctp_transport **transportp, + int dif, int sdif); static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - const union sctp_addr *daddr); + const union sctp_addr *daddr, + int dif, int sdif); static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, - struct sctp_transport **pt); + struct sctp_transport **pt, + int dif, int sdif); static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb); @@ -92,11 +95,11 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_chunk *chunk; union sctp_addr src; union sctp_addr dest; - int bound_dev_if; int family; struct sctp_af *af; struct net *net = dev_net(skb->dev); bool is_gso = skb_is_gso(skb) && skb_is_gso_sctp(skb); + int dif, sdif; if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -141,6 +144,8 @@ int sctp_rcv(struct sk_buff *skb) /* Initialize local addresses for lookups. */ af->from_skb(&src, skb, 1); af->from_skb(&dest, skb, 0); + dif = af->skb_iif(skb); + sdif = af->skb_sdif(skb); /* If the packet is to or from a non-unicast address, * silently discard the packet. @@ -157,35 +162,15 @@ int sctp_rcv(struct sk_buff *skb) !af->addr_valid(&dest, NULL, skb)) goto discard_it; - asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport); + asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport, dif, sdif); if (!asoc) - ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src); + ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src, dif, sdif); /* Retrieve the common input handling substructure. */ rcvr = asoc ? &asoc->base : &ep->base; sk = rcvr->sk; - /* - * If a frame arrives on an interface and the receiving socket is - * bound to another interface, via SO_BINDTODEVICE, treat it as OOTB - */ - bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); - if (bound_dev_if && (bound_dev_if != af->skb_iif(skb))) { - if (transport) { - sctp_transport_put(transport); - asoc = NULL; - transport = NULL; - } else { - sctp_endpoint_put(ep); - ep = NULL; - } - sk = net->sctp.ctl_sock; - ep = sctp_sk(sk)->ep; - sctp_endpoint_hold(ep); - rcvr = &ep->base; - } - /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * An SCTP packet is called an "out of the blue" (OOTB) @@ -485,6 +470,8 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, struct sctp_association *asoc; struct sctp_transport *transport = NULL; __u32 vtag = ntohl(sctphdr->vtag); + int sdif = inet_sdif(skb); + int dif = inet_iif(skb); *app = NULL; *tpp = NULL; @@ -500,7 +487,7 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *skb, /* Look for an association that matches the incoming ICMP error * packet. */ - asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport); + asoc = __sctp_lookup_association(net, &saddr, &daddr, &transport, dif, sdif); if (!asoc) return NULL; @@ -850,7 +837,8 @@ static inline __u32 sctp_hashfn(const struct net *net, __be16 lport, static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct sctp_hashbucket *head; struct sctp_endpoint *ep; @@ -863,7 +851,7 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint( head = &sctp_ep_hashtable[hash]; read_lock(&head->lock); sctp_for_each_hentry(ep, &head->chain) { - if (sctp_endpoint_is_match(ep, net, laddr)) + if (sctp_endpoint_is_match(ep, net, laddr, dif, sdif)) goto hit; } @@ -990,14 +978,26 @@ void sctp_unhash_transport(struct sctp_transport *t) sctp_hash_params); } +bool sctp_sk_bound_dev_eq(struct net *net, int bound_dev_if, int dif, int sdif) +{ + bool l3mdev_accept = true; + +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + l3mdev_accept = !!READ_ONCE(net->sctp.l3mdev_accept); +#endif + return inet_bound_dev_eq(l3mdev_accept, bound_dev_if, dif, sdif); +} + /* return a transport with holding it */ struct sctp_transport *sctp_addrs_lookup_transport( struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct rhlist_head *tmp, *list; struct sctp_transport *t; + int bound_dev_if; struct sctp_hash_cmp_arg arg = { .paddr = paddr, .net = net, @@ -1011,7 +1011,9 @@ struct sctp_transport *sctp_addrs_lookup_transport( if (!sctp_transport_hold(t)) continue; - if (sctp_bind_addr_match(&t->asoc->base.bind_addr, + bound_dev_if = READ_ONCE(t->asoc->base.sk->sk_bound_dev_if); + if (sctp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif) && + sctp_bind_addr_match(&t->asoc->base.bind_addr, laddr, sctp_sk(t->asoc->base.sk))) return t; sctp_transport_put(t); @@ -1048,12 +1050,13 @@ static struct sctp_association *__sctp_lookup_association( struct net *net, const union sctp_addr *local, const union sctp_addr *peer, - struct sctp_transport **pt) + struct sctp_transport **pt, + int dif, int sdif) { struct sctp_transport *t; struct sctp_association *asoc = NULL; - t = sctp_addrs_lookup_transport(net, local, peer); + t = sctp_addrs_lookup_transport(net, local, peer, dif, sdif); if (!t) goto out; @@ -1069,12 +1072,13 @@ static struct sctp_association *sctp_lookup_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; rcu_read_lock(); - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); rcu_read_unlock(); return asoc; @@ -1083,11 +1087,12 @@ struct sctp_association *sctp_lookup_association(struct net *net, /* Is there an association matching the given local and peer addresses? */ bool sctp_has_association(struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr) + const union sctp_addr *paddr, + int dif, int sdif) { struct sctp_transport *transport; - if (sctp_lookup_association(net, laddr, paddr, &transport)) { + if (sctp_lookup_association(net, laddr, paddr, &transport, dif, sdif)) { sctp_transport_put(transport); return true; } @@ -1115,7 +1120,8 @@ bool sctp_has_association(struct net *net, */ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, struct sk_buff *skb, - const union sctp_addr *laddr, struct sctp_transport **transportp) + const union sctp_addr *laddr, struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; union sctp_addr addr; @@ -1154,7 +1160,7 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) continue; - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) return asoc; } @@ -1181,7 +1187,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( struct sctp_chunkhdr *ch, const union sctp_addr *laddr, __be16 peer_port, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_addip_chunk *asconf = (struct sctp_addip_chunk *)ch; struct sctp_af *af; @@ -1201,7 +1208,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (!af->from_addr_param(&paddr, param, peer_port, 0)) return NULL; - return __sctp_lookup_association(net, laddr, &paddr, transportp); + return __sctp_lookup_association(net, laddr, &paddr, transportp, dif, sdif); } @@ -1217,7 +1224,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc = NULL; struct sctp_chunkhdr *ch; @@ -1260,7 +1268,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, asoc = __sctp_rcv_asconf_lookup( net, ch, laddr, sctp_hdr(skb)->source, - transportp); + transportp, dif, sdif); break; default: break; @@ -1285,7 +1293,8 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, struct sk_buff *skb, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_chunkhdr *ch; @@ -1309,9 +1318,9 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, /* If this is INIT/INIT-ACK look inside the chunk too. */ if (ch->type == SCTP_CID_INIT || ch->type == SCTP_CID_INIT_ACK) - return __sctp_rcv_init_lookup(net, skb, laddr, transportp); + return __sctp_rcv_init_lookup(net, skb, laddr, transportp, dif, sdif); - return __sctp_rcv_walk_lookup(net, skb, laddr, transportp); + return __sctp_rcv_walk_lookup(net, skb, laddr, transportp, dif, sdif); } /* Lookup an association for an inbound skb. */ @@ -1319,11 +1328,12 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, struct sk_buff *skb, const union sctp_addr *paddr, const union sctp_addr *laddr, - struct sctp_transport **transportp) + struct sctp_transport **transportp, + int dif, int sdif) { struct sctp_association *asoc; - asoc = __sctp_lookup_association(net, laddr, paddr, transportp); + asoc = __sctp_lookup_association(net, laddr, paddr, transportp, dif, sdif); if (asoc) goto out; @@ -1331,7 +1341,7 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net, * SCTP Implementors Guide, 2.18 Handling of address * parameters within the INIT or INIT-ACK. */ - asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp); + asoc = __sctp_rcv_lookup_harder(net, skb, laddr, transportp, dif, sdif); if (asoc) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index a18cf0471a8d..909a89a1cff4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1394,6 +1394,10 @@ static int __net_init sctp_defaults_init(struct net *net) /* Initialize maximum autoclose timeout. */ net->sctp.max_autoclose = INT_MAX / HZ; +#ifdef CONFIG_NET_L3_MASTER_DEV + net->sctp.l3mdev_accept = 1; +#endif + status = sctp_sysctl_net_register(net); if (status) goto err_sysctl_register; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 4306164238ef..5acbdf0d38f3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5315,14 +5315,14 @@ EXPORT_SYMBOL_GPL(sctp_for_each_endpoint); int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *laddr, - const union sctp_addr *paddr, void *p) + const union sctp_addr *paddr, void *p, int dif) { struct sctp_transport *transport; struct sctp_endpoint *ep; int err = -ENOENT; rcu_read_lock(); - transport = sctp_addrs_lookup_transport(net, laddr, paddr); + transport = sctp_addrs_lookup_transport(net, laddr, paddr, dif, dif); if (!transport) { rcu_read_unlock(); return err; -- cgit v1.2.3 From ab0377803dafc58f1e22296708c1c28e309414d6 Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Wed, 16 Nov 2022 19:45:11 +0800 Subject: mrp: introduce active flags to prevent UAF when applicant uninit The caller of del_timer_sync must prevent restarting of the timer, If we have no this synchronization, there is a small probability that the cancellation will not be successful. And syzbot report the fellowing crash: ================================================================== BUG: KASAN: use-after-free in hlist_add_head include/linux/list.h:929 [inline] BUG: KASAN: use-after-free in enqueue_timer+0x18/0xa4 kernel/time/timer.c:605 Write at addr f9ff000024df6058 by task syz-fuzzer/2256 Pointer tag: [f9], memory tag: [fe] CPU: 1 PID: 2256 Comm: syz-fuzzer Not tainted 6.1.0-rc5-syzkaller-00008- ge01d50cbd6ee #0 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace.part.0+0xe0/0xf0 arch/arm64/kernel/stacktrace.c:156 dump_backtrace arch/arm64/kernel/stacktrace.c:162 [inline] show_stack+0x18/0x40 arch/arm64/kernel/stacktrace.c:163 __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x68/0x84 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x1a8/0x4a0 mm/kasan/report.c:395 kasan_report+0x94/0xb4 mm/kasan/report.c:495 __do_kernel_fault+0x164/0x1e0 arch/arm64/mm/fault.c:320 do_bad_area arch/arm64/mm/fault.c:473 [inline] do_tag_check_fault+0x78/0x8c arch/arm64/mm/fault.c:749 do_mem_abort+0x44/0x94 arch/arm64/mm/fault.c:825 el1_abort+0x40/0x60 arch/arm64/kernel/entry-common.c:367 el1h_64_sync_handler+0xd8/0xe4 arch/arm64/kernel/entry-common.c:427 el1h_64_sync+0x64/0x68 arch/arm64/kernel/entry.S:576 hlist_add_head include/linux/list.h:929 [inline] enqueue_timer+0x18/0xa4 kernel/time/timer.c:605 mod_timer+0x14/0x20 kernel/time/timer.c:1161 mrp_periodic_timer_arm net/802/mrp.c:614 [inline] mrp_periodic_timer+0xa0/0xc0 net/802/mrp.c:627 call_timer_fn.constprop.0+0x24/0x80 kernel/time/timer.c:1474 expire_timers+0x98/0xc4 kernel/time/timer.c:1519 To fix it, we can introduce a new active flags to make sure the timer will not restart. Reported-by: syzbot+6fd64001c20aa99e34a4@syzkaller.appspotmail.com Signed-off-by: Schspa Shi Signed-off-by: David S. Miller --- include/net/mrp.h | 1 + net/802/mrp.c | 18 +++++++++++++----- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/mrp.h b/include/net/mrp.h index 92cd3fb6cf9d..b28915ffea28 100644 --- a/include/net/mrp.h +++ b/include/net/mrp.h @@ -124,6 +124,7 @@ struct mrp_applicant { struct sk_buff *pdu; struct rb_root mad; struct rcu_head rcu; + bool active; }; struct mrp_port { diff --git a/net/802/mrp.c b/net/802/mrp.c index 155f74d8b14f..6c927d4b35f0 100644 --- a/net/802/mrp.c +++ b/net/802/mrp.c @@ -606,7 +606,10 @@ static void mrp_join_timer(struct timer_list *t) spin_unlock(&app->lock); mrp_queue_xmit(app); - mrp_join_timer_arm(app); + spin_lock(&app->lock); + if (likely(app->active)) + mrp_join_timer_arm(app); + spin_unlock(&app->lock); } static void mrp_periodic_timer_arm(struct mrp_applicant *app) @@ -620,11 +623,12 @@ static void mrp_periodic_timer(struct timer_list *t) struct mrp_applicant *app = from_timer(app, t, periodic_timer); spin_lock(&app->lock); - mrp_mad_event(app, MRP_EVENT_PERIODIC); - mrp_pdu_queue(app); + if (likely(app->active)) { + mrp_mad_event(app, MRP_EVENT_PERIODIC); + mrp_pdu_queue(app); + mrp_periodic_timer_arm(app); + } spin_unlock(&app->lock); - - mrp_periodic_timer_arm(app); } static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) @@ -872,6 +876,7 @@ int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) app->dev = dev; app->app = appl; app->mad = RB_ROOT; + app->active = true; spin_lock_init(&app->lock); skb_queue_head_init(&app->queue); rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); @@ -900,6 +905,9 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) RCU_INIT_POINTER(port->applicants[appl->type], NULL); + spin_lock_bh(&app->lock); + app->active = false; + spin_unlock_bh(&app->lock); /* Delete timer and generate a final TX event to flush out * all pending messages before the applicant is gone. */ -- cgit v1.2.3 From c73a72f4cbb47672c8cc7f7d7aba52f1cb15baca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 17 Nov 2022 19:39:03 -0800 Subject: netlink: remove the flex array from struct nlmsghdr I've added a flex array to struct nlmsghdr in commit 738136a0e375 ("netlink: split up copies in the ack construction") to allow accessing the data easily. It leads to warnings with clang, if user space wraps this structure into another struct and the flex array is not at the end of the container. Reviewed-by: Kees Cook Reviewed-by: David Ahern Link: https://lore.kernel.org/all/20221114023927.GA685@u2004-local/ Link: https://lore.kernel.org/r/20221118033903.1651026-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/netlink.h | 2 -- net/netlink/af_netlink.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 5da0da59bf01..e2ae82e3f9f7 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,7 +48,6 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID - * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -56,7 +55,6 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; - __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9ebdf3262015..d73091f6bb0f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2514,7 +2514,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; - memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } -- cgit v1.2.3 From ef66c5475d7fb864c2418d3bdd19dee46324624b Mon Sep 17 00:00:00 2001 From: David Vernet Date: Sat, 19 Nov 2022 23:10:01 -0600 Subject: bpf: Allow multiple modifiers in reg_type_str() prefix reg_type_str() in the verifier currently only allows a single register type modifier to be present in the 'prefix' string which is eventually stored in the env type_str_buf. This currently works fine because there are no overlapping type modifiers, but once PTR_TRUSTED is added, that will no longer be the case. This patch updates reg_type_str() to support having multiple modifiers in the prefix string, and updates the size of type_str_buf to be 128 bytes. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20221120051004.3605026-2-void@manifault.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- kernel/bpf/verifier.c | 19 ++++++++----------- 2 files changed, 9 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 23f30c685f28..608dde740fef 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -19,7 +19,7 @@ */ #define BPF_MAX_VAR_SIZ (1 << 29) /* size of type_str_buf in bpf_verifier. */ -#define TYPE_STR_BUF_LEN 64 +#define TYPE_STR_BUF_LEN 128 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 195d24316750..67a6f11d953c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -557,7 +557,7 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) static const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { - char postfix[16] = {0}, prefix[32] = {0}; + char postfix[16] = {0}, prefix[64] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "scalar", @@ -589,16 +589,13 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(postfix, "_or_null", 16); } - if (type & MEM_RDONLY) - strncpy(prefix, "rdonly_", 32); - if (type & MEM_RINGBUF) - strncpy(prefix, "ringbuf_", 32); - if (type & MEM_USER) - strncpy(prefix, "user_", 32); - if (type & MEM_PERCPU) - strncpy(prefix, "percpu_", 32); - if (type & PTR_UNTRUSTED) - strncpy(prefix, "untrusted_", 32); + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s", + type & MEM_RDONLY ? "rdonly_" : "", + type & MEM_RINGBUF ? "ringbuf_" : "", + type & MEM_USER ? "user_" : "", + type & MEM_PERCPU ? "percpu_" : "", + type & PTR_UNTRUSTED ? "untrusted_" : "" + ); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); -- cgit v1.2.3 From 3f00c52393445ed49aadc1a567aa502c6333b1a1 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Sat, 19 Nov 2022 23:10:02 -0600 Subject: bpf: Allow trusted pointers to be passed to KF_TRUSTED_ARGS kfuncs Kfuncs currently support specifying the KF_TRUSTED_ARGS flag to signal to the verifier that it should enforce that a BPF program passes it a "safe", trusted pointer. Currently, "safe" means that the pointer is either PTR_TO_CTX, or is refcounted. There may be cases, however, where the kernel passes a BPF program a safe / trusted pointer to an object that the BPF program wishes to use as a kptr, but because the object does not yet have a ref_obj_id from the perspective of the verifier, the program would be unable to pass it to a KF_ACQUIRE | KF_TRUSTED_ARGS kfunc. The solution is to expand the set of pointers that are considered trusted according to KF_TRUSTED_ARGS, so that programs can invoke kfuncs with these pointers without getting rejected by the verifier. There is already a PTR_UNTRUSTED flag that is set in some scenarios, such as when a BPF program reads a kptr directly from a map without performing a bpf_kptr_xchg() call. These pointers of course can and should be rejected by the verifier. Unfortunately, however, PTR_UNTRUSTED does not cover all the cases for safety that need to be addressed to adequately protect kfuncs. Specifically, pointers obtained by a BPF program "walking" a struct are _not_ considered PTR_UNTRUSTED according to BPF. For example, say that we were to add a kfunc called bpf_task_acquire(), with KF_ACQUIRE | KF_TRUSTED_ARGS, to acquire a struct task_struct *. If we only used PTR_UNTRUSTED to signal that a task was unsafe to pass to a kfunc, the verifier would mistakenly allow the following unsafe BPF program to be loaded: SEC("tp_btf/task_newtask") int BPF_PROG(unsafe_acquire_task, struct task_struct *task, u64 clone_flags) { struct task_struct *acquired, *nested; nested = task->last_wakee; /* Would not be rejected by the verifier. */ acquired = bpf_task_acquire(nested); if (!acquired) return 0; bpf_task_release(acquired); return 0; } To address this, this patch defines a new type flag called PTR_TRUSTED which tracks whether a PTR_TO_BTF_ID pointer is safe to pass to a KF_TRUSTED_ARGS kfunc or a BPF helper function. PTR_TRUSTED pointers are passed directly from the kernel as a tracepoint or struct_ops callback argument. Any nested pointer that is obtained from walking a PTR_TRUSTED pointer is no longer PTR_TRUSTED. From the example above, the struct task_struct *task argument is PTR_TRUSTED, but the 'nested' pointer obtained from 'task->last_wakee' is not PTR_TRUSTED. A subsequent patch will add kfuncs for storing a task kfunc as a kptr, and then another patch will add selftests to validate. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20221120051004.3605026-3-void@manifault.com Signed-off-by: Alexei Starovoitov --- Documentation/bpf/kfuncs.rst | 30 +++++----- include/linux/bpf.h | 30 ++++++++++ include/linux/bpf_verifier.h | 7 +++ include/linux/btf.h | 65 ++++++++++++-------- kernel/bpf/btf.c | 8 +++ kernel/bpf/verifier.c | 69 ++++++++++++++++++---- kernel/trace/bpf_trace.c | 2 +- net/ipv4/bpf_tcp_ca.c | 4 +- tools/testing/selftests/bpf/verifier/calls.c | 2 +- .../testing/selftests/bpf/verifier/ref_tracking.c | 4 +- 10 files changed, 164 insertions(+), 57 deletions(-) (limited to 'include') diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index 3b1501c3b6cd..90774479ab7a 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -161,22 +161,20 @@ KF_ACQUIRE and KF_RET_NULL flags. -------------------------- The KF_TRUSTED_ARGS flag is used for kfuncs taking pointer arguments. It -indicates that the all pointer arguments will always have a guaranteed lifetime, -and pointers to kernel objects are always passed to helpers in their unmodified -form (as obtained from acquire kfuncs). - -It can be used to enforce that a pointer to a refcounted object acquired from a -kfunc or BPF helper is passed as an argument to this kfunc without any -modifications (e.g. pointer arithmetic) such that it is trusted and points to -the original object. - -Meanwhile, it is also allowed pass pointers to normal memory to such kfuncs, -but those can have a non-zero offset. - -This flag is often used for kfuncs that operate (change some property, perform -some operation) on an object that was obtained using an acquire kfunc. Such -kfuncs need an unchanged pointer to ensure the integrity of the operation being -performed on the expected object. +indicates that the all pointer arguments are valid, and that all pointers to +BTF objects have been passed in their unmodified form (that is, at a zero +offset, and without having been obtained from walking another pointer). + +There are two types of pointers to kernel objects which are considered "valid": + +1. Pointers which are passed as tracepoint or struct_ops callback arguments. +2. Pointers which were returned from a KF_ACQUIRE or KF_KPTR_GET kfunc. + +Pointers to non-BTF objects (e.g. scalar pointers) may also be passed to +KF_TRUSTED_ARGS kfuncs, and may have a non-zero offset. + +The definition of "valid" pointers is subject to change at any time, and has +absolutely no ABI stability guarantees. 2.4.6 KF_SLEEPABLE flag ----------------------- diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8b32376ce746..c9eafa67f2a2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -543,6 +543,35 @@ enum bpf_type_flag { */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), + /* PTR was passed from the kernel in a trusted context, and may be + * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions. + * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. + * PTR_UNTRUSTED refers to a kptr that was read directly from a map + * without invoking bpf_kptr_xchg(). What we really need to know is + * whether a pointer is safe to pass to a kfunc or BPF helper function. + * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF + * helpers, they do not cover all possible instances of unsafe + * pointers. For example, a pointer that was obtained from walking a + * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the + * fact that it may be NULL, invalid, etc. This is due to backwards + * compatibility requirements, as this was the behavior that was first + * introduced when kptrs were added. The behavior is now considered + * deprecated, and PTR_UNTRUSTED will eventually be removed. + * + * PTR_TRUSTED, on the other hand, is a pointer that the kernel + * guarantees to be valid and safe to pass to kfuncs and BPF helpers. + * For example, pointers passed to tracepoint arguments are considered + * PTR_TRUSTED, as are pointers that are passed to struct_ops + * callbacks. As alluded to above, pointers that are obtained from + * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a + * struct task_struct *task is PTR_TRUSTED, then accessing + * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored + * in a BPF register. Similarly, pointers passed to certain programs + * types such as kretprobes are not guaranteed to be valid, as they may + * for example contain an object that was recently freed. + */ + PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; @@ -636,6 +665,7 @@ enum bpf_return_type { RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, + RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 608dde740fef..545152ac136c 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -680,4 +680,11 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) + +static inline bool bpf_type_has_unsafe_modifiers(u32 type) +{ + return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS; +} + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index d5b26380a60f..d38aa4251c28 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -19,36 +19,53 @@ #define KF_RELEASE (1 << 1) /* kfunc is a release function */ #define KF_RET_NULL (1 << 2) /* kfunc returns a pointer that may be NULL */ #define KF_KPTR_GET (1 << 3) /* kfunc returns reference to a kptr */ -/* Trusted arguments are those which are meant to be referenced arguments with - * unchanged offset. It is used to enforce that pointers obtained from acquire - * kfuncs remain unmodified when being passed to helpers taking trusted args. +/* Trusted arguments are those which are guaranteed to be valid when passed to + * the kfunc. It is used to enforce that pointers obtained from either acquire + * kfuncs, or from the main kernel on a tracepoint or struct_ops callback + * invocation, remain unmodified when being passed to helpers taking trusted + * args. * - * Consider - * struct foo { - * int data; - * struct foo *next; - * }; + * Consider, for example, the following new task tracepoint: * - * struct bar { - * int data; - * struct foo f; - * }; + * SEC("tp_btf/task_newtask") + * int BPF_PROG(new_task_tp, struct task_struct *task, u64 clone_flags) + * { + * ... + * } * - * struct foo *f = alloc_foo(); // Acquire kfunc - * struct bar *b = alloc_bar(); // Acquire kfunc + * And the following kfunc: * - * If a kfunc set_foo_data() wants to operate only on the allocated object, it - * will set the KF_TRUSTED_ARGS flag, which will prevent unsafe usage like: + * BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) * - * set_foo_data(f, 42); // Allowed - * set_foo_data(f->next, 42); // Rejected, non-referenced pointer - * set_foo_data(&f->next, 42);// Rejected, referenced, but wrong type - * set_foo_data(&b->f, 42); // Rejected, referenced, but bad offset + * All invocations to the kfunc must pass the unmodified, unwalked task: * - * In the final case, usually for the purposes of type matching, it is deduced - * by looking at the type of the member at the offset, but due to the - * requirement of trusted argument, this deduction will be strict and not done - * for this case. + * bpf_task_acquire(task); // Allowed + * bpf_task_acquire(task->last_wakee); // Rejected, walked task + * + * Programs may also pass referenced tasks directly to the kfunc: + * + * struct task_struct *acquired; + * + * acquired = bpf_task_acquire(task); // Allowed, same as above + * bpf_task_acquire(acquired); // Allowed + * bpf_task_acquire(task); // Allowed + * bpf_task_acquire(acquired->last_wakee); // Rejected, walked task + * + * Programs may _not_, however, pass a task from an arbitrary fentry/fexit, or + * kprobe/kretprobe to the kfunc, as BPF cannot guarantee that all of these + * pointers are guaranteed to be safe. For example, the following BPF program + * would be rejected: + * + * SEC("kretprobe/free_task") + * int BPF_PROG(free_task_probe, struct task_struct *tsk) + * { + * struct task_struct *acquired; + * + * acquired = bpf_task_acquire(acquired); // Rejected, not a trusted pointer + * bpf_task_release(acquired); + * + * return 0; + * } */ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7d5fab61535..d52054ec69c9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5799,6 +5799,11 @@ static u32 get_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, return nr_args + 1; } +static bool prog_type_args_trusted(enum bpf_prog_type prog_type) +{ + return prog_type == BPF_PROG_TYPE_TRACING || prog_type == BPF_PROG_TYPE_STRUCT_OPS; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -5942,6 +5947,9 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = PTR_TO_BTF_ID; + if (prog_type_args_trusted(prog->type)) + info->reg_type |= PTR_TRUSTED; + if (tgt_prog) { enum bpf_prog_type tgt_type; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 67a6f11d953c..5bc9d84d7924 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -589,12 +589,13 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(postfix, "_or_null", 16); } - snprintf(prefix, sizeof(prefix), "%s%s%s%s%s", + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", - type & PTR_UNTRUSTED ? "untrusted_" : "" + type & PTR_UNTRUSTED ? "untrusted_" : "", + type & PTR_TRUSTED ? "trusted_" : "" ); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", @@ -3856,7 +3857,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno) { const char *targ_name = kernel_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id); - int perm_flags = PTR_MAYBE_NULL; + int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED; const char *reg_name = ""; /* Only unreferenced case accepts untrusted pointers */ @@ -4732,6 +4733,9 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (type_flag(reg->type) & PTR_UNTRUSTED) flag |= PTR_UNTRUSTED; + /* Any pointer obtained from walking a trusted pointer is no longer trusted. */ + flag &= ~PTR_TRUSTED; + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); @@ -5844,6 +5848,7 @@ static const struct bpf_reg_types btf_id_sock_common_types = { PTR_TO_TCP_SOCK, PTR_TO_XDP_SOCK, PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, }, .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], }; @@ -5884,8 +5889,18 @@ static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; -static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; -static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_BTF_ID | MEM_PERCPU } }; +static const struct bpf_reg_types btf_ptr_types = { + .types = { + PTR_TO_BTF_ID, + PTR_TO_BTF_ID | PTR_TRUSTED, + }, +}; +static const struct bpf_reg_types percpu_btf_ptr_types = { + .types = { + PTR_TO_BTF_ID | MEM_PERCPU, + PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED, + } +}; static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } }; static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } }; static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5973,7 +5988,7 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, return -EACCES; found: - if (reg->type == PTR_TO_BTF_ID) { + if (reg->type == PTR_TO_BTF_ID || reg->type & PTR_TRUSTED) { /* For bpf_sk_release, it needs to match against first member * 'struct sock_common', hence make an exception for it. This * allows bpf_sk_release to work for multiple socket types. @@ -6055,6 +6070,8 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, */ case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: + case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset * can be non-zero. @@ -7939,6 +7956,25 @@ static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); } +static bool is_trusted_reg(const struct bpf_reg_state *reg) +{ + /* A referenced register is always trusted. */ + if (reg->ref_obj_id) + return true; + + /* If a register is not referenced, it is trusted if it has either the + * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the + * other type modifiers may be safe, but we elect to take an opt-in + * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are + * not. + * + * Eventually, we should make PTR_TRUSTED the single source of truth + * for whether a register is trusted. + */ + return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && + !bpf_type_has_unsafe_modifiers(reg->type); +} + static bool __kfunc_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) @@ -8220,7 +8256,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, const char *reg_ref_tname; u32 reg_ref_id; - if (reg->type == PTR_TO_BTF_ID) { + if (base_type(reg->type) == PTR_TO_BTF_ID) { reg_btf = reg->btf; reg_ref_id = reg->btf_id; } else { @@ -8366,6 +8402,7 @@ static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_ ptr = reg->map_ptr; break; case PTR_TO_BTF_ID | MEM_ALLOC: + case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: ptr = reg->btf; break; default: @@ -8596,8 +8633,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta)) break; - if (!reg->ref_obj_id) { - verbose(env, "R%d must be referenced\n", regno); + + if (!is_trusted_reg(reg)) { + verbose(env, "R%d must be referenced or trusted\n", regno); return -EINVAL; } fallthrough; @@ -8702,9 +8740,13 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ - if (reg->type != PTR_TO_BTF_ID && - (!reg2btf_ids[base_type(reg->type)] || type_flag(reg->type))) { - verbose(env, "arg#%d expected pointer to btf or socket\n", i); + if ((base_type(reg->type) != PTR_TO_BTF_ID || + bpf_type_has_unsafe_modifiers(reg->type)) && + !reg2btf_ids[base_type(reg->type)]) { + verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); + verbose(env, "expected %s or socket\n", + reg_type_str(env, base_type(reg->type) | + (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); @@ -14713,6 +14755,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) break; case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_UNTRUSTED: + case PTR_TO_BTF_ID | PTR_TRUSTED: /* PTR_TO_BTF_ID | MEM_ALLOC always has a valid lifetime, unlike * PTR_TO_BTF_ID, and an active ref_obj_id, but the same cannot * be said once it is marked PTR_UNTRUSTED, hence we must handle @@ -14720,6 +14763,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: + case PTR_TO_BTF_ID | PTR_UNTRUSTED | PTR_TRUSTED: + case PTR_TO_BTF_ID | PTR_UNTRUSTED | MEM_ALLOC | PTR_TRUSTED: if (type == BPF_READ) { insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f2d8d070d024..5b9008bc597b 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -774,7 +774,7 @@ BPF_CALL_0(bpf_get_current_task_btf) const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, - .ret_type = RET_PTR_TO_BTF_ID, + .ret_type = RET_PTR_TO_BTF_ID_TRUSTED, .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index d15c91de995f..4517d2bd186a 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -61,7 +61,9 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; - if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + if (base_type(info->reg_type) == PTR_TO_BTF_ID && + !bpf_type_has_unsafe_modifiers(info->reg_type) && + info->btf_id == sock_id) /* promote it to tcp_sock */ info->btf_id = tcp_sock_id; diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 86d6fef2e3b4..3193915c5ee6 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -109,7 +109,7 @@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, - .errstr = "arg#0 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 3 }, { "bpf_kfunc_call_test_release", 5 }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 55cba01c99d5..9540164712b7 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -142,7 +142,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_user_key", 2 }, { "bpf_key_put", 4 }, @@ -163,7 +163,7 @@ .kfunc = "bpf", .expected_attach_type = BPF_LSM_MAC, .flags = BPF_F_SLEEPABLE, - .errstr = "arg#0 expected pointer to btf or socket", + .errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket", .fixup_kfunc_btf_id = { { "bpf_lookup_system_key", 1 }, { "bpf_key_put", 3 }, -- cgit v1.2.3 From fd264ca020948a743e4c36731dfdecc4a812153c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 20 Nov 2022 11:54:32 -0800 Subject: bpf: Add a kfunc to type cast from bpf uapi ctx to kernel ctx Implement bpf_cast_to_kern_ctx() kfunc which does a type cast of a uapi ctx object to the corresponding kernel ctx. Previously if users want to access some data available in kctx but not in uapi ctx, bpf_probe_read_kernel() helper is needed. The introduction of bpf_cast_to_kern_ctx() allows direct memory access which makes code simpler and easier to understand. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221120195432.3113982-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf.h | 5 +++++ kernel/bpf/btf.c | 20 ++++++++++++++++++++ kernel/bpf/helpers.c | 6 ++++++ kernel/bpf/verifier.c | 22 ++++++++++++++++++++++ 4 files changed, 53 insertions(+) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index d38aa4251c28..9ed00077db6e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -487,6 +487,7 @@ const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); +int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type); bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2); #else @@ -531,6 +532,10 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, { return NULL; } +static inline int get_kern_ctx_btf_id(struct bpf_verifier_log *log, + enum bpf_prog_type prog_type) { + return -EINVAL; +} static inline bool btf_types_are_same(const struct btf *btf1, u32 id1, const struct btf *btf2, u32 id2) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1c78d4df9e18..1a59cc7ad730 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5603,6 +5603,26 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, return kern_ctx_type->type; } +int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type) +{ + const struct btf_member *kctx_member; + const struct btf_type *conv_struct; + const struct btf_type *kctx_type; + u32 kctx_type_id; + + conv_struct = bpf_ctx_convert.t; + /* get member for kernel ctx type */ + kctx_member = btf_type_member(conv_struct) + bpf_ctx_convert_map[prog_type] * 2 + 1; + kctx_type_id = kctx_member->type; + kctx_type = btf_type_by_id(btf_vmlinux, kctx_type_id); + if (!btf_type_is_struct(kctx_type)) { + bpf_log(log, "kern ctx type id %u is not a struct\n", kctx_type_id); + return -EINVAL; + } + + return kctx_type_id; +} + BTF_ID_LIST(bpf_ctx_convert_btf_id) BTF_ID(struct, bpf_ctx_convert) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8e0d80b6bf09..e45e72676f5a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1879,6 +1879,11 @@ void bpf_task_release(struct task_struct *p) put_task_struct_rcu_user(p); } +void *bpf_cast_to_kern_ctx(void *obj) +{ + return obj; +} + __diag_pop(); BTF_SET8_START(generic_btf_ids) @@ -1907,6 +1912,7 @@ BTF_ID(struct, task_struct) BTF_ID(func, bpf_task_release) BTF_SET8_START(common_btf_ids) +BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb090af35477..d63cc0fb0a9c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7907,6 +7907,7 @@ struct bpf_kfunc_call_arg_meta { u32 ref_obj_id; u8 release_regno; bool r0_rdonly; + u32 ret_btf_id; u64 r0_size; struct { u64 value; @@ -8151,6 +8152,7 @@ enum special_kfunc_type { KF_bpf_list_push_back, KF_bpf_list_pop_front, KF_bpf_list_pop_back, + KF_bpf_cast_to_kern_ctx, }; BTF_SET_START(special_kfunc_set) @@ -8160,6 +8162,7 @@ BTF_ID(func, bpf_list_push_front) BTF_ID(func, bpf_list_push_back) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) +BTF_ID(func, bpf_cast_to_kern_ctx) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -8169,6 +8172,7 @@ BTF_ID(func, bpf_list_push_front) BTF_ID(func, bpf_list_push_back) BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) +BTF_ID(func, bpf_cast_to_kern_ctx) static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, @@ -8182,6 +8186,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg = ®s[regno]; bool arg_mem_size = false; + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) + return KF_ARG_PTR_TO_CTX; + /* In this function, we verify the kfunc's BTF as per the argument type, * leaving the rest of the verification with respect to the register * type to our caller. When a set of conditions hold in the BTF type of @@ -8668,6 +8675,13 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "arg#%d expected pointer to ctx, but got %s\n", i, btf_type_str(t)); return -EINVAL; } + + if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + ret = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog)); + if (ret < 0) + return -EINVAL; + meta->ret_btf_id = ret; + } break; case KF_ARG_PTR_TO_ALLOC_BTF_ID: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { @@ -8922,6 +8936,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, regs[BPF_REG_0].btf = field->list_head.btf; regs[BPF_REG_0].btf_id = field->list_head.value_btf_id; regs[BPF_REG_0].off = field->list_head.node_offset; + } else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; + regs[BPF_REG_0].btf = desc_btf; + regs[BPF_REG_0].btf_id = meta.ret_btf_id; } else { verbose(env, "kernel function %s unhandled dynamic return type\n", meta.func_name); @@ -15175,6 +15194,9 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, insn_buf[1] = addr[1]; insn_buf[2] = *insn; *cnt = 3; + } else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { + insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1); + *cnt = 1; } return 0; } -- cgit v1.2.3 From a3400e8746b626531099e4d9fd8eac41be066683 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 18 Nov 2022 10:46:08 -0800 Subject: mptcp: more detailed error reporting on endpoint creation Endpoint creation can fail for a number of reasons; in case of failure append the error number to the extended ack message, using a newly introduced generic helper. Additionally let mptcp_pm_nl_append_new_local_addr() report different error reasons. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/net/genetlink.h | 3 +++ net/mptcp/pm_netlink.c | 24 +++++++++++++----------- 2 files changed, 16 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/genetlink.h b/include/net/genetlink.h index d21210709f84..ed4622dd4828 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -125,6 +125,9 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) +#define GENL_SET_ERR_MSG_FMT(info, msg, args...) \ + NL_SET_ERR_MSG_FMT((info)->extack, msg, ##args) + /* Report that a root attribute is missing */ #define GENL_REQ_ATTR_CHECK(info, attr) ({ \ struct genl_info *__info = (info); \ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index fdf2ee29f762..d66fbd558263 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -912,10 +912,14 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, */ if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID) pernet->next_id = 1; - if (pernet->addrs >= MPTCP_PM_ADDR_MAX) + if (pernet->addrs >= MPTCP_PM_ADDR_MAX) { + ret = -ERANGE; goto out; - if (test_bit(entry->addr.id, pernet->id_bitmap)) + } + if (test_bit(entry->addr.id, pernet->id_bitmap)) { + ret = -EBUSY; goto out; + } /* do not insert duplicate address, differentiate on port only * singled addresses @@ -929,8 +933,10 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, * endpoint is an implicit one and the user-space * did not provide an endpoint id */ - if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) + if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) { + ret = -EEXIST; goto out; + } if (entry->addr.id) goto out; @@ -1016,16 +1022,12 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, addrlen = sizeof(struct sockaddr_in6); #endif err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen); - if (err) { - pr_warn("kernel_bind error, err=%d", err); + if (err) return err; - } err = kernel_listen(ssock, backlog); - if (err) { - pr_warn("kernel_listen error, err=%d", err); + if (err) return err; - } return 0; } @@ -1329,13 +1331,13 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) if (entry->addr.port) { ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); if (ret) { - GENL_SET_ERR_MSG(info, "create listen socket error"); + GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret); goto out_free; } } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); if (ret < 0) { - GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); + GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; } -- cgit v1.2.3 From 33d5eeb9a684a2e962ca0be3fe557a2c9f48d8e2 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 19 Nov 2022 15:14:04 -0800 Subject: net: mscc: ocelot: remove redundant stats_layout pointers Ever since commit 4d1d157fb6a4 ("net: mscc: ocelot: share the common stat definitions between all drivers") the stats_layout entry in ocelot and felix drivers have become redundant. Remove the unnecessary code. Suggested-by: Vladimir Oltean Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- drivers/net/dsa/ocelot/felix.c | 1 - drivers/net/dsa/ocelot/felix.h | 1 - drivers/net/dsa/ocelot/felix_vsc9959.c | 5 ----- drivers/net/dsa/ocelot/seville_vsc9953.c | 5 ----- drivers/net/ethernet/mscc/ocelot_stats.c | 20 ++++++++++++-------- drivers/net/ethernet/mscc/ocelot_vsc7514.c | 5 ----- include/soc/mscc/ocelot.h | 1 - 7 files changed, 12 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 44e160f32067..3b738cb2ae6e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1363,7 +1363,6 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return -ENOMEM; ocelot->map = felix->info->map; - ocelot->stats_layout = felix->info->stats_layout; ocelot->num_mact_rows = felix->info->num_mact_rows; ocelot->vcap = felix->info->vcap; ocelot->vcap_pol.base = felix->info->vcap_pol_base; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 42338116eed0..be22d6ccd7c8 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -28,7 +28,6 @@ struct felix_info { const struct ocelot_ops *ops; const u32 *port_modes; int num_mact_rows; - const struct ocelot_stat_layout *stats_layout; int num_ports; int num_tx_queues; struct vcap_props *vcap; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index b0ae8d6156f6..01ac70fd7ddf 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -565,10 +565,6 @@ static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = { [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 7, 4), }; -static const struct ocelot_stat_layout vsc9959_stats_layout[OCELOT_NUM_STATS] = { - OCELOT_COMMON_STATS, -}; - static const struct vcap_field vsc9959_vcap_es0_keys[] = { [VCAP_ES0_EGR_PORT] = { 0, 3}, [VCAP_ES0_IGR_PORT] = { 3, 3}, @@ -2546,7 +2542,6 @@ static const struct felix_info felix_info_vsc9959 = { .regfields = vsc9959_regfields, .map = vsc9959_regmap, .ops = &vsc9959_ops, - .stats_layout = vsc9959_stats_layout, .vcap = vsc9959_vcap_props, .vcap_pol_base = VSC9959_VCAP_POLICER_BASE, .vcap_pol_max = VSC9959_VCAP_POLICER_MAX, diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 6500c1697dd6..88ed3a2e487a 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -543,10 +543,6 @@ static const struct reg_field vsc9953_regfields[REGFIELD_MAX] = { [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 11, 4), }; -static const struct ocelot_stat_layout vsc9953_stats_layout[OCELOT_NUM_STATS] = { - OCELOT_COMMON_STATS, -}; - static const struct vcap_field vsc9953_vcap_es0_keys[] = { [VCAP_ES0_EGR_PORT] = { 0, 4}, [VCAP_ES0_IGR_PORT] = { 4, 4}, @@ -970,7 +966,6 @@ static const struct felix_info seville_info_vsc9953 = { .regfields = vsc9953_regfields, .map = vsc9953_regmap, .ops = &vsc9953_ops, - .stats_layout = vsc9953_stats_layout, .vcap = vsc9953_vcap_props, .vcap_pol_base = VSC9953_VCAP_POLICER_BASE, .vcap_pol_max = VSC9953_VCAP_POLICER_MAX, diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index dbd20b125cea..5dc132f61d6a 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -9,6 +9,10 @@ #include #include "ocelot.h" +static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = { + OCELOT_COMMON_STATS, +}; + /* Read the counters from hardware and keep them in region->buf. * Caller must hold &ocelot->stat_view_lock. */ @@ -93,10 +97,10 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data) return; for (i = 0; i < OCELOT_NUM_STATS; i++) { - if (ocelot->stats_layout[i].name[0] == '\0') + if (ocelot_stats_layout[i].name[0] == '\0') continue; - memcpy(data + i * ETH_GSTRING_LEN, ocelot->stats_layout[i].name, + memcpy(data + i * ETH_GSTRING_LEN, ocelot_stats_layout[i].name, ETH_GSTRING_LEN); } } @@ -137,7 +141,7 @@ int ocelot_get_sset_count(struct ocelot *ocelot, int port, int sset) return -EOPNOTSUPP; for (i = 0; i < OCELOT_NUM_STATS; i++) - if (ocelot->stats_layout[i].name[0] != '\0') + if (ocelot_stats_layout[i].name[0] != '\0') num_stats++; return num_stats; @@ -154,7 +158,7 @@ static void ocelot_port_ethtool_stats_cb(struct ocelot *ocelot, int port, for (i = 0; i < OCELOT_NUM_STATS; i++) { int index = port * OCELOT_NUM_STATS + i; - if (ocelot->stats_layout[i].name[0] == '\0') + if (ocelot_stats_layout[i].name[0] == '\0') continue; *data++ = ocelot->stats[index]; @@ -389,10 +393,10 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot) INIT_LIST_HEAD(&ocelot->stats_regions); for (i = 0; i < OCELOT_NUM_STATS; i++) { - if (!ocelot->stats_layout[i].reg) + if (!ocelot_stats_layout[i].reg) continue; - if (region && ocelot->stats_layout[i].reg == last + 4) { + if (region && ocelot_stats_layout[i].reg == last + 4) { region->count++; } else { region = devm_kzalloc(ocelot->dev, sizeof(*region), @@ -400,12 +404,12 @@ static int ocelot_prepare_stats_regions(struct ocelot *ocelot) if (!region) return -ENOMEM; - region->base = ocelot->stats_layout[i].reg; + region->base = ocelot_stats_layout[i].reg; region->count = 1; list_add_tail(®ion->node, &ocelot->stats_regions); } - last = ocelot->stats_layout[i].reg; + last = ocelot_stats_layout[i].reg; } list_for_each_entry(region, &ocelot->stats_regions, node) { diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 93431d2ff4f1..b097fd4a4061 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -100,10 +100,6 @@ static const struct reg_field ocelot_regfields[REGFIELD_MAX] = { [SYS_PAUSE_CFG_PAUSE_ENA] = REG_FIELD_ID(SYS_PAUSE_CFG, 0, 1, 12, 4), }; -static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = { - OCELOT_COMMON_STATS, -}; - static void ocelot_pll5_init(struct ocelot *ocelot) { /* Configure PLL5. This will need a proper CCF driver @@ -138,7 +134,6 @@ static int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) int ret; ocelot->map = ocelot_regmap; - ocelot->stats_layout = ocelot_stats_layout; ocelot->num_mact_rows = 1024; ocelot->ops = ops; diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 967ba30ea636..995b5950afe6 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -967,7 +967,6 @@ struct ocelot { struct regmap *targets[TARGET_MAX]; struct regmap_field *regfields[REGFIELD_MAX]; const u32 *const *map; - const struct ocelot_stat_layout *stats_layout; struct list_head stats_regions; u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM]; -- cgit v1.2.3 From a3bb8f521fd8703cdb429d3e52f3e6802706c87d Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sat, 19 Nov 2022 15:14:05 -0800 Subject: net: mscc: ocelot: remove unnecessary exposure of stats structures Since commit 4d1d157fb6a4 ("net: mscc: ocelot: share the common stat definitions between all drivers") there is no longer a need to share the stats structures to the world. Relocate these definitions to inside ocelot_stats.c instead of a global include header. Signed-off-by: Colin Foster Reviewed-by: Vladimir Oltean Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mscc/ocelot_stats.c | 216 +++++++++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 215 ------------------------------ 2 files changed, 216 insertions(+), 215 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index 5dc132f61d6a..68e9f450c468 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -9,6 +9,221 @@ #include #include "ocelot.h" +enum ocelot_stat { + OCELOT_STAT_RX_OCTETS, + OCELOT_STAT_RX_UNICAST, + OCELOT_STAT_RX_MULTICAST, + OCELOT_STAT_RX_BROADCAST, + OCELOT_STAT_RX_SHORTS, + OCELOT_STAT_RX_FRAGMENTS, + OCELOT_STAT_RX_JABBERS, + OCELOT_STAT_RX_CRC_ALIGN_ERRS, + OCELOT_STAT_RX_SYM_ERRS, + OCELOT_STAT_RX_64, + OCELOT_STAT_RX_65_127, + OCELOT_STAT_RX_128_255, + OCELOT_STAT_RX_256_511, + OCELOT_STAT_RX_512_1023, + OCELOT_STAT_RX_1024_1526, + OCELOT_STAT_RX_1527_MAX, + OCELOT_STAT_RX_PAUSE, + OCELOT_STAT_RX_CONTROL, + OCELOT_STAT_RX_LONGS, + OCELOT_STAT_RX_CLASSIFIED_DROPS, + OCELOT_STAT_RX_RED_PRIO_0, + OCELOT_STAT_RX_RED_PRIO_1, + OCELOT_STAT_RX_RED_PRIO_2, + OCELOT_STAT_RX_RED_PRIO_3, + OCELOT_STAT_RX_RED_PRIO_4, + OCELOT_STAT_RX_RED_PRIO_5, + OCELOT_STAT_RX_RED_PRIO_6, + OCELOT_STAT_RX_RED_PRIO_7, + OCELOT_STAT_RX_YELLOW_PRIO_0, + OCELOT_STAT_RX_YELLOW_PRIO_1, + OCELOT_STAT_RX_YELLOW_PRIO_2, + OCELOT_STAT_RX_YELLOW_PRIO_3, + OCELOT_STAT_RX_YELLOW_PRIO_4, + OCELOT_STAT_RX_YELLOW_PRIO_5, + OCELOT_STAT_RX_YELLOW_PRIO_6, + OCELOT_STAT_RX_YELLOW_PRIO_7, + OCELOT_STAT_RX_GREEN_PRIO_0, + OCELOT_STAT_RX_GREEN_PRIO_1, + OCELOT_STAT_RX_GREEN_PRIO_2, + OCELOT_STAT_RX_GREEN_PRIO_3, + OCELOT_STAT_RX_GREEN_PRIO_4, + OCELOT_STAT_RX_GREEN_PRIO_5, + OCELOT_STAT_RX_GREEN_PRIO_6, + OCELOT_STAT_RX_GREEN_PRIO_7, + OCELOT_STAT_TX_OCTETS, + OCELOT_STAT_TX_UNICAST, + OCELOT_STAT_TX_MULTICAST, + OCELOT_STAT_TX_BROADCAST, + OCELOT_STAT_TX_COLLISION, + OCELOT_STAT_TX_DROPS, + OCELOT_STAT_TX_PAUSE, + OCELOT_STAT_TX_64, + OCELOT_STAT_TX_65_127, + OCELOT_STAT_TX_128_255, + OCELOT_STAT_TX_256_511, + OCELOT_STAT_TX_512_1023, + OCELOT_STAT_TX_1024_1526, + OCELOT_STAT_TX_1527_MAX, + OCELOT_STAT_TX_YELLOW_PRIO_0, + OCELOT_STAT_TX_YELLOW_PRIO_1, + OCELOT_STAT_TX_YELLOW_PRIO_2, + OCELOT_STAT_TX_YELLOW_PRIO_3, + OCELOT_STAT_TX_YELLOW_PRIO_4, + OCELOT_STAT_TX_YELLOW_PRIO_5, + OCELOT_STAT_TX_YELLOW_PRIO_6, + OCELOT_STAT_TX_YELLOW_PRIO_7, + OCELOT_STAT_TX_GREEN_PRIO_0, + OCELOT_STAT_TX_GREEN_PRIO_1, + OCELOT_STAT_TX_GREEN_PRIO_2, + OCELOT_STAT_TX_GREEN_PRIO_3, + OCELOT_STAT_TX_GREEN_PRIO_4, + OCELOT_STAT_TX_GREEN_PRIO_5, + OCELOT_STAT_TX_GREEN_PRIO_6, + OCELOT_STAT_TX_GREEN_PRIO_7, + OCELOT_STAT_TX_AGED, + OCELOT_STAT_DROP_LOCAL, + OCELOT_STAT_DROP_TAIL, + OCELOT_STAT_DROP_YELLOW_PRIO_0, + OCELOT_STAT_DROP_YELLOW_PRIO_1, + OCELOT_STAT_DROP_YELLOW_PRIO_2, + OCELOT_STAT_DROP_YELLOW_PRIO_3, + OCELOT_STAT_DROP_YELLOW_PRIO_4, + OCELOT_STAT_DROP_YELLOW_PRIO_5, + OCELOT_STAT_DROP_YELLOW_PRIO_6, + OCELOT_STAT_DROP_YELLOW_PRIO_7, + OCELOT_STAT_DROP_GREEN_PRIO_0, + OCELOT_STAT_DROP_GREEN_PRIO_1, + OCELOT_STAT_DROP_GREEN_PRIO_2, + OCELOT_STAT_DROP_GREEN_PRIO_3, + OCELOT_STAT_DROP_GREEN_PRIO_4, + OCELOT_STAT_DROP_GREEN_PRIO_5, + OCELOT_STAT_DROP_GREEN_PRIO_6, + OCELOT_STAT_DROP_GREEN_PRIO_7, + OCELOT_NUM_STATS, +}; + +struct ocelot_stat_layout { + u32 reg; + char name[ETH_GSTRING_LEN]; +}; + +/* 32-bit counter checked for wraparound by ocelot_port_update_stats() + * and copied to ocelot->stats. + */ +#define OCELOT_STAT(kind) \ + [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind } +/* Same as above, except also exported to ethtool -S. Standard counters should + * only be exposed to more specific interfaces rather than by their string name. + */ +#define OCELOT_STAT_ETHTOOL(kind, ethtool_name) \ + [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind, .name = ethtool_name } + +#define OCELOT_COMMON_STATS \ + OCELOT_STAT_ETHTOOL(RX_OCTETS, "rx_octets"), \ + OCELOT_STAT_ETHTOOL(RX_UNICAST, "rx_unicast"), \ + OCELOT_STAT_ETHTOOL(RX_MULTICAST, "rx_multicast"), \ + OCELOT_STAT_ETHTOOL(RX_BROADCAST, "rx_broadcast"), \ + OCELOT_STAT_ETHTOOL(RX_SHORTS, "rx_shorts"), \ + OCELOT_STAT_ETHTOOL(RX_FRAGMENTS, "rx_fragments"), \ + OCELOT_STAT_ETHTOOL(RX_JABBERS, "rx_jabbers"), \ + OCELOT_STAT_ETHTOOL(RX_CRC_ALIGN_ERRS, "rx_crc_align_errs"), \ + OCELOT_STAT_ETHTOOL(RX_SYM_ERRS, "rx_sym_errs"), \ + OCELOT_STAT_ETHTOOL(RX_64, "rx_frames_below_65_octets"), \ + OCELOT_STAT_ETHTOOL(RX_65_127, "rx_frames_65_to_127_octets"), \ + OCELOT_STAT_ETHTOOL(RX_128_255, "rx_frames_128_to_255_octets"), \ + OCELOT_STAT_ETHTOOL(RX_256_511, "rx_frames_256_to_511_octets"), \ + OCELOT_STAT_ETHTOOL(RX_512_1023, "rx_frames_512_to_1023_octets"), \ + OCELOT_STAT_ETHTOOL(RX_1024_1526, "rx_frames_1024_to_1526_octets"), \ + OCELOT_STAT_ETHTOOL(RX_1527_MAX, "rx_frames_over_1526_octets"), \ + OCELOT_STAT_ETHTOOL(RX_PAUSE, "rx_pause"), \ + OCELOT_STAT_ETHTOOL(RX_CONTROL, "rx_control"), \ + OCELOT_STAT_ETHTOOL(RX_LONGS, "rx_longs"), \ + OCELOT_STAT_ETHTOOL(RX_CLASSIFIED_DROPS, "rx_classified_drops"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_0, "rx_red_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_1, "rx_red_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_2, "rx_red_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_3, "rx_red_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_4, "rx_red_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_5, "rx_red_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_6, "rx_red_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_RED_PRIO_7, "rx_red_prio_7"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_0, "rx_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_1, "rx_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_2, "rx_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_3, "rx_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_4, "rx_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_5, "rx_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_6, "rx_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_7, "rx_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_0, "rx_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_1, "rx_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_2, "rx_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_3, "rx_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_4, "rx_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_5, "rx_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_6, "rx_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_7, "rx_green_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_OCTETS, "tx_octets"), \ + OCELOT_STAT_ETHTOOL(TX_UNICAST, "tx_unicast"), \ + OCELOT_STAT_ETHTOOL(TX_MULTICAST, "tx_multicast"), \ + OCELOT_STAT_ETHTOOL(TX_BROADCAST, "tx_broadcast"), \ + OCELOT_STAT_ETHTOOL(TX_COLLISION, "tx_collision"), \ + OCELOT_STAT_ETHTOOL(TX_DROPS, "tx_drops"), \ + OCELOT_STAT_ETHTOOL(TX_PAUSE, "tx_pause"), \ + OCELOT_STAT_ETHTOOL(TX_64, "tx_frames_below_65_octets"), \ + OCELOT_STAT_ETHTOOL(TX_65_127, "tx_frames_65_to_127_octets"), \ + OCELOT_STAT_ETHTOOL(TX_128_255, "tx_frames_128_255_octets"), \ + OCELOT_STAT_ETHTOOL(TX_256_511, "tx_frames_256_511_octets"), \ + OCELOT_STAT_ETHTOOL(TX_512_1023, "tx_frames_512_1023_octets"), \ + OCELOT_STAT_ETHTOOL(TX_1024_1526, "tx_frames_1024_1526_octets"), \ + OCELOT_STAT_ETHTOOL(TX_1527_MAX, "tx_frames_over_1526_octets"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_0, "tx_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_1, "tx_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_2, "tx_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_3, "tx_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_4, "tx_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_5, "tx_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_6, "tx_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_7, "tx_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_0, "tx_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_1, "tx_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_2, "tx_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_3, "tx_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_4, "tx_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_5, "tx_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_6, "tx_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_7, "tx_green_prio_7"), \ + OCELOT_STAT_ETHTOOL(TX_AGED, "tx_aged"), \ + OCELOT_STAT_ETHTOOL(DROP_LOCAL, "drop_local"), \ + OCELOT_STAT_ETHTOOL(DROP_TAIL, "drop_tail"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_0, "drop_yellow_prio_0"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_1, "drop_yellow_prio_1"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_2, "drop_yellow_prio_2"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_3, "drop_yellow_prio_3"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_4, "drop_yellow_prio_4"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_5, "drop_yellow_prio_5"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_6, "drop_yellow_prio_6"), \ + OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_7, "drop_yellow_prio_7"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_0, "drop_green_prio_0"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_1, "drop_green_prio_1"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_2, "drop_green_prio_2"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_3, "drop_green_prio_3"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_4, "drop_green_prio_4"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_5, "drop_green_prio_5"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_6, "drop_green_prio_6"), \ + OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_7, "drop_green_prio_7") + +struct ocelot_stats_region { + struct list_head node; + u32 base; + int count; + u32 *buf; +}; + static const struct ocelot_stat_layout ocelot_stats_layout[OCELOT_NUM_STATS] = { OCELOT_COMMON_STATS, }; @@ -460,3 +675,4 @@ void ocelot_stats_deinit(struct ocelot *ocelot) cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); } + diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 995b5950afe6..df62be80a193 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -596,221 +596,6 @@ enum ocelot_ptp_pins { TOD_ACC_PIN }; -enum ocelot_stat { - OCELOT_STAT_RX_OCTETS, - OCELOT_STAT_RX_UNICAST, - OCELOT_STAT_RX_MULTICAST, - OCELOT_STAT_RX_BROADCAST, - OCELOT_STAT_RX_SHORTS, - OCELOT_STAT_RX_FRAGMENTS, - OCELOT_STAT_RX_JABBERS, - OCELOT_STAT_RX_CRC_ALIGN_ERRS, - OCELOT_STAT_RX_SYM_ERRS, - OCELOT_STAT_RX_64, - OCELOT_STAT_RX_65_127, - OCELOT_STAT_RX_128_255, - OCELOT_STAT_RX_256_511, - OCELOT_STAT_RX_512_1023, - OCELOT_STAT_RX_1024_1526, - OCELOT_STAT_RX_1527_MAX, - OCELOT_STAT_RX_PAUSE, - OCELOT_STAT_RX_CONTROL, - OCELOT_STAT_RX_LONGS, - OCELOT_STAT_RX_CLASSIFIED_DROPS, - OCELOT_STAT_RX_RED_PRIO_0, - OCELOT_STAT_RX_RED_PRIO_1, - OCELOT_STAT_RX_RED_PRIO_2, - OCELOT_STAT_RX_RED_PRIO_3, - OCELOT_STAT_RX_RED_PRIO_4, - OCELOT_STAT_RX_RED_PRIO_5, - OCELOT_STAT_RX_RED_PRIO_6, - OCELOT_STAT_RX_RED_PRIO_7, - OCELOT_STAT_RX_YELLOW_PRIO_0, - OCELOT_STAT_RX_YELLOW_PRIO_1, - OCELOT_STAT_RX_YELLOW_PRIO_2, - OCELOT_STAT_RX_YELLOW_PRIO_3, - OCELOT_STAT_RX_YELLOW_PRIO_4, - OCELOT_STAT_RX_YELLOW_PRIO_5, - OCELOT_STAT_RX_YELLOW_PRIO_6, - OCELOT_STAT_RX_YELLOW_PRIO_7, - OCELOT_STAT_RX_GREEN_PRIO_0, - OCELOT_STAT_RX_GREEN_PRIO_1, - OCELOT_STAT_RX_GREEN_PRIO_2, - OCELOT_STAT_RX_GREEN_PRIO_3, - OCELOT_STAT_RX_GREEN_PRIO_4, - OCELOT_STAT_RX_GREEN_PRIO_5, - OCELOT_STAT_RX_GREEN_PRIO_6, - OCELOT_STAT_RX_GREEN_PRIO_7, - OCELOT_STAT_TX_OCTETS, - OCELOT_STAT_TX_UNICAST, - OCELOT_STAT_TX_MULTICAST, - OCELOT_STAT_TX_BROADCAST, - OCELOT_STAT_TX_COLLISION, - OCELOT_STAT_TX_DROPS, - OCELOT_STAT_TX_PAUSE, - OCELOT_STAT_TX_64, - OCELOT_STAT_TX_65_127, - OCELOT_STAT_TX_128_255, - OCELOT_STAT_TX_256_511, - OCELOT_STAT_TX_512_1023, - OCELOT_STAT_TX_1024_1526, - OCELOT_STAT_TX_1527_MAX, - OCELOT_STAT_TX_YELLOW_PRIO_0, - OCELOT_STAT_TX_YELLOW_PRIO_1, - OCELOT_STAT_TX_YELLOW_PRIO_2, - OCELOT_STAT_TX_YELLOW_PRIO_3, - OCELOT_STAT_TX_YELLOW_PRIO_4, - OCELOT_STAT_TX_YELLOW_PRIO_5, - OCELOT_STAT_TX_YELLOW_PRIO_6, - OCELOT_STAT_TX_YELLOW_PRIO_7, - OCELOT_STAT_TX_GREEN_PRIO_0, - OCELOT_STAT_TX_GREEN_PRIO_1, - OCELOT_STAT_TX_GREEN_PRIO_2, - OCELOT_STAT_TX_GREEN_PRIO_3, - OCELOT_STAT_TX_GREEN_PRIO_4, - OCELOT_STAT_TX_GREEN_PRIO_5, - OCELOT_STAT_TX_GREEN_PRIO_6, - OCELOT_STAT_TX_GREEN_PRIO_7, - OCELOT_STAT_TX_AGED, - OCELOT_STAT_DROP_LOCAL, - OCELOT_STAT_DROP_TAIL, - OCELOT_STAT_DROP_YELLOW_PRIO_0, - OCELOT_STAT_DROP_YELLOW_PRIO_1, - OCELOT_STAT_DROP_YELLOW_PRIO_2, - OCELOT_STAT_DROP_YELLOW_PRIO_3, - OCELOT_STAT_DROP_YELLOW_PRIO_4, - OCELOT_STAT_DROP_YELLOW_PRIO_5, - OCELOT_STAT_DROP_YELLOW_PRIO_6, - OCELOT_STAT_DROP_YELLOW_PRIO_7, - OCELOT_STAT_DROP_GREEN_PRIO_0, - OCELOT_STAT_DROP_GREEN_PRIO_1, - OCELOT_STAT_DROP_GREEN_PRIO_2, - OCELOT_STAT_DROP_GREEN_PRIO_3, - OCELOT_STAT_DROP_GREEN_PRIO_4, - OCELOT_STAT_DROP_GREEN_PRIO_5, - OCELOT_STAT_DROP_GREEN_PRIO_6, - OCELOT_STAT_DROP_GREEN_PRIO_7, - OCELOT_NUM_STATS, -}; - -struct ocelot_stat_layout { - u32 reg; - char name[ETH_GSTRING_LEN]; -}; - -/* 32-bit counter checked for wraparound by ocelot_port_update_stats() - * and copied to ocelot->stats. - */ -#define OCELOT_STAT(kind) \ - [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind } -/* Same as above, except also exported to ethtool -S. Standard counters should - * only be exposed to more specific interfaces rather than by their string name. - */ -#define OCELOT_STAT_ETHTOOL(kind, ethtool_name) \ - [OCELOT_STAT_ ## kind] = { .reg = SYS_COUNT_ ## kind, .name = ethtool_name } - -#define OCELOT_COMMON_STATS \ - OCELOT_STAT_ETHTOOL(RX_OCTETS, "rx_octets"), \ - OCELOT_STAT_ETHTOOL(RX_UNICAST, "rx_unicast"), \ - OCELOT_STAT_ETHTOOL(RX_MULTICAST, "rx_multicast"), \ - OCELOT_STAT_ETHTOOL(RX_BROADCAST, "rx_broadcast"), \ - OCELOT_STAT_ETHTOOL(RX_SHORTS, "rx_shorts"), \ - OCELOT_STAT_ETHTOOL(RX_FRAGMENTS, "rx_fragments"), \ - OCELOT_STAT_ETHTOOL(RX_JABBERS, "rx_jabbers"), \ - OCELOT_STAT_ETHTOOL(RX_CRC_ALIGN_ERRS, "rx_crc_align_errs"), \ - OCELOT_STAT_ETHTOOL(RX_SYM_ERRS, "rx_sym_errs"), \ - OCELOT_STAT_ETHTOOL(RX_64, "rx_frames_below_65_octets"), \ - OCELOT_STAT_ETHTOOL(RX_65_127, "rx_frames_65_to_127_octets"), \ - OCELOT_STAT_ETHTOOL(RX_128_255, "rx_frames_128_to_255_octets"), \ - OCELOT_STAT_ETHTOOL(RX_256_511, "rx_frames_256_to_511_octets"), \ - OCELOT_STAT_ETHTOOL(RX_512_1023, "rx_frames_512_to_1023_octets"), \ - OCELOT_STAT_ETHTOOL(RX_1024_1526, "rx_frames_1024_to_1526_octets"), \ - OCELOT_STAT_ETHTOOL(RX_1527_MAX, "rx_frames_over_1526_octets"), \ - OCELOT_STAT_ETHTOOL(RX_PAUSE, "rx_pause"), \ - OCELOT_STAT_ETHTOOL(RX_CONTROL, "rx_control"), \ - OCELOT_STAT_ETHTOOL(RX_LONGS, "rx_longs"), \ - OCELOT_STAT_ETHTOOL(RX_CLASSIFIED_DROPS, "rx_classified_drops"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_0, "rx_red_prio_0"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_1, "rx_red_prio_1"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_2, "rx_red_prio_2"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_3, "rx_red_prio_3"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_4, "rx_red_prio_4"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_5, "rx_red_prio_5"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_6, "rx_red_prio_6"), \ - OCELOT_STAT_ETHTOOL(RX_RED_PRIO_7, "rx_red_prio_7"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_0, "rx_yellow_prio_0"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_1, "rx_yellow_prio_1"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_2, "rx_yellow_prio_2"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_3, "rx_yellow_prio_3"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_4, "rx_yellow_prio_4"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_5, "rx_yellow_prio_5"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_6, "rx_yellow_prio_6"), \ - OCELOT_STAT_ETHTOOL(RX_YELLOW_PRIO_7, "rx_yellow_prio_7"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_0, "rx_green_prio_0"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_1, "rx_green_prio_1"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_2, "rx_green_prio_2"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_3, "rx_green_prio_3"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_4, "rx_green_prio_4"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_5, "rx_green_prio_5"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_6, "rx_green_prio_6"), \ - OCELOT_STAT_ETHTOOL(RX_GREEN_PRIO_7, "rx_green_prio_7"), \ - OCELOT_STAT_ETHTOOL(TX_OCTETS, "tx_octets"), \ - OCELOT_STAT_ETHTOOL(TX_UNICAST, "tx_unicast"), \ - OCELOT_STAT_ETHTOOL(TX_MULTICAST, "tx_multicast"), \ - OCELOT_STAT_ETHTOOL(TX_BROADCAST, "tx_broadcast"), \ - OCELOT_STAT_ETHTOOL(TX_COLLISION, "tx_collision"), \ - OCELOT_STAT_ETHTOOL(TX_DROPS, "tx_drops"), \ - OCELOT_STAT_ETHTOOL(TX_PAUSE, "tx_pause"), \ - OCELOT_STAT_ETHTOOL(TX_64, "tx_frames_below_65_octets"), \ - OCELOT_STAT_ETHTOOL(TX_65_127, "tx_frames_65_to_127_octets"), \ - OCELOT_STAT_ETHTOOL(TX_128_255, "tx_frames_128_255_octets"), \ - OCELOT_STAT_ETHTOOL(TX_256_511, "tx_frames_256_511_octets"), \ - OCELOT_STAT_ETHTOOL(TX_512_1023, "tx_frames_512_1023_octets"), \ - OCELOT_STAT_ETHTOOL(TX_1024_1526, "tx_frames_1024_1526_octets"), \ - OCELOT_STAT_ETHTOOL(TX_1527_MAX, "tx_frames_over_1526_octets"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_0, "tx_yellow_prio_0"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_1, "tx_yellow_prio_1"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_2, "tx_yellow_prio_2"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_3, "tx_yellow_prio_3"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_4, "tx_yellow_prio_4"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_5, "tx_yellow_prio_5"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_6, "tx_yellow_prio_6"), \ - OCELOT_STAT_ETHTOOL(TX_YELLOW_PRIO_7, "tx_yellow_prio_7"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_0, "tx_green_prio_0"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_1, "tx_green_prio_1"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_2, "tx_green_prio_2"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_3, "tx_green_prio_3"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_4, "tx_green_prio_4"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_5, "tx_green_prio_5"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_6, "tx_green_prio_6"), \ - OCELOT_STAT_ETHTOOL(TX_GREEN_PRIO_7, "tx_green_prio_7"), \ - OCELOT_STAT_ETHTOOL(TX_AGED, "tx_aged"), \ - OCELOT_STAT_ETHTOOL(DROP_LOCAL, "drop_local"), \ - OCELOT_STAT_ETHTOOL(DROP_TAIL, "drop_tail"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_0, "drop_yellow_prio_0"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_1, "drop_yellow_prio_1"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_2, "drop_yellow_prio_2"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_3, "drop_yellow_prio_3"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_4, "drop_yellow_prio_4"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_5, "drop_yellow_prio_5"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_6, "drop_yellow_prio_6"), \ - OCELOT_STAT_ETHTOOL(DROP_YELLOW_PRIO_7, "drop_yellow_prio_7"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_0, "drop_green_prio_0"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_1, "drop_green_prio_1"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_2, "drop_green_prio_2"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_3, "drop_green_prio_3"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_4, "drop_green_prio_4"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_5, "drop_green_prio_5"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_6, "drop_green_prio_6"), \ - OCELOT_STAT_ETHTOOL(DROP_GREEN_PRIO_7, "drop_green_prio_7") - -struct ocelot_stats_region { - struct list_head node; - u32 base; - int count; - u32 *buf; -}; - enum ocelot_tag_prefix { OCELOT_TAG_PREFIX_DISABLED = 0, OCELOT_TAG_PREFIX_NONE, -- cgit v1.2.3 From c5fb8ead3283955dc68671f853017b181f96fdc1 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 21 Nov 2022 15:55:39 +0200 Subject: net: dsa: unexport dsa_dev_to_net_device() dsa.o and dsa2.o are linked into the same dsa_core.o, there is no reason to export this symbol when its only caller is local. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 2 -- net/dsa/dsa.c | 1 - net/dsa/dsa_priv.h | 2 ++ 3 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 82da44561f4c..d5bfcb63d4c2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1285,8 +1285,6 @@ struct dsa_switch_driver { const struct dsa_switch_ops *ops; }; -struct net_device *dsa_dev_to_net_device(struct device *dev); - bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 4afd3edbd64d..07158c7560b5 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -182,7 +182,6 @@ struct net_device *dsa_dev_to_net_device(struct device *dev) return NULL; } -EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); /* Determine if we should defer delivery of skb until we have a rx timestamp. * diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 24e0ea218a35..b60987e8d931 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -247,6 +247,8 @@ const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol); const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name); void dsa_tag_driver_put(const struct dsa_device_ops *ops); +struct net_device *dsa_dev_to_net_device(struct device *dev); + bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b); bool dsa_schedule_work(struct work_struct *work); -- cgit v1.2.3 From 19d05ea712ecbbb67d302664da5ec58b37b9aece Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 21 Nov 2022 15:55:54 +0200 Subject: net: dsa: move tag_8021q headers to their proper place tag_8021q definitions are all over the place. Some are exported to linux/dsa/8021q.h (visible by DSA core, taggers, switch drivers and everyone else), and some are in dsa_priv.h. Move the structures that don't need external visibility into tag_8021q.c, and the ones which don't need the world or switch drivers to see them into tag_8021q.h. We also have the tag_8021q.h inclusion from switch.c, which is basically the entire reason why tag_8021q.c was built into DSA in commit 8b6e638b4be2 ("net: dsa: build tag_8021q.c as part of DSA core"). I still don't know how to better deal with that, so leave it alone. Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- include/linux/dsa/8021q.h | 31 +------------------------------ include/net/dsa.h | 1 + net/dsa/dsa_priv.h | 8 -------- net/dsa/port.c | 1 + net/dsa/switch.c | 1 + net/dsa/tag_8021q.c | 15 +++++++++++++++ net/dsa/tag_8021q.h | 27 +++++++++++++++++++++++++++ net/dsa/tag_ocelot_8021q.c | 1 + net/dsa/tag_sja1105.c | 1 + 9 files changed, 48 insertions(+), 38 deletions(-) create mode 100644 net/dsa/tag_8021q.h (limited to 'include') diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 3ed117e299ec..f3664ee12170 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -5,28 +5,8 @@ #ifndef _NET_DSA_8021Q_H #define _NET_DSA_8021Q_H -#include -#include #include - -struct dsa_switch; -struct dsa_port; -struct sk_buff; -struct net_device; - -struct dsa_tag_8021q_vlan { - struct list_head list; - int port; - u16 vid; - refcount_t refcount; -}; - -struct dsa_8021q_context { - struct dsa_switch *ds; - struct list_head vlans; - /* EtherType of RX VID, used for filtering on master interface */ - __be16 proto; -}; +#include int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); @@ -38,15 +18,6 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge); -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci); - -void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *vbid); - -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, - int vbid); - u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num); u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp); diff --git a/include/net/dsa.h b/include/net/dsa.h index d5bfcb63d4c2..96086289aa9b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -22,6 +22,7 @@ #include #include +struct dsa_8021q_context; struct tc_action; struct phy_device; struct fixed_phy_status; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index aa685d2309e0..265659954ffd 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -13,15 +13,7 @@ #define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG -struct dsa_notifier_tag_8021q_vlan_info; - /* netlink.c */ extern struct rtnl_link_ops dsa_link_ops __read_mostly; -/* tag_8021q.c */ -int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, - struct dsa_notifier_tag_8021q_vlan_info *info); -int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, - struct dsa_notifier_tag_8021q_vlan_info *info); - #endif diff --git a/net/dsa/port.c b/net/dsa/port.c index e6d5c05b41b4..67ad1adec2a2 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -16,6 +16,7 @@ #include "port.h" #include "slave.h" #include "switch.h" +#include "tag_8021q.h" /** * dsa_port_notify - Notify the switching fabric of changes to a port diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 4420af0081af..e53cc0c3c933 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -17,6 +17,7 @@ #include "port.h" #include "slave.h" #include "switch.h" +#include "tag_8021q.h" static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index abd994dc76d5..ac2eb933106e 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -11,6 +11,7 @@ #include "port.h" #include "switch.h" #include "tag.h" +#include "tag_8021q.h" /* Binary structure of the fake 12-bit VID field (when the TPID is * ETH_P_DSA_8021Q): @@ -63,6 +64,20 @@ #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) +struct dsa_tag_8021q_vlan { + struct list_head list; + int port; + u16 vid; + refcount_t refcount; +}; + +struct dsa_8021q_context { + struct dsa_switch *ds; + struct list_head vlans; + /* EtherType of RX VID, used for filtering on master interface */ + __be16 proto; +}; + u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num) { /* The VBID value of 0 is reserved for precise TX, but it is also diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h new file mode 100644 index 000000000000..b75cbaa028ef --- /dev/null +++ b/net/dsa/tag_8021q.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_TAG_8021Q_H +#define __DSA_TAG_8021Q_H + +#include + +#include "switch.h" + +struct sk_buff; +struct net_device; + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); + +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid); + +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, + int vbid); + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); + +#endif diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 7f0c2d71e89b..1f0b8c20eba5 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -12,6 +12,7 @@ #include #include "tag.h" +#include "tag_8021q.h" #define OCELOT_8021Q_NAME "ocelot-8021q" diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 8f581617e15c..f14f51b41491 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -7,6 +7,7 @@ #include #include "tag.h" +#include "tag_8021q.h" #define SJA1105_NAME "sja1105" #define SJA1110_NAME "sja1110" -- cgit v1.2.3 From beb3d47d1d3d7185bb401af628ad32ee204a9526 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 23 Nov 2022 07:57:59 -0800 Subject: bpf: Fix a BTF_ID_LIST bug with CONFIG_DEBUG_INFO_BTF not set With CONFIG_DEBUG_INFO_BTF not set, we hit the following compilation error, /.../kernel/bpf/verifier.c:8196:23: error: array index 6 is past the end of the array (that has type 'u32[5]' (aka 'unsigned int[5]')) [-Werror,-Warray-bounds] if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) ^ ~~~~~~~~~~~~~~~~~~~~~~~ /.../kernel/bpf/verifier.c:8174:1: note: array 'special_kfunc_list' declared here BTF_ID_LIST(special_kfunc_list) ^ /.../include/linux/btf_ids.h:207:27: note: expanded from macro 'BTF_ID_LIST' #define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; ^ /.../kernel/bpf/verifier.c:8443:19: error: array index 5 is past the end of the array (that has type 'u32[5]' (aka 'unsigned int[5]')) [-Werror,-Warray-bounds] btf_id == special_kfunc_list[KF_bpf_list_pop_back]; ^ ~~~~~~~~~~~~~~~~~~~~ /.../kernel/bpf/verifier.c:8174:1: note: array 'special_kfunc_list' declared here BTF_ID_LIST(special_kfunc_list) ^ /.../include/linux/btf_ids.h:207:27: note: expanded from macro 'BTF_ID_LIST' #define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; ... Fix the problem by increase the size of BTF_ID_LIST to 16 to avoid compilation error and also prevent potentially unintended issue due to out-of-bound access. Reported-by: kernel test robot Reported-by: Dan Carpenter Reported-by: Nathan Chancellor Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221123155759.2669749-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/btf_ids.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index c9744efd202f..93397711a68c 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -204,7 +204,7 @@ extern struct btf_id_set8 name; #else -#define BTF_ID_LIST(name) static u32 __maybe_unused name[5]; +#define BTF_ID_LIST(name) static u32 __maybe_unused name[16]; #define BTF_ID(prefix, name) #define BTF_ID_FLAGS(prefix, name, ...) #define BTF_ID_UNUSED -- cgit v1.2.3 From 72b43bde38de4aa05e6a7fa12d7965f48180deb6 Mon Sep 17 00:00:00 2001 From: Ji Rongfeng Date: Fri, 18 Nov 2022 16:18:18 +0800 Subject: bpf: Update bpf_{g,s}etsockopt() documentation * append missing optnames to the end * simplify bpf_getsockopt()'s doc Signed-off-by: Ji Rongfeng Link: https://lore.kernel.org/r/DU0P192MB15479B86200B1216EC90E162D6099@DU0P192MB1547.EURP192.PROD.OUTLOOK.COM Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 21 ++++++++++++--------- tools/include/uapi/linux/bpf.h | 23 +++++++++++++---------- 2 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ab86145df760..f89de51a45db 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2584,14 +2584,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -2808,12 +2813,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6580448e9f77..f89de51a45db 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2584,14 +2584,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -2647,7 +2652,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -2808,12 +2813,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * -- cgit v1.2.3 From 14e5f71e31ff3925cc970fa7907393ee7f4b748d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 22 Nov 2022 20:09:47 -0800 Subject: net: use %pS for kfree_skb tracing event location For the cases where 'reason' doesn't give any clue, it's still nice to be able to track the kfree_skb caller location. %p doesn't help much so let's use %pS which prints the symbol+offset. Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20221123040947.1015721-1-sdf@google.com Signed-off-by: Paolo Abeni --- include/trace/events/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 50a974f7dfb4..25ab1ff9423d 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,7 +42,7 @@ TRACE_EVENT(kfree_skb, __entry->reason = reason; ), - TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", + TP_printk("skbaddr=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) -- cgit v1.2.3 From 5a0f663f0189cf9e031e444f97c029717a99548d Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 23 Nov 2022 21:32:06 -0800 Subject: compiler_types: Define __rcu as __attribute__((btf_type_tag("rcu"))) Currently, without rcu attribute info in BTF, the verifier treats rcu tagged pointer as a normal pointer. This might be a problem for sleepable program where rcu_read_lock()/unlock() is not available. For example, for a sleepable fentry program, if rcu protected memory access is interleaved with a sleepable helper/kfunc, it is possible the memory access after the sleepable helper/kfunc might be invalid since the object might have been freed then. To prevent such cases, introducing rcu tagging for memory accesses in verifier can help to reject such programs. To enable rcu tagging in BTF, during kernel compilation, define __rcu as attribute btf_type_tag("rcu") so __rcu information can be preserved in dwarf and btf, and later can be used for bpf prog verification. Acked-by: KP Singh Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221124053206.2373141-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/compiler_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index eb0466236661..7c1afe0f4129 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -49,7 +49,8 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # endif # define __iomem # define __percpu BTF_TYPE_TAG(percpu) -# define __rcu +# define __rcu BTF_TYPE_TAG(rcu) + # define __chk_user_ptr(x) (void)0 # define __chk_io_ptr(x) (void)0 /* context/locking */ -- cgit v1.2.3 From 01685c5bddaa6df3d662c8afed5e5289fcc68e5a Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 23 Nov 2022 21:32:11 -0800 Subject: bpf: Introduce might_sleep field in bpf_func_proto Introduce bpf_func_proto->might_sleep to indicate a particular helper might sleep. This will make later check whether a helper might be sleepable or not easier. Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221124053211.2373553-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + kernel/bpf/bpf_lsm.c | 6 ++++-- kernel/bpf/helpers.c | 2 ++ kernel/bpf/verifier.c | 5 +++++ kernel/trace/bpf_trace.c | 4 ++-- 5 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c9eafa67f2a2..43fd7eeeeabb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -682,6 +682,7 @@ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; + bool might_sleep; enum bpf_return_type ret_type; union { struct { diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index d6c9b3705f24..ae0267f150b5 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -151,6 +151,7 @@ BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) static const struct bpf_func_proto bpf_ima_inode_hash_proto = { .func = bpf_ima_inode_hash, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], @@ -169,6 +170,7 @@ BTF_ID_LIST_SINGLE(bpf_ima_file_hash_btf_ids, struct, file) static const struct bpf_func_proto bpf_ima_file_hash_proto = { .func = bpf_ima_file_hash, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_ima_file_hash_btf_ids[0], @@ -221,9 +223,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_bprm_opts_set: return &bpf_bprm_opts_set_proto; case BPF_FUNC_ima_inode_hash: - return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; + return &bpf_ima_inode_hash_proto; case BPF_FUNC_ima_file_hash: - return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL; + return &bpf_ima_file_hash_proto; case BPF_FUNC_get_attach_cookie: return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL; #ifdef CONFIG_NET diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 2299bb0d89e5..9296b654dbd7 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -661,6 +661,7 @@ BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size, const struct bpf_func_proto bpf_copy_from_user_proto = { .func = bpf_copy_from_user, .gpl_only = false, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, @@ -691,6 +692,7 @@ BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size, const struct bpf_func_proto bpf_copy_from_user_task_proto = { .func = bpf_copy_from_user_task, .gpl_only = true, + .might_sleep = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9528a066cfa5..068cc885903c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -7516,6 +7516,11 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } + if (!env->prog->aux->sleepable && fn->might_sleep) { + verbose(env, "helper call might sleep in a non-sleepable prog\n"); + return -EINVAL; + } + /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 5b9008bc597b..3bbd3f0c810c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1485,9 +1485,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_task_stack: return &bpf_get_task_stack_proto; case BPF_FUNC_copy_from_user: - return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; + return &bpf_copy_from_user_proto; case BPF_FUNC_copy_from_user_task: - return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL; + return &bpf_copy_from_user_task_proto; case BPF_FUNC_snprintf_btf: return &bpf_snprintf_btf_proto; case BPF_FUNC_per_cpu_ptr: -- cgit v1.2.3 From 9bb00b2895cbfe0ad410457b605d0a72524168c1 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 23 Nov 2022 21:32:17 -0800 Subject: bpf: Add kfunc bpf_rcu_read_lock/unlock() Add two kfunc's bpf_rcu_read_lock() and bpf_rcu_read_unlock(). These two kfunc's can be used for all program types. The following is an example about how rcu pointer are used w.r.t. bpf_rcu_read_lock()/bpf_rcu_read_unlock(). struct task_struct { ... struct task_struct *last_wakee; struct task_struct __rcu *real_parent; ... }; Let us say prog does 'task = bpf_get_current_task_btf()' to get a 'task' pointer. The basic rules are: - 'real_parent = task->real_parent' should be inside bpf_rcu_read_lock region. This is to simulate rcu_dereference() operation. The 'real_parent' is marked as MEM_RCU only if (1). task->real_parent is inside bpf_rcu_read_lock region, and (2). task is a trusted ptr. So MEM_RCU marked ptr can be 'trusted' inside the bpf_rcu_read_lock region. - 'last_wakee = real_parent->last_wakee' should be inside bpf_rcu_read_lock region since it tries to access rcu protected memory. - the ptr 'last_wakee' will be marked as PTR_UNTRUSTED since in general it is not clear whether the object pointed by 'last_wakee' is valid or not even inside bpf_rcu_read_lock region. The verifier will reset all rcu pointer register states to untrusted at bpf_rcu_read_unlock() kfunc call site, so any such rcu pointer won't be trusted any more outside the bpf_rcu_read_lock() region. The current implementation does not support nested rcu read lock region in the prog. Acked-by: Martin KaFai Lau Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221124053217.2373910-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 + include/linux/bpf_verifier.h | 5 +- kernel/bpf/btf.c | 3 + kernel/bpf/helpers.c | 12 ++++ kernel/bpf/verifier.c | 162 +++++++++++++++++++++++++++++++++++-------- 5 files changed, 155 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 43fd7eeeeabb..c6aa6912ea16 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -572,6 +572,9 @@ enum bpf_type_flag { */ PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), + /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */ + MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), + __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 545152ac136c..c05aa6e1f6f5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -344,6 +344,7 @@ struct bpf_verifier_state { u32 id; } active_lock; bool speculative; + bool active_rcu_lock; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -445,6 +446,7 @@ struct bpf_insn_aux_data { u32 seen; /* this insn was processed by the verifier at env->pass_cnt */ bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */ bool zext_dst; /* this insn zero extends dst reg */ + bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ @@ -534,6 +536,7 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; + bool rcu_tag_supported; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; @@ -680,7 +683,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } -#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | MEM_RCU | PTR_TRUSTED) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9dbfda2b5c6c..bd3369100239 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6238,6 +6238,9 @@ error: /* check __percpu tag */ if (strcmp(tag_value, "percpu") == 0) tmp_flag = MEM_PERCPU; + /* check __rcu tag */ + if (strcmp(tag_value, "rcu") == 0) + tmp_flag = MEM_RCU; } stype = btf_type_skip_modifiers(btf, mtype->type, &id); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9296b654dbd7..a5a511430f2a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1990,6 +1990,16 @@ void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) return obj__ign; } +void bpf_rcu_read_lock(void) +{ + rcu_read_lock(); +} + +void bpf_rcu_read_unlock(void) +{ + rcu_read_unlock(); +} + __diag_pop(); BTF_SET8_START(generic_btf_ids) @@ -2031,6 +2041,8 @@ BTF_ID(func, bpf_cgroup_release) BTF_SET8_START(common_btf_ids) BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_ID_FLAGS(func, bpf_rdonly_cast) +BTF_ID_FLAGS(func, bpf_rcu_read_lock) +BTF_ID_FLAGS(func, bpf_rcu_read_unlock) BTF_SET8_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 068cc885903c..f4500479f1c2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -527,6 +527,14 @@ static bool is_callback_calling_function(enum bpf_func_id func_id) func_id == BPF_FUNC_user_ringbuf_drain; } +static bool is_storage_get_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_storage_get || + func_id == BPF_FUNC_inode_storage_get || + func_id == BPF_FUNC_task_storage_get || + func_id == BPF_FUNC_cgrp_storage_get; +} + static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id, const struct bpf_map *map) { @@ -589,11 +597,12 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(postfix, "_or_null", 16); } - snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s", + snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s", type & MEM_RDONLY ? "rdonly_" : "", type & MEM_RINGBUF ? "ringbuf_" : "", type & MEM_USER ? "user_" : "", type & MEM_PERCPU ? "percpu_" : "", + type & MEM_RCU ? "rcu_" : "", type & PTR_UNTRUSTED ? "untrusted_" : "", type & PTR_TRUSTED ? "trusted_" : "" ); @@ -1220,6 +1229,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->frame[i] = NULL; } dst_state->speculative = src->speculative; + dst_state->active_rcu_lock = src->active_rcu_lock; dst_state->curframe = src->curframe; dst_state->active_lock.ptr = src->active_lock.ptr; dst_state->active_lock.id = src->active_lock.id; @@ -4258,6 +4268,25 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) return reg->type == PTR_TO_FLOW_KEYS; } +static bool is_trusted_reg(const struct bpf_reg_state *reg) +{ + /* A referenced register is always trusted. */ + if (reg->ref_obj_id) + return true; + + /* If a register is not referenced, it is trusted if it has the + * MEM_ALLOC, MEM_RCU or PTR_TRUSTED type modifiers, and no others. Some of the + * other type modifiers may be safe, but we elect to take an opt-in + * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are + * not. + * + * Eventually, we should make PTR_TRUSTED the single source of truth + * for whether a register is trusted. + */ + return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && + !bpf_type_has_unsafe_modifiers(reg->type); +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -4737,9 +4766,28 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (type_flag(reg->type) & PTR_UNTRUSTED) flag |= PTR_UNTRUSTED; - /* Any pointer obtained from walking a trusted pointer is no longer trusted. */ + /* By default any pointer obtained from walking a trusted pointer is + * no longer trusted except the rcu case below. + */ flag &= ~PTR_TRUSTED; + if (flag & MEM_RCU) { + /* Mark value register as MEM_RCU only if it is protected by + * bpf_rcu_read_lock() and the ptr reg is trusted. MEM_RCU + * itself can already indicate trustedness inside the rcu + * read lock region. Also mark it as PTR_TRUSTED. + */ + if (!env->cur_state->active_rcu_lock || !is_trusted_reg(reg)) + flag &= ~MEM_RCU; + else + flag |= PTR_TRUSTED; + } else if (reg->type & MEM_RCU) { + /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged + * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively. + */ + flag |= PTR_UNTRUSTED; + } + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); @@ -5897,6 +5945,7 @@ static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, + PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED, }, }; static const struct bpf_reg_types percpu_btf_ptr_types = { @@ -6075,6 +6124,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset @@ -7539,6 +7589,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } + if (env->cur_state->active_rcu_lock) { + if (fn->might_sleep) { + verbose(env, "sleepable helper %s#%d in rcu_read_lock region\n", + func_id_name(func_id), func_id); + return -EINVAL; + } + + if (env->prog->aux->sleepable && is_storage_get_function(func_id)) + env->insn_aux_data[insn_idx].storage_get_func_atomic = true; + } + meta.func_id = func_id; /* check args */ for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { @@ -7966,25 +8027,6 @@ static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); } -static bool is_trusted_reg(const struct bpf_reg_state *reg) -{ - /* A referenced register is always trusted. */ - if (reg->ref_obj_id) - return true; - - /* If a register is not referenced, it is trusted if it has either the - * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the - * other type modifiers may be safe, but we elect to take an opt-in - * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are - * not. - * - * Eventually, we should make PTR_TRUSTED the single source of truth - * for whether a register is trusted. - */ - return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS && - !bpf_type_has_unsafe_modifiers(reg->type); -} - static bool __kfunc_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) @@ -8163,6 +8205,8 @@ enum special_kfunc_type { KF_bpf_list_pop_back, KF_bpf_cast_to_kern_ctx, KF_bpf_rdonly_cast, + KF_bpf_rcu_read_lock, + KF_bpf_rcu_read_unlock, }; BTF_SET_START(special_kfunc_set) @@ -8185,6 +8229,18 @@ BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) +BTF_ID(func, bpf_rcu_read_lock) +BTF_ID(func, bpf_rcu_read_unlock) + +static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_lock]; +} + +static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock]; +} static enum kfunc_ptr_arg_type get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, @@ -8817,6 +8873,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct btf_type *t, *func, *func_proto, *ptr_type; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; + bool sleepable, rcu_lock, rcu_unlock; struct bpf_kfunc_call_arg_meta meta; u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; @@ -8858,11 +8915,45 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EACCES; } - if (is_kfunc_sleepable(&meta) && !env->prog->aux->sleepable) { + sleepable = is_kfunc_sleepable(&meta); + if (sleepable && !env->prog->aux->sleepable) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } + rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); + rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); + if ((rcu_lock || rcu_unlock) && !env->rcu_tag_supported) { + verbose(env, "no vmlinux btf rcu tag support for kfunc %s\n", func_name); + return -EACCES; + } + + if (env->cur_state->active_rcu_lock) { + struct bpf_func_state *state; + struct bpf_reg_state *reg; + + if (rcu_lock) { + verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); + return -EINVAL; + } else if (rcu_unlock) { + bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + if (reg->type & MEM_RCU) { + reg->type &= ~(MEM_RCU | PTR_TRUSTED); + reg->type |= PTR_UNTRUSTED; + } + })); + env->cur_state->active_rcu_lock = false; + } else if (sleepable) { + verbose(env, "kernel func %s is sleepable within rcu_read_lock region\n", func_name); + return -EACCES; + } + } else if (rcu_lock) { + env->cur_state->active_rcu_lock = true; + } else if (rcu_unlock) { + verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name); + return -EINVAL; + } + /* Check the arguments */ err = check_kfunc_args(env, &meta); if (err < 0) @@ -11754,6 +11845,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (env->cur_state->active_rcu_lock) { + verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_rcu_read_lock-ed region\n"); + return -EINVAL; + } + if (regs[ctx_reg].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -13019,6 +13115,9 @@ static bool states_equal(struct bpf_verifier_env *env, old->active_lock.id != cur->active_lock.id) return false; + if (old->active_rcu_lock != cur->active_rcu_lock) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -13706,6 +13805,11 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (env->cur_state->active_rcu_lock) { + verbose(env, "bpf_rcu_read_unlock is missing\n"); + return -EINVAL; + } + /* We must do check_reference_leak here before * prepare_func_exit to handle the case when * state->curframe > 0, it may be a callback @@ -15494,14 +15598,12 @@ static int do_misc_fixups(struct bpf_verifier_env *env) goto patch_call_imm; } - if (insn->imm == BPF_FUNC_task_storage_get || - insn->imm == BPF_FUNC_sk_storage_get || - insn->imm == BPF_FUNC_inode_storage_get || - insn->imm == BPF_FUNC_cgrp_storage_get) { - if (env->prog->aux->sleepable) - insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); - else + if (is_storage_get_function(insn->imm)) { + if (!env->prog->aux->sleepable || + env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); + else + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); insn_buf[1] = *insn; cnt = 2; @@ -16580,6 +16682,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); + env->rcu_tag_supported = btf_vmlinux && + btf_find_by_name_kind(btf_vmlinux, "rcu", BTF_KIND_TYPE_TAG) > 0; if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; -- cgit v1.2.3 From bd12240337f43522b99c43f8976af34c712b5f57 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 24 Nov 2022 15:43:42 +0100 Subject: xfrm: add extack to xfrm_do_migrate Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 3 ++- net/key/af_key.c | 2 +- net/xfrm/xfrm_policy.c | 28 ++++++++++++++++++++-------- net/xfrm/xfrm_user.c | 16 +++++++++++----- 4 files changed, 34 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dbc81f5eb553..576566bd0be9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1703,7 +1703,8 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap, u32 if_id); + struct xfrm_encap_tmpl *encap, u32 if_id, + struct netlink_ext_ack *extack); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); diff --git a/net/key/af_key.c b/net/key/af_key.c index c85df5b958d2..7f4ff5fe2257 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2626,7 +2626,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL, net, NULL, 0); + kma ? &k : NULL, net, NULL, 0, NULL); out: return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a049f91d4446..9b9e2765363d 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4333,7 +4333,8 @@ static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tm /* update endpoint address(es) of template(s) */ static int xfrm_policy_migrate(struct xfrm_policy *pol, - struct xfrm_migrate *m, int num_migrate) + struct xfrm_migrate *m, int num_migrate, + struct netlink_ext_ack *extack) { struct xfrm_migrate *mp; int i, j, n = 0; @@ -4341,6 +4342,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, write_lock_bh(&pol->lock); if (unlikely(pol->walk.dead)) { /* target policy has been deleted */ + NL_SET_ERR_MSG(extack, "Target policy not found"); write_unlock_bh(&pol->lock); return -ENOENT; } @@ -4372,17 +4374,22 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, return 0; } -static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) +static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate, + struct netlink_ext_ack *extack) { int i, j; - if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) + if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) { + NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)"); return -EINVAL; + } for (i = 0; i < num_migrate; i++) { if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || - xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) + xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) { + NL_SET_ERR_MSG(extack, "Addresses in the MIGRATE attribute's list cannot be null"); return -EINVAL; + } /* check if there is any duplicated entry */ for (j = i + 1; j < num_migrate; j++) { @@ -4393,8 +4400,10 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) m[i].proto == m[j].proto && m[i].mode == m[j].mode && m[i].reqid == m[j].reqid && - m[i].old_family == m[j].old_family) + m[i].old_family == m[j].old_family) { + NL_SET_ERR_MSG(extack, "Entries in the MIGRATE attribute's list must be unique"); return -EINVAL; + } } } @@ -4404,7 +4413,8 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap, u32 if_id) + struct xfrm_encap_tmpl *encap, u32 if_id, + struct netlink_ext_ack *extack) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -4414,11 +4424,12 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *mp; /* Stage 0 - sanity checks */ - err = xfrm_migrate_check(m, num_migrate); + err = xfrm_migrate_check(m, num_migrate, extack); if (err < 0) goto out; if (dir >= XFRM_POLICY_MAX) { + NL_SET_ERR_MSG(extack, "Invalid policy direction"); err = -EINVAL; goto out; } @@ -4426,6 +4437,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* Stage 1 - find policy */ pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id); if (!pol) { + NL_SET_ERR_MSG(extack, "Target policy not found"); err = -ENOENT; goto out; } @@ -4447,7 +4459,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 3 - update policy */ - err = xfrm_policy_migrate(pol, m, num_migrate); + err = xfrm_policy_migrate(pol, m, num_migrate, extack); if (err < 0) goto restore_state; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 13607df4f30d..c5d6a92d73cb 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2687,7 +2687,8 @@ nomem: #ifdef CONFIG_XFRM_MIGRATE static int copy_from_user_migrate(struct xfrm_migrate *ma, struct xfrm_kmaddress *k, - struct nlattr **attrs, int *num) + struct nlattr **attrs, int *num, + struct netlink_ext_ack *extack) { struct nlattr *rt = attrs[XFRMA_MIGRATE]; struct xfrm_user_migrate *um; @@ -2706,8 +2707,10 @@ static int copy_from_user_migrate(struct xfrm_migrate *ma, um = nla_data(rt); num_migrate = nla_len(rt) / sizeof(*um); - if (num_migrate <= 0 || num_migrate > XFRM_MAX_DEPTH) + if (num_migrate <= 0 || num_migrate > XFRM_MAX_DEPTH) { + NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)"); return -EINVAL; + } for (i = 0; i < num_migrate; i++, um++, ma++) { memcpy(&ma->old_daddr, &um->old_daddr, sizeof(ma->old_daddr)); @@ -2740,8 +2743,10 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_encap_tmpl *encap = NULL; u32 if_id = 0; - if (!attrs[XFRMA_MIGRATE]) + if (!attrs[XFRMA_MIGRATE]) { + NL_SET_ERR_MSG(extack, "Missing required MIGRATE attribute"); return -EINVAL; + } kmp = attrs[XFRMA_KMADDRESS] ? &km : NULL; @@ -2749,7 +2754,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; - err = copy_from_user_migrate(m, kmp, attrs, &n); + err = copy_from_user_migrate(m, kmp, attrs, &n, extack); if (err) return err; @@ -2766,7 +2771,8 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); - err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id); + err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, + if_id, extack); kfree(encap); -- cgit v1.2.3 From c2dad11e0466a27d40041845cf63cdfb4fbd991f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Thu, 24 Nov 2022 15:43:43 +0100 Subject: xfrm: add extack to xfrm_alloc_userspi Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 5 +++-- net/key/af_key.c | 4 ++-- net/xfrm/xfrm_state.c | 21 ++++++++++++++++----- net/xfrm/xfrm_user.c | 8 +++++--- 4 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 576566bd0be9..e0cc6791c001 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1681,8 +1681,9 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); -int verify_spi_info(u8 proto, u32 min, u32 max); -int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); +int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack); +int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi, + struct netlink_ext_ack *extack); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, diff --git a/net/key/af_key.c b/net/key/af_key.c index 7f4ff5fe2257..e1d2155605aa 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1377,13 +1377,13 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ max_spi = range->sadb_spirange_max; } - err = verify_spi_info(x->id.proto, min_spi, max_spi); + err = verify_spi_info(x->id.proto, min_spi, max_spi, NULL); if (err) { xfrm_state_put(x); return err; } - err = xfrm_alloc_spi(x, min_spi, max_spi); + err = xfrm_alloc_spi(x, min_spi, max_spi, NULL); resp_skb = err ? ERR_PTR(err) : pfkey_xfrm_state2msg(x); if (IS_ERR(resp_skb)) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 81df34b3da6e..d0ae17e3bb38 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2017,7 +2017,7 @@ u32 xfrm_get_acqseq(void) } EXPORT_SYMBOL(xfrm_get_acqseq); -int verify_spi_info(u8 proto, u32 min, u32 max) +int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack) { switch (proto) { case IPPROTO_AH: @@ -2026,22 +2026,28 @@ int verify_spi_info(u8 proto, u32 min, u32 max) case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ - if (max >= 0x10000) + if (max >= 0x10000) { + NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535"); return -EINVAL; + } break; default: + NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP"); return -EINVAL; } - if (min > max) + if (min > max) { + NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max"); return -EINVAL; + } return 0; } EXPORT_SYMBOL(verify_spi_info); -int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) +int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, + struct netlink_ext_ack *extack) { struct net *net = xs_net(x); unsigned int h; @@ -2053,8 +2059,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); - if (x->km.state == XFRM_STATE_DEAD) + if (x->km.state == XFRM_STATE_DEAD) { + NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state"); goto unlock; + } err = 0; if (x->id.spi) @@ -2065,6 +2073,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) if (minspi == maxspi) { x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family); if (x0) { + NL_SET_ERR_MSG(extack, "Requested SPI is already in use"); xfrm_state_put(x0); goto unlock; } @@ -2089,6 +2098,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; + } else { + NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); } unlock: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c5d6a92d73cb..5c280e04e02c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1523,7 +1523,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, u32 if_id = 0; p = nlmsg_data(nlh); - err = verify_spi_info(p->info.id.proto, p->min, p->max); + err = verify_spi_info(p->info.id.proto, p->min, p->max, extack); if (err) goto out_noput; @@ -1551,10 +1551,12 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, &p->info.saddr, 1, family); err = -ENOENT; - if (!x) + if (!x) { + NL_SET_ERR_MSG(extack, "Target ACQUIRE not found"); goto out_noput; + } - err = xfrm_alloc_spi(x, p->min, p->max); + err = xfrm_alloc_spi(x, p->min, p->max, extack); if (err) goto out; -- cgit v1.2.3 From a66d79ee0bd5140a64b72cde588f8c83a55a1eb9 Mon Sep 17 00:00:00 2001 From: Sujuan Chen Date: Thu, 24 Nov 2022 11:18:14 +0800 Subject: net: ethernet: mtk_wed: add wcid overwritten support for wed v1 All wed versions should enable the wcid overwritten feature, since the wcid size is controlled by the wlan driver. Tested-by: Sujuan Chen Co-developed-by: Bo Jiao Signed-off-by: Bo Jiao Signed-off-by: Sujuan Chen Signed-off-by: David S. Miller --- drivers/net/ethernet/mediatek/mtk_wed.c | 13 ++++++++----- drivers/net/ethernet/mediatek/mtk_wed_regs.h | 2 ++ include/linux/soc/mediatek/mtk_wed.h | 3 +++ 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 7d8842378c2b..16d7af88bbac 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -526,9 +526,9 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) MTK_WED_WPDMA_RX_D_RX_DRV_EN); wed_clr(dev, MTK_WED_WDMA_GLO_CFG, MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); - - mtk_wed_set_512_support(dev, false); } + + mtk_wed_set_512_support(dev, false); } static void @@ -1290,9 +1290,10 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) if (mtk_wed_rro_cfg(dev)) return; - mtk_wed_set_512_support(dev, dev->wlan.wcid_512); } + mtk_wed_set_512_support(dev, dev->wlan.wcid_512); + mtk_wed_dma_enable(dev); dev->running = true; } @@ -1358,11 +1359,13 @@ mtk_wed_attach(struct mtk_wed_device *dev) } mtk_wed_hw_init_early(dev); - if (hw->version == 1) + if (hw->version == 1) { regmap_update_bits(hw->hifsys, HIFSYS_DMA_AG_MAP, BIT(hw->index), 0); - else + } else { + dev->rev_id = wed_r32(dev, MTK_WED_REV_ID); ret = mtk_wed_wo_init(hw); + } out: if (ret) mtk_wed_detach(dev); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h index 9e39dace95eb..873d50b9a6e6 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h @@ -20,6 +20,8 @@ struct mtk_wdma_desc { __le32 info; } __packed __aligned(4); +#define MTK_WED_REV_ID 0x004 + #define MTK_WED_RESET 0x008 #define MTK_WED_RESET_TX_BM BIT(0) #define MTK_WED_RESET_TX_FREE_AGENT BIT(4) diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 8294978f4bca..1b1ef57609f7 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -85,6 +85,9 @@ struct mtk_wed_device { int irq; u8 version; + /* used by wlan driver */ + u32 rev_id; + struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; struct mtk_wed_ring rx_ring[MTK_WED_RX_QUEUES]; struct mtk_wed_ring txfree_ring; -- cgit v1.2.3 From 4c47867bc789bdc722f3bb760355c2c246fbe9af Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 24 Nov 2022 12:15:54 +0100 Subject: of: net: export of_get_mac_address_nvmem() Export of_get_mac_addr_nvmem() and rename it to of_get_mac_address_nvmem() in order to fit the convention followed by the existing exported helpers of the same kind. This way, OF compatible drivers using eg. fwnode_get_mac_address() can do a direct call to it instead of calling of_get_mac_address() just for the nvmem step, avoiding to repeat an expensive DT lookup which has already been done once. Eventually, fwnode_get_mac_address() should probably be updated to perform the nvmem lookup directly, but as of today, nvmem cells seem not to be supported by ACPI yet which would defeat this kind of extension. Suggested-by: Marcin Wojtas Signed-off-by: Miquel Raynal Signed-off-by: Paolo Abeni --- include/linux/of_net.h | 6 ++++++ net/core/of_net.c | 5 +++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 0484b613ca64..d88715a0b3a5 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -14,6 +14,7 @@ struct net_device; extern int of_get_phy_mode(struct device_node *np, phy_interface_t *interface); extern int of_get_mac_address(struct device_node *np, u8 *mac); +extern int of_get_mac_address_nvmem(struct device_node *np, u8 *mac); int of_get_ethdev_address(struct device_node *np, struct net_device *dev); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else @@ -28,6 +29,11 @@ static inline int of_get_mac_address(struct device_node *np, u8 *mac) return -ENODEV; } +static inline int of_get_mac_address_nvmem(struct device_node *np, u8 *mac) +{ + return -ENODEV; +} + static inline int of_get_ethdev_address(struct device_node *np, struct net_device *dev) { return -ENODEV; diff --git a/net/core/of_net.c b/net/core/of_net.c index f1a9bf7578e7..55d3fe229269 100644 --- a/net/core/of_net.c +++ b/net/core/of_net.c @@ -57,7 +57,7 @@ static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr) return -ENODEV; } -static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) +int of_get_mac_address_nvmem(struct device_node *np, u8 *addr) { struct platform_device *pdev = of_find_device_by_node(np); struct nvmem_cell *cell; @@ -94,6 +94,7 @@ static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) return 0; } +EXPORT_SYMBOL(of_get_mac_address_nvmem); /** * of_get_mac_address() @@ -140,7 +141,7 @@ int of_get_mac_address(struct device_node *np, u8 *addr) if (!ret) return 0; - return of_get_mac_addr_nvmem(np, addr); + return of_get_mac_address_nvmem(np, addr); } EXPORT_SYMBOL(of_get_mac_address); -- cgit v1.2.3 From f78cd9c783e09a0fe454b0fc8b39c22025d7869e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 24 Nov 2022 16:22:53 +0100 Subject: net: ethernet: mtk_wed: update mtk_wed_stop Update mtk_wed_stop routine and rename old mtk_wed_stop() to mtk_wed_deinit(). This is a preliminary patch to add Wireless Ethernet Dispatcher reset support. Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mediatek/mtk_wed.c | 32 +++++++++++++++++++++++--------- include/linux/soc/mediatek/mtk_wed.h | 4 ++++ 2 files changed, 27 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index dbe10bbdb6f6..42b7e0407a9b 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -539,14 +539,8 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) static void mtk_wed_stop(struct mtk_wed_device *dev) { - mtk_wed_dma_disable(dev); mtk_wed_set_ext_int(dev, false); - wed_clr(dev, MTK_WED_CTRL, - MTK_WED_CTRL_WDMA_INT_AGENT_EN | - MTK_WED_CTRL_WPDMA_INT_AGENT_EN | - MTK_WED_CTRL_WED_TX_BM_EN | - MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); wed_w32(dev, MTK_WED_WPDMA_INT_TRIGGER, 0); wed_w32(dev, MTK_WED_WDMA_INT_TRIGGER, 0); wdma_w32(dev, MTK_WDMA_INT_MASK, 0); @@ -558,7 +552,27 @@ mtk_wed_stop(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_EXT_INT_MASK1, 0); wed_w32(dev, MTK_WED_EXT_INT_MASK2, 0); - wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); +} + +static void +mtk_wed_deinit(struct mtk_wed_device *dev) +{ + mtk_wed_stop(dev); + mtk_wed_dma_disable(dev); + + wed_clr(dev, MTK_WED_CTRL, + MTK_WED_CTRL_WDMA_INT_AGENT_EN | + MTK_WED_CTRL_WPDMA_INT_AGENT_EN | + MTK_WED_CTRL_WED_TX_BM_EN | + MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); + + if (dev->hw->version == 1) + return; + + wed_clr(dev, MTK_WED_CTRL, + MTK_WED_CTRL_RX_ROUTE_QM_EN | + MTK_WED_CTRL_WED_RX_BM_EN | + MTK_WED_CTRL_RX_RRO_QM_EN); } static void @@ -568,7 +582,7 @@ mtk_wed_detach(struct mtk_wed_device *dev) mutex_lock(&hw_lock); - mtk_wed_stop(dev); + mtk_wed_deinit(dev); mtk_wdma_rx_reset(dev); mtk_wed_reset(dev, MTK_WED_RESET_WED); @@ -670,7 +684,7 @@ mtk_wed_hw_init_early(struct mtk_wed_device *dev) { u32 mask, set; - mtk_wed_stop(dev); + mtk_wed_deinit(dev); mtk_wed_reset(dev, MTK_WED_RESET_WED); mtk_wed_set_wpdma(dev); diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 1b1ef57609f7..c43510e541df 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -234,6 +234,8 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) (_dev)->ops->ppe_check(_dev, _skb, _reason, _hash) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) \ (_dev)->ops->msg_update(_dev, _id, _msg, _len) +#define mtk_wed_device_stop(_dev) (_dev)->ops->stop(_dev) +#define mtk_wed_device_dma_reset(_dev) (_dev)->ops->reset_dma(_dev) #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -250,6 +252,8 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) -ENODEV #define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) do {} while (0) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV +#define mtk_wed_device_stop(_dev) do {} while (0) +#define mtk_wed_device_dma_reset(_dev) do {} while (0) #endif #endif -- cgit v1.2.3 From 23dca7a90017ff2512c501f7da4c7ca7a95c2d6e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 24 Nov 2022 16:22:55 +0100 Subject: net: ethernet: mtk_wed: add reset to tx_ring_setup callback Introduce reset parameter to mtk_wed_tx_ring_setup signature. This is a preliminary patch to add Wireless Ethernet Dispatcher reset support. Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- drivers/net/ethernet/mediatek/mtk_wed.c | 19 +++++++++++-------- drivers/net/wireless/mediatek/mt76/dma.c | 2 +- include/linux/soc/mediatek/mtk_wed.h | 8 ++++---- 3 files changed, 16 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 9594885d5e50..d041615b2bac 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1181,7 +1181,8 @@ mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, } static int -mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) +mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size, + bool reset) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; struct mtk_wed_ring *wdma; @@ -1190,8 +1191,8 @@ mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) return -EINVAL; wdma = &dev->rx_wdma[idx]; - if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, - true)) + if (!reset && mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, + desc_size, true)) return -ENOMEM; wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE, @@ -1389,7 +1390,7 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) if (!dev->rx_wdma[i].desc) - mtk_wed_wdma_rx_ring_setup(dev, i, 16); + mtk_wed_wdma_rx_ring_setup(dev, i, 16, false); mtk_wed_hw_init(dev); mtk_wed_configure_irq(dev, irq_mask); @@ -1498,7 +1499,8 @@ unlock: } static int -mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) +mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs, + bool reset) { struct mtk_wed_ring *ring = &dev->tx_ring[idx]; @@ -1517,11 +1519,12 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) if (WARN_ON(idx >= ARRAY_SIZE(dev->tx_ring))) return -EINVAL; - if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, - sizeof(*ring->desc), true)) + if (!reset && mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, + sizeof(*ring->desc), true)) return -ENOMEM; - if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE, + reset)) return -ENOMEM; ring->reg_base = MTK_WED_RING_TX(idx); diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 7378c4d1e156..28cbf07046c3 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -502,7 +502,7 @@ mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q) switch (type) { case MT76_WED_Q_TX: - ret = mtk_wed_device_tx_ring_setup(wed, ring, q->regs); + ret = mtk_wed_device_tx_ring_setup(wed, ring, q->regs, false); if (!ret) q->wed_regs = wed->tx_ring[ring].reg_base; break; diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index c43510e541df..beb190449704 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -158,7 +158,7 @@ struct mtk_wed_device { struct mtk_wed_ops { int (*attach)(struct mtk_wed_device *dev); int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, - void __iomem *regs); + void __iomem *regs, bool reset); int (*rx_ring_setup)(struct mtk_wed_device *dev, int ring, void __iomem *regs); int (*txfree_ring_setup)(struct mtk_wed_device *dev, @@ -216,8 +216,8 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) #define mtk_wed_device_active(_dev) !!(_dev)->ops #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) #define mtk_wed_device_start(_dev, _mask) (_dev)->ops->start(_dev, _mask) -#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) \ - (_dev)->ops->tx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs, _reset) \ + (_dev)->ops->tx_ring_setup(_dev, _ring, _regs, _reset) #define mtk_wed_device_txfree_ring_setup(_dev, _regs) \ (_dev)->ops->txfree_ring_setup(_dev, _regs) #define mtk_wed_device_reg_read(_dev, _reg) \ @@ -243,7 +243,7 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) } #define mtk_wed_device_detach(_dev) do {} while (0) #define mtk_wed_device_start(_dev, _mask) do {} while (0) -#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_tx_ring_setup(_dev, _ring, _regs, _reset) -ENODEV #define mtk_wed_device_txfree_ring_setup(_dev, _ring, _regs) -ENODEV #define mtk_wed_device_reg_read(_dev, _reg) 0 #define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) -- cgit v1.2.3 From 51147284eb7d685a689a5d1b7772faec278a2338 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Tue, 29 Nov 2022 14:55:34 +0100 Subject: ieee802154: Advertize coordinators discovery Let's introduce the basics for advertizing discovered PANs and coordinators, which is: - A new "scan" netlink message group. - A couple of netlink command/attribute. - The main netlink helper to send a netlink message with all the necessary information to forward the main information to the user. Two netlink attributes are proactively added to support future UWB complex channels, but are not actually used yet. Co-developed-by: David Girault Signed-off-by: David Girault Signed-off-by: Miquel Raynal Acked-by: Alexander Aring Link: https://lore.kernel.org/r/20221129135535.532513-2-miquel.raynal@bootlin.com Signed-off-by: Stefan Schmidt --- include/net/cfg802154.h | 18 ++++++++ include/net/nl802154.h | 43 +++++++++++++++++++ net/ieee802154/nl802154.c | 103 ++++++++++++++++++++++++++++++++++++++++++++++ net/ieee802154/nl802154.h | 2 + 4 files changed, 166 insertions(+) (limited to 'include') diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index e1481f9cf049..d09c393d229f 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -260,6 +260,24 @@ struct ieee802154_addr { }; }; +/** + * struct ieee802154_coord_desc - Coordinator descriptor + * @addr: PAN ID and coordinator address + * @page: page this coordinator is using + * @channel: channel this coordinator is using + * @superframe_spec: SuperFrame specification as received + * @link_quality: link quality indicator at which the beacon was received + * @gts_permit: the coordinator accepts GTS requests + */ +struct ieee802154_coord_desc { + struct ieee802154_addr addr; + u8 page; + u8 channel; + u16 superframe_spec; + u8 link_quality; + bool gts_permit; +}; + struct ieee802154_llsec_key_id { u8 mode; u8 id; diff --git a/include/net/nl802154.h b/include/net/nl802154.h index f5850b569c52..b79a89d5207c 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -72,6 +72,8 @@ enum nl802154_commands { NL802154_CMD_NEW_SEC_LEVEL, NL802154_CMD_DEL_SEC_LEVEL, + NL802154_CMD_SCAN_EVENT, + /* add new commands above here */ /* used to define NL802154_CMD_MAX below */ @@ -131,6 +133,8 @@ enum nl802154_attrs { NL802154_ATTR_PID, NL802154_ATTR_NETNS_FD, + NL802154_ATTR_COORDINATOR, + /* add attributes here, update the policy in nl802154.c */ #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL @@ -216,6 +220,45 @@ enum nl802154_wpan_phy_capability_attr { NL802154_CAP_ATTR_MAX = __NL802154_CAP_ATTR_AFTER_LAST - 1 }; +/** + * enum nl802154_coord - Netlink attributes for a coord + * + * @__NL802154_COORD_INVALID: invalid + * @NL802154_COORD_PANID: PANID of the coordinator (2 bytes) + * @NL802154_COORD_ADDR: coordinator address, (8 bytes or 2 bytes) + * @NL802154_COORD_CHANNEL: channel number, related to @NL802154_COORD_PAGE (u8) + * @NL802154_COORD_PAGE: channel page, related to @NL802154_COORD_CHANNEL (u8) + * @NL802154_COORD_PREAMBLE_CODE: Preamble code used when the beacon was received, + * this is PHY dependent and optional (u8) + * @NL802154_COORD_MEAN_PRF: Mean PRF used when the beacon was received, + * this is PHY dependent and optional (u8) + * @NL802154_COORD_SUPERFRAME_SPEC: superframe specification of the PAN (u16) + * @NL802154_COORD_LINK_QUALITY: signal quality of beacon in unspecified units, + * scaled to 0..255 (u8) + * @NL802154_COORD_GTS_PERMIT: set to true if GTS is permitted on this PAN + * @NL802154_COORD_PAYLOAD_DATA: binary data containing the raw data from the + * frame payload, (only if beacon or probe response had data) + * @NL802154_COORD_PAD: attribute used for padding for 64-bit alignment + * @NL802154_COORD_MAX: highest coordinator attribute + */ +enum nl802154_coord { + __NL802154_COORD_INVALID, + NL802154_COORD_PANID, + NL802154_COORD_ADDR, + NL802154_COORD_CHANNEL, + NL802154_COORD_PAGE, + NL802154_COORD_PREAMBLE_CODE, + NL802154_COORD_MEAN_PRF, + NL802154_COORD_SUPERFRAME_SPEC, + NL802154_COORD_LINK_QUALITY, + NL802154_COORD_GTS_PERMIT, + NL802154_COORD_PAYLOAD_DATA, + NL802154_COORD_PAD, + + /* keep last */ + NL802154_COORD_MAX, +}; + /** * enum nl802154_cca_modes - cca modes * diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 38c4f3cb010e..80dc73182785 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -26,10 +26,12 @@ static struct genl_family nl802154_fam; /* multicast groups */ enum nl802154_multicast_groups { NL802154_MCGRP_CONFIG, + NL802154_MCGRP_SCAN, }; static const struct genl_multicast_group nl802154_mcgrps[] = { [NL802154_MCGRP_CONFIG] = { .name = "config", }, + [NL802154_MCGRP_SCAN] = { .name = "scan", }, }; /* returns ERR_PTR values */ @@ -216,6 +218,9 @@ static const struct nla_policy nl802154_policy[NL802154_ATTR_MAX+1] = { [NL802154_ATTR_PID] = { .type = NLA_U32 }, [NL802154_ATTR_NETNS_FD] = { .type = NLA_U32 }, + + [NL802154_ATTR_COORDINATOR] = { .type = NLA_NESTED }, + #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL [NL802154_ATTR_SEC_ENABLED] = { .type = NLA_U8, }, [NL802154_ATTR_SEC_OUT_LEVEL] = { .type = NLA_U32, }, @@ -1281,6 +1286,104 @@ static int nl802154_wpan_phy_netns(struct sk_buff *skb, struct genl_info *info) return err; } +static int nl802154_prep_scan_event_msg(struct sk_buff *msg, + struct cfg802154_registered_device *rdev, + struct wpan_dev *wpan_dev, + u32 portid, u32 seq, int flags, u8 cmd, + struct ieee802154_coord_desc *desc) +{ + struct nlattr *nla; + void *hdr; + + hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); + if (!hdr) + return -ENOBUFS; + + if (nla_put_u32(msg, NL802154_ATTR_WPAN_PHY, rdev->wpan_phy_idx)) + goto nla_put_failure; + + if (wpan_dev->netdev && + nla_put_u32(msg, NL802154_ATTR_IFINDEX, wpan_dev->netdev->ifindex)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, NL802154_ATTR_WPAN_DEV, + wpan_dev_id(wpan_dev), NL802154_ATTR_PAD)) + goto nla_put_failure; + + nla = nla_nest_start_noflag(msg, NL802154_ATTR_COORDINATOR); + if (!nla) + goto nla_put_failure; + + if (nla_put(msg, NL802154_COORD_PANID, IEEE802154_PAN_ID_LEN, + &desc->addr.pan_id)) + goto nla_put_failure; + + if (desc->addr.mode == IEEE802154_ADDR_SHORT) { + if (nla_put(msg, NL802154_COORD_ADDR, + IEEE802154_SHORT_ADDR_LEN, + &desc->addr.short_addr)) + goto nla_put_failure; + } else { + if (nla_put(msg, NL802154_COORD_ADDR, + IEEE802154_EXTENDED_ADDR_LEN, + &desc->addr.extended_addr)) + goto nla_put_failure; + } + + if (nla_put_u8(msg, NL802154_COORD_CHANNEL, desc->channel)) + goto nla_put_failure; + + if (nla_put_u8(msg, NL802154_COORD_PAGE, desc->page)) + goto nla_put_failure; + + if (nla_put_u16(msg, NL802154_COORD_SUPERFRAME_SPEC, + desc->superframe_spec)) + goto nla_put_failure; + + if (nla_put_u8(msg, NL802154_COORD_LINK_QUALITY, desc->link_quality)) + goto nla_put_failure; + + if (desc->gts_permit && nla_put_flag(msg, NL802154_COORD_GTS_PERMIT)) + goto nla_put_failure; + + /* TODO: NL802154_COORD_PAYLOAD_DATA if any */ + + nla_nest_end(msg, nla); + + genlmsg_end(msg, hdr); + + return 0; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + + return -EMSGSIZE; +} + +int nl802154_scan_event(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + struct ieee802154_coord_desc *desc) +{ + struct cfg802154_registered_device *rdev = wpan_phy_to_rdev(wpan_phy); + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + ret = nl802154_prep_scan_event_msg(msg, rdev, wpan_dev, 0, 0, 0, + NL802154_CMD_SCAN_EVENT, + desc); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + return genlmsg_multicast_netns(&nl802154_fam, wpan_phy_net(wpan_phy), + msg, 0, NL802154_MCGRP_SCAN, GFP_ATOMIC); +} +EXPORT_SYMBOL_GPL(nl802154_scan_event); + #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL static const struct nla_policy nl802154_dev_addr_policy[NL802154_DEV_ADDR_ATTR_MAX + 1] = { [NL802154_DEV_ADDR_ATTR_PAN_ID] = { .type = NLA_U16 }, diff --git a/net/ieee802154/nl802154.h b/net/ieee802154/nl802154.h index 8c4b6d08954c..89b805500032 100644 --- a/net/ieee802154/nl802154.h +++ b/net/ieee802154/nl802154.h @@ -4,5 +4,7 @@ int nl802154_init(void); void nl802154_exit(void); +int nl802154_scan_event(struct wpan_phy *wpan_phy, struct wpan_dev *wpan_dev, + struct ieee802154_coord_desc *desc); #endif /* __IEEE802154_NL802154_H */ -- cgit v1.2.3 From 12eb0f84a601cec8920b56d7ffd4182a6bfd6521 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 29 Sep 2022 13:45:08 +0200 Subject: net/mlx5: Remove unused ctx variables Remove mlx5_priv.ctx_list and ctx_lock which are no longer used after commit 601c10c89cbb ("net/mlx5: Delete custom device management logic"). Signed-off-by: Petr Pavlu Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 -- include/linux/mlx5/driver.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 25e87e5d9270..7f5db13e3550 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1603,8 +1603,6 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) int err; memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile)); - INIT_LIST_HEAD(&priv->ctx_list); - spin_lock_init(&priv->ctx_lock); lockdep_register_key(&dev->lock_key); mutex_init(&dev->intf_state_mutex); lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 06cbad166225..d476255c9a3f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -606,8 +606,6 @@ struct mlx5_priv { struct list_head pgdir_list; /* end: alloc staff */ - struct list_head ctx_list; - spinlock_t ctx_lock; struct mlx5_adev **adev; int adev_idx; int sw_vhca_id; -- cgit v1.2.3 From b146658f2ed90768b769222ca418617274242b32 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 31 Oct 2022 14:18:22 +0200 Subject: net/mlx5e: Add padding when needed in UMR WQEs Per the device spec, MTTs/KLMs list in a UMR WQE must be aligned to 64B. Per our SW design, the MTT/KLMs list would need alignment only if it's too small, for example on PPC when PAGE_SIZE is 64KB, and only 4 pages are needed to cover a MPWQE of size 256KB. Padding, if needed, is taken into account when calculating the UMR WQE fields (ds_cnt and xlt_octowords), however no entries are provided, instead garbage is passed. No real harm though, as these parts act as gaps between the RX MPWQEs and not used by any of them. Hence, in practice, device does not try to write any incoming packet to them. Still, prefer providing clean padding marking the end of the list, and do not map garbage into the RQ memory region. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 11 +++++++++++ include/linux/mlx5/device.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index b1ea0b995d9c..8d71736116e0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -727,6 +727,17 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) }; } + /* Pad if needed, in case the value set to ucseg->xlt_octowords + * in mlx5e_build_umr_wqe() needed alignment. + */ + if (rq->mpwqe.pages_per_wqe & (MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT - 1)) { + int pad = ALIGN(rq->mpwqe.pages_per_wqe, MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT) - + rq->mpwqe.pages_per_wqe; + + memset(&umr_wqe->inline_mtts[rq->mpwqe.pages_per_wqe], 0, + sizeof(*umr_wqe->inline_mtts) * pad); + } + bitmap_zero(wi->xdp_xmit_bitmap, rq->mpwqe.pages_per_wqe); wi->consumed_strides = 0; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index eb3fac30488b..97275965f156 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -294,6 +294,7 @@ enum { #define MLX5_UMR_MTT_ALIGNMENT 0x40 #define MLX5_UMR_MTT_MASK (MLX5_UMR_MTT_ALIGNMENT - 1) #define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT +#define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_MTT_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) -- cgit v1.2.3 From 683d78a0d46235edfd3c50ddbc4af1065b422670 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 31 Oct 2022 14:30:23 +0200 Subject: net/mlx5: Remove unused UMR MTT definitions Defines MLX5_UMR_MTT_MASK and MLX5_UMR_MTT_MIN_CHUNK_SIZE are not in use. Remove them. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 97275965f156..ecf840e2989b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -292,8 +292,6 @@ enum { #define MLX5_UMR_KLM_ALIGNMENT 4 #define MLX5_UMR_MTT_ALIGNMENT 0x40 -#define MLX5_UMR_MTT_MASK (MLX5_UMR_MTT_ALIGNMENT - 1) -#define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_MTT_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) -- cgit v1.2.3 From 02648b4b09d506bd4df2e17bf109c229fc728640 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 31 Oct 2022 14:44:57 +0200 Subject: net/mlx5: Generalize name of UMR alignment definition Per the device spec, MLX5_UMR_MTT_ALIGNMENT is good not only for UMR MTT entries, but for all other entries as well, like KLMs and KSMs. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/odp.c | 3 +-- drivers/infiniband/hw/mlx5/umr.c | 14 +++++++------- drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- include/linux/mlx5/device.h | 4 ++-- 6 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index bc97958818bb..e6e021af6aa9 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -230,8 +230,7 @@ static bool mlx5_ib_invalidate_range(struct mmu_interval_notifier *mni, struct ib_umem_odp *umem_odp = container_of(mni, struct ib_umem_odp, notifier); struct mlx5_ib_mr *mr; - const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT / - sizeof(struct mlx5_mtt)) - 1; + const u64 umr_block_mask = MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT - 1; u64 idx = 0, blk_start_idx = 0; u64 invalidations = 0; unsigned long start; diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c index d5105b5c9979..029e9536ec28 100644 --- a/drivers/infiniband/hw/mlx5/umr.c +++ b/drivers/infiniband/hw/mlx5/umr.c @@ -418,7 +418,7 @@ int mlx5r_umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd, } #define MLX5_MAX_UMR_CHUNK \ - ((1 << (MLX5_MAX_UMR_SHIFT + 4)) - MLX5_UMR_MTT_ALIGNMENT) + ((1 << (MLX5_MAX_UMR_SHIFT + 4)) - MLX5_UMR_FLEX_ALIGNMENT) #define MLX5_SPARE_UMR_CHUNK 0x10000 /* @@ -428,11 +428,11 @@ int mlx5r_umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd, */ static void *mlx5r_umr_alloc_xlt(size_t *nents, size_t ent_size, gfp_t gfp_mask) { - const size_t xlt_chunk_align = MLX5_UMR_MTT_ALIGNMENT / ent_size; + const size_t xlt_chunk_align = MLX5_UMR_FLEX_ALIGNMENT / ent_size; size_t size; void *res = NULL; - static_assert(PAGE_SIZE % MLX5_UMR_MTT_ALIGNMENT == 0); + static_assert(PAGE_SIZE % MLX5_UMR_FLEX_ALIGNMENT == 0); /* * MLX5_IB_UPD_XLT_ATOMIC doesn't signal an atomic context just that the @@ -666,7 +666,7 @@ int mlx5r_umr_update_mr_pas(struct mlx5_ib_mr *mr, unsigned int flags) } final_size = (void *)cur_mtt - (void *)mtt; - sg.length = ALIGN(final_size, MLX5_UMR_MTT_ALIGNMENT); + sg.length = ALIGN(final_size, MLX5_UMR_FLEX_ALIGNMENT); memset(cur_mtt, 0, sg.length - final_size); mlx5r_umr_final_update_xlt(dev, &wqe, mr, &sg, flags); @@ -690,7 +690,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, int desc_size = (flags & MLX5_IB_UPD_XLT_INDIRECT) ? sizeof(struct mlx5_klm) : sizeof(struct mlx5_mtt); - const int page_align = MLX5_UMR_MTT_ALIGNMENT / desc_size; + const int page_align = MLX5_UMR_FLEX_ALIGNMENT / desc_size; struct mlx5_ib_dev *dev = mr_to_mdev(mr); struct device *ddev = &dev->mdev->pdev->dev; const int page_mask = page_align - 1; @@ -711,7 +711,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, if (WARN_ON(!mr->umem->is_odp)) return -EINVAL; - /* UMR copies MTTs in units of MLX5_UMR_MTT_ALIGNMENT bytes, + /* UMR copies MTTs in units of MLX5_UMR_FLEX_ALIGNMENT bytes, * so we need to align the offset and length accordingly */ if (idx & page_mask) { @@ -748,7 +748,7 @@ int mlx5r_umr_update_xlt(struct mlx5_ib_mr *mr, u64 idx, int npages, mlx5_odp_populate_xlt(xlt, idx, npages, mr, flags); dma_sync_single_for_device(ddev, sg.addr, sg.length, DMA_TO_DEVICE); - sg.length = ALIGN(size_to_map, MLX5_UMR_MTT_ALIGNMENT); + sg.length = ALIGN(size_to_map, MLX5_UMR_FLEX_ALIGNMENT); if (pages_mapped + pages_iter >= pages_to_map) mlx5r_umr_final_update_xlt(dev, &wqe, mr, &sg, flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index ff5b302531d5..3cad59ac1b48 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -103,11 +103,11 @@ struct page_pool; * size actually used at runtime, but it's not a problem when calculating static * array sizes. */ -#define MLX5_UMR_MAX_MTT_SPACE \ +#define MLX5_UMR_MAX_FLEX_SPACE \ (ALIGN_DOWN(MLX5_SEND_WQE_MAX_SIZE - sizeof(struct mlx5e_umr_wqe), \ - MLX5_UMR_MTT_ALIGNMENT)) + MLX5_UMR_FLEX_ALIGNMENT)) #define MLX5_MPWRQ_MAX_PAGES_PER_WQE \ - rounddown_pow_of_two(MLX5_UMR_MAX_MTT_SPACE / sizeof(struct mlx5_mtt)) + rounddown_pow_of_two(MLX5_UMR_MAX_FLEX_SPACE / sizeof(struct mlx5_mtt)) #define MLX5E_MAX_RQ_NUM_MTTS \ (ALIGN_DOWN(U16_MAX, 4) * 2) /* Fits into u16 and aligned by WQEBB. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 9ec9662d1d0b..585bdc8383ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -107,7 +107,7 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, /* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */ max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB; max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe), - MLX5_UMR_MTT_ALIGNMENT) / umr_entry_size; + MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size; max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift; WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU); @@ -146,7 +146,7 @@ u16 mlx5e_mpwrq_umr_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift, u16 umr_wqe_sz; umr_wqe_sz = sizeof(struct mlx5e_umr_wqe) + - ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); + ALIGN(pages_per_wqe * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT); WARN_ON_ONCE(DIV_ROUND_UP(umr_wqe_sz, MLX5_SEND_WQE_DS) > MLX5_WQE_CTRL_DS_MASK); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 217c8a478977..199387c6bf16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -208,7 +208,7 @@ static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_ u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode); u32 sz; - sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); + sz = ALIGN(entries * umr_entry_size, MLX5_UMR_FLEX_ALIGNMENT); return sz / MLX5_OCTWORD; } diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ecf840e2989b..a02f779f5c5b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -291,8 +291,8 @@ enum { }; #define MLX5_UMR_KLM_ALIGNMENT 4 -#define MLX5_UMR_MTT_ALIGNMENT 0x40 -#define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_MTT_ALIGNMENT / sizeof(struct mlx5_mtt)) +#define MLX5_UMR_FLEX_ALIGNMENT 0x40 +#define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) -- cgit v1.2.3 From daab2e9c54a52dea8dbd1af516e6f986eeed2556 Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 31 Oct 2022 14:24:02 +0200 Subject: net/mlx5: Use generic definition for UMR KLM alignment MLX5_UMR_KLM_ALIGNMENT is in units of number of entries, while MLX5_UMR_MTT_ALIGNMENT (generalized and renamed to MLX5_UMR_FLEX_ALIGNMENT) is in byte units. This is misleading and confusing. Replace this KLM definition with one based on the generic definition. Signed-off-by: Tariq Toukan Reviewed-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 10 +++++----- include/linux/mlx5/device.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 3cad59ac1b48..65790ff58a74 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -160,7 +160,7 @@ struct page_pool; (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm)) #define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\ - ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT) + ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT) #define MLX5E_MAX_KLM_PER_WQE(mdev) \ MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 8d71736116e0..c8820ab22169 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -593,8 +593,8 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, int headroom, i; headroom = rq->buff.headroom; - new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); - entries = ALIGN(klm_entries, MLX5_UMR_KLM_ALIGNMENT); + new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1)); + entries = ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT); wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries); pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs); umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); @@ -603,7 +603,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, for (i = 0; i < entries; i++, index++) { dma_info = &shampo->info[index]; if (i >= klm_entries || (index < shampo->pi && shampo->pi - index < - MLX5_UMR_KLM_ALIGNMENT)) + MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT)) goto update_klm; header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) << MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE; @@ -668,8 +668,8 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq) if (!klm_entries) return 0; - klm_entries += (shampo->pi & (MLX5_UMR_KLM_ALIGNMENT - 1)); - index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_ALIGNMENT); + klm_entries += (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1)); + index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT); entries_before = shampo->hd_per_wq - index; if (unlikely(entries_before < klm_entries)) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index a02f779f5c5b..5fe5d198b57a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -290,9 +290,9 @@ enum { MLX5_UMR_INLINE = (1 << 7), }; -#define MLX5_UMR_KLM_ALIGNMENT 4 #define MLX5_UMR_FLEX_ALIGNMENT 0x40 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt)) +#define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) -- cgit v1.2.3 From bff3d0534804452e19c097ae6b4eb4b4d846d67f Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Fri, 4 Nov 2022 18:18:35 +0100 Subject: netfilter: conntrack: add sctp DATA_SENT state SCTP conntrack currently assumes that the SCTP endpoints will probe secondary paths using HEARTBEAT before sending traffic. But, according to RFC 9260, SCTP endpoints can send any traffic on any of the confirmed paths after SCTP association is up. SCTP endpoints that sends INIT will confirm all peer addresses that upper layer configures, and the SCTP endpoint that receives COOKIE_ECHO will only confirm the address it sent the INIT_ACK to. So, we can have a situation where the INIT sender can start to use secondary paths without the need to send HEARTBEAT. This patch allows DATA/SACK packets to create new connection tracking entry. A new state has been added to indicate that a DATA/SACK chunk has been seen in the original direction - SCTP_CONNTRACK_DATA_SENT. State transitions mostly follows the HEARTBEAT_SENT, except on receiving HEARTBEAT/HEARTBEAT_ACK/DATA/SACK in the reply direction. State transitions in original direction: - DATA_SENT behaves similar to HEARTBEAT_SENT for all chunks, except that it remains in DATA_SENT on receving HEARTBEAT, HEARTBEAT_ACK/DATA/SACK chunks State transitions in reply direction: - DATA_SENT behaves similar to HEARTBEAT_SENT for all chunks, except that it moves to HEARTBEAT_ACKED on receiving HEARTBEAT/HEARTBEAT_ACK/DATA/SACK chunks Note: This patch still doesn't solve the problem when the SCTP endpoint decides to use primary paths for association establishment but uses a secondary path for association shutdown. We still have to depend on timeout for connections to expire in such a case. Signed-off-by: Sriram Yagnaraman Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 1 + include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 1 + net/netfilter/nf_conntrack_proto_sctp.c | 104 ++++++++++++--------- net/netfilter/nf_conntrack_standalone.c | 8 ++ 4 files changed, 71 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index edc6ddab0de6..c742469afe21 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -16,6 +16,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, SCTP_CONNTRACK_HEARTBEAT_ACKED, + SCTP_CONNTRACK_DATA_SENT, SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 6b20fb22717b..94e74034706d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -95,6 +95,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, + CTA_TIMEOUT_SCTP_DATA_SENT, __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 5a936334b517..d88b92a8ffca 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -60,6 +60,7 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, + [SCTP_CONNTRACK_DATA_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -74,6 +75,7 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT #define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED +#define sDS SCTP_CONNTRACK_DATA_SENT #define sIV SCTP_CONNTRACK_MAX /* @@ -90,15 +92,16 @@ COOKIE WAIT - We have seen an INIT chunk in the original direction, or als COOKIE ECHOED - We have seen a COOKIE_ECHO chunk in the original direction. ESTABLISHED - We have seen a COOKIE_ACK in the reply direction. SHUTDOWN_SENT - We have seen a SHUTDOWN chunk in the original direction. -SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply directoin. +SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply direction. SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite to that of the SHUTDOWN chunk. CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to - that of the HEARTBEAT chunk. Secondary connection is - established. +HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction + opposite to that of the HEARTBEAT/DATA chunk. Secondary connection + is established. +DATA_SENT - We have seen a DATA/SACK in a new flow. */ /* TODO @@ -112,36 +115,38 @@ cookie echoed to closed. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, +/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS} }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, +/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, } }; @@ -253,6 +258,11 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; + case SCTP_CID_DATA: + case SCTP_CID_SACK: + pr_debug("SCTP_CID_DATA/SACK"); + i = 11; + break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", @@ -306,7 +316,9 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; - } else if (sch->type == SCTP_CID_HEARTBEAT) { + } else if (sch->type == SCTP_CID_HEARTBEAT || + sch->type == SCTP_CID_DATA || + sch->type == SCTP_CID_SACK) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; @@ -392,19 +404,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; - } - - /* Check the verification tag (Sec 8.5) */ - if (!test_bit(SCTP_CID_INIT, map) && - !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && - !test_bit(SCTP_CID_COOKIE_ECHO, map) && - !test_bit(SCTP_CID_ABORT, map) && - !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && - !test_bit(SCTP_CID_HEARTBEAT, map) && - !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && - sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out; + } else { + /* Check the verification tag (Sec 8.5) */ + if (!test_bit(SCTP_CID_INIT, map) && + !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && + !test_bit(SCTP_CID_COOKIE_ECHO, map) && + !test_bit(SCTP_CID_ABORT, map) && + !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && + sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out; + } } old_state = new_state = SCTP_CONNTRACK_NONE; @@ -464,6 +476,11 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } + } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } } old_state = ct->proto.sctp.state; @@ -684,6 +701,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..a884c06abf09 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -602,6 +602,7 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -892,6 +893,12 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = { + .procname = "nf_conntrack_sctp_timeout_data_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1036,6 +1043,7 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); XASSIGN(HEARTBEAT_ACKED, sn); + XASSIGN(DATA_SENT, sn); #undef XASSIGN #endif } -- cgit v1.2.3 From a70e483460d58e64504dd679fd127e9549385c86 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 9 Nov 2022 12:21:58 +0100 Subject: netfilter: conntrack: merge ipv4+ipv6 confirm functions No need to have distinct functions. After merge, ipv6 can avoid protooff computation if the connection neither needs sequence adjustment nor helper invocation -- this is the normal case. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_core.h | 3 +- net/bridge/netfilter/nf_conntrack_bridge.c | 32 +------- net/netfilter/nf_conntrack_proto.c | 124 +++++++++++++---------------- 3 files changed, 57 insertions(+), 102 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index b2b9de70d9f4..71d1269fe4d4 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -71,8 +71,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) return ret; } -unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, - struct nf_conn *ct, enum ip_conntrack_info ctinfo); +unsigned int nf_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l4proto *proto); diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 73242962be5d..5c5dd437f1c2 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -366,42 +366,12 @@ static int nf_ct_bridge_refrag_post(struct net *net, struct sock *sk, return br_dev_queue_push_xmit(net, sk, skb); } -static unsigned int nf_ct_bridge_confirm(struct sk_buff *skb) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - int protoff; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return nf_conntrack_confirm(skb); - - switch (skb->protocol) { - case htons(ETH_P_IP): - protoff = skb_network_offset(skb) + ip_hdrlen(skb); - break; - case htons(ETH_P_IPV6): { - unsigned char pnum = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, - &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) - return nf_conntrack_confirm(skb); - } - break; - default: - return NF_ACCEPT; - } - return nf_confirm(skb, protoff, ct, ctinfo); -} - static unsigned int nf_ct_bridge_post(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int ret; - ret = nf_ct_bridge_confirm(skb); + ret = nf_confirm(priv, skb, state); if (ret != NF_ACCEPT) return ret; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 895b09cbd7cf..99323fb12d0f 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -121,17 +121,61 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto) }; EXPORT_SYMBOL_GPL(nf_ct_l4proto_find); -unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, - struct nf_conn *ct, enum ip_conntrack_info ctinfo) +static bool in_vrf_postrouting(const struct nf_hook_state *state) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (state->hook == NF_INET_POST_ROUTING && + netif_is_l3_master(state->out)) + return true; +#endif + return false; +} + +unsigned int nf_confirm(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) { const struct nf_conn_help *help; + enum ip_conntrack_info ctinfo; + unsigned int protoff; + struct nf_conn *ct; + bool seqadj_needed; + __be16 frag_off; + u8 pnum; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct || in_vrf_postrouting(state)) + return NF_ACCEPT; help = nfct_help(ct); + + seqadj_needed = test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb); + if (!help && !seqadj_needed) + return nf_conntrack_confirm(skb); + + /* helper->help() do not expect ICMP packets */ + if (ctinfo == IP_CT_RELATED_REPLY) + return nf_conntrack_confirm(skb); + + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + protoff = skb_network_offset(skb) + ip_hdrlen(skb); + break; + case NFPROTO_IPV6: + pnum = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) + return nf_conntrack_confirm(skb); + break; + default: + return nf_conntrack_confirm(skb); + } + if (help) { const struct nf_conntrack_helper *helper; int ret; - /* rcu_read_lock()ed by nf_hook_thresh */ + /* rcu_read_lock()ed by nf_hook */ helper = rcu_dereference(help->helper); if (helper) { ret = helper->help(skb, @@ -142,12 +186,10 @@ unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, } } - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_is_loopback_packet(skb)) { - if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { - NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return NF_DROP; - } + if (seqadj_needed && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; } /* We've seen it coming out the other side: confirm it */ @@ -155,35 +197,6 @@ unsigned int nf_confirm(struct sk_buff *skb, unsigned int protoff, } EXPORT_SYMBOL_GPL(nf_confirm); -static bool in_vrf_postrouting(const struct nf_hook_state *state) -{ -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) - if (state->hook == NF_INET_POST_ROUTING && - netif_is_l3_master(state->out)) - return true; -#endif - return false; -} - -static unsigned int ipv4_confirm(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return nf_conntrack_confirm(skb); - - if (in_vrf_postrouting(state)) - return NF_ACCEPT; - - return nf_confirm(skb, - skb_network_offset(skb) + ip_hdrlen(skb), - ct, ctinfo); -} - static unsigned int ipv4_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -230,13 +243,13 @@ static const struct nf_hook_ops ipv4_conntrack_ops[] = { .priority = NF_IP_PRI_CONNTRACK, }, { - .hook = ipv4_confirm, + .hook = nf_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { - .hook = ipv4_confirm, + .hook = nf_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, @@ -373,33 +386,6 @@ static struct nf_sockopt_ops so_getorigdst6 = { .owner = THIS_MODULE, }; -static unsigned int ipv6_confirm(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned char pnum = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int protoff; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return nf_conntrack_confirm(skb); - - if (in_vrf_postrouting(state)) - return NF_ACCEPT; - - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, - &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return nf_conntrack_confirm(skb); - } - - return nf_confirm(skb, protoff, ct, ctinfo); -} - static unsigned int ipv6_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -428,13 +414,13 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { .priority = NF_IP6_PRI_CONNTRACK, }, { - .hook = ipv6_confirm, + .hook = nf_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { - .hook = ipv6_confirm, + .hook = nf_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_LAST - 1, -- cgit v1.2.3 From e9374524950512a1769f610a868fcdf89ea59b8e Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Tue, 22 Nov 2022 20:30:57 +0100 Subject: netfilter: ipset: Add support for new bitmask parameter Add a new parameter to complement the existing 'netmask' option. The main difference between netmask and bitmask is that bitmask takes any arbitrary ip address as input, it does not have to be a valid netmask. The name of the new parameter is 'bitmask'. This lets us mask out arbitrary bits in the ip address, for example: ipset create set1 hash:ip bitmask 255.128.255.0 ipset create set2 hash:ip,port family inet6 bitmask ffff::ff80 Signed-off-by: Vishwanath Pai Signed-off-by: Joshua Hunt Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 10 ++++ include/uapi/linux/netfilter/ipset/ip_set.h | 2 + net/netfilter/ipset/ip_set_hash_gen.h | 71 +++++++++++++++++++++++++---- net/netfilter/ipset/ip_set_hash_ip.c | 19 ++++---- net/netfilter/ipset/ip_set_hash_ipport.c | 24 +++++++++- net/netfilter/ipset/ip_set_hash_netnet.c | 26 +++++++++-- 6 files changed, 126 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ada1296c87d5..ab934ad951a8 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -515,6 +515,16 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, *skbinfo = ext->skbinfo; } +static inline void +nf_inet_addr_mask_inplace(union nf_inet_addr *a1, + const union nf_inet_addr *mask) +{ + a1->all[0] &= mask->all[0]; + a1->all[1] &= mask->all[1]; + a1->all[2] &= mask->all[2]; + a1->all[3] &= mask->all[3]; +} + #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index 79e5d68b87af..333807efd32b 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -85,6 +85,7 @@ enum { IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */ IPSET_ATTR_MARK, /* 10 */ IPSET_ATTR_MARKMASK, /* 11 */ + IPSET_ATTR_BITMASK, /* 12 */ /* Reserve empty slots */ IPSET_ATTR_CADT_MAX = 16, /* Create-only specific attributes */ @@ -153,6 +154,7 @@ enum ipset_errno { IPSET_ERR_COMMENT, IPSET_ERR_INVALID_MARKMASK, IPSET_ERR_SKBINFO, + IPSET_ERR_BITMASK_NETMASK_EXCL, /* Type specific error codes */ IPSET_ERR_TYPE_SPECIFIC = 4352, diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3adc291d9ce1..fdb5225a3e5c 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -159,6 +159,17 @@ htable_size(u8 hbits) (SET_WITH_TIMEOUT(set) && \ ip_set_timeout_expired(ext_timeout(d, set))) +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) +static const union nf_inet_addr onesmask = { + .all[0] = 0xffffffff, + .all[1] = 0xffffffff, + .all[2] = 0xffffffff, + .all[3] = 0xffffffff +}; + +static const union nf_inet_addr zeromask = {}; +#endif + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -283,8 +294,9 @@ struct htype { u32 markmask; /* markmask value for mark mask to store */ #endif u8 bucketsize; /* max elements in an array block */ -#ifdef IP_SET_HASH_WITH_NETMASK +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) u8 netmask; /* netmask value for subnets to store */ + union nf_inet_addr bitmask; /* stores bitmask */ #endif struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ @@ -459,8 +471,8 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) /* Resizing changes htable_bits, so we ignore it */ return x->maxelem == y->maxelem && a->timeout == b->timeout && -#ifdef IP_SET_HASH_WITH_NETMASK - x->netmask == y->netmask && +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + nf_inet_addr_cmp(&x->bitmask, &y->bitmask) && #endif #ifdef IP_SET_HASH_WITH_MARKMASK x->markmask == y->markmask && @@ -1264,9 +1276,21 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) htonl(jhash_size(htable_bits))) || nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; +#ifdef IP_SET_HASH_WITH_BITMASK + /* if netmask is set to anything other than HOST_MASK we know that the user supplied netmask + * and not bitmask. These two are mutually exclusive. */ + if (h->netmask == HOST_MASK && !nf_inet_addr_cmp(&onesmask, &h->bitmask)) { + if (set->family == NFPROTO_IPV4) { + if (nla_put_ipaddr4(skb, IPSET_ATTR_BITMASK, h->bitmask.ip)) + goto nla_put_failure; + } else if (set->family == NFPROTO_IPV6) { + if (nla_put_ipaddr6(skb, IPSET_ATTR_BITMASK, &h->bitmask.in6)) + goto nla_put_failure; + } + } +#endif #ifdef IP_SET_HASH_WITH_NETMASK - if (h->netmask != HOST_MASK && - nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) + if (h->netmask != HOST_MASK && nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) goto nla_put_failure; #endif #ifdef IP_SET_HASH_WITH_MARKMASK @@ -1429,8 +1453,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, u32 markmask; #endif u8 hbits; -#ifdef IP_SET_HASH_WITH_NETMASK - u8 netmask; +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + int ret __attribute__((unused)) = 0; + u8 netmask = set->family == NFPROTO_IPV4 ? 32 : 128; + union nf_inet_addr bitmask = onesmask; #endif size_t hsize; struct htype *h; @@ -1468,7 +1494,6 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif #ifdef IP_SET_HASH_WITH_NETMASK - netmask = set->family == NFPROTO_IPV4 ? 32 : 128; if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); @@ -1476,6 +1501,33 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, (set->family == NFPROTO_IPV6 && netmask > 128) || netmask == 0) return -IPSET_ERR_INVALID_NETMASK; + + /* we convert netmask to bitmask and store it */ + if (set->family == NFPROTO_IPV4) + bitmask.ip = ip_set_netmask(netmask); + else + ip6_netmask(&bitmask, netmask); + } +#endif + +#ifdef IP_SET_HASH_WITH_BITMASK + if (tb[IPSET_ATTR_BITMASK]) { + /* bitmask and netmask do the same thing, allow only one of these options */ + if (tb[IPSET_ATTR_NETMASK]) + return -IPSET_ERR_BITMASK_NETMASK_EXCL; + + if (set->family == NFPROTO_IPV4) { + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_BITMASK], &bitmask.ip); + if (ret || !bitmask.ip) + return -IPSET_ERR_INVALID_NETMASK; + } else if (set->family == NFPROTO_IPV6) { + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_BITMASK], &bitmask); + if (ret || ipv6_addr_any(&bitmask.in6)) + return -IPSET_ERR_INVALID_NETMASK; + } + + if (nf_inet_addr_cmp(&bitmask, &zeromask)) + return -IPSET_ERR_INVALID_NETMASK; } #endif @@ -1518,7 +1570,8 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, for (i = 0; i < ahash_numof_locks(hbits); i++) spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; -#ifdef IP_SET_HASH_WITH_NETMASK +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + h->bitmask = bitmask; h->netmask = netmask; #endif #ifdef IP_SET_HASH_WITH_MARKMASK diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..556f74268a28 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -24,7 +24,8 @@ /* 2 Comments support */ /* 3 Forceadd support */ /* 4 skbinfo support */ -#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */ +/* 5 bucketsize, initval support */ +#define IPSET_TYPE_REV_MAX 6 /* bitmask support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -34,6 +35,7 @@ MODULE_ALIAS("ip_set_hash:ip"); /* Type specific function prefix */ #define HTYPE hash_ip #define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK /* IPv4 variant */ @@ -86,7 +88,7 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb, __be32 ip; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip); - ip &= ip_set_netmask(h->netmask); + ip &= h->bitmask.ip; if (ip == 0) return -EINVAL; @@ -119,7 +121,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - ip &= ip_set_hostmask(h->netmask); + ip &= ntohl(h->bitmask.ip); e.ip = htonl(ip); if (e.ip == 0) return -IPSET_ERR_HASH_ELEM; @@ -187,12 +189,6 @@ hash_ip6_data_equal(const struct hash_ip6_elem *ip1, return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6); } -static void -hash_ip6_netmask(union nf_inet_addr *ip, u8 prefix) -{ - ip6_netmask(ip, prefix); -} - static bool hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e) { @@ -229,7 +225,7 @@ hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb, struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); - hash_ip6_netmask(&e.ip, h->netmask); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -EINVAL; @@ -268,7 +264,7 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - hash_ip6_netmask(&e.ip, h->netmask); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -IPSET_ERR_HASH_ELEM; @@ -295,6 +291,7 @@ static struct ip_set_type hash_ip_type __read_mostly = { [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 7303138e46be..2ffbd0b78a8c 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -26,7 +26,8 @@ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ +/* 6 bucketsize, initval support added */ +#define IPSET_TYPE_REV_MAX 7 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -35,6 +36,8 @@ MODULE_ALIAS("ip_set_hash:ip,port"); /* Type specific function prefix */ #define HTYPE hash_ipport +#define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK /* IPv4 variant */ @@ -92,12 +95,16 @@ hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + const struct MTYPE *h = set->data; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); + e.ip &= h->bitmask.ip; + if (e.ip == 0) + return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -129,6 +136,10 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; + e.ip &= h->bitmask.ip; + if (e.ip == 0) + return -EINVAL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { @@ -253,12 +264,17 @@ hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + const struct MTYPE *h = set->data; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); + if (ipv6_addr_any(&e.ip.in6)) + return -EINVAL; + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -298,6 +314,10 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); + if (ipv6_addr_any(&e.ip.in6)) + return -EINVAL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { @@ -356,6 +376,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 3d09eefe998a..cdfb78c6e0d3 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -23,7 +23,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ /* 2 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ +/* 3 bucketsize, initval support added */ +#define IPSET_TYPE_REV_MAX 4 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -33,6 +34,8 @@ MODULE_ALIAS("ip_set_hash:net,net"); /* Type specific function prefix */ #define HTYPE hash_netnet #define IP_SET_HASH_WITH_NETS +#define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK #define IPSET_NET_COUNT 2 /* IPv4 variants */ @@ -153,8 +156,8 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]); ip4addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1]); - e.ip[0] &= ip_set_netmask(e.cidr[0]); - e.ip[1] &= ip_set_netmask(e.cidr[1]); + e.ip[0] &= (ip_set_netmask(e.cidr[0]) & h->bitmask.ip); + e.ip[1] &= (ip_set_netmask(e.cidr[1]) & h->bitmask.ip); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -213,8 +216,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) { - e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0])); - e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1])); + e.ip[0] = htonl(ip & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[0])); + e.ip[1] = htonl(ip2_from & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[1])); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; @@ -404,6 +407,11 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); + nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); + nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); + if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) + return -EINVAL; + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -414,6 +422,7 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + const struct hash_netnet6 *h = set->data; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -453,6 +462,11 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); + nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); + nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); + if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) + return -IPSET_ERR_HASH_ELEM; + if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); @@ -484,6 +498,8 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, -- cgit v1.2.3 From c67cae551f0df80421b5703ee56ff5e2fe9c4de6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 25 Nov 2022 14:06:17 -0800 Subject: bpf: Tighten ptr_to_btf_id checks. The networking programs typically don't require CAP_PERFMON, but through kfuncs like bpf_cast_to_kern_ctx() they can access memory through PTR_TO_BTF_ID. In such case enforce CAP_PERFMON. Also make sure that only GPL programs can access kernel data structures. All kfuncs require GPL already. Also remove allow_ptr_to_map_access. It's the same as allow_ptr_leaks and different name for the same check only causes confusion. Fixes: fd264ca02094 ("bpf: Add a kfunc to type cast from bpf uapi ctx to kernel ctx") Fixes: 50c6b8a9aea2 ("selftests/bpf: Add a test for btf_type_tag "percpu"") Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20221125220617.26846-1-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 5 ----- include/linux/bpf_verifier.h | 1 - kernel/bpf/verifier.c | 17 ++++++++++++++--- tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c | 1 + tools/testing/selftests/bpf/verifier/map_ptr.c | 8 ++++---- 5 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 67452103bb86..4920ac252754 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1909,11 +1909,6 @@ static inline bool bpf_allow_uninit_stack(void) return perfmon_capable(); } -static inline bool bpf_allow_ptr_to_map_access(void) -{ - return perfmon_capable(); -} - static inline bool bpf_bypass_spec_v1(void) { return perfmon_capable(); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c05aa6e1f6f5..b5090e89cb3f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -531,7 +531,6 @@ struct bpf_verifier_env { bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; - bool allow_ptr_to_map_access; bool bpf_capable; bool bypass_spec_v1; bool bypass_spec_v4; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4e7f1d085e53..d0ecc0b18b20 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4703,6 +4703,18 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, u32 btf_id; int ret; + if (!env->allow_ptr_leaks) { + verbose(env, + "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + tname); + return -EPERM; + } + if (!env->prog->gpl_compatible && btf_is_kernel(reg->btf)) { + verbose(env, + "Cannot access kernel 'struct %s' from non-GPL compatible program\n", + tname); + return -EINVAL; + } if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", @@ -4823,9 +4835,9 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id); tname = btf_name_by_offset(btf_vmlinux, t->name_off); - if (!env->allow_ptr_to_map_access) { + if (!env->allow_ptr_leaks) { verbose(env, - "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", + "'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n", tname); return -EPERM; } @@ -16679,7 +16691,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c index 8feddb8289cf..38f78d9345de 100644 --- a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c +++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c @@ -64,3 +64,4 @@ int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path) return 0; } +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c index 1f82021429bf..17ee84dc7766 100644 --- a/tools/testing/selftests/bpf/verifier/map_ptr.c +++ b/tools/testing/selftests/bpf/verifier/map_ptr.c @@ -9,7 +9,7 @@ }, .fixup_map_array_48b = { 1 }, .result_unpriv = REJECT, - .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", .result = REJECT, .errstr = "R1 is bpf_array invalid negative access: off=-8", }, @@ -26,7 +26,7 @@ }, .fixup_map_array_48b = { 3 }, .result_unpriv = REJECT, - .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", .result = REJECT, .errstr = "only read from bpf_array is supported", }, @@ -41,7 +41,7 @@ }, .fixup_map_array_48b = { 1 }, .result_unpriv = REJECT, - .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", .result = REJECT, .errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4", .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, @@ -57,7 +57,7 @@ }, .fixup_map_array_48b = { 1 }, .result_unpriv = REJECT, - .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", + .errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", .result = ACCEPT, .retval = 1, }, -- cgit v1.2.3 From a351d6087bf7d3d8440d58d3bf244ec64b89394a Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Tue, 29 Nov 2022 18:40:39 +0800 Subject: bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes When redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag. So we need to save the BPF_F_INGRESS flag in sk_psock and use it when redirection. Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support") Signed-off-by: Pengcheng Yang Signed-off-by: Daniel Borkmann Acked-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/1669718441-2654-3-git-send-email-yangpc@wangsu.com --- include/linux/skmsg.h | 1 + include/net/tcp.h | 4 ++-- net/core/skmsg.c | 9 ++++++--- net/ipv4/tcp_bpf.c | 11 ++++++----- net/tls/tls_sw.c | 6 ++++-- 5 files changed, 19 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 70d6cb94e580..84f787416a54 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -82,6 +82,7 @@ struct sk_psock { u32 apply_bytes; u32 cork_bytes; u32 eval; + bool redir_ingress; /* undefined if sk_redir is null */ struct sk_msg *cork; struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) diff --git a/include/net/tcp.h b/include/net/tcp.h index 6b814e788f00..b87e7381bddf 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2319,8 +2319,8 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); #endif /* CONFIG_BPF_SYSCALL */ -int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes, - int flags); +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags); #endif /* CONFIG_NET_SOCK_MSG */ #if !defined(CONFIG_BPF_SYSCALL) || !defined(CONFIG_NET_SOCK_MSG) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e6b9ced3eda8..53d0251788aa 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -886,13 +886,16 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, ret = sk_psock_map_verd(ret, msg->sk_redir); psock->apply_bytes = msg->apply_bytes; if (ret == __SK_REDIRECT) { - if (psock->sk_redir) + if (psock->sk_redir) { sock_put(psock->sk_redir); - psock->sk_redir = msg->sk_redir; - if (!psock->sk_redir) { + psock->sk_redir = NULL; + } + if (!msg->sk_redir) { ret = __SK_DROP; goto out; } + psock->redir_ingress = sk_msg_to_ingress(msg); + psock->sk_redir = msg->sk_redir; sock_hold(psock->sk_redir); } out: diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index f3e868f4cd9e..275c5ca9e04d 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -131,10 +131,9 @@ static int tcp_bpf_push_locked(struct sock *sk, struct sk_msg *msg, return ret; } -int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, - u32 bytes, int flags) +int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, + struct sk_msg *msg, u32 bytes, int flags) { - bool ingress = sk_msg_to_ingress(msg); struct sk_psock *psock = sk_psock_get(sk); int ret; @@ -276,7 +275,7 @@ msg_bytes_ready: static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = sk_msg_full(msg); + bool cork = false, enospc = sk_msg_full(msg), redir_ingress; struct sock *sk_redir; u32 tosend, origsize, sent, delta = 0; u32 eval; @@ -322,6 +321,7 @@ more_data: sk_msg_apply_bytes(psock, tosend); break; case __SK_REDIRECT: + redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); if (!psock->apply_bytes) { @@ -338,7 +338,8 @@ more_data: release_sock(sk); origsize = msg->sg.size; - ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + ret = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, + msg, tosend, flags); sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 264cf367e265..9ed978634125 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -792,7 +792,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, struct sk_psock *psock; struct sock *sk_redir; struct tls_rec *rec; - bool enospc, policy; + bool enospc, policy, redir_ingress; int err = 0, send; u32 delta = 0; @@ -837,6 +837,7 @@ more_data: } break; case __SK_REDIRECT: + redir_ingress = psock->redir_ingress; sk_redir = psock->sk_redir; memcpy(&msg_redir, msg, sizeof(*msg)); if (msg->apply_bytes < send) @@ -846,7 +847,8 @@ more_data: sk_msg_return_zero(sk, msg, send); msg->sg.size -= send; release_sock(sk); - err = tcp_bpf_sendmsg_redir(sk_redir, &msg_redir, send, flags); + err = tcp_bpf_sendmsg_redir(sk_redir, redir_ingress, + &msg_redir, send, flags); lock_sock(sk); if (err < 0) { *copied -= sk_msg_free_nocharge(sk, &msg_redir); -- cgit v1.2.3 From 3144bfa5078e0df7507a4de72061501e6a0e56be Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 29 Nov 2022 21:21:47 -0800 Subject: bpf: Fix a compilation failure with clang lto build When building the kernel with clang lto (CONFIG_LTO_CLANG_FULL=y), the following compilation error will appear: $ make LLVM=1 LLVM_IAS=1 -j ... ld.lld: error: ld-temp.o :26889:1: symbol 'cgroup_storage_map_btf_ids' is already defined cgroup_storage_map_btf_ids:; ^ make[1]: *** [/.../bpf-next/scripts/Makefile.vmlinux_o:61: vmlinux.o] Error 1 In local_storage.c, we have BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_local_storage_map) Commit c4bcfb38a95e ("bpf: Implement cgroup storage available to non-cgroup-attached bpf progs") added the above identical BTF_ID_LIST_SINGLE definition in bpf_cgrp_storage.c. With duplicated definitions, llvm linker complains with lto build. Also, extracting btf_id of 'struct bpf_local_storage_map' is defined four times for sk, inode, task and cgrp local storages. Let us define a single global one with a different name than cgroup_storage_map_btf_ids, which also fixed the lto compilation error. Fixes: c4bcfb38a95e ("bpf: Implement cgroup storage available to non-cgroup-attached bpf progs") Signed-off-by: Yonghong Song Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20221130052147.1591625-1-yhs@fb.com --- include/linux/btf_ids.h | 1 + kernel/bpf/bpf_cgrp_storage.c | 3 +-- kernel/bpf/bpf_inode_storage.c | 4 +--- kernel/bpf/bpf_task_storage.c | 4 ++-- net/core/bpf_sk_storage.c | 3 +-- 5 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 93397711a68c..3a4f7cd882ca 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -266,5 +266,6 @@ MAX_BTF_TRACING_TYPE, extern u32 btf_tracing_ids[]; extern u32 bpf_cgroup_btf_id[]; +extern u32 bpf_local_storage_map_btf_id[]; #endif diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index 309403800f82..6cdf6d9ed91d 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -211,7 +211,6 @@ BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgro return ret; } -BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_local_storage_map) const struct bpf_map_ops cgrp_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -222,7 +221,7 @@ const struct bpf_map_ops cgrp_storage_map_ops = { .map_update_elem = bpf_cgrp_storage_update_elem, .map_delete_elem = bpf_cgrp_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_id = &cgroup_storage_map_btf_ids[0], + .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = cgroup_storage_ptr, }; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 6a1d4d22816a..05f4c66c9089 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -213,8 +213,6 @@ static void inode_storage_map_free(struct bpf_map *map) bpf_local_storage_map_free(map, &inode_cache, NULL); } -BTF_ID_LIST_SINGLE(inode_storage_map_btf_ids, struct, - bpf_local_storage_map) const struct bpf_map_ops inode_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -225,7 +223,7 @@ const struct bpf_map_ops inode_storage_map_ops = { .map_update_elem = bpf_fd_inode_storage_update_elem, .map_delete_elem = bpf_fd_inode_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_id = &inode_storage_map_btf_ids[0], + .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = inode_storage_ptr, }; diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 8e832db8151a..1e486055a523 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -324,7 +324,7 @@ static void task_storage_map_free(struct bpf_map *map) bpf_local_storage_map_free(map, &task_cache, &bpf_task_storage_busy); } -BTF_ID_LIST_SINGLE(task_storage_map_btf_ids, struct, bpf_local_storage_map) +BTF_ID_LIST_GLOBAL_SINGLE(bpf_local_storage_map_btf_id, struct, bpf_local_storage_map) const struct bpf_map_ops task_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -335,7 +335,7 @@ const struct bpf_map_ops task_storage_map_ops = { .map_update_elem = bpf_pid_task_storage_update_elem, .map_delete_elem = bpf_pid_task_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_id = &task_storage_map_btf_ids[0], + .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_owner_storage_ptr = task_storage_ptr, }; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 9d2288c0736e..bb378c33f542 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -310,7 +310,6 @@ bpf_sk_storage_ptr(void *owner) return &sk->sk_bpf_storage; } -BTF_ID_LIST_SINGLE(sk_storage_map_btf_ids, struct, bpf_local_storage_map) const struct bpf_map_ops sk_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, @@ -321,7 +320,7 @@ const struct bpf_map_ops sk_storage_map_ops = { .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, - .map_btf_id = &sk_storage_map_btf_ids[0], + .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_local_storage_charge = bpf_sk_storage_charge, .map_local_storage_uncharge = bpf_sk_storage_uncharge, .map_owner_storage_ptr = bpf_sk_storage_ptr, -- cgit v1.2.3 From af6397c9ee2b42988c912dcad2fca1f43d5c1c99 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 28 Nov 2022 12:36:44 -0800 Subject: devlink: support directly reading from region memory To read from a region, user space must currently request a new snapshot of the region and then read from that snapshot. This can sometimes be overkill if user space only reads a tiny portion. They first create the snapshot, then request a read, then destroy the snapshot. For regions which have a single underlying "contents", it makes sense to allow supporting direct reading of the region data. Extend the DEVLINK_CMD_REGION_READ to allow direct reading from a region if requested via the new DEVLINK_ATTR_REGION_DIRECT. If this attribute is set, then perform a direct read instead of using a snapshot. Direct read is mutually exclusive with DEVLINK_ATTR_REGION_SNAPSHOT_ID, and care is taken to ensure that we reject commands which provide incorrect attributes. Regions must enable support for direct read by implementing the .read() callback function. If a region does not support such direct reads, a suitable extended error message is reported. Signed-off-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- .../networking/devlink/devlink-region.rst | 13 ++++ include/net/devlink.h | 16 +++++ include/uapi/linux/devlink.h | 2 + net/core/devlink.c | 80 +++++++++++++++++----- 4 files changed, 94 insertions(+), 17 deletions(-) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index f06dca9a1eb6..9232cd7da301 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -31,6 +31,15 @@ in its ``devlink_region_ops`` structure. If snapshot id is not set in the ``DEVLINK_CMD_REGION_NEW`` request kernel will allocate one and send the snapshot information to user space. +Regions may optionally allow directly reading from their contents without a +snapshot. Direct read requests are not atomic. In particular a read request +of size 256 bytes or larger will be split into multiple chunks. If atomic +access is required, use a snapshot. A driver wishing to enable this for a +region should implement the ``.read`` callback in the ``devlink_region_ops`` +structure. User space can request a direct read by using the +``DEVLINK_ATTR_REGION_DIRECT`` attribute instead of specifying a snapshot +id. + example usage ------------- @@ -65,6 +74,10 @@ example usage $ devlink region read pci/0000:00:05.0/fw-health snapshot 1 address 0 length 16 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30 + # Read from the region without a snapshot + $ devlink region read pci/0000:00:05.0/fw-health address 16 length 16 + 0000000000000010 0000 0000 ffff ff04 0029 8c00 0028 8cc8 + As regions are likely very device or driver specific, no generic regions are defined. See the driver-specific documentation files for information on the specific regions a driver supports. diff --git a/include/net/devlink.h b/include/net/devlink.h index 074a79b8933f..02528f736f65 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -650,6 +650,10 @@ struct devlink_info_req; * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @read: callback to directly read a portion of the region. On success, + * the data pointer will be updated with the contents of the + * requested portion of the region. The function will be called + * while the devlink instance lock is held. * @priv: Pointer to driver private data for the region operation */ struct devlink_region_ops { @@ -659,6 +663,10 @@ struct devlink_region_ops { const struct devlink_region_ops *ops, struct netlink_ext_ack *extack, u8 **data); + int (*read)(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data); void *priv; }; @@ -670,6 +678,10 @@ struct devlink_region_ops { * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @read: callback to directly read a portion of the region. On success, + * the data pointer will be updated with the contents of the + * requested portion of the region. The function will be called + * while the devlink instance lock is held. * @priv: Pointer to driver private data for the region operation */ struct devlink_port_region_ops { @@ -679,6 +691,10 @@ struct devlink_port_region_ops { const struct devlink_port_region_ops *ops, struct netlink_ext_ack *extack, u8 **data); + int (*read)(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data); void *priv; }; diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 498d0d5d0957..70191d96af89 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -610,6 +610,8 @@ enum devlink_attr { DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ DEVLINK_ATTR_RATE_TX_WEIGHT, /* u32 */ + DEVLINK_ATTR_REGION_DIRECT, /* flag */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 6c05cfaa571d..298041a44aa8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -6515,6 +6515,26 @@ devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, return 0; } +static int +devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, + u64 curr_offset, struct netlink_ext_ack *extack) +{ + struct devlink_region *region = cb_priv; + + return region->port_ops->read(region->port, region->port_ops, extack, + curr_offset, chunk_size, chunk); +} + +static int +devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, + u64 curr_offset, struct netlink_ext_ack *extack) +{ + struct devlink_region *region = cb_priv; + + return region->ops->read(region->devlink, region->ops, extack, + curr_offset, chunk_size, chunk); +} + static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { @@ -6523,12 +6543,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->attrs; struct devlink_port *port = NULL; - struct devlink_snapshot *snapshot; + devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; - u32 snapshot_id; + void *region_cb_priv; void *hdr; int err; @@ -6546,12 +6566,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } - if (!attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { - NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); - err = -EINVAL; - goto out_unlock; - } - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); @@ -6577,12 +6591,43 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; - snapshot_id = nla_get_u32(snapshot_attr); - snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); - if (!snapshot) { - NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); - err = -EINVAL; - goto out_unlock; + if (!snapshot_attr) { + if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { + NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); + err = -EINVAL; + goto out_unlock; + } + + if (!region->ops->read) { + NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); + err = -EOPNOTSUPP; + goto out_unlock; + } + + if (port) + region_cb = &devlink_region_port_direct_fill; + else + region_cb = &devlink_region_direct_fill; + region_cb_priv = region; + } else { + struct devlink_snapshot *snapshot; + u32 snapshot_id; + + if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { + NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); + err = -EINVAL; + goto out_unlock; + } + + snapshot_id = nla_get_u32(snapshot_attr); + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) { + NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); + err = -EINVAL; + goto out_unlock; + } + region_cb = &devlink_region_snapshot_fill; + region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && @@ -6633,9 +6678,9 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; } - err = devlink_nl_region_read_fill(skb, &devlink_region_snapshot_fill, - snapshot, start_offset, end_offset, - &ret_offset, cb->extack); + err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, + start_offset, end_offset, &ret_offset, + cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; @@ -9280,6 +9325,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit v1.2.3 From 226bf980550627c88549b112ac6c8fb40873afb4 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 29 Nov 2022 18:51:38 +0900 Subject: net: devlink: let the core report the driver name instead of the drivers The driver name is available in device_driver::name. Right now, drivers still have to report this piece of information themselves in their devlink_ops::info_get callback function. In order to factorize code, make devlink_nl_info_fill() add the driver name attribute. Now that the core sets the driver name attribute, drivers are not supposed to call devlink_info_driver_name_put() anymore. Remove devlink_info_driver_name_put() and clean-up all the drivers using this function in their callback. Signed-off-by: Vincent Mailhol Tested-by: Ido Schimmel # mlxsw Reviewed-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- .../crypto/marvell/octeontx2/otx2_cpt_devlink.c | 4 ---- drivers/net/dsa/hirschmann/hellcreek.c | 5 ----- drivers/net/dsa/mv88e6xxx/devlink.c | 5 ----- drivers/net/dsa/sja1105/sja1105_devlink.c | 12 +++------- drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 4 ---- .../ethernet/freescale/dpaa2/dpaa2-eth-devlink.c | 11 +-------- .../net/ethernet/fungible/funeth/funeth_devlink.c | 2 +- .../ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c | 5 ----- .../hisilicon/hns3/hns3vf/hclgevf_devlink.c | 5 ----- drivers/net/ethernet/intel/ice/ice_devlink.c | 6 ----- .../ethernet/marvell/octeontx2/af/rvu_devlink.c | 2 +- .../ethernet/marvell/octeontx2/nic/otx2_devlink.c | 9 +------- .../ethernet/marvell/prestera/prestera_devlink.c | 5 ----- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 4 ---- drivers/net/ethernet/mellanox/mlxsw/core.c | 5 ----- drivers/net/ethernet/netronome/nfp/nfp_devlink.c | 4 ---- .../net/ethernet/pensando/ionic/ionic_devlink.c | 4 ---- drivers/net/ethernet/qlogic/qed/qed_devlink.c | 4 ---- drivers/net/netdevsim/dev.c | 3 --- drivers/ptp/ptp_ocp.c | 4 ---- include/net/devlink.h | 2 -- net/core/devlink.c | 26 +++++++++++++++------- 22 files changed, 25 insertions(+), 106 deletions(-) (limited to 'include') diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c index 7503f6b18ac5..a2aba0b0d68a 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_devlink.c @@ -76,10 +76,6 @@ static int otx2_cpt_devlink_info_get(struct devlink *dl, struct otx2_cptpf_dev *cptpf = cpt_dl->cptpf; int err; - err = devlink_info_driver_name_put(req, "rvu_cptpf"); - if (err) - return err; - err = otx2_cpt_dl_info_firmware_version_put(req, cptpf->eng_grps.grp, "fw.ae", OTX2_CPT_AE_TYPES); if (err) diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 951f7935c872..595a548bb0a8 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -1176,11 +1176,6 @@ static int hellcreek_devlink_info_get(struct dsa_switch *ds, struct netlink_ext_ack *extack) { struct hellcreek *hellcreek = ds->priv; - int ret; - - ret = devlink_info_driver_name_put(req, "hellcreek"); - if (ret) - return ret; return devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 1266eabee086..a08dab75e0c0 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -821,11 +821,6 @@ int mv88e6xxx_devlink_info_get(struct dsa_switch *ds, struct netlink_ext_ack *extack) { struct mv88e6xxx_chip *chip = ds->priv; - int err; - - err = devlink_info_driver_name_put(req, "mv88e6xxx"); - if (err) - return err; return devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 10c6fea1227f..da532614f34a 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -120,16 +120,10 @@ int sja1105_devlink_info_get(struct dsa_switch *ds, struct netlink_ext_ack *extack) { struct sja1105_private *priv = ds->priv; - int rc; - - rc = devlink_info_driver_name_put(req, "sja1105"); - if (rc) - return rc; - rc = devlink_info_version_fixed_put(req, - DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, - priv->info->name); - return rc; + return devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, + priv->info->name); } int sja1105_devlink_setup(struct dsa_switch *ds) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 8a6f788f6294..26913dc816d3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -892,10 +892,6 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req, u32 ver = 0; int rc; - rc = devlink_info_driver_name_put(req, DRV_MODULE_NAME); - if (rc) - return rc; - if (BNXT_PF(bp) && (bp->flags & BNXT_FLAG_DSN_VALID)) { sprintf(buf, "%02X-%02X-%02X-%02X-%02X-%02X-%02X-%02X", bp->dsn[7], bp->dsn[6], bp->dsn[5], bp->dsn[4], diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c index 5c6dd3029e2f..76f808d38066 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c @@ -37,18 +37,9 @@ static int dpaa2_eth_dl_info_get(struct devlink *devlink, struct dpaa2_eth_devlink_priv *dl_priv = devlink_priv(devlink); struct dpaa2_eth_priv *priv = dl_priv->dpaa2_priv; char buf[10]; - int err; - - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; scnprintf(buf, 10, "%d.%d", priv->dpni_ver_major, priv->dpni_ver_minor); - err = devlink_info_version_running_put(req, "dpni", buf); - if (err) - return err; - - return 0; + return devlink_info_version_running_put(req, "dpni", buf); } static struct dpaa2_eth_trap_item * diff --git a/drivers/net/ethernet/fungible/funeth/funeth_devlink.c b/drivers/net/ethernet/fungible/funeth/funeth_devlink.c index d50c222948b4..6668375edff6 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_devlink.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_devlink.c @@ -6,7 +6,7 @@ static int fun_dl_info_get(struct devlink *dl, struct devlink_info_req *req, struct netlink_ext_ack *extack) { - return devlink_info_driver_name_put(req, KBUILD_MODNAME); + return 0; } static const struct devlink_ops fun_dl_ops = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index 4c441e6a5082..3d3b69605423 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -13,11 +13,6 @@ static int hclge_devlink_info_get(struct devlink *devlink, struct hclge_devlink_priv *priv = devlink_priv(devlink); char version_str[HCLGE_DEVLINK_FW_STRING_LEN]; struct hclge_dev *hdev = priv->hdev; - int ret; - - ret = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (ret) - return ret; snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu", hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index fdc19868b818..a6c3c5e8f0ab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -13,11 +13,6 @@ static int hclgevf_devlink_info_get(struct devlink *devlink, struct hclgevf_devlink_priv *priv = devlink_priv(devlink); char version_str[HCLGEVF_DEVLINK_FW_STRING_LEN]; struct hclgevf_dev *hdev = priv->hdev; - int ret; - - ret = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (ret) - return ret; snprintf(version_str, sizeof(version_str), "%lu.%lu.%lu.%lu", hnae3_get_field(hdev->fw_version, HNAE3_FW_VERSION_BYTE3_MASK, diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 946d64e577c9..8286e47b4bae 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -311,12 +311,6 @@ static int ice_devlink_info_get(struct devlink *devlink, } } - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Unable to set driver name"); - goto out_free_ctx; - } - ice_info_get_dsn(pf, ctx); err = devlink_info_serial_number_put(req, ctx->buf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 88dee589cb21..f15439d26d21 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1550,7 +1550,7 @@ static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack) { - return devlink_info_driver_name_put(req, DRV_NAME); + return 0; } static const struct devlink_ops rvu_devlink_ops = { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 777a27047c8e..5cc6416cf1a6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -77,18 +77,11 @@ static const struct devlink_param otx2_dl_params[] = { otx2_dl_mcam_count_validate), }; -/* Devlink OPs */ static int otx2_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, struct netlink_ext_ack *extack) { - struct otx2_devlink *otx2_dl = devlink_priv(devlink); - struct otx2_nic *pfvf = otx2_dl->pfvf; - - if (is_otx2_vf(pfvf->pcifunc)) - return devlink_info_driver_name_put(req, "rvu_nicvf"); - - return devlink_info_driver_name_put(req, "rvu_nicpf"); + return 0; } static const struct devlink_ops otx2_devlink_ops = { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 84ad05c9f12d..2a4c9df4eb79 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -355,11 +355,6 @@ static int prestera_dl_info_get(struct devlink *dl, { struct prestera_switch *sw = devlink_priv(dl); char buf[16]; - int err; - - err = devlink_info_driver_name_put(req, PRESTERA_DRV_NAME); - if (err) - return err; snprintf(buf, sizeof(buf), "%d.%d.%d", sw->dev->fw_rev.maj, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index cc2ae427dcb0..751bc4a9edcf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -46,10 +46,6 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, u32 running_fw, stored_fw; int err; - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; - err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index a83f6bc30072..a0a06e2eff82 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1459,11 +1459,6 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, char buf[32]; int err; - err = devlink_info_driver_name_put(req, - mlxsw_core->bus_info->device_kind); - if (err) - return err; - mlxsw_reg_mgir_pack(mgir_pl); err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mgir), mgir_pl); if (err) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 784f23602a8a..bf6bae557158 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -239,10 +239,6 @@ nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, char *buf = NULL; int err; - err = devlink_info_driver_name_put(req, "nfp"); - if (err) - return err; - vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor"); part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno"); sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial"); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 567f778433e2..e6ff757895ab 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -26,10 +26,6 @@ static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req, char buf[16]; int err = 0; - err = devlink_info_driver_name_put(req, IONIC_DRV_NAME); - if (err) - return err; - err = devlink_info_version_running_put(req, DEVLINK_INFO_VERSION_GENERIC_FW, idev->dev_info.fw_version); diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index 6bb4e165b592..922c47797af6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -162,10 +162,6 @@ static int qed_devlink_info_get(struct devlink *devlink, dev_info = &cdev->common_dev_info; - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; - memcpy(buf, cdev->hwfns[0].hw_info.part_num, sizeof(cdev->hwfns[0].hw_info.part_num)); buf[sizeof(cdev->hwfns[0].hw_info.part_num)] = 0; diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index e14686594a71..b962fc8e1397 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -994,9 +994,6 @@ static int nsim_dev_info_get(struct devlink *devlink, { int err; - err = devlink_info_driver_name_put(req, DRV_NAME); - if (err) - return err; err = devlink_info_version_stored_put_ext(req, "fw.mgmt", "10.20.30", DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 154d58cbd9ce..4bbaccd543ad 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -1647,10 +1647,6 @@ ptp_ocp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, char buf[32]; int err; - err = devlink_info_driver_name_put(req, KBUILD_MODNAME); - if (err) - return err; - fw_image = bp->fw_loader ? "loader" : "fw"; sprintf(buf, "%d.%d", bp->fw_tag, bp->fw_version); err = devlink_info_version_running_put(req, fw_image, buf); diff --git a/include/net/devlink.h b/include/net/devlink.h index 02528f736f65..5f6eca5e4a40 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1762,8 +1762,6 @@ int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id); int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn); -int devlink_info_driver_name_put(struct devlink_info_req *req, - const char *name); int devlink_info_board_serial_number_put(struct devlink_info_req *req, const char *bsn); diff --git a/net/core/devlink.c b/net/core/devlink.c index 298041a44aa8..60eb0f46520f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -6707,14 +6707,6 @@ out_unlock: return err; } -int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); -} -EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); - int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) { if (!req->msg) @@ -6823,11 +6815,25 @@ int devlink_info_version_running_put_ext(struct devlink_info_req *req, } EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); +static int devlink_nl_driver_info_get(struct device_driver *drv, + struct devlink_info_req *req) +{ + if (!drv) + return 0; + + if (drv->name[0]) + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, + drv->name); + + return 0; +} + static int devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) { + struct device *dev = devlink_to_dev(devlink); struct devlink_info_req req = {}; void *hdr; int err; @@ -6845,6 +6851,10 @@ devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto err_cancel_msg; + err = devlink_nl_driver_info_get(dev->driver, &req); + if (err) + goto err_cancel_msg; + genlmsg_end(msg, hdr); return 0; -- cgit v1.2.3 From bc66fa87d4fda9053a8145e5718fc278c2b88253 Mon Sep 17 00:00:00 2001 From: Xiaolei Wang Date: Wed, 30 Nov 2022 10:12:16 +0800 Subject: net: phy: Add link between phy dev and mac dev If the external phy used by current mac interface is managed by another mac interface, it means that this network port cannot work independently, especially when the system suspends and resumes, the following trace may appear, so we should create a device link between phy dev and mac dev. WARNING: CPU: 0 PID: 24 at drivers/net/phy/phy.c:983 phy_error+0x20/0x68 Modules linked in: CPU: 0 PID: 24 Comm: kworker/0:2 Not tainted 6.1.0-rc3-00011-g5aaef24b5c6d-dirty #34 Hardware name: Freescale i.MX6 SoloX (Device Tree) Workqueue: events_power_efficient phy_state_machine unwind_backtrace from show_stack+0x10/0x14 show_stack from dump_stack_lvl+0x68/0x90 dump_stack_lvl from __warn+0xb4/0x24c __warn from warn_slowpath_fmt+0x5c/0xd8 warn_slowpath_fmt from phy_error+0x20/0x68 phy_error from phy_state_machine+0x22c/0x23c phy_state_machine from process_one_work+0x288/0x744 process_one_work from worker_thread+0x3c/0x500 worker_thread from kthread+0xf0/0x114 kthread from ret_from_fork+0x14/0x28 Exception stack(0xf0951fb0 to 0xf0951ff8) Signed-off-by: Xiaolei Wang Tested-by: Florian Fainelli Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20221130021216.1052230-1-xiaolei.wang@windriver.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/phy_device.c | 12 ++++++++++++ include/linux/phy.h | 4 ++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8cff61dbc4b5..716870a4499c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1512,6 +1512,15 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, phy_resume(phydev); phy_led_triggers_register(phydev); + /** + * If the external phy used by current mac interface is managed by + * another mac interface, so we should create a device link between + * phy dev and mac dev. + */ + if (phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) + phydev->devlink = device_link_add(dev->dev.parent, &phydev->mdio.dev, + DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS); + return err; error: @@ -1750,6 +1759,9 @@ void phy_detach(struct phy_device *phydev) struct module *ndev_owner = NULL; struct mii_bus *bus; + if (phydev->devlink) + device_link_del(phydev->devlink); + if (phydev->sysfs_links) { if (dev) sysfs_remove_link(&dev->dev.kobj, "phydev"); diff --git a/include/linux/phy.h b/include/linux/phy.h index 9a3752c0c444..71eeb4e3b1fd 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -529,6 +529,8 @@ struct macsec_ops; * * @mdio: MDIO bus this PHY is on * @drv: Pointer to the driver for this PHY instance + * @devlink: Create a link between phy dev and mac dev, if the external phy + * used by current mac interface is managed by another mac interface. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -618,6 +620,8 @@ struct phy_device { /* And management functions */ struct phy_driver *drv; + struct device_link *devlink; + u32 phy_id; struct phy_c45_device_ids c45_ids; -- cgit v1.2.3 From 278ab9793116a8531ffaa52b4e61644971131e35 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 30 Nov 2022 13:26:45 -0800 Subject: wifi: ieee80211: Do not open-code qos address offsets When building with -Wstringop-overflow, GCC's KASAN implementation does not correctly perform bounds checking within some complex structures when faced with literal offsets, and can get very confused. For example, this warning is seen due to literal offsets into sturct ieee80211_hdr that may or may not be large enough: drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c: In function 'iwl_mvm_rx_mpdu_mq': drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c:2022:29: warning: writing 1 byte into a region of size 0 [-Wstringop-overflow=] 2022 | *qc &= ~IEEE80211_QOS_CTL_A_MSDU_PRESENT; In file included from drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h:32, from drivers/net/wireless/intel/iwlwifi/mvm/sta.h:15, from drivers/net/wireless/intel/iwlwifi/mvm/mvm.h:27, from drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c:10: drivers/net/wireless/intel/iwlwifi/mvm/../fw/api/rx.h:559:16: note: at offset [78, 166] into destination object 'mpdu_len' of size 2 559 | __le16 mpdu_len; | ^~~~~~~~ Refactor ieee80211_get_qos_ctl() to avoid using literal offsets, requiring the creation of the actual structure that is described in the comments. Explicitly choose the desired offset, making the code more human-readable too. This is one of the last remaining warning to fix before enabling -Wstringop-overflow globally. Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97490 Link: https://github.com/KSPP/linux/issues/181 Cc: Johannes Berg Cc: Kalle Valo Cc: Gregory Greenman Cc: "Gustavo A. R. Silva" Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221130212641.never.627-kees@kernel.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 6252f02f38b7..80d6308dea06 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -338,6 +338,17 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_qos_hdr_4addr { + __le16 frame_control; + __le16 duration_id; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; + __le16 seq_ctrl; + u8 addr4[ETH_ALEN]; + __le16 qos_ctrl; +} __packed __aligned(2); + struct ieee80211_trigger { __le16 frame_control; __le16 duration; @@ -4060,16 +4071,21 @@ struct ieee80211_he_6ghz_capa { * @hdr: the frame * * The qos ctrl bytes come after the frame_control, duration, seq_num - * and 3 or 4 addresses of length ETH_ALEN. - * 3 addr: 2 + 2 + 2 + 3*6 = 24 - * 4 addr: 2 + 2 + 2 + 4*6 = 30 + * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose + * between struct ieee80211_qos_hdr_4addr and struct ieee80211_qos_hdr. */ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) { - if (ieee80211_has_a4(hdr->frame_control)) - return (u8 *)hdr + 30; + union { + struct ieee80211_qos_hdr addr3; + struct ieee80211_qos_hdr_4addr addr4; + } *qos; + + qos = (void *)hdr; + if (ieee80211_has_a4(qos->addr3.frame_control)) + return (u8 *)&qos->addr4.qos_ctrl; else - return (u8 *)hdr + 24; + return (u8 *)&qos->addr3.qos_ctrl; } /** -- cgit v1.2.3 From 4d371d6e3746d84056f150fdaa66c85f65f60124 Mon Sep 17 00:00:00 2001 From: Philipp Hortmann Date: Mon, 14 Nov 2022 21:01:35 +0100 Subject: wifi: cfg80211: Correct example of ieee80211_iface_limit Correct wrong closing bracket. Signed-off-by: Philipp Hortmann Link: https://lore.kernel.org/r/20221114200135.GA100176@matrix-ESPRIMO-P710 Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 11a370e64143..03d4f4deadae 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4742,7 +4742,7 @@ struct ieee80211_iface_limit { * * struct ieee80211_iface_limit limits1[] = { * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, - * { .max = 1, .types = BIT(NL80211_IFTYPE_AP}, }, + * { .max = 1, .types = BIT(NL80211_IFTYPE_AP), }, * }; * struct ieee80211_iface_combination combination1 = { * .limits = limits1, -- cgit v1.2.3 From 75bfdbf2fca372e2709bcaa43e8cf1147766ae96 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 3 Nov 2022 22:27:52 +0000 Subject: rxrpc: Implement an in-kernel rxperf server for testing purposes Implement an in-kernel rxperf server to allow kernel-based rxrpc services to be tested directly, unlike with AFS where they're accessed by the fileserver when the latter decides it wants to. This is implemented as a module that, if loaded, opens UDP port 7009 (afs3-rmtsys) and listens on it for incoming calls. Calls can be generated using the rxperf command shipped with OpenAFS, for example. Changes ======= ver #2) - Use min_t() instead of min(). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: Jakub Kicinski --- include/net/af_rxrpc.h | 1 + net/rxrpc/Kconfig | 7 + net/rxrpc/Makefile | 3 + net/rxrpc/rxperf.c | 619 +++++++++++++++++++++++++++++++++++++++++++++++++ net/rxrpc/server_key.c | 25 ++ 5 files changed, 655 insertions(+) create mode 100644 net/rxrpc/rxperf.c (limited to 'include') diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index b69ca695935c..dc033f08191e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -71,5 +71,6 @@ void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *, unsigned long); int rxrpc_sock_set_min_security_level(struct sock *sk, unsigned int val); +int rxrpc_sock_set_security_keyring(struct sock *, struct key *); #endif /* _NET_RXRPC_H */ diff --git a/net/rxrpc/Kconfig b/net/rxrpc/Kconfig index accd35c05577..7ae023b37a83 100644 --- a/net/rxrpc/Kconfig +++ b/net/rxrpc/Kconfig @@ -58,4 +58,11 @@ config RXKAD See Documentation/networking/rxrpc.rst. +config RXPERF + tristate "RxRPC test service" + help + Provide an rxperf service tester. This listens on UDP port 7009 for + incoming calls from the rxperf program (an example of which can be + found in OpenAFS). + endif diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index fdeba488fc6e..79687477d93c 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -36,3 +36,6 @@ rxrpc-y := \ rxrpc-$(CONFIG_PROC_FS) += proc.o rxrpc-$(CONFIG_RXKAD) += rxkad.o rxrpc-$(CONFIG_SYSCTL) += sysctl.o + + +obj-$(CONFIG_RXPERF) += rxperf.o diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c new file mode 100644 index 000000000000..66f5eea291ff --- /dev/null +++ b/net/rxrpc/rxperf.c @@ -0,0 +1,619 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* In-kernel rxperf server for testing purposes. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) "rxperf: " fmt +#include +#include +#include +#include + +MODULE_DESCRIPTION("rxperf test server (afs)"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +#define RXPERF_PORT 7009 +#define RX_PERF_SERVICE 147 +#define RX_PERF_VERSION 3 +#define RX_PERF_SEND 0 +#define RX_PERF_RECV 1 +#define RX_PERF_RPC 3 +#define RX_PERF_FILE 4 +#define RX_PERF_MAGIC_COOKIE 0x4711 + +struct rxperf_proto_params { + __be32 version; + __be32 type; + __be32 rsize; + __be32 wsize; +} __packed; + +static const u8 rxperf_magic_cookie[] = { 0x00, 0x00, 0x47, 0x11 }; +static const u8 secret[8] = { 0xa7, 0x83, 0x8a, 0xcb, 0xc7, 0x83, 0xec, 0x94 }; + +enum rxperf_call_state { + RXPERF_CALL_SV_AWAIT_PARAMS, /* Server: Awaiting parameter block */ + RXPERF_CALL_SV_AWAIT_REQUEST, /* Server: Awaiting request data */ + RXPERF_CALL_SV_REPLYING, /* Server: Replying */ + RXPERF_CALL_SV_AWAIT_ACK, /* Server: Awaiting final ACK */ + RXPERF_CALL_COMPLETE, /* Completed or failed */ +}; + +struct rxperf_call { + struct rxrpc_call *rxcall; + struct iov_iter iter; + struct kvec kvec[1]; + struct work_struct work; + const char *type; + size_t iov_len; + size_t req_len; /* Size of request blob */ + size_t reply_len; /* Size of reply blob */ + unsigned int debug_id; + unsigned int operation_id; + struct rxperf_proto_params params; + __be32 tmp[2]; + s32 abort_code; + enum rxperf_call_state state; + short error; + unsigned short unmarshal; + u16 service_id; + int (*deliver)(struct rxperf_call *call); + void (*processor)(struct work_struct *work); +}; + +static struct socket *rxperf_socket; +static struct key *rxperf_sec_keyring; /* Ring of security/crypto keys */ +static struct workqueue_struct *rxperf_workqueue; + +static void rxperf_deliver_to_call(struct work_struct *work); +static int rxperf_deliver_param_block(struct rxperf_call *call); +static int rxperf_deliver_request(struct rxperf_call *call); +static int rxperf_process_call(struct rxperf_call *call); +static void rxperf_charge_preallocation(struct work_struct *work); + +static DECLARE_WORK(rxperf_charge_preallocation_work, + rxperf_charge_preallocation); + +static inline void rxperf_set_call_state(struct rxperf_call *call, + enum rxperf_call_state to) +{ + call->state = to; +} + +static inline void rxperf_set_call_complete(struct rxperf_call *call, + int error, s32 remote_abort) +{ + if (call->state != RXPERF_CALL_COMPLETE) { + call->abort_code = remote_abort; + call->error = error; + call->state = RXPERF_CALL_COMPLETE; + } +} + +static void rxperf_rx_discard_new_call(struct rxrpc_call *rxcall, + unsigned long user_call_ID) +{ + kfree((struct rxperf_call *)user_call_ID); +} + +static void rxperf_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long user_call_ID) +{ + queue_work(rxperf_workqueue, &rxperf_charge_preallocation_work); +} + +static void rxperf_queue_call_work(struct rxperf_call *call) +{ + queue_work(rxperf_workqueue, &call->work); +} + +static void rxperf_notify_rx(struct sock *sk, struct rxrpc_call *rxcall, + unsigned long call_user_ID) +{ + struct rxperf_call *call = (struct rxperf_call *)call_user_ID; + + if (call->state != RXPERF_CALL_COMPLETE) + rxperf_queue_call_work(call); +} + +static void rxperf_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID) +{ + struct rxperf_call *call = (struct rxperf_call *)user_call_ID; + + call->rxcall = rxcall; +} + +static void rxperf_notify_end_reply_tx(struct sock *sock, + struct rxrpc_call *rxcall, + unsigned long call_user_ID) +{ + rxperf_set_call_state((struct rxperf_call *)call_user_ID, + RXPERF_CALL_SV_AWAIT_ACK); +} + +/* + * Charge the incoming call preallocation. + */ +static void rxperf_charge_preallocation(struct work_struct *work) +{ + struct rxperf_call *call; + + for (;;) { + call = kzalloc(sizeof(*call), GFP_KERNEL); + if (!call) + break; + + call->type = "unset"; + call->debug_id = atomic_inc_return(&rxrpc_debug_id); + call->deliver = rxperf_deliver_param_block; + call->state = RXPERF_CALL_SV_AWAIT_PARAMS; + call->service_id = RX_PERF_SERVICE; + call->iov_len = sizeof(call->params); + call->kvec[0].iov_len = sizeof(call->params); + call->kvec[0].iov_base = &call->params; + iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len); + INIT_WORK(&call->work, rxperf_deliver_to_call); + + if (rxrpc_kernel_charge_accept(rxperf_socket, + rxperf_notify_rx, + rxperf_rx_attach, + (unsigned long)call, + GFP_KERNEL, + call->debug_id) < 0) + break; + call = NULL; + } + + kfree(call); +} + +/* + * Open an rxrpc socket and bind it to be a server for callback notifications + * - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT + */ +static int rxperf_open_socket(void) +{ + struct sockaddr_rxrpc srx; + struct socket *socket; + int ret; + + ret = sock_create_kern(&init_net, AF_RXRPC, SOCK_DGRAM, PF_INET6, + &socket); + if (ret < 0) + goto error_1; + + socket->sk->sk_allocation = GFP_NOFS; + + /* bind the callback manager's address to make this a server socket */ + memset(&srx, 0, sizeof(srx)); + srx.srx_family = AF_RXRPC; + srx.srx_service = RX_PERF_SERVICE; + srx.transport_type = SOCK_DGRAM; + srx.transport_len = sizeof(srx.transport.sin6); + srx.transport.sin6.sin6_family = AF_INET6; + srx.transport.sin6.sin6_port = htons(RXPERF_PORT); + + ret = rxrpc_sock_set_min_security_level(socket->sk, + RXRPC_SECURITY_ENCRYPT); + if (ret < 0) + goto error_2; + + ret = rxrpc_sock_set_security_keyring(socket->sk, rxperf_sec_keyring); + + ret = kernel_bind(socket, (struct sockaddr *)&srx, sizeof(srx)); + if (ret < 0) + goto error_2; + + rxrpc_kernel_new_call_notification(socket, rxperf_rx_new_call, + rxperf_rx_discard_new_call); + + ret = kernel_listen(socket, INT_MAX); + if (ret < 0) + goto error_2; + + rxperf_socket = socket; + rxperf_charge_preallocation(&rxperf_charge_preallocation_work); + return 0; + +error_2: + sock_release(socket); +error_1: + pr_err("Can't set up rxperf socket: %d\n", ret); + return ret; +} + +/* + * close the rxrpc socket rxperf was using + */ +static void rxperf_close_socket(void) +{ + kernel_listen(rxperf_socket, 0); + kernel_sock_shutdown(rxperf_socket, SHUT_RDWR); + flush_workqueue(rxperf_workqueue); + sock_release(rxperf_socket); +} + +/* + * Log remote abort codes that indicate that we have a protocol disagreement + * with the server. + */ +static void rxperf_log_error(struct rxperf_call *call, s32 remote_abort) +{ + static int max = 0; + const char *msg; + int m; + + switch (remote_abort) { + case RX_EOF: msg = "unexpected EOF"; break; + case RXGEN_CC_MARSHAL: msg = "client marshalling"; break; + case RXGEN_CC_UNMARSHAL: msg = "client unmarshalling"; break; + case RXGEN_SS_MARSHAL: msg = "server marshalling"; break; + case RXGEN_SS_UNMARSHAL: msg = "server unmarshalling"; break; + case RXGEN_DECODE: msg = "opcode decode"; break; + case RXGEN_SS_XDRFREE: msg = "server XDR cleanup"; break; + case RXGEN_CC_XDRFREE: msg = "client XDR cleanup"; break; + case -32: msg = "insufficient data"; break; + default: + return; + } + + m = max; + if (m < 3) { + max = m + 1; + pr_info("Peer reported %s failure on %s\n", msg, call->type); + } +} + +/* + * deliver messages to a call + */ +static void rxperf_deliver_to_call(struct work_struct *work) +{ + struct rxperf_call *call = container_of(work, struct rxperf_call, work); + enum rxperf_call_state state; + u32 abort_code, remote_abort = 0; + int ret; + + if (call->state == RXPERF_CALL_COMPLETE) + return; + + while (state = call->state, + state == RXPERF_CALL_SV_AWAIT_PARAMS || + state == RXPERF_CALL_SV_AWAIT_REQUEST || + state == RXPERF_CALL_SV_AWAIT_ACK + ) { + if (state == RXPERF_CALL_SV_AWAIT_ACK) { + if (!rxrpc_kernel_check_life(rxperf_socket, call->rxcall)) + goto call_complete; + return; + } + + ret = call->deliver(call); + if (ret == 0) + ret = rxperf_process_call(call); + + switch (ret) { + case 0: + continue; + case -EINPROGRESS: + case -EAGAIN: + return; + case -ECONNABORTED: + rxperf_log_error(call, call->abort_code); + goto call_complete; + case -EOPNOTSUPP: + abort_code = RXGEN_OPCODE; + rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, + abort_code, ret, "GOP"); + goto call_complete; + case -ENOTSUPP: + abort_code = RX_USER_ABORT; + rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, + abort_code, ret, "GUA"); + goto call_complete; + case -EIO: + pr_err("Call %u in bad state %u\n", + call->debug_id, call->state); + fallthrough; + case -ENODATA: + case -EBADMSG: + case -EMSGSIZE: + case -ENOMEM: + case -EFAULT: + rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, + RXGEN_SS_UNMARSHAL, ret, "GUM"); + goto call_complete; + default: + rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, + RX_CALL_DEAD, ret, "GER"); + goto call_complete; + } + } + +call_complete: + rxperf_set_call_complete(call, ret, remote_abort); + /* The call may have been requeued */ + rxrpc_kernel_end_call(rxperf_socket, call->rxcall); + cancel_work(&call->work); + kfree(call); +} + +/* + * Extract a piece of data from the received data socket buffers. + */ +static int rxperf_extract_data(struct rxperf_call *call, bool want_more) +{ + u32 remote_abort = 0; + int ret; + + ret = rxrpc_kernel_recv_data(rxperf_socket, call->rxcall, &call->iter, + &call->iov_len, want_more, &remote_abort, + &call->service_id); + pr_debug("Extract i=%zu l=%zu m=%u ret=%d\n", + iov_iter_count(&call->iter), call->iov_len, want_more, ret); + if (ret == 0 || ret == -EAGAIN) + return ret; + + if (ret == 1) { + switch (call->state) { + case RXPERF_CALL_SV_AWAIT_REQUEST: + rxperf_set_call_state(call, RXPERF_CALL_SV_REPLYING); + break; + case RXPERF_CALL_COMPLETE: + pr_debug("premature completion %d", call->error); + return call->error; + default: + break; + } + return 0; + } + + rxperf_set_call_complete(call, ret, remote_abort); + return ret; +} + +/* + * Grab the operation ID from an incoming manager call. + */ +static int rxperf_deliver_param_block(struct rxperf_call *call) +{ + u32 version; + int ret; + + /* Extract the parameter block */ + ret = rxperf_extract_data(call, true); + if (ret < 0) + return ret; + + version = ntohl(call->params.version); + call->operation_id = ntohl(call->params.type); + call->deliver = rxperf_deliver_request; + + if (version != RX_PERF_VERSION) { + pr_info("Version mismatch %x\n", version); + return -ENOTSUPP; + } + + switch (call->operation_id) { + case RX_PERF_SEND: + call->type = "send"; + call->reply_len = 0; + call->iov_len = 4; /* Expect req size */ + break; + case RX_PERF_RECV: + call->type = "recv"; + call->req_len = 0; + call->iov_len = 4; /* Expect reply size */ + break; + case RX_PERF_RPC: + call->type = "rpc"; + call->iov_len = 8; /* Expect req size and reply size */ + break; + case RX_PERF_FILE: + call->type = "file"; + fallthrough; + default: + return -EOPNOTSUPP; + } + + rxperf_set_call_state(call, RXPERF_CALL_SV_AWAIT_REQUEST); + return call->deliver(call); +} + +/* + * Deliver the request data. + */ +static int rxperf_deliver_request(struct rxperf_call *call) +{ + int ret; + + switch (call->unmarshal) { + case 0: + call->kvec[0].iov_len = call->iov_len; + call->kvec[0].iov_base = call->tmp; + iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len); + call->unmarshal++; + fallthrough; + case 1: + ret = rxperf_extract_data(call, true); + if (ret < 0) + return ret; + + switch (call->operation_id) { + case RX_PERF_SEND: + call->type = "send"; + call->req_len = ntohl(call->tmp[0]); + call->reply_len = 0; + break; + case RX_PERF_RECV: + call->type = "recv"; + call->req_len = 0; + call->reply_len = ntohl(call->tmp[0]); + break; + case RX_PERF_RPC: + call->type = "rpc"; + call->req_len = ntohl(call->tmp[0]); + call->reply_len = ntohl(call->tmp[1]); + break; + default: + pr_info("Can't parse extra params\n"); + return -EIO; + } + + pr_debug("CALL op=%s rq=%zx rp=%zx\n", + call->type, call->req_len, call->reply_len); + + call->iov_len = call->req_len; + iov_iter_discard(&call->iter, READ, call->req_len); + call->unmarshal++; + fallthrough; + case 2: + ret = rxperf_extract_data(call, false); + if (ret < 0) + return ret; + call->unmarshal++; + fallthrough; + default: + return 0; + } +} + +/* + * Process a call for which we've received the request. + */ +static int rxperf_process_call(struct rxperf_call *call) +{ + struct msghdr msg = {}; + struct bio_vec bv[1]; + struct kvec iov[1]; + ssize_t n; + size_t reply_len = call->reply_len, len; + + rxrpc_kernel_set_tx_length(rxperf_socket, call->rxcall, + reply_len + sizeof(rxperf_magic_cookie)); + + while (reply_len > 0) { + len = min_t(size_t, reply_len, PAGE_SIZE); + bv[0].bv_page = ZERO_PAGE(0); + bv[0].bv_offset = 0; + bv[0].bv_len = len; + iov_iter_bvec(&msg.msg_iter, WRITE, bv, 1, len); + msg.msg_flags = MSG_MORE; + n = rxrpc_kernel_send_data(rxperf_socket, call->rxcall, &msg, + len, rxperf_notify_end_reply_tx); + if (n < 0) + return n; + if (n == 0) + return -EIO; + reply_len -= n; + } + + len = sizeof(rxperf_magic_cookie); + iov[0].iov_base = (void *)rxperf_magic_cookie; + iov[0].iov_len = len; + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); + msg.msg_flags = 0; + n = rxrpc_kernel_send_data(rxperf_socket, call->rxcall, &msg, len, + rxperf_notify_end_reply_tx); + if (n >= 0) + return 0; /* Success */ + + if (n == -ENOMEM) + rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, + RXGEN_SS_MARSHAL, -ENOMEM, "GOM"); + return n; +} + +/* + * Add a key to the security keyring. + */ +static int rxperf_add_key(struct key *keyring) +{ + key_ref_t kref; + int ret; + + kref = key_create_or_update(make_key_ref(keyring, true), + "rxrpc_s", + __stringify(RX_PERF_SERVICE) ":2", + secret, + sizeof(secret), + KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH + | KEY_USR_VIEW, + KEY_ALLOC_NOT_IN_QUOTA); + + if (IS_ERR(kref)) { + pr_err("Can't allocate rxperf server key: %ld\n", PTR_ERR(kref)); + return PTR_ERR(kref); + } + + ret = key_link(keyring, key_ref_to_ptr(kref)); + if (ret < 0) + pr_err("Can't link rxperf server key: %d\n", ret); + key_ref_put(kref); + return ret; +} + +/* + * Initialise the rxperf server. + */ +static int __init rxperf_init(void) +{ + struct key *keyring; + int ret = -ENOMEM; + + pr_info("Server registering\n"); + + rxperf_workqueue = alloc_workqueue("rxperf", 0, 0); + if (!rxperf_workqueue) + goto error_workqueue; + + keyring = keyring_alloc("rxperf_server", + GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), + KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | + KEY_POS_WRITE | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH | + KEY_USR_WRITE | + KEY_OTH_VIEW | KEY_OTH_READ | KEY_OTH_SEARCH, + KEY_ALLOC_NOT_IN_QUOTA, + NULL, NULL); + if (IS_ERR(keyring)) { + pr_err("Can't allocate rxperf server keyring: %ld\n", + PTR_ERR(keyring)); + goto error_keyring; + } + rxperf_sec_keyring = keyring; + ret = rxperf_add_key(keyring); + if (ret < 0) + goto error_key; + + ret = rxperf_open_socket(); + if (ret < 0) + goto error_socket; + return 0; + +error_socket: +error_key: + key_put(rxperf_sec_keyring); +error_keyring: + destroy_workqueue(rxperf_workqueue); + rcu_barrier(); +error_workqueue: + pr_err("Failed to register: %d\n", ret); + return ret; +} +late_initcall(rxperf_init); /* Must be called after net/ to create socket */ + +static void __exit rxperf_exit(void) +{ + pr_info("Server unregistering.\n"); + + rxperf_close_socket(); + key_put(rxperf_sec_keyring); + destroy_workqueue(rxperf_workqueue); + rcu_barrier(); +} +module_exit(rxperf_exit); + diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c index ee269e0e6ee8..e51940589ee5 100644 --- a/net/rxrpc/server_key.c +++ b/net/rxrpc/server_key.c @@ -144,3 +144,28 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) _leave(" = 0 [key %x]", key->serial); return 0; } + +/** + * rxrpc_sock_set_security_keyring - Set the security keyring for a kernel service + * @sk: The socket to set the keyring on + * @keyring: The keyring to set + * + * Set the server security keyring on an rxrpc socket. This is used to provide + * the encryption keys for a kernel service. + */ +int rxrpc_sock_set_security_keyring(struct sock *sk, struct key *keyring) +{ + struct rxrpc_sock *rx = rxrpc_sk(sk); + int ret = 0; + + lock_sock(sk); + if (rx->securities) + ret = -EINVAL; + else if (rx->sk.sk_state != RXRPC_UNBOUND) + ret = -EISCONN; + else + rx->securities = key_get(keyring); + release_sock(sk); + return ret; +} +EXPORT_SYMBOL(rxrpc_sock_set_security_keyring); -- cgit v1.2.3 From 2ed83ed2be1b2395f11a95f0fec2b87ed71aebd8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 17 Nov 2022 10:04:15 +0000 Subject: rxrpc: Remove decl for rxrpc_kernel_call_is_complete() rxrpc_kernel_call_is_complete() has been removed, so remove its declaration too. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/net/af_rxrpc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index dc033f08191e..d5a5ae926380 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -66,7 +66,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); -bool rxrpc_kernel_call_is_complete(struct rxrpc_call *); void rxrpc_kernel_set_max_life(struct socket *, struct rxrpc_call *, unsigned long); -- cgit v1.2.3 From 2ebdb26e6abd2a773ab5f009ac38a6de973a2bcf Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 11:51:06 +0100 Subject: rxrpc: Remove the [k_]proto() debugging macros Remove the kproto() and _proto() debugging macros in preference to using tracepoints for this. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 60 ++++++++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 10 -------- net/rxrpc/conn_event.c | 4 --- net/rxrpc/input.c | 17 ------------- net/rxrpc/local_event.c | 3 --- net/rxrpc/output.c | 2 -- net/rxrpc/peer_event.c | 4 --- net/rxrpc/rxkad.c | 9 +++---- 8 files changed, 63 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b9886d1df825..2b77f9a75bf7 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -733,6 +733,66 @@ TRACE_EVENT(rxrpc_rx_abort, __entry->abort_code) ); +TRACE_EVENT(rxrpc_rx_challenge, + TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial, + u32 version, u32 nonce, u32 min_level), + + TP_ARGS(conn, serial, version, nonce, min_level), + + TP_STRUCT__entry( + __field(unsigned int, conn ) + __field(rxrpc_serial_t, serial ) + __field(u32, version ) + __field(u32, nonce ) + __field(u32, min_level ) + ), + + TP_fast_assign( + __entry->conn = conn->debug_id; + __entry->serial = serial; + __entry->version = version; + __entry->nonce = nonce; + __entry->min_level = min_level; + ), + + TP_printk("C=%08x CHALLENGE %08x v=%x n=%x ml=%x", + __entry->conn, + __entry->serial, + __entry->version, + __entry->nonce, + __entry->min_level) + ); + +TRACE_EVENT(rxrpc_rx_response, + TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial, + u32 version, u32 kvno, u32 ticket_len), + + TP_ARGS(conn, serial, version, kvno, ticket_len), + + TP_STRUCT__entry( + __field(unsigned int, conn ) + __field(rxrpc_serial_t, serial ) + __field(u32, version ) + __field(u32, kvno ) + __field(u32, ticket_len ) + ), + + TP_fast_assign( + __entry->conn = conn->debug_id; + __entry->serial = serial; + __entry->version = version; + __entry->kvno = kvno; + __entry->ticket_len = ticket_len; + ), + + TP_printk("C=%08x RESPONSE %08x v=%x kvno=%x tl=%x", + __entry->conn, + __entry->serial, + __entry->version, + __entry->kvno, + __entry->ticket_len) + ); + TRACE_EVENT(rxrpc_rx_rwind_change, TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, u32 rwind, bool wake), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index f5c538ce3e23..a3a29390e12b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1190,7 +1190,6 @@ extern unsigned int rxrpc_debug; #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) -#define kproto(FMT,...) dbgprintk("### "FMT ,##__VA_ARGS__) #define knet(FMT,...) dbgprintk("@@@ "FMT ,##__VA_ARGS__) @@ -1198,14 +1197,12 @@ extern unsigned int rxrpc_debug; #define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) #define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) #define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) -#define _proto(FMT,...) kproto(FMT,##__VA_ARGS__) #define _net(FMT,...) knet(FMT,##__VA_ARGS__) #elif defined(CONFIG_AF_RXRPC_DEBUG) #define RXRPC_DEBUG_KENTER 0x01 #define RXRPC_DEBUG_KLEAVE 0x02 #define RXRPC_DEBUG_KDEBUG 0x04 -#define RXRPC_DEBUG_KPROTO 0x08 #define RXRPC_DEBUG_KNET 0x10 #define _enter(FMT,...) \ @@ -1226,12 +1223,6 @@ do { \ kdebug(FMT,##__VA_ARGS__); \ } while (0) -#define _proto(FMT,...) \ -do { \ - if (unlikely(rxrpc_debug & RXRPC_DEBUG_KPROTO)) \ - kproto(FMT,##__VA_ARGS__); \ -} while (0) - #define _net(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KNET)) \ @@ -1242,7 +1233,6 @@ do { \ #define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__) -#define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__) #define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__) #endif diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aab069701398..d5549cbfc71b 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -122,14 +122,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code); break; case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), pkt.ack.reason, 0); - _proto("Tx ACK %%%u [re]", serial); break; } @@ -242,7 +240,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); whdr.serial = htonl(serial); - _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -315,7 +312,6 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return -EPROTO; } abort_code = ntohl(wtmp); - _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); conn->error = -ECONNABORTED; conn->abort_code = abort_code; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index bdf70b81addc..646ee61af40e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -551,9 +551,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) atomic64_read(&call->ackr_window), call->rx_highest_seq, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x }", - sp->hdr.serial, seq0, sp->hdr.flags); - state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { rxrpc_free_skb(skb, rxrpc_skb_freed); @@ -708,11 +705,6 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, bool wake = false; u32 rwind = ntohl(ackinfo->rwind); - _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", - sp->hdr.serial, - ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), - rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { @@ -855,7 +847,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { @@ -1014,9 +1005,6 @@ out_not_locked: static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - _proto("Rx ACKALL %%%u", sp->hdr.serial); spin_lock(&call->input_lock); @@ -1044,8 +1032,6 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_abort(call, sp->hdr.serial, abort_code); - _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); - rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, abort_code, -ECONNABORTED); } @@ -1081,8 +1067,6 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, goto no_free; case RXRPC_PACKET_TYPE_BUSY: - _proto("Rx BUSY %%%u", sp->hdr.serial); - /* Just ignore BUSY packets from the server; the retry and * lifespan timers will take care of business. BUSY packets * from the client don't make sense. @@ -1325,7 +1309,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto discard; default: - _proto("Rx Bad Packet Type %u", sp->hdr.type); goto bad_message; } diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 19e929c7c38b..f23a3fbabbda 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -63,8 +63,6 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, len = iov[0].iov_len + iov[1].iov_len; - _proto("Tx VERSION (reply)"); - ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, @@ -98,7 +96,6 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &v, 1) < 0) return; - _proto("Rx VERSION { %02x }", v); if (v == 0) rxrpc_send_version_request(local, &sp->hdr, skb); break; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index c5eed0e83e47..635acf3dbd77 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -701,8 +701,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) len = iov[0].iov_len + iov[1].iov_len; - _proto("Tx VERSION (keepalive)"); - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); ret = do_udp_sendmsg(peer->local->socket, &msg, len); if (ret < 0) diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index cda3890657a9..be781c156e89 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -253,15 +253,12 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; default: - _proto("Rx Received ICMP error { type=%u code=%u }", - ee->ee_type, ee->ee_code); break; } break; case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: - _proto("Rx Received local error { error=%d }", err); compl = RXRPC_CALL_LOCAL_ERROR; break; @@ -270,7 +267,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, err = EHOSTUNREACH; fallthrough; default: - _proto("Rx Received error report { orig=%u }", ee->ee_origin); break; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 110a5550c0a6..36cf40442a7e 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -704,7 +704,6 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx CHALLENGE %%%u", serial); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -762,7 +761,6 @@ static int rxkad_send_response(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx RESPONSE %%%u", serial); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { @@ -856,8 +854,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, nonce = ntohl(challenge.nonce); min_level = ntohl(challenge.min_level); - _proto("Rx CHALLENGE %%%u { v=%u n=%u ml=%u }", - sp->hdr.serial, version, nonce, min_level); + trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level); eproto = tracepoint_string("chall_ver"); abort_code = RXKADINCONSISTENCY; @@ -1139,8 +1136,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, version = ntohl(response->version); ticket_len = ntohl(response->ticket_len); kvno = ntohl(response->kvno); - _proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }", - sp->hdr.serial, version, kvno, ticket_len); + + trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len); eproto = tracepoint_string("rxkad_rsp_ver"); abort_code = RXKADINCONSISTENCY; -- cgit v1.2.3 From 0fde882fc9ee9cc2e66e8c5a5a93c83932d7ca95 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 13:00:34 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_local tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_local tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 49 ++++++++++++++++++++-------- net/rxrpc/af_rxrpc.c | 8 ++--- net/rxrpc/ar-internal.h | 41 ++++++++++++++++++----- net/rxrpc/call_accept.c | 4 +-- net/rxrpc/call_event.c | 2 +- net/rxrpc/conn_client.c | 2 +- net/rxrpc/conn_event.c | 4 +-- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 4 +-- net/rxrpc/local_object.c | 78 ++++++++++++++++++++++++-------------------- net/rxrpc/output.c | 3 +- net/rxrpc/peer_event.c | 4 +-- net/rxrpc/peer_object.c | 4 +-- 13 files changed, 129 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 2b77f9a75bf7..015569845b1d 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -32,12 +32,35 @@ E_(rxrpc_skb_unshared_nomem, "US0") #define rxrpc_local_traces \ - EM(rxrpc_local_got, "GOT") \ - EM(rxrpc_local_new, "NEW") \ - EM(rxrpc_local_processing, "PRO") \ - EM(rxrpc_local_put, "PUT") \ - EM(rxrpc_local_queued, "QUE") \ - E_(rxrpc_local_tx_ack, "TAK") + EM(rxrpc_local_free, "FREE ") \ + EM(rxrpc_local_get_client_conn, "GET conn-cln") \ + EM(rxrpc_local_get_for_use, "GET for-use ") \ + EM(rxrpc_local_get_peer, "GET peer ") \ + EM(rxrpc_local_get_prealloc_conn, "GET conn-pre") \ + EM(rxrpc_local_get_queue, "GET queue ") \ + EM(rxrpc_local_new, "NEW ") \ + EM(rxrpc_local_processing, "PROCESSING ") \ + EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_local_put_bind, "PUT bind ") \ + EM(rxrpc_local_put_for_use, "PUT for-use ") \ + EM(rxrpc_local_put_kill_conn, "PUT conn-kil") \ + EM(rxrpc_local_put_peer, "PUT peer ") \ + EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ + EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ + EM(rxrpc_local_put_queue, "PUT queue ") \ + EM(rxrpc_local_queued, "QUEUED ") \ + EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ + EM(rxrpc_local_stop, "STOP ") \ + EM(rxrpc_local_stopped, "STOPPED ") \ + EM(rxrpc_local_unuse_bind, "UNU bind ") \ + EM(rxrpc_local_unuse_conn_work, "UNU conn-wrk") \ + EM(rxrpc_local_unuse_peer_keepalive, "UNU peer-kpa") \ + EM(rxrpc_local_unuse_release_sock, "UNU rel-sock") \ + EM(rxrpc_local_unuse_work, "UNU work ") \ + EM(rxrpc_local_use_conn_work, "USE conn-wrk") \ + EM(rxrpc_local_use_lookup, "USE lookup ") \ + EM(rxrpc_local_use_peer_keepalive, "USE peer-kpa") \ + E_(rxrpc_local_use_work, "USE work ") #define rxrpc_peer_traces \ EM(rxrpc_peer_got, "GOT") \ @@ -345,29 +368,29 @@ rxrpc_txqueue_traces; TRACE_EVENT(rxrpc_local, TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op, - int usage, const void *where), + int ref, int usage), - TP_ARGS(local_debug_id, op, usage, where), + TP_ARGS(local_debug_id, op, ref, usage), TP_STRUCT__entry( __field(unsigned int, local ) __field(int, op ) + __field(int, ref ) __field(int, usage ) - __field(const void *, where ) ), TP_fast_assign( __entry->local = local_debug_id; __entry->op = op; + __entry->ref = ref; __entry->usage = usage; - __entry->where = where; ), - TP_printk("L=%08x %s u=%d sp=%pSR", + TP_printk("L=%08x %s r=%d u=%d", __entry->local, __print_symbolic(__entry->op, rxrpc_local_traces), - __entry->usage, - __entry->where) + __entry->ref, + __entry->usage) ); TRACE_EVENT(rxrpc_peer, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index aacdd96a9886..989ebca899f3 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -194,8 +194,8 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use: write_unlock(&local->services_lock); - rxrpc_unuse_local(local); - rxrpc_put_local(local); + rxrpc_unuse_local(local, rxrpc_local_unuse_bind); + rxrpc_put_local(local, rxrpc_local_put_bind); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -888,8 +888,8 @@ static int rxrpc_release_sock(struct sock *sk) flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_unuse_local(rx->local); - rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local, rxrpc_local_unuse_release_sock); + rxrpc_put_local(rx->local, rxrpc_local_put_release_sock); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7c48b0163032..dde9ce21ef48 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -979,22 +979,45 @@ extern void rxrpc_process_local_events(struct rxrpc_local *); * local_object.c */ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); -struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); -struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); -void rxrpc_put_local(struct rxrpc_local *); -struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); -void rxrpc_unuse_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); +void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); +void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); -static inline bool __rxrpc_unuse_local(struct rxrpc_local *local) +static inline bool __rxrpc_unuse_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - return atomic_dec_return(&local->active_users) == 0; + unsigned int debug_id = local->debug_id; + int r, u; + + r = refcount_read(&local->ref); + u = atomic_dec_return(&local->active_users); + trace_rxrpc_local(debug_id, why, r, u); + return u == 0; +} + +static inline bool __rxrpc_use_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) +{ + int r, u; + + r = refcount_read(&local->ref); + u = atomic_fetch_add_unless(&local->active_users, 1, 0); + trace_rxrpc_local(local->debug_id, why, r, u); + return u != 0; } -static inline bool __rxrpc_use_local(struct rxrpc_local *local) +static inline void rxrpc_see_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0; + int r, u; + + r = refcount_read(&local->ref); + u = atomic_read(&local->active_users); + trace_rxrpc_local(local->debug_id, why, r, u); } /* diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 4888959e4727..1b12d4e28373 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -197,7 +197,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; - rxrpc_put_local(peer->local); + rxrpc_put_local(peer->local, rxrpc_local_put_prealloc_conn); kfree(peer); tail = (tail + 1) & (size - 1); } @@ -305,7 +305,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, b->conn_backlog[conn_tail] = NULL; smp_store_release(&b->conn_backlog_tail, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - conn->local = rxrpc_get_local(local); + conn->local = rxrpc_get_local(local, rxrpc_local_get_prealloc_conn); conn->peer = peer; rxrpc_see_connection(conn); rxrpc_new_incoming_connection(rx, conn, sec, skb); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b17ed37434bd..591af8e2e3d0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -114,7 +114,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (in_task()) { rxrpc_transmit_ack_packets(call->peer->local); } else { - rxrpc_get_local(local); + rxrpc_get_local(local, rxrpc_local_get_queue); rxrpc_queue_local(local); } } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 71404b33623f..9a69b4c1b182 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -208,7 +208,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) rxrpc_get_bundle(bundle); rxrpc_get_peer(conn->peer); - rxrpc_get_local(conn->local); + rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index f890a30c4df6..225edaf019f1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -474,9 +474,9 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_see_connection(conn); - if (__rxrpc_use_local(conn->local)) { + if (__rxrpc_use_local(conn->local, rxrpc_local_use_conn_work)) { rxrpc_do_process_connection(conn); - rxrpc_unuse_local(conn->local); + rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } rxrpc_put_connection(conn); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ad6e5ee1f069..725359afeac0 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -366,7 +366,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) wake_up_var(&conn->local->rxnet->nr_conns); - rxrpc_put_local(conn->local); + rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); kfree(conn); _leave(""); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 42c8257158f7..cecfd201d832 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1133,7 +1133,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb); - if (rxrpc_get_local_maybe(local)) { + if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); } else { @@ -1146,7 +1146,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, */ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { - if (rxrpc_get_local_maybe(local)) { + if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); } else { diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 11080c335d42..1617ce651b9b 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -110,7 +110,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; - trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1); } _leave(" = %p", local); @@ -228,7 +228,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, * we're attempting to use a local address that the dying * object is still using. */ - if (!rxrpc_use_local(local)) + if (!rxrpc_use_local(local, rxrpc_local_use_lookup)) break; goto found; @@ -272,32 +272,32 @@ addr_in_use: /* * Get a ref on a local endpoint. */ -struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); - int r; + int r, u; + u = atomic_read(&local->active_users); __refcount_inc(&local->ref, &r); - trace_rxrpc_local(local->debug_id, rxrpc_local_got, r + 1, here); + trace_rxrpc_local(local->debug_id, why, r + 1, u); return local; } /* * Get a ref on a local endpoint unless its usage has already reached 0. */ -struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); - int r; + int r, u; - if (local) { - if (__refcount_inc_not_zero(&local->ref, &r)) - trace_rxrpc_local(local->debug_id, rxrpc_local_got, - r + 1, here); - else - local = NULL; + if (local && __refcount_inc_not_zero(&local->ref, &r)) { + u = atomic_read(&local->active_users); + trace_rxrpc_local(local->debug_id, why, r + 1, u); + return local; } - return local; + + return NULL; } /* @@ -305,31 +305,31 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) */ void rxrpc_queue_local(struct rxrpc_local *local) { - const void *here = __builtin_return_address(0); unsigned int debug_id = local->debug_id; int r = refcount_read(&local->ref); + int u = atomic_read(&local->active_users); if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(debug_id, rxrpc_local_queued, r + 1, here); + trace_rxrpc_local(debug_id, rxrpc_local_queued, r, u); else - rxrpc_put_local(local); + rxrpc_put_local(local, rxrpc_local_put_already_queued); } /* * Drop a ref on a local endpoint. */ -void rxrpc_put_local(struct rxrpc_local *local) +void rxrpc_put_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id; bool dead; - int r; + int r, u; if (local) { debug_id = local->debug_id; + u = atomic_read(&local->active_users); dead = __refcount_dec_and_test(&local->ref, &r); - trace_rxrpc_local(debug_id, rxrpc_local_put, r, here); + trace_rxrpc_local(debug_id, why, r, u); if (dead) call_rcu(&local->rcu, rxrpc_local_rcu); @@ -339,14 +339,15 @@ void rxrpc_put_local(struct rxrpc_local *local) /* * Start using a local endpoint. */ -struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - local = rxrpc_get_local_maybe(local); + local = rxrpc_get_local_maybe(local, rxrpc_local_get_for_use); if (!local) return NULL; - if (!__rxrpc_use_local(local)) { - rxrpc_put_local(local); + if (!__rxrpc_use_local(local, why)) { + rxrpc_put_local(local, rxrpc_local_put_for_use); return NULL; } @@ -357,11 +358,18 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) * Cease using a local endpoint. Once the number of active users reaches 0, we * start the closure of the transport in the work processor. */ -void rxrpc_unuse_local(struct rxrpc_local *local) +void rxrpc_unuse_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { + unsigned int debug_id; + int r, u; + if (local) { - if (__rxrpc_unuse_local(local)) { - rxrpc_get_local(local); + debug_id = local->debug_id; + r = refcount_read(&local->ref); + u = atomic_dec_return(&local->active_users); + trace_rxrpc_local(debug_id, why, r, u); + if (u == 0) { + rxrpc_get_local(local, rxrpc_local_get_queue); rxrpc_queue_local(local); } } @@ -418,12 +426,11 @@ static void rxrpc_local_processor(struct work_struct *work) if (local->dead) return; - trace_rxrpc_local(local->debug_id, rxrpc_local_processing, - refcount_read(&local->ref), NULL); + rxrpc_see_local(local, rxrpc_local_processing); do { again = false; - if (!__rxrpc_use_local(local)) { + if (!__rxrpc_use_local(local, rxrpc_local_use_work)) { rxrpc_local_destroyer(local); break; } @@ -443,10 +450,10 @@ static void rxrpc_local_processor(struct work_struct *work) again = true; } - __rxrpc_unuse_local(local); + __rxrpc_unuse_local(local, rxrpc_local_unuse_work); } while (again); - rxrpc_put_local(local); + rxrpc_put_local(local, rxrpc_local_put_queue); } /* @@ -460,6 +467,7 @@ static void rxrpc_local_rcu(struct rcu_head *rcu) ASSERT(!work_pending(&local->processor)); + rxrpc_see_local(local, rxrpc_local_free); kfree(local); _leave(""); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index b5d8eac8c49c..2762b7ada9ae 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -288,8 +288,7 @@ void rxrpc_transmit_ack_packets(struct rxrpc_local *local) LIST_HEAD(queue); int ret; - trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, - refcount_read(&local->ref), NULL); + rxrpc_see_local(local, rxrpc_local_see_tx_ack); if (list_empty(&local->ack_tx_queue)) return; diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index ad4d1769e02b..3f8d104ecaa7 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -266,7 +266,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, if (!rxrpc_get_peer_maybe(peer)) continue; - if (__rxrpc_use_local(peer->local)) { + if (__rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive)) { spin_unlock_bh(&rxnet->peer_hash_lock); keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; @@ -289,7 +289,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_unuse_local(peer->local); + rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } rxrpc_put_peer_locked(peer); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index b3c3c1c344fc..bcef897560e7 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -215,7 +215,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { refcount_set(&peer->ref, 1); - peer->local = rxrpc_get_local(local); + peer->local = rxrpc_get_local(local, rxrpc_local_get_peer); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -294,7 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, static void rxrpc_free_peer(struct rxrpc_peer *peer) { - rxrpc_put_local(peer->local); + rxrpc_put_local(peer->local, rxrpc_local_put_peer); kfree_rcu(peer, rcu); } -- cgit v1.2.3 From 47c810a79844462d3468d831edc00971757693e0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 13:39:34 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_peer tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_peer tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 43 ++++++++++++++++++++++++++----------------- net/rxrpc/af_rxrpc.c | 2 +- net/rxrpc/ar-internal.h | 11 ++++++----- net/rxrpc/call_accept.c | 8 +++++--- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_client.c | 8 ++++---- net/rxrpc/conn_object.c | 2 +- net/rxrpc/peer_event.c | 8 ++++---- net/rxrpc/peer_object.c | 34 ++++++++++++++++------------------ net/rxrpc/sendmsg.c | 2 +- 10 files changed, 65 insertions(+), 55 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 015569845b1d..1c74143a51c1 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -63,10 +63,23 @@ E_(rxrpc_local_use_work, "USE work ") #define rxrpc_peer_traces \ - EM(rxrpc_peer_got, "GOT") \ - EM(rxrpc_peer_new, "NEW") \ - EM(rxrpc_peer_processing, "PRO") \ - E_(rxrpc_peer_put, "PUT") + EM(rxrpc_peer_free, "FREE ") \ + EM(rxrpc_peer_get_accept, "GET accept ") \ + EM(rxrpc_peer_get_activate_call, "GET act-call") \ + EM(rxrpc_peer_get_bundle, "GET bundle ") \ + EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ + EM(rxrpc_peer_get_input_error, "GET inpt-err") \ + EM(rxrpc_peer_get_keepalive, "GET keepaliv") \ + EM(rxrpc_peer_get_lookup_client, "GET look-cln") \ + EM(rxrpc_peer_get_service_conn, "GET srv-conn") \ + EM(rxrpc_peer_new_client, "NEW client ") \ + EM(rxrpc_peer_new_prealloc, "NEW prealloc") \ + EM(rxrpc_peer_put_bundle, "PUT bundle ") \ + EM(rxrpc_peer_put_call, "PUT call ") \ + EM(rxrpc_peer_put_conn, "PUT conn ") \ + EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ + EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ + E_(rxrpc_peer_put_keepalive, "PUT keepaliv") #define rxrpc_conn_traces \ EM(rxrpc_conn_got, "GOT") \ @@ -394,30 +407,26 @@ TRACE_EVENT(rxrpc_local, ); TRACE_EVENT(rxrpc_peer, - TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op, - int usage, const void *where), + TP_PROTO(unsigned int peer_debug_id, int ref, enum rxrpc_peer_trace why), - TP_ARGS(peer_debug_id, op, usage, where), + TP_ARGS(peer_debug_id, ref, why), TP_STRUCT__entry( __field(unsigned int, peer ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) + __field(int, ref ) + __field(int, why ) ), TP_fast_assign( __entry->peer = peer_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; ), - TP_printk("P=%08x %s u=%d sp=%pSR", + TP_printk("P=%08x %s r=%d", __entry->peer, - __print_symbolic(__entry->op, rxrpc_peer_traces), - __entry->usage, - __entry->where) + __print_symbolic(__entry->why, rxrpc_peer_traces), + __entry->ref) ); TRACE_EVENT(rxrpc_conn, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 989ebca899f3..7a0dc01741e7 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -328,7 +328,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, mutex_unlock(&call->user_mutex); } - rxrpc_put_peer(cp.peer); + rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p", call); return call; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index dde9ce21ef48..6cb111e9761c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1063,14 +1063,15 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); -struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, + enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); -struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); -struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); -void rxrpc_put_peer(struct rxrpc_peer *); -void rxrpc_put_peer_locked(struct rxrpc_peer *); +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); +void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); +void rxrpc_put_peer_locked(struct rxrpc_peer *, enum rxrpc_peer_trace); /* * proc.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 1b12d4e28373..f6bc3b07c3e5 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -70,7 +70,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, head = b->peer_backlog_head; tail = READ_ONCE(b->peer_backlog_tail); if (CIRC_CNT(head, tail, size) < max) { - struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp); + struct rxrpc_peer *peer; + + peer = rxrpc_alloc_peer(rx->local, gfp, rxrpc_peer_new_prealloc); if (!peer) return -ENOMEM; b->peer_backlog[head] = peer; @@ -286,7 +288,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, return NULL; if (!conn) { - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_service_conn)) peer = NULL; if (!peer) { peer = b->peer_backlog[peer_tail]; @@ -323,7 +325,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; - call->peer = rxrpc_get_peer(conn->peer); + call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_accept); call->cong_ssthresh = call->peer->cong_ssthresh; call->tx_last_sent = ktime_get_real(); return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 59928f0a8fe1..1b725afd6e2c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -636,7 +636,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_delete_call_timer(call); rxrpc_put_connection(call->conn); - rxrpc_put_peer(call->peer); + rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9a69b4c1b182..9444da235a48 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -123,7 +123,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle = kzalloc(sizeof(*bundle), gfp); if (bundle) { bundle->local = cp->local; - bundle->peer = rxrpc_get_peer(cp->peer); + bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle); bundle->key = cp->key; bundle->exclusive = cp->exclusive; bundle->upgrade = cp->upgrade; @@ -145,7 +145,7 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { - rxrpc_put_peer(bundle->peer); + rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); kfree(bundle); } @@ -207,7 +207,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) write_unlock(&rxnet->conn_lock); rxrpc_get_bundle(bundle); - rxrpc_get_peer(conn->peer); + rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); @@ -543,7 +543,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, rxrpc_see_call(call); list_del_init(&call->chan_wait_link); - call->peer = rxrpc_get_peer(conn->peer); + call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn); call->cid = conn->proto.cid | channel; call->call_id = call_id; diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 725359afeac0..554ee5dd3325 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -362,7 +362,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle); - rxrpc_put_peer(conn->peer); + rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) wake_up_var(&conn->local->rxnet->nr_conns); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 3f8d104ecaa7..5e97d321ac38 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -168,7 +168,7 @@ void rxrpc_error_report(struct sock *sk) } peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_input_error)) peer = NULL; if (!peer) { rcu_read_unlock(); @@ -190,7 +190,7 @@ void rxrpc_error_report(struct sock *sk) out: rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); - rxrpc_put_peer(peer); + rxrpc_put_peer(peer, rxrpc_peer_put_input_error); _leave(""); } @@ -263,7 +263,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, struct rxrpc_peer, keepalive_link); list_del_init(&peer->keepalive_link); - if (!rxrpc_get_peer_maybe(peer)) + if (!rxrpc_get_peer_maybe(peer, rxrpc_peer_get_keepalive)) continue; if (__rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive)) { @@ -291,7 +291,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, &rxnet->peer_keepalive[slot & mask]); rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } - rxrpc_put_peer_locked(peer); + rxrpc_put_peer_locked(peer, rxrpc_peer_put_keepalive); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index bcef897560e7..9e682a60a800 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -205,9 +205,9 @@ static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, /* * Allocate a peer. */ -struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, + enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); struct rxrpc_peer *peer; _enter(""); @@ -226,7 +226,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); + trace_rxrpc_peer(peer->debug_id, why, 1); } _leave(" = %p", peer); @@ -282,7 +282,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, _enter(""); - peer = rxrpc_alloc_peer(local, gfp); + peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); rxrpc_init_peer(rx, peer, hash_key); @@ -294,6 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, static void rxrpc_free_peer(struct rxrpc_peer *peer) { + trace_rxrpc_peer(peer->debug_id, 0, rxrpc_peer_free); rxrpc_put_local(peer->local, rxrpc_local_put_peer); kfree_rcu(peer, rcu); } @@ -334,7 +335,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* search the peer list first */ rcu_read_lock(); peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_lookup_client)) peer = NULL; rcu_read_unlock(); @@ -352,7 +353,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_lookup_client)) peer = NULL; if (!peer) { hash_add_rcu(rxnet->peer_hash, @@ -376,27 +377,26 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* * Get a ref on a peer record. */ -struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); int r; __refcount_inc(&peer->ref, &r); - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); + trace_rxrpc_peer(peer->debug_id, why, r + 1); return peer; } /* * Get a ref on a peer record unless its usage has already reached 0. */ -struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer, + enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); int r; if (peer) { if (__refcount_inc_not_zero(&peer->ref, &r)) - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); + trace_rxrpc_peer(peer->debug_id, r + 1, why); else peer = NULL; } @@ -423,9 +423,8 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) /* * Drop a ref on a peer record. */ -void rxrpc_put_peer(struct rxrpc_peer *peer) +void rxrpc_put_peer(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id; bool dead; int r; @@ -433,7 +432,7 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) if (peer) { debug_id = peer->debug_id; dead = __refcount_dec_and_test(&peer->ref, &r); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + trace_rxrpc_peer(debug_id, r - 1, why); if (dead) __rxrpc_put_peer(peer); } @@ -443,15 +442,14 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) * Drop a ref on a peer record where the caller already holds the * peer_hash_lock. */ -void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +void rxrpc_put_peer_locked(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = peer->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&peer->ref, &r); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + trace_rxrpc_peer(debug_id, r - 1, why); if (dead) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index e5fd8a95bf71..cfe0badba0b3 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -604,7 +604,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ - rxrpc_put_peer(cp.peer); + rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p\n", call); return call; } -- cgit v1.2.3 From 7fa25105b2d32fcb0f38668bc20d0adf6508322f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 14:06:16 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_conn tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_conn tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 58 ++++++++++++++++++++++++++++---------------- net/rxrpc/ar-internal.h | 21 +++++++++------- net/rxrpc/call_accept.c | 9 +++---- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_client.c | 28 ++++++++++----------- net/rxrpc/conn_event.c | 4 +-- net/rxrpc/conn_object.c | 40 +++++++++++++++--------------- net/rxrpc/conn_service.c | 4 +-- net/rxrpc/input.c | 2 +- 9 files changed, 92 insertions(+), 76 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 1c74143a51c1..e09568a8c173 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -82,14 +82,34 @@ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") #define rxrpc_conn_traces \ - EM(rxrpc_conn_got, "GOT") \ - EM(rxrpc_conn_new_client, "NWc") \ - EM(rxrpc_conn_new_service, "NWs") \ - EM(rxrpc_conn_put_client, "PTc") \ - EM(rxrpc_conn_put_service, "PTs") \ - EM(rxrpc_conn_queued, "QUE") \ - EM(rxrpc_conn_reap_service, "RPs") \ - E_(rxrpc_conn_seen, "SEE") + EM(rxrpc_conn_free, "FREE ") \ + EM(rxrpc_conn_get_activate_call, "GET act-call") \ + EM(rxrpc_conn_get_call_input, "GET inp-call") \ + EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ + EM(rxrpc_conn_get_idle, "GET idle ") \ + EM(rxrpc_conn_get_poke, "GET poke ") \ + EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ + EM(rxrpc_conn_new_client, "NEW client ") \ + EM(rxrpc_conn_new_service, "NEW service ") \ + EM(rxrpc_conn_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_conn_put_call, "PUT call ") \ + EM(rxrpc_conn_put_call_input, "PUT inp-call") \ + EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ + EM(rxrpc_conn_put_discard, "PUT discard ") \ + EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \ + EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ + EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ + EM(rxrpc_conn_put_poke, "PUT poke ") \ + EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ + EM(rxrpc_conn_put_unidle, "PUT unidle ") \ + EM(rxrpc_conn_put_work, "PUT work ") \ + EM(rxrpc_conn_queue_challenge, "GQ chall ") \ + EM(rxrpc_conn_queue_retry_work, "GQ retry-wk") \ + EM(rxrpc_conn_queue_rx_work, "GQ rx-work ") \ + EM(rxrpc_conn_queue_timer, "GQ timer ") \ + EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ + EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ + E_(rxrpc_conn_see_work, "SEE work ") #define rxrpc_client_traces \ EM(rxrpc_client_activate_chans, "Activa") \ @@ -430,30 +450,26 @@ TRACE_EVENT(rxrpc_peer, ); TRACE_EVENT(rxrpc_conn, - TP_PROTO(unsigned int conn_debug_id, enum rxrpc_conn_trace op, - int usage, const void *where), + TP_PROTO(unsigned int conn_debug_id, int ref, enum rxrpc_conn_trace why), - TP_ARGS(conn_debug_id, op, usage, where), + TP_ARGS(conn_debug_id, ref, why), TP_STRUCT__entry( __field(unsigned int, conn ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) + __field(int, ref ) + __field(int, why ) ), TP_fast_assign( __entry->conn = conn_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; ), - TP_printk("C=%08x %s u=%d sp=%pSR", + TP_printk("C=%08x %s r=%d", __entry->conn, - __print_symbolic(__entry->op, rxrpc_conn_traces), - __entry->usage, - __entry->where) + __print_symbolic(__entry->why, rxrpc_conn_traces), + __entry->ref) ); TRACE_EVENT(rxrpc_client, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6cb111e9761c..bc8281c410c5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -882,7 +882,7 @@ int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); -void rxrpc_put_client_conn(struct rxrpc_connection *); +void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); void rxrpc_clean_up_local_conns(struct rxrpc_local *); @@ -906,11 +906,13 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); -bool rxrpc_queue_conn(struct rxrpc_connection *); -void rxrpc_see_connection(struct rxrpc_connection *); -struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *); -struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); -void rxrpc_put_service_conn(struct rxrpc_connection *); +bool rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, + enum rxrpc_conn_trace); +struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, + enum rxrpc_conn_trace); +void rxrpc_put_service_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); @@ -924,15 +926,16 @@ static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) return !rxrpc_conn_is_client(conn); } -static inline void rxrpc_put_connection(struct rxrpc_connection *conn) +static inline void rxrpc_put_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { if (!conn) return; if (rxrpc_conn_is_client(conn)) - rxrpc_put_client_conn(conn); + rxrpc_put_client_conn(conn, why); else - rxrpc_put_service_conn(conn); + rxrpc_put_service_conn(conn, why); } static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index f6bc3b07c3e5..04b52e28e0cc 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -91,9 +91,6 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, b->conn_backlog[head] = conn; smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); - - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - refcount_read(&conn->ref), here); } /* Now it gets complicated, because calls get registered with the @@ -309,10 +306,10 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); conn->local = rxrpc_get_local(local, rxrpc_local_get_prealloc_conn); conn->peer = peer; - rxrpc_see_connection(conn); + rxrpc_see_connection(conn, rxrpc_conn_see_new_service_conn); rxrpc_new_incoming_connection(rx, conn, sec, skb); } else { - rxrpc_get_connection(conn); + rxrpc_get_connection(conn, rxrpc_conn_get_service_conn); } /* And now we can allocate and set up a new call */ @@ -402,7 +399,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, case RXRPC_CONN_SERVICE_UNSECURED: conn->state = RXRPC_CONN_SERVICE_CHALLENGING; set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); - rxrpc_queue_conn(call->conn); + rxrpc_queue_conn(call->conn, rxrpc_conn_queue_challenge); break; case RXRPC_CONN_SERVICE: diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 1b725afd6e2c..29ec4013aa0b 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -635,7 +635,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_delete_call_timer(call); - rxrpc_put_connection(call->conn); + rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9444da235a48..dcfec6a45255 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -211,9 +211,8 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, - refcount_read(&conn->ref), - __builtin_return_address(0)); + trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), + rxrpc_conn_new_client); atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); @@ -467,10 +466,10 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (candidate) { _debug("discard C=%x", candidate->debug_id); trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate); + rxrpc_put_connection(candidate, rxrpc_conn_put_discard); } - rxrpc_put_connection(old); + rxrpc_put_connection(old, rxrpc_conn_put_noreuse); _leave(""); } @@ -544,7 +543,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, rxrpc_see_call(call); list_del_init(&call->chan_wait_link); call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); - call->conn = rxrpc_get_connection(conn); + call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); call->cid = conn->proto.cid | channel; call->call_id = call_id; call->security = conn->security; @@ -592,7 +591,7 @@ static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connecti } spin_unlock(&rxnet->client_conn_cache_lock); if (drop_ref) - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_unidle); } } @@ -896,7 +895,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); conn->idle_timestamp = jiffies; - rxrpc_get_connection(conn); + rxrpc_get_connection(conn, rxrpc_conn_get_idle); spin_lock(&rxnet->client_conn_cache_lock); list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); spin_unlock(&rxnet->client_conn_cache_lock); @@ -938,7 +937,7 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_drop) { rxrpc_deactivate_bundle(bundle); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_unbundle); } } @@ -983,15 +982,15 @@ static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) /* * Clean up a dead client connections. */ -void rxrpc_put_client_conn(struct rxrpc_connection *conn) +void rxrpc_put_client_conn(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&conn->ref, &r); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, r - 1, here); + trace_rxrpc_conn(debug_id, r - 1, why); if (dead) rxrpc_kill_client_conn(conn); } @@ -1063,7 +1062,8 @@ next: spin_unlock(&rxnet->client_conn_cache_lock); rxrpc_unbundle_conn(conn); - rxrpc_put_connection(conn); /* Drop the ->cache_link ref */ + /* Drop the ->cache_link ref */ + rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle); nr_conns--; goto next; @@ -1134,7 +1134,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) struct rxrpc_connection, cache_link); list_del_init(&conn->cache_link); rxrpc_unbundle_conn(conn); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_local_dead); } _leave(" [culled]"); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 225edaf019f1..817f895c77ca 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -472,14 +472,14 @@ void rxrpc_process_connection(struct work_struct *work) struct rxrpc_connection *conn = container_of(work, struct rxrpc_connection, processor); - rxrpc_see_connection(conn); + rxrpc_see_connection(conn, rxrpc_conn_see_work); if (__rxrpc_use_local(conn->local, rxrpc_local_use_conn_work)) { rxrpc_do_process_connection(conn); rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_work); _leave(""); return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 554ee5dd3325..bbace8d9953d 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -26,7 +26,7 @@ static void rxrpc_connection_timer(struct timer_list *timer) struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); - rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn, rxrpc_conn_queue_timer); } /* @@ -260,43 +260,42 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) * Queue a connection's work processor, getting a ref to pass to the work * queue. */ -bool rxrpc_queue_conn(struct rxrpc_connection *conn) +bool rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; if (!__refcount_inc_not_zero(&conn->ref, &r)) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, r + 1, here); + trace_rxrpc_conn(conn->debug_id, why, r + 1); else - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_already_queued); return true; } /* * Note the re-emergence of a connection. */ -void rxrpc_see_connection(struct rxrpc_connection *conn) +void rxrpc_see_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); if (conn) { - int n = refcount_read(&conn->ref); + int r = refcount_read(&conn->ref); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); + trace_rxrpc_conn(conn->debug_id, r, why); } } /* * Get a ref on a connection. */ -struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; __refcount_inc(&conn->ref, &r); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r, here); + trace_rxrpc_conn(conn->debug_id, r + 1, why); return conn; } @@ -304,14 +303,14 @@ struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) * Try to get a ref on a connection. */ struct rxrpc_connection * -rxrpc_get_connection_maybe(struct rxrpc_connection *conn) +rxrpc_get_connection_maybe(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; if (conn) { if (__refcount_inc_not_zero(&conn->ref, &r)) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r + 1, here); + trace_rxrpc_conn(conn->debug_id, r + 1, why); else conn = NULL; } @@ -331,14 +330,14 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, /* * Release a service connection */ -void rxrpc_put_service_conn(struct rxrpc_connection *conn) +void rxrpc_put_service_conn(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; int r; __refcount_dec(&conn->ref, &r); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, r - 1, here); + trace_rxrpc_conn(debug_id, r - 1, why); if (r - 1 == 1) rxrpc_set_service_reap_timer(conn->local->rxnet, jiffies + rxrpc_connection_expiry); @@ -354,6 +353,9 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); + trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), + rxrpc_conn_free); + ASSERTCMP(refcount_read(&conn->ref), ==, 0); del_timer_sync(&conn->timer); @@ -419,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (!refcount_dec_if_one(&conn->ref)) continue; - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); + rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); if (rxrpc_conn_is_client(conn)) BUG(); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index a3b91864ef21..bf087213bd4d 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -141,9 +141,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - refcount_read(&conn->ref), - __builtin_return_address(0)); + rxrpc_see_connection(conn, rxrpc_conn_new_service); } return conn; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cecfd201d832..c8ff7489b412 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1121,7 +1121,7 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); } /* -- cgit v1.2.3 From cb0fc0c9722c0c001510e2a6d9b0a78b80421487 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 14:39:26 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_call tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_call tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 83 ++++++++++++++++++++--------------- net/rxrpc/ar-internal.h | 8 ++-- net/rxrpc/call_accept.c | 16 +++---- net/rxrpc/call_event.c | 8 ++-- net/rxrpc/call_object.c | 102 +++++++++++++++++++------------------------ net/rxrpc/conn_client.c | 2 +- net/rxrpc/input.c | 8 ++-- net/rxrpc/output.c | 2 +- net/rxrpc/peer_event.c | 2 +- net/rxrpc/recvmsg.c | 8 ++-- net/rxrpc/sendmsg.c | 4 +- 11 files changed, 121 insertions(+), 122 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index e09568a8c173..3f6de4294148 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -127,26 +127,44 @@ E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ - EM(rxrpc_call_connected, "CON") \ - EM(rxrpc_call_error, "*E*") \ - EM(rxrpc_call_got, "GOT") \ - EM(rxrpc_call_got_kernel, "Gke") \ - EM(rxrpc_call_got_timer, "GTM") \ - EM(rxrpc_call_got_tx, "Gtx") \ - EM(rxrpc_call_got_userid, "Gus") \ - EM(rxrpc_call_new_client, "NWc") \ - EM(rxrpc_call_new_service, "NWs") \ - EM(rxrpc_call_put, "PUT") \ - EM(rxrpc_call_put_kernel, "Pke") \ - EM(rxrpc_call_put_noqueue, "PnQ") \ - EM(rxrpc_call_put_notimer, "PnT") \ - EM(rxrpc_call_put_timer, "PTM") \ - EM(rxrpc_call_put_tx, "Ptx") \ - EM(rxrpc_call_put_userid, "Pus") \ - EM(rxrpc_call_queued, "QUE") \ - EM(rxrpc_call_queued_ref, "QUR") \ - EM(rxrpc_call_release, "RLS") \ - E_(rxrpc_call_seen, "SEE") + EM(rxrpc_call_get_input, "GET input ") \ + EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ + EM(rxrpc_call_get_notify_socket, "GET notify ") \ + EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ + EM(rxrpc_call_get_release_sock, "GET rel-sock") \ + EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ + EM(rxrpc_call_get_send_ack, "GET send-ack") \ + EM(rxrpc_call_get_timer, "GET timer ") \ + EM(rxrpc_call_get_userid, "GET user-id ") \ + EM(rxrpc_call_new_client, "NEW client ") \ + EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ + EM(rxrpc_call_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ + EM(rxrpc_call_put_input, "PUT input ") \ + EM(rxrpc_call_put_kernel, "PUT kernel ") \ + EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ + EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ + EM(rxrpc_call_put_send_ack, "PUT send-ack") \ + EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ + EM(rxrpc_call_put_timer, "PUT timer ") \ + EM(rxrpc_call_put_timer_already, "PUT timer-al") \ + EM(rxrpc_call_put_unnotify, "PUT unnotify") \ + EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ + EM(rxrpc_call_put_work, "PUT work ") \ + EM(rxrpc_call_queue_abort, "QUE abort ") \ + EM(rxrpc_call_queue_requeue, "QUE requeue ") \ + EM(rxrpc_call_queue_resend, "QUE resend ") \ + EM(rxrpc_call_queue_timer, "QUE timer ") \ + EM(rxrpc_call_see_accept, "SEE accept ") \ + EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ + EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ + EM(rxrpc_call_see_connected, "SEE connect ") \ + EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ + EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_release, "SEE release ") \ + EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ + E_(rxrpc_call_see_zap, "SEE zap ") #define rxrpc_txqueue_traces \ EM(rxrpc_txqueue_await_reply, "AWR") \ @@ -503,32 +521,29 @@ TRACE_EVENT(rxrpc_client, ); TRACE_EVENT(rxrpc_call, - TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op, - int usage, const void *where, const void *aux), + TP_PROTO(unsigned int call_debug_id, int ref, unsigned long aux, + enum rxrpc_call_trace why), - TP_ARGS(call_debug_id, op, usage, where, aux), + TP_ARGS(call_debug_id, ref, aux, why), TP_STRUCT__entry( __field(unsigned int, call ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) - __field(const void *, aux ) + __field(int, ref ) + __field(int, why ) + __field(unsigned long, aux ) ), TP_fast_assign( __entry->call = call_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; __entry->aux = aux; ), - TP_printk("c=%08x %s u=%d sp=%pSR a=%p", + TP_printk("c=%08x %s r=%d a=%lx", __entry->call, - __print_symbolic(__entry->op, rxrpc_call_traces), - __entry->usage, - __entry->where, + __print_symbolic(__entry->why, rxrpc_call_traces), + __entry->ref, __entry->aux) ); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bc8281c410c5..82eb09b961a0 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -847,10 +847,10 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -bool __rxrpc_queue_call(struct rxrpc_call *); -bool rxrpc_queue_call(struct rxrpc_call *); -void rxrpc_see_call(struct rxrpc_call *); -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op); +bool __rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +bool rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); +bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 04b52e28e0cc..dd4ca4bee77f 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -38,7 +38,6 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, unsigned long user_call_ID, gfp_t gfp, unsigned int debug_id) { - const void *here = __builtin_return_address(0); struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); struct rb_node *parent, **pp; @@ -102,9 +101,8 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, - refcount_read(&call->ref), - here, (const void *)user_call_ID); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + user_call_ID, rxrpc_call_new_prealloc_service); write_lock(&rx->call_lock); @@ -125,11 +123,11 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->user_call_ID = user_call_ID; call->notify_rx = notify_rx; if (user_attach_call) { - rxrpc_get_call(call, rxrpc_call_got_kernel); + rxrpc_get_call(call, rxrpc_call_get_kernel_service); user_attach_call(call, user_call_ID); } - rxrpc_get_call(call, rxrpc_call_got_userid); + rxrpc_get_call(call, rxrpc_call_get_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); set_bit(RXRPC_CALL_HAS_USERID, &call->flags); @@ -229,7 +227,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) } rxrpc_call_completed(call); rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_discard_prealloc); tail = (tail + 1) & (size - 1); } @@ -318,7 +316,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, smp_store_release(&b->call_backlog_tail, (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_accept); call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; @@ -430,7 +428,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel * service to prevent the call from being deallocated too early. */ - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_discard_prealloc); _leave(" = %p{%d}", call, call->debug_id); return call; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 591af8e2e3d0..0c8d2186cda8 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -101,7 +101,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, txb->ack.reason = ack_reason; txb->ack.nAcks = 0; - if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + if (!rxrpc_try_get_call(call, rxrpc_call_get_send_ack)) { rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); return; } @@ -302,7 +302,7 @@ void rxrpc_process_call(struct work_struct *work) unsigned int iterations = 0; rxrpc_serial_t ackr_serial; - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_input); //printk("\n--------------------\n"); _enter("{%d,%s,%lx}", @@ -436,12 +436,12 @@ recheck_state: goto requeue; out_put: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_work); out: _leave(""); return; requeue: - __rxrpc_queue_call(call); + __rxrpc_queue_call(call, rxrpc_call_queue_requeue); goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 29ec4013aa0b..afd957f6dc1c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -53,9 +53,9 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - __rxrpc_queue_call(call); + __rxrpc_queue_call(call, rxrpc_call_queue_timer); } else { - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_already_queued); } } @@ -64,10 +64,10 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why) { - if (rxrpc_try_get_call(call, rxrpc_call_got_timer)) { + if (rxrpc_try_get_call(call, rxrpc_call_get_timer)) { trace_rxrpc_timer(call, why, now); if (timer_reduce(&call->timer, expire_at)) - rxrpc_put_call(call, rxrpc_call_put_notimer); + rxrpc_put_call(call, rxrpc_call_put_timer_already); } } @@ -110,7 +110,7 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, return NULL; found_extant_call: - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_sendmsg); read_unlock(&rx->call_lock); _leave(" = %p [%d]", call, refcount_read(&call->ref)); return call; @@ -270,7 +270,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_net *rxnet; struct semaphore *limiter; struct rb_node *parent, **pp; - const void *here = __builtin_return_address(0); int ret; _enter("%p,%lx", rx, p->user_call_ID); @@ -291,9 +290,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, - refcount_read(&call->ref), - here, (const void *)p->user_call_ID); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + p->user_call_ID, rxrpc_call_new_client); if (p->kernel) __set_bit(RXRPC_CALL_KERNEL, &call->flags); @@ -322,7 +320,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, rcu_assign_pointer(call->socket, rx); call->user_call_ID = p->user_call_ID; __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); - rxrpc_get_call(call, rxrpc_call_got_userid); + rxrpc_get_call(call, rxrpc_call_get_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); list_add(&call->sock_link, &rx->sock_calls); @@ -344,8 +342,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error_attached_to_socket; - trace_rxrpc_call(call->debug_id, rxrpc_call_connected, - refcount_read(&call->ref), here, NULL); + rxrpc_see_call(call, rxrpc_call_see_connected); rxrpc_start_call_timer(call); @@ -362,11 +359,11 @@ error_dup_user_ID: release_sock(&rx->sk); __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, -EEXIST); - trace_rxrpc_call(call->debug_id, rxrpc_call_error, - refcount_read(&call->ref), here, ERR_PTR(-EEXIST)); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, + rxrpc_call_see_userid_exists); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_userid_exists); _leave(" = -EEXIST"); return ERR_PTR(-EEXIST); @@ -376,8 +373,8 @@ error_dup_user_ID: * leave the error to recvmsg() to deal with. */ error_attached_to_socket: - trace_rxrpc_call(call->debug_id, rxrpc_call_error, - refcount_read(&call->ref), here, ERR_PTR(ret)); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret, + rxrpc_call_see_connect_failed); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); @@ -428,72 +425,65 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, /* * Queue a call's work processor, getting a ref to pass to the work queue. */ -bool rxrpc_queue_call(struct rxrpc_call *call) +bool rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); int n; if (!__refcount_inc_not_zero(&call->ref, &n)) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, - here, NULL); + trace_rxrpc_call(call->debug_id, n + 1, 0, why); else - rxrpc_put_call(call, rxrpc_call_put_noqueue); + rxrpc_put_call(call, rxrpc_call_put_already_queued); return true; } /* * Queue a call's work processor, passing the callers ref to the work queue. */ -bool __rxrpc_queue_call(struct rxrpc_call *call) +bool __rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); int n = refcount_read(&call->ref); + ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, - here, NULL); + trace_rxrpc_call(call->debug_id, n, 0, why); else - rxrpc_put_call(call, rxrpc_call_put_noqueue); + rxrpc_put_call(call, rxrpc_call_put_already_queued); return true; } /* * Note the re-emergence of a call. */ -void rxrpc_see_call(struct rxrpc_call *call) +void rxrpc_see_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); if (call) { - int n = refcount_read(&call->ref); + int r = refcount_read(&call->ref); - trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, - here, NULL); + trace_rxrpc_call(call->debug_id, r, 0, why); } } -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); - int n; + int r; - if (!__refcount_inc_not_zero(&call->ref, &n)) + if (!__refcount_inc_not_zero(&call->ref, &r)) return false; - trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, r + 1, 0, why); return true; } /* * Note the addition of a ref on a call. */ -void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); - int n; + int r; - __refcount_inc(&call->ref, &n); - trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); + __refcount_inc(&call->ref, &r); + trace_rxrpc_call(call->debug_id, r + 1, 0, why); } /* @@ -510,15 +500,13 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) */ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { - const void *here = __builtin_return_address(0); struct rxrpc_connection *conn = call->conn; bool put = false; _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); - trace_rxrpc_call(call->debug_id, rxrpc_call_release, - refcount_read(&call->ref), - here, (const void *)call->flags); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + call->flags, rxrpc_call_see_release); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -544,14 +532,14 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) write_unlock_bh(&rx->recvmsg_lock); if (put) - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_unnotify); write_lock(&rx->call_lock); if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { rb_erase(&call->sock_node, &rx->calls); memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); - rxrpc_put_call(call, rxrpc_call_put_userid); + rxrpc_put_call(call, rxrpc_call_put_userid_exists); } list_del(&call->sock_link); @@ -580,17 +568,17 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) struct rxrpc_call, accept_link); list_del(&call->accept_link); rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_release_sock_tba); } while (!list_empty(&rx->sock_calls)) { call = list_entry(rx->sock_calls.next, struct rxrpc_call, sock_link); - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_release_sock); rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET); rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_release_sock); } _leave(""); @@ -599,20 +587,18 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) /* * release a call */ -void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { struct rxrpc_net *rxnet = call->rxnet; - const void *here = __builtin_return_address(0); unsigned int debug_id = call->debug_id; bool dead; - int n; + int r; ASSERT(call != NULL); - dead = __refcount_dec_and_test(&call->ref, &n); - trace_rxrpc_call(debug_id, op, n, here, NULL); + dead = __refcount_dec_and_test(&call->ref, &r); + trace_rxrpc_call(debug_id, r - 1, 0, why); if (dead) { - _debug("call %d dead", call->debug_id); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); if (!list_empty(&call->link)) { @@ -701,7 +687,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) struct rxrpc_call, link); _debug("Zapping call %p", call); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_zap); list_del_init(&call->link); pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index dcfec6a45255..4352e777aa2a 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -540,7 +540,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_activate_client); list_del_init(&call->chan_wait_link); call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index c8ff7489b412..09b44cd11c9b 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -14,7 +14,7 @@ static void rxrpc_proto_abort(const char *why, { if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) { set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_abort); } } @@ -175,7 +175,7 @@ out_no_clear_ca: call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_resend); return; packet_loss_detected: @@ -678,7 +678,7 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { if (after(call->acks_lost_top, call->acks_prev_seq) && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_resend); } /* @@ -1099,7 +1099,7 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, default: if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) { set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_abort); } trace_rxrpc_improper_term(call); break; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 2762b7ada9ae..d324e88f7642 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -310,7 +310,7 @@ void rxrpc_transmit_ack_packets(struct rxrpc_local *local) } list_del_init(&txb->tx_link); - rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_call(txb->call, rxrpc_call_put_send_ack); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 5e97d321ac38..b28739d10927 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -238,7 +238,7 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, struct rxrpc_call *call; hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) { - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_distribute_error); rxrpc_set_call_completion(call, compl, 0, -error); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 134122f5961a..c84d2b620396 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -42,7 +42,7 @@ void rxrpc_notify_socket(struct rxrpc_call *call) } else { write_lock_bh(&rx->recvmsg_lock); if (list_empty(&call->recvmsg_link)) { - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_notify_socket); list_add_tail(&call->recvmsg_link, &rx->recvmsg_q); } write_unlock_bh(&rx->recvmsg_lock); @@ -451,7 +451,7 @@ try_again: if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_recvmsg); write_unlock_bh(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); @@ -537,7 +537,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; @@ -548,7 +548,7 @@ error_requeue_call: write_unlock_bh(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); } error_no_call: release_sock(&rx->sk); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index cfe0badba0b3..76b1e2e89c1e 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -667,7 +667,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_sendmsg); ret = -EBUSY; goto error_release_sock; default: @@ -737,7 +737,7 @@ out_put_unlock: if (!dropped_lock) mutex_unlock(&call->user_mutex); error_put: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_sendmsg); _leave(" = %d", ret); return ret; -- cgit v1.2.3 From fa3492abb64b93b2b5d6fdf7a5b687a1fa810d74 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Nov 2022 21:54:46 +0000 Subject: rxrpc: Trace rxrpc_bundle refcount Add a tracepoint for the rxrpc_bundle refcounting. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 34 ++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 4 ++-- net/rxrpc/conn_client.c | 27 ++++++++++++++++----------- net/rxrpc/conn_object.c | 2 +- net/rxrpc/conn_service.c | 3 ++- 5 files changed, 55 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 3f6de4294148..6f5be7ac7f6b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -81,6 +81,15 @@ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") +#define rxrpc_bundle_traces \ + EM(rxrpc_bundle_free, "FREE ") \ + EM(rxrpc_bundle_get_client_call, "GET clt-call") \ + EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \ + EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \ + EM(rxrpc_bundle_put_conn, "PUT conn ") \ + EM(rxrpc_bundle_put_discard, "PUT discard ") \ + E_(rxrpc_bundle_new, "NEW ") + #define rxrpc_conn_traces \ EM(rxrpc_conn_free, "FREE ") \ EM(rxrpc_conn_get_activate_call, "GET act-call") \ @@ -361,6 +370,7 @@ #define EM(a, b) a, #define E_(a, b) a +enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); @@ -390,6 +400,7 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +rxrpc_bundle_traces; rxrpc_call_traces; rxrpc_client_traces; rxrpc_congest_changes; @@ -467,6 +478,29 @@ TRACE_EVENT(rxrpc_peer, __entry->ref) ); +TRACE_EVENT(rxrpc_bundle, + TP_PROTO(unsigned int bundle_debug_id, int ref, enum rxrpc_bundle_trace why), + + TP_ARGS(bundle_debug_id, ref, why), + + TP_STRUCT__entry( + __field(unsigned int, bundle ) + __field(int, ref ) + __field(int, why ) + ), + + TP_fast_assign( + __entry->bundle = bundle_debug_id; + __entry->ref = ref; + __entry->why = why; + ), + + TP_printk("CB=%08x %s r=%d", + __entry->bundle, + __print_symbolic(__entry->why, rxrpc_bundle_traces), + __entry->ref) + ); + TRACE_EVENT(rxrpc_conn, TP_PROTO(unsigned int conn_debug_id, int ref, enum rxrpc_conn_trace why), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 82eb09b961a0..c588c0e81f63 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -875,8 +875,8 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); -struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *); -void rxrpc_put_bundle(struct rxrpc_bundle *); +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); +void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 4352e777aa2a..34ff6fa85c32 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -133,31 +133,36 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); + trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new); } return bundle; } -struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle, + enum rxrpc_bundle_trace why) { - refcount_inc(&bundle->ref); + int r; + + __refcount_inc(&bundle->ref, &r); + trace_rxrpc_bundle(bundle->debug_id, r + 1, why); return bundle; } static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { + trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); kfree(bundle); } -void rxrpc_put_bundle(struct rxrpc_bundle *bundle) +void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why) { - unsigned int d = bundle->debug_id; + unsigned int id = bundle->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&bundle->ref, &r); - - _debug("PUT B=%x %d", d, r - 1); + trace_rxrpc_bundle(id, r - 1, why); if (dead) rxrpc_free_bundle(bundle); } @@ -206,7 +211,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - rxrpc_get_bundle(bundle); + rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); @@ -342,7 +347,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); - rxrpc_get_bundle(candidate); + rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); spin_unlock(&local->client_bundles_lock); _leave(" = %u [new]", candidate->debug_id); return candidate; @@ -350,7 +355,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: - rxrpc_get_bundle(bundle); + rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); @@ -740,7 +745,7 @@ granted_channel: out_put_bundle: rxrpc_deactivate_bundle(bundle); - rxrpc_put_bundle(bundle); + rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call); out: _leave(" = %d", ret); return ret; @@ -958,7 +963,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) spin_unlock(&local->client_bundles_lock); if (need_put) - rxrpc_put_bundle(bundle); + rxrpc_put_bundle(bundle, rxrpc_bundle_put_discard); } } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index bbace8d9953d..f7c271a740ed 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -363,7 +363,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->key); - rxrpc_put_bundle(conn->bundle); + rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index bf087213bd4d..2c44d67b43dc 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -133,7 +133,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; refcount_set(&conn->ref, 2); - conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle); + conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle, + rxrpc_bundle_get_service_conn); atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); -- cgit v1.2.3 From 9a36a6bc22ca1c0a9d82228171e05dc785fa1154 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 15:31:21 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for sk_buff tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the sk_buff tracepoint. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 57 +++++++++++++++++++++++++------------------- net/rxrpc/call_event.c | 4 ++-- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_event.c | 6 ++--- net/rxrpc/input.c | 36 ++++++++++++++-------------- net/rxrpc/local_event.c | 4 ++-- net/rxrpc/output.c | 6 ++--- net/rxrpc/peer_event.c | 8 +++---- net/rxrpc/recvmsg.c | 6 ++--- net/rxrpc/skbuff.c | 36 ++++++++++++---------------- 10 files changed, 84 insertions(+), 81 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 6f5be7ac7f6b..5a2292baffc8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,19 +17,31 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_skb_traces \ - EM(rxrpc_skb_ack, "ACK") \ - EM(rxrpc_skb_cleaned, "CLN") \ - EM(rxrpc_skb_cloned_jumbo, "CLJ") \ - EM(rxrpc_skb_freed, "FRE") \ - EM(rxrpc_skb_got, "GOT") \ - EM(rxrpc_skb_lost, "*L*") \ - EM(rxrpc_skb_new, "NEW") \ - EM(rxrpc_skb_purged, "PUR") \ - EM(rxrpc_skb_received, "RCV") \ - EM(rxrpc_skb_rotated, "ROT") \ - EM(rxrpc_skb_seen, "SEE") \ - EM(rxrpc_skb_unshared, "UNS") \ - E_(rxrpc_skb_unshared_nomem, "US0") + EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ + EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ + EM(rxrpc_skb_get_ack, "GET ack ") \ + EM(rxrpc_skb_get_conn_work, "GET conn-work") \ + EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \ + EM(rxrpc_skb_get_to_recvmsg_oos, "GET to-recv-o") \ + EM(rxrpc_skb_new_encap_rcv, "NEW encap-rcv") \ + EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ + EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ + EM(rxrpc_skb_new_unshared, "NEW unshared ") \ + EM(rxrpc_skb_put_ack, "PUT ack ") \ + EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ + EM(rxrpc_skb_put_error_report, "PUT error-rep") \ + EM(rxrpc_skb_put_input, "PUT input ") \ + EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \ + EM(rxrpc_skb_put_lose, "PUT lose ") \ + EM(rxrpc_skb_put_purge, "PUT purge ") \ + EM(rxrpc_skb_put_rotate, "PUT rotate ") \ + EM(rxrpc_skb_put_unknown, "PUT unknown ") \ + EM(rxrpc_skb_see_conn_work, "SEE conn-work") \ + EM(rxrpc_skb_see_local_work, "SEE locl-work") \ + EM(rxrpc_skb_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_skb_see_reject, "SEE reject ") \ + EM(rxrpc_skb_see_rotate, "SEE rotate ") \ + E_(rxrpc_skb_see_version, "SEE version ") #define rxrpc_local_traces \ EM(rxrpc_local_free, "FREE ") \ @@ -582,33 +594,30 @@ TRACE_EVENT(rxrpc_call, ); TRACE_EVENT(rxrpc_skb, - TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op, - int usage, int mod_count, const void *where), + TP_PROTO(struct sk_buff *skb, int usage, int mod_count, + enum rxrpc_skb_trace why), - TP_ARGS(skb, op, usage, mod_count, where), + TP_ARGS(skb, usage, mod_count, why), TP_STRUCT__entry( __field(struct sk_buff *, skb ) - __field(enum rxrpc_skb_trace, op ) __field(int, usage ) __field(int, mod_count ) - __field(const void *, where ) + __field(enum rxrpc_skb_trace, why ) ), TP_fast_assign( __entry->skb = skb; - __entry->op = op; __entry->usage = usage; __entry->mod_count = mod_count; - __entry->where = where; + __entry->why = why; ), - TP_printk("s=%p Rx %s u=%d m=%d p=%pSR", + TP_printk("s=%p Rx %s u=%d m=%d", __entry->skb, - __print_symbolic(__entry->op, rxrpc_skb_traces), + __print_symbolic(__entry->why, rxrpc_skb_traces), __entry->usage, - __entry->mod_count, - __entry->where) + __entry->mod_count) ); TRACE_EVENT(rxrpc_rx_packet, diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0c8d2186cda8..29ca02e53c47 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -153,7 +153,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) spin_lock_bh(&call->acks_ack_lock); ack_skb = call->acks_soft_tbl; if (ack_skb) { - rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + rxrpc_get_skb(ack_skb, rxrpc_skb_get_ack); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); } spin_unlock_bh(&call->acks_ack_lock); @@ -251,7 +251,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) no_further_resend: spin_unlock(&call->tx_lock); no_resend: - rxrpc_free_skb(ack_skb, rxrpc_skb_freed); + rxrpc_free_skb(ack_skb, rxrpc_skb_put_ack); resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index afd957f6dc1c..815209673115 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -663,7 +663,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 817f895c77ca..49d885f73fa5 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -437,7 +437,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_conn_work); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -449,7 +449,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); break; } } @@ -463,7 +463,7 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); return; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 09b44cd11c9b..ab8b7a1be935 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -485,7 +485,7 @@ send_ack: rxrpc_propose_ack_input_data); err_free: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } /* @@ -513,7 +513,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb kdebug("couldn't clone"); return false; } - rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + rxrpc_new_skb(jskb, rxrpc_skb_new_jumbo_subpacket); jsp = rxrpc_skb(jskb); jsp->offset = offset; jsp->len = RXRPC_JUMBO_DATALEN; @@ -553,7 +553,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); return; } @@ -563,14 +563,14 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (sp->hdr.securityIndex != 0) { struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); return; } if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_unshared); + rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } } @@ -609,7 +609,7 @@ out: rxrpc_notify_socket(call); spin_unlock(&call->input_lock); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); _leave(" [queued]"); } @@ -994,8 +994,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) out: spin_unlock(&call->input_lock); out_not_locked: - rxrpc_free_skb(skb_put, rxrpc_skb_freed); - rxrpc_free_skb(skb_old, rxrpc_skb_freed); + rxrpc_free_skb(skb_put, rxrpc_skb_put_input); + rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } /* @@ -1075,7 +1075,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, break; } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); no_free: _leave(""); } @@ -1137,7 +1137,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -1150,7 +1150,7 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -1228,7 +1228,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); - rxrpc_new_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_new_encap_rcv); skb_pull(skb, sizeof(struct udphdr)); @@ -1245,7 +1245,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_lost); + rxrpc_free_skb(skb, rxrpc_skb_put_lose); return 0; } } @@ -1286,14 +1286,14 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.securityIndex != 0) { struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); goto out; } if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_unshared); + rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } } @@ -1434,7 +1434,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto out; discard: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); out: trace_rxrpc_rx_done(0, 0); return 0; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index f23a3fbabbda..c344383a20b2 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -88,7 +88,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_local_work); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { @@ -105,7 +105,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) break; } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } _leave(""); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index d324e88f7642..131c7a76fb06 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -615,7 +615,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_reject); sp = rxrpc_skb(skb); switch (skb->mark) { @@ -631,7 +631,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ioc = 2; break; default: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); continue; } @@ -656,7 +656,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) rxrpc_tx_point_reject); } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index b28739d10927..f35cfc458dcf 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -158,12 +158,12 @@ void rxrpc_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } - rxrpc_new_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_new_error_report); serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); return; } @@ -172,7 +172,7 @@ void rxrpc_error_report(struct sock *sk) peer = NULL; if (!peer) { rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); _leave(" [no peer]"); return; } @@ -189,7 +189,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_store_error(peer, serr); out: rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); rxrpc_put_peer(peer, rxrpc_peer_put_input_error); _leave(""); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index c84d2b620396..bfac9e09347e 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -229,7 +229,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) _enter("%d", call->debug_id); skb = skb_dequeue(&call->recvmsg_queue); - rxrpc_see_skb(skb, rxrpc_skb_rotated); + rxrpc_see_skb(skb, rxrpc_skb_see_rotate); sp = rxrpc_skb(skb); tseq = sp->hdr.seq; @@ -240,7 +240,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) if (after(tseq, call->rx_consumed)) smp_store_release(&call->rx_consumed, tseq); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_rotate); trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, serial, call->rx_consumed); @@ -302,7 +302,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, */ skb = skb_peek(&call->recvmsg_queue); while (skb) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_recvmsg); sp = rxrpc_skb(skb); seq = sp->hdr.seq; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 0c827d5bb2b8..ebe0c75e7b07 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* ar-skbuff.c: socket buffer destruction handling +/* Socket buffer accounting * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -19,56 +19,50 @@ /* * Note the allocation or reception of a socket buffer. */ -void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ -void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } } /* * Note the addition of a ref on a socket buffer. */ -void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); skb_get(skb); } /* * Note the dropping of a ref on a socket buffer by the core. */ -void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, here); + trace_rxrpc_skb(skb, 0, n, why); } /* * Note the destruction of a socket buffer. */ -void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); if (skb) { - int n; - n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); kfree_skb(skb); } } @@ -78,12 +72,12 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) */ void rxrpc_purge_queue(struct sk_buff_head *list) { - const void *here = __builtin_return_address(0); struct sk_buff *skb; + while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, + rxrpc_skb_put_purge); kfree_skb(skb); } } -- cgit v1.2.3 From 3feda9d69c83983b530cea6287ba4fea0e5c3b87 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Nov 2022 09:00:55 +0000 Subject: rxrpc: Don't hold a ref for call timer or workqueue Currently, rxrpc gives the call timer a ref on the call when it starts it and this is passed along to the workqueue by the timer expiration function. The problem comes when queue_work() fails (ie. the work item is already queued): the timer routine must put the ref - but this may cause the cleanup code to run. This has the unfortunate effect that the cleanup code may then be run in softirq context - which means that any spinlocks it might need to touch have to be guarded to disable softirqs (ie. they need a "_bh" suffix). Fix this by: (1) Don't give a ref to the timer. (2) Making the expiration function not do anything if the refcount is 0. Note that this is more of an optimisation. (3) Make sure that the cleanup routine waits for timer to complete. However, this has a consequence that timer cannot give a ref to the work item. Therefore the following fixes are also necessary: (4) Don't give a ref to the work item. (5) Make the work item return asap if it sees the ref count is 0. (6) Make sure that the cleanup routine waits for the work item to complete. Unfortunately, neither the timer nor the work item can simply get around the problem by just using refcount_inc_not_zero() as the waits would still have to be done, and there would still be the possibility of having to put the ref in the expiration function. Note the call work item is going to go away with the work being transferred to the I/O thread, so the wait in (6) will become obsolete. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 6 +-- net/rxrpc/ar-internal.h | 6 +-- net/rxrpc/call_event.c | 11 ++--- net/rxrpc/call_object.c | 111 ++++++++++++++++--------------------------- net/rxrpc/txbuf.c | 2 + 5 files changed, 52 insertions(+), 84 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 5a2292baffc8..4538de0079a5 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -155,11 +155,9 @@ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ EM(rxrpc_call_get_send_ack, "GET send-ack") \ - EM(rxrpc_call_get_timer, "GET timer ") \ EM(rxrpc_call_get_userid, "GET user-id ") \ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ - EM(rxrpc_call_put_already_queued, "PUT alreadyq") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ @@ -168,11 +166,8 @@ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ EM(rxrpc_call_put_send_ack, "PUT send-ack") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ - EM(rxrpc_call_put_timer, "PUT timer ") \ - EM(rxrpc_call_put_timer_already, "PUT timer-al") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ - EM(rxrpc_call_put_work, "PUT work ") \ EM(rxrpc_call_queue_abort, "QUE abort ") \ EM(rxrpc_call_queue_requeue, "QUE requeue ") \ EM(rxrpc_call_queue_resend, "QUE resend ") \ @@ -368,6 +363,7 @@ EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ EM(rxrpc_txbuf_put_trans, "PUT TRANS ") \ + EM(rxrpc_txbuf_see_out_of_step, "OUT-OF-STEP") \ EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c588c0e81f63..03523a864c11 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -598,6 +598,7 @@ struct rxrpc_call { u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ + struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ @@ -827,8 +828,6 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why); -void rxrpc_delete_call_timer(struct rxrpc_call *call); - /* * call_object.c */ @@ -847,8 +846,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -bool __rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); -bool rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 29ca02e53c47..049b92b1c040 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -323,8 +323,8 @@ recheck_state: rxrpc_shrink_call_tx_buffer(call); if (call->state == RXRPC_CALL_COMPLETE) { - rxrpc_delete_call_timer(call); - goto out_put; + del_timer_sync(&call->timer); + goto out; } /* Work out if any timeouts tripped */ @@ -432,16 +432,15 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) + if (call->events) goto requeue; -out_put: - rxrpc_put_call(call, rxrpc_call_put_work); out: _leave(""); return; requeue: - __rxrpc_queue_call(call, rxrpc_call_queue_requeue); + if (call->state < RXRPC_CALL_COMPLETE) + rxrpc_queue_call(call, rxrpc_call_queue_requeue); goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 815209673115..9cd7e0190ef4 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -53,9 +53,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - __rxrpc_queue_call(call, rxrpc_call_queue_timer); - } else { - rxrpc_put_call(call, rxrpc_call_put_already_queued); + rxrpc_queue_call(call, rxrpc_call_queue_timer); } } @@ -64,21 +62,14 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why) { - if (rxrpc_try_get_call(call, rxrpc_call_get_timer)) { - trace_rxrpc_timer(call, why, now); - if (timer_reduce(&call->timer, expire_at)) - rxrpc_put_call(call, rxrpc_call_put_timer_already); - } -} - -void rxrpc_delete_call_timer(struct rxrpc_call *call) -{ - if (del_timer_sync(&call->timer)) - rxrpc_put_call(call, rxrpc_call_put_timer); + trace_rxrpc_timer(call, why, now); + timer_reduce(&call->timer, expire_at); } static struct lock_class_key rxrpc_call_user_mutex_lock_class_key; +static void rxrpc_destroy_call(struct work_struct *); + /* * find an extant server call * - called in process context with IRQs enabled @@ -139,7 +130,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, &rxrpc_call_user_mutex_lock_class_key); timer_setup(&call->timer, rxrpc_call_timer_expired, 0); - INIT_WORK(&call->processor, &rxrpc_process_call); + INIT_WORK(&call->processor, rxrpc_process_call); + INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->chan_wait_link); INIT_LIST_HEAD(&call->accept_link); @@ -423,34 +415,12 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, } /* - * Queue a call's work processor, getting a ref to pass to the work queue. + * Queue a call's work processor. */ -bool rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) +void rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - int n; - - if (!__refcount_inc_not_zero(&call->ref, &n)) - return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, n + 1, 0, why); - else - rxrpc_put_call(call, rxrpc_call_put_already_queued); - return true; -} - -/* - * Queue a call's work processor, passing the callers ref to the work queue. - */ -bool __rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) -{ - int n = refcount_read(&call->ref); - - ASSERTCMP(n, >=, 1); - if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, n, 0, why); - else - rxrpc_put_call(call, rxrpc_call_put_already_queued); - return true; + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, why); } /* @@ -514,7 +484,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) BUG(); rxrpc_put_call_slot(call); - rxrpc_delete_call_timer(call); + del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ write_lock_bh(&rx->recvmsg_lock); @@ -612,36 +582,41 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) } /* - * Final call destruction - but must be done in process context. + * Free up the call under RCU. */ -static void rxrpc_destroy_call(struct work_struct *work) +static void rxrpc_rcu_free_call(struct rcu_head *rcu) { - struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - struct rxrpc_net *rxnet = call->rxnet; - - rxrpc_delete_call_timer(call); + struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_net *rxnet = READ_ONCE(call->rxnet); - rxrpc_put_connection(call->conn, rxrpc_conn_put_call); - rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); } /* - * Final call destruction under RCU. + * Final call destruction - but must be done in process context. */ -static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +static void rxrpc_destroy_call(struct work_struct *work) { - struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); + struct rxrpc_txbuf *txb; - if (in_softirq()) { - INIT_WORK(&call->processor, rxrpc_destroy_call); - if (!rxrpc_queue_work(&call->processor)) - BUG(); - } else { - rxrpc_destroy_call(&call->processor); + del_timer_sync(&call->timer); + cancel_work_sync(&call->processor); /* The processor may restart the timer */ + del_timer_sync(&call->timer); + + rxrpc_cleanup_ring(call); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); + rxrpc_put_connection(call->conn, rxrpc_conn_put_call); + rxrpc_put_peer(call->peer, rxrpc_peer_put_call); + call_rcu(&call->rcu, rxrpc_rcu_free_call); } /* @@ -649,23 +624,21 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { - struct rxrpc_txbuf *txb; - memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - rxrpc_cleanup_ring(call); - while ((txb = list_first_entry_or_null(&call->tx_buffer, - struct rxrpc_txbuf, call_link))) { - list_del(&txb->call_link); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); - } - rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); + del_timer_sync(&call->timer); + cancel_work(&call->processor); - call_rcu(&call->rcu, rxrpc_rcu_destroy_call); + if (in_softirq() || work_busy(&call->processor)) + /* Can't use the rxrpc workqueue as we need to cancel/flush + * something that may be running/waiting there. + */ + schedule_work(&call->destroyer); + else + rxrpc_destroy_call(&call->destroyer); } /* diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 96bfee89927b..f93dc666a3a0 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -120,6 +120,8 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) if (before(hard_ack, txb->seq)) break; + if (txb->seq != call->tx_bottom + 1) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_out_of_step); ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); call->tx_bottom++; list_del_rcu(&txb->call_link); -- cgit v1.2.3 From 3cec055c56958c5498eeb3ed9fb2aef2d28c030f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Nov 2022 12:43:50 +0000 Subject: rxrpc: Don't hold a ref for connection workqueue Currently, rxrpc gives the connection's work item a ref on the connection when it queues it - and this is called from the timer expiration function. The problem comes when queue_work() fails (ie. the work item is already queued): the timer routine must put the ref - but this may cause the cleanup code to run. This has the unfortunate effect that the cleanup code may then be run in softirq context - which means that any spinlocks it might need to touch have to be guarded to disable softirqs (ie. they need a "_bh" suffix). (1) Don't give a ref to the work item. (2) Simplify handling of service connections by adding a separate active count so that the refcount isn't also used for this. (3) Connection destruction for both client and service connections can then be cleaned up by putting rxrpc_put_connection() out of line and making a tidy progression through the destruction code (offloaded to a workqueue if put from softirq or processor function context). The RCU part of the cleanup then only deals with the freeing at the end. (4) Make rxrpc_queue_conn() return immediately if it sees the active count is -1 rather then queuing the connection. (5) Make sure that the cleanup routine waits for the work item to complete. (6) Stash the rxrpc_net pointer in the conn struct so that the rcu free routine can use it, even if the local endpoint has been freed. Unfortunately, neither the timer nor the work item can simply get around the problem by just using refcount_inc_not_zero() as the waits would still have to be done, and there would still be the possibility of having to put the ref in the expiration function. Note the connection work item is mostly going to go away with the main event work being transferred to the I/O thread, so the wait in (6) will become obsolete. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 11 ++- net/rxrpc/ar-internal.h | 25 ++----- net/rxrpc/call_accept.c | 1 + net/rxrpc/conn_client.c | 31 ++------ net/rxrpc/conn_event.c | 4 - net/rxrpc/conn_object.c | 169 ++++++++++++++++++++++++------------------- net/rxrpc/conn_service.c | 4 +- net/rxrpc/net_ns.c | 2 +- net/rxrpc/proc.c | 5 +- 9 files changed, 123 insertions(+), 129 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4538de0079a5..44a9be9836f9 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -112,7 +112,6 @@ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ EM(rxrpc_conn_new_service, "NEW service ") \ - EM(rxrpc_conn_put_already_queued, "PUT alreadyq") \ EM(rxrpc_conn_put_call, "PUT call ") \ EM(rxrpc_conn_put_call_input, "PUT inp-call") \ EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ @@ -121,13 +120,13 @@ EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ EM(rxrpc_conn_put_poke, "PUT poke ") \ + EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \ EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ EM(rxrpc_conn_put_unidle, "PUT unidle ") \ - EM(rxrpc_conn_put_work, "PUT work ") \ - EM(rxrpc_conn_queue_challenge, "GQ chall ") \ - EM(rxrpc_conn_queue_retry_work, "GQ retry-wk") \ - EM(rxrpc_conn_queue_rx_work, "GQ rx-work ") \ - EM(rxrpc_conn_queue_timer, "GQ timer ") \ + EM(rxrpc_conn_queue_challenge, "QUE chall ") \ + EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \ + EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \ + EM(rxrpc_conn_queue_timer, "QUE timer ") \ EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ E_(rxrpc_conn_see_work, "SEE work ") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 03523a864c11..41a57c145f2b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -76,7 +76,7 @@ struct rxrpc_net { bool kill_all_client_conns; atomic_t nr_client_conns; spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ - spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ + struct mutex client_conn_discard_lock; /* Prevent multiple discarders */ struct list_head idle_client_conns; struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; @@ -432,9 +432,11 @@ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ + struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ refcount_t ref; + atomic_t active; /* Active count for service conns */ struct rcu_head rcu; struct list_head cache_link; @@ -455,6 +457,7 @@ struct rxrpc_connection { struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ + struct work_struct destructor; /* In-process-context destroyer */ struct rxrpc_bundle *bundle; /* Client connection bundle */ struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ @@ -897,20 +900,20 @@ void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; -struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); +struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, struct sk_buff *, struct rxrpc_peer **); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); -void rxrpc_kill_connection(struct rxrpc_connection *); -bool rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_kill_client_conn(struct rxrpc_connection *); +void rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, enum rxrpc_conn_trace); -void rxrpc_put_service_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_put_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); @@ -924,18 +927,6 @@ static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) return !rxrpc_conn_is_client(conn); } -static inline void rxrpc_put_connection(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - if (!conn) - return; - - if (rxrpc_conn_is_client(conn)) - rxrpc_put_client_conn(conn, why); - else - rxrpc_put_service_conn(conn, why); -} - static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, unsigned long expire_at) { diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index dd4ca4bee77f..8d106b626aa3 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -308,6 +308,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_new_incoming_connection(rx, conn, sec, skb); } else { rxrpc_get_connection(conn, rxrpc_conn_get_service_conn); + atomic_inc(&conn->active); } /* And now we can allocate and set up a new call */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 34ff6fa85c32..9485a3d18f29 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -51,7 +51,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp) { - struct rxrpc_net *rxnet = conn->local->rxnet; + struct rxrpc_net *rxnet = conn->rxnet; int id; _enter(""); @@ -179,7 +179,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) _enter(""); - conn = rxrpc_alloc_connection(gfp); + conn = rxrpc_alloc_connection(rxnet, gfp); if (!conn) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); @@ -243,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) if (!conn) goto dont_reuse; - rxnet = conn->local->rxnet; + rxnet = conn->rxnet; if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; @@ -970,7 +970,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) /* * Clean up a dead client connection. */ -static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) +void rxrpc_kill_client_conn(struct rxrpc_connection *conn) { struct rxrpc_local *local = conn->local; struct rxrpc_net *rxnet = local->rxnet; @@ -981,23 +981,6 @@ static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) atomic_dec(&rxnet->nr_client_conns); rxrpc_put_client_connection_id(conn); - rxrpc_kill_connection(conn); -} - -/* - * Clean up a dead client connections. - */ -void rxrpc_put_client_conn(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - unsigned int debug_id = conn->debug_id; - bool dead; - int r; - - dead = __refcount_dec_and_test(&conn->ref, &r); - trace_rxrpc_conn(debug_id, r - 1, why); - if (dead) - rxrpc_kill_client_conn(conn); } /* @@ -1023,7 +1006,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work) } /* Don't double up on the discarding */ - if (!spin_trylock(&rxnet->client_conn_discard_lock)) { + if (!mutex_trylock(&rxnet->client_conn_discard_lock)) { _leave(" [already]"); return; } @@ -1061,6 +1044,7 @@ next: goto not_yet_expired; } + atomic_dec(&conn->active); trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_del_init(&conn->cache_link); @@ -1087,7 +1071,7 @@ not_yet_expired: out: spin_unlock(&rxnet->client_conn_cache_lock); - spin_unlock(&rxnet->client_conn_discard_lock); + mutex_unlock(&rxnet->client_conn_discard_lock); _leave(""); } @@ -1127,6 +1111,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, cache_link) { if (conn->local == local) { + atomic_dec(&conn->active); trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_move(&conn->cache_link, &graveyard); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 49d885f73fa5..23a74e35052d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -478,8 +478,4 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_do_process_connection(conn); rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } - - rxrpc_put_connection(conn, rxrpc_conn_put_work); - _leave(""); - return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index f7c271a740ed..c2e05ea29f12 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -19,7 +19,9 @@ unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60; unsigned int __read_mostly rxrpc_closed_conn_expiry = 10; -static void rxrpc_destroy_connection(struct rcu_head *); +static void rxrpc_clean_up_connection(struct work_struct *work); +static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, + unsigned long reap_at); static void rxrpc_connection_timer(struct timer_list *timer) { @@ -32,7 +34,8 @@ static void rxrpc_connection_timer(struct timer_list *timer) /* * allocate a new connection */ -struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) +struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, + gfp_t gfp) { struct rxrpc_connection *conn; @@ -42,10 +45,12 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) if (conn) { INIT_LIST_HEAD(&conn->cache_link); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); - INIT_WORK(&conn->processor, &rxrpc_process_connection); + INIT_WORK(&conn->processor, rxrpc_process_connection); + INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); skb_queue_head_init(&conn->rx_queue); + conn->rxnet = rxnet; conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); @@ -224,53 +229,20 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; -} - -/* - * Kill off a connection. - */ -void rxrpc_kill_connection(struct rxrpc_connection *conn) -{ - struct rxrpc_net *rxnet = conn->local->rxnet; - - ASSERT(!rcu_access_pointer(conn->channels[0].call) && - !rcu_access_pointer(conn->channels[1].call) && - !rcu_access_pointer(conn->channels[2].call) && - !rcu_access_pointer(conn->channels[3].call)); - ASSERT(list_empty(&conn->cache_link)); - - write_lock(&rxnet->conn_lock); - list_del_init(&conn->proc_link); - write_unlock(&rxnet->conn_lock); - - /* Drain the Rx queue. Note that even though we've unpublished, an - * incoming packet could still be being added to our Rx queue, so we - * will need to drain it again in the RCU cleanup handler. - */ - rxrpc_purge_queue(&conn->rx_queue); - - /* Leave final destruction to RCU. The connection processor work item - * must carry a ref on the connection to prevent us getting here whilst - * it is queued or running. - */ - call_rcu(&conn->rcu, rxrpc_destroy_connection); + if (atomic_dec_and_test(&conn->active)) + rxrpc_set_service_reap_timer(conn->rxnet, + jiffies + rxrpc_connection_expiry); } /* * Queue a connection's work processor, getting a ref to pass to the work * queue. */ -bool rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) +void rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { - int r; - - if (!__refcount_inc_not_zero(&conn->ref, &r)) - return false; - if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn->debug_id, why, r + 1); - else - rxrpc_put_connection(conn, rxrpc_conn_put_already_queued); - return true; + if (atomic_read(&conn->active) >= 0 && + rxrpc_queue_work(&conn->processor)) + rxrpc_see_connection(conn, why); } /* @@ -327,51 +299,96 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, timer_reduce(&rxnet->service_conn_reap_timer, reap_at); } -/* - * Release a service connection - */ -void rxrpc_put_service_conn(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - unsigned int debug_id = conn->debug_id; - int r; - - __refcount_dec(&conn->ref, &r); - trace_rxrpc_conn(debug_id, r - 1, why); - if (r - 1 == 1) - rxrpc_set_service_reap_timer(conn->local->rxnet, - jiffies + rxrpc_connection_expiry); -} - /* * destroy a virtual connection */ -static void rxrpc_destroy_connection(struct rcu_head *rcu) +static void rxrpc_rcu_free_connection(struct rcu_head *rcu) { struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); + struct rxrpc_net *rxnet = conn->rxnet; _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), rxrpc_conn_free); + kfree(conn); - ASSERTCMP(refcount_read(&conn->ref), ==, 0); + if (atomic_dec_and_test(&rxnet->nr_conns)) + wake_up_var(&rxnet->nr_conns); +} + +/* + * Clean up a dead connection. + */ +static void rxrpc_clean_up_connection(struct work_struct *work) +{ + struct rxrpc_connection *conn = + container_of(work, struct rxrpc_connection, destructor); + struct rxrpc_net *rxnet = conn->rxnet; + + ASSERT(!rcu_access_pointer(conn->channels[0].call) && + !rcu_access_pointer(conn->channels[1].call) && + !rcu_access_pointer(conn->channels[2].call) && + !rcu_access_pointer(conn->channels[3].call)); + ASSERT(list_empty(&conn->cache_link)); del_timer_sync(&conn->timer); + cancel_work_sync(&conn->processor); /* Processing may restart the timer */ + del_timer_sync(&conn->timer); + + write_lock(&rxnet->conn_lock); + list_del_init(&conn->proc_link); + write_unlock(&rxnet->conn_lock); + rxrpc_purge_queue(&conn->rx_queue); + rxrpc_kill_client_conn(conn); + conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); - - if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) - wake_up_var(&conn->local->rxnet->nr_conns); rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); - kfree(conn); - _leave(""); + /* Drain the Rx queue. Note that even though we've unpublished, an + * incoming packet could still be being added to our Rx queue, so we + * will need to drain it again in the RCU cleanup handler. + */ + rxrpc_purge_queue(&conn->rx_queue); + + call_rcu(&conn->rcu, rxrpc_rcu_free_connection); +} + +/* + * Drop a ref on a connection. + */ +void rxrpc_put_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) +{ + unsigned int debug_id; + bool dead; + int r; + + if (!conn) + return; + + debug_id = conn->debug_id; + dead = __refcount_dec_and_test(&conn->ref, &r); + trace_rxrpc_conn(debug_id, r - 1, why); + if (dead) { + del_timer(&conn->timer); + cancel_work(&conn->processor); + + if (in_softirq() || work_busy(&conn->processor) || + timer_pending(&conn->timer)) + /* Can't use the rxrpc workqueue as we need to cancel/flush + * something that may be running/waiting there. + */ + schedule_work(&conn->destructor); + else + rxrpc_clean_up_connection(&conn->destructor); + } } /* @@ -383,6 +400,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) struct rxrpc_net *rxnet = container_of(work, struct rxrpc_net, service_conn_reaper); unsigned long expire_at, earliest, idle_timestamp, now; + int active; LIST_HEAD(graveyard); @@ -393,8 +411,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { - ASSERTCMP(refcount_read(&conn->ref), >, 0); - if (likely(refcount_read(&conn->ref) > 1)) + ASSERTCMP(atomic_read(&conn->active), >=, 0); + if (likely(atomic_read(&conn->active) > 0)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; @@ -405,8 +423,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (conn->local->service_closed) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; - _debug("reap CONN %d { u=%d,t=%ld }", - conn->debug_id, refcount_read(&conn->ref), + _debug("reap CONN %d { a=%d,t=%ld }", + conn->debug_id, atomic_read(&conn->active), (long)expire_at - (long)now); if (time_before(now, expire_at)) { @@ -416,10 +434,11 @@ void rxrpc_service_connection_reaper(struct work_struct *work) } } - /* The usage count sits at 1 whilst the object is unused on the - * list; we reduce that to 0 to make the object unavailable. + /* The activity count sits at 0 whilst the conn is unused on + * the list; we reduce that to -1 to make the conn unavailable. */ - if (!refcount_dec_if_one(&conn->ref)) + active = 0; + if (!atomic_try_cmpxchg(&conn->active, &active, -1)) continue; rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); @@ -443,8 +462,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) link); list_del_init(&conn->link); - ASSERTCMP(refcount_read(&conn->ref), ==, 0); - rxrpc_kill_connection(conn); + ASSERTCMP(atomic_read(&conn->active), ==, -1); + rxrpc_put_connection(conn, rxrpc_conn_put_service_reaped); } _leave(""); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 2c44d67b43dc..b5ae7c753fc3 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -125,7 +125,7 @@ replace_old_connection: struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxnet, gfp_t gfp) { - struct rxrpc_connection *conn = rxrpc_alloc_connection(gfp); + struct rxrpc_connection *conn = rxrpc_alloc_connection(rxnet, gfp); if (conn) { /* We maintain an extra ref on the connection whilst it is on @@ -181,6 +181,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id == rx->service_upgrade.from) conn->service_id = rx->service_upgrade.to; + atomic_set(&conn->active, 1); + /* Make the connection a target for incoming packets. */ rxrpc_publish_service_conn(conn->peer, conn); } diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 84242c0e467c..5905530e2f33 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -65,7 +65,7 @@ static __net_init int rxrpc_init_net(struct net *net) atomic_set(&rxnet->nr_client_conns, 0); rxnet->kill_all_client_conns = false; spin_lock_init(&rxnet->client_conn_cache_lock); - spin_lock_init(&rxnet->client_conn_discard_lock); + mutex_init(&rxnet->client_conn_discard_lock); INIT_LIST_HEAD(&rxnet->idle_client_conns); INIT_WORK(&rxnet->client_conn_reaper, rxrpc_discard_expired_client_conns); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index bb2edf6db896..d3a6d24cf871 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -159,7 +159,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " SvID ConnID End Use State Key " + " SvID ConnID End Ref Act State Key " " Serial ISerial CallId0 CallId1 CallId2 CallId3\n" ); return 0; @@ -177,7 +177,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &conn->peer->srx.transport); print: seq_printf(seq, - "UDP %-47.47s %-47.47s %4x %08x %s %3u" + "UDP %-47.47s %-47.47s %4x %08x %s %3u %3d" " %s %08x %08x %08x %08x %08x %08x %08x\n", lbuff, rbuff, @@ -185,6 +185,7 @@ print: conn->proto.cid, rxrpc_conn_is_service(conn) ? "Svc" : "Clt", refcount_read(&conn->ref), + atomic_read(&conn->active), rxrpc_conn_states[conn->state], key_serial(conn->key), atomic_read(&conn->serial), -- cgit v1.2.3 From 15f661dc95daec9b38e8e4cc931c95afe0ae0cef Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 10 Oct 2022 15:51:39 +0100 Subject: rxrpc: Implement a mechanism to send an event notification to a call Provide a means by which an event notification can be sent to a call such that the I/O thread can process it rather than it being done in a separate workqueue. This will allow a lot of locking to be removed. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 52 ++++++++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 5 ++++- net/rxrpc/call_object.c | 24 ++++++++++++++++++++ net/rxrpc/input.c | 3 +-- net/rxrpc/io_thread.c | 20 +++++++++++++++-- net/rxrpc/local_object.c | 1 + 6 files changed, 100 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 44a9be9836f9..0b12d96c7921 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -16,6 +16,13 @@ /* * Declare tracing information enums and their string mappings for display. */ +#define rxrpc_call_poke_traces \ + EM(rxrpc_call_poke_error, "Error") \ + EM(rxrpc_call_poke_idle, "Idle") \ + EM(rxrpc_call_poke_start, "Start") \ + EM(rxrpc_call_poke_timer, "Timer") \ + E_(rxrpc_call_poke_timer_now, "Timer-now") + #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ @@ -150,6 +157,7 @@ EM(rxrpc_call_get_input, "GET input ") \ EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ EM(rxrpc_call_get_notify_socket, "GET notify ") \ + EM(rxrpc_call_get_poke, "GET poke ") \ EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ @@ -160,6 +168,7 @@ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ + EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -378,6 +387,7 @@ #define E_(a, b) a enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); +enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); @@ -408,6 +418,7 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #define E_(a, b) TRACE_DEFINE_ENUM(a); rxrpc_bundle_traces; +rxrpc_call_poke_traces; rxrpc_call_traces; rxrpc_client_traces; rxrpc_congest_changes; @@ -1747,6 +1758,47 @@ TRACE_EVENT(rxrpc_txbuf, __entry->ref) ); +TRACE_EVENT(rxrpc_poke_call, + TP_PROTO(struct rxrpc_call *call, bool busy, + enum rxrpc_call_poke_trace what), + + TP_ARGS(call, busy, what), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + __field(bool, busy ) + __field(enum rxrpc_call_poke_trace, what ) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + __entry->busy = busy; + __entry->what = what; + ), + + TP_printk("c=%08x %s%s", + __entry->call_debug_id, + __print_symbolic(__entry->what, rxrpc_call_poke_traces), + __entry->busy ? "!" : "") + ); + +TRACE_EVENT(rxrpc_call_poked, + TP_PROTO(struct rxrpc_call *call), + + TP_ARGS(call), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + ), + + TP_printk("c=%08x", + __entry->call_debug_id) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 654e9dab107c..a80655fa9dfb 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -292,6 +292,7 @@ struct rxrpc_local { struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct sk_buff_head rx_queue; /* Received packets */ + struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ spinlock_t lock; /* access lock */ @@ -616,6 +617,7 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ + struct list_head attend_link; /* Link in local->call_attend_q */ struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ @@ -843,6 +845,7 @@ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern struct kmem_cache *rxrpc_call_jar; +void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what); struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, @@ -951,7 +954,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); +void rxrpc_input_call_event(struct rxrpc_call *, struct sk_buff *); void rxrpc_input_implicit_end_call(struct rxrpc_sock *, struct rxrpc_connection *, struct rxrpc_call *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f6d1b3a6f8c6..997641e3d1c8 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -45,6 +45,29 @@ static struct semaphore rxrpc_call_limiter = static struct semaphore rxrpc_kernel_call_limiter = __SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000); +void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) +{ + struct rxrpc_local *local; + struct rxrpc_peer *peer = call->peer; + bool busy; + + if (WARN_ON_ONCE(!peer)) + return; + local = peer->local; + + if (call->state < RXRPC_CALL_COMPLETE) { + spin_lock_bh(&local->lock); + busy = !list_empty(&call->attend_link); + trace_rxrpc_poke_call(call, busy, what); + if (!busy) { + rxrpc_get_call(call, rxrpc_call_get_poke); + list_add_tail(&call->attend_link, &local->call_attend_q); + } + spin_unlock_bh(&local->lock); + rxrpc_wake_up_io_thread(local); + } +} + static void rxrpc_call_timer_expired(struct timer_list *t) { struct rxrpc_call *call = from_timer(call, t, timer); @@ -137,6 +160,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->attend_link); INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 13c52145a926..036f02371051 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1017,8 +1017,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) /* * Process an incoming call packet. */ -void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb) +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 416c6101cf78..cc249bc6b8cd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -366,7 +366,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Process a call packet; this either discards or passes on the ref * elsewhere. */ - rxrpc_input_call_packet(call, skb); + rxrpc_input_call_event(call, skb); goto out; discard: @@ -413,6 +413,7 @@ int rxrpc_io_thread(void *data) { struct sk_buff_head rx_queue; struct rxrpc_local *local = data; + struct rxrpc_call *call; struct sk_buff *skb; skb_queue_head_init(&rx_queue); @@ -422,6 +423,20 @@ int rxrpc_io_thread(void *data) for (;;) { rxrpc_inc_stat(local->rxnet, stat_io_loop); + /* Deal with calls that want immediate attention. */ + if ((call = list_first_entry_or_null(&local->call_attend_q, + struct rxrpc_call, + attend_link))) { + spin_lock_bh(&local->lock); + list_del_init(&call->attend_link); + spin_unlock_bh(&local->lock); + + trace_rxrpc_call_poked(call); + rxrpc_input_call_event(call, NULL); + rxrpc_put_call(call, rxrpc_call_put_poke); + continue; + } + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { @@ -450,7 +465,8 @@ int rxrpc_io_thread(void *data) } set_current_state(TASK_INTERRUPTIBLE); - if (!skb_queue_empty(&local->rx_queue)) { + if (!skb_queue_empty(&local->rx_queue) || + !list_empty(&local->call_attend_q)) { __set_current_state(TASK_RUNNING); continue; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 6b4d77219f36..03f491cc23ef 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -104,6 +104,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); skb_queue_head_init(&local->rx_queue); + INIT_LIST_HEAD(&local->call_attend_q); local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); spin_lock_init(&local->lock); -- cgit v1.2.3 From f3441d4125fc98995858550a5521b8d7daf0504a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 21:58:36 +0100 Subject: rxrpc: Copy client call parameters into rxrpc_call earlier Copy client call parameters into rxrpc_call earlier so that that can be used to convey them to the connection code - which can then be offloaded to the I/O thread. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +++ net/rxrpc/ar-internal.h | 7 ++++++- net/rxrpc/call_accept.c | 2 ++ net/rxrpc/call_object.c | 50 +++++++++++++++++++++++++++----------------- net/rxrpc/conn_client.c | 2 +- net/rxrpc/io_thread.c | 4 ++-- net/rxrpc/output.c | 2 +- net/rxrpc/proc.c | 25 +++++++--------------- net/rxrpc/recvmsg.c | 8 +++---- net/rxrpc/security.c | 30 ++++++++++++++++++++++++++ net/rxrpc/txbuf.c | 2 +- 11 files changed, 87 insertions(+), 48 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 0b12d96c7921..8bd48358f757 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -52,6 +52,7 @@ #define rxrpc_local_traces \ EM(rxrpc_local_free, "FREE ") \ + EM(rxrpc_local_get_call, "GET call ") \ EM(rxrpc_local_get_client_conn, "GET conn-cln") \ EM(rxrpc_local_get_for_use, "GET for-use ") \ EM(rxrpc_local_get_peer, "GET peer ") \ @@ -61,6 +62,7 @@ EM(rxrpc_local_processing, "PROCESSING ") \ EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ EM(rxrpc_local_put_bind, "PUT bind ") \ + EM(rxrpc_local_put_call, "PUT call ") \ EM(rxrpc_local_put_for_use, "PUT for-use ") \ EM(rxrpc_local_put_kill_conn, "PUT conn-kil") \ EM(rxrpc_local_put_peer, "PUT peer ") \ @@ -166,6 +168,7 @@ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ + EM(rxrpc_call_put_discard_error, "PUT disc-err") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index a80655fa9dfb..3bd6a5eb2fb7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -530,6 +530,7 @@ enum rxrpc_call_flag { RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ + RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ }; /* @@ -592,10 +593,13 @@ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ + struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ + struct key *key; /* Security details */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ + struct sockaddr_rxrpc dest_srx; /* Destination address */ unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ @@ -631,11 +635,11 @@ struct rxrpc_call { enum rxrpc_call_state state; /* current state of call */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; - u16 service_id; /* service ID */ u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ + u32 security_level; /* Security level selected */ int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ @@ -1147,6 +1151,7 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); const struct rxrpc_security *rxrpc_security_lookup(u8); void rxrpc_exit_security(void); +int rxrpc_init_client_call_security(struct rxrpc_call *); int rxrpc_init_client_conn_security(struct rxrpc_connection *); const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *, struct sk_buff *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 8d106b626aa3..8bc327aa2beb 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -318,10 +318,12 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); rxrpc_see_call(call, rxrpc_call_see_accept); + call->local = rxrpc_get_local(conn->local, rxrpc_local_get_call); call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_accept); + call->dest_srx = peer->srx; call->cong_ssthresh = call->peer->cong_ssthresh; call->tx_last_sent = ktime_get_real(); return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 997641e3d1c8..2622d06bb0d6 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -47,14 +47,9 @@ static struct semaphore rxrpc_kernel_call_limiter = void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) { - struct rxrpc_local *local; - struct rxrpc_peer *peer = call->peer; + struct rxrpc_local *local = call->local; bool busy; - if (WARN_ON_ONCE(!peer)) - return; - local = peer->local; - if (call->state < RXRPC_CALL_COMPLETE) { spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); @@ -200,22 +195,45 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, */ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, struct sockaddr_rxrpc *srx, + struct rxrpc_conn_parameters *cp, + struct rxrpc_call_params *p, gfp_t gfp, unsigned int debug_id) { struct rxrpc_call *call; ktime_t now; + int ret; _enter(""); call = rxrpc_alloc_call(rx, gfp, debug_id); if (!call) return ERR_PTR(-ENOMEM); - call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; - call->service_id = srx->srx_service; now = ktime_get_real(); - call->acks_latest_ts = now; - call->cong_tstamp = now; + call->acks_latest_ts = now; + call->cong_tstamp = now; + call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; + call->dest_srx = *srx; + call->interruptibility = p->interruptibility; + call->tx_total_len = p->tx_total_len; + call->key = key_get(cp->key); + call->local = rxrpc_get_local(cp->local, rxrpc_local_get_call); + if (p->kernel) + __set_bit(RXRPC_CALL_KERNEL, &call->flags); + if (cp->upgrade) + __set_bit(RXRPC_CALL_UPGRADE, &call->flags); + if (cp->exclusive) + __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); + + ret = rxrpc_init_client_call_security(call); + if (ret < 0) { + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_put_call(call, rxrpc_call_put_discard_error); + return ERR_PTR(ret); + } + + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + p->user_call_ID, rxrpc_call_new_client); _leave(" = %p", call); return call; @@ -295,7 +313,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return ERR_PTR(-ERESTARTSYS); } - call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); + call = rxrpc_alloc_client_call(rx, srx, cp, p, gfp, debug_id); if (IS_ERR(call)) { release_sock(&rx->sk); up(limiter); @@ -303,13 +321,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } - call->interruptibility = p->interruptibility; - call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), - p->user_call_ID, rxrpc_call_new_client); - if (p->kernel) - __set_bit(RXRPC_CALL_KERNEL, &call->flags); - /* We need to protect a partially set up call against the user as we * will be acting outside the socket lock. */ @@ -413,7 +424,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, rcu_assign_pointer(call->socket, rx); call->call_id = sp->hdr.callNumber; - call->service_id = sp->hdr.serviceId; + call->dest_srx.srx_service = sp->hdr.serviceId; call->cid = sp->hdr.cid; call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; @@ -639,6 +650,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); + rxrpc_put_local(call->local, rxrpc_local_put_call); call_rcu(&call->rcu, rxrpc_rcu_free_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9485a3d18f29..ab3dd22fadc0 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -553,7 +553,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, call->call_id = call_id; call->security = conn->security; call->security_ix = conn->security_ix; - call->service_id = conn->service_id; + call->dest_srx.srx_service = conn->service_id; trace_rxrpc_connect_call(call); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index cc249bc6b8cd..2119941b6d6c 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -343,8 +343,8 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) } if (call) { - if (sp->hdr.serviceId != call->service_id) - call->service_id = sp->hdr.serviceId; + if (sp->hdr.serviceId != call->dest_srx.srx_service) + call->dest_srx.srx_service = sp->hdr.serviceId; if ((int)sp->hdr.serial - (int)call->rx_serial > 0) call->rx_serial = sp->hdr.serial; if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 131c7a76fb06..e2ce7dadbb7a 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -357,7 +357,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) pkt.whdr.userStatus = 0; pkt.whdr.securityIndex = call->security_ix; pkt.whdr._rsvd = 0; - pkt.whdr.serviceId = htons(call->service_id); + pkt.whdr.serviceId = htons(call->dest_srx.srx_service); pkt.abort_code = htonl(call->abort_code); iov[0].iov_base = &pkt; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 35d5b43c677e..5af7c8ee4b1a 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -49,8 +49,6 @@ static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) static int rxrpc_call_seq_show(struct seq_file *seq, void *v) { struct rxrpc_local *local; - struct rxrpc_sock *rx; - struct rxrpc_peer *peer; struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; @@ -69,22 +67,13 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call = list_entry(v, struct rxrpc_call, link); - rx = rcu_dereference(call->socket); - if (rx) { - local = READ_ONCE(rx->local); - if (local) - sprintf(lbuff, "%pISpc", &local->srx.transport); - else - strcpy(lbuff, "no_local"); - } else { - strcpy(lbuff, "no_socket"); - } - - peer = call->peer; - if (peer) - sprintf(rbuff, "%pISpc", &peer->srx.transport); + local = call->local; + if (local) + sprintf(lbuff, "%pISpc", &local->srx.transport); else - strcpy(rbuff, "no_connection"); + strcpy(lbuff, "no_local"); + + sprintf(rbuff, "%pISpc", &call->dest_srx.transport); if (call->state != RXRPC_CALL_SERVER_PREALLOC) { timeout = READ_ONCE(call->expect_rx_by); @@ -98,7 +87,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", lbuff, rbuff, - call->service_id, + call->dest_srx.srx_service, call->cid, call->call_id, rxrpc_is_service_call(call) ? "Svc" : "Clt", diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index bfac9e09347e..5df7f468abed 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -490,11 +490,9 @@ try_again: } if (msg->msg_name && call->peer) { - struct sockaddr_rxrpc *srx = msg->msg_name; - size_t len = sizeof(call->peer->srx); + size_t len = sizeof(call->dest_srx); - memcpy(msg->msg_name, &call->peer->srx, len); - srx->srx_service = call->service_id; + memcpy(msg->msg_name, &call->dest_srx, len); msg->msg_namelen = len; } @@ -639,7 +637,7 @@ read_phase_complete: out: rxrpc_transmit_ack_packets(call->peer->local); if (_service) - *_service = call->service_id; + *_service = call->dest_srx.srx_service; mutex_unlock(&call->user_mutex); _leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort); return ret; diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index e6ddac9b3732..209f2c25a0da 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -62,6 +62,36 @@ const struct rxrpc_security *rxrpc_security_lookup(u8 security_index) return rxrpc_security_types[security_index]; } +/* + * Initialise the security on a client call. + */ +int rxrpc_init_client_call_security(struct rxrpc_call *call) +{ + const struct rxrpc_security *sec; + struct rxrpc_key_token *token; + struct key *key = call->key; + int ret; + + if (!key) + return 0; + + ret = key_validate(key); + if (ret < 0) + return ret; + + for (token = key->payload.data[0]; token; token = token->next) { + sec = rxrpc_security_lookup(token->security_index); + if (sec) + goto found; + } + return -EKEYREJECTED; + +found: + call->security = sec; + _leave(" = 0"); + return 0; +} + /* * initialise the security on a client connection */ diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index f93dc666a3a0..90ff00c340cd 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -44,7 +44,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->wire.userStatus = 0; txb->wire.securityIndex = call->security_ix; txb->wire._rsvd = 0; - txb->wire.serviceId = htons(call->service_id); + txb->wire.serviceId = htons(call->dest_srx.srx_service); trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, -- cgit v1.2.3 From cf37b5987508878647161ec3cdba0bb00a1b607a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 31 Mar 2022 23:55:08 +0100 Subject: rxrpc: Move DATA transmission into call processor work item Move DATA transmission into the call processor work item. In a future patch, this will be called from the I/O thread rather than being itsown work item. This will allow DATA transmission to be driven directly by incoming ACKs, pokes and timers as those are processed. The Tx queue is also split: The queue of packets prepared by sendmsg is now places in call->tx_sendmsg and the packet dispatcher decants the packets into call->tx_buffer as space becomes available in the transmission window. This allows sendmsg to run ahead of the available space to try and prevent an underflow in transmission. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 6 +++- net/rxrpc/ar-internal.h | 5 ++- net/rxrpc/call_event.c | 83 ++++++++++++++++++++++++++++++++++++++++---- net/rxrpc/call_object.c | 6 ++++ net/rxrpc/output.c | 48 +++++++++++++++++++++++++ net/rxrpc/sendmsg.c | 83 +++++++------------------------------------- net/rxrpc/txbuf.c | 10 ++++-- 7 files changed, 161 insertions(+), 80 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 8bd48358f757..c3043fbea0e6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -183,6 +183,7 @@ EM(rxrpc_call_queue_requeue, "QUE requeue ") \ EM(rxrpc_call_queue_resend, "QUE resend ") \ EM(rxrpc_call_queue_timer, "QUE timer ") \ + EM(rxrpc_call_queue_tx_data, "QUE tx-data ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ @@ -738,6 +739,7 @@ TRACE_EVENT(rxrpc_txqueue, __field(rxrpc_seq_t, acks_hard_ack ) __field(rxrpc_seq_t, tx_bottom ) __field(rxrpc_seq_t, tx_top ) + __field(rxrpc_seq_t, tx_prepared ) __field(int, tx_winsize ) ), @@ -747,16 +749,18 @@ TRACE_EVENT(rxrpc_txqueue, __entry->acks_hard_ack = call->acks_hard_ack; __entry->tx_bottom = call->tx_bottom; __entry->tx_top = call->tx_top; + __entry->tx_prepared = call->tx_prepared; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u", + TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u/%u", __entry->call, __print_symbolic(__entry->why, rxrpc_txqueue_traces), __entry->tx_bottom, __entry->acks_hard_ack, __entry->tx_top - __entry->tx_bottom, __entry->tx_top - __entry->acks_hard_ack, + __entry->tx_prepared - __entry->tx_bottom, __entry->tx_winsize) ); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 3bd6a5eb2fb7..6af7298af39b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -646,9 +646,11 @@ struct rxrpc_call { /* Transmitted data tracking. */ spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_sendmsg; /* Sendmsg prepared packets */ struct list_head tx_buffer; /* Buffer of transmissible packets */ rxrpc_seq_t tx_bottom; /* First packet in buffer */ rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ + rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ @@ -766,7 +768,7 @@ struct rxrpc_send_params { */ struct rxrpc_txbuf { struct rcu_head rcu; - struct list_head call_link; /* Link in call->tx_queue */ + struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ struct rxrpc_call *call; /* Call to which belongs */ ktime_t last_sent; /* Time at which last transmitted */ @@ -1067,6 +1069,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); +void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); /* * peer_event.c diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 3925b55e2064..c9f835292f7b 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -291,6 +291,72 @@ out: _leave(""); } +static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) +{ + unsigned int winsize = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + rxrpc_seq_t window = call->acks_hard_ack, wtop = window + winsize; + rxrpc_seq_t tx_top = call->tx_top; + int space; + + space = wtop - tx_top; + return space > 0; +} + +/* + * Decant some if the sendmsg prepared queue into the transmission buffer. + */ +static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + + if (rxrpc_is_client_call(call) && + !test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + rxrpc_expose_client_call(call); + + while ((txb = list_first_entry_or_null(&call->tx_sendmsg, + struct rxrpc_txbuf, call_link))) { + spin_lock(&call->tx_lock); + list_del(&txb->call_link); + spin_unlock(&call->tx_lock); + + call->tx_top = txb->seq; + list_add_tail(&txb->call_link, &call->tx_buffer); + + rxrpc_transmit_one(call, txb); + + // TODO: Drain the transmission buffers. Do this somewhere better + if (after(call->acks_hard_ack, call->tx_bottom + 16)) + rxrpc_shrink_call_tx_buffer(call); + + if (!rxrpc_tx_window_has_space(call)) + break; + } +} + +static void rxrpc_transmit_some_data(struct rxrpc_call *call) +{ + switch (call->state) { + case RXRPC_CALL_SERVER_ACK_REQUEST: + if (list_empty(&call->tx_sendmsg)) + return; + fallthrough; + + case RXRPC_CALL_SERVER_SEND_REPLY: + case RXRPC_CALL_SERVER_AWAIT_ACK: + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + if (!rxrpc_tx_window_has_space(call)) + return; + if (list_empty(&call->tx_sendmsg)) + return; + rxrpc_decant_prepared_tx(call); + break; + default: + return; + } +} + /* * Handle retransmission and deferred ACK/abort generation. */ @@ -309,19 +375,22 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + if (call->acks_hard_ack != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + /* Limit the number of times we do this before returning to the manager */ - iterations++; - if (iterations > 5) - goto requeue; + if (!rxrpc_tx_window_has_space(call) || + list_empty(&call->tx_sendmsg)) { + iterations++; + if (iterations > 5) + goto requeue; + } if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; } - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) - rxrpc_shrink_call_tx_buffer(call); - if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); goto out; @@ -387,6 +456,8 @@ recheck_state: set_bit(RXRPC_CALL_EV_RESEND, &call->events); } + rxrpc_transmit_some_data(call); + /* Process events */ if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) { if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 2622d06bb0d6..96a7edd3a842 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -156,6 +156,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); INIT_LIST_HEAD(&call->attend_link); + INIT_LIST_HEAD(&call->tx_sendmsg); INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); @@ -641,6 +642,11 @@ static void rxrpc_destroy_call(struct work_struct *work) del_timer_sync(&call->timer); rxrpc_cleanup_ring(call); + while ((txb = list_first_entry_or_null(&call->tx_sendmsg, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } while ((txb = list_first_entry_or_null(&call->tx_buffer, struct rxrpc_txbuf, call_link))) { list_del(&txb->call_link); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index e2ce7dadbb7a..c8147e50060b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -465,6 +465,14 @@ dont_set_request_ack: trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + + /* Track what we've attempted to transmit at least once so that the + * retransmission algorithm doesn't try to resend what we haven't sent + * yet. However, this can race as we can receive an ACK before we get + * to this point. But, OTOH, if we won't get an ACK mentioning this + * packet unless the far side received it (though it could have + * discarded it anyway and NAK'd it). + */ cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently @@ -712,3 +720,43 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) peer->last_tx_at = ktime_get_seconds(); _leave(""); } + +/* + * Schedule an instant Tx resend. + */ +static inline void rxrpc_instant_resend(struct rxrpc_call *call, + struct rxrpc_txbuf *txb) +{ + if (call->state < RXRPC_CALL_COMPLETE) + kdebug("resend"); +} + +/* + * Transmit one packet. + */ +void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + int ret; + + ret = rxrpc_send_data_packet(call, txb); + if (ret < 0) { + switch (ret) { + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + 0, ret); + break; + default: + _debug("need instant resend %d", ret); + rxrpc_instant_resend(call, txb); + } + } else { + unsigned long now = jiffies; + unsigned long resend_at = now + call->peer->rto_j; + + WRITE_ONCE(call->resend_at, resend_at); + rxrpc_reduce_call_timer(call, resend_at, now, + rxrpc_timer_set_for_send); + } +} diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 76b1e2e89c1e..11af37275d5b 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,30 +22,9 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size; - rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); - - /* If we haven't transmitted anything for >1RTT, we should reset the - * congestion management state. - */ - if (ktime_before(ktime_add_us(call->tx_last_sent, - call->peer->srtt_us >> 3), - ktime_get_real())) { - if (RXRPC_TX_SMSS > 2190) - win_size = 2; - else if (RXRPC_TX_SMSS > 1095) - win_size = 3; - else - win_size = 4; - win_size += call->cong_extra; - } else { - win_size = min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); - } - if (_tx_win) - *_tx_win = tx_win; - return call->tx_top - tx_win < win_size; + *_tx_win = call->tx_bottom; + return call->tx_prepared - call->tx_bottom < 256; } /* @@ -66,11 +45,6 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } @@ -107,11 +81,6 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; @@ -137,11 +106,6 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } @@ -207,29 +171,27 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, unsigned long now; rxrpc_seq_t seq = txb->seq; bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); - int ret; rxrpc_inc_stat(call->rxnet, stat_tx_data); - ASSERTCMP(seq, ==, call->tx_top + 1); + ASSERTCMP(txb->seq, ==, call->tx_prepared + 1); /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ txb->last_sent = ktime_get_real(); - /* Add the packet to the call's output buffer */ - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); - spin_lock(&call->tx_lock); - list_add_tail(&txb->call_link, &call->tx_buffer); - call->tx_top = seq; - spin_unlock(&call->tx_lock); - if (last) trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); + /* Add the packet to the call's output buffer */ + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_sendmsg); + call->tx_prepared = seq; + spin_unlock(&call->tx_lock); + if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); write_lock_bh(&call->state_lock); @@ -258,30 +220,11 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, write_unlock_bh(&call->state_lock); } - if (seq == 1 && rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - ret = rxrpc_send_data_packet(call, txb); - if (ret < 0) { - switch (ret) { - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - 0, ret); - goto out; - } - } else { - unsigned long now = jiffies; - unsigned long resend_at = now + call->peer->rto_j; - WRITE_ONCE(call->resend_at, resend_at); - rxrpc_reduce_call_timer(call, resend_at, now, - rxrpc_timer_set_for_send); - } - -out: - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); + /* Stick the packet on the crypto queue or the transmission queue as + * appropriate. + */ + rxrpc_queue_call(call, rxrpc_call_queue_tx_data); } /* diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 90ff00c340cd..a5054389dfbb 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -34,7 +34,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->offset = 0; txb->flags = 0; txb->ack_why = 0; - txb->seq = call->tx_top + 1; + txb->seq = call->tx_prepared + 1; txb->wire.epoch = htonl(call->conn->proto.epoch); txb->wire.cid = htonl(call->cid); txb->wire.callNumber = htonl(call->call_id); @@ -107,6 +107,7 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) { struct rxrpc_txbuf *txb; rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + bool wake = false; _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); @@ -123,7 +124,7 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) if (txb->seq != call->tx_bottom + 1) rxrpc_see_txbuf(txb, rxrpc_txbuf_see_out_of_step); ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); - call->tx_bottom++; + smp_store_release(&call->tx_bottom, call->tx_bottom + 1); list_del_rcu(&txb->call_link); trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); @@ -131,7 +132,12 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) spin_unlock(&call->tx_lock); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + if (after(call->acks_hard_ack, call->tx_bottom + 128)) + wake = true; } spin_unlock(&call->tx_lock); + + if (wake) + wake_up(&call->waitq); } -- cgit v1.2.3 From 2d1faf7a0ca3c0b327cf064c80e4e775532c9319 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2022 15:43:51 +0100 Subject: rxrpc: Simplify skbuff accounting in receive path A received skbuff needs a ref when it gets put on a call data queue or conn packet queue, and rxrpc_input_packet() and co. jump through a lot of hoops to avoid double-dropping the skbuff ref so that we can avoid getting a ref when we queue the packet. Change this so that the skbuff ref is unconditionally dropped by the caller of rxrpc_input_packet(). An additional ref is then taken on the packet if it is pushed onto a queue. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +- net/rxrpc/input.c | 45 ++++++++++++++-------------- net/rxrpc/io_thread.c | 70 ++++++++++++++++++++------------------------ 3 files changed, 56 insertions(+), 62 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c3043fbea0e6..82b1327c2ba6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -28,6 +28,8 @@ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ EM(rxrpc_skb_get_ack, "GET ack ") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ + EM(rxrpc_skb_get_local_work, "GET locl-work") \ + EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \ EM(rxrpc_skb_get_to_recvmsg_oos, "GET to-recv-o") \ EM(rxrpc_skb_new_encap_rcv, "NEW encap-rcv") \ @@ -39,7 +41,6 @@ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ EM(rxrpc_skb_put_jumbo_subpacket, "PUT jumbo-sub") \ - EM(rxrpc_skb_put_lose, "PUT lose ") \ EM(rxrpc_skb_put_purge, "PUT purge ") \ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 036f02371051..42addbcf59f9 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -338,7 +338,8 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, /* * Process a DATA packet. */ -static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, + bool *_notify) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct sk_buff *oos; @@ -361,7 +362,7 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && seq + 1 != wtop) { rxrpc_proto_abort("LSN", call, seq); - goto err_free; + return; } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && @@ -369,7 +370,7 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", call->debug_id, seq, window, wtop, wlimit); rxrpc_proto_abort("LSA", call, seq); - goto err_free; + return; } } @@ -402,9 +403,11 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (after(window, wtop)) wtop = window; + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg); + spin_lock(&call->recvmsg_queue.lock); rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); - skb = NULL; + *_notify = true; while ((oos = skb_peek(&call->rx_oos_queue))) { struct rxrpc_skb_priv *osp = rxrpc_skb(oos); @@ -456,16 +459,17 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_skb_priv *osp = rxrpc_skb(oos); if (after(osp->hdr.seq, seq)) { + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); __skb_queue_before(&call->rx_oos_queue, oos, skb); goto oos_queued; } } + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); __skb_queue_tail(&call->rx_oos_queue, skb); oos_queued: trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, sp->hdr.serial, sp->hdr.seq); - skb = NULL; } send_ack: @@ -483,9 +487,6 @@ send_ack: else rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_input_data); - -err_free: - rxrpc_free_skb(skb, rxrpc_skb_put_input); } /* @@ -498,6 +499,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb struct sk_buff *jskb; unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len - offset; + bool notify = false; while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { if (len < RXRPC_JUMBO_SUBPKTLEN) @@ -517,7 +519,8 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb jsp = rxrpc_skb(jskb); jsp->offset = offset; jsp->len = RXRPC_JUMBO_DATALEN; - rxrpc_input_data_one(call, jskb); + rxrpc_input_data_one(call, jskb, ¬ify); + rxrpc_free_skb(jskb, rxrpc_skb_put_jumbo_subpacket); sp->hdr.flags = jhdr.flags; sp->hdr._rsvd = ntohs(jhdr._rsvd); @@ -529,7 +532,11 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb sp->offset = offset; sp->len = len; - rxrpc_input_data_one(call, skb); + rxrpc_input_data_one(call, skb, ¬ify); + if (notify) { + trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); + rxrpc_notify_socket(call); + } return true; protocol_error: @@ -552,10 +559,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) skb->len, seq0); state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) { - rxrpc_free_skb(skb, rxrpc_skb_put_input); + if (state >= RXRPC_CALL_COMPLETE) return; - } /* Unshare the packet so that it can be modified for in-place * decryption. @@ -605,7 +610,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); - rxrpc_free_skb(skb, rxrpc_skb_put_input); _leave(" [queued]"); } @@ -797,7 +801,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_ackinfo info; - struct sk_buff *skb_old = NULL, *skb_put = skb; + struct sk_buff *skb_old = NULL; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -963,6 +967,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } + rxrpc_get_skb(skb, rxrpc_skb_get_ack); spin_lock(&call->acks_ack_lock); skb_old = call->acks_soft_tbl; call->acks_soft_tbl = skb; @@ -970,7 +975,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); - skb_put = NULL; } else if (call->acks_soft_tbl) { spin_lock(&call->acks_ack_lock); skb_old = call->acks_soft_tbl; @@ -986,7 +990,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); out: - rxrpc_free_skb(skb_put, rxrpc_skb_put_input); rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } @@ -1037,11 +1040,11 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: rxrpc_input_data(call, skb); - goto no_free; + break; case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - goto no_free; + break; case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets from the server; the retry and @@ -1061,10 +1064,6 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) default: break; } - - rxrpc_free_skb(skb, rxrpc_skb_put_input); -no_free: - _leave(""); } /* diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 2119941b6d6c..91b8ba5b90db 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -72,6 +72,7 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, { _enter("%p,%p", conn, skb); + rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); skb_queue_tail(&conn->rx_queue, skb); rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); } @@ -86,10 +87,9 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, _enter("%p,%p", local, skb); if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { + rxrpc_get_skb(skb, rxrpc_skb_get_local_work); skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -99,10 +99,9 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { + rxrpc_get_skb(skb, rxrpc_skb_get_reject_work); skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -153,7 +152,7 @@ static bool rxrpc_extract_abort(struct sk_buff *skb) /* * Process packets received on the local endpoint */ -static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) +static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct rxrpc_channel *chan; @@ -161,6 +160,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; + struct sk_buff *skb = *_skb; unsigned int channel; if (skb->tstamp == 0) @@ -181,7 +181,6 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_put_lose); return 0; } } @@ -193,13 +192,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) - goto discard; + return 0; rxrpc_post_packet_to_local(local, skb); - goto out; + return 0; case RXRPC_PACKET_TYPE_BUSY: if (rxrpc_to_server(sp)) - goto discard; + return 0; fallthrough; case RXRPC_PACKET_TYPE_ACK: case RXRPC_PACKET_TYPE_ACKALL: @@ -208,7 +207,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) break; case RXRPC_PACKET_TYPE_ABORT: if (!rxrpc_extract_abort(skb)) - return true; /* Just discard if malformed */ + return 0; /* Just discard if malformed */ break; case RXRPC_PACKET_TYPE_DATA: @@ -220,15 +219,16 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) * decryption. */ if (sp->hdr.securityIndex != 0) { - struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); - if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); - goto out; + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) { + rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem); + *_skb = NULL; + return 0; } - if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); - skb = nskb; + if (skb != *_skb) { + rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare); + *_skb = skb; rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } @@ -237,18 +237,18 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) case RXRPC_PACKET_TYPE_CHALLENGE: if (rxrpc_to_server(sp)) - goto discard; + return 0; break; case RXRPC_PACKET_TYPE_RESPONSE: if (rxrpc_to_client(sp)) - goto discard; + return 0; break; /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: - goto discard; + return 0; default: goto bad_message; @@ -268,7 +268,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.seq == 1) goto unsupported_service; - goto discard; + return 0; } } @@ -294,7 +294,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - goto out; + return 0; } if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) @@ -306,19 +306,19 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - goto discard; + return 0; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - goto discard; + return 0; /* For the previous service call, if completed * successfully, we discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - goto discard; + return 0; /* But otherwise we need to retransmit the final packet * from data cached in the connection record. @@ -329,7 +329,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) sp->hdr.serial, sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); - goto out; + return 0; } call = rcu_dereference(chan->call); @@ -357,21 +357,14 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) sp->hdr.type != RXRPC_PACKET_TYPE_DATA) goto bad_message; if (sp->hdr.seq != 1) - goto discard; + return 0; call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; } - /* Process a call packet; this either discards or passes on the ref - * elsewhere. - */ + /* Process a call packet. */ rxrpc_input_call_event(call, skb); - goto out; - -discard: - rxrpc_free_skb(skb, rxrpc_skb_put_input); -out: trace_rxrpc_rx_done(0, 0); return 0; @@ -400,9 +393,7 @@ protocol_error: post_abort: skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: - trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); - _leave(" [badmsg]"); return 0; } @@ -441,9 +432,12 @@ int rxrpc_io_thread(void *data) if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: + skb->priority = 0; rcu_read_lock(); - rxrpc_input_packet(local, skb); + rxrpc_input_packet(local, &skb); rcu_read_unlock(); + trace_rxrpc_rx_done(skb->mark, skb->priority); + rxrpc_free_skb(skb, rxrpc_skb_put_input); break; case RXRPC_SKB_MARK_ERROR: rxrpc_input_error(local, skb); -- cgit v1.2.3 From 5e6ef4f1017c7f844e305283bbd8875af475e2fc Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 23 Jan 2020 13:13:41 +0000 Subject: rxrpc: Make the I/O thread take over the call and local processor work Move the functions from the call->processor and local->processor work items into the domain of the I/O thread. The call event processor, now called from the I/O thread, then takes over the job of cranking the call state machine, processing incoming packets and transmitting DATA, ACK and ABORT packets. In a future patch, rxrpc_send_ACK() will transmit the ACK on the spot rather than queuing it for later transmission. The call event processor becomes purely received-skb driven. It only transmits things in response to events. We use "pokes" to queue a dummy skb to make it do things like start/resume transmitting data. Timer expiry also results in pokes. The connection event processor, becomes similar, though crypto events, such as dealing with CHALLENGE and RESPONSE packets is offloaded to a work item to avoid doing crypto in the I/O thread. The local event processor is removed and VERSION response packets are generated directly from the packet parser. Similarly, ABORTs generated in response to protocol errors will be transmitted immediately rather than being pushed onto a queue for later transmission. Changes: ======== ver #2) - Fix a couple of introduced lock context imbalances. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 42 +++--- net/rxrpc/ar-internal.h | 50 +++---- net/rxrpc/call_accept.c | 126 ++++++++--------- net/rxrpc/call_event.c | 171 ++++++++++------------- net/rxrpc/call_object.c | 56 +++++--- net/rxrpc/conn_event.c | 60 ++++++++ net/rxrpc/conn_object.c | 93 +++++-------- net/rxrpc/input.c | 167 ++++++---------------- net/rxrpc/io_thread.c | 319 ++++++++++++++++++++----------------------- net/rxrpc/local_event.c | 43 +----- net/rxrpc/local_object.c | 69 +--------- net/rxrpc/output.c | 92 +++++-------- net/rxrpc/peer_event.c | 29 ++-- net/rxrpc/recvmsg.c | 9 +- net/rxrpc/sendmsg.c | 10 +- 15 files changed, 545 insertions(+), 791 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 82b1327c2ba6..c49b0c233594 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -26,7 +26,6 @@ #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ - EM(rxrpc_skb_get_ack, "GET ack ") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ @@ -36,7 +35,6 @@ EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ EM(rxrpc_skb_new_unshared, "NEW unshared ") \ - EM(rxrpc_skb_put_ack, "PUT ack ") \ EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ @@ -45,7 +43,6 @@ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ EM(rxrpc_skb_see_conn_work, "SEE conn-work") \ - EM(rxrpc_skb_see_local_work, "SEE locl-work") \ EM(rxrpc_skb_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_skb_see_reject, "SEE reject ") \ EM(rxrpc_skb_see_rotate, "SEE rotate ") \ @@ -58,10 +55,7 @@ EM(rxrpc_local_get_for_use, "GET for-use ") \ EM(rxrpc_local_get_peer, "GET peer ") \ EM(rxrpc_local_get_prealloc_conn, "GET conn-pre") \ - EM(rxrpc_local_get_queue, "GET queue ") \ EM(rxrpc_local_new, "NEW ") \ - EM(rxrpc_local_processing, "PROCESSING ") \ - EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ EM(rxrpc_local_put_bind, "PUT bind ") \ EM(rxrpc_local_put_call, "PUT call ") \ EM(rxrpc_local_put_for_use, "PUT for-use ") \ @@ -69,8 +63,6 @@ EM(rxrpc_local_put_peer, "PUT peer ") \ EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ - EM(rxrpc_local_put_queue, "PUT queue ") \ - EM(rxrpc_local_queued, "QUEUED ") \ EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ EM(rxrpc_local_stop, "STOP ") \ EM(rxrpc_local_stopped, "STOPPED ") \ @@ -78,11 +70,9 @@ EM(rxrpc_local_unuse_conn_work, "UNU conn-wrk") \ EM(rxrpc_local_unuse_peer_keepalive, "UNU peer-kpa") \ EM(rxrpc_local_unuse_release_sock, "UNU rel-sock") \ - EM(rxrpc_local_unuse_work, "UNU work ") \ EM(rxrpc_local_use_conn_work, "USE conn-wrk") \ EM(rxrpc_local_use_lookup, "USE lookup ") \ - EM(rxrpc_local_use_peer_keepalive, "USE peer-kpa") \ - E_(rxrpc_local_use_work, "USE work ") + E_(rxrpc_local_use_peer_keepalive, "USE peer-kpa") #define rxrpc_peer_traces \ EM(rxrpc_peer_free, "FREE ") \ @@ -90,6 +80,7 @@ EM(rxrpc_peer_get_activate_call, "GET act-call") \ EM(rxrpc_peer_get_bundle, "GET bundle ") \ EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ + EM(rxrpc_peer_get_input, "GET input ") \ EM(rxrpc_peer_get_input_error, "GET inpt-err") \ EM(rxrpc_peer_get_keepalive, "GET keepaliv") \ EM(rxrpc_peer_get_lookup_client, "GET look-cln") \ @@ -100,6 +91,7 @@ EM(rxrpc_peer_put_call, "PUT call ") \ EM(rxrpc_peer_put_conn, "PUT conn ") \ EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ + EM(rxrpc_peer_put_input, "PUT input ") \ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") @@ -180,11 +172,6 @@ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ - EM(rxrpc_call_queue_abort, "QUE abort ") \ - EM(rxrpc_call_queue_requeue, "QUE requeue ") \ - EM(rxrpc_call_queue_resend, "QUE resend ") \ - EM(rxrpc_call_queue_timer, "QUE timer ") \ - EM(rxrpc_call_queue_tx_data, "QUE tx-data ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ @@ -282,6 +269,7 @@ EM(rxrpc_propose_ack_respond_to_ping, "Rsp2Png") \ EM(rxrpc_propose_ack_retry_tx, "RetryTx") \ EM(rxrpc_propose_ack_rotate_rx, "RxAck ") \ + EM(rxrpc_propose_ack_rx_idle, "RxIdle ") \ E_(rxrpc_propose_ack_terminal_ack, "ClTerm ") #define rxrpc_congest_modes \ @@ -1532,6 +1520,7 @@ TRACE_EVENT(rxrpc_connect_call, __field(unsigned long, user_call_ID ) __field(u32, cid ) __field(u32, call_id ) + __field_struct(struct sockaddr_rxrpc, srx ) ), TP_fast_assign( @@ -1539,33 +1528,42 @@ TRACE_EVENT(rxrpc_connect_call, __entry->user_call_ID = call->user_call_ID; __entry->cid = call->cid; __entry->call_id = call->call_id; + __entry->srx = call->dest_srx; ), - TP_printk("c=%08x u=%p %08x:%08x", + TP_printk("c=%08x u=%p %08x:%08x dst=%pISp", __entry->call, (void *)__entry->user_call_ID, __entry->cid, - __entry->call_id) + __entry->call_id, + &__entry->srx.transport) ); TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call), + TP_PROTO(struct rxrpc_call *call, struct sk_buff *ack), - TP_ARGS(call), + TP_ARGS(call, ack), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) + __field(rxrpc_seq_t, transmitted ) + __field(rxrpc_serial_t, ack_serial ) ), TP_fast_assign( + struct rxrpc_skb_priv *sp = ack ? rxrpc_skb(ack) : NULL; __entry->call = call->debug_id; __entry->seq = call->acks_hard_ack; + __entry->transmitted = call->tx_transmitted; + __entry->ack_serial = sp ? sp->hdr.serial : 0; ), - TP_printk("c=%08x q=%x", + TP_printk("c=%08x r=%x q=%x tq=%x", __entry->call, - __entry->seq) + __entry->ack_serial, + __entry->seq, + __entry->transmitted) ); TRACE_EVENT(rxrpc_rx_icmp, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c3c915a05627..6b993a3d4186 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -283,14 +283,11 @@ struct rxrpc_local { struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct hlist_node link; struct socket *socket; /* my UDP socket */ - struct work_struct processor; struct task_struct *io_thread; struct list_head ack_tx_queue; /* List of ACKs that need sending */ spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ - struct sk_buff_head reject_queue; /* packets awaiting rejection */ - struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct sk_buff_head rx_queue; /* Received packets */ struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ @@ -524,23 +521,19 @@ enum rxrpc_call_flag { RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ - RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ - RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ - RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ + RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ABORT, /* need to generate abort */ - RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ + RXRPC_CALL_EV_INITIAL_PING, /* Send initial ping for a new service call */ }; /* @@ -611,7 +604,6 @@ struct rxrpc_call { u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ struct timer_list timer; /* Combined event timer */ - struct work_struct processor; /* Event processor */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ @@ -705,11 +697,7 @@ struct rxrpc_call { rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ - rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ - rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ - struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ - spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* @@ -822,10 +810,9 @@ extern struct workqueue_struct *rxrpc_workqueue; */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); -struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, - struct rxrpc_sock *, - struct sockaddr_rxrpc *, - struct sk_buff *); +bool rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *, + struct rxrpc_connection *, struct sockaddr_rxrpc *, + struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); @@ -838,13 +825,15 @@ void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); -void rxrpc_process_call(struct work_struct *); +void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long expire_at, unsigned long now, enum rxrpc_timer_trace why); +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); + /* * call_object.c */ @@ -864,9 +853,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -void rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); -bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); +struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); @@ -908,6 +896,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); */ void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); +int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); /* * conn_object.c @@ -916,10 +905,9 @@ extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); -struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, - struct sockaddr_rxrpc *, - struct sk_buff *, - struct rxrpc_peer **); +struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, + struct sockaddr_rxrpc *, + struct sk_buff *); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_client_conn(struct rxrpc_connection *); @@ -962,8 +950,8 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_input_call_event(struct rxrpc_call *, struct sk_buff *); -void rxrpc_input_implicit_end_call(struct rxrpc_connection *, struct rxrpc_call *); +void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); +void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); /* * io_thread.c @@ -993,7 +981,9 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ -extern void rxrpc_process_local_events(struct rxrpc_local *); +void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_host_header *hdr, + struct sk_buff *skb); /* * local_object.c @@ -1004,7 +994,6 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); -void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_local(struct rxrpc_local *local); void rxrpc_destroy_all_locals(struct rxrpc_net *); @@ -1068,7 +1057,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); -void rxrpc_reject_packets(struct rxrpc_local *); +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); @@ -1178,7 +1167,6 @@ int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int); * skbuff.c */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); -void rxrpc_packet_destructor(struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 11134b7cec17..87b46c2a1985 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -100,6 +100,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, return -ENOMEM; call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; + __set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), user_call_ID, rxrpc_call_new_prealloc_service); @@ -234,21 +235,6 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) kfree(b); } -/* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_count < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - rxrpc_propose_ack_ping_for_params); -} - /* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. @@ -330,33 +316,56 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, } /* - * Set up a new incoming call. Called in BH context with the RCU read lock - * held. + * Set up a new incoming call. Called from the I/O thread. * * If this is for a kernel service, when we allocate the call, it will have * three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the * retainer ref obtained from the backlog buffer. Prealloc calls for userspace - * services only have the ref from the backlog buffer. We pass this ref to the - * caller. + * services only have the ref from the backlog buffer. * * If we want to report an error, we mark the skb with the packet type and - * abort code and return NULL. - * - * The call is returned with the user access mutex held and a ref on it. + * abort code and return false. */ -struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, - struct rxrpc_sock *rx, - struct sockaddr_rxrpc *peer_srx, - struct sk_buff *skb) +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); const struct rxrpc_security *sec = NULL; - struct rxrpc_connection *conn; - struct rxrpc_peer *peer = NULL; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_call *call = NULL; + struct rxrpc_sock *rx; _enter(""); + /* Don't set up a call for anything other than the first DATA packet. */ + if (sp->hdr.seq != 1 || + sp->hdr.type != RXRPC_PACKET_TYPE_DATA) + return true; /* Just discard */ + + rcu_read_lock(); + + /* Weed out packets to services we're not offering. Packets that would + * begin a call are explicitly rejected and the rest are just + * discarded. + */ + rx = rcu_dereference(local->service); + if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && + sp->hdr.serviceId != rx->second_service) + ) { + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + sp->hdr.seq == 1) + goto unsupported_service; + goto discard; + } + + if (!conn) { + sec = rxrpc_get_incoming_security(rx, skb); + if (!sec) + goto reject; + } + spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { @@ -367,19 +376,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, goto no_call; } - /* The peer, connection and call may all have sprung into existence due - * to a duplicate packet being handled on another CPU in parallel, so - * we have to recheck the routing. However, we're now holding - * rx->incoming_lock, so the values should remain stable. - */ - conn = rxrpc_find_connection_rcu(local, peer_srx, skb, &peer); - - if (!conn) { - sec = rxrpc_get_incoming_security(rx, skb); - if (!sec) - goto no_call; - } - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, peer_srx, skb); if (!call) { @@ -398,35 +394,15 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rx->notify_new_call(&rx->sk, call, call->user_call_ID); spin_lock(&conn->state_lock); - switch (conn->state) { - case RXRPC_CONN_SERVICE_UNSECURED: + if (conn->state == RXRPC_CONN_SERVICE_UNSECURED) { conn->state = RXRPC_CONN_SERVICE_CHALLENGING; set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); rxrpc_queue_conn(call->conn, rxrpc_conn_queue_challenge); - break; - - case RXRPC_CONN_SERVICE: - write_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - write_unlock(&call->state_lock); - break; - - case RXRPC_CONN_REMOTELY_ABORTED: - rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - conn->abort_code, conn->error); - break; - case RXRPC_CONN_LOCALLY_ABORTED: - rxrpc_abort_call("CON", call, sp->hdr.seq, - conn->abort_code, conn->error); - break; - default: - BUG(); } spin_unlock(&conn->state_lock); - spin_unlock(&rx->incoming_lock); - rxrpc_send_ping(call, skb); + spin_unlock(&rx->incoming_lock); + rcu_read_unlock(); if (hlist_unhashed(&call->error_link)) { spin_lock(&call->peer->lock); @@ -435,12 +411,24 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, } _leave(" = %p{%d}", call, call->debug_id); - return call; - + rxrpc_input_call_event(call, skb); + rxrpc_put_call(call, rxrpc_call_put_input); + return true; + +unsupported_service: + trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EOPNOTSUPP); + skb->priority = RX_INVALID_OPERATION; + goto reject; no_call: spin_unlock(&rx->incoming_lock); - _leave(" = NULL [%u]", skb->mark); - return NULL; +reject: + rcu_read_unlock(); + _leave(" = f [%u]", skb->mark); + return false; +discard: + rcu_read_unlock(); + return true; } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index c9f835292f7b..9db62fa55c62 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -74,11 +74,6 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return; - if (ack_reason == RXRPC_ACK_DELAY && - test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { - trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); - return; - } rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); @@ -111,12 +106,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, spin_unlock_bh(&local->ack_tx_lock); trace_rxrpc_send_ack(call, why, ack_reason, serial); - if (!rcu_read_lock_held()) { - rxrpc_transmit_ack_packets(call->peer->local); - } else { - rxrpc_get_local(local, rxrpc_local_get_queue); - rxrpc_queue_local(local); - } + rxrpc_wake_up_io_thread(local); } /* @@ -130,11 +120,10 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) /* * Perform retransmission of NAK'd and unack'd packets. */ -static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) +void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) { struct rxrpc_ackpacket *ack = NULL; struct rxrpc_txbuf *txb; - struct sk_buff *ack_skb = NULL; unsigned long resend_at; rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; @@ -148,32 +137,21 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); oldest = now; - /* See if there's an ACK saved with a soft-ACK table in it. */ - if (call->acks_soft_tbl) { - spin_lock_bh(&call->acks_ack_lock); - ack_skb = call->acks_soft_tbl; - if (ack_skb) { - rxrpc_get_skb(ack_skb, rxrpc_skb_get_ack); - ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - } - spin_unlock_bh(&call->acks_ack_lock); - } - if (list_empty(&call->tx_buffer)) goto no_resend; - spin_lock(&call->tx_lock); - if (list_empty(&call->tx_buffer)) goto no_further_resend; - trace_rxrpc_resend(call); + trace_rxrpc_resend(call, ack_skb); txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); /* Scan the soft ACK table without dropping the lock and resend any * explicitly NAK'd packets. */ - if (ack) { + if (ack_skb) { + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + for (i = 0; i < ack->nAcks; i++) { rxrpc_seq_t seq; @@ -197,7 +175,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); if (list_empty(&txb->tx_link)) { - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); list_add_tail(&txb->tx_link, &retrans_queue); set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } @@ -241,7 +218,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) do_resend: unacked = true; if (list_empty(&txb->tx_link)) { - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); list_add_tail(&txb->tx_link, &retrans_queue); set_bit(RXRPC_TXBUF_RESENT, &txb->flags); rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); @@ -249,10 +225,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) } no_further_resend: - spin_unlock(&call->tx_lock); no_resend: - rxrpc_free_skb(ack_skb, rxrpc_skb_put_ack); - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, !list_empty(&retrans_queue)); @@ -266,7 +239,7 @@ no_resend: * retransmitting data. */ if (list_empty(&retrans_queue)) { - rxrpc_reduce_call_timer(call, resend_at, now_j, + rxrpc_reduce_call_timer(call, resend_at, jiffies, rxrpc_timer_set_for_resend); ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) @@ -276,15 +249,11 @@ no_resend: goto out; } + /* Retransmit the queue */ while ((txb = list_first_entry_or_null(&retrans_queue, struct rxrpc_txbuf, tx_link))) { list_del_init(&txb->tx_link); - rxrpc_send_data_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - - trace_rxrpc_retransmit(call, txb->seq, - ktime_to_ns(ktime_sub(txb->last_sent, - max_age))); + rxrpc_transmit_one(call, txb); } out: @@ -357,16 +326,27 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) } } +/* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_initial_ping(struct rxrpc_call *call) +{ + if (call->peer->rtt_count < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real())) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_params); +} + /* * Handle retransmission and deferred ACK/abort generation. */ -void rxrpc_process_call(struct work_struct *work) +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_call *call = - container_of(work, struct rxrpc_call, processor); unsigned long now, next, t; - unsigned int iterations = 0; rxrpc_serial_t ackr_serial; + bool resend = false, expired = false; rxrpc_see_call(call, rxrpc_call_see_input); @@ -374,47 +354,31 @@ void rxrpc_process_call(struct work_struct *work) _enter("{%d,%s,%lx}", call->debug_id, rxrpc_call_states[call->state], call->events); -recheck_state: - if (call->acks_hard_ack != call->tx_bottom) - rxrpc_shrink_call_tx_buffer(call); - - /* Limit the number of times we do this before returning to the manager */ - if (!rxrpc_tx_window_has_space(call) || - list_empty(&call->tx_sendmsg)) { - iterations++; - if (iterations > 5) - goto requeue; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - rxrpc_send_abort_packet(call); - goto recheck_state; - } + if (call->state == RXRPC_CALL_COMPLETE) + goto out; - if (call->state == RXRPC_CALL_COMPLETE) { - del_timer_sync(&call->timer); + if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; - } - /* Work out if any timeouts tripped */ + /* If we see our async-event poke, check for timeout trippage. */ now = jiffies; t = READ_ONCE(call->expect_rx_by); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->expect_req_by); if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST && time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->expect_term_by); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->delay_ack_at); @@ -453,13 +417,19 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now); cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_RESEND, &call->events); + resend = true; } + if (skb) + rxrpc_input_call_packet(call, skb); + rxrpc_transmit_some_data(call); + if (test_and_clear_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events)) + rxrpc_send_initial_ping(call); + /* Process events */ - if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) { + if (expired) { if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && (int)call->conn->hi_serial - (int)call->rx_serial > 0) { trace_rxrpc_call_reset(call); @@ -467,51 +437,50 @@ recheck_state: } else { rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); } - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - goto recheck_state; + rxrpc_send_abort_packet(call); + goto out; } - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { - call->acks_lost_top = call->tx_top; + if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - } - if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && - call->state != RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_resend(call, now); - goto recheck_state; - } + if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_resend(call, NULL); + + if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, + rxrpc_propose_ack_rx_idle); + + if (atomic_read(&call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, + rxrpc_propose_ack_input_data); /* Make sure the timer is restarted */ - next = call->expect_rx_by; + if (call->state != RXRPC_CALL_COMPLETE) { + next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } - set(call->expect_req_by); - set(call->expect_term_by); - set(call->delay_ack_at); - set(call->ack_lost_at); - set(call->resend_at); - set(call->keepalive_at); - set(call->ping_at); - - now = jiffies; - if (time_after_eq(now, next)) - goto recheck_state; + set(call->expect_req_by); + set(call->expect_term_by); + set(call->delay_ack_at); + set(call->ack_lost_at); + set(call->resend_at); + set(call->keepalive_at); + set(call->ping_at); - rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + now = jiffies; + if (time_after_eq(now, next)) + rxrpc_poke_call(call, rxrpc_call_poke_timer_now); - /* other events may have been raised since we started checking */ - if (call->events) - goto requeue; + rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + } out: + if (call->state == RXRPC_CALL_COMPLETE) + del_timer_sync(&call->timer); + if (call->acks_hard_ack != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); _leave(""); - return; - -requeue: - if (call->state < RXRPC_CALL_COMPLETE) - rxrpc_queue_call(call, rxrpc_call_queue_requeue); - goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 7570b4e67bc5..d441a715d988 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -71,7 +71,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - rxrpc_queue_call(call, rxrpc_call_queue_timer); + rxrpc_poke_call(call, rxrpc_call_poke_timer); } } @@ -148,7 +148,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, &rxrpc_call_user_mutex_lock_class_key); timer_setup(&call->timer, rxrpc_call_timer_expired, 0); - INIT_WORK(&call->processor, rxrpc_process_call); INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->chan_wait_link); @@ -163,7 +162,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); - spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; @@ -252,6 +250,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; + call->keepalive_at = j; call->expect_rx_by = j; call->expect_req_by = j; call->expect_term_by = j; @@ -430,6 +429,29 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; + spin_lock(&conn->state_lock); + + switch (conn->state) { + case RXRPC_CONN_SERVICE_UNSECURED: + case RXRPC_CONN_SERVICE_CHALLENGING: + call->state = RXRPC_CALL_SERVER_SECURING; + break; + case RXRPC_CONN_SERVICE: + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + break; + + case RXRPC_CONN_REMOTELY_ABORTED: + __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + conn->abort_code, conn->error); + break; + case RXRPC_CONN_LOCALLY_ABORTED: + __rxrpc_abort_call("CON", call, 1, + conn->abort_code, conn->error); + break; + default: + BUG(); + } + /* Set the channel for this call. We don't get channel_lock as we're * only defending against the data_ready handler (which we're called * from) and the RESPONSE packet parser (which is only really @@ -440,6 +462,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, conn->channels[chan].call_counter = call->call_id; conn->channels[chan].call_id = call->call_id; rcu_assign_pointer(conn->channels[chan].call, call); + spin_unlock(&conn->state_lock); spin_lock(&conn->peer->lock); hlist_add_head(&call->error_link, &conn->peer->error_targets); @@ -449,15 +472,6 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, _leave(""); } -/* - * Queue a call's work processor. - */ -void rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) -{ - if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, why); -} - /* * Note the re-emergence of a call. */ @@ -470,14 +484,15 @@ void rxrpc_see_call(struct rxrpc_call *call, enum rxrpc_call_trace why) } } -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) +struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *call, + enum rxrpc_call_trace why) { int r; - if (!__refcount_inc_not_zero(&call->ref, &r)) - return false; + if (!call || !__refcount_inc_not_zero(&call->ref, &r)) + return NULL; trace_rxrpc_call(call->debug_id, r + 1, 0, why); - return true; + return call; } /* @@ -637,8 +652,6 @@ static void rxrpc_destroy_call(struct work_struct *work) struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); struct rxrpc_txbuf *txb; - del_timer_sync(&call->timer); - cancel_work_sync(&call->processor); /* The processor may restart the timer */ del_timer_sync(&call->timer); rxrpc_cleanup_ring(call); @@ -652,8 +665,8 @@ static void rxrpc_destroy_call(struct work_struct *work) list_del(&txb->call_link); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); rxrpc_put_local(call->local, rxrpc_local_put_call); @@ -670,10 +683,9 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - del_timer_sync(&call->timer); - cancel_work(&call->processor); + del_timer(&call->timer); - if (rcu_read_lock_held() || work_busy(&call->processor)) + if (rcu_read_lock_held()) /* Can't use the rxrpc workqueue as we need to cancel/flush * something that may be running/waiting there. */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 23a74e35052d..643a56322224 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -479,3 +479,63 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } } + +/* + * post connection-level events to the connection + * - this includes challenges, responses, some aborts and call terminal packet + * retransmission. + */ +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + _enter("%p,%p", conn, skb); + + rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); + skb_queue_tail(&conn->rx_queue, skb); + rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); +} + +/* + * Input a connection-level packet. + */ +int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + _leave(" = -ECONNABORTED [%u]", conn->state); + return -ECONNABORTED; + } + + _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_DATA: + case RXRPC_PACKET_TYPE_ACK: + rxrpc_conn_retransmit_call(conn, skb, + sp->hdr.cid & RXRPC_CHANNELMASK); + return 0; + + case RXRPC_PACKET_TYPE_BUSY: + /* Just ignore BUSY packets for now. */ + return 0; + + case RXRPC_PACKET_TYPE_ABORT: + conn->error = -ECONNABORTED; + conn->abort_code = skb->priority; + conn->state = RXRPC_CONN_REMOTELY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); + return -ECONNABORTED; + + case RXRPC_PACKET_TYPE_CHALLENGE: + case RXRPC_PACKET_TYPE_RESPONSE: + rxrpc_post_packet_to_conn(conn, skb); + return 0; + + default: + trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, + tracepoint_string("bad_conn_pkt")); + return -EPROTO; + } +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 98e49646ca1d..3c8f83dacb2b 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -72,76 +72,55 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, * * The caller must be holding the RCU read lock. */ -struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, - struct sockaddr_rxrpc *srx, - struct sk_buff *skb, - struct rxrpc_peer **_peer) +struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, + struct sk_buff *skb) { struct rxrpc_connection *conn; - struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); - k.epoch = sp->hdr.epoch; - k.cid = sp->hdr.cid & RXRPC_CIDMASK; - - if (rxrpc_to_server(sp)) { - /* We need to look up service connections by the full protocol - * parameter set. We look up the peer first as an intermediate - * step and then the connection from the peer's tree. - */ - peer = rxrpc_lookup_peer_rcu(local, srx); - if (!peer) - goto not_found; - *_peer = peer; - conn = rxrpc_find_service_conn_rcu(peer, skb); - if (!conn || refcount_read(&conn->ref) == 0) - goto not_found; - _leave(" = %p", conn); - return conn; - } else { - /* Look up client connections by connection ID alone as their - * IDs are unique for this machine. - */ - conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); - if (!conn || refcount_read(&conn->ref) == 0) { - _debug("no conn"); - goto not_found; - } + /* Look up client connections by connection ID alone as their IDs are + * unique for this machine. + */ + conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); + if (!conn || refcount_read(&conn->ref) == 0) { + _debug("no conn"); + goto not_found; + } - if (conn->proto.epoch != k.epoch || - conn->local != local) + if (conn->proto.epoch != sp->hdr.epoch || + conn->local != local) + goto not_found; + + peer = conn->peer; + switch (srx->transport.family) { + case AF_INET: + if (peer->srx.transport.sin.sin_port != + srx->transport.sin.sin_port || + peer->srx.transport.sin.sin_addr.s_addr != + srx->transport.sin.sin_addr.s_addr) goto not_found; - - peer = conn->peer; - switch (srx->transport.family) { - case AF_INET: - if (peer->srx.transport.sin.sin_port != - srx->transport.sin.sin_port || - peer->srx.transport.sin.sin_addr.s_addr != - srx->transport.sin.sin_addr.s_addr) - goto not_found; - break; + break; #ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - if (peer->srx.transport.sin6.sin6_port != - srx->transport.sin6.sin6_port || - memcmp(&peer->srx.transport.sin6.sin6_addr, - &srx->transport.sin6.sin6_addr, - sizeof(struct in6_addr)) != 0) - goto not_found; - break; + case AF_INET6: + if (peer->srx.transport.sin6.sin6_port != + srx->transport.sin6.sin6_port || + memcmp(&peer->srx.transport.sin6.sin6_addr, + &srx->transport.sin6.sin6_addr, + sizeof(struct in6_addr)) != 0) + goto not_found; + break; #endif - default: - BUG(); - } - - _leave(" = %p", conn); - return conn; + default: + BUG(); } + _leave(" = %p", conn); + return conn; + not_found: _leave(" = NULL"); return NULL; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 01d32f817a7a..7ae7046f0b03 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -12,10 +12,8 @@ static void rxrpc_proto_abort(const char *why, struct rxrpc_call *call, rxrpc_seq_t seq) { - if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call, rxrpc_call_queue_abort); - } + if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) + rxrpc_send_abort_packet(call); } /* @@ -174,8 +172,8 @@ out_no_clear_ca: call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call, rxrpc_call_queue_resend); + if (resend) + rxrpc_resend(call, skb); return; packet_loss_detected: @@ -398,6 +396,8 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, /* Send an immediate ACK if we fill in a hole */ else if (!skb_queue_empty(&call->rx_oos_queue)) ack_reason = RXRPC_ACK_DELAY; + else + atomic_inc_return(&call->ackr_nr_unacked); window++; if (after(window, wtop)) @@ -473,14 +473,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, } send_ack: - if (ack_reason < 0 && - atomic_inc_return(&call->ackr_nr_unacked) > 2 && - test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - ack_reason = RXRPC_ACK_IDLE; - } else if (ack_reason >= 0) { - set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); - } - if (ack_reason >= 0) rxrpc_send_ACK(call, ack_reason, serial, rxrpc_propose_ack_input_data); @@ -510,7 +502,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb &jhdr, sizeof(jhdr)) < 0) goto protocol_error; - jskb = skb_clone(skb, GFP_ATOMIC); + jskb = skb_clone(skb, GFP_NOFS); if (!jskb) { kdebug("couldn't clone"); return false; @@ -562,24 +554,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (state >= RXRPC_CALL_COMPLETE) return; - /* Unshare the packet so that it can be modified for in-place - * decryption. - */ - if (sp->hdr.securityIndex != 0) { - struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); - if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); - return; - } - - if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); - skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_new_unshared); - sp = rxrpc_skb(skb); - } - } - if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -599,15 +573,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto out; + goto out_notify; if (!rxrpc_input_split_jumbo(call, skb)) { rxrpc_proto_abort("VLD", call, sp->hdr.seq); - goto out; + goto out_notify; } skb = NULL; -out: +out_notify: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); _leave(" [queued]"); @@ -667,32 +641,6 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } -/* - * Process the response to a ping that we sent to find out if we lost an ACK. - * - * If we got back a ping response that indicates a lower tx_top than what we - * had at the time of the ping transmission, we adjudge all the DATA packets - * sent between the response tx_top and the ping-time tx_top to have been lost. - */ -static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) -{ - if (after(call->acks_lost_top, call->acks_prev_seq) && - !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call, rxrpc_call_queue_resend); -} - -/* - * Process a ping response. - */ -static void rxrpc_input_ping_response(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t acked_serial, - rxrpc_serial_t ack_serial) -{ - if (acked_serial == call->acks_lost_ping) - rxrpc_input_check_for_lost_ack(call); -} - /* * Process the extra information that may be appended to an ACK packet */ @@ -801,7 +749,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_ackinfo info; - struct sk_buff *skb_old = NULL; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -809,10 +756,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { - rxrpc_proto_abort("XAK", call, 0); - goto out; - } + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) + return rxrpc_proto_abort("XAK", call, 0); offset += sizeof(ack); ack_serial = sp->hdr.serial; @@ -863,7 +808,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - goto out; + return; } /* If we get an OUT_OF_SEQUENCE ACK from the server, that can also @@ -877,7 +822,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - goto out; + return; } /* Discard any out-of-order or duplicate ACKs (outside lock). */ @@ -885,39 +830,25 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - goto out; + return; } info.rxMTU = 0; ioffset = offset + nr_acks + 3; if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { - rxrpc_proto_abort("XAI", call, 0); - goto out; - } + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) + return rxrpc_proto_abort("XAI", call, 0); if (nr_acks > 0) skb_condense(skb); - /* Discard any out-of-order or duplicate ACKs (inside lock). */ - if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, - first_soft_ack, call->acks_first_seq, - prev_pkt, call->acks_prev_seq); - goto out; - } call->acks_latest_ts = skb->tstamp; - call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; switch (ack.reason) { case RXRPC_ACK_PING: break; - case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); - fallthrough; default: if (after(acked_serial, call->acks_highest_serial)) call->acks_highest_serial = acked_serial; @@ -928,10 +859,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (info.rxMTU) rxrpc_input_ackinfo(call, skb, &info); - if (first_soft_ack == 0) { - rxrpc_proto_abort("AK0", call, 0); - goto out; - } + if (first_soft_ack == 0) + return rxrpc_proto_abort("AK0", call, 0); /* Ignore ACKs unless we are or have just been transmitting. */ switch (READ_ONCE(call->state)) { @@ -941,45 +870,27 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - goto out; + return; } if (before(hard_ack, call->acks_hard_ack) || - after(hard_ack, call->tx_top)) { - rxrpc_proto_abort("AKW", call, 0); - goto out; - } - if (nr_acks > call->tx_top - hard_ack) { - rxrpc_proto_abort("AKN", call, 0); - goto out; - } + after(hard_ack, call->tx_top)) + return rxrpc_proto_abort("AKW", call, 0); + if (nr_acks > call->tx_top - hard_ack) + return rxrpc_proto_abort("AKN", call, 0); if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); - goto out; + return; } } if (nr_acks > 0) { - if (offset > (int)skb->len - nr_acks) { - rxrpc_proto_abort("XSA", call, 0); - goto out; - } - - rxrpc_get_skb(skb, rxrpc_skb_get_ack); - spin_lock(&call->acks_ack_lock); - skb_old = call->acks_soft_tbl; - call->acks_soft_tbl = skb; - spin_unlock(&call->acks_ack_lock); - + if (offset > (int)skb->len - nr_acks) + return rxrpc_proto_abort("XSA", call, 0); rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); - } else if (call->acks_soft_tbl) { - spin_lock(&call->acks_ack_lock); - skb_old = call->acks_soft_tbl; - call->acks_soft_tbl = NULL; - spin_unlock(&call->acks_ack_lock); } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && @@ -989,8 +900,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); -out: - rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } /* @@ -1020,13 +929,20 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) /* * Process an incoming call packet. */ -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) +void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; _enter("%p,%p", call, skb); + if (sp->hdr.serviceId != call->dest_srx.srx_service) + call->dest_srx.srx_service = sp->hdr.serviceId; + if ((int)sp->hdr.serial - (int)call->rx_serial > 0) + call->rx_serial = sp->hdr.serial; + if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) + set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + timo = READ_ONCE(call->next_rx_timo); if (timo) { unsigned long now = jiffies, expect_rx_by; @@ -1072,9 +988,10 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) * * TODO: If callNumber > call_id + 1, renegotiate security. */ -void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, - struct rxrpc_call *call) +void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_connection *conn = call->conn; + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); @@ -1082,14 +999,14 @@ void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, case RXRPC_CALL_COMPLETE: break; default: - if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call, rxrpc_call_queue_abort); - } + if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) + rxrpc_send_abort_packet(call); trace_rxrpc_improper_term(call); break; } + rxrpc_input_call_event(call, skb); + spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->bundle->channel_lock); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index bc65d83fab88..19aa315eddf5 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -9,6 +9,10 @@ #include "ar-internal.h" +static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb); + /* * handle data received on the local endpoint * - may be called in interrupt context @@ -63,45 +67,19 @@ void rxrpc_error_report(struct sock *sk) } /* - * post connection-level events to the connection - * - this includes challenges, responses, some aborts and call terminal packet - * retransmission. + * Process event packets targeted at a local endpoint. */ -static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, - struct sk_buff *skb) +static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) { - _enter("%p,%p", conn, skb); - - rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); - skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); -} + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + char v; -/* - * post endpoint-level events to the local endpoint - * - this includes debug and version messages - */ -static void rxrpc_post_packet_to_local(struct rxrpc_local *local, - struct sk_buff *skb) -{ - _enter("%p,%p", local, skb); + _enter(""); - if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { - rxrpc_get_skb(skb, rxrpc_skb_get_local_work); - skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); - } -} - -/* - * put a packet up for transport-level abort - */ -static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) -{ - if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { - rxrpc_get_skb(skb, rxrpc_skb_get_reject_work); - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + rxrpc_see_skb(skb, rxrpc_skb_see_version); + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &v, 1) >= 0) { + if (v == 0) + rxrpc_send_version_request(local, &sp->hdr, skb); } } @@ -156,22 +134,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct sockaddr_rxrpc peer_srx; - struct rxrpc_channel *chan; - struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; - struct rxrpc_sock *rx = NULL; struct sk_buff *skb = *_skb; - unsigned int channel; - - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); + int ret = 0; skb_pull(skb, sizeof(struct udphdr)); - /* The UDP protocol already released all skb resources; - * we are free to add our own data there. - */ sp = rxrpc_skb(skb); /* dig out the RxRPC connection details */ @@ -186,15 +155,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) } } - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); trace_rxrpc_rx_packet(sp); switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) return 0; - rxrpc_post_packet_to_local(local, skb); + rxrpc_input_version(local, skb); return 0; case RXRPC_PACKET_TYPE_BUSY: @@ -259,7 +226,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) goto bad_message; if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0)) - return 0; /* Unsupported address type - discard. */ + return true; /* Unsupported address type - discard. */ if (peer_srx.transport.family != local->srx.transport.family && (peer_srx.transport.family == AF_INET && @@ -267,171 +234,172 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", peer_srx.transport.family, local->srx.transport.family); - return 0; /* Wrong address type - discard. */ + return true; /* Wrong address type - discard. */ + } + + if (rxrpc_to_client(sp)) { + rcu_read_lock(); + conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb); + conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); + rcu_read_unlock(); + if (!conn) { + trace_rxrpc_abort(0, "NCC", sp->hdr.cid, + sp->hdr.callNumber, sp->hdr.seq, + RXKADINCONSISTENCY, EBADMSG); + goto protocol_error; + } + + ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); + rxrpc_put_connection(conn, rxrpc_conn_put_call_input); + return ret; } + /* We need to look up service connections by the full protocol + * parameter set. We look up the peer first as an intermediate step + * and then the connection from the peer's tree. + */ rcu_read_lock(); - if (rxrpc_to_server(sp)) { - /* Weed out packets to services we're not offering. Packets - * that would begin a call are explicitly rejected and the rest - * are just discarded. - */ - rx = rcu_dereference(local->service); - if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && - sp->hdr.serviceId != rx->second_service) - ) { - rcu_read_unlock(); - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - sp->hdr.seq == 1) - goto unsupported_service; - return 0; - } + peer = rxrpc_lookup_peer_rcu(local, &peer_srx); + if (!peer) { + rcu_read_unlock(); + return rxrpc_new_incoming_call(local, NULL, NULL, &peer_srx, skb); } - conn = rxrpc_find_connection_rcu(local, &peer_srx, skb, &peer); + conn = rxrpc_find_service_conn_rcu(peer, skb); + conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); if (conn) { - if (sp->hdr.securityIndex != conn->security_ix) - goto wrong_security; + rcu_read_unlock(); + ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); + rxrpc_put_connection(conn, rxrpc_conn_put_call_input); + return ret; + } - if (sp->hdr.serviceId != conn->service_id) { - int old_id; + peer = rxrpc_get_peer_maybe(peer, rxrpc_peer_get_input); + rcu_read_unlock(); - if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) - goto reupgrade; - old_id = cmpxchg(&conn->service_id, conn->orig_service_id, - sp->hdr.serviceId); + ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb); + rxrpc_put_peer(peer, rxrpc_peer_put_input); + if (ret < 0) + goto reject_packet; + return 0; - if (old_id != conn->orig_service_id && - old_id != sp->hdr.serviceId) - goto reupgrade; - } +bad_message: + trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_PROTOCOL_ERROR, EBADMSG); +protocol_error: + skb->priority = RX_PROTOCOL_ERROR; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; +reject_packet: + rxrpc_reject_packet(local, skb); + return ret; +} - if (sp->hdr.callNumber == 0) { - /* Connection-level packet */ - _debug("CONN %p {%d}", conn, conn->debug_id); - conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_conn_input); - rcu_read_unlock(); - if (conn) { - rxrpc_post_packet_to_conn(conn, skb); - rxrpc_put_connection(conn, rxrpc_conn_put_conn_input); - } - return 0; - } +/* + * Deal with a packet that's associated with an extant connection. + */ +static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_channel *chan; + struct rxrpc_call *call = NULL; + unsigned int channel; - if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) - conn->hi_serial = sp->hdr.serial; + if (sp->hdr.securityIndex != conn->security_ix) + goto wrong_security; - /* Call-bound packets are routed by connection channel. */ - channel = sp->hdr.cid & RXRPC_CHANNELMASK; - chan = &conn->channels[channel]; + if (sp->hdr.serviceId != conn->service_id) { + int old_id; - /* Ignore really old calls */ - if (sp->hdr.callNumber < chan->last_call) { - rcu_read_unlock(); - return 0; - } + if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) + goto reupgrade; + old_id = cmpxchg(&conn->service_id, conn->orig_service_id, + sp->hdr.serviceId); - if (sp->hdr.callNumber == chan->last_call) { - if (chan->call || - sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) { - rcu_read_unlock(); - return 0; - } + if (old_id != conn->orig_service_id && + old_id != sp->hdr.serviceId) + goto reupgrade; + } - /* For the previous service call, if completed - * successfully, we discard all further packets. - */ - if (rxrpc_conn_is_service(conn) && - chan->last_type == RXRPC_PACKET_TYPE_ACK) { - rcu_read_unlock(); - return 0; - } + if (after(sp->hdr.serial, conn->hi_serial)) + conn->hi_serial = sp->hdr.serial; - /* But otherwise we need to retransmit the final packet - * from data cached in the connection record. - */ - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) - trace_rxrpc_rx_data(chan->call_debug_id, - sp->hdr.seq, - sp->hdr.serial, - sp->hdr.flags); - conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); - rcu_read_unlock(); - if (conn) { - rxrpc_post_packet_to_conn(conn, skb); - rxrpc_put_connection(conn, rxrpc_conn_put_call_input); - } + /* It's a connection-level packet if the call number is 0. */ + if (sp->hdr.callNumber == 0) + return rxrpc_input_conn_packet(conn, skb); + + /* Call-bound packets are routed by connection channel. */ + channel = sp->hdr.cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + + /* Ignore really old calls */ + if (sp->hdr.callNumber < chan->last_call) + return 0; + + if (sp->hdr.callNumber == chan->last_call) { + if (chan->call || + sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) return 0; - } - call = rcu_dereference(chan->call); + /* For the previous service call, if completed successfully, we + * discard all further packets. + */ + if (rxrpc_conn_is_service(conn) && + chan->last_type == RXRPC_PACKET_TYPE_ACK) + return 0; - if (sp->hdr.callNumber > chan->call_id) { - if (rxrpc_to_client(sp)) { - rcu_read_unlock(); - goto reject_packet; - } - if (call) { - rxrpc_input_implicit_end_call(conn, call); - chan->call = NULL; - call = NULL; - } - } + /* But otherwise we need to retransmit the final packet from + * data cached in the connection record. + */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) + trace_rxrpc_rx_data(chan->call_debug_id, + sp->hdr.seq, + sp->hdr.serial, + sp->hdr.flags); + rxrpc_input_conn_packet(conn, skb); + return 0; + } - if (call && !rxrpc_try_get_call(call, rxrpc_call_get_input)) - call = NULL; + rcu_read_lock(); + call = rxrpc_try_get_call(rcu_dereference(chan->call), + rxrpc_call_get_input); + rcu_read_unlock(); + + if (sp->hdr.callNumber > chan->call_id) { + if (rxrpc_to_client(sp)) { + rxrpc_put_call(call, rxrpc_call_put_input); + goto reject_packet; + } if (call) { - if (sp->hdr.serviceId != call->dest_srx.srx_service) - call->dest_srx.srx_service = sp->hdr.serviceId; - if ((int)sp->hdr.serial - (int)call->rx_serial > 0) - call->rx_serial = sp->hdr.serial; - if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) - set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + rxrpc_implicit_end_call(call, skb); + rxrpc_put_call(call, rxrpc_call_put_input); + call = NULL; } } if (!call) { - if (rxrpc_to_client(sp) || - sp->hdr.type != RXRPC_PACKET_TYPE_DATA) { - rcu_read_unlock(); + if (rxrpc_to_client(sp)) goto bad_message; - } - if (sp->hdr.seq != 1) { - rcu_read_unlock(); + if (rxrpc_new_incoming_call(conn->local, conn->peer, conn, + peer_srx, skb)) return 0; - } - call = rxrpc_new_incoming_call(local, rx, &peer_srx, skb); - if (!call) { - rcu_read_unlock(); - goto reject_packet; - } + goto reject_packet; } - rcu_read_unlock(); - - /* Process a call packet. */ rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - trace_rxrpc_rx_done(0, 0); return 0; wrong_security: - rcu_read_unlock(); trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RXKADINCONSISTENCY, EBADMSG); skb->priority = RXKADINCONSISTENCY; goto post_abort; -unsupported_service: - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->priority = RX_INVALID_OPERATION; - goto post_abort; - reupgrade: - rcu_read_unlock(); trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); goto protocol_error; @@ -444,7 +412,7 @@ protocol_error: post_abort: skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: - rxrpc_reject_packet(local, skb); + rxrpc_reject_packet(conn->local, skb); return 0; } @@ -479,6 +447,11 @@ int rxrpc_io_thread(void *data) continue; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + continue; + } + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index c344383a20b2..5e69ea6b233d 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -21,9 +21,9 @@ static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; /* * Reply to a version request */ -static void rxrpc_send_version_request(struct rxrpc_local *local, - struct rxrpc_host_header *hdr, - struct sk_buff *skb) +void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_host_header *hdr, + struct sk_buff *skb) { struct rxrpc_wire_header whdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -73,40 +73,3 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, _leave(""); } - -/* - * Process event packets targeted at a local endpoint. - */ -void rxrpc_process_local_events(struct rxrpc_local *local) -{ - struct sk_buff *skb; - char v; - - _enter(""); - - skb = skb_dequeue(&local->event_queue); - if (skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - rxrpc_see_skb(skb, rxrpc_skb_see_local_work); - _debug("{%d},{%u}", local->debug_id, sp->hdr.type); - - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_VERSION: - if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - &v, 1) < 0) - return; - if (v == 0) - rxrpc_send_version_request(local, &sp->hdr, skb); - break; - - default: - /* Just ignore anything we don't understand */ - break; - } - - rxrpc_free_skb(skb, rxrpc_skb_put_input); - } - - _leave(""); -} diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 03f491cc23ef..c73a5a1bc088 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -20,7 +20,6 @@ #include #include "ar-internal.h" -static void rxrpc_local_processor(struct work_struct *); static void rxrpc_local_rcu(struct rcu_head *); /* @@ -97,12 +96,9 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); - INIT_WORK(&local->processor, rxrpc_local_processor); INIT_LIST_HEAD(&local->ack_tx_queue); spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); - skb_queue_head_init(&local->reject_queue); - skb_queue_head_init(&local->event_queue); skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->call_attend_q); local->client_bundles = RB_ROOT; @@ -318,21 +314,6 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local, return NULL; } -/* - * Queue a local endpoint and pass the caller's reference to the work item. - */ -void rxrpc_queue_local(struct rxrpc_local *local) -{ - unsigned int debug_id = local->debug_id; - int r = refcount_read(&local->ref); - int u = atomic_read(&local->active_users); - - if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(debug_id, rxrpc_local_queued, r, u); - else - rxrpc_put_local(local, rxrpc_local_put_already_queued); -} - /* * Drop a ref on a local endpoint. */ @@ -374,7 +355,7 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local, /* * Cease using a local endpoint. Once the number of active users reaches 0, we - * start the closure of the transport in the work processor. + * start the closure of the transport in the I/O thread.. */ void rxrpc_unuse_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { @@ -416,52 +397,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) /* At this point, there should be no more packets coming in to the * local endpoint. */ - rxrpc_purge_queue(&local->reject_queue); - rxrpc_purge_queue(&local->event_queue); rxrpc_purge_queue(&local->rx_queue); } -/* - * Process events on an endpoint. The work item carries a ref which - * we must release. - */ -static void rxrpc_local_processor(struct work_struct *work) -{ - struct rxrpc_local *local = - container_of(work, struct rxrpc_local, processor); - bool again; - - if (local->dead) - return; - - rxrpc_see_local(local, rxrpc_local_processing); - - do { - again = false; - if (!__rxrpc_use_local(local, rxrpc_local_use_work)) - break; - - if (!list_empty(&local->ack_tx_queue)) { - rxrpc_transmit_ack_packets(local); - again = true; - } - - if (!skb_queue_empty(&local->reject_queue)) { - rxrpc_reject_packets(local); - again = true; - } - - if (!skb_queue_empty(&local->event_queue)) { - rxrpc_process_local_events(local); - again = true; - } - - __rxrpc_unuse_local(local, rxrpc_local_unuse_work); - } while (again); - - rxrpc_put_local(local, rxrpc_local_put_queue); -} - /* * Destroy a local endpoint after the RCU grace period expires. */ @@ -469,13 +407,8 @@ static void rxrpc_local_rcu(struct rcu_head *rcu) { struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu); - _enter("%d", local->debug_id); - - ASSERT(!work_pending(&local->processor)); - rxrpc_see_local(local, rxrpc_local_free); kfree(local); - _leave(""); } /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 71963b4523be..2ea1fa1b8a6f 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -229,11 +229,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; - if (txb->ack.reason == RXRPC_ACK_DELAY) - clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); - if (txb->ack.reason == RXRPC_ACK_IDLE) - clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); - n = rxrpc_fill_out_ack(conn, call, txb); if (n == 0) return 0; @@ -247,8 +242,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); - if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) - call->acks_lost_ping = serial; if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); @@ -588,21 +581,20 @@ send_fragmentable: } /* - * reject packets through the local endpoint + * Reject a packet through the local endpoint. */ -void rxrpc_reject_packets(struct rxrpc_local *local) +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { - struct sockaddr_rxrpc srx; - struct rxrpc_skb_priv *sp; struct rxrpc_wire_header whdr; - struct sk_buff *skb; + struct sockaddr_rxrpc srx; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; struct kvec iov[2]; size_t size; __be32 code; int ret, ioc; - _enter("%d", local->debug_id); + rxrpc_see_skb(skb, rxrpc_skb_see_reject); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -616,52 +608,42 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); - while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_see_reject); - sp = rxrpc_skb(skb); + switch (skb->mark) { + case RXRPC_SKB_MARK_REJECT_BUSY: + whdr.type = RXRPC_PACKET_TYPE_BUSY; + size = sizeof(whdr); + ioc = 1; + break; + case RXRPC_SKB_MARK_REJECT_ABORT: + whdr.type = RXRPC_PACKET_TYPE_ABORT; + code = htonl(skb->priority); + size = sizeof(whdr) + sizeof(code); + ioc = 2; + break; + default: + return; + } - switch (skb->mark) { - case RXRPC_SKB_MARK_REJECT_BUSY: - whdr.type = RXRPC_PACKET_TYPE_BUSY; - size = sizeof(whdr); - ioc = 1; - break; - case RXRPC_SKB_MARK_REJECT_ABORT: - whdr.type = RXRPC_PACKET_TYPE_ABORT; - code = htonl(skb->priority); - size = sizeof(whdr) + sizeof(code); - ioc = 2; - break; - default: - rxrpc_free_skb(skb, rxrpc_skb_put_input); - continue; - } + if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { + msg.msg_namelen = srx.transport_len; - if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { - msg.msg_namelen = srx.transport_len; - - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.serviceId = htons(sp->hdr.serviceId); - whdr.flags = sp->hdr.flags; - whdr.flags ^= RXRPC_CLIENT_INITIATED; - whdr.flags &= RXRPC_CLIENT_INITIATED; - - iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); - ret = do_udp_sendmsg(local->socket, &msg, size); - if (ret < 0) - trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_point_reject); - else - trace_rxrpc_tx_packet(local->debug_id, &whdr, - rxrpc_tx_point_reject); - } + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.serviceId = htons(sp->hdr.serviceId); + whdr.flags = sp->hdr.flags; + whdr.flags ^= RXRPC_CLIENT_INITIATED; + whdr.flags &= RXRPC_CLIENT_INITIATED; - rxrpc_free_skb(skb, rxrpc_skb_put_input); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); + ret = do_udp_sendmsg(local->socket, &msg, size); + if (ret < 0) + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_point_reject); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_reject); } - - _leave(""); } /* diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 97d017ca3dc4..fb8096e93d2c 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -18,9 +18,9 @@ #include #include "ar-internal.h" -static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); -static void rxrpc_distribute_error(struct rxrpc_peer *, int, - enum rxrpc_call_completion); +static void rxrpc_store_error(struct rxrpc_peer *, struct sk_buff *); +static void rxrpc_distribute_error(struct rxrpc_peer *, struct sk_buff *, + enum rxrpc_call_completion, int); /* * Find the peer associated with a local error. @@ -161,7 +161,7 @@ void rxrpc_input_error(struct rxrpc_local *local, struct sk_buff *skb) goto out; } - rxrpc_store_error(peer, serr); + rxrpc_store_error(peer, skb); out: rxrpc_put_peer(peer, rxrpc_peer_put_input_error); } @@ -169,19 +169,15 @@ out: /* * Map an error report to error codes on the peer record. */ -static void rxrpc_store_error(struct rxrpc_peer *peer, - struct sock_exterr_skb *serr) +static void rxrpc_store_error(struct rxrpc_peer *peer, struct sk_buff *skb) { enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR; - struct sock_extended_err *ee; - int err; + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + struct sock_extended_err *ee = &serr->ee; + int err = ee->ee_errno; _enter(""); - ee = &serr->ee; - - err = ee->ee_errno; - switch (ee->ee_origin) { case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: @@ -197,14 +193,14 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; } - rxrpc_distribute_error(peer, err, compl); + rxrpc_distribute_error(peer, skb, compl, err); } /* * Distribute an error that occurred on a peer. */ -static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, - enum rxrpc_call_completion compl) +static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, + enum rxrpc_call_completion compl, int err) { struct rxrpc_call *call; HLIST_HEAD(error_targets); @@ -219,7 +215,8 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, spin_unlock(&peer->lock); rxrpc_see_call(call, rxrpc_call_see_distribute_error); - rxrpc_set_call_completion(call, compl, 0, -error); + rxrpc_set_call_completion(call, compl, 0, -err); + rxrpc_input_call_event(call, skb); spin_lock(&peer->lock); } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 5df7f468abed..77d03b9e4c4c 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -253,11 +253,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) acked = atomic_add_return(call->rx_consumed - old_consumed, &call->ackr_nr_consumed); if (acked > 2 && - !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_rotate_rx); - rxrpc_transmit_ack_packets(call->peer->local); - } + !test_and_set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) + rxrpc_poke_call(call, rxrpc_call_poke_idle); } /* @@ -377,7 +374,7 @@ done: trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) - set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); + set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); return ret; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 11af37275d5b..58e0a36f6aa9 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -170,7 +170,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, { unsigned long now; rxrpc_seq_t seq = txb->seq; - bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; rxrpc_inc_stat(call->rxnet, stat_tx_data); @@ -188,6 +188,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, /* Add the packet to the call's output buffer */ spin_lock(&call->tx_lock); + poke = list_empty(&call->tx_sendmsg); list_add_tail(&txb->call_link, &call->tx_sendmsg); call->tx_prepared = seq; spin_unlock(&call->tx_lock); @@ -220,11 +221,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, write_unlock_bh(&call->state_lock); } - - /* Stick the packet on the crypto queue or the transmission queue as - * appropriate. - */ - rxrpc_queue_call(call, rxrpc_call_queue_tx_data); + if (poke) + rxrpc_poke_call(call, rxrpc_call_poke_start); } /* -- cgit v1.2.3 From 32cf8edb079a6a687a2b5dba39a813a0bbd0ddf9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Nov 2022 13:47:35 +0000 Subject: rxrpc: Trace/count transmission underflows and cwnd resets Add a tracepoint to log when a cwnd reset occurs due to lack of transmission on a call. Add stat counters to count transmission underflows (ie. when we have tx window space, but sendmsg doesn't manage to keep up), cwnd resets and transmission failures. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 38 ++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 3 +++ net/rxrpc/call_event.c | 4 +++- net/rxrpc/input.c | 7 +++++-- net/rxrpc/output.c | 2 ++ net/rxrpc/proc.c | 14 ++++++++++---- 6 files changed, 61 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c49b0c233594..b41e913ae78a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1446,6 +1446,44 @@ TRACE_EVENT(rxrpc_congest, __entry->sum.retrans_timeo ? " rTxTo" : "") ); +TRACE_EVENT(rxrpc_reset_cwnd, + TP_PROTO(struct rxrpc_call *call, ktime_t now), + + TP_ARGS(call, now), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_congest_mode, mode ) + __field(unsigned short, cwnd ) + __field(unsigned short, extra ) + __field(rxrpc_seq_t, hard_ack ) + __field(rxrpc_seq_t, prepared ) + __field(ktime_t, since_last_tx ) + __field(bool, has_data ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->mode = call->cong_mode; + __entry->cwnd = call->cong_cwnd; + __entry->extra = call->cong_extra; + __entry->hard_ack = call->acks_hard_ack; + __entry->prepared = call->tx_prepared - call->tx_bottom; + __entry->since_last_tx = ktime_sub(now, call->tx_last_sent); + __entry->has_data = !list_empty(&call->tx_sendmsg); + ), + + TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu d=%u", + __entry->call, + __entry->hard_ack, + __print_symbolic(__entry->mode, rxrpc_congest_modes), + __entry->cwnd, + __entry->extra, + __entry->prepared, + ktime_to_ns(__entry->since_last_tx), + __entry->has_data) + ); + TRACE_EVENT(rxrpc_disconnect_call, TP_PROTO(struct rxrpc_call *call), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6b993a3d4186..6cfe366ee224 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -101,6 +101,9 @@ struct rxrpc_net { atomic_t stat_tx_data_retrans; atomic_t stat_tx_data_send; atomic_t stat_tx_data_send_frag; + atomic_t stat_tx_data_send_fail; + atomic_t stat_tx_data_underflow; + atomic_t stat_tx_data_cwnd_reset; atomic_t stat_rx_data; atomic_t stat_rx_data_reqack; atomic_t stat_rx_data_jumbo; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 18591f9ecc6a..9f1e490ab976 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -317,8 +317,10 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (!rxrpc_tx_window_has_space(call)) return; - if (list_empty(&call->tx_sendmsg)) + if (list_empty(&call->tx_sendmsg)) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_underflow); return; + } rxrpc_decant_prepared_tx(call); break; default: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index dd2ac5d55e1c..2988e3d0c1f6 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -27,6 +27,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, enum rxrpc_congest_change change = rxrpc_cong_no_change; unsigned int cumulative_acks = call->cong_cumul_acks; unsigned int cwnd = call->cong_cwnd; + ktime_t now; bool resend = false; summary->flight_size = @@ -59,13 +60,15 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, /* If we haven't transmitted anything for >1RTT, we should reset the * congestion management state. */ + now = ktime_get_real(); if ((call->cong_mode == RXRPC_CALL_SLOW_START || call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && ktime_before(ktime_add_us(call->tx_last_sent, - call->peer->srtt_us >> 3), - ktime_get_real()) + call->peer->srtt_us >> 3), now) ) { + trace_rxrpc_reset_cwnd(call, now); change = rxrpc_cong_idle_reset; + rxrpc_inc_stat(call->rxnet, stat_tx_data_cwnd_reset); summary->mode = RXRPC_CALL_SLOW_START; if (RXRPC_TX_SMSS > 2190) summary->cwnd = 2; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index e5d715b855fc..8147a47d1702 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -485,6 +485,7 @@ dont_set_request_ack: up_read(&conn->local->defrag_sem); if (ret < 0) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); @@ -567,6 +568,7 @@ send_fragmentable: } if (ret < 0) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 5af7c8ee4b1a..6816934cb4cf 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -398,13 +398,16 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(seq)); seq_printf(seq, - "Data : send=%u sendf=%u\n", + "Data : send=%u sendf=%u fail=%u\n", atomic_read(&rxnet->stat_tx_data_send), - atomic_read(&rxnet->stat_tx_data_send_frag)); + atomic_read(&rxnet->stat_tx_data_send_frag), + atomic_read(&rxnet->stat_tx_data_send_fail)); seq_printf(seq, - "Data-Tx : nr=%u retrans=%u\n", + "Data-Tx : nr=%u retrans=%u uf=%u cwr=%u\n", atomic_read(&rxnet->stat_tx_data), - atomic_read(&rxnet->stat_tx_data_retrans)); + atomic_read(&rxnet->stat_tx_data_retrans), + atomic_read(&rxnet->stat_tx_data_underflow), + atomic_read(&rxnet->stat_tx_data_cwnd_reset)); seq_printf(seq, "Data-Rx : nr=%u reqack=%u jumbo=%u\n", atomic_read(&rxnet->stat_rx_data), @@ -472,8 +475,11 @@ int rxrpc_stats_clear(struct file *file, char *buf, size_t size) atomic_set(&rxnet->stat_tx_data, 0); atomic_set(&rxnet->stat_tx_data_retrans, 0); + atomic_set(&rxnet->stat_tx_data_underflow, 0); + atomic_set(&rxnet->stat_tx_data_cwnd_reset, 0); atomic_set(&rxnet->stat_tx_data_send, 0); atomic_set(&rxnet->stat_tx_data_send_frag, 0); + atomic_set(&rxnet->stat_tx_data_send_fail, 0); atomic_set(&rxnet->stat_rx_data, 0); atomic_set(&rxnet->stat_rx_data_reqack, 0); atomic_set(&rxnet->stat_rx_data_jumbo, 0); -- cgit v1.2.3 From b0346843b1076b34a0278ff601f8f287535cb064 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:13 +0000 Subject: rxrpc: Transmit ACKs at the point of generation For ACKs generated inside the I/O thread, transmit the ACK at the point of generation. Where the ACK is generated outside of the I/O thread, it's offloaded to the I/O thread to transmit it. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 --- net/rxrpc/ar-internal.h | 5 +---- net/rxrpc/call_event.c | 17 ++--------------- net/rxrpc/io_thread.c | 5 ----- net/rxrpc/local_object.c | 2 -- net/rxrpc/output.c | 42 ++---------------------------------------- net/rxrpc/recvmsg.c | 3 --- net/rxrpc/sendmsg.c | 2 -- net/rxrpc/txbuf.c | 1 - 9 files changed, 5 insertions(+), 75 deletions(-) (limited to 'include') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b41e913ae78a..049b52e7aa6a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -63,7 +63,6 @@ EM(rxrpc_local_put_peer, "PUT peer ") \ EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ - EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ EM(rxrpc_local_stop, "STOP ") \ EM(rxrpc_local_stopped, "STOPPED ") \ EM(rxrpc_local_unuse_bind, "UNU bind ") \ @@ -156,7 +155,6 @@ EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ - EM(rxrpc_call_get_send_ack, "GET send-ack") \ EM(rxrpc_call_get_userid, "GET user-id ") \ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ @@ -168,7 +166,6 @@ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ - EM(rxrpc_call_put_send_ack, "PUT send-ack") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 2a4928249a64..e7dccab7b741 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -287,8 +287,6 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; - struct list_head ack_tx_queue; /* List of ACKs that need sending */ - spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head rx_queue; /* Received packets */ @@ -762,7 +760,6 @@ struct rxrpc_txbuf { struct rcu_head rcu; struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ - struct rxrpc_call *call; /* Call to which belongs */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ @@ -1047,7 +1044,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -void rxrpc_transmit_ack_packets(struct rxrpc_local *); +int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index fd122e3726bd..b2cf448fb02c 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -69,7 +69,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - struct rxrpc_local *local = call->conn->local; struct rxrpc_txbuf *txb; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -96,17 +95,9 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, txb->ack.reason = ack_reason; txb->ack.nAcks = 0; - if (!rxrpc_try_get_call(call, rxrpc_call_get_send_ack)) { - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); - return; - } - - spin_lock(&local->ack_tx_lock); - list_add_tail(&txb->tx_link, &local->ack_tx_queue); - spin_unlock(&local->ack_tx_lock); trace_rxrpc_send_ack(call, why, ack_reason, serial); - - rxrpc_wake_up_io_thread(local); + rxrpc_send_ack_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } /* @@ -294,10 +285,6 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) rxrpc_transmit_one(call, txb); - // TODO: Drain the transmission buffers. Do this somewhere better - if (after(call->acks_hard_ack, call->tx_bottom + 16)) - rxrpc_shrink_call_tx_buffer(call); - if (!rxrpc_tx_window_has_space(call)) break; } diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 19aa315eddf5..d83ae3193032 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -447,11 +447,6 @@ int rxrpc_io_thread(void *data) continue; } - if (!list_empty(&local->ack_tx_queue)) { - rxrpc_transmit_ack_packets(local); - continue; - } - /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 1e994a83db2b..44222923c0d1 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -96,8 +96,6 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); - INIT_LIST_HEAD(&local->ack_tx_queue); - spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->call_attend_q); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8147a47d1702..3d8c9f830ee0 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -203,12 +203,11 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, } /* - * Send an ACK call packet. + * Transmit an ACK packet. */ -static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) +int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; - struct rxrpc_call *call = txb->call; struct msghdr msg; struct kvec iov[1]; rxrpc_serial_t serial; @@ -271,43 +270,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * return ret; } -/* - * ACK transmitter for a local endpoint. The UDP socket locks around each - * transmission, so we can only transmit one packet at a time, ACK, DATA or - * otherwise. - */ -void rxrpc_transmit_ack_packets(struct rxrpc_local *local) -{ - LIST_HEAD(queue); - int ret; - - rxrpc_see_local(local, rxrpc_local_see_tx_ack); - - if (list_empty(&local->ack_tx_queue)) - return; - - spin_lock(&local->ack_tx_lock); - list_splice_tail_init(&local->ack_tx_queue, &queue); - spin_unlock(&local->ack_tx_lock); - - while (!list_empty(&queue)) { - struct rxrpc_txbuf *txb = - list_entry(queue.next, struct rxrpc_txbuf, tx_link); - - ret = rxrpc_send_ack_packet(local, txb); - if (ret < 0 && ret != -ECONNRESET) { - spin_lock(&local->ack_tx_lock); - list_splice_init(&queue, &local->ack_tx_queue); - spin_unlock(&local->ack_tx_lock); - break; - } - - list_del_init(&txb->tx_link); - rxrpc_put_call(txb->call, rxrpc_call_put_send_ack); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); - } -} - /* * Send an ABORT call packet. */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3a8576e9daf3..36b25d003cf0 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -320,7 +320,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ret = ret2; goto out; } - rxrpc_transmit_ack_packets(call->peer->local); } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -502,7 +501,6 @@ try_again: if (ret == -EAGAIN) ret = 0; - rxrpc_transmit_ack_packets(call->peer->local); if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; @@ -632,7 +630,6 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->dest_srx.srx_service; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 2c861c55ed70..9fa7e37f7155 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -276,8 +276,6 @@ reload: rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { - rxrpc_transmit_ack_packets(call->peer->local); - if (!txb) { size_t remain, bufsize, chunk, offset; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index a5054389dfbb..d2cf2aac3adb 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -26,7 +26,6 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, INIT_LIST_HEAD(&txb->call_link); INIT_LIST_HEAD(&txb->tx_link); refcount_set(&txb->ref, 1); - txb->call = call; txb->call_debug_id = call->debug_id; txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); txb->space = sizeof(txb->data); -- cgit v1.2.3 From 7d360f6061db01830adfdb1eaa3977b19db0c30b Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 10 Oct 2022 11:43:38 +0200 Subject: wifi: mac80211: add support for restricting netdev features per vif This can be used to selectively disable feature flags for checksum offload, scatter/gather or GSO by changing vif->netdev_features. Removing features from vif->netdev_features does not affect the netdev features themselves, but instead fixes up skbs in the tx path so that the offloads are not needed in the driver. Aside from making it easier to deal with vif type based hardware limitations, this also makes it possible to optimize performance on hardware without native GSO support by declaring GSO support in hw->netdev_features and removing it from vif->netdev_features. This allows mac80211 to handle GSO segmentation after the sta lookup, but before itxq enqueue, thus reducing the number of unnecessary sta lookups, as well as some other per-packet processing. Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20221010094338.78070-1-nbd@nbd.name Signed-off-by: Johannes Berg --- include/net/fq_impl.h | 16 +-- include/net/mac80211.h | 5 + net/mac80211/iface.c | 1 + net/mac80211/tx.c | 283 ++++++++++++++++++++++++++++++++----------------- 4 files changed, 202 insertions(+), 103 deletions(-) (limited to 'include') diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index 524b510f1c68..9467e33dfb36 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -200,6 +200,7 @@ static void fq_tin_enqueue(struct fq *fq, fq_skb_free_t free_func) { struct fq_flow *flow; + struct sk_buff *next; bool oom; lockdep_assert_held(&fq->lock); @@ -214,11 +215,15 @@ static void fq_tin_enqueue(struct fq *fq, } flow->tin = tin; - flow->backlog += skb->len; - tin->backlog_bytes += skb->len; - tin->backlog_packets++; - fq->memory_usage += skb->truesize; - fq->backlog++; + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); + flow->backlog += skb->len; + tin->backlog_bytes += skb->len; + tin->backlog_packets++; + fq->memory_usage += skb->truesize; + fq->backlog++; + __skb_queue_tail(&flow->queue, skb); + } if (list_empty(&flow->flowchain)) { flow->deficit = fq->quantum; @@ -226,7 +231,6 @@ static void fq_tin_enqueue(struct fq *fq, &tin->new_flows); } - __skb_queue_tail(&flow->queue, skb); oom = (fq->memory_usage > fq->memory_limit); while (fq->backlog > fq->limit || oom) { flow = fq_find_fattest_flow(fq); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 721c450a9ccd..689da327ce2e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1807,6 +1807,10 @@ struct ieee80211_vif_cfg { * @addr: address of this interface * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively + * @netdev_features: tx netdev features supported by the hardware for this + * vif. mac80211 initializes this to hw->netdev_features, and the driver + * can mask out specific tx features. mac80211 will handle software fixup + * for masked offloads (GSO, CSUM) * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed @@ -1848,6 +1852,7 @@ struct ieee80211_vif { struct ieee80211_txq *txq; + netdev_features_t netdev_features; u32 driver_flags; u32 offload_flags; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 7b2843df3813..d49a5906a943 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -2178,6 +2178,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ndev->hw_features |= ndev->features & MAC80211_SUPPORTED_FEATURES_TX; + sdata->vif.netdev_features = local->hw.netdev_features; netdev_set_default_ethtool_ops(ndev, &ieee80211_ethtool_ops); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 774e62860c45..2171cd1ca807 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1355,7 +1355,11 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb) { - IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time(); + struct sk_buff *next; + codel_time_t now = codel_get_time(); + + skb_list_walk_safe(skb, skb, next) + IEEE80211_SKB_CB(skb)->control.enqueue_time = now; } static u32 codel_skb_len_func(const struct sk_buff *skb) @@ -3578,55 +3582,79 @@ ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, return TX_CONTINUE; } -static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, - struct ieee80211_fast_tx *fast_tx, - struct sk_buff *skb) +static netdev_features_t +ieee80211_sdata_netdev_features(struct ieee80211_sub_if_data *sdata) { - struct ieee80211_local *local = sdata->local; - u16 ethertype = (skb->data[12] << 8) | skb->data[13]; - int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2); - int hw_headroom = sdata->local->hw.extra_tx_headroom; - struct ethhdr eth; - struct ieee80211_tx_info *info; - struct ieee80211_hdr *hdr = (void *)fast_tx->hdr; - struct ieee80211_tx_data tx; - ieee80211_tx_result r; - struct tid_ampdu_tx *tid_tx = NULL; - u8 tid = IEEE80211_NUM_TIDS; + if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN) + return sdata->vif.netdev_features; - /* control port protocol needs a lot of special handling */ - if (cpu_to_be16(ethertype) == sdata->control_port_protocol) - return false; + if (!sdata->bss) + return 0; - /* only RFC 1042 SNAP */ - if (ethertype < ETH_P_802_3_MIN) - return false; + sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); + return sdata->vif.netdev_features; +} - /* don't handle TX status request here either */ - if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS) - return false; +static struct sk_buff * +ieee80211_tx_skb_fixup(struct sk_buff *skb, netdev_features_t features) +{ + if (skb_is_gso(skb)) { + struct sk_buff *segs; - if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { - tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; - tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); - if (tid_tx) { - if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) - return false; - if (tid_tx->timeout) - tid_tx->last_tx = jiffies; - } + segs = skb_gso_segment(skb, features); + if (!segs) + return skb; + if (IS_ERR(segs)) + goto free; + + consume_skb(skb); + return segs; } - /* after this point (skb is modified) we cannot return false */ + if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) + goto free; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + int ofs = skb_checksum_start_offset(skb); + + if (skb->encapsulation) + skb_set_inner_transport_header(skb, ofs); + else + skb_set_transport_header(skb, ofs); + + if (skb_csum_hwoffload_help(skb, features)) + goto free; + } + + skb_mark_not_on_list(skb); + return skb; + +free: + kfree_skb(skb); + return NULL; +} + +static void __ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct ieee80211_fast_tx *fast_tx, + struct sk_buff *skb, u8 tid, bool ampdu) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr = (void *)fast_tx->hdr; + struct ieee80211_tx_info *info; + struct ieee80211_tx_data tx; + ieee80211_tx_result r; + int hw_headroom = sdata->local->hw.extra_tx_headroom; + int extra_head = fast_tx->hdr_len - (ETH_HLEN - 2); + struct ethhdr eth; skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) - return true; + return; if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) && ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb)) - return true; + return; /* will not be crypto-handled beyond what we do here, so use false * as the may-encrypt argument for the resize to not account for @@ -3635,10 +3663,8 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, if (unlikely(ieee80211_skb_resize(sdata, skb, max_t(int, extra_head + hw_headroom - skb_headroom(skb), 0), - ENCRYPT_NO))) { - kfree_skb(skb); - return true; - } + ENCRYPT_NO))) + goto free; memcpy(ð, skb->data, ETH_HLEN - 2); hdr = skb_push(skb, extra_head); @@ -3652,7 +3678,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, info->control.vif = &sdata->vif; info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT | IEEE80211_TX_CTL_DONTFRAG | - (tid_tx ? IEEE80211_TX_CTL_AMPDU : 0); + (ampdu ? IEEE80211_TX_CTL_AMPDU : 0); info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT | u32_encode_bits(IEEE80211_LINK_UNSPECIFIED, IEEE80211_TX_CTRL_MLO_LINK); @@ -3676,16 +3702,14 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, tx.key = fast_tx->key; if (ieee80211_queue_skb(local, sdata, sta, skb)) - return true; + return; tx.skb = skb; r = ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs, fast_tx->key, &tx); tx.skb = NULL; - if (r == TX_DROP) { - kfree_skb(skb); - return true; - } + if (r == TX_DROP) + goto free; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, @@ -3693,6 +3717,56 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, __skb_queue_tail(&tx.skbs, skb); ieee80211_tx_frags(local, &sdata->vif, sta, &tx.skbs, false); + return; + +free: + kfree_skb(skb); +} + +static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct ieee80211_fast_tx *fast_tx, + struct sk_buff *skb) +{ + u16 ethertype = (skb->data[12] << 8) | skb->data[13]; + struct ieee80211_hdr *hdr = (void *)fast_tx->hdr; + struct tid_ampdu_tx *tid_tx = NULL; + struct sk_buff *next; + u8 tid = IEEE80211_NUM_TIDS; + + /* control port protocol needs a lot of special handling */ + if (cpu_to_be16(ethertype) == sdata->control_port_protocol) + return false; + + /* only RFC 1042 SNAP */ + if (ethertype < ETH_P_802_3_MIN) + return false; + + /* don't handle TX status request here either */ + if (skb->sk && skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS) + return false; + + if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) { + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; + tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); + if (tid_tx) { + if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) + return false; + if (tid_tx->timeout) + tid_tx->last_tx = jiffies; + } + } + + /* after this point (skb is modified) we cannot return false */ + skb = ieee80211_tx_skb_fixup(skb, ieee80211_sdata_netdev_features(sdata)); + if (!skb) + return true; + + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); + __ieee80211_xmit_fast(sdata, sta, fast_tx, skb, tid, tid_tx); + } + return true; } @@ -4192,31 +4266,14 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, goto out; } - if (skb_is_gso(skb)) { - struct sk_buff *segs; - - segs = skb_gso_segment(skb, 0); - if (IS_ERR(segs)) { - goto out_free; - } else if (segs) { - consume_skb(skb); - skb = segs; - } - } else { - /* we cannot process non-linear frames on this path */ - if (skb_linearize(skb)) - goto out_free; - - /* the frame could be fragmented, software-encrypted, and other - * things so we cannot really handle checksum offload with it - - * fix it up in software before we handle anything else. - */ - if (skb->ip_summed == CHECKSUM_PARTIAL) { - skb_set_transport_header(skb, - skb_checksum_start_offset(skb)); - if (skb_checksum_help(skb)) - goto out_free; - } + /* the frame could be fragmented, software-encrypted, and other + * things so we cannot really handle checksum or GSO offload. + * fix it up in software before we handle anything else. + */ + skb = ieee80211_tx_skb_fixup(skb, 0); + if (!skb) { + len = 0; + goto out; } skb_list_walk_safe(skb, skb, next) { @@ -4434,9 +4491,11 @@ normal: return NETDEV_TX_OK; } -static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, struct sta_info *sta, - bool txpending) + + +static bool __ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, struct sta_info *sta, + bool txpending) { struct ieee80211_local *local = sdata->local; struct ieee80211_tx_control control = {}; @@ -4445,14 +4504,6 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, unsigned long flags; int q = info->hw_queue; - if (sta) - sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift); - - ieee80211_tpt_led_trig_tx(local, skb->len); - - if (ieee80211_queue_skb(local, sdata, sta, skb)) - return true; - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); if (local->queue_stop_reasons[q] || @@ -4479,6 +4530,26 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, return true; } +static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb, struct sta_info *sta, + bool txpending) +{ + struct ieee80211_local *local = sdata->local; + struct sk_buff *next; + bool ret = true; + + if (ieee80211_queue_skb(local, sdata, sta, skb)) + return true; + + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); + if (!__ieee80211_tx_8023(sdata, skb, sta, txpending)) + ret = false; + } + + return ret; +} + static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct net_device *dev, struct sta_info *sta, struct ieee80211_key *key, struct sk_buff *skb) @@ -4486,9 +4557,13 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_info *info; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; + struct sk_buff *seg, *next; + unsigned int skbs = 0, len = 0; + u16 queue; u8 tid; - skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, sta, skb)); + queue = ieee80211_select_queue(sdata, sta, skb); + skb_set_queue_mapping(skb, queue); if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) @@ -4498,9 +4573,6 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, if (unlikely(!skb)) return; - info = IEEE80211_SKB_CB(skb); - memset(info, 0, sizeof(*info)); - ieee80211_aggr_check(sdata, sta, skb); tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; @@ -4514,22 +4586,20 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, return; } - info->flags |= IEEE80211_TX_CTL_AMPDU; if (tid_tx->timeout) tid_tx->last_tx = jiffies; } - if (unlikely(skb->sk && - skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) - info->ack_frame_id = ieee80211_store_ack_skb(local, skb, - &info->flags, NULL); - - info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)]; + skb = ieee80211_tx_skb_fixup(skb, ieee80211_sdata_netdev_features(sdata)); + if (!skb) + return; - dev_sw_netstats_tx_add(dev, 1, skb->len); + info = IEEE80211_SKB_CB(skb); + memset(info, 0, sizeof(*info)); + if (tid_tx) + info->flags |= IEEE80211_TX_CTL_AMPDU; - sta->deflink.tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len; - sta->deflink.tx_stats.packets[skb_get_queue_mapping(skb)]++; + info->hw_queue = sdata->vif.hw_queue[queue]; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, @@ -4541,6 +4611,24 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, if (key) info->control.hw_key = &key->conf; + skb_list_walk_safe(skb, seg, next) { + skbs++; + len += seg->len; + if (seg != skb) + memcpy(IEEE80211_SKB_CB(seg), info, sizeof(*info)); + } + + if (unlikely(skb->sk && + skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS)) + info->ack_frame_id = ieee80211_store_ack_skb(local, skb, + &info->flags, NULL); + + dev_sw_netstats_tx_add(dev, skbs, len); + sta->deflink.tx_stats.packets[queue] += skbs; + sta->deflink.tx_stats.bytes[queue] += len; + + ieee80211_tpt_led_trig_tx(local, len); + ieee80211_tx_8023(sdata, skb, sta, false); return; @@ -4582,6 +4670,7 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb, key->conf.cipher == WLAN_CIPHER_SUITE_TKIP)) goto skip_offload; + sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); ieee80211_8023_xmit(sdata, dev, sta, key, skb); goto out; -- cgit v1.2.3 From eb8c507296f6038d46010396d91b42a05c3b64d9 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 23 Nov 2022 17:38:55 +0000 Subject: jump_label: Prevent key->enabled int overflow 1. With CONFIG_JUMP_LABEL=n static_key_slow_inc() doesn't have any protection against key->enabled refcounter overflow. 2. With CONFIG_JUMP_LABEL=y static_key_slow_inc_cpuslocked() still may turn the refcounter negative as (v + 1) may overflow. key->enabled is indeed a ref-counter as it's documented in multiple places: top comment in jump_label.h, Documentation/staging/static-keys.rst, etc. As -1 is reserved for static key that's in process of being enabled, functions would break with negative key->enabled refcount: - for CONFIG_JUMP_LABEL=n negative return of static_key_count() breaks static_key_false(), static_key_true() - the ref counter may become 0 from negative side by too many static_key_slow_inc() calls and lead to use-after-free issues. These flaws result in that some users have to introduce an additional mutex and prevent the reference counter from overflowing themselves, see bpf_enable_runtime_stats() checking the counter against INT_MAX / 2. Prevent the reference counter overflow by checking if (v + 1) > 0. Change functions API to return whether the increment was successful. Signed-off-by: Dmitry Safonov Acked-by: Jakub Kicinski Acked-by: Peter Zijlstra (Intel) Signed-off-by: Jakub Kicinski --- include/linux/jump_label.h | 21 +++++++++++++---- kernel/jump_label.c | 56 ++++++++++++++++++++++++++++++++++++---------- 2 files changed, 61 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 570831ca9951..4e968ebadce6 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -224,9 +224,10 @@ extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); -extern void static_key_slow_inc(struct static_key *key); +extern bool static_key_slow_inc(struct static_key *key); +extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); -extern void static_key_slow_inc_cpuslocked(struct static_key *key); +extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); @@ -278,11 +279,23 @@ static __always_inline bool static_key_true(struct static_key *key) return false; } -static inline void static_key_slow_inc(struct static_key *key) +static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { + int v; + STATIC_KEY_CHECK_USE(key); - atomic_inc(&key->enabled); + /* + * Prevent key->enabled getting negative to follow the same semantics + * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. + */ + v = atomic_read(&key->enabled); + do { + if (v < 0 || (v + 1) < 0) + return false; + } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); + return true; } +#define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 4d6c6f5f60db..d9c822bbffb8 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -113,9 +113,40 @@ int static_key_count(struct static_key *key) } EXPORT_SYMBOL_GPL(static_key_count); -void static_key_slow_inc_cpuslocked(struct static_key *key) +/* + * static_key_fast_inc_not_disabled - adds a user for a static key + * @key: static key that must be already enabled + * + * The caller must make sure that the static key can't get disabled while + * in this function. It doesn't patch jump labels, only adds a user to + * an already enabled static key. + * + * Returns true if the increment was done. Unlike refcount_t the ref counter + * is not saturated, but will fail to increment on overflow. + */ +bool static_key_fast_inc_not_disabled(struct static_key *key) { + int v; + STATIC_KEY_CHECK_USE(key); + /* + * Negative key->enabled has a special meaning: it sends + * static_key_slow_inc() down the slow path, and it is non-zero + * so it counts as "enabled" in jump_label_update(). Note that + * atomic_inc_unless_negative() checks >= 0, so roll our own. + */ + v = atomic_read(&key->enabled); + do { + if (v <= 0 || (v + 1) < 0) + return false; + } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); + + return true; +} +EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); + +bool static_key_slow_inc_cpuslocked(struct static_key *key) +{ lockdep_assert_cpus_held(); /* @@ -124,15 +155,9 @@ void static_key_slow_inc_cpuslocked(struct static_key *key) * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. - * - * So give a special meaning to negative key->enabled: it sends - * static_key_slow_inc() down the slow path, and it is non-zero - * so it counts as "enabled" in jump_label_update(). Note that - * atomic_inc_unless_negative() checks >= 0, so roll our own. */ - for (int v = atomic_read(&key->enabled); v > 0; ) - if (likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))) - return; + if (static_key_fast_inc_not_disabled(key)) + return true; jump_label_lock(); if (atomic_read(&key->enabled) == 0) { @@ -144,16 +169,23 @@ void static_key_slow_inc_cpuslocked(struct static_key *key) */ atomic_set_release(&key->enabled, 1); } else { - atomic_inc(&key->enabled); + if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) { + jump_label_unlock(); + return false; + } } jump_label_unlock(); + return true; } -void static_key_slow_inc(struct static_key *key) +bool static_key_slow_inc(struct static_key *key) { + bool ret; + cpus_read_lock(); - static_key_slow_inc_cpuslocked(key); + ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); + return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); -- cgit v1.2.3 From 459837b522f7dff3b6681f534d8fff4eca19b7d1 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 23 Nov 2022 17:38:57 +0000 Subject: net/tcp: Disable TCP-MD5 static key on tcp_md5sig_info destruction To do that, separate two scenarios: - where it's the first MD5 key on the system, which means that enabling of the static key may need to sleep; - copying of an existing key from a listening socket to the request socket upon receiving a signed TCP segment, where static key was already enabled (when the key was added to the listening socket). Now the life-time of the static branch for TCP-MD5 is until: - last tcp_md5sig_info is destroyed - last socket in time-wait state with MD5 key is closed. Which means that after all sockets with TCP-MD5 keys are gone, the system gets back the performance of disabled md5-key static branch. While at here, provide static_key_fast_inc() helper that does ref counter increment in atomic fashion (without grabbing cpus_read_lock() on CONFIG_JUMP_LABEL=y). This is needed to add a new user for a static_key when the caller controls the lifetime of another user. Signed-off-by: Dmitry Safonov Acked-by: Jakub Kicinski Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 10 +++++-- net/ipv4/tcp.c | 5 +--- net/ipv4/tcp_ipv4.c | 71 +++++++++++++++++++++++++++++++++++++++--------- net/ipv4/tcp_minisocks.c | 16 ++++++++--- net/ipv4/tcp_output.c | 4 +-- net/ipv6/tcp_ipv6.c | 10 +++---- 6 files changed, 84 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index 6b814e788f00..f925377066fe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1675,7 +1675,11 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, - const u8 *newkey, u8 newkeylen, gfp_t gfp); + const u8 *newkey, u8 newkeylen); +int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + struct tcp_md5sig_key *key); + int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags); struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, @@ -1683,7 +1687,7 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, #ifdef CONFIG_TCP_MD5SIG #include -extern struct static_key_false tcp_md5_needed; +extern struct static_key_false_deferred tcp_md5_needed; struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family); @@ -1691,7 +1695,7 @@ static inline struct tcp_md5sig_key * tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { - if (!static_branch_unlikely(&tcp_md5_needed)) + if (!static_branch_unlikely(&tcp_md5_needed.key)) return NULL; return __tcp_md5_do_lookup(sk, l3index, addr, family); } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 24602a5184b0..001947136b0a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4464,11 +4464,8 @@ bool tcp_alloc_md5sig_pool(void) if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) { mutex_lock(&tcp_md5sig_mutex); - if (!tcp_md5sig_pool_populated) { + if (!tcp_md5sig_pool_populated) __tcp_alloc_md5sig_pool(); - if (tcp_md5sig_pool_populated) - static_branch_inc(&tcp_md5_needed); - } mutex_unlock(&tcp_md5sig_mutex); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c72e53835397..5d83a332f1dd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1053,7 +1053,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) * We need to maintain these in the sk structure. */ -DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); +DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); EXPORT_SYMBOL(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) @@ -1166,9 +1166,6 @@ static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - if (rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) - return 0; - md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) return -ENOMEM; @@ -1180,9 +1177,9 @@ static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) } /* This can be called on a newly created socket, from other files */ -int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, int l3index, u8 flags, - const u8 *newkey, u8 newkeylen, gfp_t gfp) +static int __tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; @@ -1209,9 +1206,6 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, return 0; } - if (tcp_md5sig_info_add(sk, gfp)) - return -ENOMEM; - md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); @@ -1235,8 +1229,59 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } + +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, u8 flags, + const u8 *newkey, u8 newkeylen) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) + return -ENOMEM; + + if (!static_branch_inc(&tcp_md5_needed.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, + newkey, newkeylen, GFP_KERNEL); +} EXPORT_SYMBOL(tcp_md5_do_add); +int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, + int family, u8 prefixlen, int l3index, + struct tcp_md5sig_key *key) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) + return -ENOMEM; + + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { + struct tcp_md5sig_info *md5sig; + + md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); + net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); + rcu_assign_pointer(tp->md5sig_info, NULL); + kfree_rcu(md5sig); + return -EUSERS; + } + } + + return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, + key->flags, key->key, key->keylen, + sk_gfp_mask(sk, GFP_ATOMIC)); +} +EXPORT_SYMBOL(tcp_md5_key_copy); + int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) { @@ -1323,7 +1368,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1580,8 +1625,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags, - key->key, key->keylen, GFP_ATOMIC); + tcp_md5_key_copy(newsk, addr, AF_INET, 32, l3index, key); sk_gso_disable(newsk); } #endif @@ -2273,6 +2317,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_clear_md5_list(sk); kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); tp->md5sig_info = NULL; + static_branch_slow_dec_deferred(&tcp_md5_needed); } #endif diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index c375f603a16c..6908812d50d3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -291,13 +291,19 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) */ do { tcptw->tw_md5_key = NULL; - if (static_branch_unlikely(&tcp_md5_needed)) { + if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_md5sig_key *key; key = tp->af_specific->md5_lookup(sk, sk); if (key) { tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); - BUG_ON(tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()); + if (!tcptw->tw_md5_key) + break; + BUG_ON(!tcp_alloc_md5sig_pool()); + if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { + kfree(tcptw->tw_md5_key); + tcptw->tw_md5_key = NULL; + } } } } while (0); @@ -337,11 +343,13 @@ EXPORT_SYMBOL(tcp_time_wait); void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed)) { + if (static_branch_unlikely(&tcp_md5_needed.key)) { struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_key) + if (twsk->tw_md5_key) { kfree_rcu(twsk->tw_md5_key, rcu); + static_branch_slow_dec_deferred(&tcp_md5_needed); + } } #endif } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 894410dc9293..71d01cf3c13e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -766,7 +766,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { @@ -922,7 +922,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - if (static_branch_unlikely(&tcp_md5_needed) && + if (static_branch_unlikely(&tcp_md5_needed.key) && rcu_access_pointer(tp->md5sig_info)) { *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f52b6f271a24..80df917ced5f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -665,12 +665,11 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, if (ipv6_addr_v4mapped(&sin6->sin6_addr)) return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], AF_INET, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, - GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, AF_INET6, prefixlen, l3index, flags, - cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); + cmd.tcpm_key, cmd.tcpm_keylen); } static int tcp_v6_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1370,9 +1369,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, - AF_INET6, 128, l3index, key->flags, key->key, key->keylen, - sk_gfp_mask(sk, GFP_ATOMIC)); + tcp_md5_key_copy(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, + AF_INET6, 128, l3index, key); } #endif -- cgit v1.2.3 From f8c9dfbd875b17fee59c7f1aa35a4944d4e6d810 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 30 Nov 2022 15:06:28 +0100 Subject: mptcp: add pm listener events This patch adds two new MPTCP netlink event types for PM listening socket create and close, named MPTCP_EVENT_LISTENER_CREATED and MPTCP_EVENT_LISTENER_CLOSED. Add a new function mptcp_event_pm_listener() to push the new events with family, port and addr to userspace. Invoke mptcp_event_pm_listener() with MPTCP_EVENT_LISTENER_CREATED in mptcp_listen() and mptcp_pm_nl_create_listen_socket(), invoke it with MPTCP_EVENT_LISTENER_CLOSED in __mptcp_close_ssk(). Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 9 ++++++++ net/mptcp/pm_netlink.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++ net/mptcp/protocol.c | 3 +++ net/mptcp/protocol.h | 2 ++ 4 files changed, 71 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index dfe19bf13f4c..32af2d278cb4 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -160,6 +160,12 @@ struct mptcp_info { * daddr4 | daddr6, sport, dport, backup, if_idx * [, error] * The priority of a subflow has changed. 'error' should not be set. + * + * MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 + * A new PM listener is created. + * + * MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 + * A PM listener is closed. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, @@ -174,6 +180,9 @@ enum mptcp_event_type { MPTCP_EVENT_SUB_CLOSED = 11, MPTCP_EVENT_SUB_PRIORITY = 13, + + MPTCP_EVENT_LISTENER_CREATED = 15, + MPTCP_EVENT_LISTENER_CLOSED = 16, }; enum mptcp_event_attr { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d66fbd558263..eef69d0e44ec 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1029,6 +1029,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; + mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); + return 0; } @@ -2152,6 +2154,58 @@ nla_put_failure: kfree_skb(skb); } +void mptcp_event_pm_listener(const struct sock *ssk, + enum mptcp_event_type event) +{ + const struct inet_sock *issk = inet_sk(ssk); + struct net *net = sock_net(ssk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, event); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) + goto nla_put_failure; + + if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) + goto nla_put_failure; + + switch (ssk->sk_family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) + goto nla_put_failure; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: { + const struct ipv6_pinfo *np = inet6_sk(ssk); + + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + goto nla_put_failure; + break; + } +#endif + default: + WARN_ON_ONCE(1); + goto nla_put_failure; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_KERNEL); + return; + +nla_put_failure: + kfree_skb(skb); +} + void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { @@ -2197,6 +2251,9 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, if (mptcp_event_sub_closed(skb, msk, ssk) < 0) goto nla_put_failure; break; + case MPTCP_EVENT_LISTENER_CREATED: + case MPTCP_EVENT_LISTENER_CLOSED: + break; } genlmsg_end(skb, nlh); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b0d387be500a..f6f93957275b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2355,6 +2355,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(ssk); inet_csk_listen_stop(ssk); + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); } __tcp_close(ssk, 0); @@ -3647,6 +3648,8 @@ static int mptcp_listen(struct socket *sock, int backlog) if (!err) mptcp_copy_inaddrs(sock->sk, ssock->sk); + mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); + unlock: release_sock(sock->sk); return err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8b4379a2cd85..955fb3d88eb3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -839,6 +839,8 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_info *info); void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); +void mptcp_event_pm_listener(const struct sock *ssk, + enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, -- cgit v1.2.3 From 7d802c8098c50fb7dcf5dfcb6466482e1f2b15e4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 30 Nov 2022 18:04:31 -0500 Subject: sctp: delete free member from struct sctp_sched_ops After commit 9ed7bfc79542 ("sctp: fix memory leak in sctp_stream_outq_migrate()"), sctp_sched_set_sched() is the only place calling sched->free(), and it can actually be replaced by sched->free_sid() on each stream, and yet there's already a loop to traverse all streams in sctp_sched_set_sched(). This patch adds a function sctp_sched_free_sched() where it calls sched->free_sid() for each stream to replace sched->free() calls in sctp_sched_set_sched() and then deletes the unused free member from struct sctp_sched_ops. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/e10aac150aca2686cb0bd0570299ec716da5a5c0.1669849471.git.lucien.xin@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sctp/stream_sched.h | 2 -- net/sctp/stream_sched.c | 38 ++++++++++++++++++++------------------ net/sctp/stream_sched_prio.c | 27 --------------------------- net/sctp/stream_sched_rr.c | 6 ------ 4 files changed, 20 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h index 65058faea4db..fa00dc20a0d7 100644 --- a/include/net/sctp/stream_sched.h +++ b/include/net/sctp/stream_sched.h @@ -28,8 +28,6 @@ struct sctp_sched_ops { int (*init_sid)(struct sctp_stream *stream, __u16 sid, gfp_t gfp); /* free a stream */ void (*free_sid)(struct sctp_stream *stream, __u16 sid); - /* Frees the entire thing */ - void (*free)(struct sctp_stream *stream); /* Enqueue a chunk */ void (*enqueue)(struct sctp_outq *q, struct sctp_datamsg *msg); diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 7c8f9d89e16a..330067002deb 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -50,10 +50,6 @@ static void sctp_sched_fcfs_free_sid(struct sctp_stream *stream, __u16 sid) { } -static void sctp_sched_fcfs_free(struct sctp_stream *stream) -{ -} - static void sctp_sched_fcfs_enqueue(struct sctp_outq *q, struct sctp_datamsg *msg) { @@ -101,7 +97,6 @@ static struct sctp_sched_ops sctp_sched_fcfs = { .init = sctp_sched_fcfs_init, .init_sid = sctp_sched_fcfs_init_sid, .free_sid = sctp_sched_fcfs_free_sid, - .free = sctp_sched_fcfs_free, .enqueue = sctp_sched_fcfs_enqueue, .dequeue = sctp_sched_fcfs_dequeue, .dequeue_done = sctp_sched_fcfs_dequeue_done, @@ -131,6 +126,23 @@ void sctp_sched_ops_init(void) sctp_sched_ops_rr_init(); } +static void sctp_sched_free_sched(struct sctp_stream *stream) +{ + struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + struct sctp_stream_out_ext *soute; + int i; + + sched->unsched_all(stream); + for (i = 0; i < stream->outcnt; i++) { + soute = SCTP_SO(stream, i)->ext; + if (!soute) + continue; + sched->free_sid(stream, i); + /* Give the next scheduler a clean slate. */ + memset_after(soute, 0, outq); + } +} + int sctp_sched_set_sched(struct sctp_association *asoc, enum sctp_sched_type sched) { @@ -146,18 +158,8 @@ int sctp_sched_set_sched(struct sctp_association *asoc, if (sched > SCTP_SS_MAX) return -EINVAL; - if (old) { - old->free(&asoc->stream); - - /* Give the next scheduler a clean slate. */ - for (i = 0; i < asoc->stream.outcnt; i++) { - struct sctp_stream_out_ext *ext = SCTP_SO(&asoc->stream, i)->ext; - - if (!ext) - continue; - memset_after(ext, 0, outq); - } - } + if (old) + sctp_sched_free_sched(&asoc->stream); asoc->outqueue.sched = n; n->init(&asoc->stream); @@ -181,7 +183,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, return ret; err: - n->free(&asoc->stream); + sctp_sched_free_sched(&asoc->stream); asoc->outqueue.sched = &sctp_sched_fcfs; /* Always safe */ return ret; diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 4fc9f2923ed1..42d4800f263d 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -222,32 +222,6 @@ static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) kfree(prio); } -static void sctp_sched_prio_free(struct sctp_stream *stream) -{ - struct sctp_stream_priorities *prio, *n; - LIST_HEAD(list); - int i; - - /* As we don't keep a list of priorities, to avoid multiple - * frees we have to do it in 3 steps: - * 1. unsched everyone, so the lists are free to use in 2. - * 2. build the list of the priorities - * 3. free the list - */ - sctp_sched_prio_unsched_all(stream); - for (i = 0; i < stream->outcnt; i++) { - if (!SCTP_SO(stream, i)->ext) - continue; - prio = SCTP_SO(stream, i)->ext->prio_head; - if (prio && list_empty(&prio->prio_sched)) - list_add(&prio->prio_sched, &list); - } - list_for_each_entry_safe(prio, n, &list, prio_sched) { - list_del_init(&prio->prio_sched); - kfree(prio); - } -} - static void sctp_sched_prio_enqueue(struct sctp_outq *q, struct sctp_datamsg *msg) { @@ -342,7 +316,6 @@ static struct sctp_sched_ops sctp_sched_prio = { .init = sctp_sched_prio_init, .init_sid = sctp_sched_prio_init_sid, .free_sid = sctp_sched_prio_free_sid, - .free = sctp_sched_prio_free, .enqueue = sctp_sched_prio_enqueue, .dequeue = sctp_sched_prio_dequeue, .dequeue_done = sctp_sched_prio_dequeue_done, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index cc444fe0d67c..1f235e7f643a 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -94,11 +94,6 @@ static void sctp_sched_rr_free_sid(struct sctp_stream *stream, __u16 sid) { } -static void sctp_sched_rr_free(struct sctp_stream *stream) -{ - sctp_sched_rr_unsched_all(stream); -} - static void sctp_sched_rr_enqueue(struct sctp_outq *q, struct sctp_datamsg *msg) { @@ -182,7 +177,6 @@ static struct sctp_sched_ops sctp_sched_rr = { .init = sctp_sched_rr_init, .init_sid = sctp_sched_rr_init_sid, .free_sid = sctp_sched_rr_free_sid, - .free = sctp_sched_rr_free, .enqueue = sctp_sched_rr_enqueue, .dequeue = sctp_sched_rr_dequeue, .dequeue_done = sctp_sched_rr_dequeue_done, -- cgit v1.2.3 From d93607082e982223cf92750f2d9039ff365b9d24 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 30 Nov 2022 23:28:26 +0100 Subject: net: add netdev_sw_irq_coalesce_default_on() Add a helper for drivers wanting to set SW IRQ coalescing by default. The related sysfs attributes can be used to override the default values. Follow Jakub's suggestion and put this functionality into net core so that drivers wanting to use software interrupt coalescing per default don't have to open-code it. Note that this function needs to be called before the netdevice is registered. Suggested-by: Jakub Kicinski Signed-off-by: Heiner Kallweit Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5aa35c58c342..f78db610ada5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -78,6 +78,7 @@ struct xdp_buff; void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); +void netdev_sw_irq_coalesce_default_on(struct net_device *dev); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ diff --git a/net/core/dev.c b/net/core/dev.c index 7627c475d991..b76fb37b381e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10517,6 +10517,22 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); +/** + * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default + * @dev: netdev to enable the IRQ coalescing on + * + * Sets a conservative default for SW IRQ coalescing. Users can use + * sysfs attributes to override the default values. + */ +void netdev_sw_irq_coalesce_default_on(struct net_device *dev) +{ + WARN_ON(dev->reg_state == NETREG_REGISTERED); + + dev->gro_flush_timeout = 20000; + dev->napi_defer_hard_irqs = 1; +} +EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); + void netdev_freemem(struct net_device *dev) { char *addr = (char *)dev - dev->padded; -- cgit v1.2.3 From fca1aa75518c03b04c3c249e9a9134faf9ca18c5 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 3 Dec 2022 10:46:02 -0800 Subject: bpf: Handle MEM_RCU type properly Commit 9bb00b2895cb ("bpf: Add kfunc bpf_rcu_read_lock/unlock()") introduced MEM_RCU and bpf_rcu_read_lock/unlock() support. In that commit, a rcu pointer is tagged with both MEM_RCU and PTR_TRUSTED so that it can be passed into kfuncs or helpers as an argument. Martin raised a good question in [1] such that the rcu pointer, although being able to accessing the object, might have reference count of 0. This might cause a problem if the rcu pointer is passed to a kfunc which expects trusted arguments where ref count should be greater than 0. This patch makes the following changes related to MEM_RCU pointer: - MEM_RCU pointer might be NULL (PTR_MAYBE_NULL). - Introduce KF_RCU so MEM_RCU ptr can be acquired with a KF_RCU tagged kfunc which assumes ref count of rcu ptr could be zero. - For mem access 'b = ptr->a', say 'ptr' is a MEM_RCU ptr, and 'a' is tagged with __rcu as well. Let us mark 'b' as MEM_RCU | PTR_MAYBE_NULL. [1] https://lore.kernel.org/bpf/ac70f574-4023-664e-b711-e0d3b18117fd@linux.dev/ Fixes: 9bb00b2895cb ("bpf: Add kfunc bpf_rcu_read_lock/unlock()") Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221203184602.477272-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 2 +- include/linux/btf.h | 1 + kernel/bpf/helpers.c | 14 ++++++++++++++ kernel/bpf/verifier.c | 45 +++++++++++++++++++++++++++++++------------- 4 files changed, 48 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b5090e89cb3f..c07b351a5bc7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -682,7 +682,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) } } -#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | MEM_RCU | PTR_TRUSTED) +#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED) static inline bool bpf_type_has_unsafe_modifiers(u32 type) { diff --git a/include/linux/btf.h b/include/linux/btf.h index 9ed00077db6e..cbd6e4096f8c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -70,6 +70,7 @@ #define KF_TRUSTED_ARGS (1 << 4) /* kfunc only takes trusted pointer arguments */ #define KF_SLEEPABLE (1 << 5) /* kfunc may sleep */ #define KF_DESTRUCTIVE (1 << 6) /* kfunc performs destructive actions */ +#define KF_RCU (1 << 7) /* kfunc only takes rcu pointer arguments */ /* * Return the name of the passed struct, if exists, or halt the build if for diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a5a511430f2a..cca642358e80 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1837,6 +1837,19 @@ struct task_struct *bpf_task_acquire(struct task_struct *p) return p; } +/** + * bpf_task_acquire_not_zero - Acquire a reference to a rcu task object. A task + * acquired by this kfunc which is not stored in a map as a kptr, must be + * released by calling bpf_task_release(). + * @p: The task on which a reference is being acquired. + */ +struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) +{ + if (!refcount_inc_not_zero(&p->rcu_users)) + return NULL; + return p; +} + /** * bpf_task_kptr_get - Acquire a reference on a struct task_struct kptr. A task * kptr acquired by this kfunc which is not subsequently stored in a map, must @@ -2013,6 +2026,7 @@ BTF_ID_FLAGS(func, bpf_list_push_back) BTF_ID_FLAGS(func, bpf_list_pop_front, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_list_pop_back, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE) #ifdef CONFIG_CGROUPS diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b0db9c10567b..66b82f52b5bc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4275,7 +4275,7 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) return true; /* If a register is not referenced, it is trusted if it has the - * MEM_ALLOC, MEM_RCU or PTR_TRUSTED type modifiers, and no others. Some of the + * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the * other type modifiers may be safe, but we elect to take an opt-in * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are * not. @@ -4287,6 +4287,11 @@ static bool is_trusted_reg(const struct bpf_reg_state *reg) !bpf_type_has_unsafe_modifiers(reg->type); } +static bool is_rcu_reg(const struct bpf_reg_state *reg) +{ + return reg->type & MEM_RCU; +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -4785,14 +4790,16 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (flag & MEM_RCU) { /* Mark value register as MEM_RCU only if it is protected by - * bpf_rcu_read_lock() and the ptr reg is trusted. MEM_RCU + * bpf_rcu_read_lock() and the ptr reg is rcu or trusted. MEM_RCU * itself can already indicate trustedness inside the rcu - * read lock region. Also mark it as PTR_TRUSTED. + * read lock region. Also mark rcu pointer as PTR_MAYBE_NULL since + * it could be null in some cases. */ - if (!env->cur_state->active_rcu_lock || !is_trusted_reg(reg)) + if (!env->cur_state->active_rcu_lock || + !(is_trusted_reg(reg) || is_rcu_reg(reg))) flag &= ~MEM_RCU; else - flag |= PTR_TRUSTED; + flag |= PTR_MAYBE_NULL; } else if (reg->type & MEM_RCU) { /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively. @@ -5957,7 +5964,7 @@ static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID, PTR_TO_BTF_ID | PTR_TRUSTED, - PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED, + PTR_TO_BTF_ID | MEM_RCU, }, }; static const struct bpf_reg_types percpu_btf_ptr_types = { @@ -6136,7 +6143,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | MEM_ALLOC: case PTR_TO_BTF_ID | PTR_TRUSTED: - case PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: /* When referenced PTR_TO_BTF_ID is passed to release function, * it's fixed offset must be 0. In the other cases, fixed offset @@ -8038,6 +8045,11 @@ static bool is_kfunc_destructive(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_DESTRUCTIVE; } +static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU; +} + static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg) { return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET); @@ -8722,13 +8734,20 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ switch (kf_arg_type) { case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: - if (!is_kfunc_trusted_args(meta)) + if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; if (!is_trusted_reg(reg)) { - verbose(env, "R%d must be referenced or trusted\n", regno); - return -EINVAL; + if (!is_kfunc_rcu(meta)) { + verbose(env, "R%d must be referenced or trusted\n", regno); + return -EINVAL; + } + if (!is_rcu_reg(reg)) { + verbose(env, "R%d must be a rcu pointer\n", regno); + return -EINVAL; + } } + fallthrough; case KF_ARG_PTR_TO_CTX: /* Trusted arguments have the same offset checks as release arguments */ @@ -8839,7 +8858,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || - bpf_type_has_unsafe_modifiers(reg->type)) && + (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && !reg2btf_ids[base_type(reg->type)]) { verbose(env, "arg#%d is %s ", i, reg_type_str(env, reg->type)); verbose(env, "expected %s or socket\n", @@ -8954,7 +8973,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } else if (rcu_unlock) { bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ if (reg->type & MEM_RCU) { - reg->type &= ~(MEM_RCU | PTR_TRUSTED); + reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; } })); @@ -11294,7 +11313,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, bool is_null) { if (type_may_be_null(reg->type) && reg->id == id && - !WARN_ON_ONCE(!reg->id)) { + (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) { /* Old offset (both fixed and variable parts) should have been * known-zero, because we don't allow pointer arithmetic on * pointers that might be NULL. If we see this happening, don't -- cgit v1.2.3 From c0c852dd1876dc1db4600ce951a92aadd3073b1c Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 3 Dec 2022 12:49:54 -0800 Subject: bpf: Do not mark certain LSM hook arguments as trusted Martin mentioned that the verifier cannot assume arguments from LSM hook sk_alloc_security being trusted since after the hook is called, the sk ref_count is set to 1. This will overwrite the ref_count changed by the bpf program and may cause ref_count underflow later on. I then further checked some other hooks. For example, for bpf_lsm_file_alloc() hook in fs/file_table.c, f->f_cred = get_cred(cred); error = security_file_alloc(f); if (unlikely(error)) { file_free_rcu(&f->f_rcuhead); return ERR_PTR(error); } atomic_long_set(&f->f_count, 1); The input parameter 'f' to security_file_alloc() cannot be trusted as well. Specifically, I investiaged bpf_map/bpf_prog/file/sk/task alloc/free lsm hooks. Except bpf_map_alloc and task_alloc, arguments for all other hooks should not be considered as trusted. This may not be a complete list, but it covers common usage for sk and task. Fixes: 3f00c5239344 ("bpf: Allow trusted pointers to be passed to KF_TRUSTED_ARGS kfuncs") Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221203204954.2043348-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_lsm.h | 6 ++++++ kernel/bpf/bpf_lsm.c | 16 ++++++++++++++++ kernel/bpf/btf.c | 2 ++ tools/testing/selftests/bpf/prog_tests/task_kfunc.c | 1 + tools/testing/selftests/bpf/progs/task_kfunc_failure.c | 11 +++++++++++ 5 files changed, 36 insertions(+) (limited to 'include') diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h index 4bcf76a9bb06..1de7ece5d36d 100644 --- a/include/linux/bpf_lsm.h +++ b/include/linux/bpf_lsm.h @@ -28,6 +28,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog); bool bpf_lsm_is_sleepable_hook(u32 btf_id); +bool bpf_lsm_is_trusted(const struct bpf_prog *prog); static inline struct bpf_storage_blob *bpf_inode( const struct inode *inode) @@ -51,6 +52,11 @@ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id) return false; } +static inline bool bpf_lsm_is_trusted(const struct bpf_prog *prog) +{ + return false; +} + static inline int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) { diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index ae0267f150b5..9ea42a45da47 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -345,11 +345,27 @@ BTF_ID(func, bpf_lsm_task_to_inode) BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) +BTF_SET_START(untrusted_lsm_hooks) +BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) +BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_file_alloc_security) +BTF_ID(func, bpf_lsm_file_free_security) +BTF_ID(func, bpf_lsm_sk_alloc_security) +BTF_ID(func, bpf_lsm_sk_free_security) +BTF_ID(func, bpf_lsm_task_free) +BTF_SET_END(untrusted_lsm_hooks) + bool bpf_lsm_is_sleepable_hook(u32 btf_id) { return btf_id_set_contains(&sleepable_lsm_hooks, btf_id); } +bool bpf_lsm_is_trusted(const struct bpf_prog *prog) +{ + return !btf_id_set_contains(&untrusted_lsm_hooks, prog->aux->attach_btf_id); +} + const struct bpf_prog_ops lsm_prog_ops = { }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d11cbf8cece7..c80bd8709e69 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -5829,6 +5830,7 @@ static bool prog_args_trusted(const struct bpf_prog *prog) case BPF_PROG_TYPE_TRACING: return atype == BPF_TRACE_RAW_TP || atype == BPF_TRACE_ITER; case BPF_PROG_TYPE_LSM: + return bpf_lsm_is_trusted(prog); case BPF_PROG_TYPE_STRUCT_OPS: return true; default: diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c index ffd8ef4303c8..18848c31e36f 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c +++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c @@ -103,6 +103,7 @@ static struct { {"task_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"}, {"task_kfunc_release_unacquired", "release kernel function bpf_task_release expects"}, {"task_kfunc_from_pid_no_null_check", "arg#0 is ptr_or_null_ expected ptr_ or socket"}, + {"task_kfunc_from_lsm_task_free", "reg type unsupported for arg#0 function"}, }; static void verify_fail(const char *prog_name, const char *expected_err_msg) diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c index e310473190d5..87fa1db9d9b5 100644 --- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c +++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c @@ -271,3 +271,14 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl return 0; } + +SEC("lsm/task_free") +int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task) +{ + struct task_struct *acquired; + + /* the argument of lsm task_free hook is untrusted. */ + acquired = bpf_task_acquire(task); + bpf_task_release(acquired); + return 0; +} -- cgit v1.2.3 From d14f28b8c1de668bab863bf5892a49c824cb110d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 20:41:27 +0200 Subject: xfrm: add new packet offload flag In the next patches, the xfrm core code will be extended to support new type of offload - packet offload. In that mode, both policy and state should be specially configured in order to perform whole offloaded data path. Full offload takes care of encryption, decryption, encapsulation and other operations with headers. As this mode is new for XFRM policy flow, we can "start fresh" with flag bits and release first and second bit for future use. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 7 +++++++ include/uapi/linux/xfrm.h | 6 ++++++ net/xfrm/xfrm_device.c | 3 +++ net/xfrm/xfrm_user.c | 2 ++ 4 files changed, 18 insertions(+) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e0cc6791c001..b39d24fa2ef0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -131,12 +131,19 @@ enum { XFRM_DEV_OFFLOAD_OUT, }; +enum { + XFRM_DEV_OFFLOAD_UNSPECIFIED, + XFRM_DEV_OFFLOAD_CRYPTO, + XFRM_DEV_OFFLOAD_PACKET, +}; + struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; u8 dir : 2; + u8 type : 2; }; struct xfrm_mode { diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 4f84ea7ee14c..23543c33fee8 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -519,6 +519,12 @@ struct xfrm_user_offload { */ #define XFRM_OFFLOAD_IPV6 1 #define XFRM_OFFLOAD_INBOUND 2 +/* Two bits above are relevant for state path only, while + * offload is used for both policy and state flows. + * + * In policy offload mode, they are free and can be safely reused. + */ +#define XFRM_OFFLOAD_PACKET 4 struct xfrm_userpolicy_default { #define XFRM_USERPOLICY_UNSPEC 0 diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 21269e8f2db4..3b0c1ca8d4bb 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -291,12 +291,15 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, else xso->dir = XFRM_DEV_OFFLOAD_OUT; + xso->type = XFRM_DEV_OFFLOAD_CRYPTO; + err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; netdev_put(dev, &xso->dev_tracker); + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; if (err != -EOPNOTSUPP) { NL_SET_ERR_MSG(extack, "Device failed to offload this state"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 0eb4696661c8..c3b8c1532718 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -956,6 +956,8 @@ static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) xuo->ifindex = xso->dev->ifindex; if (xso->dir == XFRM_DEV_OFFLOAD_IN) xuo->flags = XFRM_OFFLOAD_INBOUND; + if (xso->type == XFRM_DEV_OFFLOAD_PACKET) + xuo->flags |= XFRM_OFFLOAD_PACKET; return 0; } -- cgit v1.2.3 From 919e43fad5163a8ceb39826ecdee897a9f799351 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 20:41:29 +0200 Subject: xfrm: add an interface to offload policy Extend netlink interface to add and delete XFRM policy from the device. This functionality is a first step to implement packet IPsec offload solution. Signed-off-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/linux/netdevice.h | 3 +++ include/net/xfrm.h | 45 +++++++++++++++++++++++++++++++ net/xfrm/xfrm_device.c | 67 ++++++++++++++++++++++++++++++++++++++++++++- net/xfrm/xfrm_policy.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++ net/xfrm/xfrm_user.c | 18 +++++++++++++ 5 files changed, 201 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5aa35c58c342..4096e3fe8e4a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1040,6 +1040,9 @@ struct xfrmdev_ops { bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); + int (*xdo_dev_policy_add) (struct xfrm_policy *x); + void (*xdo_dev_policy_delete) (struct xfrm_policy *x); + void (*xdo_dev_policy_free) (struct xfrm_policy *x); }; #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b39d24fa2ef0..6fea34cbdf48 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -129,6 +129,7 @@ struct xfrm_state_walk { enum { XFRM_DEV_OFFLOAD_IN = 1, XFRM_DEV_OFFLOAD_OUT, + XFRM_DEV_OFFLOAD_FWD, }; enum { @@ -541,6 +542,8 @@ struct xfrm_policy { struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; struct hlist_node bydst_inexact_list; struct rcu_head rcu; + + struct xfrm_dev_offload xdo; }; static inline struct net *xp_net(const struct xfrm_policy *xp) @@ -1585,6 +1588,8 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); +int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, + bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); @@ -1899,6 +1904,9 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo, struct netlink_ext_ack *extack); +int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, + struct xfrm_user_offload *xuo, u8 dir, + struct netlink_ext_ack *extack); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) @@ -1947,6 +1955,28 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) netdev_put(dev, &xso->dev_tracker); } } + +static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) +{ + struct xfrm_dev_offload *xdo = &x->xdo; + struct net_device *dev = xdo->dev; + + if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_policy_delete) + dev->xfrmdev_ops->xdo_dev_policy_delete(x); +} + +static inline void xfrm_dev_policy_free(struct xfrm_policy *x) +{ + struct xfrm_dev_offload *xdo = &x->xdo; + struct net_device *dev = xdo->dev; + + if (dev && dev->xfrmdev_ops) { + if (dev->xfrmdev_ops->xdo_dev_policy_free) + dev->xfrmdev_ops->xdo_dev_policy_free(x); + xdo->dev = NULL; + netdev_put(dev, &xdo->dev_tracker); + } +} #else static inline void xfrm_dev_resume(struct sk_buff *skb) { @@ -1974,6 +2004,21 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) { } +static inline int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, + struct xfrm_user_offload *xuo, u8 dir, + struct netlink_ext_ack *extack) +{ + return 0; +} + +static inline void xfrm_dev_policy_delete(struct xfrm_policy *x) +{ +} + +static inline void xfrm_dev_policy_free(struct xfrm_policy *x) +{ +} + static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { return false; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3184b2c394b6..04ae510dcc66 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -325,6 +325,69 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } EXPORT_SYMBOL_GPL(xfrm_dev_state_add); +int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp, + struct xfrm_user_offload *xuo, u8 dir, + struct netlink_ext_ack *extack) +{ + struct xfrm_dev_offload *xdo = &xp->xdo; + struct net_device *dev; + int err; + + if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) { + /* We support only packet offload mode and it means + * that user must set XFRM_OFFLOAD_PACKET bit. + */ + NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request"); + return -EINVAL; + } + + dev = dev_get_by_index(net, xuo->ifindex); + if (!dev) + return -EINVAL; + + if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) { + xdo->dev = NULL; + dev_put(dev); + NL_SET_ERR_MSG(extack, "Policy offload is not supported"); + return -EINVAL; + } + + xdo->dev = dev; + netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC); + xdo->real_dev = dev; + xdo->type = XFRM_DEV_OFFLOAD_PACKET; + switch (dir) { + case XFRM_POLICY_IN: + xdo->dir = XFRM_DEV_OFFLOAD_IN; + break; + case XFRM_POLICY_OUT: + xdo->dir = XFRM_DEV_OFFLOAD_OUT; + break; + case XFRM_POLICY_FWD: + xdo->dir = XFRM_DEV_OFFLOAD_FWD; + break; + default: + xdo->dev = NULL; + dev_put(dev); + NL_SET_ERR_MSG(extack, "Unrecognized oflload direction"); + return -EINVAL; + } + + err = dev->xfrmdev_ops->xdo_dev_policy_add(xp); + if (err) { + xdo->dev = NULL; + xdo->real_dev = NULL; + xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; + xdo->dir = 0; + netdev_put(dev, &xdo->dev_tracker); + NL_SET_ERR_MSG(extack, "Device failed to offload this policy"); + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(xfrm_dev_policy_add); + bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { int mtu; @@ -427,8 +490,10 @@ static int xfrm_api_check(struct net_device *dev) static int xfrm_dev_down(struct net_device *dev) { - if (dev->features & NETIF_F_HW_ESP) + if (dev->features & NETIF_F_HW_ESP) { xfrm_dev_state_flush(dev_net(dev), dev, true); + xfrm_dev_policy_flush(dev_net(dev), dev, true); + } return NOTIFY_DONE; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9b9e2765363d..8b8760907563 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -425,6 +425,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer)) BUG(); + xfrm_dev_policy_free(policy); call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); @@ -1769,12 +1770,41 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) } return err; } + +static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, + struct net_device *dev, + bool task_valid) +{ + struct xfrm_policy *pol; + int err = 0; + + list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead || + xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || + pol->xdo.dev != dev) + continue; + + err = security_xfrm_policy_delete(pol->security); + if (err) { + xfrm_audit_policy_delete(pol, 0, task_valid); + return err; + } + } + return err; +} #else static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } + +static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, + struct net_device *dev, + bool task_valid) +{ + return 0; +} #endif int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) @@ -1814,6 +1844,44 @@ out: } EXPORT_SYMBOL(xfrm_policy_flush); +int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, + bool task_valid) +{ + int dir, err = 0, cnt = 0; + struct xfrm_policy *pol; + + spin_lock_bh(&net->xfrm.xfrm_policy_lock); + + err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid); + if (err) + goto out; + +again: + list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + dir = xfrm_policy_id2dir(pol->index); + if (pol->walk.dead || + dir >= XFRM_POLICY_MAX || + pol->xdo.dev != dev) + continue; + + __xfrm_policy_unlink(pol, dir); + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + cnt++; + xfrm_audit_policy_delete(pol, 1, task_valid); + xfrm_policy_kill(pol); + spin_lock_bh(&net->xfrm.xfrm_policy_lock); + goto again; + } + if (cnt) + __xfrm_policy_inexact_flush(net); + else + err = -ESRCH; +out: + spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + return err; +} +EXPORT_SYMBOL(xfrm_dev_policy_flush); + int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) @@ -2245,6 +2313,7 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { + xfrm_dev_policy_delete(pol); xfrm_policy_kill(pol); return 0; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c3b8c1532718..cf5172d4ce68 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1892,6 +1892,15 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, if (attrs[XFRMA_IF_ID]) xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + /* configure the hardware if offload is requested */ + if (attrs[XFRMA_OFFLOAD_DEV]) { + err = xfrm_dev_policy_add(net, xp, + nla_data(attrs[XFRMA_OFFLOAD_DEV]), + p->dir, extack); + if (err) + goto error; + } + return xp; error: *errp = err; @@ -1931,6 +1940,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, xfrm_audit_policy_add(xp, err ? 0 : 1, true); if (err) { + xfrm_dev_policy_delete(xp); security_xfrm_policy_free(xp->security); kfree(xp); return err; @@ -2043,6 +2053,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); + if (!err && xp->xdo.dev) + err = copy_user_offload(&xp->xdo, skb); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3381,6 +3393,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); + if (!err && xp->xdo.dev) + err = copy_user_offload(&xp->xdo, skb); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3499,6 +3513,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); + if (!err && xp->xdo.dev) + err = copy_user_offload(&xp->xdo, skb); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3582,6 +3598,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e err = xfrm_mark_put(skb, &xp->mark); if (!err) err = xfrm_if_id_put(skb, xp->if_id); + if (!err && xp->xdo.dev) + err = copy_user_offload(&xp->xdo, skb); if (err) goto out_free_skb; -- cgit v1.2.3 From 5958372ddf628fe6f4c3e49425734ad32fcfb13c Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 20:41:31 +0200 Subject: xfrm: add RX datapath protection for IPsec packet offload mode Traffic received by device with enabled IPsec packet offload should be forwarded to the stack only after decryption, packet headers and trailers removed. Such packets are expected to be seen as normal (non-XFRM) ones, while not-supported packets should be dropped by the HW. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 55 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 32 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fea34cbdf48..b6ee14991a32 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1102,6 +1102,29 @@ xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, un return !0; } +#ifdef CONFIG_XFRM +static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) +{ + struct sec_path *sp = skb_sec_path(skb); + + return sp->xvec[sp->len - 1]; +} +#endif + +static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) +{ +#ifdef CONFIG_XFRM + struct sec_path *sp = skb_sec_path(skb); + + if (!sp || !sp->olen || sp->len != sp->olen) + return NULL; + + return &sp->ovec[sp->olen - 1]; +#else + return NULL; +#endif +} + #ifdef CONFIG_XFRM int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); @@ -1133,10 +1156,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, { struct net *net = dev_net(skb->dev); int ndir = dir | (reverse ? XFRM_POLICY_MASK + 1 : 0); + struct xfrm_offload *xo = xfrm_offload(skb); + struct xfrm_state *x; if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); + if (xo) { + x = xfrm_input_state(skb); + if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) + return (xo->flags & CRYPTO_DONE) && + (xo->status & CRYPTO_SUCCESS); + } + return __xfrm_check_nopolicy(net, skb, dir) || __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); @@ -1872,29 +1904,6 @@ static inline void xfrm_states_delete(struct xfrm_state **states, int n) } #endif -#ifdef CONFIG_XFRM -static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) -{ - struct sec_path *sp = skb_sec_path(skb); - - return sp->xvec[sp->len - 1]; -} -#endif - -static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) -{ -#ifdef CONFIG_XFRM - struct sec_path *sp = skb_sec_path(skb); - - if (!sp || !sp->olen || sp->len != sp->olen) - return NULL; - - return &sp->ovec[sp->olen - 1]; -#else - return NULL; -#endif -} - void __init xfrm_dev_init(void); #ifdef CONFIG_XFRM_OFFLOAD -- cgit v1.2.3 From f3da86dc2c8c9004445cfbb15ac086773622d853 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 20:41:33 +0200 Subject: xfrm: add support to HW update soft and hard limits Both in RX and TX, the traffic that performs IPsec packet offload transformation is accounted by HW. It is needed to properly handle hard limits that require to drop the packet. It means that XFRM core needs to update internal counters with the one that accounted by the HW, so new callbacks are introduced in this patch. In case of soft or hard limit is occurred, the driver should call to xfrm_state_check_expire() that will perform key rekeying exactly as done by XFRM core. Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/linux/netdevice.h | 1 + include/net/xfrm.h | 17 +++++++++++++++++ net/xfrm/xfrm_state.c | 4 ++++ 3 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4096e3fe8e4a..29ae964e3b89 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1040,6 +1040,7 @@ struct xfrmdev_ops { bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); + void (*xdo_dev_state_update_curlft) (struct xfrm_state *x); int (*xdo_dev_policy_add) (struct xfrm_policy *x); void (*xdo_dev_policy_delete) (struct xfrm_policy *x); void (*xdo_dev_policy_free) (struct xfrm_policy *x); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b6ee14991a32..5413cdd5ad62 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1571,6 +1571,23 @@ struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); +#ifdef CONFIG_XFRM_OFFLOAD +static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xdo = &x->xso; + struct net_device *dev = xdo->dev; + + if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) + return; + + if (dev && dev->xfrmdev_ops && + dev->xfrmdev_ops->xdo_dev_state_update_curlft) + dev->xfrmdev_ops->xdo_dev_state_update_curlft(x); + +} +#else +static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x) {} +#endif void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); int xfrm_state_update(struct xfrm_state *x); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2a190e85da80..cc1d0ea42672 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -570,6 +570,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) int err = 0; spin_lock(&x->lock); + xfrm_dev_state_update_curlft(x); + if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) @@ -1936,6 +1938,8 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { + xfrm_dev_state_update_curlft(x); + if (!x->curlft.use_time) x->curlft.use_time = ktime_get_real_seconds(); -- cgit v1.2.3 From a46e9010124256f5bf5fc2c241a45cf1944b768e Mon Sep 17 00:00:00 2001 From: Revanth Kumar Uppala Date: Thu, 1 Dec 2022 15:58:43 +0000 Subject: net: stmmac: Power up SERDES after the PHY link The Tegra MGBE ethernet controller requires that the SERDES link is powered-up after the PHY link is up, otherwise the link fails to become ready following a resume from suspend. Add a variable to indicate that the SERDES link must be powered-up after the PHY link. Signed-off-by: Revanth Kumar Uppala Signed-off-by: Jon Hunter Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +++++-- include/linux/stmmac.h | 1 + 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 18c7ca29da2c..f36590d0c830 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -988,6 +988,9 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 old_ctrl, ctrl; + if (priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) + priv->plat->serdes_powerup(priv->dev, priv->plat->bsp_priv); + old_ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl = old_ctrl & ~priv->hw->link.speed_mask; @@ -3809,7 +3812,7 @@ static int __stmmac_open(struct net_device *dev, stmmac_reset_queues_param(priv); - if (priv->plat->serdes_powerup) { + if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(dev, priv->plat->bsp_priv); if (ret < 0) { netdev_err(priv->dev, "%s: Serdes powerup failed\n", @@ -7518,7 +7521,7 @@ int stmmac_resume(struct device *dev) stmmac_mdio_reset(priv->mii); } - if (priv->plat->serdes_powerup) { + if (!priv->plat->serdes_up_after_phy_linkup && priv->plat->serdes_powerup) { ret = priv->plat->serdes_powerup(ndev, priv->plat->bsp_priv); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fb2e88614f5d..83ca2e8eb6b5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -271,5 +271,6 @@ struct plat_stmmacenet_data { int msi_tx_base_vec; bool use_phy_wol; bool sph_disable; + bool serdes_up_after_phy_linkup; }; #endif -- cgit v1.2.3 From 7112a04664bfc10ae4709b2079fe3991cbd1fe18 Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Thu, 1 Dec 2022 16:25:55 -0800 Subject: ethtool: add netlink based get rss support Add netlink based support for "ethtool -x [context x]" command by implementing ETHTOOL_MSG_RSS_GET netlink message. This is equivalent to functionality provided via ETHTOOL_GRSSH in ioctl path. It sends RSS table, hash key and hash function of an interface to user space. This patch implements existing functionality available in ioctl path and enables addition of new RSS context based parameters in future. Signed-off-by: Sudheer Mogilappagari Link: https://lore.kernel.org/r/20221202002555.241580-1-sudheer.mogilappagari@intel.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 31 +++++- include/uapi/linux/ethtool_netlink.h | 14 +++ net/ethtool/Makefile | 2 +- net/ethtool/netlink.c | 7 ++ net/ethtool/netlink.h | 2 + net/ethtool/rss.c | 153 +++++++++++++++++++++++++++ 6 files changed, 207 insertions(+), 2 deletions(-) create mode 100644 net/ethtool/rss.c (limited to 'include') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index bede24ef44fd..f10f8eb44255 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -222,6 +222,7 @@ Userspace to kernel: ``ETHTOOL_MSG_MODULE_GET`` get transceiver module parameters ``ETHTOOL_MSG_PSE_SET`` set PSE parameters ``ETHTOOL_MSG_PSE_GET`` get PSE parameters + ``ETHTOOL_MSG_RSS_GET`` get RSS settings ===================================== ================================= Kernel to userspace: @@ -263,6 +264,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ``ETHTOOL_MSG_PSE_GET_REPLY`` PSE parameters + ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1687,6 +1689,33 @@ to control PoDL PSE Admin functions. This option is implementing ``IEEE 802.3-2018`` 30.15.1.2.1 acPoDLPSEAdminControl. See ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` for supported values. +RSS_GET +======= + +Get indirection table, hash key and hash function info associated with a +RSS context of an interface similar to ``ETHTOOL_GRSSH`` ioctl request. + +Request contents: + +===================================== ====== ========================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number +===================================== ====== ========================== + +Kernel response contents: + +===================================== ====== ========================== + ``ETHTOOL_A_RSS_HEADER`` nested reply header + ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func + ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes + ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes +===================================== ====== ========================== + +ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function +being used. Current supported options are toeplitz, xor or crc32. +ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte +indicates queue number. + Request translation =================== @@ -1768,7 +1797,7 @@ are netlink only. ``ETHTOOL_GMODULEEEPROM`` ``ETHTOOL_MSG_MODULE_EEPROM_GET`` ``ETHTOOL_GEEE`` ``ETHTOOL_MSG_EEE_GET`` ``ETHTOOL_SEEE`` ``ETHTOOL_MSG_EEE_SET`` - ``ETHTOOL_GRSSH`` n/a + ``ETHTOOL_GRSSH`` ``ETHTOOL_MSG_RSS_GET`` ``ETHTOOL_SRSSH`` n/a ``ETHTOOL_GTUNABLE`` n/a ``ETHTOOL_STUNABLE`` n/a diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index aaf7c6963d61..5799a9db034e 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -51,6 +51,7 @@ enum { ETHTOOL_MSG_MODULE_SET, ETHTOOL_MSG_PSE_GET, ETHTOOL_MSG_PSE_SET, + ETHTOOL_MSG_RSS_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -97,6 +98,7 @@ enum { ETHTOOL_MSG_MODULE_GET_REPLY, ETHTOOL_MSG_MODULE_NTF, ETHTOOL_MSG_PSE_GET_REPLY, + ETHTOOL_MSG_RSS_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -880,6 +882,18 @@ enum { ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1) }; +enum { + ETHTOOL_A_RSS_UNSPEC, + ETHTOOL_A_RSS_HEADER, + ETHTOOL_A_RSS_CONTEXT, /* u32 */ + ETHTOOL_A_RSS_HFUNC, /* u32 */ + ETHTOOL_A_RSS_INDIR, /* binary */ + ETHTOOL_A_RSS_HKEY, /* binary */ + + __ETHTOOL_A_RSS_CNT, + ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 72ab0944262a..228f13df2e18 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -4,7 +4,7 @@ obj-y += ioctl.o common.o obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o -ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ +ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o \ diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1a4c11356c96..aee98be6237f 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -287,6 +287,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, + [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1040,6 +1041,12 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_pse_set_policy, .maxattr = ARRAY_SIZE(ethnl_pse_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_RSS_GET, + .doit = ethnl_default_doit, + .policy = ethnl_rss_get_policy, + .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 1bfd374f9718..3753787ba233 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -346,6 +346,7 @@ extern const struct ethnl_request_ops ethnl_stats_request_ops; extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct ethnl_request_ops ethnl_pse_request_ops; +extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -386,6 +387,7 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; +extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c new file mode 100644 index 000000000000..ebe6145aed3f --- /dev/null +++ b/net/ethtool/rss.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct rss_req_info { + struct ethnl_req_info base; + u32 rss_context; +}; + +struct rss_reply_data { + struct ethnl_reply_data base; + u32 indir_size; + u32 hkey_size; + u32 hfunc; + u32 *indir_table; + u8 *hkey; +}; + +#define RSS_REQINFO(__req_base) \ + container_of(__req_base, struct rss_req_info, base) + +#define RSS_REPDATA(__reply_base) \ + container_of(__reply_base, struct rss_reply_data, base) + +const struct nla_policy ethnl_rss_get_policy[] = { + [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, +}; + +static int +rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rss_req_info *request = RSS_REQINFO(req_info); + + if (tb[ETHTOOL_A_RSS_CONTEXT]) + request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + + return 0; +} + +static int +rss_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, struct genl_info *info) +{ + struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + u32 total_size, indir_bytes; + u8 dev_hfunc = 0; + u8 *rss_config; + int ret; + + ops = dev->ethtool_ops; + if (!ops->get_rxfh) + return -EOPNOTSUPP; + + /* Some drivers don't handle rss_context */ + if (request->rss_context && !ops->get_rxfh_context) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + data->indir_size = 0; + data->hkey_size = 0; + if (ops->get_rxfh_indir_size) + data->indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + data->hkey_size = ops->get_rxfh_key_size(dev); + + indir_bytes = data->indir_size * sizeof(u32); + total_size = indir_bytes + data->hkey_size; + rss_config = kzalloc(total_size, GFP_KERNEL); + if (!rss_config) { + ret = -ENOMEM; + goto out_ops; + } + + if (data->indir_size) + data->indir_table = (u32 *)rss_config; + + if (data->hkey_size) + data->hkey = rss_config + indir_bytes; + + if (request->rss_context) + ret = ops->get_rxfh_context(dev, data->indir_table, data->hkey, + &dev_hfunc, request->rss_context); + else + ret = ops->get_rxfh(dev, data->indir_table, data->hkey, + &dev_hfunc); + + if (ret) + goto out_ops; + + data->hfunc = dev_hfunc; +out_ops: + ethnl_ops_complete(dev); + return ret; +} + +static int +rss_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + int len; + + len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ + nla_total_size(data->hkey_size); /* _RSS_HKEY */ + + return len; +} + +static int +rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + + if (nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc) || + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table) || + nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)) + return -EMSGSIZE; + + return 0; +} + +static void rss_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + + kfree(data->indir_table); +} + +const struct ethnl_request_ops ethnl_rss_request_ops = { + .request_cmd = ETHTOOL_MSG_RSS_GET, + .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, + .hdr_attr = ETHTOOL_A_RSS_HEADER, + .req_info_size = sizeof(struct rss_req_info), + .reply_data_size = sizeof(struct rss_reply_data), + + .parse_request = rss_parse_request, + .prepare_data = rss_prepare_data, + .reply_size = rss_reply_size, + .fill_reply = rss_fill_reply, + .cleanup_data = rss_cleanup_data, +}; -- cgit v1.2.3 From 94151f5aa9667c562281abeaaa5e89b9d5c17729 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sat, 3 Dec 2022 10:46:57 +0200 Subject: xfrm: interface: Add unstable helpers for setting/getting XFRM metadata from TC-BPF This change adds xfrm metadata helpers using the unstable kfunc call interface for the TC-BPF hooks. This allows steering traffic towards different IPsec connections based on logic implemented in bpf programs. This object is built based on the availability of BTF debug info. When setting the xfrm metadata, percpu metadata dsts are used in order to avoid allocating a metadata dst per packet. In order to guarantee safe module unload, the percpu dsts are allocated on first use and never freed. The percpu pointer is stored in net/core/filter.c so that it can be reused on module reload. The metadata percpu dsts take ownership of the original skb dsts so that they may be used as part of the xfrm transmission logic - e.g. for MTU calculations. Signed-off-by: Eyal Birger Link: https://lore.kernel.org/r/20221203084659.1837829-3-eyal.birger@gmail.com Signed-off-by: Martin KaFai Lau --- include/net/dst_metadata.h | 1 + include/net/xfrm.h | 17 ++++++ net/core/dst.c | 8 ++- net/core/filter.c | 9 ++++ net/xfrm/Makefile | 6 +++ net/xfrm/xfrm_interface_bpf.c | 115 +++++++++++++++++++++++++++++++++++++++++ net/xfrm/xfrm_interface_core.c | 14 +++++ 7 files changed, 168 insertions(+), 2 deletions(-) create mode 100644 net/xfrm/xfrm_interface_bpf.c (limited to 'include') diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index a454cf4327fe..1b7fae4c6b24 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -26,6 +26,7 @@ struct macsec_info { struct xfrm_md_info { u32 if_id; int link; + struct dst_entry *dst_orig; }; struct metadata_dst { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e0cc6791c001..3707e6b34e67 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -2086,4 +2086,21 @@ static inline bool xfrm6_local_dontfrag(const struct sock *sk) return false; } #endif + +#if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +extern struct metadata_dst __percpu *xfrm_bpf_md_dst; + +int register_xfrm_interface_bpf(void); + +#else + +static inline int register_xfrm_interface_bpf(void) +{ + return 0; +} + +#endif + #endif /* _NET_XFRM_H */ diff --git a/net/core/dst.c b/net/core/dst.c index bc9c9be4e080..bb14a0392388 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -316,6 +316,8 @@ void metadata_dst_free(struct metadata_dst *md_dst) if (md_dst->type == METADATA_IP_TUNNEL) dst_cache_destroy(&md_dst->u.tun_info.dst_cache); #endif + if (md_dst->type == METADATA_XFRM) + dst_release(md_dst->u.xfrm_info.dst_orig); kfree(md_dst); } EXPORT_SYMBOL_GPL(metadata_dst_free); @@ -340,16 +342,18 @@ EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); void metadata_dst_free_percpu(struct metadata_dst __percpu *md_dst) { -#ifdef CONFIG_DST_CACHE int cpu; for_each_possible_cpu(cpu) { struct metadata_dst *one_md_dst = per_cpu_ptr(md_dst, cpu); +#ifdef CONFIG_DST_CACHE if (one_md_dst->type == METADATA_IP_TUNNEL) dst_cache_destroy(&one_md_dst->u.tun_info.dst_cache); - } #endif + if (one_md_dst->type == METADATA_XFRM) + dst_release(one_md_dst->u.xfrm_info.dst_orig); + } free_percpu(md_dst); } EXPORT_SYMBOL_GPL(metadata_dst_free_percpu); diff --git a/net/core/filter.c b/net/core/filter.c index 8607136b6e2c..929358677183 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5631,6 +5631,15 @@ static const struct bpf_func_proto bpf_bind_proto = { }; #ifdef CONFIG_XFRM + +#if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ + (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + +struct metadata_dst __percpu *xfrm_bpf_md_dst; +EXPORT_SYMBOL_GPL(xfrm_bpf_md_dst); + +#endif + BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 08a2870fdd36..cd47f88921f5 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -5,6 +5,12 @@ xfrm_interface-$(CONFIG_XFRM_INTERFACE) += xfrm_interface_core.o +ifeq ($(CONFIG_XFRM_INTERFACE),m) +xfrm_interface-$(CONFIG_DEBUG_INFO_BTF_MODULES) += xfrm_interface_bpf.o +else ifeq ($(CONFIG_XFRM_INTERFACE),y) +xfrm_interface-$(CONFIG_DEBUG_INFO_BTF) += xfrm_interface_bpf.o +endif + obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ xfrm_sysctl.o xfrm_replay.o xfrm_device.o diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c new file mode 100644 index 000000000000..1ef2162cebcf --- /dev/null +++ b/net/xfrm/xfrm_interface_bpf.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable XFRM Helpers for TC-BPF hook + * + * These are called from SCHED_CLS BPF programs. Note that it is + * allowed to break compatibility for these functions since the interface they + * are exposed through to BPF programs is explicitly unstable. + */ + +#include +#include + +#include +#include + +/* bpf_xfrm_info - XFRM metadata information + * + * Members: + * @if_id - XFRM if_id: + * Transmit: if_id to be used in policy and state lookups + * Receive: if_id of the state matched for the incoming packet + * @link - Underlying device ifindex: + * Transmit: used as the underlying device in VRF routing + * Receive: the device on which the packet had been received + */ +struct bpf_xfrm_info { + u32 if_id; + int link; +}; + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in xfrm_interface BTF"); + +/* bpf_skb_get_xfrm_info - Get XFRM metadata + * + * Parameters: + * @skb_ctx - Pointer to ctx (__sk_buff) in TC program + * Cannot be NULL + * @to - Pointer to memory to which the metadata will be copied + * Cannot be NULL + */ +__used noinline +int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct xfrm_md_info *info; + + info = skb_xfrm_md_info(skb); + if (!info) + return -EINVAL; + + to->if_id = info->if_id; + to->link = info->link; + return 0; +} + +/* bpf_skb_get_xfrm_info - Set XFRM metadata + * + * Parameters: + * @skb_ctx - Pointer to ctx (__sk_buff) in TC program + * Cannot be NULL + * @from - Pointer to memory from which the metadata will be copied + * Cannot be NULL + */ +__used noinline +int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, + const struct bpf_xfrm_info *from) +{ + struct sk_buff *skb = (struct sk_buff *)skb_ctx; + struct metadata_dst *md_dst; + struct xfrm_md_info *info; + + if (unlikely(skb_metadata_dst(skb))) + return -EINVAL; + + if (!xfrm_bpf_md_dst) { + struct metadata_dst __percpu *tmp; + + tmp = metadata_dst_alloc_percpu(0, METADATA_XFRM, GFP_ATOMIC); + if (!tmp) + return -ENOMEM; + if (cmpxchg(&xfrm_bpf_md_dst, NULL, tmp)) + metadata_dst_free_percpu(tmp); + } + md_dst = this_cpu_ptr(xfrm_bpf_md_dst); + + info = &md_dst->u.xfrm_info; + + info->if_id = from->if_id; + info->link = from->link; + skb_dst_force(skb); + info->dst_orig = skb_dst(skb); + + dst_hold((struct dst_entry *)md_dst); + skb_dst_set(skb, (struct dst_entry *)md_dst); + return 0; +} + +__diag_pop() + +BTF_SET8_START(xfrm_ifc_kfunc_set) +BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info) +BTF_ID_FLAGS(func, bpf_skb_set_xfrm_info) +BTF_SET8_END(xfrm_ifc_kfunc_set) + +static const struct btf_kfunc_id_set xfrm_interface_kfunc_set = { + .owner = THIS_MODULE, + .set = &xfrm_ifc_kfunc_set, +}; + +int __init register_xfrm_interface_bpf(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &xfrm_interface_kfunc_set); +} diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 5a67b120c4db..1f99dc469027 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -396,6 +396,14 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if_id = md_info->if_id; fl->flowi_oif = md_info->link; + if (md_info->dst_orig) { + struct dst_entry *tmp_dst = dst; + + dst = md_info->dst_orig; + skb_dst_set(skb, dst); + md_info->dst_orig = NULL; + dst_release(tmp_dst); + } } else { if_id = xi->p.if_id; } @@ -1162,12 +1170,18 @@ static int __init xfrmi_init(void) if (err < 0) goto rtnl_link_failed; + err = register_xfrm_interface_bpf(); + if (err < 0) + goto kfunc_failed; + lwtunnel_encap_add_ops(&xfrmi_encap_ops, LWTUNNEL_ENCAP_XFRM); xfrm_if_register_cb(&xfrm_if_cb); return err; +kfunc_failed: + rtnl_link_unregister(&xfrmi_link_ops); rtnl_link_failed: xfrmi6_fini(); xfrmi6_failed: -- cgit v1.2.3 From 3afee4ed336ed7a6cff78d23339879ffb654e02e Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 22:10:23 +0200 Subject: net/mlx5: Add HW definitions for IPsec packet offload Add all needed bits to support IPsec packet offload mode. Reviewed-by: Raed Salem Reviewed-by: Saeed Mahameed Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h | 1 + include/linux/mlx5/mlx5_ifc.h | 53 +++++++++++++++++++++-- 2 files changed, 51 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h index 4312614bf3bc..c8fc3c838642 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.h @@ -71,6 +71,7 @@ enum { }; enum { + MLX5_ACCESS_ASO_OPC_MOD_IPSEC = 0x0, MLX5_ACCESS_ASO_OPC_MOD_FLOW_METER = 0x2, MLX5_ACCESS_ASO_OPC_MOD_MACSEC = 0x5, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5a4e914e2a6f..300b56ea5ff4 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -445,7 +445,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x6]; + u8 reformat_add_esp_trasport[0x1]; + u8 reserved_at_41[0x2]; + u8 reformat_del_esp_trasport[0x1]; + u8 reserved_at_44[0x2]; u8 execute_aso[0x1]; u8 reserved_at_47[0x19]; @@ -638,8 +641,10 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 reserved_at_1a0[0x8]; u8 macsec_syndrome[0x8]; + u8 ipsec_syndrome[0x8]; + u8 reserved_at_1b8[0x8]; - u8 reserved_at_1b0[0x50]; + u8 reserved_at_1c0[0x40]; }; struct mlx5_ifc_fte_match_set_misc3_bits { @@ -6384,6 +6389,9 @@ enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5, + MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8, + MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb, MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11, @@ -11563,6 +11571,41 @@ enum { MLX5_IPSEC_OBJECT_ICV_LEN_16B, }; +enum { + MLX5_IPSEC_ASO_REG_C_0_1 = 0x0, + MLX5_IPSEC_ASO_REG_C_2_3 = 0x1, + MLX5_IPSEC_ASO_REG_C_4_5 = 0x2, + MLX5_IPSEC_ASO_REG_C_6_7 = 0x3, +}; + +enum { + MLX5_IPSEC_ASO_MODE = 0x0, + MLX5_IPSEC_ASO_REPLAY_PROTECTION = 0x1, + MLX5_IPSEC_ASO_INC_SN = 0x2, +}; + +struct mlx5_ifc_ipsec_aso_bits { + u8 valid[0x1]; + u8 reserved_at_201[0x1]; + u8 mode[0x2]; + u8 window_sz[0x2]; + u8 soft_lft_arm[0x1]; + u8 hard_lft_arm[0x1]; + u8 remove_flow_enable[0x1]; + u8 esn_event_arm[0x1]; + u8 reserved_at_20a[0x16]; + + u8 remove_flow_pkt_cnt[0x20]; + + u8 remove_flow_soft_lft[0x20]; + + u8 reserved_at_260[0x80]; + + u8 mode_parameter[0x20]; + + u8 replay_protection_window[0x100]; +}; + struct mlx5_ifc_ipsec_obj_bits { u8 modify_field_select[0x40]; u8 full_offload[0x1]; @@ -11584,7 +11627,11 @@ struct mlx5_ifc_ipsec_obj_bits { u8 implicit_iv[0x40]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x8]; + u8 ipsec_aso_access_pd[0x18]; + u8 reserved_at_120[0xe0]; + + struct mlx5_ifc_ipsec_aso_bits ipsec_aso; }; struct mlx5_ifc_create_ipsec_obj_in_bits { -- cgit v1.2.3 From bffdeaa8a5af7200b0e74c9d5a41167f86626a36 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Tue, 6 Dec 2022 15:33:43 -0800 Subject: bpf: decouple prune and jump points BPF verifier marks some instructions as prune points. Currently these prune points serve two purposes. It's a point where verifier tries to find previously verified state and check current state's equivalence to short circuit verification for current code path. But also currently it's a point where jump history, used for precision backtracking, is updated. This is done so that non-linear flow of execution could be properly backtracked. Such coupling is coincidental and unnecessary. Some prune points are not part of some non-linear jump path, so don't need update of jump history. On the other hand, not all instructions which have to be recorded in jump history necessarily are good prune points. This patch splits prune and jump points into independent flags. Currently all prune points are marked as jump points to minimize amount of changes in this patch, but next patch will perform some optimization of prune vs jmp point placement. No functional changes are intended. Acked-by: John Fastabend Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20221206233345.438540-2-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + kernel/bpf/verifier.c | 57 +++++++++++++++++++++++++++++++++----------- 2 files changed, 44 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c07b351a5bc7..70d06a99f0b8 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -452,6 +452,7 @@ struct bpf_insn_aux_data { /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ bool prune_point; + bool jmp_point; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 67a13110bc22..cf580e4c00f5 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2530,6 +2530,16 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static void mark_jmp_point(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].jmp_point = true; +} + +static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].jmp_point; +} + /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) @@ -2538,6 +2548,9 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_idx_pair *p; size_t alloc_size; + if (!is_jmp_point(env, env->insn_idx)) + return 0; + cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); @@ -12140,11 +12153,16 @@ static struct bpf_verifier_state_list **explored_state( return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } -static void init_explored_state(struct bpf_verifier_env *env, int idx) +static void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } +static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].prune_point; +} + enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, @@ -12173,9 +12191,11 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return -EINVAL; } - if (e == BRANCH) + if (e == BRANCH) { /* mark branch target for state pruning */ - init_explored_state(env, w); + mark_prune_point(env, w); + mark_jmp_point(env, w); + } if (insn_state[w] == 0) { /* tree-edge */ @@ -12213,10 +12233,13 @@ static int visit_func_call_insn(int t, int insn_cnt, if (ret) return ret; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + if (t + 1 < insn_cnt) { + mark_prune_point(env, t + 1); + mark_jmp_point(env, t + 1); + } if (visit_callee) { - init_explored_state(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, /* It's ok to allow recursion from CFG point of * view. __check_func_call() will do the actual @@ -12250,13 +12273,15 @@ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) return DONE_EXPLORING; case BPF_CALL: - if (insns[t].imm == BPF_FUNC_timer_set_callback) + if (insns[t].imm == BPF_FUNC_timer_set_callback) { /* Mark this call insn to trigger is_state_visited() check * before call itself is processed by __check_func_call(). * Otherwise new async state will be pushed for further * exploration. */ - init_explored_state(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); + } return visit_func_call_insn(t, insn_cnt, insns, env, insns[t].src_reg == BPF_PSEUDO_CALL); @@ -12274,18 +12299,22 @@ static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) * but it's marked, since backtracking needs * to record jmp history in is_state_visited(). */ - init_explored_state(env, t + insns[t].off + 1); + mark_prune_point(env, t + insns[t].off + 1); + mark_jmp_point(env, t + insns[t].off + 1); /* tell verifier to check for equivalent states * after every call and jump */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + if (t + 1 < insn_cnt) { + mark_prune_point(env, t + 1); + mark_jmp_point(env, t + 1); + } return ret; default: /* conditional jump with two edges */ - init_explored_state(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret) return ret; @@ -13320,11 +13349,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; - if (!env->insn_aux_data[insn_idx].prune_point) + if (!is_prune_point(env, insn_idx)) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ - return 0; + return push_jmp_history(env, cur); /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 -- cgit v1.2.3 From e9b4aeed56699b469206d05e706ddf2db95700a9 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 3 Dec 2022 17:51:04 +0100 Subject: net: xsk: Don't include There is no need to include here. Prefer the less invasive which is needed for 'hlist_head'. Signed-off-by: Christophe JAILLET Acked-by: John Fastabend Link: https://lore.kernel.org/r/88d6a1d88764cca328610854f890a9ca1f4b029e.1670086246.git.christophe.jaillet@wanadoo.fr Signed-off-by: Alexei Starovoitov --- include/net/netns/xdp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netns/xdp.h b/include/net/netns/xdp.h index e5734261ba0a..21a4f25a187a 100644 --- a/include/net/netns/xdp.h +++ b/include/net/netns/xdp.h @@ -2,8 +2,8 @@ #ifndef __NETNS_XDP_H__ #define __NETNS_XDP_H__ -#include #include +#include struct netns_xdp { struct mutex lock; -- cgit v1.2.3 From ed883bec679b027b198d57a336715f8298fb88b4 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 5 Dec 2022 12:34:42 +0100 Subject: net: ethernet: mtk_wed: add reset to rx_ring_setup callback This patch adds reset parameter to mtk_wed_rx_ring_setup signature in order to align rx_ring_setup callback to tx_ring_setup one introduced in 'commit 23dca7a90017 ("net: ethernet: mtk_wed: add reset to tx_ring_setup callback")' Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Reviewed-by: Leon Romanovsky Link: https://lore.kernel.org/r/29c6e7a5469e784406cf3e2920351d1207713d05.1670239984.git.lorenzo@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_wed.c | 20 +++++++++++++------- drivers/net/wireless/mediatek/mt76/dma.c | 2 +- include/linux/soc/mediatek/mtk_wed.h | 8 ++++---- 3 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index d041615b2bac..06b6cc53fa02 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1210,7 +1210,8 @@ mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size, } static int -mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size) +mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size, + bool reset) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; struct mtk_wed_ring *wdma; @@ -1219,8 +1220,8 @@ mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size) return -EINVAL; wdma = &dev->tx_wdma[idx]; - if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, - true)) + if (!reset && mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, + desc_size, true)) return -ENOMEM; wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_BASE, @@ -1230,6 +1231,9 @@ mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size) wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0); wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_DMA_IDX, 0); + if (reset) + mtk_wed_ring_reset(wdma, MTK_WED_WDMA_RING_SIZE, true); + if (!idx) { wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_BASE, wdma->desc_phys); @@ -1569,18 +1573,20 @@ mtk_wed_txfree_ring_setup(struct mtk_wed_device *dev, void __iomem *regs) } static int -mtk_wed_rx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) +mtk_wed_rx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs, + bool reset) { struct mtk_wed_ring *ring = &dev->rx_ring[idx]; if (WARN_ON(idx >= ARRAY_SIZE(dev->rx_ring))) return -EINVAL; - if (mtk_wed_ring_alloc(dev, ring, MTK_WED_RX_RING_SIZE, - sizeof(*ring->desc), false)) + if (!reset && mtk_wed_ring_alloc(dev, ring, MTK_WED_RX_RING_SIZE, + sizeof(*ring->desc), false)) return -ENOMEM; - if (mtk_wed_wdma_tx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + if (mtk_wed_wdma_tx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE, + reset)) return -ENOMEM; ring->reg_base = MTK_WED_RING_RX_DATA(idx); diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 3f8c0845fcca..f795548562f5 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -648,7 +648,7 @@ mt76_dma_wed_setup(struct mt76_dev *dev, struct mt76_queue *q) q->wed_regs = wed->txfree_ring.reg_base; break; case MT76_WED_Q_RX: - ret = mtk_wed_device_rx_ring_setup(wed, ring, q->regs); + ret = mtk_wed_device_rx_ring_setup(wed, ring, q->regs, false); if (!ret) q->wed_regs = wed->rx_ring[ring].reg_base; break; diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index beb190449704..a0746d4aec20 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -160,7 +160,7 @@ struct mtk_wed_ops { int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, void __iomem *regs, bool reset); int (*rx_ring_setup)(struct mtk_wed_device *dev, int ring, - void __iomem *regs); + void __iomem *regs, bool reset); int (*txfree_ring_setup)(struct mtk_wed_device *dev, void __iomem *regs); int (*msg_update)(struct mtk_wed_device *dev, int cmd_id, @@ -228,8 +228,8 @@ mtk_wed_get_rx_capa(struct mtk_wed_device *dev) (_dev)->ops->irq_get(_dev, _mask) #define mtk_wed_device_irq_set_mask(_dev, _mask) \ (_dev)->ops->irq_set_mask(_dev, _mask) -#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) \ - (_dev)->ops->rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs, _reset) \ + (_dev)->ops->rx_ring_setup(_dev, _ring, _regs, _reset) #define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) \ (_dev)->ops->ppe_check(_dev, _skb, _reason, _hash) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) \ @@ -249,7 +249,7 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) #define mtk_wed_device_irq_get(_dev, _mask) 0 #define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) -#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs, _reset) -ENODEV #define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) do {} while (0) #define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV #define mtk_wed_device_stop(_dev) do {} while (0) -- cgit v1.2.3 From 5b481acab4ce017fda8166fa9428511da41109e5 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Tue, 6 Dec 2022 15:59:32 +0100 Subject: bpf: do not rely on ALLOW_ERROR_INJECTION for fmod_ret The current way of expressing that a non-bpf kernel component is willing to accept that bpf programs can be attached to it and that they can change the return value is to abuse ALLOW_ERROR_INJECTION. This is debated in the link below, and the result is that it is not a reasonable thing to do. Reuse the kfunc declaration structure to also tag the kernel functions we want to be fmodret. This way we can control from any subsystem which functions are being modified by bpf without touching the verifier. Link: https://lore.kernel.org/all/20221121104403.1545f9b5@gandalf.local.home/ Suggested-by: Alexei Starovoitov Signed-off-by: Benjamin Tissoires Acked-by: Alexei Starovoitov Link: https://lore.kernel.org/r/20221206145936.922196-2-benjamin.tissoires@redhat.com --- include/linux/btf.h | 2 ++ kernel/bpf/btf.c | 30 +++++++++++++++++++++++++----- kernel/bpf/verifier.c | 17 +++++++++++++++-- net/bpf/test_run.c | 14 +++++++++++--- 4 files changed, 53 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/btf.h b/include/linux/btf.h index f9aababc5d78..6a0808e7845c 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -412,8 +412,10 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_id_set_contains(const struct btf *btf, enum bpf_prog_type prog_type, u32 kfunc_btf_id); +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id); int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, const struct btf_kfunc_id_set *s); +int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset); s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 35c07afac924..c1df506293e4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -204,6 +204,7 @@ enum btf_kfunc_hook { BTF_KFUNC_HOOK_STRUCT_OPS, BTF_KFUNC_HOOK_TRACING, BTF_KFUNC_HOOK_SYSCALL, + BTF_KFUNC_HOOK_FMODRET, BTF_KFUNC_HOOK_MAX, }; @@ -7448,11 +7449,14 @@ u32 *btf_kfunc_id_set_contains(const struct btf *btf, return __btf_kfunc_id_set_contains(btf, hook, kfunc_btf_id); } -/* This function must be invoked only from initcalls/module init functions */ -int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, - const struct btf_kfunc_id_set *kset) +u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id) +{ + return __btf_kfunc_id_set_contains(btf, BTF_KFUNC_HOOK_FMODRET, kfunc_btf_id); +} + +static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, + const struct btf_kfunc_id_set *kset) { - enum btf_kfunc_hook hook; struct btf *btf; int ret; @@ -7471,13 +7475,29 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, if (IS_ERR(btf)) return PTR_ERR(btf); - hook = bpf_prog_type_to_kfunc_hook(prog_type); ret = btf_populate_kfunc_set(btf, hook, kset->set); btf_put(btf); return ret; } + +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, + const struct btf_kfunc_id_set *kset) +{ + enum btf_kfunc_hook hook; + + hook = bpf_prog_type_to_kfunc_hook(prog_type); + return __register_btf_kfunc_id_set(hook, kset); +} EXPORT_SYMBOL_GPL(register_btf_kfunc_id_set); +/* This function must be invoked only from initcalls/module init functions */ +int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset) +{ + return __register_btf_kfunc_id_set(BTF_KFUNC_HOOK_FMODRET, kset); +} +EXPORT_SYMBOL_GPL(register_btf_fmodret_id_set); + s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id) { struct btf_id_dtor_kfunc_tab *tab = btf->dtor_kfunc_tab; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 225666307bba..ec2e6ec7309e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15021,12 +15021,22 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: - /* fentry/fexit/fmod_ret progs can be sleepable only if they are + + /* fentry/fexit/fmod_ret progs can be sleepable if they are * attached to ALLOW_ERROR_INJECTION and are not in denylist. */ if (!check_non_sleepable_error_inject(btf_id) && within_error_injection_list(addr)) ret = 0; + /* fentry/fexit/fmod_ret progs can also be sleepable if they are + * in the fmodret id set with the KF_SLEEPABLE flag. + */ + else { + u32 *flags = btf_kfunc_is_modify_return(btf, btf_id); + + if (flags && (*flags & KF_SLEEPABLE)) + ret = 0; + } break; case BPF_PROG_TYPE_LSM: /* LSM progs check that they are attached to bpf_lsm_*() funcs. @@ -15047,7 +15057,10 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "can't modify return codes of BPF programs\n"); return -EINVAL; } - ret = check_attach_modify_return(addr, tname); + ret = -EINVAL; + if (btf_kfunc_is_modify_return(btf, btf_id) || + !check_attach_modify_return(addr, tname)) + ret = 0; if (ret) { bpf_log(log, "%s() is not modifiable\n", tname); return ret; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 13d578ce2a09..5079fb089b5f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -489,7 +489,6 @@ int noinline bpf_fentry_test1(int a) return a + 1; } EXPORT_SYMBOL_GPL(bpf_fentry_test1); -ALLOW_ERROR_INJECTION(bpf_fentry_test1, ERRNO); int noinline bpf_fentry_test2(int a, u64 b) { @@ -733,7 +732,15 @@ noinline void bpf_kfunc_call_test_destructive(void) __diag_pop(); -ALLOW_ERROR_INJECTION(bpf_modify_return_test, ERRNO); +BTF_SET8_START(bpf_test_modify_return_ids) +BTF_ID_FLAGS(func, bpf_modify_return_test) +BTF_ID_FLAGS(func, bpf_fentry_test1, KF_SLEEPABLE) +BTF_SET8_END(bpf_test_modify_return_ids) + +static const struct btf_kfunc_id_set bpf_test_modify_return_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modify_return_ids, +}; BTF_SET8_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) @@ -1668,7 +1675,8 @@ static int __init bpf_prog_test_run_init(void) }; int ret; - ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); + ret = register_btf_fmodret_id_set(&bpf_test_modify_return_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_prog_test_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_prog_test_kfunc_set); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_prog_test_kfunc_set); return ret ?: register_btf_id_dtor_kfuncs(bpf_prog_test_dtor_kfunc, -- cgit v1.2.3 From df268f6ca7da1088d7ecff4250d1478d3fa2406b Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Tue, 6 Dec 2022 20:51:12 +0200 Subject: net/mlx5: Introduce IFC bits for migratable Introduce IFC related capabilities to enable setting VF to be able to perform live migration. e.g.: to be migratable. Signed-off-by: Yishai Hadas Reviewed-by: Mark Bloch Acked-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- include/linux/mlx5/mlx5_ifc.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5a4e914e2a6f..2093131483c7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -68,6 +68,7 @@ enum { MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4, + MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20, MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25, }; @@ -1875,7 +1876,10 @@ struct mlx5_ifc_cmd_hca_cap_bits { }; struct mlx5_ifc_cmd_hca_cap_2_bits { - u8 reserved_at_0[0xa0]; + u8 reserved_at_0[0x80]; + + u8 migratable[0x1]; + u8 reserved_at_81[0x1f]; u8 max_reformat_insert_size[0x8]; u8 max_reformat_insert_offset[0x8]; -- cgit v1.2.3 From da65e9ff3bf614d2836e38e1d405c7073e6ba3b7 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 20:51:15 +0200 Subject: devlink: Expose port function commands to control RoCE Expose port function commands to enable / disable RoCE, this is used to control the port RoCE device capabilities. When RoCE is disabled for a function of the port, function cannot create any RoCE specific resources (e.g GID table). It also saves system memory utilization. For example disabling RoCE enable a VF/SF saves 1 Mbytes of system memory per function. Example of a PCI VF port which supports function configuration: Set RoCE of the VF's port function. $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 roce enable $ devlink port function set pci/0000:06:00.0/2 roce disable $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 roce disable Signed-off-by: Shay Drory Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 34 ++++++- include/net/devlink.h | 18 ++++ include/uapi/linux/devlink.h | 10 ++ net/core/devlink.c | 113 ++++++++++++++++++++++ 4 files changed, 174 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 2c637f4aae8e..c3302d23e480 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -110,7 +110,7 @@ devlink ports for both the controllers. Function configuration ====================== -A user can configure the function attribute before enumerating the PCI +Users can configure one or more function attributes before enumerating the PCI function. Usually it means, user should configure function attribute before a bus specific device for the function is created. However, when SRIOV is enabled, virtual function devices are created on the PCI bus. @@ -122,6 +122,9 @@ A user may set the hardware address of the function using `devlink port function set hw_addr` command. For Ethernet port function this means a MAC address. +Users may also set the RoCE capability of the function using +`devlink port function set roce` command. + Function attributes =================== @@ -162,6 +165,35 @@ device created for the PCI VF/SF. function: hw_addr 00:00:00:00:88:88 +RoCE capability setup +--------------------- +Not all PCI VFs/SFs require RoCE capability. + +When RoCE capability is disabled, it saves system memory per PCI VF/SF. + +When user disables RoCE capability for a VF/SF, user application cannot send or +receive any RoCE packets through this VF/SF and RoCE GID table for this PCI +will be empty. + +When RoCE capability is disabled in the device using port function attribute, +VF/SF driver cannot override it. + +- Get RoCE capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 roce enable + +- Set RoCE capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 roce disable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 roce disable + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index 5f6eca5e4a40..ce4c65d2f2e7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1451,6 +1451,24 @@ struct devlink_ops { int (*port_function_hw_addr_set)(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); + /** + * @port_fn_roce_get: Port function's roce get function. + * + * Query RoCE state of a function managed by the devlink port. + * Return -EOPNOTSUPP if port function RoCE handling is not supported. + */ + int (*port_fn_roce_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + /** + * @port_fn_roce_set: Port function's roce set function. + * + * Enable/Disable the RoCE state of a function managed by the devlink + * port. + * Return -EOPNOTSUPP if port function RoCE handling is not supported. + */ + int (*port_fn_roce_set)(struct devlink_port *devlink_port, + bool enable, struct netlink_ext_ack *extack); /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 70191d96af89..6cc2925bd478 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -658,11 +658,21 @@ enum devlink_resource_unit { DEVLINK_RESOURCE_UNIT_ENTRY, }; +enum devlink_port_fn_attr_cap { + DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, + + /* Add new caps above */ + __DEVLINK_PORT_FN_ATTR_CAPS_MAX, +}; + +#define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) + enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 diff --git a/net/core/devlink.c b/net/core/devlink.c index 035249c5dd17..8c0ad52431c5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -195,11 +195,16 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); +#define DEVLINK_PORT_FN_CAPS_VALID_MASK \ + (_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1) + static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, DEVLINK_PORT_FN_STATE_ACTIVE), + [DEVLINK_PORT_FN_ATTR_CAPS] = + NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), }; static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { @@ -680,6 +685,60 @@ devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, return 0; } +static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, + u32 cap, bool is_enable) +{ + caps->selector |= cap; + if (is_enable) + caps->value |= cap; +} + +static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!ops->port_fn_roce_get) + return 0; + + err = ops->port_fn_roce_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable); + return 0; +} + +static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + struct nla_bitfield32 caps = {}; + int err; + + err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack); + if (err) + return err; + + if (!caps.selector) + return 0; + err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, + caps.selector); + if (err) + return err; + + *msg_updated = true; + return 0; +} + static int devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, @@ -1263,6 +1322,35 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, return 0; } +static int +devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + return ops->port_fn_roce_set(devlink_port, enable, extack); +} + +static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nla_bitfield32 caps; + u32 caps_value; + int err; + + caps = nla_get_bitfield32(attr); + caps_value = caps.value & caps.selector; + if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) { + err = devlink_port_fn_roce_set(devlink_port, + caps_value & DEVLINK_PORT_FN_CAP_ROCE, + extack); + if (err) + return err; + } + return 0; +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -1281,6 +1369,10 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por &msg_updated); if (err) goto out; + err = devlink_port_fn_caps_fill(ops, port, msg, extack, + &msg_updated); + if (err) + goto out; err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); out: if (err || !msg_updated) @@ -1653,6 +1745,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, struct netlink_ext_ack *extack) { const struct devlink_ops *ops = devlink_port->devlink->ops; + struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && !ops->port_function_hw_addr_set) { @@ -1665,6 +1758,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, "Function does not support state setting"); return -EOPNOTSUPP; } + attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; + if (attr) { + struct nla_bitfield32 caps; + + caps = nla_get_bitfield32(attr); + if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE && + !ops->port_fn_roce_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support RoCE function attribute"); + return -EOPNOTSUPP; + } + } return 0; } @@ -1692,6 +1797,14 @@ static int devlink_port_function_set(struct devlink_port *port, if (err) return err; } + + attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; + if (attr) { + err = devlink_port_fn_caps_set(port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. -- cgit v1.2.3 From 47d0c500d76c7b1d220c47cd875763fef04eba2e Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 20:51:16 +0200 Subject: net/mlx5: Add generic getters for other functions caps Downstream patch requires to get other function GENERAL2 caps while mlx5_vport_get_other_func_cap() gets only one type of caps (general). Rename it to represent this and introduce a generic implementation of mlx5_vport_get_other_func_cap(). Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Acked-by: Saeed Mahameed Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/vport.c | 6 ++++-- include/linux/mlx5/vport.h | 2 ++ 5 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9b6fbb19c22a..33dffcb8bdd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3889,7 +3889,7 @@ static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, if (!query_ctx) return -ENOMEM; - err = mlx5_vport_get_other_func_cap(esw->dev, vport_num, query_ctx); + err = mlx5_vport_get_other_func_general_cap(esw->dev, vport_num, query_ctx); if (err) goto out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index a806e3de7b7c..09473983778f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -324,7 +324,8 @@ void mlx5_unload_one_devl_locked(struct mlx5_core_dev *dev); int mlx5_load_one(struct mlx5_core_dev *dev, bool recovery); int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery); -int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out); +#define mlx5_vport_get_other_func_general_cap(dev, fid, out) \ + mlx5_vport_get_other_func_cap(dev, fid, out, MLX5_CAP_GENERAL) void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work); static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 662f1d55e30e..6bde18bcd42f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "mlx5_core.h" #include "mlx5_irq.h" #include "pci_irq.h" @@ -101,7 +102,7 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int function_id, goto out; } - ret = mlx5_vport_get_other_func_cap(dev, function_id, query_cap); + ret = mlx5_vport_get_other_func_general_cap(dev, function_id, query_cap); if (ret) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index d5c317325030..7eca7582f243 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -1160,14 +1160,16 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); -int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out) +int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out, + u16 opmod) { - u16 opmod = (MLX5_CAP_GENERAL << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01); u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)] = {}; + opmod = (opmod << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01); MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); MLX5_SET(query_hca_cap_in, in, op_mod, opmod); MLX5_SET(query_hca_cap_in, in, function_id, function_id); MLX5_SET(query_hca_cap_in, in, other_function, true); return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out); } +EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap); diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index aad53cb72f17..7f31432f44c2 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -132,4 +132,6 @@ int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev, int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev); u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev); +int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out, + u16 opmod); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From a8ce7b26a51efc4d7753b23d639ae092878a6193 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 20:51:18 +0200 Subject: devlink: Expose port function commands to control migratable Expose port function commands to enable / disable migratable capability, this is used to set the port function as migratable. Live migration is the process of transferring a live virtual machine from one physical host to another without disrupting its normal operation. In order for a VM to be able to perform LM, all the VM components must be able to perform migration. e.g.: to be migratable. In order for VF to be migratable, VF must be bound to VFIO driver with migration support. When migratable capability is enabled for a function of the port, the device is making the necessary preparations for the function to be migratable, which might include disabling features which cannot be migrated. Example of LM with migratable function configuration: Set migratable of the VF's port function. $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 migratable disable $ devlink port function set pci/0000:06:00.0/2 migratable enable $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 migratable enable Bind VF to VFIO driver with migration support: $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/unbind $ echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:08:00.0/driver_override $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/bind Attach VF to the VM. Start the VM. Perform LM. Signed-off-by: Shay Drory Reviewed-by: Jiri Pirko Acked-by: Shannon Nelson Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 46 +++++++++++++++++++ include/net/devlink.h | 21 +++++++++ include/uapi/linux/devlink.h | 3 ++ net/core/devlink.c | 55 +++++++++++++++++++++++ 4 files changed, 125 insertions(+) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index c3302d23e480..3da590953ce8 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -125,6 +125,9 @@ this means a MAC address. Users may also set the RoCE capability of the function using `devlink port function set roce` command. +Users may also set the function as migratable using +'devlink port function set migratable' command. + Function attributes =================== @@ -194,6 +197,49 @@ VF/SF driver cannot override it. function: hw_addr 00:00:00:00:00:00 roce disable +migratable capability setup +--------------------------- +Live migration is the process of transferring a live virtual machine +from one physical host to another without disrupting its normal +operation. + +User who want PCI VFs to be able to perform live migration need to +explicitly enable the VF migratable capability. + +When user enables migratable capability for a VF, and the HV binds the VF to VFIO driver +with migration support, the user can migrate the VM with this VF from one HV to a +different one. + +However, when migratable capability is enable, device will disable features which cannot +be migrated. Thus migratable cap can impose limitations on a VF so let the user decide. + +Example of LM with migratable function configuration: +- Get migratable capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable disable + +- Set migratable capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 migratable enable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable enable + +- Bind VF to VFIO driver with migration support:: + + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/unbind + $ echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:08:00.0/driver_override + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/bind + +Attach VF to the VM. +Start the VM. +Perform live migration. + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index ce4c65d2f2e7..0f376a28b9c4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1469,6 +1469,27 @@ struct devlink_ops { */ int (*port_fn_roce_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_get: Port function's migratable get function. + * + * Query migratable state of a function managed by the devlink port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_set: Port function's migratable set function. + * + * Enable/Disable migratable state of a function managed by the devlink + * port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6cc2925bd478..3782d4219ac9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -660,12 +660,15 @@ enum devlink_resource_unit { enum devlink_port_fn_attr_cap { DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, + DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT, /* Add new caps above */ __DEVLINK_PORT_FN_ATTR_CAPS_MAX, }; #define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) +#define DEVLINK_PORT_FN_CAP_MIGRATABLE \ + _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT) enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ad52431c5..ab40ebcb4aea 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -715,6 +715,29 @@ static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, return 0; } +static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!ops->port_fn_migratable_get || + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) + return 0; + + err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); + return 0; +} + static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, struct devlink_port *devlink_port, struct sk_buff *msg, @@ -728,6 +751,10 @@ static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, if (err) return err; + err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack); + if (err) + return err; + if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, @@ -1322,6 +1349,15 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, return 0; } +static int +devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + return ops->port_fn_migratable_set(devlink_port, enable, extack); +} + static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) @@ -1348,6 +1384,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, if (err) return err; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + err = devlink_port_fn_mig_set(devlink_port, caps_value & + DEVLINK_PORT_FN_CAP_MIGRATABLE, + extack); + if (err) + return err; + } return 0; } @@ -1769,6 +1812,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + if (!ops->port_fn_migratable_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support migratable function attribute"); + return -EOPNOTSUPP; + } + if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "migratable function attribute supported for VFs only"); + return -EOPNOTSUPP; + } + } } return 0; } -- cgit v1.2.3 From f1543c7abab25d93bc8e9fae79b4cb3153ed6669 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 31 May 2022 13:55:28 +0300 Subject: net/mlx5: mlx5_ifc updates for MATCH_DEFINER general object Update full structure of match definer and add an ID of the SELECT match definer type. Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 68 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 66 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 2093131483c7..294cfe175c4b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6108,6 +6108,38 @@ struct mlx5_ifc_match_definer_format_32_bits { u8 inner_dmac_15_0[0x10]; }; +enum { + MLX5_IFC_DEFINER_FORMAT_ID_SELECT = 61, +}; + +#define MLX5_IFC_DEFINER_FORMAT_OFFSET_UNUSED 0x0 +#define MLX5_IFC_DEFINER_FORMAT_OFFSET_OUTER_ETH_PKT_LEN 0x48 +#define MLX5_IFC_DEFINER_DW_SELECTORS_NUM 9 +#define MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM 8 + +struct mlx5_ifc_match_definer_match_mask_bits { + u8 reserved_at_1c0[5][0x20]; + u8 match_dw_8[0x20]; + u8 match_dw_7[0x20]; + u8 match_dw_6[0x20]; + u8 match_dw_5[0x20]; + u8 match_dw_4[0x20]; + u8 match_dw_3[0x20]; + u8 match_dw_2[0x20]; + u8 match_dw_1[0x20]; + u8 match_dw_0[0x20]; + + u8 match_byte_7[0x8]; + u8 match_byte_6[0x8]; + u8 match_byte_5[0x8]; + u8 match_byte_4[0x8]; + + u8 match_byte_3[0x8]; + u8 match_byte_2[0x8]; + u8 match_byte_1[0x8]; + u8 match_byte_0[0x8]; +}; + struct mlx5_ifc_match_definer_bits { u8 modify_field_select[0x40]; @@ -6116,9 +6148,41 @@ struct mlx5_ifc_match_definer_bits { u8 reserved_at_80[0x10]; u8 format_id[0x10]; - u8 reserved_at_a0[0x160]; + u8 reserved_at_a0[0x60]; - u8 match_mask[16][0x20]; + u8 format_select_dw3[0x8]; + u8 format_select_dw2[0x8]; + u8 format_select_dw1[0x8]; + u8 format_select_dw0[0x8]; + + u8 format_select_dw7[0x8]; + u8 format_select_dw6[0x8]; + u8 format_select_dw5[0x8]; + u8 format_select_dw4[0x8]; + + u8 reserved_at_100[0x18]; + u8 format_select_dw8[0x8]; + + u8 reserved_at_120[0x20]; + + u8 format_select_byte3[0x8]; + u8 format_select_byte2[0x8]; + u8 format_select_byte1[0x8]; + u8 format_select_byte0[0x8]; + + u8 format_select_byte7[0x8]; + u8 format_select_byte6[0x8]; + u8 format_select_byte5[0x8]; + u8 format_select_byte4[0x8]; + + u8 reserved_at_180[0x40]; + + union { + struct { + u8 match_mask[16][0x20]; + }; + struct mlx5_ifc_match_definer_match_mask_bits match_mask_format; + }; }; struct mlx5_ifc_general_obj_in_cmd_hdr_bits { -- cgit v1.2.3 From 38bf24c38d19dc4ba5ec684ac2afa2f8e256db1e Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 15 Aug 2022 12:45:28 +0300 Subject: net/mlx5: fs, add match on ranges API Range is a new flow destination type which allows matching on a range of values instead of matching on a specific value. Range flow destination has the following fields: - hit_ft: flow table to forward the traffic in case of hit - miss_ft: flow table to forward the traffic in case of miss - field: which packet characteristic to match on - min: minimal value for the selected field - max: maximal value for the selected field Note: - In order to match, the value in the packet should meet the following criteria: min <= value < max - Currently, the only supported field type is L2 packet length Signed-off-by: Yevgeny Kliteynik Reviewed-by: Alex Vesker Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 16 ++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 11 +++++++++-- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 1 + include/linux/mlx5/fs.h | 12 ++++++++++++ 4 files changed, 38 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index c5bb79a4fa57..2732128e7a6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -228,6 +228,17 @@ const char *parse_fs_hdrs(struct trace_seq *p, return ret; } +static const char +*fs_dest_range_field_to_str(enum mlx5_flow_dest_range_field field) +{ + switch (field) { + case MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN: + return "packet len"; + default: + return "unknown dest range field"; + } +} + const char *parse_fs_dst(struct trace_seq *p, const struct mlx5_flow_destination *dst, u32 counter_id) @@ -259,6 +270,11 @@ const char *parse_fs_dst(struct trace_seq *p, case MLX5_FLOW_DESTINATION_TYPE_PORT: trace_seq_printf(p, "port\n"); break; + case MLX5_FLOW_DESTINATION_TYPE_RANGE: + trace_seq_printf(p, "field=%s min=%d max=%d\n", + fs_dest_range_field_to_str(dst->range.field), + dst->range.min, dst->range.max); + break; case MLX5_FLOW_DESTINATION_TYPE_NONE: trace_seq_printf(p, "none\n"); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index d53190f22871..4dcd26b86662 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -448,7 +448,8 @@ static bool is_fwd_dest_type(enum mlx5_flow_destination_type type) type == MLX5_FLOW_DESTINATION_TYPE_UPLINK || type == MLX5_FLOW_DESTINATION_TYPE_VPORT || type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER || - type == MLX5_FLOW_DESTINATION_TYPE_TIR; + type == MLX5_FLOW_DESTINATION_TYPE_TIR || + type == MLX5_FLOW_DESTINATION_TYPE_RANGE; } static bool check_valid_spec(const struct mlx5_flow_spec *spec) @@ -1578,7 +1579,13 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM && d1->ft_num == d2->ft_num) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER && - d1->sampler_id == d2->sampler_id)) + d1->sampler_id == d2->sampler_id) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_RANGE && + d1->range.field == d2->range.field && + d1->range.hit_ft == d2->range.hit_ft && + d1->range.miss_ft == d2->range.miss_ft && + d1->range.min == d2->range.min && + d1->range.max == d2->range.max)) return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 3af50fd04d28..f137a0611b77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -123,6 +123,7 @@ enum mlx5_flow_steering_mode { enum mlx5_flow_steering_capabilty { MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX = 1UL << 0, MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX = 1UL << 1, + MLX5_FLOW_STEERING_CAP_MATCH_RANGES = 1UL << 2, }; struct mlx5_flow_steering { diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index c7a91981cd5a..ba6958b49a8e 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -50,6 +50,7 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_PORT, MLX5_FLOW_DESTINATION_TYPE_COUNTER, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM, + MLX5_FLOW_DESTINATION_TYPE_RANGE, }; enum { @@ -143,6 +144,10 @@ enum { MLX5_FLOW_DEST_VPORT_REFORMAT_ID = BIT(1), }; +enum mlx5_flow_dest_range_field { + MLX5_FLOW_DEST_RANGE_FIELD_PKT_LEN = 0, +}; + struct mlx5_flow_destination { enum mlx5_flow_destination_type type; union { @@ -156,6 +161,13 @@ struct mlx5_flow_destination { struct mlx5_pkt_reformat *pkt_reformat; u8 flags; } vport; + struct { + struct mlx5_flow_table *hit_ft; + struct mlx5_flow_table *miss_ft; + enum mlx5_flow_dest_range_field field; + u32 min; + u32 max; + } range; u32 sampler_id; }; }; -- cgit v1.2.3 From 6b75bd3d036745b9be30917909f03602099adbdb Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 8 Dec 2022 02:11:35 +0530 Subject: bpf: Refactor ARG_PTR_TO_DYNPTR checks into process_dynptr_func ARG_PTR_TO_DYNPTR is akin to ARG_PTR_TO_TIMER, ARG_PTR_TO_KPTR, where the underlying register type is subjected to more special checks to determine the type of object represented by the pointer and its state consistency. Move dynptr checks to their own 'process_dynptr_func' function so that is consistent and in-line with existing code. This also makes it easier to reuse this code for kfunc handling. Then, reuse this consolidated function in kfunc dynptr handling too. Note that for kfuncs, the arg_type constraint of DYNPTR_TYPE_LOCAL has been lifted. Acked-by: David Vernet Acked-by: Joanne Koong Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221207204141.308952-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 8 +- kernel/bpf/verifier.c | 134 +++++++++++---------- .../selftests/bpf/prog_tests/kfunc_dynptr_param.c | 7 +- .../selftests/bpf/progs/test_kfunc_dynptr_param.c | 12 -- 4 files changed, 75 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 70d06a99f0b8..df0cb825e0e3 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -615,11 +615,9 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, enum bpf_arg_type arg_type); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); -bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, - struct bpf_reg_state *reg); -bool is_dynptr_type_expected(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, - enum bpf_arg_type arg_type); +struct bpf_call_arg_meta; +int process_dynptr_func(struct bpf_verifier_env *env, int regno, + enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta); /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 3194e9d9e4e4..fcd8a71035aa 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -810,8 +810,7 @@ static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_ return true; } -bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, - struct bpf_reg_state *reg) +static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi = get_spi(reg->off); @@ -830,9 +829,8 @@ bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, return true; } -bool is_dynptr_type_expected(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, - enum bpf_arg_type arg_type) +static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + enum bpf_arg_type arg_type) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type dynptr_type; @@ -5859,6 +5857,65 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, return 0; } +int process_dynptr_func(struct bpf_verifier_env *env, int regno, + enum bpf_arg_type arg_type, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + + /* We only need to check for initialized / uninitialized helper + * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the + * assumption is that if it is, that a helper function + * initialized the dynptr on behalf of the BPF program. + */ + if (base_type(reg->type) == PTR_TO_DYNPTR) + return 0; + if (arg_type & MEM_UNINIT) { + if (!is_dynptr_reg_valid_uninit(env, reg)) { + verbose(env, "Dynptr has to be an uninitialized dynptr\n"); + return -EINVAL; + } + + /* We only support one dynptr being uninitialized at the moment, + * which is sufficient for the helper functions we have right now. + */ + if (meta->uninit_dynptr_regno) { + verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); + return -EFAULT; + } + + meta->uninit_dynptr_regno = regno; + } else { + if (!is_dynptr_reg_valid_init(env, reg)) { + verbose(env, + "Expected an initialized dynptr as arg #%d\n", + regno); + return -EINVAL; + } + + if (!is_dynptr_type_expected(env, reg, arg_type)) { + const char *err_extra = ""; + + switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { + case DYNPTR_TYPE_LOCAL: + err_extra = "local"; + break; + case DYNPTR_TYPE_RINGBUF: + err_extra = "ringbuf"; + break; + default: + err_extra = ""; + break; + } + verbose(env, + "Expected a dynptr of type %s as arg #%d\n", + err_extra, regno); + return -EINVAL; + } + } + return 0; +} + static bool arg_type_is_mem_size(enum bpf_arg_type type) { return type == ARG_CONST_SIZE || @@ -6390,52 +6447,8 @@ skip_type_check: err = check_mem_size_reg(env, reg, regno, true, meta); break; case ARG_PTR_TO_DYNPTR: - /* We only need to check for initialized / uninitialized helper - * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the - * assumption is that if it is, that a helper function - * initialized the dynptr on behalf of the BPF program. - */ - if (base_type(reg->type) == PTR_TO_DYNPTR) - break; - if (arg_type & MEM_UNINIT) { - if (!is_dynptr_reg_valid_uninit(env, reg)) { - verbose(env, "Dynptr has to be an uninitialized dynptr\n"); - return -EINVAL; - } - - /* We only support one dynptr being uninitialized at the moment, - * which is sufficient for the helper functions we have right now. - */ - if (meta->uninit_dynptr_regno) { - verbose(env, "verifier internal error: multiple uninitialized dynptr args\n"); - return -EFAULT; - } - - meta->uninit_dynptr_regno = regno; - } else if (!is_dynptr_reg_valid_init(env, reg)) { - verbose(env, - "Expected an initialized dynptr as arg #%d\n", - arg + 1); - return -EINVAL; - } else if (!is_dynptr_type_expected(env, reg, arg_type)) { - const char *err_extra = ""; - - switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { - case DYNPTR_TYPE_LOCAL: - err_extra = "local"; - break; - case DYNPTR_TYPE_RINGBUF: - err_extra = "ringbuf"; - break; - default: - err_extra = ""; - break; - } - verbose(env, - "Expected a dynptr of type %s as arg #%d\n", - err_extra, arg + 1); - return -EINVAL; - } + if (process_dynptr_func(env, regno, arg_type, meta)) + return -EACCES; break; case ARG_CONST_ALLOC_SIZE_OR_ZERO: if (!tnum_is_const(reg->var_off)) { @@ -8829,22 +8842,15 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return ret; break; case KF_ARG_PTR_TO_DYNPTR: - if (reg->type != PTR_TO_STACK) { - verbose(env, "arg#%d expected pointer to stack\n", i); - return -EINVAL; - } - - if (!is_dynptr_reg_valid_init(env, reg)) { - verbose(env, "arg#%d pointer type %s %s must be valid and initialized\n", - i, btf_type_str(ref_t), ref_tname); + if (reg->type != PTR_TO_STACK && + reg->type != PTR_TO_DYNPTR) { + verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); return -EINVAL; } - if (!is_dynptr_type_expected(env, reg, ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL)) { - verbose(env, "arg#%d pointer type %s %s points to unsupported dynamic pointer type\n", - i, btf_type_str(ref_t), ref_tname); - return -EINVAL; - } + ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR, NULL); + if (ret < 0) + return ret; break; case KF_ARG_PTR_TO_LIST_HEAD: if (reg->type != PTR_TO_MAP_VALUE && diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c index 55d641c1f126..a9229260a6ce 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c @@ -18,11 +18,8 @@ static struct { const char *expected_verifier_err_msg; int expected_runtime_err; } kfunc_dynptr_tests[] = { - {"dynptr_type_not_supp", - "arg#0 pointer type STRUCT bpf_dynptr_kern points to unsupported dynamic pointer type", 0}, - {"not_valid_dynptr", - "arg#0 pointer type STRUCT bpf_dynptr_kern must be valid and initialized", 0}, - {"not_ptr_to_stack", "arg#0 expected pointer to stack", 0}, + {"not_valid_dynptr", "Expected an initialized dynptr as arg #1", 0}, + {"not_ptr_to_stack", "arg#0 expected pointer to stack or dynptr_ptr", 0}, {"dynptr_data_null", NULL, -EBADMSG}, }; diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index ce39d096bba3..f4a8250329b2 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -32,18 +32,6 @@ int err, pid; char _license[] SEC("license") = "GPL"; -SEC("?lsm.s/bpf") -int BPF_PROG(dynptr_type_not_supp, int cmd, union bpf_attr *attr, - unsigned int size) -{ - char write_data[64] = "hello there, world!!"; - struct bpf_dynptr ptr; - - bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(write_data), 0, &ptr); - - return bpf_verify_pkcs7_signature(&ptr, &ptr, NULL); -} - SEC("?lsm.s/bpf") int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) { -- cgit v1.2.3 From 270605317366e4535d8d9fc3d9da1ad0fb3c9d45 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 8 Dec 2022 02:11:37 +0530 Subject: bpf: Rework process_dynptr_func Recently, user ringbuf support introduced a PTR_TO_DYNPTR register type for use in callback state, because in case of user ringbuf helpers, there is no dynptr on the stack that is passed into the callback. To reflect such a state, a special register type was created. However, some checks have been bypassed incorrectly during the addition of this feature. First, for arg_type with MEM_UNINIT flag which initialize a dynptr, they must be rejected for such register type. Secondly, in the future, there are plans to add dynptr helpers that operate on the dynptr itself and may change its offset and other properties. In all of these cases, PTR_TO_DYNPTR shouldn't be allowed to be passed to such helpers, however the current code simply returns 0. The rejection for helpers that release the dynptr is already handled. For fixing this, we take a step back and rework existing code in a way that will allow fitting in all classes of helpers and have a coherent model for dealing with the variety of use cases in which dynptr is used. First, for ARG_PTR_TO_DYNPTR, it can either be set alone or together with a DYNPTR_TYPE_* constant that denotes the only type it accepts. Next, helpers which initialize a dynptr use MEM_UNINIT to indicate this fact. To make the distinction clear, use MEM_RDONLY flag to indicate that the helper only operates on the memory pointed to by the dynptr, not the dynptr itself. In C parlance, it would be equivalent to taking the dynptr as a point to const argument. When either of these flags are not present, the helper is allowed to mutate both the dynptr itself and also the memory it points to. Currently, the read only status of the memory is not tracked in the dynptr, but it would be trivial to add this support inside dynptr state of the register. With these changes and renaming PTR_TO_DYNPTR to CONST_PTR_TO_DYNPTR to better reflect its usage, it can no longer be passed to helpers that initialize a dynptr, i.e. bpf_dynptr_from_mem, bpf_ringbuf_reserve_dynptr. A note to reviewers is that in code that does mark_stack_slots_dynptr, and unmark_stack_slots_dynptr, we implicitly rely on the fact that PTR_TO_STACK reg is the only case that can reach that code path, as one cannot pass CONST_PTR_TO_DYNPTR to helpers that don't set MEM_RDONLY. In both cases such helpers won't be setting that flag. The next patch will add a couple of selftest cases to make sure this doesn't break. Fixes: 205715673844 ("bpf: Add bpf_user_ringbuf_drain() helper") Acked-by: Joanne Koong Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221207204141.308952-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 +- include/uapi/linux/bpf.h | 8 +- kernel/bpf/helpers.c | 18 +- kernel/bpf/verifier.c | 227 +++++++++++++++------ scripts/bpf_doc.py | 1 + tools/include/uapi/linux/bpf.h | 8 +- .../selftests/bpf/prog_tests/user_ringbuf.c | 4 +- 7 files changed, 191 insertions(+), 79 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4920ac252754..3de24cfb7a3d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -775,7 +775,7 @@ enum bpf_reg_type { PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_DYNPTR, /* reg points to a dynptr */ + CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ @@ -2828,7 +2828,7 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr); +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f89de51a45db..464ca3f01fe7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5293,7 +5293,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5303,7 +5303,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5313,7 +5313,7 @@ union bpf_attr { * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr or if *flags* is not 0. * - * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) * Description * Get a pointer to the underlying dynptr data. * @@ -5414,7 +5414,7 @@ union bpf_attr { * Drain samples from the specified user ring buffer, and invoke * the provided callback for each such sample: * - * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx); + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); * * If **callback_fn** returns 0, the helper will continue to try * and drain the next sample, up to a maximum of diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6ed5875b97a3..fa1093d4ad6b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1404,7 +1404,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { #define DYNPTR_SIZE_MASK 0xFFFFFF #define DYNPTR_RDONLY_BIT BIT(31) -static bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) +static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_RDONLY_BIT; } @@ -1414,7 +1414,7 @@ static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_typ ptr->size |= type << DYNPTR_TYPE_SHIFT; } -u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr) +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_SIZE_MASK; } @@ -1438,7 +1438,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) memset(ptr, 0, sizeof(*ptr)); } -static int bpf_dynptr_check_off_len(struct bpf_dynptr_kern *ptr, u32 offset, u32 len) +static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) { u32 size = bpf_dynptr_get_size(ptr); @@ -1483,7 +1483,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, u32, offset, u64, flags) { int err; @@ -1506,12 +1506,12 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_PTR_TO_DYNPTR, + .arg3_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; -BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, +BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len, u64, flags) { int err; @@ -1532,14 +1532,14 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = { .func = bpf_dynptr_write, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_DYNPTR, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) { int err; @@ -1560,7 +1560,7 @@ static const struct bpf_func_proto bpf_dynptr_data_proto = { .func = bpf_dynptr_data, .gpl_only = false, .ret_type = RET_PTR_TO_DYNPTR_MEM_OR_NULL, - .arg1_type = ARG_PTR_TO_DYNPTR, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb742ac75844..a880776bd999 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -592,7 +592,7 @@ static const char *reg_type_str(struct bpf_verifier_env *env, [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", - [PTR_TO_DYNPTR] = "dynptr_ptr", + [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { @@ -725,6 +725,28 @@ static bool dynptr_type_refcounted(enum bpf_dynptr_type type) return type == BPF_DYNPTR_TYPE_RINGBUF; } +static void __mark_dynptr_reg(struct bpf_reg_state *reg, + enum bpf_dynptr_type type, + bool first_slot); + +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); + +static void mark_dynptr_stack_regs(struct bpf_reg_state *sreg1, + struct bpf_reg_state *sreg2, + enum bpf_dynptr_type type) +{ + __mark_dynptr_reg(sreg1, type, true); + __mark_dynptr_reg(sreg2, type, false); +} + +static void mark_dynptr_cb_reg(struct bpf_reg_state *reg, + enum bpf_dynptr_type type) +{ + __mark_dynptr_reg(reg, type, true); +} + + static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx) { @@ -746,9 +768,8 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; - state->stack[spi].spilled_ptr.dynptr.first_slot = true; - state->stack[spi].spilled_ptr.dynptr.type = type; - state->stack[spi - 1].spilled_ptr.dynptr.type = type; + mark_dynptr_stack_regs(&state->stack[spi].spilled_ptr, + &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ @@ -756,8 +777,8 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (id < 0) return id; - state->stack[spi].spilled_ptr.id = id; - state->stack[spi - 1].spilled_ptr.id = id; + state->stack[spi].spilled_ptr.ref_obj_id = id; + state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } return 0; @@ -779,25 +800,23 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re } /* Invalidate any slices associated with this dynptr */ - if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { - release_reference(env, state->stack[spi].spilled_ptr.id); - state->stack[spi].spilled_ptr.id = 0; - state->stack[spi - 1].spilled_ptr.id = 0; - } - - state->stack[spi].spilled_ptr.dynptr.first_slot = false; - state->stack[spi].spilled_ptr.dynptr.type = 0; - state->stack[spi - 1].spilled_ptr.dynptr.type = 0; + if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) + WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id)); + __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); + __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); - int i; + int spi, i; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return false; + spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) return true; @@ -813,9 +832,14 @@ static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_ static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; int i; + /* This already represents first slot of initialized bpf_dynptr */ + if (reg->type == CONST_PTR_TO_DYNPTR) + return true; + + spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || !state->stack[spi].spilled_ptr.dynptr.first_slot) return false; @@ -834,15 +858,19 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type dynptr_type; - int spi = get_spi(reg->off); + int spi; /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ if (arg_type == ARG_PTR_TO_DYNPTR) return true; dynptr_type = arg_to_dynptr_type(arg_type); - - return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; + if (reg->type == CONST_PTR_TO_DYNPTR) { + return reg->dynptr.type == dynptr_type; + } else { + spi = get_spi(reg->off); + return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; + } } /* The reg state of a pointer or a bounded scalar was saved when @@ -1354,9 +1382,6 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg); - /* This helper doesn't clear reg->id */ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { @@ -1419,6 +1444,19 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, __mark_reg_known_zero(regs + regno); } +static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, + bool first_slot) +{ + /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for + * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply + * set it unconditionally as it is ignored for STACK_DYNPTR anyway. + */ + __mark_reg_known_zero(reg); + reg->type = CONST_PTR_TO_DYNPTR; + reg->dynptr.type = type; + reg->dynptr.first_slot = first_slot; +} + static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { if (base_type(reg->type) == PTR_TO_MAP_VALUE) { @@ -5857,19 +5895,58 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, return 0; } +/* There are two register types representing a bpf_dynptr, one is PTR_TO_STACK + * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR. + * + * In both cases we deal with the first 8 bytes, but need to mark the next 8 + * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of + * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object. + * + * Mutability of bpf_dynptr is at two levels, one is at the level of struct + * bpf_dynptr itself, i.e. whether the helper is receiving a pointer to struct + * bpf_dynptr or pointer to const struct bpf_dynptr. In the former case, it can + * mutate the view of the dynptr and also possibly destroy it. In the latter + * case, it cannot mutate the bpf_dynptr itself but it can still mutate the + * memory that dynptr points to. + * + * The verifier will keep track both levels of mutation (bpf_dynptr's in + * reg->type and the memory's in reg->dynptr.type), but there is no support for + * readonly dynptr view yet, hence only the first case is tracked and checked. + * + * This is consistent with how C applies the const modifier to a struct object, + * where the pointer itself inside bpf_dynptr becomes const but not what it + * points to. + * + * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument + * type, and declare it as 'const struct bpf_dynptr *' in their prototype. + */ int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, - struct bpf_call_arg_meta *meta) + enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - /* We only need to check for initialized / uninitialized helper - * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the - * assumption is that if it is, that a helper function - * initialized the dynptr on behalf of the BPF program. + /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an + * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): + */ + if ((arg_type & (MEM_UNINIT | MEM_RDONLY)) == (MEM_UNINIT | MEM_RDONLY)) { + verbose(env, "verifier internal error: misconfigured dynptr helper type flags\n"); + return -EFAULT; + } + /* MEM_UNINIT - Points to memory that is an appropriate candidate for + * constructing a mutable bpf_dynptr object. + * + * Currently, this is only possible with PTR_TO_STACK + * pointing to a region of at least 16 bytes which doesn't + * contain an existing bpf_dynptr. + * + * MEM_RDONLY - Points to a initialized bpf_dynptr that will not be + * mutated or destroyed. However, the memory it points to + * may be mutated. + * + * None - Points to a initialized dynptr that can be mutated and + * destroyed, including mutation of the memory it points + * to. */ - if (base_type(reg->type) == PTR_TO_DYNPTR) - return 0; if (arg_type & MEM_UNINIT) { if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); @@ -5885,7 +5962,13 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, } meta->uninit_dynptr_regno = regno; - } else { + } else /* MEM_RDONLY and None case from above */ { + /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ + if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { + verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); + return -EINVAL; + } + if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", @@ -5893,7 +5976,8 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, return -EINVAL; } - if (!is_dynptr_type_expected(env, reg, arg_type)) { + /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ + if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { const char *err_extra = ""; switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { @@ -6056,7 +6140,7 @@ static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } } static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, - PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL, + CONST_PTR_TO_DYNPTR, } }; @@ -6241,12 +6325,16 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, return __check_ptr_off_reg(env, reg, regno, fixed_off_ok); } -static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static u32 dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->ref_obj_id; - return state->stack[spi].spilled_ptr.id; + spi = get_spi(reg->off); + return state->stack[spi].spilled_ptr.ref_obj_id; } static int check_func_arg(struct bpf_verifier_env *env, u32 arg, @@ -6311,11 +6399,22 @@ skip_type_check: if (arg_type_is_release(arg_type)) { if (arg_type_is_dynptr(arg_type)) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.id) { - verbose(env, "arg %d is an unacquired reference\n", regno); + /* Only dynptr created on stack can be released, thus + * the get_spi and stack state checks for spilled_ptr + * should only be done before process_dynptr_func for + * PTR_TO_STACK. + */ + if (reg->type == PTR_TO_STACK) { + spi = get_spi(reg->off); + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || + !state->stack[spi].spilled_ptr.ref_obj_id) { + verbose(env, "arg %d is an unacquired reference\n", regno); + return -EINVAL; + } + } else { + verbose(env, "cannot release unowned const bpf_dynptr\n"); return -EINVAL; } } else if (!reg->ref_obj_id && !register_is_null(reg)) { @@ -7289,11 +7388,10 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, { /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void * callback_ctx, u64 flags); - * callback_fn(struct bpf_dynptr_t* dynptr, void *callback_ctx); + * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); - callee->regs[BPF_REG_1].type = PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL; - __mark_reg_known_zero(&callee->regs[BPF_REG_1]); + mark_dynptr_cb_reg(&callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ @@ -7687,7 +7785,15 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); + /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot + * be reinitialized by any dynptr helper. Hence, mark_stack_slots_dynptr + * is safe to do directly. + */ if (meta.uninit_dynptr_regno) { + if (regs[meta.uninit_dynptr_regno].type == CONST_PTR_TO_DYNPTR) { + verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be initialized\n"); + return -EFAULT; + } /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, @@ -7705,15 +7811,24 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (meta.release_regno) { err = -EINVAL; - if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) + /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot + * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr + * is safe to do directly. + */ + if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) { + if (regs[meta.release_regno].type == CONST_PTR_TO_DYNPTR) { + verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be released\n"); + return -EFAULT; + } err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); - else if (meta.ref_obj_id) + } else if (meta.ref_obj_id) { err = release_reference(env, meta.ref_obj_id); - /* meta.ref_obj_id can only be 0 if register that is meant to be - * released is NULL, which must be > R0. - */ - else if (register_is_null(®s[meta.release_regno])) + } else if (register_is_null(®s[meta.release_regno])) { + /* meta.ref_obj_id can only be 0 if register that is meant to be + * released is NULL, which must be > R0. + */ err = 0; + } if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -7787,11 +7902,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EFAULT; } - if (base_type(reg->type) != PTR_TO_DYNPTR) - /* Find the id of the dynptr we're - * tracking the reference of - */ - meta.ref_obj_id = stack_slot_get_id(env, reg); + meta.ref_obj_id = dynptr_ref_obj_id(env, reg); break; } } @@ -8848,12 +8959,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_DYNPTR: if (reg->type != PTR_TO_STACK && - reg->type != PTR_TO_DYNPTR) { + reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); return -EINVAL; } - ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR, NULL); + ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR | MEM_RDONLY, NULL); if (ret < 0) return ret; break; diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index fdb0aff8cb5a..e8d90829f23e 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -752,6 +752,7 @@ class PrinterHelpers(Printer): 'struct bpf_timer', 'struct mptcp_sock', 'struct bpf_dynptr', + 'const struct bpf_dynptr', 'struct iphdr', 'struct ipv6hdr', } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f89de51a45db..464ca3f01fe7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5293,7 +5293,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5303,7 +5303,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5313,7 +5313,7 @@ union bpf_attr { * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr or if *flags* is not 0. * - * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) * Description * Get a pointer to the underlying dynptr data. * @@ -5414,7 +5414,7 @@ union bpf_attr { * Drain samples from the specified user ring buffer, and invoke * the provided callback for each such sample: * - * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx); + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); * * If **callback_fn** returns 0, the helper will continue to try * and drain the next sample, up to a maximum of diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c index 02b18d018b36..aefa0a474e58 100644 --- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c @@ -673,8 +673,8 @@ static struct { {"user_ringbuf_callback_write_forbidden", "invalid mem access 'dynptr_ptr'"}, {"user_ringbuf_callback_null_context_write", "invalid mem access 'scalar'"}, {"user_ringbuf_callback_null_context_read", "invalid mem access 'scalar'"}, - {"user_ringbuf_callback_discard_dynptr", "arg 1 is an unacquired reference"}, - {"user_ringbuf_callback_submit_dynptr", "arg 1 is an unacquired reference"}, + {"user_ringbuf_callback_discard_dynptr", "cannot release unowned const bpf_dynptr"}, + {"user_ringbuf_callback_submit_dynptr", "cannot release unowned const bpf_dynptr"}, {"user_ringbuf_callback_invalid_return", "At callback return the register R0 has value"}, }; -- cgit v1.2.3 From b534dc46c8ae0165b1b2509be24dbea4fa9c4011 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 7 Dec 2022 09:37:01 -0500 Subject: net_tstamp: add SOF_TIMESTAMPING_OPT_ID_TCP Add an option to initialize SOF_TIMESTAMPING_OPT_ID for TCP from write_seq sockets instead of snd_una. This should have been the behavior from the start. Because processes may now exist that rely on the established behavior, do not change behavior of the existing option, but add the right behavior with a new flag. It is encouraged to always set SOF_TIMESTAMPING_OPT_ID_TCP on stream sockets along with the existing SOF_TIMESTAMPING_OPT_ID. Intuitively the contract is that the counter is zero after the setsockopt, so that the next write N results in a notification for the last byte N - 1. On idle sockets snd_una == write_seq and this holds for both. But on sockets with data in transmission, snd_una records the unacked offset in the stream. This depends on the ACK response from the peer. A process cannot learn this in a race free manner (ioctl SIOCOUTQ is one racy approach). write_seq records the offset at the last byte written by the process. This is a better starting point. It matches the intuitive contract in all circumstances, unaffected by external behavior. The new timestamp flag necessitates increasing sk_tsflags to 32 bits. Move the field in struct sock to avoid growing the socket (for some common CONFIG variants). The UAPI interface so_timestamping.flags is already int, so 32 bits wide. Reported-by: Sotirios Delimanolis Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20221207143701.29861-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/networking/timestamping.rst | 32 ++++++++++++++++++++++++++++++- include/net/sock.h | 6 +++--- include/uapi/linux/net_tstamp.h | 3 ++- net/core/sock.c | 9 ++++++++- net/ethtool/common.c | 1 + 5 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index be4eb1242057..f17c01834a12 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -179,7 +179,8 @@ SOF_TIMESTAMPING_OPT_ID: identifier and returns that along with the timestamp. The identifier is derived from a per-socket u32 counter (that wraps). For datagram sockets, the counter increments with each sent packet. For stream - sockets, it increments with every byte. + sockets, it increments with every byte. For stream sockets, also set + SOF_TIMESTAMPING_OPT_ID_TCP, see the section below. The counter starts at zero. It is initialized the first time that the socket option is enabled. It is reset each time the option is @@ -192,6 +193,35 @@ SOF_TIMESTAMPING_OPT_ID: among all possibly concurrently outstanding timestamp requests for that socket. +SOF_TIMESTAMPING_OPT_ID_TCP: + Pass this modifier along with SOF_TIMESTAMPING_OPT_ID for new TCP + timestamping applications. SOF_TIMESTAMPING_OPT_ID defines how the + counter increments for stream sockets, but its starting point is + not entirely trivial. This option fixes that. + + For stream sockets, if SOF_TIMESTAMPING_OPT_ID is set, this should + always be set too. On datagram sockets the option has no effect. + + A reasonable expectation is that the counter is reset to zero with + the system call, so that a subsequent write() of N bytes generates + a timestamp with counter N-1. SOF_TIMESTAMPING_OPT_ID_TCP + implements this behavior under all conditions. + + SOF_TIMESTAMPING_OPT_ID without modifier often reports the same, + especially when the socket option is set when no data is in + transmission. If data is being transmitted, it may be off by the + length of the output queue (SIOCOUTQ). + + The difference is due to being based on snd_una versus write_seq. + snd_una is the offset in the stream acknowledged by the peer. This + depends on factors outside of process control, such as network RTT. + write_seq is the last byte written by the process. This offset is + not affected by external inputs. + + The difference is subtle and unlikely to be noticed when configured + at initial socket creation, when no data is queued or sent. But + SOF_TIMESTAMPING_OPT_ID_TCP behavior is more robust regardless of + when the socket option is set. SOF_TIMESTAMPING_OPT_CMSG: Support recv() cmsg for all timestamped packets. Control messages diff --git a/include/net/sock.h b/include/net/sock.h index 6d207e7c4ad0..ecea3dcc2217 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -503,10 +503,10 @@ struct sock { #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif - u16 sk_tsflags; - u8 sk_shutdown; atomic_t sk_tskey; atomic_t sk_zckey; + u32 sk_tsflags; + u8 sk_shutdown; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, @@ -1899,7 +1899,7 @@ static inline void sock_replace_proto(struct sock *sk, struct proto *proto) struct sockcm_cookie { u64 transmit_time; u32 mark; - u16 tsflags; + u32 tsflags; }; static inline void sockcm_init(struct sockcm_cookie *sockc, diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 55501e5e7ac8..a2c66b3d7f0f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -31,8 +31,9 @@ enum { SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13), SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14), SOF_TIMESTAMPING_BIND_PHC = (1 << 15), + SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID_TCP, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; diff --git a/net/core/sock.c b/net/core/sock.c index 4571914a4aa8..b0ab841e0aed 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -901,13 +901,20 @@ int sock_set_timestamping(struct sock *sk, int optname, if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; + if (val & SOF_TIMESTAMPING_OPT_ID_TCP && + !(val & SOF_TIMESTAMPING_OPT_ID)) + return -EINVAL; + if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; - atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); + if (val & SOF_TIMESTAMPING_OPT_ID_TCP) + atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq); + else + atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 21cfe8557205..6f399afc2ff2 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -417,6 +417,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", + [const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)] = "option-id-tcp", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); -- cgit v1.2.3 From 2a7d228f1ae78b6eabef5f18bd1a8d2280555628 Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 6 Dec 2022 10:55:10 -0300 Subject: net/sched: move struct action_ops definition out of ifdef The type definition should be visible even in configurations not using CONFIG_NET_CLS_ACT. Signed-off-by: Pedro Tammela Reviewed-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Signed-off-by: David S. Miller --- include/net/act_api.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/act_api.h b/include/net/act_api.h index c94ea1a306e0..2a6f443f0ef6 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -101,11 +101,6 @@ static inline enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) return hw_stats; } -#ifdef CONFIG_NET_CLS_ACT - -#define ACT_P_CREATED 1 -#define ACT_P_DELETED 1 - typedef void (*tc_action_priv_destructor)(void *priv); struct tc_action_ops { @@ -140,6 +135,11 @@ struct tc_action_ops { struct netlink_ext_ack *extack); }; +#ifdef CONFIG_NET_CLS_ACT + +#define ACT_P_CREATED 1 +#define ACT_P_DELETED 1 + struct tc_action_net { struct tcf_idrinfo *idrinfo; const struct tc_action_ops *ops; -- cgit v1.2.3 From 7f0e810220e2d985338ecdd907c1598404db251d Mon Sep 17 00:00:00 2001 From: Pedro Tammela Date: Tue, 6 Dec 2022 10:55:11 -0300 Subject: net/sched: add retpoline wrapper for tc On kernels using retpoline as a spectrev2 mitigation, optimize actions and filters that are compiled as built-ins into a direct call. On subsequent patches we expose the classifiers and actions functions and wire up the wrapper into tc. Signed-off-by: Pedro Tammela Reviewed-by: Jamal Hadi Salim Reviewed-by: Victor Nogueira Signed-off-by: David S. Miller --- include/net/tc_wrapper.h | 251 +++++++++++++++++++++++++++++++++++++++++++++++ net/sched/sch_api.c | 5 + 2 files changed, 256 insertions(+) create mode 100644 include/net/tc_wrapper.h (limited to 'include') diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h new file mode 100644 index 000000000000..ceed2fc089ff --- /dev/null +++ b/include/net/tc_wrapper.h @@ -0,0 +1,251 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_TC_WRAPPER_H +#define __NET_TC_WRAPPER_H + +#include + +#if IS_ENABLED(CONFIG_RETPOLINE) + +#include +#include +#include + +#define TC_INDIRECT_SCOPE + +extern struct static_key_false tc_skip_wrapper; + +/* TC Actions */ +#ifdef CONFIG_NET_CLS_ACT + +#define TC_INDIRECT_ACTION_DECLARE(fname) \ + INDIRECT_CALLABLE_DECLARE(int fname(struct sk_buff *skb, \ + const struct tc_action *a, \ + struct tcf_result *res)) + +TC_INDIRECT_ACTION_DECLARE(tcf_bpf_act); +TC_INDIRECT_ACTION_DECLARE(tcf_connmark_act); +TC_INDIRECT_ACTION_DECLARE(tcf_csum_act); +TC_INDIRECT_ACTION_DECLARE(tcf_ct_act); +TC_INDIRECT_ACTION_DECLARE(tcf_ctinfo_act); +TC_INDIRECT_ACTION_DECLARE(tcf_gact_act); +TC_INDIRECT_ACTION_DECLARE(tcf_gate_act); +TC_INDIRECT_ACTION_DECLARE(tcf_ife_act); +TC_INDIRECT_ACTION_DECLARE(tcf_ipt_act); +TC_INDIRECT_ACTION_DECLARE(tcf_mirred_act); +TC_INDIRECT_ACTION_DECLARE(tcf_mpls_act); +TC_INDIRECT_ACTION_DECLARE(tcf_nat_act); +TC_INDIRECT_ACTION_DECLARE(tcf_pedit_act); +TC_INDIRECT_ACTION_DECLARE(tcf_police_act); +TC_INDIRECT_ACTION_DECLARE(tcf_sample_act); +TC_INDIRECT_ACTION_DECLARE(tcf_simp_act); +TC_INDIRECT_ACTION_DECLARE(tcf_skbedit_act); +TC_INDIRECT_ACTION_DECLARE(tcf_skbmod_act); +TC_INDIRECT_ACTION_DECLARE(tcf_vlan_act); +TC_INDIRECT_ACTION_DECLARE(tunnel_key_act); + +static inline int tc_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + if (static_branch_likely(&tc_skip_wrapper)) + goto skip; + +#if IS_BUILTIN(CONFIG_NET_ACT_GACT) + if (a->ops->act == tcf_gact_act) + return tcf_gact_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_MIRRED) + if (a->ops->act == tcf_mirred_act) + return tcf_mirred_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_PEDIT) + if (a->ops->act == tcf_pedit_act) + return tcf_pedit_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_SKBEDIT) + if (a->ops->act == tcf_skbedit_act) + return tcf_skbedit_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_SKBMOD) + if (a->ops->act == tcf_skbmod_act) + return tcf_skbmod_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_POLICE) + if (a->ops->act == tcf_police_act) + return tcf_police_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_BPF) + if (a->ops->act == tcf_bpf_act) + return tcf_bpf_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_CONNMARK) + if (a->ops->act == tcf_connmark_act) + return tcf_connmark_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_CSUM) + if (a->ops->act == tcf_csum_act) + return tcf_csum_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_CT) + if (a->ops->act == tcf_ct_act) + return tcf_ct_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_CTINFO) + if (a->ops->act == tcf_ctinfo_act) + return tcf_ctinfo_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_GATE) + if (a->ops->act == tcf_gate_act) + return tcf_gate_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_MPLS) + if (a->ops->act == tcf_mpls_act) + return tcf_mpls_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_NAT) + if (a->ops->act == tcf_nat_act) + return tcf_nat_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_TUNNEL_KEY) + if (a->ops->act == tunnel_key_act) + return tunnel_key_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_VLAN) + if (a->ops->act == tcf_vlan_act) + return tcf_vlan_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_IFE) + if (a->ops->act == tcf_ife_act) + return tcf_ife_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_IPT) + if (a->ops->act == tcf_ipt_act) + return tcf_ipt_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_SIMP) + if (a->ops->act == tcf_simp_act) + return tcf_simp_act(skb, a, res); +#endif +#if IS_BUILTIN(CONFIG_NET_ACT_SAMPLE) + if (a->ops->act == tcf_sample_act) + return tcf_sample_act(skb, a, res); +#endif + +skip: + return a->ops->act(skb, a, res); +} + +#endif /* CONFIG_NET_CLS_ACT */ + +/* TC Filters */ +#ifdef CONFIG_NET_CLS + +#define TC_INDIRECT_FILTER_DECLARE(fname) \ + INDIRECT_CALLABLE_DECLARE(int fname(struct sk_buff *skb, \ + const struct tcf_proto *tp, \ + struct tcf_result *res)) + +TC_INDIRECT_FILTER_DECLARE(basic_classify); +TC_INDIRECT_FILTER_DECLARE(cls_bpf_classify); +TC_INDIRECT_FILTER_DECLARE(cls_cgroup_classify); +TC_INDIRECT_FILTER_DECLARE(fl_classify); +TC_INDIRECT_FILTER_DECLARE(flow_classify); +TC_INDIRECT_FILTER_DECLARE(fw_classify); +TC_INDIRECT_FILTER_DECLARE(mall_classify); +TC_INDIRECT_FILTER_DECLARE(route4_classify); +TC_INDIRECT_FILTER_DECLARE(rsvp_classify); +TC_INDIRECT_FILTER_DECLARE(rsvp6_classify); +TC_INDIRECT_FILTER_DECLARE(tcindex_classify); +TC_INDIRECT_FILTER_DECLARE(u32_classify); + +static inline int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) +{ + if (static_branch_likely(&tc_skip_wrapper)) + goto skip; + +#if IS_BUILTIN(CONFIG_NET_CLS_BPF) + if (tp->classify == cls_bpf_classify) + return cls_bpf_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_U32) + if (tp->classify == u32_classify) + return u32_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_FLOWER) + if (tp->classify == fl_classify) + return fl_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_FW) + if (tp->classify == fw_classify) + return fw_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_MATCHALL) + if (tp->classify == mall_classify) + return mall_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_BASIC) + if (tp->classify == basic_classify) + return basic_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_CGROUP) + if (tp->classify == cls_cgroup_classify) + return cls_cgroup_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_FLOW) + if (tp->classify == flow_classify) + return flow_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_ROUTE4) + if (tp->classify == route4_classify) + return route4_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_RSVP) + if (tp->classify == rsvp_classify) + return rsvp_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_RSVP6) + if (tp->classify == rsvp6_classify) + return rsvp6_classify(skb, tp, res); +#endif +#if IS_BUILTIN(CONFIG_NET_CLS_TCINDEX) + if (tp->classify == tcindex_classify) + return tcindex_classify(skb, tp, res); +#endif + +skip: + return tp->classify(skb, tp, res); +} + +static inline void tc_wrapper_init(void) +{ +#ifdef CONFIG_X86 + if (!cpu_feature_enabled(X86_FEATURE_RETPOLINE)) + static_branch_enable(&tc_skip_wrapper); +#endif +} + +#endif /* CONFIG_NET_CLS */ + +#else + +#define TC_INDIRECT_SCOPE static + +static inline int tc_act(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) +{ + return a->ops->act(skb, a, res); +} + +static inline int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res) +{ + return tp->classify(skb, tp, res); +} + +static inline void tc_wrapper_init(void) +{ +} + +#endif + +#endif /* __NET_TC_WRAPPER_H */ diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 4a27dfb1ba0f..2317db02c764 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -31,6 +31,7 @@ #include #include #include +#include #include @@ -2273,6 +2274,8 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; +DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); + static int __init pktsched_init(void) { int err; @@ -2300,6 +2303,8 @@ static int __init pktsched_init(void) rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, 0); + tc_wrapper_init(); + return 0; } -- cgit v1.2.3 From e47877c7aa821c413b45e05f804819579bdfa1a3 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 6 Dec 2022 11:36:32 -1000 Subject: rhashtable: Allow rhashtable to be used from irq-safe contexts rhashtable currently only does bh-safe synchronization making it impossible to use from irq-safe contexts. Switch it to use irq-safe synchronization to remove the restriction. v2: Update the lock functions to return the ulong flags value and unlock functions to take the value directly instead of passing around the pointer. Suggested by Linus. Signed-off-by: Tejun Heo Reviewed-by: David Vernet Acked-by: Josh Don Acked-by: Hao Luo Acked-by: Barret Rhoden Cc: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 61 +++++++++++++++++++++++++++------------------- lib/rhashtable.c | 16 +++++++----- 2 files changed, 46 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 68dab3e08aad..5b5357c0bd8c 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -323,29 +323,36 @@ static inline struct rhash_lock_head __rcu **rht_bucket_insert( * When we write to a bucket without unlocking, we use rht_assign_locked(). */ -static inline void rht_lock(struct bucket_table *tbl, - struct rhash_lock_head __rcu **bkt) +static inline unsigned long rht_lock(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bkt) { - local_bh_disable(); + unsigned long flags; + + local_irq_save(flags); bit_spin_lock(0, (unsigned long *)bkt); lock_map_acquire(&tbl->dep_map); + return flags; } -static inline void rht_lock_nested(struct bucket_table *tbl, - struct rhash_lock_head __rcu **bucket, - unsigned int subclass) +static inline unsigned long rht_lock_nested(struct bucket_table *tbl, + struct rhash_lock_head __rcu **bucket, + unsigned int subclass) { - local_bh_disable(); + unsigned long flags; + + local_irq_save(flags); bit_spin_lock(0, (unsigned long *)bucket); lock_acquire_exclusive(&tbl->dep_map, subclass, 0, NULL, _THIS_IP_); + return flags; } static inline void rht_unlock(struct bucket_table *tbl, - struct rhash_lock_head __rcu **bkt) + struct rhash_lock_head __rcu **bkt, + unsigned long flags) { lock_map_release(&tbl->dep_map); bit_spin_unlock(0, (unsigned long *)bkt); - local_bh_enable(); + local_irq_restore(flags); } static inline struct rhash_head *__rht_ptr( @@ -393,7 +400,8 @@ static inline void rht_assign_locked(struct rhash_lock_head __rcu **bkt, static inline void rht_assign_unlock(struct bucket_table *tbl, struct rhash_lock_head __rcu **bkt, - struct rhash_head *obj) + struct rhash_head *obj, + unsigned long flags) { if (rht_is_a_nulls(obj)) obj = NULL; @@ -401,7 +409,7 @@ static inline void rht_assign_unlock(struct bucket_table *tbl, rcu_assign_pointer(*bkt, (void *)obj); preempt_enable(); __release(bitlock); - local_bh_enable(); + local_irq_restore(flags); } /** @@ -706,6 +714,7 @@ static inline void *__rhashtable_insert_fast( struct rhash_head __rcu **pprev; struct bucket_table *tbl; struct rhash_head *head; + unsigned long flags; unsigned int hash; int elasticity; void *data; @@ -720,11 +729,11 @@ static inline void *__rhashtable_insert_fast( if (!bkt) goto out; pprev = NULL; - rht_lock(tbl, bkt); + flags = rht_lock(tbl, bkt); if (unlikely(rcu_access_pointer(tbl->future_tbl))) { slow_path: - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); rcu_read_unlock(); return rhashtable_insert_slow(ht, key, obj); } @@ -756,9 +765,9 @@ slow_path: RCU_INIT_POINTER(list->rhead.next, head); if (pprev) { rcu_assign_pointer(*pprev, obj); - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); } else - rht_assign_unlock(tbl, bkt, obj); + rht_assign_unlock(tbl, bkt, obj, flags); data = NULL; goto out; } @@ -785,7 +794,7 @@ slow_path: } atomic_inc(&ht->nelems); - rht_assign_unlock(tbl, bkt, obj); + rht_assign_unlock(tbl, bkt, obj, flags); if (rht_grow_above_75(ht, tbl)) schedule_work(&ht->run_work); @@ -797,7 +806,7 @@ out: return data; out_unlock: - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); goto out; } @@ -991,6 +1000,7 @@ static inline int __rhashtable_remove_fast_one( struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; + unsigned long flags; unsigned int hash; int err = -ENOENT; @@ -999,7 +1009,7 @@ static inline int __rhashtable_remove_fast_one( if (!bkt) return -ENOENT; pprev = NULL; - rht_lock(tbl, bkt); + flags = rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { struct rhlist_head *list; @@ -1043,14 +1053,14 @@ static inline int __rhashtable_remove_fast_one( if (pprev) { rcu_assign_pointer(*pprev, obj); - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); } else { - rht_assign_unlock(tbl, bkt, obj); + rht_assign_unlock(tbl, bkt, obj, flags); } goto unlocked; } - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); unlocked: if (err > 0) { atomic_dec(&ht->nelems); @@ -1143,6 +1153,7 @@ static inline int __rhashtable_replace_fast( struct rhash_lock_head __rcu **bkt; struct rhash_head __rcu **pprev; struct rhash_head *he; + unsigned long flags; unsigned int hash; int err = -ENOENT; @@ -1158,7 +1169,7 @@ static inline int __rhashtable_replace_fast( return -ENOENT; pprev = NULL; - rht_lock(tbl, bkt); + flags = rht_lock(tbl, bkt); rht_for_each_from(he, rht_ptr(bkt, tbl, hash), tbl, hash) { if (he != obj_old) { @@ -1169,15 +1180,15 @@ static inline int __rhashtable_replace_fast( rcu_assign_pointer(obj_new->next, obj_old->next); if (pprev) { rcu_assign_pointer(*pprev, obj_new); - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); } else { - rht_assign_unlock(tbl, bkt, obj_new); + rht_assign_unlock(tbl, bkt, obj_new, flags); } err = 0; goto unlocked; } - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); unlocked: return err; diff --git a/lib/rhashtable.c b/lib/rhashtable.c index e12bbfb240b8..6ae2ba8e06a2 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -231,6 +231,7 @@ static int rhashtable_rehash_one(struct rhashtable *ht, struct rhash_head *head, *next, *entry; struct rhash_head __rcu **pprev = NULL; unsigned int new_hash; + unsigned long flags; if (new_tbl->nest) goto out; @@ -253,13 +254,14 @@ static int rhashtable_rehash_one(struct rhashtable *ht, new_hash = head_hashfn(ht, new_tbl, entry); - rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], SINGLE_DEPTH_NESTING); + flags = rht_lock_nested(new_tbl, &new_tbl->buckets[new_hash], + SINGLE_DEPTH_NESTING); head = rht_ptr(new_tbl->buckets + new_hash, new_tbl, new_hash); RCU_INIT_POINTER(entry->next, head); - rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry); + rht_assign_unlock(new_tbl, &new_tbl->buckets[new_hash], entry, flags); if (pprev) rcu_assign_pointer(*pprev, next); @@ -276,18 +278,19 @@ static int rhashtable_rehash_chain(struct rhashtable *ht, { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); struct rhash_lock_head __rcu **bkt = rht_bucket_var(old_tbl, old_hash); + unsigned long flags; int err; if (!bkt) return 0; - rht_lock(old_tbl, bkt); + flags = rht_lock(old_tbl, bkt); while (!(err = rhashtable_rehash_one(ht, bkt, old_hash))) ; if (err == -ENOENT) err = 0; - rht_unlock(old_tbl, bkt); + rht_unlock(old_tbl, bkt, flags); return err; } @@ -590,6 +593,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, struct bucket_table *new_tbl; struct bucket_table *tbl; struct rhash_lock_head __rcu **bkt; + unsigned long flags; unsigned int hash; void *data; @@ -607,7 +611,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); data = ERR_PTR(-EAGAIN); } else { - rht_lock(tbl, bkt); + flags = rht_lock(tbl, bkt); data = rhashtable_lookup_one(ht, bkt, tbl, hash, key, obj); new_tbl = rhashtable_insert_one(ht, bkt, tbl, @@ -615,7 +619,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, if (PTR_ERR(new_tbl) != -EEXIST) data = ERR_CAST(new_tbl); - rht_unlock(tbl, bkt); + rht_unlock(tbl, bkt, flags); } } while (!IS_ERR_OR_NULL(new_tbl)); -- cgit v1.2.3 From 1933ea365aa7a48ce26bea2ea09c9f7cc48cc668 Mon Sep 17 00:00:00 2001 From: wangchuanlei Date: Tue, 6 Dec 2022 20:38:57 -0500 Subject: net: openvswitch: Add support to count upcall packets Add support to count upall packets, when kmod of openvswitch upcall to count the number of packets for upcall succeed and failed, which is a better way to see how many packets upcalled on every interfaces. Signed-off-by: wangchuanlei Acked-by: Eelco Chaudron Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 14 +++++++++++ net/openvswitch/datapath.c | 41 ++++++++++++++++++++++++++++++++ net/openvswitch/vport.c | 50 ++++++++++++++++++++++++++++++++++++++++ net/openvswitch/vport.h | 16 +++++++++++++ 4 files changed, 121 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 94066f87e9ee..c5d62ee82567 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -277,11 +277,25 @@ enum ovs_vport_attr { OVS_VPORT_ATTR_PAD, OVS_VPORT_ATTR_IFINDEX, OVS_VPORT_ATTR_NETNSID, + OVS_VPORT_ATTR_UPCALL_STATS, __OVS_VPORT_ATTR_MAX }; #define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1) +/** + * enum ovs_vport_upcall_attr - attributes for %OVS_VPORT_UPCALL* commands + * @OVS_VPORT_UPCALL_SUCCESS: 64-bit upcall success packets. + * @OVS_VPORT_UPCALL_FAIL: 64-bit upcall fail packets. + */ +enum ovs_vport_upcall_attr { + OVS_VPORT_UPCALL_ATTR_SUCCESS, + OVS_VPORT_UPCALL_ATTR_FAIL, + __OVS_VPORT_UPCALL_ATTR_MAX +}; + +#define OVS_VPORT_UPCALL_ATTR_MAX (__OVS_VPORT_UPCALL_ATTR_MAX - 1) + enum { OVS_VXLAN_EXT_UNSPEC, OVS_VXLAN_EXT_GBP, /* Flag or __u32 */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 861dfb8daf4a..932bcf766d63 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -209,6 +209,26 @@ static struct vport *new_vport(const struct vport_parms *parms) return vport; } +static void ovs_vport_update_upcall_stats(struct sk_buff *skb, + const struct dp_upcall_info *upcall_info, + bool upcall_result) +{ + struct vport *p = OVS_CB(skb)->input_vport; + struct vport_upcall_stats_percpu *stats; + + if (upcall_info->cmd != OVS_PACKET_CMD_MISS && + upcall_info->cmd != OVS_PACKET_CMD_ACTION) + return; + + stats = this_cpu_ptr(p->upcall_stats); + u64_stats_update_begin(&stats->syncp); + if (upcall_result) + u64_stats_inc(&stats->n_success); + else + u64_stats_inc(&stats->n_fail); + u64_stats_update_end(&stats->syncp); +} + void ovs_dp_detach_port(struct vport *p) { ASSERT_OVSL(); @@ -216,6 +236,9 @@ void ovs_dp_detach_port(struct vport *p) /* First drop references to device. */ hlist_del_rcu(&p->dp_hash_node); + /* Free percpu memory */ + free_percpu(p->upcall_stats); + /* Then destroy it. */ ovs_vport_del(p); } @@ -305,6 +328,8 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen); else err = queue_gso_packets(dp, skb, key, upcall_info, cutlen); + + ovs_vport_update_upcall_stats(skb, upcall_info, !err); if (err) goto err; @@ -1826,6 +1851,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_portids; } + vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); + if (!vport->upcall_stats) { + err = -ENOMEM; + goto err_destroy_portids; + } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_NEW); BUG_ON(err < 0); @@ -2098,6 +2129,9 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, OVS_VPORT_ATTR_PAD)) goto nla_put_failure; + if (ovs_vport_get_upcall_stats(vport, skb)) + goto nla_put_failure; + if (ovs_vport_get_upcall_portids(vport, skb)) goto nla_put_failure; @@ -2279,6 +2313,12 @@ restart: goto exit_unlock_free; } + vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); + if (!vport->upcall_stats) { + err = -ENOMEM; + goto exit_unlock_free; + } + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW, GFP_KERNEL); @@ -2508,6 +2548,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, + [OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED }, }; static const struct genl_small_ops dp_vport_genl_ops[] = { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 82a74f998966..7e0f5c45b512 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -284,6 +284,56 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) stats->tx_packets = dev_stats->tx_packets; } +/** + * ovs_vport_get_upcall_stats - retrieve upcall stats + * + * @vport: vport from which to retrieve the stats. + * @skb: sk_buff where upcall stats should be appended. + * + * Retrieves upcall stats for the given device. + * + * Must be called with ovs_mutex or rcu_read_lock. + */ +int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) +{ + struct nlattr *nla; + int i; + + __u64 tx_success = 0; + __u64 tx_fail = 0; + + for_each_possible_cpu(i) { + const struct vport_upcall_stats_percpu *stats; + unsigned int start; + + stats = per_cpu_ptr(vport->upcall_stats, i); + do { + start = u64_stats_fetch_begin(&stats->syncp); + tx_success += u64_stats_read(&stats->n_success); + tx_fail += u64_stats_read(&stats->n_fail); + } while (u64_stats_fetch_retry(&stats->syncp, start)); + } + + nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); + if (!nla) + return -EMSGSIZE; + + if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_SUCCESS, tx_success, + OVS_VPORT_ATTR_PAD)) { + nla_nest_cancel(skb, nla); + return -EMSGSIZE; + } + + if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_FAIL, tx_fail, + OVS_VPORT_ATTR_PAD)) { + nla_nest_cancel(skb, nla); + return -EMSGSIZE; + } + nla_nest_end(skb, nla); + + return 0; +} + /** * ovs_vport_get_options - retrieve device options * diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 6ff45e8a0868..3e71ca8ad8a7 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -32,6 +32,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name); void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *); +int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb); + int ovs_vport_set_options(struct vport *, struct nlattr *options); int ovs_vport_get_options(const struct vport *, struct sk_buff *); @@ -65,6 +67,7 @@ struct vport_portids { * @hash_node: Element in @dev_table hash table in vport.c. * @dp_hash_node: Element in @datapath->ports hash table in datapath.c. * @ops: Class structure. + * @upcall_stats: Upcall stats of every ports. * @detach_list: list used for detaching vport in net-exit call. * @rcu: RCU callback head for deferred destruction. */ @@ -78,6 +81,7 @@ struct vport { struct hlist_node hash_node; struct hlist_node dp_hash_node; const struct vport_ops *ops; + struct vport_upcall_stats_percpu __percpu *upcall_stats; struct list_head detach_list; struct rcu_head rcu; @@ -137,6 +141,18 @@ struct vport_ops { struct list_head list; }; +/** + * struct vport_upcall_stats_percpu - per-cpu packet upcall statistics for + * a given vport. + * @n_success: Number of packets that upcall to userspace succeed. + * @n_fail: Number of packets that upcall to userspace failed. + */ +struct vport_upcall_stats_percpu { + struct u64_stats_sync syncp; + u64_stats_t n_success; + u64_stats_t n_fail; +}; + struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *, const struct vport_parms *); void ovs_vport_free(struct vport *); -- cgit v1.2.3 From ce098da1497c6dee9589fce2c61d1910f4fcf0e7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 7 Dec 2022 22:02:59 -0800 Subject: skbuff: Introduce slab_build_skb() syzkaller reported: BUG: KASAN: slab-out-of-bounds in __build_skb_around+0x235/0x340 net/core/skbuff.c:294 Write of size 32 at addr ffff88802aa172c0 by task syz-executor413/5295 For bpf_prog_test_run_skb(), which uses a kmalloc()ed buffer passed to build_skb(). When build_skb() is passed a frag_size of 0, it means the buffer came from kmalloc. In these cases, ksize() is used to find its actual size, but since the allocation may not have been made to that size, actually perform the krealloc() call so that all the associated buffer size checking will be correctly notified (and use the "new" pointer so that compiler hinting works correctly). Split this logic out into a new interface, slab_build_skb(), but leave the original 0 checking for now to catch any stragglers. Reported-by: syzbot+fda18eaa8c12534ccb3b@syzkaller.appspotmail.com Link: https://groups.google.com/g/syzkaller-bugs/c/UnIKxTtU5-0/m/-wbXinkgAQAJ Fixes: 38931d8989b5 ("mm: Make ksize() a reporting-only function") Cc: Pavel Begunkov Cc: pepsipu Cc: syzbot+fda18eaa8c12534ccb3b@syzkaller.appspotmail.com Cc: Vlastimil Babka Cc: kasan-dev Cc: Andrii Nakryiko Cc: ast@kernel.org Cc: Daniel Borkmann Cc: Hao Luo Cc: Jesper Dangaard Brouer Cc: John Fastabend Cc: jolsa@kernel.org Cc: KP Singh Cc: martin.lau@linux.dev Cc: Stanislav Fomichev Cc: song@kernel.org Cc: Yonghong Song Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20221208060256.give.994-kees@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/broadcom/bnx2.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 2 +- include/linux/skbuff.h | 1 + net/bpf/test_run.c | 2 +- net/core/skbuff.c | 70 +++++++++++++++++++++++++++---- 5 files changed, 66 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index dbe310144780..9f473854b0f4 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -3045,7 +3045,7 @@ error: dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size, DMA_FROM_DEVICE); - skb = build_skb(data, 0); + skb = slab_build_skb(data); if (!skb) { kfree(data); goto error; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index ed274f033626..e5116a86cfbc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -200,7 +200,7 @@ static void qed_ll2b_complete_rx_packet(void *cxt, dma_unmap_single(&cdev->pdev->dev, buffer->phys_addr, cdev->ll2->rx_size, DMA_FROM_DEVICE); - skb = build_skb(buffer->data, 0); + skb = slab_build_skb(buffer->data); if (!skb) { DP_INFO(cdev, "Failed to build SKB\n"); kfree(buffer->data); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4e464a27adaf..4c8492401a10 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1255,6 +1255,7 @@ struct sk_buff *build_skb_around(struct sk_buff *skb, void skb_attempt_defer_free(struct sk_buff *skb); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); +struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6094ef7cffcd..c9bfd263dcef 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -1128,7 +1128,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, } sock_init_data(NULL, sk); - skb = build_skb(data, 0); + skb = slab_build_skb(data); if (!skb) { kfree(data); kfree(ctx); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4bf95e36ed16..3cbba7099c0f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -270,12 +270,10 @@ static struct sk_buff *napi_skb_cache_get(void) return skb; } -/* Caller must provide SKB that is memset cleared */ -static void __build_skb_around(struct sk_buff *skb, void *data, - unsigned int frag_size) +static inline void __finalize_skb_around(struct sk_buff *skb, void *data, + unsigned int size) { struct skb_shared_info *shinfo; - unsigned int size = frag_size ? : ksize(data); size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -297,15 +295,71 @@ static void __build_skb_around(struct sk_buff *skb, void *data, skb_set_kcov_handle(skb, kcov_common_handle()); } +static inline void *__slab_build_skb(struct sk_buff *skb, void *data, + unsigned int *size) +{ + void *resized; + + /* Must find the allocation size (and grow it to match). */ + *size = ksize(data); + /* krealloc() will immediately return "data" when + * "ksize(data)" is requested: it is the existing upper + * bounds. As a result, GFP_ATOMIC will be ignored. Note + * that this "new" pointer needs to be passed back to the + * caller for use so the __alloc_size hinting will be + * tracked correctly. + */ + resized = krealloc(data, *size, GFP_ATOMIC); + WARN_ON_ONCE(resized != data); + return resized; +} + +/* build_skb() variant which can operate on slab buffers. + * Note that this should be used sparingly as slab buffers + * cannot be combined efficiently by GRO! + */ +struct sk_buff *slab_build_skb(void *data) +{ + struct sk_buff *skb; + unsigned int size; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (unlikely(!skb)) + return NULL; + + memset(skb, 0, offsetof(struct sk_buff, tail)); + data = __slab_build_skb(skb, data, &size); + __finalize_skb_around(skb, data, size); + + return skb; +} +EXPORT_SYMBOL(slab_build_skb); + +/* Caller must provide SKB that is memset cleared */ +static void __build_skb_around(struct sk_buff *skb, void *data, + unsigned int frag_size) +{ + unsigned int size = frag_size; + + /* frag_size == 0 is considered deprecated now. Callers + * using slab buffer should use slab_build_skb() instead. + */ + if (WARN_ONCE(size == 0, "Use slab_build_skb() instead")) + data = __slab_build_skb(skb, data, &size); + + __finalize_skb_around(skb, data, size); +} + /** * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of data, or 0 if head was kmalloced + * @frag_size: size of data (must not be 0) * * Allocate a new &sk_buff. Caller provides space holding head and - * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator - * or vmalloc() + * skb_shared_info. @data must have been allocated from the page + * allocator or vmalloc(). (A @frag_size of 0 to indicate a kmalloc() + * allocation is deprecated, and callers should use slab_build_skb() + * instead.) * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : -- cgit v1.2.3 From 5dd9cdbc9dec3e99b19e483767e247d15ca8cc0d Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Fri, 9 Dec 2022 15:57:29 +0200 Subject: bpf: states_equal() must build idmap for all function frames verifier.c:states_equal() must maintain register ID mapping across all function frames. Otherwise the following example might be erroneously marked as safe: main: fp[-24] = map_lookup_elem(...) ; frame[0].fp[-24].id == 1 fp[-32] = map_lookup_elem(...) ; frame[0].fp[-32].id == 2 r1 = &fp[-24] r2 = &fp[-32] call foo() r0 = 0 exit foo: 0: r9 = r1 1: r8 = r2 2: r7 = ktime_get_ns() 3: r6 = ktime_get_ns() 4: if (r6 > r7) goto skip_assign 5: r9 = r8 skip_assign: ; <--- checkpoint 6: r9 = *r9 ; (a) frame[1].r9.id == 2 ; (b) frame[1].r9.id == 1 7: if r9 == 0 goto exit: ; mark_ptr_or_null_regs() transfers != 0 info ; for all regs sharing ID: ; (a) r9 != 0 => &frame[0].fp[-32] != 0 ; (b) r9 != 0 => &frame[0].fp[-24] != 0 8: r8 = *r8 ; (a) r8 == &frame[0].fp[-32] ; (b) r8 == &frame[0].fp[-32] 9: r0 = *r8 ; (a) safe ; (b) unsafe exit: 10: exit While processing call to foo() verifier considers the following execution paths: (a) 0-10 (b) 0-4,6-10 (There is also path 0-7,10 but it is not interesting for the issue at hand. (a) is verified first.) Suppose that checkpoint is created at (6) when path (a) is verified, next path (b) is verified and (6) is reached. If states_equal() maintains separate 'idmap' for each frame the mapping at (6) for frame[1] would be empty and regsafe(r9)::check_ids() would add a pair 2->1 and return true, which is an error. If states_equal() maintains single 'idmap' for all frames the mapping at (6) would be { 1->1, 2->2 } and regsafe(r9)::check_ids() would return false when trying to add a pair 2->1. This issue was suggested in the following discussion: https://lore.kernel.org/bpf/CAEf4BzbFB5g4oUfyxk9rHy-PJSLQ3h8q9mV=rVoXfr_JVm8+1Q@mail.gmail.com/ Suggested-by: Andrii Nakryiko Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20221209135733.28851-4-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 ++-- kernel/bpf/verifier.c | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index df0cb825e0e3..53d175cbaa02 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -273,9 +273,9 @@ struct bpf_id_pair { u32 cur; }; -/* Maximum number of register states that can exist at once */ -#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) #define MAX_CALL_FRAMES 8 +/* Maximum number of register states that can exist at once */ +#define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES) struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 97645f767354..00c8e0a28203 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13260,7 +13260,6 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat { int i; - memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], env->idmap_scratch)) @@ -13284,6 +13283,8 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->curframe != cur->curframe) return false; + memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); + /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. */ -- cgit v1.2.3 From 5df7d714d8cbcce7642936cc0f6532f0c4c3d197 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:45:59 +0200 Subject: ipvs: add rcu protection to stats In preparation to using RCU locking for the list with estimators, make sure the struct ip_vs_stats are released after RCU grace period by using RCU callbacks. This affects ipvs->tot_stats where we can not use RCU callbacks for ipvs, so we use allocated struct ip_vs_stats_rcu. For services and dests we force RCU callbacks for all cases. Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 8 +++++- net/netfilter/ipvs/ip_vs_core.c | 10 +++++-- net/netfilter/ipvs/ip_vs_ctl.c | 64 +++++++++++++++++++++++++++-------------- 3 files changed, 57 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff1804a0c469..bd8ae137e43b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -405,6 +405,11 @@ struct ip_vs_stats { struct ip_vs_kstats kstats0; /* reset values */ }; +struct ip_vs_stats_rcu { + struct ip_vs_stats s; + struct rcu_head rcu_head; +}; + struct dst_entry; struct iphdr; struct ip_vs_conn; @@ -688,6 +693,7 @@ struct ip_vs_dest { union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ + struct rcu_head rcu_head; struct list_head t_list; /* in dest_trash */ unsigned int in_rs_table:1; /* we are in rs_table */ }; @@ -869,7 +875,7 @@ struct netns_ipvs { atomic_t conn_count; /* connection counter */ /* ip_vs_ctl */ - struct ip_vs_stats tot_stats; /* Statistics & est. */ + struct ip_vs_stats_rcu *tot_stats; /* Statistics & est. */ int num_services; /* no of virtual services */ int num_services6; /* IPv6 virtual services */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 51ad557a525b..fcdaef1fcccf 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -143,7 +143,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->cnt.inbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(ipvs->tot_stats.cpustats); + s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.inpkts++; s->cnt.inbytes += skb->len; @@ -179,7 +179,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s->cnt.outbytes += skb->len; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(ipvs->tot_stats.cpustats); + s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.outpkts++; s->cnt.outbytes += skb->len; @@ -208,7 +208,7 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) s->cnt.conns++; u64_stats_update_end(&s->syncp); - s = this_cpu_ptr(ipvs->tot_stats.cpustats); + s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); s->cnt.conns++; u64_stats_update_end(&s->syncp); @@ -2448,6 +2448,10 @@ static void __exit ip_vs_cleanup(void) ip_vs_conn_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); + /* common rcu_barrier() used by: + * - ip_vs_control_cleanup() + */ + rcu_barrier(); pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 4d62059a6021..9016b641ae52 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -483,17 +483,14 @@ static void ip_vs_service_rcu_free(struct rcu_head *head) ip_vs_service_free(svc); } -static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay) +static void __ip_vs_svc_put(struct ip_vs_service *svc) { if (atomic_dec_and_test(&svc->refcnt)) { IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n", svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port)); - if (do_delay) - call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); - else - ip_vs_service_free(svc); + call_rcu(&svc->rcu_head, ip_vs_service_rcu_free); } } @@ -780,14 +777,22 @@ out: return dest; } +static void ip_vs_dest_rcu_free(struct rcu_head *head) +{ + struct ip_vs_dest *dest; + + dest = container_of(head, struct ip_vs_dest, rcu_head); + free_percpu(dest->stats.cpustats); + ip_vs_dest_put_and_free(dest); +} + static void ip_vs_dest_free(struct ip_vs_dest *dest) { struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1); __ip_vs_dst_cache_reset(dest); - __ip_vs_svc_put(svc, false); - free_percpu(dest->stats.cpustats); - ip_vs_dest_put_and_free(dest); + __ip_vs_svc_put(svc); + call_rcu(&dest->rcu_head, ip_vs_dest_rcu_free); } /* @@ -811,6 +816,16 @@ static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs) } } +static void ip_vs_stats_rcu_free(struct rcu_head *head) +{ + struct ip_vs_stats_rcu *rs = container_of(head, + struct ip_vs_stats_rcu, + rcu_head); + + free_percpu(rs->s.cpustats); + kfree(rs); +} + static void ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src) { @@ -923,7 +938,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, if (old_svc != svc) { ip_vs_zero_stats(&dest->stats); __ip_vs_bind_svc(dest, svc); - __ip_vs_svc_put(old_svc, true); + __ip_vs_svc_put(old_svc); } } @@ -1571,7 +1586,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) /* * Free the service if nobody refers to it */ - __ip_vs_svc_put(svc, true); + __ip_vs_svc_put(svc); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -1761,7 +1776,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs) } } - ip_vs_zero_stats(&ipvs->tot_stats); + ip_vs_zero_stats(&ipvs->tot_stats->s); return 0; } @@ -2255,7 +2270,7 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) seq_puts(seq, " Conns Packets Packets Bytes Bytes\n"); - ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats); + ip_vs_copy_stats(&show, &net_ipvs(net)->tot_stats->s); seq_printf(seq, "%8LX %8LX %8LX %16LX %16LX\n\n", (unsigned long long)show.conns, (unsigned long long)show.inpkts, @@ -2279,7 +2294,7 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) { struct net *net = seq_file_single_net(seq); - struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats; + struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats->s; struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats; struct ip_vs_kstats kstats; int i; @@ -4107,7 +4122,6 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) kfree(tbl); return -ENOMEM; } - ip_vs_start_estimator(ipvs, &ipvs->tot_stats); ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); @@ -4118,6 +4132,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, expire_nodest_conn_handler); + ip_vs_start_estimator(ipvs, &ipvs->tot_stats->s); return 0; } @@ -4129,7 +4144,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); - ip_vs_stop_estimator(ipvs, &ipvs->tot_stats); + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); if (!net_eq(net, &init_net)) kfree(ipvs->sysctl_tbl); @@ -4165,17 +4180,20 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) atomic_set(&ipvs->conn_out_counter, 0); /* procfs stats */ - ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!ipvs->tot_stats.cpustats) + ipvs->tot_stats = kzalloc(sizeof(*ipvs->tot_stats), GFP_KERNEL); + if (!ipvs->tot_stats) return -ENOMEM; + ipvs->tot_stats->s.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!ipvs->tot_stats->s.cpustats) + goto err_tot_stats; for_each_possible_cpu(i) { struct ip_vs_cpu_stats *ipvs_tot_stats; - ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats.cpustats, i); + ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats->s.cpustats, i); u64_stats_init(&ipvs_tot_stats->syncp); } - spin_lock_init(&ipvs->tot_stats.lock); + spin_lock_init(&ipvs->tot_stats->s.lock); #ifdef CONFIG_PROC_FS if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, @@ -4207,7 +4225,10 @@ err_stats: err_vs: #endif - free_percpu(ipvs->tot_stats.cpustats); + free_percpu(ipvs->tot_stats->s.cpustats); + +err_tot_stats: + kfree(ipvs->tot_stats); return -ENOMEM; } @@ -4220,7 +4241,7 @@ void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); remove_proc_entry("ip_vs", ipvs->net->proc_net); #endif - free_percpu(ipvs->tot_stats.cpustats); + call_rcu(&ipvs->tot_stats->rcu_head, ip_vs_stats_rcu_free); } int __init ip_vs_register_nl_ioctl(void) @@ -4280,5 +4301,6 @@ void ip_vs_control_cleanup(void) { EnterFunction(2); unregister_netdevice_notifier(&ip_vs_dst_notifier); + /* relying on common rcu_barrier() in ip_vs_cleanup() */ LeaveFunction(2); } -- cgit v1.2.3 From de39afb3d811ba2c028de8662adafedb4899327b Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:46:00 +0200 Subject: ipvs: use common functions for stats allocation Move alloc_percpu/free_percpu logic in new functions Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 5 +++ net/netfilter/ipvs/ip_vs_ctl.c | 96 ++++++++++++++++++++++++------------------ 2 files changed, 60 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index bd8ae137e43b..e5582c01a4a3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -410,6 +410,11 @@ struct ip_vs_stats_rcu { struct rcu_head rcu_head; }; +int ip_vs_stats_init_alloc(struct ip_vs_stats *s); +struct ip_vs_stats *ip_vs_stats_alloc(void); +void ip_vs_stats_release(struct ip_vs_stats *stats); +void ip_vs_stats_free(struct ip_vs_stats *stats); + struct dst_entry; struct iphdr; struct ip_vs_conn; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 9016b641ae52..ec6db864ac36 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -471,7 +471,7 @@ __ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc) static void ip_vs_service_free(struct ip_vs_service *svc) { - free_percpu(svc->stats.cpustats); + ip_vs_stats_release(&svc->stats); kfree(svc); } @@ -782,7 +782,7 @@ static void ip_vs_dest_rcu_free(struct rcu_head *head) struct ip_vs_dest *dest; dest = container_of(head, struct ip_vs_dest, rcu_head); - free_percpu(dest->stats.cpustats); + ip_vs_stats_release(&dest->stats); ip_vs_dest_put_and_free(dest); } @@ -822,7 +822,7 @@ static void ip_vs_stats_rcu_free(struct rcu_head *head) struct ip_vs_stats_rcu, rcu_head); - free_percpu(rs->s.cpustats); + ip_vs_stats_release(&rs->s); kfree(rs); } @@ -879,6 +879,47 @@ ip_vs_zero_stats(struct ip_vs_stats *stats) spin_unlock_bh(&stats->lock); } +/* Allocate fields after kzalloc */ +int ip_vs_stats_init_alloc(struct ip_vs_stats *s) +{ + int i; + + spin_lock_init(&s->lock); + s->cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!s->cpustats) + return -ENOMEM; + + for_each_possible_cpu(i) { + struct ip_vs_cpu_stats *cs = per_cpu_ptr(s->cpustats, i); + + u64_stats_init(&cs->syncp); + } + return 0; +} + +struct ip_vs_stats *ip_vs_stats_alloc(void) +{ + struct ip_vs_stats *s = kzalloc(sizeof(*s), GFP_KERNEL); + + if (s && ip_vs_stats_init_alloc(s) >= 0) + return s; + kfree(s); + return NULL; +} + +void ip_vs_stats_release(struct ip_vs_stats *stats) +{ + free_percpu(stats->cpustats); +} + +void ip_vs_stats_free(struct ip_vs_stats *stats) +{ + if (stats) { + ip_vs_stats_release(stats); + kfree(stats); + } +} + /* * Update a destination in the given service */ @@ -978,14 +1019,13 @@ static int ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; - unsigned int atype, i; + unsigned int atype; + int ret; EnterFunction(2); #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { - int ret; - atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && @@ -1007,16 +1047,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) if (dest == NULL) return -ENOMEM; - dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!dest->stats.cpustats) + ret = ip_vs_stats_init_alloc(&dest->stats); + if (ret < 0) goto err_alloc; - for_each_possible_cpu(i) { - struct ip_vs_cpu_stats *ip_vs_dest_stats; - ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i); - u64_stats_init(&ip_vs_dest_stats->syncp); - } - dest->af = udest->af; dest->protocol = svc->protocol; dest->vaddr = svc->addr; @@ -1032,7 +1066,6 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) INIT_HLIST_NODE(&dest->d_list); spin_lock_init(&dest->dst_lock); - spin_lock_init(&dest->stats.lock); __ip_vs_update_dest(svc, dest, udest, 1); LeaveFunction(2); @@ -1040,7 +1073,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) err_alloc: kfree(dest); - return -ENOMEM; + return ret; } @@ -1299,7 +1332,7 @@ static int ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service **svc_p) { - int ret = 0, i; + int ret = 0; struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; @@ -1359,18 +1392,9 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -ENOMEM; goto out_err; } - svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!svc->stats.cpustats) { - ret = -ENOMEM; + ret = ip_vs_stats_init_alloc(&svc->stats); + if (ret < 0) goto out_err; - } - - for_each_possible_cpu(i) { - struct ip_vs_cpu_stats *ip_vs_stats; - ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i); - u64_stats_init(&ip_vs_stats->syncp); - } - /* I'm the first user of the service */ atomic_set(&svc->refcnt, 0); @@ -1387,7 +1411,6 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, INIT_LIST_HEAD(&svc->destinations); spin_lock_init(&svc->sched_lock); - spin_lock_init(&svc->stats.lock); /* Bind the scheduler */ if (sched) { @@ -4166,7 +4189,7 @@ static struct notifier_block ip_vs_dst_notifier = { int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { - int i, idx; + int idx; /* Initialize rs_table */ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) @@ -4183,18 +4206,9 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) ipvs->tot_stats = kzalloc(sizeof(*ipvs->tot_stats), GFP_KERNEL); if (!ipvs->tot_stats) return -ENOMEM; - ipvs->tot_stats->s.cpustats = alloc_percpu(struct ip_vs_cpu_stats); - if (!ipvs->tot_stats->s.cpustats) + if (ip_vs_stats_init_alloc(&ipvs->tot_stats->s) < 0) goto err_tot_stats; - for_each_possible_cpu(i) { - struct ip_vs_cpu_stats *ipvs_tot_stats; - ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats->s.cpustats, i); - u64_stats_init(&ipvs_tot_stats->syncp); - } - - spin_lock_init(&ipvs->tot_stats->s.lock); - #ifdef CONFIG_PROC_FS if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter))) @@ -4225,7 +4239,7 @@ err_stats: err_vs: #endif - free_percpu(ipvs->tot_stats->s.cpustats); + ip_vs_stats_release(&ipvs->tot_stats->s); err_tot_stats: kfree(ipvs->tot_stats); -- cgit v1.2.3 From 1dbd8d9a82e3f26b9d063292d47ece673f48fce2 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:46:01 +0200 Subject: ipvs: use u64_stats_t for the per-cpu counters Use the provided u64_stats_t type to avoid load/store tearing. Fixes: 316580b69d0a ("u64_stats: provide u64_stats_t type") Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Tested-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 10 +++++----- net/netfilter/ipvs/ip_vs_core.c | 30 +++++++++++++++--------------- net/netfilter/ipvs/ip_vs_ctl.c | 10 +++++----- net/netfilter/ipvs/ip_vs_est.c | 20 ++++++++++---------- 4 files changed, 35 insertions(+), 35 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index e5582c01a4a3..a4d44138c2a8 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -351,11 +351,11 @@ struct ip_vs_seq { /* counters per cpu */ struct ip_vs_counters { - __u64 conns; /* connections scheduled */ - __u64 inpkts; /* incoming packets */ - __u64 outpkts; /* outgoing packets */ - __u64 inbytes; /* incoming bytes */ - __u64 outbytes; /* outgoing bytes */ + u64_stats_t conns; /* connections scheduled */ + u64_stats_t inpkts; /* incoming packets */ + u64_stats_t outpkts; /* outgoing packets */ + u64_stats_t inbytes; /* incoming bytes */ + u64_stats_t outbytes; /* outgoing bytes */ }; /* Stats per cpu */ struct ip_vs_cpu_stats { diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fcdaef1fcccf..2fcc26507d69 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -132,21 +132,21 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.inpkts++; - s->cnt.inbytes += skb->len; + u64_stats_inc(&s->cnt.inpkts); + u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.inpkts++; - s->cnt.inbytes += skb->len; + u64_stats_inc(&s->cnt.inpkts); + u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.inpkts++; - s->cnt.inbytes += skb->len; + u64_stats_inc(&s->cnt.inpkts); + u64_stats_add(&s->cnt.inbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); @@ -168,21 +168,21 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) s = this_cpu_ptr(dest->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.outpkts++; - s->cnt.outbytes += skb->len; + u64_stats_inc(&s->cnt.outpkts); + u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); svc = rcu_dereference(dest->svc); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.outpkts++; - s->cnt.outbytes += skb->len; + u64_stats_inc(&s->cnt.outpkts); + u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.outpkts++; - s->cnt.outbytes += skb->len; + u64_stats_inc(&s->cnt.outpkts); + u64_stats_add(&s->cnt.outbytes, skb->len); u64_stats_update_end(&s->syncp); local_bh_enable(); @@ -200,17 +200,17 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) s = this_cpu_ptr(cp->dest->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.conns++; + u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(svc->stats.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.conns++; + u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); s = this_cpu_ptr(ipvs->tot_stats->s.cpustats); u64_stats_update_begin(&s->syncp); - s->cnt.conns++; + u64_stats_inc(&s->cnt.conns); u64_stats_update_end(&s->syncp); local_bh_enable(); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ec6db864ac36..5f9cc2e7ba71 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2335,11 +2335,11 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) do { start = u64_stats_fetch_begin(&u->syncp); - conns = u->cnt.conns; - inpkts = u->cnt.inpkts; - outpkts = u->cnt.outpkts; - inbytes = u->cnt.inbytes; - outbytes = u->cnt.outbytes; + conns = u64_stats_read(&u->cnt.conns); + inpkts = u64_stats_read(&u->cnt.inpkts); + outpkts = u64_stats_read(&u->cnt.outpkts); + inbytes = u64_stats_read(&u->cnt.inbytes); + outbytes = u64_stats_read(&u->cnt.outbytes); } while (u64_stats_fetch_retry(&u->syncp, start)); seq_printf(seq, "%3X %8LX %8LX %8LX %16LX %16LX\n", diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 9a1a7af6a186..f53150d82a92 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -67,11 +67,11 @@ static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum, if (add) { do { start = u64_stats_fetch_begin(&s->syncp); - conns = s->cnt.conns; - inpkts = s->cnt.inpkts; - outpkts = s->cnt.outpkts; - inbytes = s->cnt.inbytes; - outbytes = s->cnt.outbytes; + conns = u64_stats_read(&s->cnt.conns); + inpkts = u64_stats_read(&s->cnt.inpkts); + outpkts = u64_stats_read(&s->cnt.outpkts); + inbytes = u64_stats_read(&s->cnt.inbytes); + outbytes = u64_stats_read(&s->cnt.outbytes); } while (u64_stats_fetch_retry(&s->syncp, start)); sum->conns += conns; sum->inpkts += inpkts; @@ -82,11 +82,11 @@ static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum, add = true; do { start = u64_stats_fetch_begin(&s->syncp); - sum->conns = s->cnt.conns; - sum->inpkts = s->cnt.inpkts; - sum->outpkts = s->cnt.outpkts; - sum->inbytes = s->cnt.inbytes; - sum->outbytes = s->cnt.outbytes; + sum->conns = u64_stats_read(&s->cnt.conns); + sum->inpkts = u64_stats_read(&s->cnt.inpkts); + sum->outpkts = u64_stats_read(&s->cnt.outpkts); + sum->inbytes = u64_stats_read(&s->cnt.inbytes); + sum->outbytes = u64_stats_read(&s->cnt.outbytes); } while (u64_stats_fetch_retry(&s->syncp, start)); } } -- cgit v1.2.3 From 705dd34440812735ece298eb5bc153fde9544d42 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:46:02 +0200 Subject: ipvs: use kthreads for stats estimation Estimating all entries in single list in timer context by single CPU causes large latency with multiple IPVS rules as reported in [1], [2], [3]. Spread the estimator structures in multiple chains and use kthread(s) for the estimation. The chains are processed in multiple (50) timer ticks to ensure the 2-second interval between estimations with some accuracy. Every chain is processed under RCU lock. Every kthread works over its own data structure and all such contexts are attached to array. The contexts can be preserved while the kthread tasks are stopped or restarted. When estimators are removed, unused kthread contexts are released and the slots in array are left empty. First kthread determines parameters to use, eg. maximum number of estimators to process per kthread based on chain's length (chain_max), allowing sub-100us cond_resched rate and estimation taking up to 1/8 of the CPU capacity to avoid any problems if chain_max is not correctly calculated. chain_max is calculated taking into account factors such as CPU speed and memory/cache speed where the cache_factor (4) is selected from real tests with current generation of CPU/NUMA configurations to correct the difference in CPU usage between cached (during calc phase) and non-cached (working) state of the estimated per-cpu data. First kthread also plays the role of distributor of added estimators to all kthreads, keeping low the time to add estimators. The optimization is based on the fact that newly added estimator should be estimated after 2 seconds, so we have the time to offload the adding to chain from controlling process to kthread 0. The allocated kthread context may grow from 1 to 50 allocated structures for timer ticks which saves memory for setups with small number of estimators. We also add delayed work est_reload_work that will make sure the kthread tasks are properly started/stopped. ip_vs_start_estimator() is changed to report errors which allows to safely store the estimators in allocated structures. Many thanks to Jiri Wiesner for his valuable comments and for spending a lot of time reviewing and testing the changes on different platforms with 48-256 CPUs and 1-8 NUMA nodes under different cpufreq governors. [1] Report from Yunhong Jiang: https://lore.kernel.org/netdev/D25792C1-1B89-45DE-9F10-EC350DC04ADC@gmail.com/ [2] https://marc.info/?l=linux-virtual-server&m=159679809118027&w=2 [3] Report from Dust: https://archive.linuxvirtualserver.org/html/lvs-devel/2020-12/msg00000.html Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Tested-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- include/net/ip_vs.h | 88 ++++- net/netfilter/ipvs/ip_vs_ctl.c | 126 ++++-- net/netfilter/ipvs/ip_vs_est.c | 876 +++++++++++++++++++++++++++++++++++++---- 3 files changed, 990 insertions(+), 100 deletions(-) (limited to 'include') diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a4d44138c2a8..04960dc6228f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -42,6 +42,8 @@ static inline struct netns_ipvs *net_ipvs(struct net* net) /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; +extern struct mutex __ip_vs_mutex; + struct ip_vs_iphdr { int hdr_flags; /* ipvs flags */ __u32 off; /* Where IP or IPv4 header starts */ @@ -365,7 +367,7 @@ struct ip_vs_cpu_stats { /* IPVS statistics objects */ struct ip_vs_estimator { - struct list_head list; + struct hlist_node list; u64 last_inbytes; u64 last_outbytes; @@ -378,6 +380,10 @@ struct ip_vs_estimator { u64 outpps; u64 inbps; u64 outbps; + + s32 ktid:16, /* kthread ID, -1=temp list */ + ktrow:8, /* row/tick ID for kthread */ + ktcid:8; /* chain ID for kthread tick */ }; /* @@ -415,6 +421,66 @@ struct ip_vs_stats *ip_vs_stats_alloc(void); void ip_vs_stats_release(struct ip_vs_stats *stats); void ip_vs_stats_free(struct ip_vs_stats *stats); +/* Process estimators in multiple timer ticks (20/50/100, see ktrow) */ +#define IPVS_EST_NTICKS 50 +/* Estimation uses a 2-second period containing ticks (in jiffies) */ +#define IPVS_EST_TICK ((2 * HZ) / IPVS_EST_NTICKS) + +/* Limit of CPU load per kthread (8 for 12.5%), ratio of CPU capacity (1/C). + * Value of 4 and above ensures kthreads will take work without exceeding + * the CPU capacity under different circumstances. + */ +#define IPVS_EST_LOAD_DIVISOR 8 + +/* Kthreads should not have work that exceeds the CPU load above 50% */ +#define IPVS_EST_CPU_KTHREADS (IPVS_EST_LOAD_DIVISOR / 2) + +/* Desired number of chains per timer tick (chain load factor in 100us units), + * 48=4.8ms of 40ms tick (12% CPU usage): + * 2 sec * 1000 ms in sec * 10 (100us in ms) / 8 (12.5%) / 50 + */ +#define IPVS_EST_CHAIN_FACTOR \ + ALIGN_DOWN(2 * 1000 * 10 / IPVS_EST_LOAD_DIVISOR / IPVS_EST_NTICKS, 8) + +/* Compiled number of chains per tick + * The defines should match cond_resched_rcu + */ +#if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU) +#define IPVS_EST_TICK_CHAINS IPVS_EST_CHAIN_FACTOR +#else +#define IPVS_EST_TICK_CHAINS 1 +#endif + +#if IPVS_EST_NTICKS > 127 +#error Too many timer ticks for ktrow +#endif + +/* Multiple chains processed in same tick */ +struct ip_vs_est_tick_data { + struct hlist_head chains[IPVS_EST_TICK_CHAINS]; + DECLARE_BITMAP(present, IPVS_EST_TICK_CHAINS); + DECLARE_BITMAP(full, IPVS_EST_TICK_CHAINS); + int chain_len[IPVS_EST_TICK_CHAINS]; +}; + +/* Context for estimation kthread */ +struct ip_vs_est_kt_data { + struct netns_ipvs *ipvs; + struct task_struct *task; /* task if running */ + struct ip_vs_est_tick_data __rcu *ticks[IPVS_EST_NTICKS]; + DECLARE_BITMAP(avail, IPVS_EST_NTICKS); /* tick has space for ests */ + unsigned long est_timer; /* estimation timer (jiffies) */ + struct ip_vs_stats *calc_stats; /* Used for calculation */ + int tick_len[IPVS_EST_NTICKS]; /* est count */ + int id; /* ktid per netns */ + int chain_max; /* max ests per tick chain */ + int tick_max; /* max ests per tick */ + int est_count; /* attached ests to kthread */ + int est_max_count; /* max ests per kthread */ + int add_row; /* row for new ests */ + int est_row; /* estimated row */ +}; + struct dst_entry; struct iphdr; struct ip_vs_conn; @@ -953,9 +1019,17 @@ struct netns_ipvs { struct ctl_table_header *lblcr_ctl_header; struct ctl_table *lblcr_ctl_table; /* ip_vs_est */ - struct list_head est_list; /* estimator list */ - spinlock_t est_lock; - struct timer_list est_timer; /* Estimation timer */ + struct delayed_work est_reload_work;/* Reload kthread tasks */ + struct mutex est_mutex; /* protect kthread tasks */ + struct hlist_head est_temp_list; /* Ests during calc phase */ + struct ip_vs_est_kt_data **est_kt_arr; /* Array of kthread data ptrs */ + unsigned long est_max_threads;/* Hard limit of kthreads */ + int est_calc_phase; /* Calculation phase */ + int est_chain_max; /* Calculated chain_max */ + int est_kt_count; /* Allocated ptrs */ + int est_add_ktid; /* ktid where to add ests */ + atomic_t est_genid; /* kthreads reload genid */ + atomic_t est_genid_done; /* applied genid */ /* ip_vs_sync */ spinlock_t sync_lock; struct ipvs_master_sync_state *ms; @@ -1486,10 +1560,14 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state); void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ -void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); +int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); +void ip_vs_est_reload_start(struct netns_ipvs *ipvs); +int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, + struct ip_vs_est_kt_data *kd); +void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); /* Various IPVS packet transmitters (from ip_vs_xmit.c) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5f9cc2e7ba71..c41a5392edc9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -49,8 +49,7 @@ MODULE_ALIAS_GENL_FAMILY(IPVS_GENL_NAME); -/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ -static DEFINE_MUTEX(__ip_vs_mutex); +DEFINE_MUTEX(__ip_vs_mutex); /* Serialize configuration with sockopt/netlink */ /* sysctl variables */ @@ -241,6 +240,47 @@ static void defense_work_handler(struct work_struct *work) } #endif +static void est_reload_work_handler(struct work_struct *work) +{ + struct netns_ipvs *ipvs = + container_of(work, struct netns_ipvs, est_reload_work.work); + int genid_done = atomic_read(&ipvs->est_genid_done); + unsigned long delay = HZ / 10; /* repeat startups after failure */ + bool repeat = false; + int genid; + int id; + + mutex_lock(&ipvs->est_mutex); + genid = atomic_read(&ipvs->est_genid); + for (id = 0; id < ipvs->est_kt_count; id++) { + struct ip_vs_est_kt_data *kd = ipvs->est_kt_arr[id]; + + /* netns clean up started, abort delayed work */ + if (!ipvs->enable) + goto unlock; + if (!kd) + continue; + /* New config ? Stop kthread tasks */ + if (genid != genid_done) + ip_vs_est_kthread_stop(kd); + if (!kd->task) { + /* Do not start kthreads above 0 in calc phase */ + if ((!id || !ipvs->est_calc_phase) && + ip_vs_est_kthread_start(ipvs, kd) < 0) + repeat = true; + } + } + + atomic_set(&ipvs->est_genid_done, genid); + + if (repeat) + queue_delayed_work(system_long_wq, &ipvs->est_reload_work, + delay); + +unlock: + mutex_unlock(&ipvs->est_mutex); +} + int ip_vs_use_count_inc(void) { @@ -831,7 +871,7 @@ ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src) { #define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->kstats.c - src->kstats0.c - spin_lock_bh(&src->lock); + spin_lock(&src->lock); IP_VS_SHOW_STATS_COUNTER(conns); IP_VS_SHOW_STATS_COUNTER(inpkts); @@ -841,7 +881,7 @@ ip_vs_copy_stats(struct ip_vs_kstats *dst, struct ip_vs_stats *src) ip_vs_read_estimator(dst, src); - spin_unlock_bh(&src->lock); + spin_unlock(&src->lock); } static void @@ -862,7 +902,7 @@ ip_vs_export_stats_user(struct ip_vs_stats_user *dst, struct ip_vs_kstats *src) static void ip_vs_zero_stats(struct ip_vs_stats *stats) { - spin_lock_bh(&stats->lock); + spin_lock(&stats->lock); /* get current counters as zero point, rates are zeroed */ @@ -876,7 +916,7 @@ ip_vs_zero_stats(struct ip_vs_stats *stats) ip_vs_zero_estimator(stats); - spin_unlock_bh(&stats->lock); + spin_unlock(&stats->lock); } /* Allocate fields after kzalloc */ @@ -998,7 +1038,6 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock_bh(&dest->dst_lock); if (add) { - ip_vs_start_estimator(svc->ipvs, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; sched = rcu_dereference_protected(svc->scheduler, 1); @@ -1051,6 +1090,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) if (ret < 0) goto err_alloc; + ret = ip_vs_start_estimator(svc->ipvs, &dest->stats); + if (ret < 0) + goto err_stats; + dest->af = udest->af; dest->protocol = svc->protocol; dest->vaddr = svc->addr; @@ -1071,6 +1114,9 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) LeaveFunction(2); return 0; +err_stats: + ip_vs_stats_release(&dest->stats); + err_alloc: kfree(dest); return ret; @@ -1135,14 +1181,18 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) IP_VS_DBG_ADDR(svc->af, &dest->vaddr), ntohs(dest->vport)); + ret = ip_vs_start_estimator(svc->ipvs, &dest->stats); + if (ret < 0) + goto err; __ip_vs_update_dest(svc, dest, udest, 1); - ret = 0; } else { /* * Allocate and initialize the dest structure */ ret = ip_vs_new_dest(svc, udest); } + +err: LeaveFunction(2); return ret; @@ -1420,6 +1470,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, sched = NULL; } + ret = ip_vs_start_estimator(ipvs, &svc->stats); + if (ret < 0) + goto out_err; + /* Bind the ct retriever */ RCU_INIT_POINTER(svc->pe, pe); pe = NULL; @@ -1432,8 +1486,6 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, if (svc->pe && svc->pe->conn_out) atomic_inc(&ipvs->conn_out_counter); - ip_vs_start_estimator(ipvs, &svc->stats); - /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services++; @@ -1444,8 +1496,15 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ip_vs_svc_hash(svc); *svc_p = svc; - /* Now there is a service - full throttle */ - ipvs->enable = 1; + + if (!ipvs->enable) { + /* Now there is a service - full throttle */ + ipvs->enable = 1; + + /* Start estimation for first time */ + ip_vs_est_reload_start(ipvs); + } + return 0; @@ -4065,13 +4124,16 @@ static void ip_vs_genl_unregister(void) static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { struct net *net = ipvs->net; - int idx; struct ctl_table *tbl; + int idx, ret; atomic_set(&ipvs->dropentry, 0); spin_lock_init(&ipvs->dropentry_lock); spin_lock_init(&ipvs->droppacket_lock); spin_lock_init(&ipvs->securetcp_lock); + INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); + INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, + expire_nodest_conn_handler); if (!net_eq(net, &init_net)) { tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); @@ -4139,24 +4201,27 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].mode = 0444; #endif + ret = -ENOMEM; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); - if (ipvs->sysctl_hdr == NULL) { - if (!net_eq(net, &init_net)) - kfree(tbl); - return -ENOMEM; - } + if (!ipvs->sysctl_hdr) + goto err; ipvs->sysctl_tbl = tbl; + + ret = ip_vs_start_estimator(ipvs, &ipvs->tot_stats->s); + if (ret < 0) + goto err; + /* Schedule defense work */ - INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); queue_delayed_work(system_long_wq, &ipvs->defense_work, DEFENSE_TIMER_PERIOD); - /* Init delayed work for expiring no dest conn */ - INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, - expire_nodest_conn_handler); - - ip_vs_start_estimator(ipvs, &ipvs->tot_stats->s); return 0; + +err: + unregister_net_sysctl_table(ipvs->sysctl_hdr); + if (!net_eq(net, &init_net)) + kfree(tbl); + return ret; } static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) @@ -4189,6 +4254,7 @@ static struct notifier_block ip_vs_dst_notifier = { int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { + int ret = -ENOMEM; int idx; /* Initialize rs_table */ @@ -4202,10 +4268,12 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) atomic_set(&ipvs->nullsvc_counter, 0); atomic_set(&ipvs->conn_out_counter, 0); + INIT_DELAYED_WORK(&ipvs->est_reload_work, est_reload_work_handler); + /* procfs stats */ ipvs->tot_stats = kzalloc(sizeof(*ipvs->tot_stats), GFP_KERNEL); if (!ipvs->tot_stats) - return -ENOMEM; + goto out; if (ip_vs_stats_init_alloc(&ipvs->tot_stats->s) < 0) goto err_tot_stats; @@ -4222,7 +4290,8 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) goto err_percpu; #endif - if (ip_vs_control_net_init_sysctl(ipvs)) + ret = ip_vs_control_net_init_sysctl(ipvs); + if (ret < 0) goto err; return 0; @@ -4243,13 +4312,16 @@ err_vs: err_tot_stats: kfree(ipvs->tot_stats); - return -ENOMEM; + +out: + return ret; } void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { ip_vs_trash_cleanup(ipvs); ip_vs_control_net_cleanup_sysctl(ipvs); + cancel_delayed_work_sync(&ipvs->est_reload_work); #ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net); remove_proc_entry("ip_vs_stats", ipvs->net->proc_net); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f53150d82a92..2fb6c097437c 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -30,9 +30,6 @@ long interval, it is easy to implement a user level daemon which periodically reads those statistical counters and measure rate. - Currently, the measurement is activated by slow timer handler. Hope - this measurement will not introduce too much load. - We measure rate during the last 8 seconds every 2 seconds: avgrate = avgrate*(1-W) + rate*W @@ -47,68 +44,76 @@ to 32-bit values for conns, packets, bps, cps and pps. * A lot of code is taken from net/core/gen_estimator.c - */ - -/* - * Make a summary from each cpu + KEY POINTS: + - cpustats counters are updated per-cpu in SoftIRQ context with BH disabled + - kthreads read the cpustats to update the estimators (svcs, dests, total) + - the states of estimators can be read (get stats) or modified (zero stats) + from processes + + KTHREADS: + - estimators are added initially to est_temp_list and later kthread 0 + distributes them to one or many kthreads for estimation + - kthread contexts are created and attached to array + - the kthread tasks are started when first service is added, before that + the total stats are not estimated + - the kthread context holds lists with estimators (chains) which are + processed every 2 seconds + - as estimators can be added dynamically and in bursts, we try to spread + them to multiple chains which are estimated at different time + - on start, kthread 0 enters calculation phase to determine the chain limits + and the limit of estimators per kthread + - est_add_ktid: ktid where to add new ests, can point to empty slot where + we should add kt data */ -static void ip_vs_read_cpu_stats(struct ip_vs_kstats *sum, - struct ip_vs_cpu_stats __percpu *stats) -{ - int i; - bool add = false; - - for_each_possible_cpu(i) { - struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); - unsigned int start; - u64 conns, inpkts, outpkts, inbytes, outbytes; - if (add) { - do { - start = u64_stats_fetch_begin(&s->syncp); - conns = u64_stats_read(&s->cnt.conns); - inpkts = u64_stats_read(&s->cnt.inpkts); - outpkts = u64_stats_read(&s->cnt.outpkts); - inbytes = u64_stats_read(&s->cnt.inbytes); - outbytes = u64_stats_read(&s->cnt.outbytes); - } while (u64_stats_fetch_retry(&s->syncp, start)); - sum->conns += conns; - sum->inpkts += inpkts; - sum->outpkts += outpkts; - sum->inbytes += inbytes; - sum->outbytes += outbytes; - } else { - add = true; - do { - start = u64_stats_fetch_begin(&s->syncp); - sum->conns = u64_stats_read(&s->cnt.conns); - sum->inpkts = u64_stats_read(&s->cnt.inpkts); - sum->outpkts = u64_stats_read(&s->cnt.outpkts); - sum->inbytes = u64_stats_read(&s->cnt.inbytes); - sum->outbytes = u64_stats_read(&s->cnt.outbytes); - } while (u64_stats_fetch_retry(&s->syncp, start)); - } - } -} +static struct lock_class_key __ipvs_est_key; +static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs); +static void ip_vs_est_drain_temp_list(struct netns_ipvs *ipvs); -static void estimation_timer(struct timer_list *t) +static void ip_vs_chain_estimation(struct hlist_head *chain) { struct ip_vs_estimator *e; + struct ip_vs_cpu_stats *c; struct ip_vs_stats *s; u64 rate; - struct netns_ipvs *ipvs = from_timer(ipvs, t, est_timer); - if (!sysctl_run_estimation(ipvs)) - goto skip; + hlist_for_each_entry_rcu(e, chain, list) { + u64 conns, inpkts, outpkts, inbytes, outbytes; + u64 kconns = 0, kinpkts = 0, koutpkts = 0; + u64 kinbytes = 0, koutbytes = 0; + unsigned int start; + int i; + + if (kthread_should_stop()) + break; - spin_lock(&ipvs->est_lock); - list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); + for_each_possible_cpu(i) { + c = per_cpu_ptr(s->cpustats, i); + do { + start = u64_stats_fetch_begin(&c->syncp); + conns = u64_stats_read(&c->cnt.conns); + inpkts = u64_stats_read(&c->cnt.inpkts); + outpkts = u64_stats_read(&c->cnt.outpkts); + inbytes = u64_stats_read(&c->cnt.inbytes); + outbytes = u64_stats_read(&c->cnt.outbytes); + } while (u64_stats_fetch_retry(&c->syncp, start)); + kconns += conns; + kinpkts += inpkts; + koutpkts += outpkts; + kinbytes += inbytes; + koutbytes += outbytes; + } spin_lock(&s->lock); - ip_vs_read_cpu_stats(&s->kstats, s->cpustats); + + s->kstats.conns = kconns; + s->kstats.inpkts = kinpkts; + s->kstats.outpkts = koutpkts; + s->kstats.inbytes = kinbytes; + s->kstats.outbytes = koutbytes; /* scaled by 2^10, but divided 2 seconds */ rate = (s->kstats.conns - e->last_conns) << 9; @@ -133,30 +138,754 @@ static void estimation_timer(struct timer_list *t) e->outbps += ((s64)rate - (s64)e->outbps) >> 2; spin_unlock(&s->lock); } - spin_unlock(&ipvs->est_lock); +} -skip: - mod_timer(&ipvs->est_timer, jiffies + 2*HZ); +static void ip_vs_tick_estimation(struct ip_vs_est_kt_data *kd, int row) +{ + struct ip_vs_est_tick_data *td; + int cid; + + rcu_read_lock(); + td = rcu_dereference(kd->ticks[row]); + if (!td) + goto out; + for_each_set_bit(cid, td->present, IPVS_EST_TICK_CHAINS) { + if (kthread_should_stop()) + break; + ip_vs_chain_estimation(&td->chains[cid]); + cond_resched_rcu(); + td = rcu_dereference(kd->ticks[row]); + if (!td) + break; + } + +out: + rcu_read_unlock(); } -void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) +static int ip_vs_estimation_kthread(void *data) { - struct ip_vs_estimator *est = &stats->est; + struct ip_vs_est_kt_data *kd = data; + struct netns_ipvs *ipvs = kd->ipvs; + int row = kd->est_row; + unsigned long now; + int id = kd->id; + long gap; + + if (id > 0) { + if (!ipvs->est_chain_max) + return 0; + } else { + if (!ipvs->est_chain_max) { + ipvs->est_calc_phase = 1; + /* commit est_calc_phase before reading est_genid */ + smp_mb(); + } + + /* kthread 0 will handle the calc phase */ + if (ipvs->est_calc_phase) + ip_vs_est_calc_phase(ipvs); + } + + while (1) { + if (!id && !hlist_empty(&ipvs->est_temp_list)) + ip_vs_est_drain_temp_list(ipvs); + set_current_state(TASK_IDLE); + if (kthread_should_stop()) + break; + + /* before estimation, check if we should sleep */ + now = jiffies; + gap = kd->est_timer - now; + if (gap > 0) { + if (gap > IPVS_EST_TICK) { + kd->est_timer = now - IPVS_EST_TICK; + gap = IPVS_EST_TICK; + } + schedule_timeout(gap); + } else { + __set_current_state(TASK_RUNNING); + if (gap < -8 * IPVS_EST_TICK) + kd->est_timer = now; + } + + if (sysctl_run_estimation(ipvs) && kd->tick_len[row]) + ip_vs_tick_estimation(kd, row); + + row++; + if (row >= IPVS_EST_NTICKS) + row = 0; + WRITE_ONCE(kd->est_row, row); + kd->est_timer += IPVS_EST_TICK; + } + __set_current_state(TASK_RUNNING); + + return 0; +} + +/* Schedule stop/start for kthread tasks */ +void ip_vs_est_reload_start(struct netns_ipvs *ipvs) +{ + /* Ignore reloads before first service is added */ + if (!ipvs->enable) + return; + /* Bump the kthread configuration genid */ + atomic_inc(&ipvs->est_genid); + queue_delayed_work(system_long_wq, &ipvs->est_reload_work, 0); +} + +/* Start kthread task with current configuration */ +int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, + struct ip_vs_est_kt_data *kd) +{ + unsigned long now; + int ret = 0; + long gap; + + lockdep_assert_held(&ipvs->est_mutex); + + if (kd->task) + goto out; + now = jiffies; + gap = kd->est_timer - now; + /* Sync est_timer if task is starting later */ + if (abs(gap) > 4 * IPVS_EST_TICK) + kd->est_timer = now; + kd->task = kthread_create(ip_vs_estimation_kthread, kd, "ipvs-e:%d:%d", + ipvs->gen, kd->id); + if (IS_ERR(kd->task)) { + ret = PTR_ERR(kd->task); + kd->task = NULL; + goto out; + } + + pr_info("starting estimator thread %d...\n", kd->id); + wake_up_process(kd->task); + +out: + return ret; +} + +void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd) +{ + if (kd->task) { + pr_info("stopping estimator thread %d...\n", kd->id); + kthread_stop(kd->task); + kd->task = NULL; + } +} + +/* Apply parameters to kthread */ +static void ip_vs_est_set_params(struct netns_ipvs *ipvs, + struct ip_vs_est_kt_data *kd) +{ + kd->chain_max = ipvs->est_chain_max; + /* We are using single chain on RCU preemption */ + if (IPVS_EST_TICK_CHAINS == 1) + kd->chain_max *= IPVS_EST_CHAIN_FACTOR; + kd->tick_max = IPVS_EST_TICK_CHAINS * kd->chain_max; + kd->est_max_count = IPVS_EST_NTICKS * kd->tick_max; +} + +/* Create and start estimation kthread in a free or new array slot */ +static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) +{ + struct ip_vs_est_kt_data *kd = NULL; + int id = ipvs->est_kt_count; + int ret = -ENOMEM; + void *arr = NULL; + int i; + + if ((unsigned long)ipvs->est_kt_count >= ipvs->est_max_threads && + ipvs->enable && ipvs->est_max_threads) + return -EINVAL; + + mutex_lock(&ipvs->est_mutex); + + for (i = 0; i < id; i++) { + if (!ipvs->est_kt_arr[i]) + break; + } + if (i >= id) { + arr = krealloc_array(ipvs->est_kt_arr, id + 1, + sizeof(struct ip_vs_est_kt_data *), + GFP_KERNEL); + if (!arr) + goto out; + ipvs->est_kt_arr = arr; + } else { + id = i; + } + + kd = kzalloc(sizeof(*kd), GFP_KERNEL); + if (!kd) + goto out; + kd->ipvs = ipvs; + bitmap_fill(kd->avail, IPVS_EST_NTICKS); + kd->est_timer = jiffies; + kd->id = id; + ip_vs_est_set_params(ipvs, kd); + + /* Pre-allocate stats used in calc phase */ + if (!id && !kd->calc_stats) { + kd->calc_stats = ip_vs_stats_alloc(); + if (!kd->calc_stats) + goto out; + } + + /* Start kthread tasks only when services are present */ + if (ipvs->enable) { + ret = ip_vs_est_kthread_start(ipvs, kd); + if (ret < 0) + goto out; + } + + if (arr) + ipvs->est_kt_count++; + ipvs->est_kt_arr[id] = kd; + kd = NULL; + /* Use most recent kthread for new ests */ + ipvs->est_add_ktid = id; + ret = 0; + +out: + mutex_unlock(&ipvs->est_mutex); + if (kd) { + ip_vs_stats_free(kd->calc_stats); + kfree(kd); + } + + return ret; +} + +/* Select ktid where to add new ests: available, unused or new slot */ +static void ip_vs_est_update_ktid(struct netns_ipvs *ipvs) +{ + int ktid, best = ipvs->est_kt_count; + struct ip_vs_est_kt_data *kd; + + for (ktid = 0; ktid < ipvs->est_kt_count; ktid++) { + kd = ipvs->est_kt_arr[ktid]; + if (kd) { + if (kd->est_count < kd->est_max_count) { + best = ktid; + break; + } + } else if (ktid < best) { + best = ktid; + } + } + ipvs->est_add_ktid = best; +} + +/* Add estimator to current kthread (est_add_ktid) */ +static int ip_vs_enqueue_estimator(struct netns_ipvs *ipvs, + struct ip_vs_estimator *est) +{ + struct ip_vs_est_kt_data *kd = NULL; + struct ip_vs_est_tick_data *td; + int ktid, row, crow, cid, ret; + int delay = est->ktrow; + + BUILD_BUG_ON_MSG(IPVS_EST_TICK_CHAINS > 127, + "Too many chains for ktcid"); + + if (ipvs->est_add_ktid < ipvs->est_kt_count) { + kd = ipvs->est_kt_arr[ipvs->est_add_ktid]; + if (kd) + goto add_est; + } + + ret = ip_vs_est_add_kthread(ipvs); + if (ret < 0) + goto out; + kd = ipvs->est_kt_arr[ipvs->est_add_ktid]; + +add_est: + ktid = kd->id; + /* For small number of estimators prefer to use few ticks, + * otherwise try to add into the last estimated row. + * est_row and add_row point after the row we should use + */ + if (kd->est_count >= 2 * kd->tick_max || delay < IPVS_EST_NTICKS - 1) + crow = READ_ONCE(kd->est_row); + else + crow = kd->add_row; + crow += delay; + if (crow >= IPVS_EST_NTICKS) + crow -= IPVS_EST_NTICKS; + /* Assume initial delay ? */ + if (delay >= IPVS_EST_NTICKS - 1) { + /* Preserve initial delay or decrease it if no space in tick */ + row = crow; + if (crow < IPVS_EST_NTICKS - 1) { + crow++; + row = find_last_bit(kd->avail, crow); + } + if (row >= crow) + row = find_last_bit(kd->avail, IPVS_EST_NTICKS); + } else { + /* Preserve delay or increase it if no space in tick */ + row = IPVS_EST_NTICKS; + if (crow > 0) + row = find_next_bit(kd->avail, IPVS_EST_NTICKS, crow); + if (row >= IPVS_EST_NTICKS) + row = find_first_bit(kd->avail, IPVS_EST_NTICKS); + } + + td = rcu_dereference_protected(kd->ticks[row], 1); + if (!td) { + td = kzalloc(sizeof(*td), GFP_KERNEL); + if (!td) { + ret = -ENOMEM; + goto out; + } + rcu_assign_pointer(kd->ticks[row], td); + } + + cid = find_first_zero_bit(td->full, IPVS_EST_TICK_CHAINS); + + kd->est_count++; + kd->tick_len[row]++; + if (!td->chain_len[cid]) + __set_bit(cid, td->present); + td->chain_len[cid]++; + est->ktid = ktid; + est->ktrow = row; + est->ktcid = cid; + hlist_add_head_rcu(&est->list, &td->chains[cid]); + + if (td->chain_len[cid] >= kd->chain_max) { + __set_bit(cid, td->full); + if (kd->tick_len[row] >= kd->tick_max) + __clear_bit(row, kd->avail); + } + + /* Update est_add_ktid to point to first available/empty kt slot */ + if (kd->est_count == kd->est_max_count) + ip_vs_est_update_ktid(ipvs); + + ret = 0; + +out: + return ret; +} - INIT_LIST_HEAD(&est->list); +/* Start estimation for stats */ +int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) +{ + struct ip_vs_estimator *est = &stats->est; + int ret; + + if (!ipvs->est_max_threads && ipvs->enable) + ipvs->est_max_threads = IPVS_EST_CPU_KTHREADS * + num_possible_cpus(); + + est->ktid = -1; + est->ktrow = IPVS_EST_NTICKS - 1; /* Initial delay */ + + /* We prefer this code to be short, kthread 0 will requeue the + * estimator to available chain. If tasks are disabled, we + * will not allocate much memory, just for kt 0. + */ + ret = 0; + if (!ipvs->est_kt_count || !ipvs->est_kt_arr[0]) + ret = ip_vs_est_add_kthread(ipvs); + if (ret >= 0) + hlist_add_head(&est->list, &ipvs->est_temp_list); + else + INIT_HLIST_NODE(&est->list); + return ret; +} - spin_lock_bh(&ipvs->est_lock); - list_add(&est->list, &ipvs->est_list); - spin_unlock_bh(&ipvs->est_lock); +static void ip_vs_est_kthread_destroy(struct ip_vs_est_kt_data *kd) +{ + if (kd) { + if (kd->task) { + pr_info("stop unused estimator thread %d...\n", kd->id); + kthread_stop(kd->task); + } + ip_vs_stats_free(kd->calc_stats); + kfree(kd); + } } +/* Unlink estimator from chain */ void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { struct ip_vs_estimator *est = &stats->est; + struct ip_vs_est_tick_data *td; + struct ip_vs_est_kt_data *kd; + int ktid = est->ktid; + int row = est->ktrow; + int cid = est->ktcid; + + /* Failed to add to chain ? */ + if (hlist_unhashed(&est->list)) + return; + + /* On return, estimator can be freed, dequeue it now */ + + /* In est_temp_list ? */ + if (ktid < 0) { + hlist_del(&est->list); + goto end_kt0; + } + + hlist_del_rcu(&est->list); + kd = ipvs->est_kt_arr[ktid]; + td = rcu_dereference_protected(kd->ticks[row], 1); + __clear_bit(cid, td->full); + td->chain_len[cid]--; + if (!td->chain_len[cid]) + __clear_bit(cid, td->present); + kd->tick_len[row]--; + __set_bit(row, kd->avail); + if (!kd->tick_len[row]) { + RCU_INIT_POINTER(kd->ticks[row], NULL); + kfree_rcu(td); + } + kd->est_count--; + if (kd->est_count) { + /* This kt slot can become available just now, prefer it */ + if (ktid < ipvs->est_add_ktid) + ipvs->est_add_ktid = ktid; + return; + } - spin_lock_bh(&ipvs->est_lock); - list_del(&est->list); - spin_unlock_bh(&ipvs->est_lock); + if (ktid > 0) { + mutex_lock(&ipvs->est_mutex); + ip_vs_est_kthread_destroy(kd); + ipvs->est_kt_arr[ktid] = NULL; + if (ktid == ipvs->est_kt_count - 1) { + ipvs->est_kt_count--; + while (ipvs->est_kt_count > 1 && + !ipvs->est_kt_arr[ipvs->est_kt_count - 1]) + ipvs->est_kt_count--; + } + mutex_unlock(&ipvs->est_mutex); + + /* This slot is now empty, prefer another available kt slot */ + if (ktid == ipvs->est_add_ktid) + ip_vs_est_update_ktid(ipvs); + } + +end_kt0: + /* kt 0 is freed after all other kthreads and chains are empty */ + if (ipvs->est_kt_count == 1 && hlist_empty(&ipvs->est_temp_list)) { + kd = ipvs->est_kt_arr[0]; + if (!kd || !kd->est_count) { + mutex_lock(&ipvs->est_mutex); + if (kd) { + ip_vs_est_kthread_destroy(kd); + ipvs->est_kt_arr[0] = NULL; + } + ipvs->est_kt_count--; + mutex_unlock(&ipvs->est_mutex); + ipvs->est_add_ktid = 0; + } + } +} + +/* Register all ests from est_temp_list to kthreads */ +static void ip_vs_est_drain_temp_list(struct netns_ipvs *ipvs) +{ + struct ip_vs_estimator *est; + + while (1) { + int max = 16; + + mutex_lock(&__ip_vs_mutex); + + while (max-- > 0) { + est = hlist_entry_safe(ipvs->est_temp_list.first, + struct ip_vs_estimator, list); + if (est) { + if (kthread_should_stop()) + goto unlock; + hlist_del_init(&est->list); + if (ip_vs_enqueue_estimator(ipvs, est) >= 0) + continue; + est->ktid = -1; + hlist_add_head(&est->list, + &ipvs->est_temp_list); + /* Abort, some entries will not be estimated + * until next attempt + */ + } + goto unlock; + } + mutex_unlock(&__ip_vs_mutex); + cond_resched(); + } + +unlock: + mutex_unlock(&__ip_vs_mutex); +} + +/* Calculate limits for all kthreads */ +static int ip_vs_est_calc_limits(struct netns_ipvs *ipvs, int *chain_max) +{ + DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + struct ip_vs_est_kt_data *kd; + struct hlist_head chain; + struct ip_vs_stats *s; + int cache_factor = 4; + int i, loops, ntest; + s32 min_est = 0; + ktime_t t1, t2; + s64 diff, val; + int max = 8; + int ret = 1; + + INIT_HLIST_HEAD(&chain); + mutex_lock(&__ip_vs_mutex); + kd = ipvs->est_kt_arr[0]; + mutex_unlock(&__ip_vs_mutex); + s = kd ? kd->calc_stats : NULL; + if (!s) + goto out; + hlist_add_head(&s->est.list, &chain); + + loops = 1; + /* Get best result from many tests */ + for (ntest = 0; ntest < 12; ntest++) { + if (!(ntest & 3)) { + /* Wait for cpufreq frequency transition */ + wait_event_idle_timeout(wq, kthread_should_stop(), + HZ / 50); + if (!ipvs->enable || kthread_should_stop()) + goto stop; + } + + local_bh_disable(); + rcu_read_lock(); + + /* Put stats in cache */ + ip_vs_chain_estimation(&chain); + + t1 = ktime_get(); + for (i = loops * cache_factor; i > 0; i--) + ip_vs_chain_estimation(&chain); + t2 = ktime_get(); + + rcu_read_unlock(); + local_bh_enable(); + + if (!ipvs->enable || kthread_should_stop()) + goto stop; + cond_resched(); + + diff = ktime_to_ns(ktime_sub(t2, t1)); + if (diff <= 1 * NSEC_PER_USEC) { + /* Do more loops on low time resolution */ + loops *= 2; + continue; + } + if (diff >= NSEC_PER_SEC) + continue; + val = diff; + do_div(val, loops); + if (!min_est || val < min_est) { + min_est = val; + /* goal: 95usec per chain */ + val = 95 * NSEC_PER_USEC; + if (val >= min_est) { + do_div(val, min_est); + max = (int)val; + } else { + max = 1; + } + } + } + +out: + if (s) + hlist_del_init(&s->est.list); + *chain_max = max; + return ret; + +stop: + ret = 0; + goto out; +} + +/* Calculate the parameters and apply them in context of kt #0 + * ECP: est_calc_phase + * ECM: est_chain_max + * ECP ECM Insert Chain enable Description + * --------------------------------------------------------------------------- + * 0 0 est_temp_list 0 create kt #0 context + * 0 0 est_temp_list 0->1 service added, start kthread #0 task + * 0->1 0 est_temp_list 1 kt task #0 started, enters calc phase + * 1 0 est_temp_list 1 kt #0: determine est_chain_max, + * stop tasks, move ests to est_temp_list + * and free kd for kthreads 1..last + * 1->0 0->N kt chains 1 ests can go to kthreads + * 0 N kt chains 1 drain est_temp_list, create new kthread + * contexts, start tasks, estimate + */ +static void ip_vs_est_calc_phase(struct netns_ipvs *ipvs) +{ + int genid = atomic_read(&ipvs->est_genid); + struct ip_vs_est_tick_data *td; + struct ip_vs_est_kt_data *kd; + struct ip_vs_estimator *est; + struct ip_vs_stats *stats; + int id, row, cid, delay; + bool last, last_td; + int chain_max; + int step; + + if (!ip_vs_est_calc_limits(ipvs, &chain_max)) + return; + + mutex_lock(&__ip_vs_mutex); + + /* Stop all other tasks, so that we can immediately move the + * estimators to est_temp_list without RCU grace period + */ + mutex_lock(&ipvs->est_mutex); + for (id = 1; id < ipvs->est_kt_count; id++) { + /* netns clean up started, abort */ + if (!ipvs->enable) + goto unlock2; + kd = ipvs->est_kt_arr[id]; + if (!kd) + continue; + ip_vs_est_kthread_stop(kd); + } + mutex_unlock(&ipvs->est_mutex); + + /* Move all estimators to est_temp_list but carefully, + * all estimators and kthread data can be released while + * we reschedule. Even for kthread 0. + */ + step = 0; + + /* Order entries in est_temp_list in ascending delay, so now + * walk delay(desc), id(desc), cid(asc) + */ + delay = IPVS_EST_NTICKS; + +next_delay: + delay--; + if (delay < 0) + goto end_dequeue; + +last_kt: + /* Destroy contexts backwards */ + id = ipvs->est_kt_count; + +next_kt: + if (!ipvs->enable || kthread_should_stop()) + goto unlock; + id--; + if (id < 0) + goto next_delay; + kd = ipvs->est_kt_arr[id]; + if (!kd) + goto next_kt; + /* kt 0 can exist with empty chains */ + if (!id && kd->est_count <= 1) + goto next_delay; + + row = kd->est_row + delay; + if (row >= IPVS_EST_NTICKS) + row -= IPVS_EST_NTICKS; + td = rcu_dereference_protected(kd->ticks[row], 1); + if (!td) + goto next_kt; + + cid = 0; + +walk_chain: + if (kthread_should_stop()) + goto unlock; + step++; + if (!(step & 63)) { + /* Give chance estimators to be added (to est_temp_list) + * and deleted (releasing kthread contexts) + */ + mutex_unlock(&__ip_vs_mutex); + cond_resched(); + mutex_lock(&__ip_vs_mutex); + + /* Current kt released ? */ + if (id >= ipvs->est_kt_count) + goto last_kt; + if (kd != ipvs->est_kt_arr[id]) + goto next_kt; + /* Current td released ? */ + if (td != rcu_dereference_protected(kd->ticks[row], 1)) + goto next_kt; + /* No fatal changes on the current kd and td */ + } + est = hlist_entry_safe(td->chains[cid].first, struct ip_vs_estimator, + list); + if (!est) { + cid++; + if (cid >= IPVS_EST_TICK_CHAINS) + goto next_kt; + goto walk_chain; + } + /* We can cheat and increase est_count to protect kt 0 context + * from release but we prefer to keep the last estimator + */ + last = kd->est_count <= 1; + /* Do not free kt #0 data */ + if (!id && last) + goto next_delay; + last_td = kd->tick_len[row] <= 1; + stats = container_of(est, struct ip_vs_stats, est); + ip_vs_stop_estimator(ipvs, stats); + /* Tasks are stopped, move without RCU grace period */ + est->ktid = -1; + est->ktrow = row - kd->est_row; + if (est->ktrow < 0) + est->ktrow += IPVS_EST_NTICKS; + hlist_add_head(&est->list, &ipvs->est_temp_list); + /* kd freed ? */ + if (last) + goto next_kt; + /* td freed ? */ + if (last_td) + goto next_kt; + goto walk_chain; + +end_dequeue: + /* All estimators removed while calculating ? */ + if (!ipvs->est_kt_count) + goto unlock; + kd = ipvs->est_kt_arr[0]; + if (!kd) + goto unlock; + kd->add_row = kd->est_row; + ipvs->est_chain_max = chain_max; + ip_vs_est_set_params(ipvs, kd); + + pr_info("using max %d ests per chain, %d per kthread\n", + kd->chain_max, kd->est_max_count); + + /* Try to keep tot_stats in kt0, enqueue it early */ + if (ipvs->tot_stats && !hlist_unhashed(&ipvs->tot_stats->s.est.list) && + ipvs->tot_stats->s.est.ktid == -1) { + hlist_del(&ipvs->tot_stats->s.est.list); + hlist_add_head(&ipvs->tot_stats->s.est.list, + &ipvs->est_temp_list); + } + + mutex_lock(&ipvs->est_mutex); + + /* We completed the calc phase, new calc phase not requested */ + if (genid == atomic_read(&ipvs->est_genid)) + ipvs->est_calc_phase = 0; + +unlock2: + mutex_unlock(&ipvs->est_mutex); + +unlock: + mutex_unlock(&__ip_vs_mutex); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) @@ -191,14 +920,25 @@ void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats) int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs) { - INIT_LIST_HEAD(&ipvs->est_list); - spin_lock_init(&ipvs->est_lock); - timer_setup(&ipvs->est_timer, estimation_timer, 0); - mod_timer(&ipvs->est_timer, jiffies + 2 * HZ); + INIT_HLIST_HEAD(&ipvs->est_temp_list); + ipvs->est_kt_arr = NULL; + ipvs->est_max_threads = 0; + ipvs->est_calc_phase = 0; + ipvs->est_chain_max = 0; + ipvs->est_kt_count = 0; + ipvs->est_add_ktid = 0; + atomic_set(&ipvs->est_genid, 0); + atomic_set(&ipvs->est_genid_done, 0); + __mutex_init(&ipvs->est_mutex, "ipvs->est_mutex", &__ipvs_est_key); return 0; } void __net_exit ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs) { - del_timer_sync(&ipvs->est_timer); + int i; + + for (i = 0; i < ipvs->est_kt_count; i++) + ip_vs_est_kthread_destroy(ipvs->est_kt_arr[i]); + kfree(ipvs->est_kt_arr); + mutex_destroy(&ipvs->est_mutex); } -- cgit v1.2.3 From f0be83d5421718ead31707b6ece34cf77d411c00 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:46:03 +0200 Subject: ipvs: add est_cpulist and est_nice sysctl vars Allow the kthreads for stats to be configured for specific cpulist (isolation) and niceness (scheduling priority). Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/ipvs-sysctl.rst | 20 +++++ include/net/ip_vs.h | 58 +++++++++++++ net/netfilter/ipvs/ip_vs_ctl.c | 143 ++++++++++++++++++++++++++++++- net/netfilter/ipvs/ip_vs_est.c | 12 ++- 4 files changed, 229 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 387fda80f05f..1b778705d706 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -129,6 +129,26 @@ drop_packet - INTEGER threshold. When the mode 3 is set, the always mode drop rate is controlled by the /proc/sys/net/ipv4/vs/am_droprate. +est_cpulist - CPULIST + Allowed CPUs for estimation kthreads + + Syntax: standard cpulist format + empty list - stop kthread tasks and estimation + default - the system's housekeeping CPUs for kthreads + + Example: + "all": all possible CPUs + "0-N": all possible CPUs, N denotes last CPU number + "0,1-N:1/2": first and all CPUs with odd number + "": empty list + +est_nice - INTEGER + default 0 + Valid range: -20 (more favorable) .. 19 (less favorable) + + Niceness value to use for the estimation kthreads (scheduling + priority) + expire_nodest_conn - BOOLEAN - 0 - disabled (default) - not 0 - enabled diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 04960dc6228f..dc51b5497cf7 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -29,6 +29,7 @@ #include #endif #include /* Netw namespace */ +#include #define IP_VS_HDR_INVERSE 1 #define IP_VS_HDR_ICMP 2 @@ -365,6 +366,9 @@ struct ip_vs_cpu_stats { struct u64_stats_sync syncp; }; +/* Default nice for estimator kthreads */ +#define IPVS_EST_NICE 0 + /* IPVS statistics objects */ struct ip_vs_estimator { struct hlist_node list; @@ -1009,6 +1013,12 @@ struct netns_ipvs { int sysctl_schedule_icmp; int sysctl_ignore_tunneled; int sysctl_run_estimation; +#ifdef CONFIG_SYSCTL + cpumask_var_t sysctl_est_cpulist; /* kthread cpumask */ + int est_cpulist_valid; /* cpulist set */ + int sysctl_est_nice; /* kthread nice */ + int est_stopped; /* stop tasks */ +#endif /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1162,6 +1172,19 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return ipvs->sysctl_run_estimation; } +static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +{ + if (ipvs->est_cpulist_valid) + return ipvs->sysctl_est_cpulist; + else + return housekeeping_cpumask(HK_TYPE_KTHREAD); +} + +static inline int sysctl_est_nice(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_est_nice; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1259,6 +1282,16 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs) return 1; } +static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) +{ + return housekeeping_cpumask(HK_TYPE_KTHREAD); +} + +static inline int sysctl_est_nice(struct netns_ipvs *ipvs) +{ + return IPVS_EST_NICE; +} + #endif /* IPVS core functions @@ -1569,6 +1602,31 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, struct ip_vs_est_kt_data *kd); void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); +static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs) +{ +#ifdef CONFIG_SYSCTL + ipvs->est_stopped = ipvs->est_cpulist_valid && + cpumask_empty(sysctl_est_cpulist(ipvs)); +#endif +} + +static inline bool ip_vs_est_stopped(struct netns_ipvs *ipvs) +{ +#ifdef CONFIG_SYSCTL + return ipvs->est_stopped; +#else + return false; +#endif +} + +static inline int ip_vs_est_max_threads(struct netns_ipvs *ipvs) +{ + unsigned int limit = IPVS_EST_CPU_KTHREADS * + cpumask_weight(sysctl_est_cpulist(ipvs)); + + return max(1U, limit); +} + /* Various IPVS packet transmitters (from ip_vs_xmit.c) */ int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c41a5392edc9..38df3ee655ed 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -263,7 +263,7 @@ static void est_reload_work_handler(struct work_struct *work) /* New config ? Stop kthread tasks */ if (genid != genid_done) ip_vs_est_kthread_stop(kd); - if (!kd->task) { + if (!kd->task && !ip_vs_est_stopped(ipvs)) { /* Do not start kthreads above 0 in calc phase */ if ((!id || !ipvs->est_calc_phase) && ip_vs_est_kthread_start(ipvs, kd) < 0) @@ -1940,6 +1940,122 @@ proc_do_sync_ports(struct ctl_table *table, int write, return rc; } +static int ipvs_proc_est_cpumask_set(struct ctl_table *table, void *buffer) +{ + struct netns_ipvs *ipvs = table->extra2; + cpumask_var_t *valp = table->data; + cpumask_var_t newmask; + int ret; + + if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) + return -ENOMEM; + + ret = cpulist_parse(buffer, newmask); + if (ret) + goto out; + + mutex_lock(&ipvs->est_mutex); + + if (!ipvs->est_cpulist_valid) { + if (!zalloc_cpumask_var(valp, GFP_KERNEL)) { + ret = -ENOMEM; + goto unlock; + } + ipvs->est_cpulist_valid = 1; + } + cpumask_and(newmask, newmask, ¤t->cpus_mask); + cpumask_copy(*valp, newmask); + /* est_max_threads may depend on cpulist size */ + ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); + ipvs->est_calc_phase = 1; + ip_vs_est_reload_start(ipvs); + +unlock: + mutex_unlock(&ipvs->est_mutex); + +out: + free_cpumask_var(newmask); + return ret; +} + +static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer, + size_t size) +{ + struct netns_ipvs *ipvs = table->extra2; + cpumask_var_t *valp = table->data; + struct cpumask *mask; + int ret; + + mutex_lock(&ipvs->est_mutex); + + if (ipvs->est_cpulist_valid) + mask = *valp; + else + mask = (struct cpumask *)housekeeping_cpumask(HK_TYPE_KTHREAD); + ret = scnprintf(buffer, size, "%*pbl\n", cpumask_pr_args(mask)); + + mutex_unlock(&ipvs->est_mutex); + + return ret; +} + +static int ipvs_proc_est_cpulist(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + + /* Ignore both read and write(append) if *ppos not 0 */ + if (*ppos || !*lenp) { + *lenp = 0; + return 0; + } + if (write) { + /* proc_sys_call_handler() appends terminator */ + ret = ipvs_proc_est_cpumask_set(table, buffer); + if (ret >= 0) + *ppos += *lenp; + } else { + /* proc_sys_call_handler() allocates 1 byte for terminator */ + ret = ipvs_proc_est_cpumask_get(table, buffer, *lenp + 1); + if (ret >= 0) { + *lenp = ret; + *ppos += *lenp; + ret = 0; + } + } + return ret; +} + +static int ipvs_proc_est_nice(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct netns_ipvs *ipvs = table->extra2; + int *valp = table->data; + int val = *valp; + int ret; + + struct ctl_table tmp_table = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); + if (write && ret >= 0) { + if (val < MIN_NICE || val > MAX_NICE) { + ret = -EINVAL; + } else { + mutex_lock(&ipvs->est_mutex); + if (*valp != val) { + *valp = val; + ip_vs_est_reload_start(ipvs); + } + mutex_unlock(&ipvs->est_mutex); + } + } + return ret; +} + /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) * Do not change order or insert new entries without @@ -2116,6 +2232,18 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "est_cpulist", + .maxlen = NR_CPUS, /* unused */ + .mode = 0644, + .proc_handler = ipvs_proc_est_cpulist, + }, + { + .procname = "est_nice", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = ipvs_proc_est_nice, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -4134,6 +4262,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); INIT_DELAYED_WORK(&ipvs->expire_nodest_conn_work, expire_nodest_conn_handler); + ipvs->est_stopped = 0; if (!net_eq(net, &init_net)) { tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); @@ -4195,6 +4324,15 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; ipvs->sysctl_run_estimation = 1; tbl[idx++].data = &ipvs->sysctl_run_estimation; + + ipvs->est_cpulist_valid = 0; + tbl[idx].extra2 = ipvs; + tbl[idx++].data = &ipvs->sysctl_est_cpulist; + + ipvs->sysctl_est_nice = IPVS_EST_NICE; + tbl[idx].extra2 = ipvs; + tbl[idx++].data = &ipvs->sysctl_est_nice; + #ifdef CONFIG_IP_VS_DEBUG /* Global sysctls must be ro in non-init netns */ if (!net_eq(net, &init_net)) @@ -4234,6 +4372,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) unregister_net_sysctl_table(ipvs->sysctl_hdr); ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s); + if (ipvs->est_cpulist_valid) + free_cpumask_var(ipvs->sysctl_est_cpulist); + if (!net_eq(net, &init_net)) kfree(ipvs->sysctl_tbl); } diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 2fb6c097437c..e0f5f5da5b6d 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -57,6 +57,9 @@ - kthread contexts are created and attached to array - the kthread tasks are started when first service is added, before that the total stats are not estimated + - when configuration (cpulist/nice) is changed, the tasks are restarted + by work (est_reload_work) + - kthread tasks are stopped while the cpulist is empty - the kthread context holds lists with estimators (chains) which are processed every 2 seconds - as estimators can be added dynamically and in bursts, we try to spread @@ -229,6 +232,7 @@ void ip_vs_est_reload_start(struct netns_ipvs *ipvs) /* Ignore reloads before first service is added */ if (!ipvs->enable) return; + ip_vs_est_stopped_recalc(ipvs); /* Bump the kthread configuration genid */ atomic_inc(&ipvs->est_genid); queue_delayed_work(system_long_wq, &ipvs->est_reload_work, 0); @@ -259,6 +263,9 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, goto out; } + set_user_nice(kd->task, sysctl_est_nice(ipvs)); + set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); @@ -334,7 +341,7 @@ static int ip_vs_est_add_kthread(struct netns_ipvs *ipvs) } /* Start kthread tasks only when services are present */ - if (ipvs->enable) { + if (ipvs->enable && !ip_vs_est_stopped(ipvs)) { ret = ip_vs_est_kthread_start(ipvs, kd); if (ret < 0) goto out; @@ -478,8 +485,7 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) int ret; if (!ipvs->est_max_threads && ipvs->enable) - ipvs->est_max_threads = IPVS_EST_CPU_KTHREADS * - num_possible_cpus(); + ipvs->est_max_threads = ip_vs_est_max_threads(ipvs); est->ktid = -1; est->ktrow = IPVS_EST_NTICKS - 1; /* Initial delay */ -- cgit v1.2.3 From 144361c1949f227df9244302da02c258a363b674 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 22 Nov 2022 18:46:04 +0200 Subject: ipvs: run_estimation should control the kthread tasks Change the run_estimation flag to start/stop the kthread tasks. Signed-off-by: Julian Anastasov Cc: yunhong-cgl jiang Cc: "dust.li" Reviewed-by: Jiri Wiesner Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/ipvs-sysctl.rst | 4 ++-- include/net/ip_vs.h | 6 ++++-- net/netfilter/ipvs/ip_vs_ctl.c | 29 ++++++++++++++++++++++++++++- net/netfilter/ipvs/ip_vs_est.c | 2 +- 4 files changed, 35 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 1b778705d706..3fb5fa142eef 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -324,8 +324,8 @@ run_estimation - BOOLEAN 0 - disabled not 0 - enabled (default) - If disabled, the estimation will be stop, and you can't see - any update on speed estimation data. + If disabled, the estimation will be suspended and kthread tasks + stopped. You can always re-enable estimation by setting this value to 1. But be careful, the first estimation after re-enable is not diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index dc51b5497cf7..c6c61100d244 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1605,8 +1605,10 @@ void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd); static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs) { #ifdef CONFIG_SYSCTL - ipvs->est_stopped = ipvs->est_cpulist_valid && - cpumask_empty(sysctl_est_cpulist(ipvs)); + /* Stop tasks while cpulist is empty or if disabled with flag */ + ipvs->est_stopped = !sysctl_run_estimation(ipvs) || + (ipvs->est_cpulist_valid && + cpumask_empty(sysctl_est_cpulist(ipvs))); #endif } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 38df3ee655ed..c9f598505642 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2056,6 +2056,32 @@ static int ipvs_proc_est_nice(struct ctl_table *table, int write, return ret; } +static int ipvs_proc_run_estimation(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct netns_ipvs *ipvs = table->extra2; + int *valp = table->data; + int val = *valp; + int ret; + + struct ctl_table tmp_table = { + .data = &val, + .maxlen = sizeof(int), + .mode = table->mode, + }; + + ret = proc_dointvec(&tmp_table, write, buffer, lenp, ppos); + if (write && ret >= 0) { + mutex_lock(&ipvs->est_mutex); + if (*valp != val) { + *valp = val; + ip_vs_est_reload_start(ipvs); + } + mutex_unlock(&ipvs->est_mutex); + } + return ret; +} + /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) * Do not change order or insert new entries without @@ -2230,7 +2256,7 @@ static struct ctl_table vs_vars[] = { .procname = "run_estimation", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = ipvs_proc_run_estimation, }, { .procname = "est_cpulist", @@ -4323,6 +4349,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) tbl[idx++].data = &ipvs->sysctl_schedule_icmp; tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; ipvs->sysctl_run_estimation = 1; + tbl[idx].extra2 = ipvs; tbl[idx++].data = &ipvs->sysctl_run_estimation; ipvs->est_cpulist_valid = 0; diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index e0f5f5da5b6d..df56073bb282 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -212,7 +212,7 @@ static int ip_vs_estimation_kthread(void *data) kd->est_timer = now; } - if (sysctl_run_estimation(ipvs) && kd->tick_len[row]) + if (kd->tick_len[row]) ip_vs_tick_estimation(kd, row); row++; -- cgit v1.2.3 From b22bbdd17a5af2cc99cf42048970b9355dcbec8b Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Wed, 7 Dec 2022 13:35:54 +0200 Subject: uapi/linux/if_tun.h: Added new offload types for USO4/6. Added 2 additional offlloads for USO(IPv4 & IPv6). Separate offloads are required for Windows VM guests, g.e. Windows may set USO rx only for IPv4. Signed-off-by: Andrew Melnychenko Signed-off-by: David S. Miller --- include/uapi/linux/if_tun.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index b6d7b868f290..287cdc81c939 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -90,6 +90,8 @@ #define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */ #define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */ #define TUN_F_UFO 0x10 /* I can handle UFO packets */ +#define TUN_F_USO4 0x20 /* I can handle USO for IPv4 packets */ +#define TUN_F_USO6 0x40 /* I can handle USO for IPv6 packets */ /* Protocol info prepended to the packets (when IFF_NO_PI is not set) */ #define TUN_PKT_STRIP 0x0001 -- cgit v1.2.3 From 34061b348ae912b9783fae7fabae69d46977a036 Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Wed, 7 Dec 2022 13:35:56 +0200 Subject: uapi/linux/virtio_net.h: Added USO types. Added new GSO type for USO: VIRTIO_NET_HDR_GSO_UDP_L4. Feature VIRTIO_NET_F_HOST_USO allows to enable NETIF_F_GSO_UDP_L4. Separated VIRTIO_NET_F_GUEST_USO4 & VIRTIO_NET_F_GUEST_USO6 features required for Windows guests. Signed-off-by: Andrew Melnychenko Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 6cb842ea8979..b4062bed186a 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -57,6 +57,9 @@ * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ +#define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ +#define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */ +#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO in. */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -130,6 +133,7 @@ struct virtio_net_hdr_v1 { #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ +#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */ #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ __u8 gso_type; __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ -- cgit v1.2.3 From 860b7f27b8f78564ca5a2f607e0820b2d352a562 Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Wed, 7 Dec 2022 13:35:57 +0200 Subject: linux/virtio_net.h: Support USO offload in vnet header. Now, it's possible to convert USO vnet packets from/to skb. Added support for GSO_UDP_L4 offload. Signed-off-by: Andrew Melnychenko Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index a960de68ac69..bdf8de2cdd93 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -15,6 +15,7 @@ static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) case VIRTIO_NET_HDR_GSO_TCPV6: return protocol == cpu_to_be16(ETH_P_IPV6); case VIRTIO_NET_HDR_GSO_UDP: + case VIRTIO_NET_HDR_GSO_UDP_L4: return protocol == cpu_to_be16(ETH_P_IP) || protocol == cpu_to_be16(ETH_P_IPV6); default: @@ -31,6 +32,7 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: + case VIRTIO_NET_HDR_GSO_UDP_L4: skb->protocol = cpu_to_be16(ETH_P_IP); break; case VIRTIO_NET_HDR_GSO_TCPV6: @@ -69,6 +71,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, ip_proto = IPPROTO_UDP; thlen = sizeof(struct udphdr); break; + case VIRTIO_NET_HDR_GSO_UDP_L4: + gso_type = SKB_GSO_UDP_L4; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); + break; default: return -EINVAL; } @@ -182,6 +189,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP_L4) + hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) -- cgit v1.2.3 From ebddb1404900657b7f03a56ee4c34a9d218c4030 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 8 Dec 2022 11:56:12 -0500 Subject: net: move the nat function to nf_nat_ovs for ovs and tc There are two nat functions are nearly the same in both OVS and TC code, (ovs_)ct_nat_execute() and ovs_ct_nat/tcf_ct_act_nat(). This patch creates nf_nat_ovs.c under netfilter and moves them there then exports nf_ct_nat() so that it can be shared by both OVS and TC, and keeps the nat (type) check and nat flag update in OVS and TC's own place, as these parts are different between OVS and TC. Note that in OVS nat function it was using skb->protocol to get the proto as it already skips vlans in key_extract(), while it doesn't in TC, and TC has to call skb_protocol() to get proto. So in nf_ct_nat_execute(), we keep using skb_protocol() which works for both OVS and TC contrack. Signed-off-by: Xin Long Acked-by: Aaron Conole Acked-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/netfilter/nf_nat.h | 4 ++ net/netfilter/Kconfig | 3 + net/netfilter/Makefile | 1 + net/netfilter/nf_nat_ovs.c | 135 ++++++++++++++++++++++++++++++++++++++++ net/openvswitch/Kconfig | 1 + net/openvswitch/conntrack.c | 137 +++-------------------------------------- net/sched/Kconfig | 1 + net/sched/act_ct.c | 136 ++++------------------------------------ 8 files changed, 166 insertions(+), 252 deletions(-) create mode 100644 net/netfilter/nf_nat_ovs.c (limited to 'include') diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index e9eb01e99d2f..9877f064548a 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -104,6 +104,10 @@ unsigned int nf_nat_inet_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, bool commit); + static inline int nf_nat_initialized(const struct nf_conn *ct, enum nf_nat_manip_type manip) { diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0846bd75b1da..f71b41c7ce2f 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -459,6 +459,9 @@ config NF_NAT_REDIRECT config NF_NAT_MASQUERADE bool +config NF_NAT_OVS + bool + config NETFILTER_SYNPROXY tristate diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1d4db1943936..3754eb06fb41 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -59,6 +59,7 @@ obj-$(CONFIG_NF_LOG_SYSLOG) += nf_log_syslog.o obj-$(CONFIG_NF_NAT) += nf_nat.o nf_nat-$(CONFIG_NF_NAT_REDIRECT) += nf_nat_redirect.o nf_nat-$(CONFIG_NF_NAT_MASQUERADE) += nf_nat_masquerade.o +nf_nat-$(CONFIG_NF_NAT_OVS) += nf_nat_ovs.o ifeq ($(CONFIG_NF_NAT),m) nf_nat-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_nat_bpf.o diff --git a/net/netfilter/nf_nat_ovs.c b/net/netfilter/nf_nat_ovs.c new file mode 100644 index 000000000000..551abd2da614 --- /dev/null +++ b/net/netfilter/nf_nat_ovs.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Support nat functions for openvswitch and used by OVS and TC conntrack. */ + +#include + +/* Modelled after nf_nat_ipv[46]_fn(). + * range is only used for new, uninitialized NAT state. + * Returns either NF_ACCEPT or NF_DROP. + */ +static int nf_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, + enum nf_nat_manip_type maniptype) +{ + __be16 proto = skb_protocol(skb, true); + int hooknum, err = NF_ACCEPT; + + /* See HOOK2MANIP(). */ + if (maniptype == NF_NAT_MANIP_SRC) + hooknum = NF_INET_LOCAL_IN; /* Source NAT */ + else + hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + if (proto == htons(ETH_P_IP) && + ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + hooknum)) + err = NF_DROP; + goto out; + } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { + __be16 frag_off; + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + int hdrlen = ipv6_skip_exthdr(skb, + sizeof(struct ipv6hdr), + &nexthdr, &frag_off); + + if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { + if (!nf_nat_icmpv6_reply_translation(skb, ct, + ctinfo, + hooknum, + hdrlen)) + err = NF_DROP; + goto out; + } + } + /* Non-ICMP, fall thru to initialize if needed. */ + fallthrough; + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + /* Initialize according to the NAT action. */ + err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) + /* Action is set up to establish a new + * mapping. + */ + ? nf_nat_setup_info(ct, range, maniptype) + : nf_nat_alloc_null_binding(ct, hooknum); + if (err != NF_ACCEPT) + goto out; + } + break; + + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + break; + + default: + err = NF_DROP; + goto out; + } + + err = nf_nat_packet(ct, ctinfo, hooknum, skb); + if (err == NF_ACCEPT) + *action |= BIT(maniptype); +out: + return err; +} + +int nf_ct_nat(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, int *action, + const struct nf_nat_range2 *range, bool commit) +{ + enum nf_nat_manip_type maniptype; + int err, ct_action = *action; + + *action = 0; + + /* Add NAT extension if not confirmed yet. */ + if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) + return NF_DROP; /* Can't NAT. */ + + if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) && + (ctinfo != IP_CT_RELATED || commit)) { + /* NAT an established or related connection like before. */ + if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) + /* This is the REPLY direction for a connection + * for which NAT was applied in the forward + * direction. Do the reverse NAT. + */ + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; + else + maniptype = ct->status & IPS_SRC_NAT + ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; + } else if (ct_action & BIT(NF_NAT_MANIP_SRC)) { + maniptype = NF_NAT_MANIP_SRC; + } else if (ct_action & BIT(NF_NAT_MANIP_DST)) { + maniptype = NF_NAT_MANIP_DST; + } else { + return NF_ACCEPT; + } + + err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = nf_ct_nat_execute(skb, ct, ctinfo, action, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = nf_ct_nat_execute(skb, ct, ctinfo, action, NULL, + NF_NAT_MANIP_SRC); + } + } + return err; +} +EXPORT_SYMBOL_GPL(nf_ct_nat); diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 15bd287f5cbd..747d537a3f06 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -15,6 +15,7 @@ config OPENVSWITCH select NET_MPLS_GSO select DST_CACHE select NET_NSH + select NF_NAT_OVS if NF_NAT help Open vSwitch is a multilayer Ethernet switch targeted at virtualized environments. In addition to supporting a variety of features diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 58c9f0edc3c4..c8b137649ca4 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -726,144 +726,27 @@ static void ovs_nat_update_key(struct sw_flow_key *key, } } -/* Modelled after nf_nat_ipv[46]_fn(). - * range is only used for new, uninitialized NAT state. - * Returns either NF_ACCEPT or NF_DROP. - */ -static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype, struct sw_flow_key *key) -{ - int hooknum, err = NF_ACCEPT; - - /* See HOOK2MANIP(). */ - if (maniptype == NF_NAT_MANIP_SRC) - hooknum = NF_INET_LOCAL_IN; /* Source NAT */ - else - hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - if (IS_ENABLED(CONFIG_NF_NAT) && - skb->protocol == htons(ETH_P_IP) && - ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - hooknum)) - err = NF_DROP; - goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && - skb->protocol == htons(ETH_P_IPV6)) { - __be16 frag_off; - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - int hdrlen = ipv6_skip_exthdr(skb, - sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, - ctinfo, - hooknum, - hdrlen)) - err = NF_DROP; - goto out; - } - } - /* Non-ICMP, fall thru to initialize if needed. */ - fallthrough; - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - /* Initialize according to the NAT action. */ - err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) - /* Action is set up to establish a new - * mapping. - */ - ? nf_nat_setup_info(ct, range, maniptype) - : nf_nat_alloc_null_binding(ct, hooknum); - if (err != NF_ACCEPT) - goto out; - } - break; - - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - - default: - err = NF_DROP; - goto out; - } - - err = nf_nat_packet(ct, ctinfo, hooknum, skb); -out: - /* Update the flow key if NAT successful. */ - if (err == NF_ACCEPT) - ovs_nat_update_key(key, skb, maniptype); - - return err; -} - /* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, const struct ovs_conntrack_info *info, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - enum nf_nat_manip_type maniptype; - int err; + int err, action = 0; if (!(info->nat & OVS_CT_NAT)) return NF_ACCEPT; + if (info->nat & OVS_CT_SRC_NAT) + action |= BIT(NF_NAT_MANIP_SRC); + if (info->nat & OVS_CT_DST_NAT) + action |= BIT(NF_NAT_MANIP_DST); - /* Add NAT extension if not confirmed yet. */ - if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) - return NF_DROP; /* Can't NAT. */ + err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit); - /* Determine NAT type. - * Check if the NAT type can be deduced from the tracked connection. - * Make sure new expected connections (IP_CT_RELATED) are NATted only - * when committing. - */ - if (ctinfo != IP_CT_NEW && ct->status & IPS_NAT_MASK && - (ctinfo != IP_CT_RELATED || info->commit)) { - /* NAT an established or related connection like before. */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) - /* This is the REPLY direction for a connection - * for which NAT was applied in the forward - * direction. Do the reverse NAT. - */ - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; - else - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; - } else if (info->nat & OVS_CT_SRC_NAT) { - maniptype = NF_NAT_MANIP_SRC; - } else if (info->nat & OVS_CT_DST_NAT) { - maniptype = NF_NAT_MANIP_DST; - } else { - return NF_ACCEPT; /* Connection is not NATed. */ - } - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key); - - if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { - if (ct->status & IPS_SRC_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype, key); - } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { - err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, - NF_NAT_MANIP_SRC, key); - } - } + if (action & BIT(NF_NAT_MANIP_SRC)) + ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC); + if (action & BIT(NF_NAT_MANIP_DST)) + ovs_nat_update_key(key, skb, NF_NAT_MANIP_DST); return err; } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 4662a6ce8a7e..777d6b50505c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -977,6 +977,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_NAT_OVS if NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index eac4e07eb56b..0ca2bb8ed026 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -864,90 +864,6 @@ static void tcf_ct_params_free_rcu(struct rcu_head *head) tcf_ct_params_free(params); } -#if IS_ENABLED(CONFIG_NF_NAT) -/* Modelled after nf_nat_ipv[46]_fn(). - * range is only used for new, uninitialized NAT state. - * Returns either NF_ACCEPT or NF_DROP. - */ -static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype) -{ - __be16 proto = skb_protocol(skb, true); - int hooknum, err = NF_ACCEPT; - - /* See HOOK2MANIP(). */ - if (maniptype == NF_NAT_MANIP_SRC) - hooknum = NF_INET_LOCAL_IN; /* Source NAT */ - else - hooknum = NF_INET_LOCAL_OUT; /* Destination NAT */ - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - if (proto == htons(ETH_P_IP) && - ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - hooknum)) - err = NF_DROP; - goto out; - } else if (IS_ENABLED(CONFIG_IPV6) && proto == htons(ETH_P_IPV6)) { - __be16 frag_off; - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - int hdrlen = ipv6_skip_exthdr(skb, - sizeof(struct ipv6hdr), - &nexthdr, &frag_off); - - if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { - if (!nf_nat_icmpv6_reply_translation(skb, ct, - ctinfo, - hooknum, - hdrlen)) - err = NF_DROP; - goto out; - } - } - /* Non-ICMP, fall thru to initialize if needed. */ - fallthrough; - case IP_CT_NEW: - /* Seen it before? This can happen for loopback, retrans, - * or local packets. - */ - if (!nf_nat_initialized(ct, maniptype)) { - /* Initialize according to the NAT action. */ - err = (range && range->flags & NF_NAT_RANGE_MAP_IPS) - /* Action is set up to establish a new - * mapping. - */ - ? nf_nat_setup_info(ct, range, maniptype) - : nf_nat_alloc_null_binding(ct, hooknum); - if (err != NF_ACCEPT) - goto out; - } - break; - - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED_REPLY: - break; - - default: - err = NF_DROP; - goto out; - } - - err = nf_nat_packet(ct, ctinfo, hooknum, skb); -out: - if (err == NF_ACCEPT) { - if (maniptype == NF_NAT_MANIP_SRC) - tc_skb_cb(skb)->post_ct_snat = 1; - if (maniptype == NF_NAT_MANIP_DST) - tc_skb_cb(skb)->post_ct_dnat = 1; - } - return err; -} -#endif /* CONFIG_NF_NAT */ - static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) @@ -987,52 +903,22 @@ static int tcf_ct_act_nat(struct sk_buff *skb, bool commit) { #if IS_ENABLED(CONFIG_NF_NAT) - int err; - enum nf_nat_manip_type maniptype; + int err, action = 0; if (!(ct_action & TCA_CT_ACT_NAT)) return NF_ACCEPT; + if (ct_action & TCA_CT_ACT_NAT_SRC) + action |= BIT(NF_NAT_MANIP_SRC); + if (ct_action & TCA_CT_ACT_NAT_DST) + action |= BIT(NF_NAT_MANIP_DST); - /* Add NAT extension if not confirmed yet. */ - if (!nf_ct_is_confirmed(ct) && !nf_ct_nat_ext_add(ct)) - return NF_DROP; /* Can't NAT. */ - - if (ctinfo != IP_CT_NEW && (ct->status & IPS_NAT_MASK) && - (ctinfo != IP_CT_RELATED || commit)) { - /* NAT an established or related connection like before. */ - if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) - /* This is the REPLY direction for a connection - * for which NAT was applied in the forward - * direction. Do the reverse NAT. - */ - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_DST : NF_NAT_MANIP_SRC; - else - maniptype = ct->status & IPS_SRC_NAT - ? NF_NAT_MANIP_SRC : NF_NAT_MANIP_DST; - } else if (ct_action & TCA_CT_ACT_NAT_SRC) { - maniptype = NF_NAT_MANIP_SRC; - } else if (ct_action & TCA_CT_ACT_NAT_DST) { - maniptype = NF_NAT_MANIP_DST; - } else { - return NF_ACCEPT; - } + err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); + + if (action & BIT(NF_NAT_MANIP_SRC)) + tc_skb_cb(skb)->post_ct_snat = 1; + if (action & BIT(NF_NAT_MANIP_DST)) + tc_skb_cb(skb)->post_ct_dnat = 1; - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { - if (ct->status & IPS_SRC_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ct_nat_execute(skb, ct, ctinfo, range, - maniptype); - } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { - err = ct_nat_execute(skb, ct, ctinfo, NULL, - NF_NAT_MANIP_SRC); - } - } return err; #else return NF_ACCEPT; -- cgit v1.2.3 From 983055bf839745ec2812fc55cacd96888aa0d7a6 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 1 Dec 2022 02:46:54 +0900 Subject: USB: core: export usb_cache_string() usb_cache_string() can also be useful for the drivers so export it. Signed-off-by: Vincent Mailhol Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/all/20221130174658.29282-4-mailhol.vincent@wanadoo.fr Signed-off-by: Marc Kleine-Budde --- drivers/usb/core/message.c | 1 + drivers/usb/core/usb.h | 1 - include/linux/usb.h | 1 + 3 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 4d59d927ae3e..127fac1af676 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1037,6 +1037,7 @@ char *usb_cache_string(struct usb_device *udev, int index) } return smallbuf; } +EXPORT_SYMBOL_GPL(usb_cache_string); /* * usb_get_device_descriptor - (re)reads the device descriptor (usbcore) diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index 82538daac8b8..0eac7d4285d1 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -47,7 +47,6 @@ extern int usb_get_device_descriptor(struct usb_device *dev, extern int usb_set_isoch_delay(struct usb_device *dev); extern int usb_get_bos_descriptor(struct usb_device *dev); extern void usb_release_bos_descriptor(struct usb_device *dev); -extern char *usb_cache_string(struct usb_device *udev, int index); extern int usb_set_configuration(struct usb_device *dev, int configuration); extern int usb_choose_configuration(struct usb_device *udev); extern int usb_generic_driver_probe(struct usb_device *udev); diff --git a/include/linux/usb.h b/include/linux/usb.h index 9ff1ad4dfad1..d2d2f41052c0 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1829,6 +1829,7 @@ static inline int usb_get_ptm_status(struct usb_device *dev, void *data) extern int usb_string(struct usb_device *dev, int index, char *buf, size_t size); +extern char *usb_cache_string(struct usb_device *udev, int index); /* wrappers that also update important state inside usbcore */ extern int usb_clear_halt(struct usb_device *dev, int pipe); -- cgit v1.2.3 From 01d80532295cd359dc43e6bd71860d5515f84372 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 1 Dec 2022 02:46:55 +0900 Subject: net: devlink: add DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER As discussed in [1], abbreviating the bootloader to "bl" might not be well understood. Instead, a bootloader technically being a firmware, name it "fw.bootloader". Add a new macro to devlink.h to formalize this new info attribute name and update the documentation. [1] https://lore.kernel.org/netdev/20221128142723.2f826d20@kernel.org/ Suggested-by: Jakub Kicinski Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/all/20221130174658.29282-5-mailhol.vincent@wanadoo.fr Signed-off-by: Marc Kleine-Budde --- Documentation/networking/devlink/devlink-info.rst | 5 +++++ include/net/devlink.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/Documentation/networking/devlink/devlink-info.rst b/Documentation/networking/devlink/devlink-info.rst index 7572bf6de5c1..1242b0e6826b 100644 --- a/Documentation/networking/devlink/devlink-info.rst +++ b/Documentation/networking/devlink/devlink-info.rst @@ -198,6 +198,11 @@ fw.bundle_id Unique identifier of the entire firmware bundle. +fw.bootloader +------------- + +Version of the bootloader. + Future work =========== diff --git a/include/net/devlink.h b/include/net/devlink.h index 0f376a28b9c4..6a2e4f21779f 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -621,6 +621,8 @@ enum devlink_param_generic_id { #define DEVLINK_INFO_VERSION_GENERIC_FW_ROCE "fw.roce" /* Firmware bundle identifier */ #define DEVLINK_INFO_VERSION_GENERIC_FW_BUNDLE_ID "fw.bundle_id" +/* Bootloader */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER "fw.bootloader" /** * struct devlink_flash_update_params - Flash Update parameters -- cgit v1.2.3 From 3fff88186f047627bb128d65155f42517f8e448f Mon Sep 17 00:00:00 2001 From: Matthieu Baerts Date: Fri, 9 Dec 2022 16:28:08 -0800 Subject: mptcp: remove MPTCP 'ifdef' in TCP SYN cookies To ease the maintenance, it is often recommended to avoid having #ifdef preprocessor conditions. Here the section related to CONFIG_MPTCP was quite short but the next commit needs to add more code around. It is then cleaner to move specific MPTCP code to functions located in net/mptcp directory. Now that mptcp_subflow_request_sock_ops structure can be static, it can also be marked as "read only after init". Suggested-by: Paolo Abeni Reviewed-by: Mat Martineau Cc: stable@vger.kernel.org Signed-off-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 12 ++++++++++-- net/ipv4/syncookies.c | 7 +++---- net/mptcp/subflow.c | 12 +++++++++++- 3 files changed, 24 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 412479ebf5ad..3c5c68618fcc 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -97,8 +97,6 @@ struct mptcp_out_options { }; #ifdef CONFIG_MPTCP -extern struct request_sock_ops mptcp_subflow_request_sock_ops; - void mptcp_init(void); static inline bool sk_is_mptcp(const struct sock *sk) @@ -188,6 +186,9 @@ void mptcp_seq_show(struct seq_file *seq); int mptcp_subflow_init_cookie_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb); +struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener); __be32 mptcp_get_reset_option(const struct sk_buff *skb); @@ -274,6 +275,13 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req, return 0; /* TCP fallback */ } +static inline struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener) +{ + return NULL; +} + static inline __be32 mptcp_reset_option(const struct sk_buff *skb) { return htonl(0u); } #endif /* CONFIG_MPTCP */ diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 942d2dfa1115..26fb97d1d4d9 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -288,12 +288,11 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, struct tcp_request_sock *treq; struct request_sock *req; -#ifdef CONFIG_MPTCP if (sk_is_mptcp(sk)) - ops = &mptcp_subflow_request_sock_ops; -#endif + req = mptcp_subflow_reqsk_alloc(ops, sk, false); + else + req = inet_reqsk_alloc(ops, sk, false); - req = inet_reqsk_alloc(ops, sk, false); if (!req) return NULL; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 2159b5f9988f..3f670f2d5c5c 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -529,7 +529,7 @@ static int subflow_v6_rebuild_header(struct sock *sk) } #endif -struct request_sock_ops mptcp_subflow_request_sock_ops; +static struct request_sock_ops mptcp_subflow_request_sock_ops __ro_after_init; static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops __ro_after_init; static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -582,6 +582,16 @@ drop: } #endif +struct request_sock *mptcp_subflow_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener) +{ + ops = &mptcp_subflow_request_sock_ops; + + return inet_reqsk_alloc(ops, sk_listener, attach_listener); +} +EXPORT_SYMBOL(mptcp_subflow_reqsk_alloc); + /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, const struct mptcp_options_received *mp_opt) -- cgit v1.2.3 From c9209b269afd29c55b8be49916725ed469f8c5d9 Mon Sep 17 00:00:00 2001 From: Archie Pusaka Date: Thu, 6 Oct 2022 17:09:31 +0800 Subject: Bluetooth: btusb: Introduce generic USB reset On cmd_timeout with no reset_gpio, reset the USB port as a last resort. This patch changes the behavior of btusb_intel_cmd_timeout and btusb_rtl_cmd_timeout. Signed-off-by: Archie Pusaka Reviewed-by: Abhishek Pandit-Subedi Reviewed-by: Ying Hsu Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/btusb.c | 35 +++++++++++++++++++++++++---------- include/net/bluetooth/hci_core.h | 1 + 2 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 3b4ae7905fd4..a9e43425c35f 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -696,6 +696,28 @@ struct btusb_data { unsigned cmd_timeout_cnt; }; +static void btusb_reset(struct hci_dev *hdev) +{ + struct btusb_data *data; + int err; + + if (hdev->reset) { + hdev->reset(hdev); + return; + } + + data = hci_get_drvdata(hdev); + /* This is not an unbalanced PM reference since the device will reset */ + err = usb_autopm_get_interface(data->intf); + if (err) { + bt_dev_err(hdev, "Failed usb_autopm_get_interface: %d", err); + return; + } + + bt_dev_err(hdev, "Resetting usb device."); + usb_queue_reset_device(data->intf); +} + static void btusb_intel_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); @@ -705,7 +727,7 @@ static void btusb_intel_cmd_timeout(struct hci_dev *hdev) return; if (!reset_gpio) { - bt_dev_err(hdev, "No way to reset. Ignoring and continuing"); + btusb_reset(hdev); return; } @@ -736,7 +758,7 @@ static void btusb_rtl_cmd_timeout(struct hci_dev *hdev) return; if (!reset_gpio) { - bt_dev_err(hdev, "No gpio to reset Realtek device, ignoring"); + btusb_reset(hdev); return; } @@ -761,7 +783,6 @@ static void btusb_qca_cmd_timeout(struct hci_dev *hdev) { struct btusb_data *data = hci_get_drvdata(hdev); struct gpio_desc *reset_gpio = data->reset_gpio; - int err; if (++data->cmd_timeout_cnt < 5) return; @@ -787,13 +808,7 @@ static void btusb_qca_cmd_timeout(struct hci_dev *hdev) return; } - bt_dev_err(hdev, "Multiple cmd timeouts seen. Resetting usb device."); - /* This is not an unbalanced PM reference since the device will reset */ - err = usb_autopm_get_interface(data->intf); - if (!err) - usb_queue_reset_device(data->intf); - else - bt_dev_err(hdev, "Failed usb_autopm_get_interface with %d", err); + btusb_reset(hdev); } static inline void btusb_free_frags(struct btusb_data *data) diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c54bc71254af..55a40f5606c3 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -659,6 +659,7 @@ struct hci_dev { int (*set_diag)(struct hci_dev *hdev, bool enable); int (*set_bdaddr)(struct hci_dev *hdev, const bdaddr_t *bdaddr); void (*cmd_timeout)(struct hci_dev *hdev); + void (*reset)(struct hci_dev *hdev); bool (*wakeup)(struct hci_dev *hdev); int (*set_quality_report)(struct hci_dev *hdev, bool enable); int (*get_data_path_id)(struct hci_dev *hdev, __u8 *data_path); -- cgit v1.2.3 From 47c50853bb9c5c35bf5c3eb00b712310ec2969e2 Mon Sep 17 00:00:00 2001 From: Igor Skalkin Date: Mon, 24 Oct 2022 15:40:33 +0200 Subject: virtio_bt: Fix alignment in configuration struct The current version of the configuration structure has unaligned 16-bit fields, but according to the specification [1], access to the configuration space must be aligned. Add a second, aligned version of the configuration structure and a new feature bit indicating that this version is being used. [1] https://docs.oasis-open.org/virtio/virtio/v1.1/virtio-v1.1.pdf Signed-off-by: Igor Skalkin Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/virtio_bt.c | 16 +++++++++++++--- include/uapi/linux/virtio_bt.h | 8 ++++++++ 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 2bbeb65b1cd3..c570c45d1480 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -313,7 +313,12 @@ static int virtbt_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BT_F_VND_HCI)) { __u16 vendor; - virtio_cread(vdev, struct virtio_bt_config, vendor, &vendor); + if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2)) + virtio_cread(vdev, struct virtio_bt_config_v2, + vendor, &vendor); + else + virtio_cread(vdev, struct virtio_bt_config, + vendor, &vendor); switch (vendor) { case VIRTIO_BT_CONFIG_VENDOR_ZEPHYR: @@ -346,8 +351,12 @@ static int virtbt_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BT_F_MSFT_EXT)) { __u16 msft_opcode; - virtio_cread(vdev, struct virtio_bt_config, - msft_opcode, &msft_opcode); + if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2)) + virtio_cread(vdev, struct virtio_bt_config_v2, + msft_opcode, &msft_opcode); + else + virtio_cread(vdev, struct virtio_bt_config, + msft_opcode, &msft_opcode); hci_set_msft_opcode(hdev, msft_opcode); } @@ -402,6 +411,7 @@ static const unsigned int virtbt_features[] = { VIRTIO_BT_F_VND_HCI, VIRTIO_BT_F_MSFT_EXT, VIRTIO_BT_F_AOSP_EXT, + VIRTIO_BT_F_CONFIG_V2, }; static struct virtio_driver virtbt_driver = { diff --git a/include/uapi/linux/virtio_bt.h b/include/uapi/linux/virtio_bt.h index a7bd48daa9a9..af798f4c9680 100644 --- a/include/uapi/linux/virtio_bt.h +++ b/include/uapi/linux/virtio_bt.h @@ -9,6 +9,7 @@ #define VIRTIO_BT_F_VND_HCI 0 /* Indicates vendor command support */ #define VIRTIO_BT_F_MSFT_EXT 1 /* Indicates MSFT vendor support */ #define VIRTIO_BT_F_AOSP_EXT 2 /* Indicates AOSP vendor support */ +#define VIRTIO_BT_F_CONFIG_V2 3 /* Use second version configuration */ enum virtio_bt_config_type { VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, @@ -28,4 +29,11 @@ struct virtio_bt_config { __u16 msft_opcode; } __attribute__((packed)); +struct virtio_bt_config_v2 { + __u8 type; + __u8 alignment; + __u16 vendor; + __u16 msft_opcode; +}; + #endif /* _UAPI_LINUX_VIRTIO_BT_H */ -- cgit v1.2.3 From ad38e55e1c89384aecee1bb0425bf1bf21ec86fd Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 4 Nov 2022 22:13:00 +0100 Subject: Bluetooth: hci_event: Ignore reserved bits in LE Extended Adv Report Broadcom controllers present on Apple Silicon devices use the upper 8 bits of the event type in the LE Extended Advertising Report for the channel on which the frame has been received. These bits are reserved according to the Bluetooth spec anyway such that we can just drop them to ensure that the advertising results are parsed correctly. The following excerpt from a btmon trace shows a report received on channel 37 by these controllers: > HCI Event: LE Meta Event (0x3e) plen 55 LE Extended Advertising Report (0x0d) Num reports: 1 Entry 0 Event type: 0x2513 Props: 0x0013 Connectable Scannable Use legacy advertising PDUs Data status: Complete Reserved (0x2500) Legacy PDU Type: Reserved (0x2513) Address type: Public (0x00) Address: XX:XX:XX:XX:XX:XX (Shenzhen Jingxun Software [...]) Primary PHY: LE 1M Secondary PHY: No packets SID: no ADI field (0xff) TX power: 127 dBm RSSI: -76 dBm (0xb4) Periodic advertising interval: 0.00 msec (0x0000) Direct address type: Public (0x00) Direct address: 00:00:00:00:00:00 (OUI 00-00-00) Data length: 0x1d [...] Flags: 0x18 Simultaneous LE and BR/EDR (Controller) Simultaneous LE and BR/EDR (Host) Company: Harman International Industries, Inc. (87) Data: [...] Service Data (UUID 0xfddf): Name (complete): JBL Flip 5 Signed-off-by: Sven Peter Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 1 + net/bluetooth/hci_event.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 684f1cd28730..a035ff6055da 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2590,6 +2590,7 @@ struct hci_ev_le_conn_complete { #define LE_EXT_ADV_DIRECT_IND 0x0004 #define LE_EXT_ADV_SCAN_RSP 0x0008 #define LE_EXT_ADV_LEGACY_PDU 0x0010 +#define LE_EXT_ADV_EVT_TYPE_MASK 0x007f #define ADDR_LE_DEV_PUBLIC 0x00 #define ADDR_LE_DEV_RANDOM 0x01 diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index faca701bce2a..ade2628aae0d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6494,7 +6494,7 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, info->length)) break; - evt_type = __le16_to_cpu(info->type); + evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, -- cgit v1.2.3 From 392fca352c7a95e2828d49e7500e26d0c87ca265 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 4 Nov 2022 22:13:01 +0100 Subject: Bluetooth: Add quirk to disable extended scanning Broadcom 4377 controllers found in Apple x86 Macs with the T2 chip claim to support extended scanning when querying supported states, < HCI Command: LE Read Supported St.. (0x08|0x001c) plen 0 > HCI Event: Command Complete (0x0e) plen 12 LE Read Supported States (0x08|0x001c) ncmd 1 Status: Success (0x00) States: 0x000003ffffffffff [...] LE Set Extended Scan Parameters (Octet 37 - Bit 5) LE Set Extended Scan Enable (Octet 37 - Bit 6) [...] , but then fail to actually implement the extended scanning: < HCI Command: LE Set Extended Sca.. (0x08|0x0041) plen 8 Own address type: Random (0x01) Filter policy: Accept all advertisement (0x00) PHYs: 0x01 Entry 0: LE 1M Type: Active (0x01) Interval: 11.250 msec (0x0012) Window: 11.250 msec (0x0012) > HCI Event: Command Complete (0x0e) plen 4 LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1 Status: Unknown HCI Command (0x01) Signed-off-by: Sven Peter Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 10 ++++++++++ include/net/bluetooth/hci_core.h | 4 +++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a035ff6055da..4cf6bc363e4f 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -274,6 +274,16 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, + + /* + * When this quirk is set, the HCI_OP_LE_SET_EXT_SCAN_ENABLE command is + * disabled. This is required for some Broadcom controllers which + * erroneously claim to support extended scanning. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_EXT_SCAN, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 55a40f5606c3..1113d74e1f9f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1690,7 +1690,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ - ((dev)->commands[37] & 0x40)) + ((dev)->commands[37] & 0x40) && \ + !test_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &(dev)->quirks)) + /* Use ext create connection if command is supported */ #define use_ext_conn(dev) ((dev)->commands[37] & 0x80) -- cgit v1.2.3 From ffcb0a445ec2d5753751437706aa0a7ea8351099 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Fri, 4 Nov 2022 22:13:02 +0100 Subject: Bluetooth: Add quirk to disable MWS Transport Configuration Broadcom 4378/4387 controllers found in Apple Silicon Macs claim to support getting MWS Transport Layer Configuration, < HCI Command: Read Local Supported... (0x04|0x0002) plen 0 > HCI Event: Command Complete (0x0e) plen 68 Read Local Supported Commands (0x04|0x0002) ncmd 1 Status: Success (0x00) [...] Get MWS Transport Layer Configuration (Octet 30 - Bit 3)] [...] , but then don't actually allow the required command: > HCI Event: Command Complete (0x0e) plen 15 Get MWS Transport Layer Configuration (0x05|0x000c) ncmd 1 Status: Command Disallowed (0x0c) Number of transports: 0 Baud rate list: 0 entries 00 00 00 00 00 00 00 00 00 00 Signed-off-by: Sven Peter Signed-off-by: Luiz Augusto von Dentz --- include/net/bluetooth/hci.h | 10 ++++++++++ include/net/bluetooth/hci_core.h | 3 +++ net/bluetooth/hci_sync.c | 2 +- 3 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 4cf6bc363e4f..8d773b042c85 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -284,6 +284,16 @@ enum { * during the hdev->setup vendor callback. */ HCI_QUIRK_BROKEN_EXT_SCAN, + + /* + * When this quirk is set, the HCI_OP_GET_MWS_TRANSPORT_CONFIG command is + * disabled. This is required for some Broadcom controllers which + * erroneously claim to support MWS Transport Layer Configuration. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, }; /* HCI device flags */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 1113d74e1f9f..7254edfba4c9 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1720,6 +1720,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) +#define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ + (!test_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &(dev)->quirks))) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 4debe205d4af..9e2d7e4b850c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4279,7 +4279,7 @@ static int hci_read_local_pairing_opts_sync(struct hci_dev *hdev) /* Get MWS transport configuration if the HCI command is supported */ static int hci_get_mws_transport_config_sync(struct hci_dev *hdev) { - if (!(hdev->commands[30] & 0x08)) + if (!mws_transport_config_capable(hdev)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_GET_MWS_TRANSPORT_CONFIG, -- cgit v1.2.3 From d7b061b80ee6f91aa0b89daa3069802d7ea4c57f Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Mon, 12 Dec 2022 11:24:26 +0800 Subject: net: tso: inline tso_count_descs() tso_count_descs() is a small function doing simple calculation, and tso_count_descs() is used in fast path, so inline it to reduce the overhead of calls. Signed-off-by: Yunsheng Lin Link: https://lore.kernel.org/r/20221212032426.16050-1-linyunsheng@huawei.com Signed-off-by: Jakub Kicinski --- include/net/tso.h | 8 +++++++- net/core/tso.c | 8 -------- 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/net/tso.h b/include/net/tso.h index 62c98a9c60f1..e7e157ae0526 100644 --- a/include/net/tso.h +++ b/include/net/tso.h @@ -2,6 +2,7 @@ #ifndef _TSO_H #define _TSO_H +#include #include #define TSO_HEADER_SIZE 256 @@ -16,7 +17,12 @@ struct tso_t { u32 tcp_seq; }; -int tso_count_descs(const struct sk_buff *skb); +/* Calculate the worst case buffer count */ +static inline int tso_count_descs(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags; +} + void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso, int size, bool is_last); void tso_build_data(const struct sk_buff *skb, struct tso_t *tso, int size); diff --git a/net/core/tso.c b/net/core/tso.c index 4148f6d48953..e00796e3b146 100644 --- a/net/core/tso.c +++ b/net/core/tso.c @@ -5,14 +5,6 @@ #include #include -/* Calculate expected number of TX descriptors */ -int tso_count_descs(const struct sk_buff *skb) -{ - /* The Marvell Way */ - return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags; -} -EXPORT_SYMBOL(tso_count_descs); - void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso, int size, bool is_last) { -- cgit v1.2.3 From 8a321cf7becc6c065ae595b837b826a2a81036b9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 9 Dec 2022 10:21:38 -0500 Subject: net: add IFF_NO_ADDRCONF and use it in bonding to prevent ipv6 addrconf Currently, in bonding it reused the IFF_SLAVE flag and checked it in ipv6 addrconf to prevent ipv6 addrconf. However, it is not a proper flag to use for no ipv6 addrconf, for bonding it has to move IFF_SLAVE flag setting ahead of dev_open() in bond_enslave(). Also, IFF_MASTER/SLAVE are historical flags used in bonding and eql, as Jiri mentioned, the new devices like Team, Failover do not use this flag. So as Jiri suggested, this patch adds IFF_NO_ADDRCONF in priv_flags of the device to indicate no ipv6 addconf, and uses it in bonding and moves IFF_SLAVE flag setting back to its original place. Signed-off-by: Xin Long Signed-off-by: Jakub Kicinski --- drivers/net/bonding/bond_main.c | 18 +++++++++++++----- include/linux/netdevice.h | 3 ++- net/ipv6/addrconf.c | 4 ++-- 3 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4048876f842c..f7767afe116b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1632,13 +1632,19 @@ static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave, { struct netdev_lag_upper_info lag_upper_info; enum netdev_lag_tx_type type; + int err; type = bond_lag_tx_type(bond); lag_upper_info.tx_type = type; lag_upper_info.hash_type = bond_lag_hash_type(bond, type); - return netdev_master_upper_dev_link(slave->dev, bond->dev, slave, - &lag_upper_info, extack); + err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave, + &lag_upper_info, extack); + if (err) + return err; + + slave->dev->flags |= IFF_SLAVE; + return 0; } static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave) @@ -1950,8 +1956,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } } - /* set slave flag before open to prevent IPv6 addrconf */ - slave_dev->flags |= IFF_SLAVE; + /* set no_addrconf flag before open to prevent IPv6 addrconf */ + slave_dev->priv_flags |= IFF_NO_ADDRCONF; /* open the slave since the application closed it */ res = dev_open(slave_dev, extack); @@ -2254,7 +2260,7 @@ err_close: dev_close(slave_dev); err_restore_mac: - slave_dev->flags &= ~IFF_SLAVE; + slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; if (!bond->params.fail_over_mac || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's @@ -2446,6 +2452,8 @@ static int __bond_release_one(struct net_device *bond_dev, /* close slave before restoring its mac address */ dev_close(slave_dev); + slave_dev->priv_flags &= ~IFF_NO_ADDRCONF; + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2287cb8eb9e4..aad12a179e54 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1662,6 +1662,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_NO_ADDRCONF: prevent ipv6 addrconf * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN @@ -1697,7 +1698,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, - /* was IFF_LIVE_RENAME_OK */ + IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9c3f5202a97b..c338dfb05d2c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3320,7 +3320,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) return; /* no link local addresses on devices flagged as slaves */ - if (idev->dev->flags & IFF_SLAVE) + if (idev->dev->priv_flags & IFF_NO_ADDRCONF) return; ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); @@ -3560,7 +3560,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (idev && idev->cnf.disable_ipv6) break; - if (dev->flags & IFF_SLAVE) { + if (dev->priv_flags & IFF_NO_ADDRCONF) { if (event == NETDEV_UP && !IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && dev->flags & IFF_MULTICAST) ipv6_mc_up(idev); -- cgit v1.2.3 From 6afaae6d12f54accf194e73ece617d1f456e438d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 10 Dec 2022 16:56:29 +0200 Subject: bridge: mcast: Allow user space to add (*, G) with a source list and filter mode Add new netlink attributes to the RTM_NEWMDB request that allow user space to add (*, G) with a source list and filter mode. The RTM_NEWMDB message can already dump such entries (created by the kernel) so there is no need to add dump support. However, the message contains a different set of attributes depending if it is a request or a response. The naming and structure of the new attributes try to follow the existing ones used in the response. Request: [ struct nlmsghdr ] [ struct br_port_msg ] [ MDBA_SET_ENTRY ] struct br_mdb_entry [ MDBA_SET_ENTRY_ATTRS ] [ MDBE_ATTR_SOURCE ] struct in_addr / struct in6_addr [ MDBE_ATTR_SRC_LIST ] // new [ MDBE_SRC_LIST_ENTRY ] [ MDBE_SRCATTR_ADDRESS ] struct in_addr / struct in6_addr [ ...] [ MDBE_ATTR_GROUP_MODE ] // new u8 Response: [ struct nlmsghdr ] [ struct br_port_msg ] [ MDBA_MDB ] [ MDBA_MDB_ENTRY ] [ MDBA_MDB_ENTRY_INFO ] struct br_mdb_entry [ MDBA_MDB_EATTR_TIMER ] u32 [ MDBA_MDB_EATTR_SOURCE ] struct in_addr / struct in6_addr [ MDBA_MDB_EATTR_RTPROT ] u8 [ MDBA_MDB_EATTR_SRC_LIST ] [ MDBA_MDB_SRCLIST_ENTRY ] [ MDBA_MDB_SRCATTR_ADDRESS ] struct in_addr / struct in6_addr [ MDBA_MDB_SRCATTR_TIMER ] u8 [...] [ MDBA_MDB_EATTR_GROUP_MODE ] u8 Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 20 +++++++ net/bridge/br_mdb.c | 130 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 150 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index a86a7e7b811f..0d9fe73fc48c 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -723,10 +723,30 @@ enum { enum { MDBE_ATTR_UNSPEC, MDBE_ATTR_SOURCE, + MDBE_ATTR_SRC_LIST, + MDBE_ATTR_GROUP_MODE, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) +/* per mdb entry source */ +enum { + MDBE_SRC_LIST_UNSPEC, + MDBE_SRC_LIST_ENTRY, + __MDBE_SRC_LIST_MAX, +}; +#define MDBE_SRC_LIST_MAX (__MDBE_SRC_LIST_MAX - 1) + +/* per mdb entry per source attributes + * these are embedded in MDBE_SRC_LIST_ENTRY + */ +enum { + MDBE_SRCATTR_UNSPEC, + MDBE_SRCATTR_ADDRESS, + __MDBE_SRCATTR_MAX, +}; +#define MDBE_SRCATTR_MAX (__MDBE_SRCATTR_MAX - 1) + /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */ enum { BRIDGE_XSTATS_UNSPEC, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e9a4b7e247e7..61d46b0a31b6 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -663,10 +663,25 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } +static const struct nla_policy +br_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { + [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), +}; + +static const struct nla_policy +br_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { + [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(br_mdbe_src_list_entry_pol), +}; + static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), + [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, + MCAST_INCLUDE), + [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), }; static bool is_valid_mdb_entry(struct br_mdb_entry *entry, @@ -1051,6 +1066,76 @@ static int __br_mdb_add(const struct br_mdb_config *cfg, return ret; } +static int br_mdb_config_src_entry_init(struct nlattr *src_entry, + struct br_mdb_src_entry *src, + __be16 proto, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, + br_mdbe_src_list_entry_pol, extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) + return -EINVAL; + + if (!is_valid_mdb_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) + return -EINVAL; + + src->addr.proto = proto; + nla_memcpy(&src->addr.src, tb[MDBE_SRCATTR_ADDRESS], + nla_len(tb[MDBE_SRCATTR_ADDRESS])); + + return 0; +} + +static int br_mdb_config_src_list_init(struct nlattr *src_list, + struct br_mdb_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nlattr *src_entry; + int rem, err; + int i = 0; + + nla_for_each_nested(src_entry, src_list, rem) + cfg->num_src_entries++; + + if (cfg->num_src_entries >= PG_SRC_ENT_LIMIT) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Exceeded maximum number of source entries (%u)", + PG_SRC_ENT_LIMIT - 1); + return -EINVAL; + } + + cfg->src_entries = kcalloc(cfg->num_src_entries, + sizeof(struct br_mdb_src_entry), GFP_KERNEL); + if (!cfg->src_entries) + return -ENOMEM; + + nla_for_each_nested(src_entry, src_list, rem) { + err = br_mdb_config_src_entry_init(src_entry, + &cfg->src_entries[i], + cfg->entry->addr.proto, + extack); + if (err) + goto err_src_entry_init; + i++; + } + + return 0; + +err_src_entry_init: + kfree(cfg->src_entries); + return err; +} + +static void br_mdb_config_src_list_fini(struct br_mdb_config *cfg) +{ + kfree(cfg->src_entries); +} + static int br_mdb_config_attrs_init(struct nlattr *set_attrs, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) @@ -1070,6 +1155,44 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, __mdb_entry_to_br_ip(cfg->entry, &cfg->group, mdb_attrs); + if (mdb_attrs[MDBE_ATTR_GROUP_MODE]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Filter mode cannot be set for host groups"); + return -EINVAL; + } + if (!br_multicast_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); + return -EINVAL; + } + cfg->filter_mode = nla_get_u8(mdb_attrs[MDBE_ATTR_GROUP_MODE]); + } else { + cfg->filter_mode = MCAST_EXCLUDE; + } + + if (mdb_attrs[MDBE_ATTR_SRC_LIST]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set for host groups"); + return -EINVAL; + } + if (!br_multicast_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); + return -EINVAL; + } + if (!mdb_attrs[MDBE_ATTR_GROUP_MODE]) { + NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); + return -EINVAL; + } + err = br_mdb_config_src_list_init(mdb_attrs[MDBE_ATTR_SRC_LIST], + cfg, extack); + if (err) + return err; + } + + if (!cfg->num_src_entries && cfg->filter_mode == MCAST_INCLUDE) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); + return -EINVAL; + } + return 0; } @@ -1162,6 +1285,11 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, return 0; } +static void br_mdb_config_fini(struct br_mdb_config *cfg) +{ + br_mdb_config_src_list_fini(cfg); +} + static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -1220,6 +1348,7 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, } out: + br_mdb_config_fini(&cfg); return err; } @@ -1295,6 +1424,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, err = __br_mdb_del(&cfg); } + br_mdb_config_fini(&cfg); return err; } -- cgit v1.2.3 From 1d7b66a7d9754c229d12c53ad6a1effe88c16ca4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 10 Dec 2022 16:56:30 +0200 Subject: bridge: mcast: Allow user space to specify MDB entry routing protocol Add the 'MDBE_ATTR_RTPORT' attribute to allow user space to specify the routing protocol of the MDB port group entry. Enforce a minimum value of 'RTPROT_STATIC' to prevent user space from using protocol values that should only be set by the kernel (e.g., 'RTPROT_KERNEL'). Maintain backward compatibility by defaulting to 'RTPROT_STATIC'. The protocol is already visible to user space in RTM_NEWMDB responses and notifications via the 'MDBA_MDB_EATTR_RTPROT' attribute. The routing protocol allows a routing daemon to distinguish between entries configured by it and those configured by the administrator. Once MDB flush is supported, the protocol can be used as a criterion according to which the flush is performed. Examples: # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 permanent proto kernel Error: integer out of range. # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 permanent proto static # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 src 192.0.2.1 permanent proto zebra # bridge mdb add dev br0 port dummy10 grp 239.1.1.2 permanent source_list 198.51.100.1,198.51.100.2 filter_mode include proto 250 # bridge -d mdb show dev br0 port dummy10 grp 239.1.1.2 src 198.51.100.2 permanent filter_mode include proto 250 dev br0 port dummy10 grp 239.1.1.2 src 198.51.100.1 permanent filter_mode include proto 250 dev br0 port dummy10 grp 239.1.1.2 permanent filter_mode include source_list 198.51.100.2/0.00,198.51.100.1/0.00 proto 250 dev br0 port dummy10 grp 239.1.1.1 src 192.0.2.1 permanent filter_mode include proto zebra dev br0 port dummy10 grp 239.1.1.1 permanent filter_mode exclude proto static Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_mdb.c | 15 +++++++++++++-- net/bridge/br_private.h | 1 + 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 0d9fe73fc48c..d9de241d90f9 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -725,6 +725,7 @@ enum { MDBE_ATTR_SOURCE, MDBE_ATTR_SRC_LIST, MDBE_ATTR_GROUP_MODE, + MDBE_ATTR_RTPROT, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 61d46b0a31b6..72d4e53193e5 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -682,6 +682,7 @@ static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), + [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; static bool is_valid_mdb_entry(struct br_mdb_entry *entry, @@ -823,7 +824,7 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - MCAST_INCLUDE, RTPROT_STATIC); + MCAST_INCLUDE, cfg->rt_protocol); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group"); return -ENOMEM; @@ -881,6 +882,7 @@ static int br_mdb_add_group_src_fwd(const struct br_mdb_config *cfg, sg_cfg.group = sg_ip; sg_cfg.src_entry = true; sg_cfg.filter_mode = MCAST_INCLUDE; + sg_cfg.rt_protocol = cfg->rt_protocol; return br_mdb_add_group_sg(&sg_cfg, sgmp, brmctx, flags, extack); } @@ -982,7 +984,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - cfg->filter_mode, RTPROT_STATIC); + cfg->filter_mode, cfg->rt_protocol); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group"); return -ENOMEM; @@ -1193,6 +1195,14 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, return -EINVAL; } + if (mdb_attrs[MDBE_ATTR_RTPROT]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be set for host groups"); + return -EINVAL; + } + cfg->rt_protocol = nla_get_u8(mdb_attrs[MDBE_ATTR_RTPROT]); + } + return 0; } @@ -1212,6 +1222,7 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, memset(cfg, 0, sizeof(*cfg)); cfg->filter_mode = MCAST_EXCLUDE; + cfg->rt_protocol = RTPROT_STATIC; bpm = nlmsg_data(nlh); if (!bpm->ifindex) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 368f5f6fa42b..cdc9e040f1f6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -106,6 +106,7 @@ struct br_mdb_config { u8 filter_mode; struct br_mdb_src_entry *src_entries; int num_src_entries; + u8 rt_protocol; }; #endif -- cgit v1.2.3 From 89300468e2b2ec216c7827ba04ac45c129794403 Mon Sep 17 00:00:00 2001 From: Coco Li Date: Sat, 10 Dec 2022 04:16:45 +0000 Subject: IPv6/GRO: generic helper to remove temporary HBH/jumbo header in driver IPv6/TCP and GRO stacks can build big TCP packets with an added temporary Hop By Hop header. Is GSO is not involved, then the temporary header needs to be removed in the driver. This patch provides a generic helper for drivers that need to modify their headers in place. Tested: Compiled and ran with ethtool -K eth1 tso off Could send Big TCP packets Signed-off-by: Coco Li Link: https://lore.kernel.org/r/20221210041646.3587757-1-lixiaoyan@google.com Signed-off-by: Jakub Kicinski --- include/net/ipv6.h | 33 +++++++++++++++++++++++++++++++++ net/ipv6/ip6_offload.c | 27 ++++----------------------- 2 files changed, 37 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d383c895592a..03f3af02a9a6 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -500,6 +500,39 @@ static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) return jhdr->nexthdr; } +/* Return 0 if HBH header is successfully removed + * Or if HBH removal is unnecessary (packet is not big TCP) + * Return error to indicate dropping the packet + */ +static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb) +{ + const int hophdr_len = sizeof(struct hop_jumbo_hdr); + int nexthdr = ipv6_has_hopopt_jumbo(skb); + struct ipv6hdr *h6; + + if (!nexthdr) + return 0; + + if (skb_cow_head(skb, 0)) + return -1; + + /* Remove the HBH header. + * Layout: [Ethernet header][IPv6 header][HBH][L4 Header] + */ + memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb), + skb_network_header(skb) - skb_mac_header(skb) + + sizeof(struct ipv6hdr)); + + __skb_pull(skb, hophdr_len); + skb->network_header += hophdr_len; + skb->mac_header += hophdr_len; + + h6 = ipv6_hdr(skb); + h6->nexthdr = nexthdr; + + return 0; +} + static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 3ee345672849..00dc2e3b0184 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; const struct net_offload *ops; - int proto, nexthdr; + int proto, err; struct frag_hdr *fptr; unsigned int payload_len; u8 *prevhdr; @@ -87,28 +87,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, bool gso_partial; skb_reset_network_header(skb); - nexthdr = ipv6_has_hopopt_jumbo(skb); - if (nexthdr) { - const int hophdr_len = sizeof(struct hop_jumbo_hdr); - int err; - - err = skb_cow_head(skb, 0); - if (err < 0) - return ERR_PTR(err); - - /* remove the HBH header. - * Layout: [Ethernet header][IPv6 header][HBH][TCP header] - */ - memmove(skb_mac_header(skb) + hophdr_len, - skb_mac_header(skb), - ETH_HLEN + sizeof(struct ipv6hdr)); - skb->data += hophdr_len; - skb->len -= hophdr_len; - skb->network_header += hophdr_len; - skb->mac_header += hophdr_len; - ipv6h = (struct ipv6hdr *)skb->data; - ipv6h->nexthdr = nexthdr; - } + err = ipv6_hopopt_jumbo_remove(skb); + if (err) + return ERR_PTR(err); nhoff = skb_network_header(skb) - skb_mac_header(skb); if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; -- cgit v1.2.3