Merge v6.18.45linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

12 files changed, 154 insertions, 88 deletions

diff --git a/include/net/act_api.h b/include/net/act_api.h
index a6d6f09dd0cd..1ef22d70553b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -270,6 +270,25 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
 struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
 					 struct tcf_chain *newchain);
 
+/* Range check for a control action supplied by user space.
+ *
+ * This is the same test tcf_action_check_ctrlact() applies to the primary
+ * control action, factored out for the *fallback* control actions
+ * (act_gact's TCA_GACT_PROB.paction and act_police's TCA_POLICE_RESULT),
+ * which must not reach tcf_action_check_ctrlact() because they have no
+ * goto_chain to allocate.  Without it, user space can store kernel-internal
+ * verdicts such as TC_ACT_CONSUMED, which is TC_ACT_VALUE_MAX + 1 and is
+ * deliberately not part of the UAPI value range.
+ */
+static inline bool tcf_action_valid(int action)
+{
+	int opcode = TC_ACT_EXT_OPCODE(action);
+
+	if (!opcode)
+		return action <= TC_ACT_VALUE_MAX;
+	return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC;
+}
+
 #ifdef CONFIG_INET
 DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
 #endif
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index a106e8d6bd6e..b353dea9aedc 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -399,8 +399,8 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev)
 
 	rcu_read_lock();
 	idev = rcu_dereference(dev->ip6_ptr);
-	if (idev)
-		refcount_inc(&idev->refcnt);
+	if (idev && !refcount_inc_not_zero(&idev->refcnt))
+		idev = NULL;
 	rcu_read_unlock();
 	return idev;
 }
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 17a97086b294..b65009a226e0 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -24,9 +24,7 @@
 #include <linux/netfilter.h>		/* for union nf_inet_addr */
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
-#include <net/route.h>
 #include <net/ipv6.h>
-#include <net/ip6_fib.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -738,10 +736,11 @@ struct ip_vs_dest {
 
 	/* connection counters and thresholds */
 	atomic_t		activeconns;	/* active connections */
-	atomic_t		inactconns;	/* inactive connections */
+	atomic_t		totalconns;	/* total connections */
 	atomic_t		persistconns;	/* persistent connections */
 	__u32			u_threshold;	/* upper threshold */
 	__u32			l_threshold;	/* lower threshold */
+	__u32			l_threshold_val;/* used lower threshold */
 
 	/* for destination cache */
 	spinlock_t		dst_lock;	/* lock of dst_cache */
@@ -1582,6 +1581,8 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
 		kfree(dest);
 }
 
+void ip_vs_dest_update_overload(struct ip_vs_dest *dest, int mode);
+
 /* IPVS sync daemon data and function prototypes
  * (from ip_vs_sync.c)
  */
@@ -1720,7 +1721,7 @@ static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
 
 void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
 		    struct ip_vs_conn *cp, int dir, unsigned int toff,
-		    bool has_ports);
+		    bool has_ports, struct ip_vs_iphdr *ciph);
 
 #ifdef CONFIG_IP_VS_IPV6
 void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
@@ -1753,30 +1754,23 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
 	return csum_partial(diff, sizeof(diff), oldsum);
 }
 
-static inline bool ip_vs_checksum_needed(struct sk_buff *skb, int af)
+static inline bool ip_vs_checksum_needed(struct sk_buff *skb)
 {
 	/* Checksum unnecessary or already validated? */
 	if (skb_csum_unnecessary(skb))
 		return false;
-	/* LOCAL_OUT ? */
-	if (!skb->dev || skb->dev->flags & IFF_LOOPBACK)
+	/* Locally generated ? */
+	if (!skb->dev)
 		return false;
-	/* !LOCAL_IN (FORWARD) ? */
-	if (af == AF_INET6) {
-		if (!(dst_rt6_info(skb_dst(skb))->rt6i_flags & RTF_LOCAL))
-			return false;
-	} else {
-		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
-			return false;
-	}
 	return true;
 }
 
 static inline bool ip_vs_checksum_common_check(struct sk_buff *skb,
 					       int offset, int proto, int af)
 {
-	if (!ip_vs_checksum_needed(skb, af))
+	if (!ip_vs_checksum_needed(skb))
 		return true;
+	/* Validate csum even for FORWARD */
 	return !nf_checksum(skb, NF_INET_LOCAL_IN, offset, proto, af);
 }
 
@@ -1887,14 +1881,21 @@ void ip_vs_unregister_hooks(struct netns_ipvs *ipvs, unsigned int af);
 static inline int
 ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
 {
-	/* We think the overhead of processing active connections is 256
+	/* We think the overhead of processing active connections is 257
 	 * times higher than that of inactive connections in average. (This
-	 * 256 times might not be accurate, we will change it later) We
+	 * 257 times might not be accurate, we will change it later) We
 	 * use the following formula to estimate the overhead now:
-	 *		  dest->activeconns*256 + dest->inactconns
+	 *		  dest->activeconns*256 + dest->totalconns
 	 */
 	return (atomic_read(&dest->activeconns) << 8) +
-		atomic_read(&dest->inactconns);
+		atomic_read(&dest->totalconns);
+}
+
+static inline int
+ip_vs_dest_inactconns(const struct ip_vs_dest *dest)
+{
+	return max(atomic_read(&dest->totalconns) -
+		   atomic_read(&dest->activeconns), 0);
 }
 
 #ifdef CONFIG_IP_VS_PROTO_TCP
diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h
index 481a7b28e6f2..23eb240d5ba7 100644
--- a/include/net/libeth/xsk.h
+++ b/include/net/libeth/xsk.h
@@ -205,7 +205,7 @@ __libeth_xsk_xmit_fill_buf_md(const struct xdp_desc *xdesc,
 	BUILD_BUG_ON(!__builtin_constant_p(tmo == libeth_xsktmo));
 	tmo = tmo == libeth_xsktmo ? &__libeth_xsktmo : tmo;
 
-	xsk_tx_metadata_request(ctx.meta, tmo, &desc);
+	xsk_tx_metadata_request(sq->pool, &ctx.meta, tmo, &desc);
 
 	return desc;
 }
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index cd00e0406cf4..feca25131930 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -14,6 +14,10 @@ struct netdev_config {
 	u8	hds_config;
 };
 
+struct netdev_queue_config {
+	u32	rx_page_size;
+};
+
 /* See the netdev.yaml spec for definition of each statistic */
 struct netdev_queue_stats_rx {
 	u64 bytes;
@@ -111,6 +115,11 @@ void netdev_stat_queue_sum(struct net_device *netdev,
 			   int tx_start, int tx_end,
 			   struct netdev_queue_stats_tx *tx_sum);
 
+enum {
+	/* The queue checks and honours the page size qcfg parameter */
+	QCFG_RX_PAGE_SIZE	= 0x1,
+};
+
 /**
  * struct netdev_queue_mgmt_ops - netdev ops for queue management
  *
@@ -130,25 +139,35 @@ void netdev_stat_queue_sum(struct net_device *netdev,
  * @ndo_queue_get_dma_dev: Get dma device for zero-copy operations to be used
  *			   for this queue. Return NULL on error.
  *
+ * @ndo_default_qcfg:	Populate queue config struct with defaults. Optional.
+ *
+ * @supported_params:	Bitmask of supported parameters, see QCFG_*.
+ *
  * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while
  * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only
  * be called for an interface which is open.
  */
 struct netdev_queue_mgmt_ops {
-	size_t			ndo_queue_mem_size;
-	int			(*ndo_queue_mem_alloc)(struct net_device *dev,
-						       void *per_queue_mem,
-						       int idx);
-	void			(*ndo_queue_mem_free)(struct net_device *dev,
-						      void *per_queue_mem);
-	int			(*ndo_queue_start)(struct net_device *dev,
-						   void *per_queue_mem,
-						   int idx);
-	int			(*ndo_queue_stop)(struct net_device *dev,
-						  void *per_queue_mem,
-						  int idx);
-	struct device *		(*ndo_queue_get_dma_dev)(struct net_device *dev,
-							 int idx);
+	size_t	ndo_queue_mem_size;
+	int	(*ndo_queue_mem_alloc)(struct net_device *dev,
+				       struct netdev_queue_config *qcfg,
+				       void *per_queue_mem,
+				       int idx);
+	void	(*ndo_queue_mem_free)(struct net_device *dev,
+				      void *per_queue_mem);
+	int	(*ndo_queue_start)(struct net_device *dev,
+				   struct netdev_queue_config *qcfg,
+				   void *per_queue_mem,
+				   int idx);
+	int	(*ndo_queue_stop)(struct net_device *dev,
+				  void *per_queue_mem,
+				  int idx);
+	void	(*ndo_default_qcfg)(struct net_device *dev,
+				    struct netdev_queue_config *qcfg);
+	struct device *	(*ndo_queue_get_dma_dev)(struct net_device *dev,
+						 int idx);
+
+	unsigned int supported_params;
 };
 
 bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx);
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 8cdcd138b33f..cfa72c485387 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -7,6 +7,7 @@
 #include <linux/sysfs.h>
 #include <net/xdp.h>
 #include <net/page_pool/types.h>
+#include <net/netdev_queues.h>
 
 /* This structure contains an instance of an RX queue. */
 struct netdev_rx_queue {
@@ -27,6 +28,7 @@ struct netdev_rx_queue {
 	struct xsk_buff_pool            *pool;
 #endif
 	struct napi_struct		*napi;
+	struct netdev_queue_config	qcfg;
 	struct pp_memory_provider_params mp_params;
 } ____cacheline_aligned_in_smp;
 
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index e9f72d2558e9..7c330caae52b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -141,6 +141,7 @@ struct flow_offload_tuple {
 	union {
 		struct {
 			struct dst_entry *dst_cache;
+			u32		ifidx;
 			u32		dst_cookie;
 		};
 		struct {
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index fb4f03ccd615..cdd95477af7a 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -161,6 +161,7 @@ struct memory_provider_ops;
 struct pp_memory_provider_params {
 	void *mp_priv;
 	const struct memory_provider_ops *mp_ops;
+	u32 rx_page_size;
 };
 
 struct page_pool {
diff --git a/include/net/route.h b/include/net/route.h
index f90106f383c5..45290177a33c 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -276,6 +276,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
 		       u32 table_id, struct fib_info *fi,
 		       int *fa_index, int fa_start, unsigned int flags);
 
+void fnhe_update_pmtu(struct fib_nh_exception *fnhe, u32 new, u32 orig);
+
 static inline void ip_rt_put(struct rtable *rt)
 {
 	/* dst_release() accepts a NULL parameter.
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 059eb6cb54f1..b15a0cdf101b 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -101,6 +101,7 @@ struct Qdisc {
 	struct hlist_node       hash;
 	u32			handle;
 	u32			parent;
+	int			depth;
 
 	struct netdev_queue	*dev_queue;
 
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 8a0967af8f0c..8bf17ba6c3bd 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -140,45 +140,16 @@ void __xsk_map_flush(struct list_head *flush_list);
 static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
 					    struct xsk_tx_metadata_compl *compl)
 {
-	if (!meta)
-		return;
+	compl->tx_timestamp = NULL;
 
-	if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
-		compl->tx_timestamp = &meta->completion.tx_timestamp;
-	else
-		compl->tx_timestamp = NULL;
-}
-
-/**
- *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
- *  and call appropriate xsk_tx_metadata_ops operation.
- *  @meta: pointer to AF_XDP metadata area
- *  @ops: pointer to struct xsk_tx_metadata_ops
- *  @priv: pointer to driver-private aread
- *
- *  This function should be called by the networking device when
- *  it prepares AF_XDP egress packet.
- */
-static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
-					   const struct xsk_tx_metadata_ops *ops,
-					   void *priv)
-{
 	if (!meta)
 		return;
 
-	if (ops->tmo_request_launch_time)
-		if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
-			ops->tmo_request_launch_time(meta->request.launch_time,
-						     priv);
-
-	if (ops->tmo_request_timestamp)
-		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
-			ops->tmo_request_timestamp(priv);
+	/* we can only arrive here if the completion timestamp has been
+	 * requested via XDP_TXMD_FLAGS_TIMESTAMP, see xsk_tx_metadata_request
+	 */
 
-	if (ops->tmo_request_checksum)
-		if (meta->flags & XDP_TXMD_FLAGS_CHECKSUM)
-			ops->tmo_request_checksum(meta->request.csum_start,
-						  meta->request.csum_offset, priv);
+	compl->tx_timestamp = &meta->completion.tx_timestamp;
 }
 
 /**
@@ -224,12 +195,6 @@ static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta,
 {
 }
 
-static inline void xsk_tx_metadata_request(struct xsk_tx_metadata *meta,
-					   const struct xsk_tx_metadata_ops *ops,
-					   void *priv)
-{
-}
-
 static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
 					    const struct xsk_tx_metadata_ops *ops,
 					    void *priv)
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index dd1d3a6e1b78..d74ca548d4d6 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -241,7 +241,7 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
  * details.
  *
  * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
- * pointer, if it is present and valid (initialized to %NULL otherwise).
+ * pointer, if it is present (initialized to %NULL otherwise).
  */
 static inline struct xdp_desc_ctx
 xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
@@ -256,24 +256,70 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
 	0)
 
 static inline bool
-xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta)
+xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
+			   const struct xsk_tx_metadata *meta, u64 *flags)
 {
-	return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
+	*flags = READ_ONCE(meta->flags);
+	if (*flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+		if (pool->tx_metadata_len <
+		    offsetofend(struct xsk_tx_metadata, request.launch_time))
+			return false;
+	return !(*flags & ~XDP_TXMD_FLAGS_VALID);
+}
+
+/**
+ *  xsk_tx_metadata_request - Evaluate AF_XDP TX metadata at submission
+ *  and call appropriate xsk_tx_metadata_ops operation.
+ *  @pool: pointer to AF_XDP buffer pool, used to validate the metadata
+ *  @pmeta: pointer to pointer to AF_XDP metadata area
+ *  @ops: pointer to struct xsk_tx_metadata_ops
+ *  @priv: pointer to driver-private area
+ *
+ *  This function should be called by the networking device when
+ *  it prepares AF_XDP egress packet.
+ */
+static inline void
+xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
+			struct xsk_tx_metadata **pmeta,
+			const struct xsk_tx_metadata_ops *ops, void *priv)
+{
+	const struct xsk_tx_metadata *meta = *pmeta;
+	u64 flags;
+
+	if (!meta)
+		return;
+
+	if (unlikely(!xsk_buff_valid_tx_metadata(pool, meta, &flags))) {
+		*pmeta = NULL;
+		return; /* no way to signal the error to the user */
+	}
+
+	if (ops->tmo_request_launch_time)
+		if (flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+			ops->tmo_request_launch_time(
+				READ_ONCE(meta->request.launch_time), priv);
+
+	if (ops->tmo_request_timestamp)
+		if (flags & XDP_TXMD_FLAGS_TIMESTAMP)
+			ops->tmo_request_timestamp(priv);
+
+	if (ops->tmo_request_checksum)
+		if (flags & XDP_TXMD_FLAGS_CHECKSUM)
+			ops->tmo_request_checksum(
+				READ_ONCE(meta->request.csum_start),
+				READ_ONCE(meta->request.csum_offset), priv);
+
+	if (!(flags & XDP_TXMD_FLAGS_TIMESTAMP))
+		*pmeta = NULL;
 }
 
 static inline struct xsk_tx_metadata *
 __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
 {
-	struct xsk_tx_metadata *meta;
-
 	if (!pool->tx_metadata_len)
 		return NULL;
 
-	meta = data - pool->tx_metadata_len;
-	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
-		return NULL; /* no way to signal the error to the user */
-
-	return meta;
+	return data - pool->tx_metadata_len;
 }
 
 static inline struct xsk_tx_metadata *
@@ -465,11 +511,20 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
 	return (struct xdp_desc_ctx){ };
 }
 
-static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
+static inline bool
+xsk_buff_valid_tx_metadata(const struct xsk_buff_pool *pool,
+			   const struct xsk_tx_metadata *meta, u64 *flags)
 {
 	return false;
 }
 
+static inline void
+xsk_tx_metadata_request(const struct xsk_buff_pool *pool,
+			struct xsk_tx_metadata **pmeta,
+			const struct xsk_tx_metadata_ops *ops, void *priv)
+{
+}
+
 static inline struct xsk_tx_metadata *
 __xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
 {