From 9630b585b607bd26f505d34620b14d75b9a5af7d Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Fri, 4 Nov 2022 19:04:59 +0300 Subject: drm/msm/gem: Prevent blocking within shrinker loop Consider this scenario: 1. APP1 continuously creates lots of small GEMs 2. APP2 triggers `drop_caches` 3. Shrinker starts to evict APP1 GEMs, while APP1 produces new purgeable GEMs 4. msm_gem_shrinker_scan() returns non-zero number of freed pages and causes shrinker to try shrink more 5. msm_gem_shrinker_scan() returns non-zero number of freed pages again, goto 4 6. The APP2 is blocked in `drop_caches` until APP1 stops producing purgeable GEMs To prevent this blocking scenario, check number of remaining pages that GPU shrinker couldn't release due to a GEM locking contention or shrinking rejection. If there are no remaining pages left to shrink, then there is no need to free up more pages and shrinker may break out from the loop. This problem was found during shrinker/madvise IOCTL testing of virtio-gpu driver. The MSM driver is affected in the same way. Reviewed-by: Rob Clark Reviewed-by: Thomas Zimmermann Fixes: b352ba54a820 ("drm/msm/gem: Convert to using drm_gem_lru") Signed-off-by: Dmitry Osipenko Link: https://lore.kernel.org/all/20230108210445.3948344-2-dmitry.osipenko@collabora.com/ --- include/drm/drm_gem.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index a17c2f903f81..b46ade812443 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -475,7 +475,9 @@ int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, void drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock); void drm_gem_lru_remove(struct drm_gem_object *obj); void drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj); -unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned nr_to_scan, +unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru, + unsigned int nr_to_scan, + unsigned long *remaining, bool (*shrink)(struct drm_gem_object *obj)); #endif /* __DRM_GEM_H__ */ -- cgit v1.2.3 From c28cd1f3433c7e339315d1ddacaeacf0fdfbe252 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Mar 2023 17:46:38 -0800 Subject: clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro We already mark fwnodes as initialized when they are registered as clock providers. We do this so that fw_devlink can tell when a clock driver doesn't use the driver core framework to probe/initialize its device. This ensures fw_devlink doesn't block the consumers of such a clock provider indefinitely. However, some users of CLK_OF_DECLARE() macros don't use the same node that matches the macro as the node for the clock provider, but they initialize the entire node. To cover these cases, also mark the nodes that match the macros as initialized when the init callback function is called. An example of this is "stericsson,u8500-clks" that's handled using CLK_OF_DECLARE() and looks something like this: clocks { compatible = "stericsson,u8500-clks"; prcmu_clk: prcmu-clock { #clock-cells = <1>; }; prcc_pclk: prcc-periph-clock { #clock-cells = <2>; }; prcc_kclk: prcc-kernel-clock { #clock-cells = <2>; }; prcc_reset: prcc-reset-controller { #reset-cells = <2>; }; ... }; This patch makes sure that "clocks" is marked as initialized so that fw_devlink knows that all nodes under it have been initialized. If the driver creates struct devices for some of the subnodes, fw_devlink is smart enough to know to wait for those devices to probe, so no special handling is required for those cases. Cc: Greg Kroah-Hartman Reported-by: Linus Walleij Link: https://lore.kernel.org/lkml/CACRpkdamxDX6EBVjKX5=D3rkHp17f5pwGdBVhzFU90-0MHY6dQ@mail.gmail.com/ Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230302014639.297514-1-saravanak@google.com Reviewed-by: Linus Walleij Tested-by: Linus Walleij Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..c9f5276006a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1363,7 +1363,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From 5adc409340b1fc82bc1175e602d14ac82ac685e3 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 1 Mar 2023 11:04:34 +0100 Subject: ACPI: x86: Introduce an acpi_quirk_skip_gpio_event_handlers() helper x86 ACPI boards which ship with only Android as their factory image usually have pretty broken ACPI tables, relying on everything being hardcoded in the factory kernel image and often disabling parts of the ACPI enumeration kernel code to avoid the broken tables causing issues. Part of this broken ACPI code is that sometimes these boards have _AEI ACPI GPIO event handlers which are broken. So far this has been dealt with in the platform/x86/x86-android-tablets.c module, which contains various workarounds for these devices, by it calling acpi_gpiochip_free_interrupts() on gpiochip-s with troublesome handlers to disable the handlers. But in some cases this is too late, if the handlers are of the edge type then gpiolib-acpi.c's code will already have run them at boot. This can cause issues such as GPIOs ending up as owned by "ACPI:OpRegion", making them unavailable for drivers which actually need them. Boards with these broken ACPI tables are already listed in drivers/acpi/x86/utils.c for e.g. acpi_quirk_skip_i2c_client_enumeration(). Extend the quirks mechanism for a new acpi_quirk_skip_gpio_event_handlers() helper, this re-uses the DMI-ids rather then having to duplicate the same DMI table in gpiolib-acpi.c . Also add the new ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS quirk to existing boards with troublesome ACPI gpio event handlers, so that the current acpi_gpiochip_free_interrupts() hack can be removed from x86-android-tablets.c . Signed-off-by: Hans de Goede Acked-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/x86/utils.c | 24 +++++++++++++++++++++--- drivers/gpio/gpiolib-acpi.c | 3 +++ include/acpi/acpi_bus.h | 5 +++++ 3 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index e45285d4e62a..4bf57cce30bb 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -251,6 +251,7 @@ bool force_storage_d3(void) #define ACPI_QUIRK_UART1_TTY_UART2_SKIP BIT(1) #define ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY BIT(2) #define ACPI_QUIRK_USE_ACPI_AC_AND_BATTERY BIT(3) +#define ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS BIT(4) static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { /* @@ -286,7 +287,8 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { }, .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | ACPI_QUIRK_UART1_TTY_UART2_SKIP | - ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), + ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY | + ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS), }, { .matches = { @@ -294,7 +296,8 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { DMI_MATCH(DMI_PRODUCT_NAME, "TF103C"), }, .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | - ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), + ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY | + ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS), }, { /* Lenovo Yoga Tablet 2 1050F/L */ @@ -336,7 +339,8 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M890BAP"), }, .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | - ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), + ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY | + ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS), }, { /* Whitelabel (sold as various brands) TM800A550L */ @@ -413,6 +417,20 @@ int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *s return 0; } EXPORT_SYMBOL_GPL(acpi_quirk_skip_serdev_enumeration); + +bool acpi_quirk_skip_gpio_event_handlers(void) +{ + const struct dmi_system_id *dmi_id; + long quirks; + + dmi_id = dmi_first_match(acpi_quirk_skip_dmi_ids); + if (!dmi_id) + return false; + + quirks = (unsigned long)dmi_id->driver_data; + return (quirks & ACPI_QUIRK_SKIP_GPIO_EVENT_HANDLERS); +} +EXPORT_SYMBOL_GPL(acpi_quirk_skip_gpio_event_handlers); #endif /* Lists of PMIC ACPI HIDs with an (often better) native charger driver */ diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index d8a421ce26a8..31ae0adbb295 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -536,6 +536,9 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + if (acpi_quirk_skip_gpio_event_handlers()) + return; + acpi_walk_resources(handle, METHOD_NAME__AEI, acpi_gpiochip_alloc_event, acpi_gpio); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 0584e9f6e339..57acb895c038 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -657,6 +657,7 @@ static inline bool acpi_quirk_skip_acpi_ac_and_battery(void) #if IS_ENABLED(CONFIG_X86_ANDROID_TABLETS) bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev); int acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip); +bool acpi_quirk_skip_gpio_event_handlers(void); #else static inline bool acpi_quirk_skip_i2c_client_enumeration(struct acpi_device *adev) { @@ -668,6 +669,10 @@ acpi_quirk_skip_serdev_enumeration(struct device *controller_parent, bool *skip) *skip = false; return 0; } +static inline bool acpi_quirk_skip_gpio_event_handlers(void) +{ + return false; +} #endif #ifdef CONFIG_PM -- cgit v1.2.3 From eb59eca0d8ac15f8c1b7f1cd35999455a90292c0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:31 +0100 Subject: interconnect: fix provider registration API The current interconnect provider interface is inherently racy as providers are expected to be added before being fully initialised. Specifically, nodes are currently not added and the provider data is not initialised until after registering the provider which can cause racing DT lookups to fail. Add a new provider API which will be used to fix up the interconnect drivers. The old API is reimplemented using the new interface and will be removed once all drivers have been fixed. Fixes: 11f1ceca7031 ("interconnect: Add generic on-chip interconnect API") Fixes: 87e3031b6fbd ("interconnect: Allow endpoints translation via DT") Cc: stable@vger.kernel.org # 5.1 Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Tested-by: Luca Ceresoli # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-4-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 52 +++++++++++++++++++++++++---------- include/linux/interconnect-provider.h | 12 ++++++++ 2 files changed, 50 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index cabb6f5df83e..7a24c1444ace 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1033,44 +1033,68 @@ int icc_nodes_remove(struct icc_provider *provider) EXPORT_SYMBOL_GPL(icc_nodes_remove); /** - * icc_provider_add() - add a new interconnect provider - * @provider: the interconnect provider that will be added into topology + * icc_provider_init() - initialize a new interconnect provider + * @provider: the interconnect provider to initialize + * + * Must be called before adding nodes to the provider. + */ +void icc_provider_init(struct icc_provider *provider) +{ + WARN_ON(!provider->set); + + INIT_LIST_HEAD(&provider->nodes); +} +EXPORT_SYMBOL_GPL(icc_provider_init); + +/** + * icc_provider_register() - register a new interconnect provider + * @provider: the interconnect provider to register * * Return: 0 on success, or an error code otherwise */ -int icc_provider_add(struct icc_provider *provider) +int icc_provider_register(struct icc_provider *provider) { - if (WARN_ON(!provider->set)) - return -EINVAL; if (WARN_ON(!provider->xlate && !provider->xlate_extended)) return -EINVAL; mutex_lock(&icc_lock); - - INIT_LIST_HEAD(&provider->nodes); list_add_tail(&provider->provider_list, &icc_providers); - mutex_unlock(&icc_lock); - dev_dbg(provider->dev, "interconnect provider added to topology\n"); + dev_dbg(provider->dev, "interconnect provider registered\n"); return 0; } -EXPORT_SYMBOL_GPL(icc_provider_add); +EXPORT_SYMBOL_GPL(icc_provider_register); /** - * icc_provider_del() - delete previously added interconnect provider - * @provider: the interconnect provider that will be removed from topology + * icc_provider_deregister() - deregister an interconnect provider + * @provider: the interconnect provider to deregister */ -void icc_provider_del(struct icc_provider *provider) +void icc_provider_deregister(struct icc_provider *provider) { mutex_lock(&icc_lock); WARN_ON(provider->users); - WARN_ON(!list_empty(&provider->nodes)); list_del(&provider->provider_list); mutex_unlock(&icc_lock); } +EXPORT_SYMBOL_GPL(icc_provider_deregister); + +int icc_provider_add(struct icc_provider *provider) +{ + icc_provider_init(provider); + + return icc_provider_register(provider); +} +EXPORT_SYMBOL_GPL(icc_provider_add); + +void icc_provider_del(struct icc_provider *provider) +{ + WARN_ON(!list_empty(&provider->nodes)); + + icc_provider_deregister(provider); +} EXPORT_SYMBOL_GPL(icc_provider_del); static const struct of_device_id __maybe_unused ignore_list[] = { diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index cd5c5a27557f..d12cd18aab3f 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -122,6 +122,9 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); +void icc_provider_init(struct icc_provider *provider); +int icc_provider_register(struct icc_provider *provider); +void icc_provider_deregister(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); @@ -167,6 +170,15 @@ static inline int icc_nodes_remove(struct icc_provider *provider) return -ENOTSUPP; } +static inline void icc_provider_init(struct icc_provider *provider) { } + +static inline int icc_provider_register(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + +static inline void icc_provider_deregister(struct icc_provider *provider) { } + static inline int icc_provider_add(struct icc_provider *provider) { return -ENOTSUPP; -- cgit v1.2.3 From 5cf9d015be160e2d90d29ae74ef1364390e8fce8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 8 Mar 2023 13:47:11 -0700 Subject: clk: Avoid invalid function names in CLK_OF_DECLARE() After commit c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro"), drivers/clk/mvebu/kirkwood.c fails to build: drivers/clk/mvebu/kirkwood.c:358:1: error: expected identifier or '(' CLK_OF_DECLARE(98dx1135_clk, "marvell,mv98dx1135-core-clock", ^ include/linux/clk-provider.h:1367:21: note: expanded from macro 'CLK_OF_DECLARE' static void __init name##_of_clk_init_declare(struct device_node *np) \ ^ :124:1: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ C function names must start with either an alphabetic letter or an underscore. To avoid generating invalid function names from clock names, add two underscores to the beginning of the identifier. Fixes: c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro") Suggested-by: Saravana Kannan Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230308-clk_of_declare-fix-v1-1-317b741e2532@kernel.org Reviewed-by: Saravana Kannan Reported-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c9f5276006a0..6f3175f0678a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1364,12 +1364,12 @@ struct clk_hw_onecell_data { }; #define CLK_OF_DECLARE(name, compat, fn) \ - static void __init name##_of_clk_init_declare(struct device_node *np) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ { \ fn(np); \ fwnode_dev_initialized(of_fwnode_handle(np), true); \ } \ - OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From 4b1a2c2a8e0ddcb89c5f6c5003bd9b53142f69e3 Mon Sep 17 00:00:00 2001 From: Lee Duncan Date: Wed, 28 Sep 2022 11:13:50 -0700 Subject: scsi: core: Add BLIST_NO_VPD_SIZE for some VDASD Some storage, such as AIX VDASD (virtual storage) and IBM 2076 (front end), fail as a result of commit c92a6b5d6335 ("scsi: core: Query VPD size before getting full page"). That commit changed getting SCSI VPD pages so that we now read just enough of the page to get the actual page size, then read the whole page in a second read. The problem is that the above mentioned hardware returns zero for the page size, because of a firmware error. In such cases, until the firmware is fixed, this new blacklist flag says to revert to the original method of reading the VPD pages, i.e. try to read a whole buffer's worth on the first try. [mkp: reworked somewhat] Fixes: c92a6b5d6335 ("scsi: core: Query VPD size before getting full page") Reported-by: Martin Wilck Suggested-by: Hannes Reinecke Signed-off-by: Lee Duncan Link: https://lore.kernel.org/r/20220928181350.9948-1-leeman.duncan@gmail.com Tested-by: Srikar Dronamraju Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi.c | 3 +++ drivers/scsi/scsi_devinfo.c | 3 ++- drivers/scsi/scsi_scan.c | 3 +++ include/scsi/scsi_device.h | 2 ++ include/scsi/scsi_devinfo.h | 6 +++--- 5 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 7d2210a006f0..5cce1ba70fc6 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -326,6 +326,9 @@ static int scsi_get_vpd_size(struct scsi_device *sdev, u8 page) unsigned char vpd_header[SCSI_VPD_HEADER_SIZE] __aligned(4); int result; + if (sdev->no_vpd_size) + return SCSI_DEFAULT_VPD_LEN; + /* * Fetch the VPD page header to find out how big the page * is. This is done to prevent problems on legacy devices diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index c7080454aea9..bc9d280417f6 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -134,7 +134,7 @@ static struct { {"3PARdata", "VV", NULL, BLIST_REPORTLUN2}, {"ADAPTEC", "AACRAID", NULL, BLIST_FORCELUN}, {"ADAPTEC", "Adaptec 5400S", NULL, BLIST_FORCELUN}, - {"AIX", "VDASD", NULL, BLIST_TRY_VPD_PAGES}, + {"AIX", "VDASD", NULL, BLIST_TRY_VPD_PAGES | BLIST_NO_VPD_SIZE}, {"AFT PRO", "-IX CF", "0.0>", BLIST_FORCELUN}, {"BELKIN", "USB 2 HS-CF", "1.95", BLIST_FORCELUN | BLIST_INQUIRY_36}, {"BROWNIE", "1200U3P", NULL, BLIST_NOREPORTLUN}, @@ -188,6 +188,7 @@ static struct { {"HPE", "OPEN-", "*", BLIST_REPORTLUN2 | BLIST_TRY_VPD_PAGES}, {"IBM", "AuSaV1S2", NULL, BLIST_FORCELUN}, {"IBM", "ProFibre 4000R", "*", BLIST_SPARSELUN | BLIST_LARGELUN}, + {"IBM", "2076", NULL, BLIST_NO_VPD_SIZE}, {"IBM", "2105", NULL, BLIST_RETRY_HWERROR}, {"iomega", "jaz 1GB", "J.86", BLIST_NOTQ | BLIST_NOLUN}, {"IOMEGA", "ZIP", NULL, BLIST_NOTQ | BLIST_NOLUN}, diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 4e842d79de31..d217be323cc6 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1057,6 +1057,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, else if (*bflags & BLIST_SKIP_VPD_PAGES) sdev->skip_vpd_pages = 1; + if (*bflags & BLIST_NO_VPD_SIZE) + sdev->no_vpd_size = 1; + transport_configure_device(&sdev->sdev_gendev); if (sdev->host->hostt->slave_configure) { diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index de310f21406c..f10a008e5bfa 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -145,6 +145,7 @@ struct scsi_device { const char * model; /* ... after scan; point to static string */ const char * rev; /* ... "nullnullnullnull" before scan */ +#define SCSI_DEFAULT_VPD_LEN 255 /* default SCSI VPD page size (max) */ struct scsi_vpd __rcu *vpd_pg0; struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; @@ -215,6 +216,7 @@ struct scsi_device { * creation time */ unsigned ignore_media_change:1; /* Ignore MEDIA CHANGE on resume */ unsigned silence_suspend:1; /* Do not print runtime PM related messages */ + unsigned no_vpd_size:1; /* No VPD size reported in header */ unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h index 5d14adae21c7..6b548dc2c496 100644 --- a/include/scsi/scsi_devinfo.h +++ b/include/scsi/scsi_devinfo.h @@ -32,7 +32,8 @@ #define BLIST_IGN_MEDIA_CHANGE ((__force blist_flags_t)(1ULL << 11)) /* do not do automatic start on add */ #define BLIST_NOSTARTONADD ((__force blist_flags_t)(1ULL << 12)) -#define __BLIST_UNUSED_13 ((__force blist_flags_t)(1ULL << 13)) +/* do not ask for VPD page size first on some broken targets */ +#define BLIST_NO_VPD_SIZE ((__force blist_flags_t)(1ULL << 13)) #define __BLIST_UNUSED_14 ((__force blist_flags_t)(1ULL << 14)) #define __BLIST_UNUSED_15 ((__force blist_flags_t)(1ULL << 15)) #define __BLIST_UNUSED_16 ((__force blist_flags_t)(1ULL << 16)) @@ -74,8 +75,7 @@ #define __BLIST_HIGH_UNUSED (~(__BLIST_LAST_USED | \ (__force blist_flags_t) \ ((__force __u64)__BLIST_LAST_USED - 1ULL))) -#define __BLIST_UNUSED_MASK (__BLIST_UNUSED_13 | \ - __BLIST_UNUSED_14 | \ +#define __BLIST_UNUSED_MASK (__BLIST_UNUSED_14 | \ __BLIST_UNUSED_15 | \ __BLIST_UNUSED_16 | \ __BLIST_UNUSED_24 | \ -- cgit v1.2.3 From fe9ae05cfbe587dda724fcf537c00bc2f287da62 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 8 Mar 2023 11:50:12 +0100 Subject: fbdev: Fix incorrect page mapping clearance at fb_deferred_io_release() The recent fix for the deferred I/O by the commit 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") caused a regression when the same fb device is opened/closed while it's being used. It resulted in a frozen screen even if something is redrawn there after the close. The breakage is because the patch was made under a wrong assumption of a single open; in the current code, fb_deferred_io_release() cleans up the page mapping of the pageref list and it calls cancel_delayed_work_sync() unconditionally, where both are no correct behavior for multiple opens. This patch adds a refcount for the opens of the device, and applies the cleanup only when all files get closed. As both fb_deferred_io_open() and _close() are called always in the fb_info lock (mutex), it's safe to use the normal int for the refcounting. Also, a useless BUG_ON() is dropped. Fixes: 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") Cc: Signed-off-by: Takashi Iwai Reviewed-by: Patrik Jakobsson Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230308105012.1845-1-tiwai@suse.de --- drivers/video/fbdev/core/fb_defio.c | 17 +++++++++++++---- include/linux/fb.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index 583cbcf09446..a3cf1f764f29 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -309,17 +309,18 @@ void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file) { + struct fb_deferred_io *fbdefio = info->fbdefio; + file->f_mapping->a_ops = &fb_deferred_io_aops; + fbdefio->open_count++; } EXPORT_SYMBOL_GPL(fb_deferred_io_open); -void fb_deferred_io_release(struct fb_info *info) +static void fb_deferred_io_lastclose(struct fb_info *info) { - struct fb_deferred_io *fbdefio = info->fbdefio; struct page *page; int i; - BUG_ON(!fbdefio); cancel_delayed_work_sync(&info->deferred_work); /* clear out the mapping that we setup */ @@ -328,13 +329,21 @@ void fb_deferred_io_release(struct fb_info *info) page->mapping = NULL; } } + +void fb_deferred_io_release(struct fb_info *info) +{ + struct fb_deferred_io *fbdefio = info->fbdefio; + + if (!--fbdefio->open_count) + fb_deferred_io_lastclose(info); +} EXPORT_SYMBOL_GPL(fb_deferred_io_release); void fb_deferred_io_cleanup(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; - fb_deferred_io_release(info); + fb_deferred_io_lastclose(info); kvfree(info->pagerefs); mutex_destroy(&fbdefio->lock); diff --git a/include/linux/fb.h b/include/linux/fb.h index 73eb1f85ea8e..05e40fcc7696 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -212,6 +212,7 @@ struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; bool sort_pagereflist; /* sort pagelist by offset */ + int open_count; /* number of opened files; protected by fb_info lock */ struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ -- cgit v1.2.3 From f85949f98206b3b11d92d695cea4efda6a81f00e Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Thu, 9 Mar 2023 13:25:27 +0100 Subject: xdp: add xdp_set_features_flag utility routine Introduce xdp_set_features_flag utility routine in order to update dynamically xdp_features according to the dynamic hw configuration via ethtool (e.g. changing number of hw rx/tx queues). Add xdp_clear_features_flag() in order to clear all xdp_feature flag. Reviewed-by: Shay Agroskin Signed-off-by: Lorenzo Bianconi Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 1 + include/net/xdp.h | 11 +++++++++++ include/uapi/linux/netdev.h | 2 ++ net/core/xdp.c | 26 +++++++++++++++++++------- tools/include/uapi/linux/netdev.h | 2 ++ 5 files changed, 35 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 24de747b5344..753e5914a8b7 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -9,6 +9,7 @@ definitions: - type: flags name: xdp-act + render-max: true entries: - name: basic diff --git a/include/net/xdp.h b/include/net/xdp.h index d517bfac937b..41c57b8b1671 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -428,12 +428,18 @@ MAX_XDP_METADATA_KFUNC, #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); +void xdp_set_features_flag(struct net_device *dev, xdp_features_t val); void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); void xdp_features_clear_redirect_target(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } +static inline void +xdp_set_features_flag(struct net_device *dev, xdp_features_t val) +{ +} + static inline void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) { @@ -445,4 +451,9 @@ xdp_features_clear_redirect_target(struct net_device *dev) } #endif +static inline void xdp_clear_features_flag(struct net_device *dev) +{ + xdp_set_features_flag(dev, 0); +} + #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 8c4e3e536c04..ed134fbdfd32 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -33,6 +33,8 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_HW_OFFLOAD = 16, NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + + NETDEV_XDP_ACT_MASK = 127, }; enum { diff --git a/net/core/xdp.c b/net/core/xdp.c index 8c92fc553317..87e654b7d06c 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -774,20 +774,32 @@ static int __init xdp_metadata_init(void) } late_initcall(xdp_metadata_init); -void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) +void xdp_set_features_flag(struct net_device *dev, xdp_features_t val) { - dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; - if (support_sg) - dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG; + val &= NETDEV_XDP_ACT_MASK; + if (dev->xdp_features == val) + return; + dev->xdp_features = val; call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); } +EXPORT_SYMBOL_GPL(xdp_set_features_flag); + +void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) +{ + xdp_features_t val = (dev->xdp_features | NETDEV_XDP_ACT_NDO_XMIT); + + if (support_sg) + val |= NETDEV_XDP_ACT_NDO_XMIT_SG; + xdp_set_features_flag(dev, val); +} EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); void xdp_features_clear_redirect_target(struct net_device *dev) { - dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT | - NETDEV_XDP_ACT_NDO_XMIT_SG); - call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); + xdp_features_t val = dev->xdp_features; + + val &= ~(NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG); + xdp_set_features_flag(dev, val); } EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 8c4e3e536c04..ed134fbdfd32 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -33,6 +33,8 @@ enum netdev_xdp_act { NETDEV_XDP_ACT_HW_OFFLOAD = 16, NETDEV_XDP_ACT_RX_SG = 32, NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + + NETDEV_XDP_ACT_MASK = 127, }; enum { -- cgit v1.2.3 From 47053904e18282af4525a02e3e0f519f014fc7f9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 24 Feb 2023 19:16:40 +0000 Subject: KVM: arm64: timers: Convert per-vcpu virtual offset to a global value Having a per-vcpu virtual offset is a pain. It needs to be synchronized on each update, and expands badly to a setup where different timers can have different offsets, or have composite offsets (as with NV). So let's start by replacing the use of the CNTVOFF_EL2 shadow register (which we want to reclaim for NV anyway), and make the virtual timer carry a pointer to a VM-wide offset. This simplifies the code significantly. It also addresses two terrible bugs: - The use of CNTVOFF_EL2 leads to some nice offset corruption when the sysreg gets reset, as reported by Joey. - The kvm mutex is taken from a vcpu ioctl, which goes against the locking rules... Reported-by: Joey Gouly Reviewed-by: Reiji Watanabe Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230224173915.GA17407@e124191.cambridge.arm.com Tested-by: Joey Gouly Link: https://lore.kernel.org/r/20230224191640.3396734-1-maz@kernel.org Signed-off-by: Oliver Upton --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/arch_timer.c | 45 +++++++++------------------------------ arch/arm64/kvm/hypercalls.c | 2 +- include/kvm/arm_arch_timer.h | 15 +++++++++++++ 4 files changed, 29 insertions(+), 36 deletions(-) (limited to 'include') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a1892a8f6032..bcd774d74f34 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -193,6 +193,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; + /* Timers */ + struct arch_timer_vm_data timer_data; + /* Mandated version of PSCI */ u32 psci_version; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 00610477ec7b..e1af4301b913 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -84,14 +84,10 @@ u64 timer_get_cval(struct arch_timer_context *ctxt) static u64 timer_get_offset(struct arch_timer_context *ctxt) { - struct kvm_vcpu *vcpu = ctxt->vcpu; + if (ctxt->offset.vm_offset) + return *ctxt->offset.vm_offset; - switch(arch_timer_ctx_index(ctxt)) { - case TIMER_VTIMER: - return __vcpu_sys_reg(vcpu, CNTVOFF_EL2); - default: - return 0; - } + return 0; } static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) @@ -128,15 +124,12 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval) static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) { - struct kvm_vcpu *vcpu = ctxt->vcpu; - - switch(arch_timer_ctx_index(ctxt)) { - case TIMER_VTIMER: - __vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset; - break; - default: + if (!ctxt->offset.vm_offset) { WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt)); + return; } + + WRITE_ONCE(*ctxt->offset.vm_offset, offset); } u64 kvm_phys_timer_read(void) @@ -765,25 +758,6 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) return 0; } -/* Make the updates of cntvoff for all vtimer contexts atomic */ -static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) -{ - unsigned long i; - struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu *tmp; - - mutex_lock(&kvm->lock); - kvm_for_each_vcpu(i, tmp, kvm) - timer_set_offset(vcpu_vtimer(tmp), cntvoff); - - /* - * When called from the vcpu create path, the CPU being created is not - * included in the loop above, so we just set it here as well. - */ - timer_set_offset(vcpu_vtimer(vcpu), cntvoff); - mutex_unlock(&kvm->lock); -} - void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); @@ -791,10 +765,11 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); vtimer->vcpu = vcpu; + vtimer->offset.vm_offset = &vcpu->kvm->arch.timer_data.voffset; ptimer->vcpu = vcpu; /* Synchronize cntvoff across all vtimers of a VM. */ - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); + timer_set_offset(vtimer, kvm_phys_timer_read()); timer_set_offset(ptimer, 0); hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); @@ -840,7 +815,7 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) break; case KVM_REG_ARM_TIMER_CNT: timer = vcpu_vtimer(vcpu); - update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value); + timer_set_offset(timer, kvm_phys_timer_read() - value); break; case KVM_REG_ARM_TIMER_CVAL: timer = vcpu_vtimer(vcpu); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 64c086c02c60..5da884e11337 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -44,7 +44,7 @@ static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) feature = smccc_get_arg1(vcpu); switch (feature) { case KVM_PTP_VIRT_COUNTER: - cycles = systime_snapshot.cycles - vcpu_read_sys_reg(vcpu, CNTVOFF_EL2); + cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: cycles = systime_snapshot.cycles; diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 71916de7c6c4..c52a6e6839da 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -23,6 +23,19 @@ enum kvm_arch_timer_regs { TIMER_REG_CTL, }; +struct arch_timer_offset { + /* + * If set, pointer to one of the offsets in the kvm's offset + * structure. If NULL, assume a zero offset. + */ + u64 *vm_offset; +}; + +struct arch_timer_vm_data { + /* Offset applied to the virtual timer/counter */ + u64 voffset; +}; + struct arch_timer_context { struct kvm_vcpu *vcpu; @@ -32,6 +45,8 @@ struct arch_timer_context { /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; + /* Offset for this counter/timer */ + struct arch_timer_offset offset; /* * We have multiple paths which can save/restore the timer state onto * the hardware, so we need some way of keeping track of where the -- cgit v1.2.3 From ab909509850b27fd39b8ba99e44cda39dbc3858c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:11 +0100 Subject: PCI: s390: Fix use-after-free of PCI resources with per-function hotplug On s390 PCI functions may be hotplugged individually even when they belong to a multi-function device. In particular on an SR-IOV device VFs may be removed and later re-added. In commit a50297cf8235 ("s390/pci: separate zbus creation from scanning") it was missed however that struct pci_bus and struct zpci_bus's resource list retained a reference to the PCI functions MMIO resources even though those resources are released and freed on hot-unplug. These stale resources may subsequently be claimed when the PCI function re-appears resulting in use-after-free. One idea of fixing this use-after-free in s390 specific code that was investigated was to simply keep resources around from the moment a PCI function first appeared until the whole virtual PCI bus created for a multi-function device disappears. The problem with this however is that due to the requirement of artificial MMIO addreesses (address cookies) extra logic is then needed to keep the address cookies compatible on re-plug. At the same time the MMIO resources semantically belong to the PCI function so tying their lifecycle to the function seems more logical. Instead a simpler approach is to remove the resources of an individually hot-unplugged PCI function from the PCI bus's resource list while keeping the resources of other PCI functions on the PCI bus untouched. This is done by introducing pci_bus_remove_resource() to remove an individual resource. Similarly the resource also needs to be removed from the struct zpci_bus's resource list. It turns out however, that there is really no need to add the MMIO resources to the struct zpci_bus's resource list at all and instead we can simply use the zpci_bar_struct's resource pointer directly. Fixes: a50297cf8235 ("s390/pci: separate zbus creation from scanning") Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20230306151014.60913-2-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci.c | 16 ++++++++++------ arch/s390/pci/pci_bus.c | 12 +++++------- arch/s390/pci/pci_bus.h | 3 +-- drivers/pci/bus.c | 21 +++++++++++++++++++++ include/linux/pci.h | 1 + 5 files changed, 38 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..e16afacc8fd1 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -544,8 +544,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; } -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +580,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1; @@ -590,17 +588,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i; + pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue; + release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); } int pcibios_device_add(struct pci_dev *pdev) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..a99926af2b69 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -41,9 +41,7 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i; if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); @@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) } if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0); } } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e064..af9f0ac79a1b 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev) int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev); static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 83ae838ceb5f..549c4bd5caec 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -76,6 +76,27 @@ struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n) } EXPORT_SYMBOL_GPL(pci_bus_resource_n); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res) +{ + struct pci_bus_resource *bus_res, *tmp; + int i; + + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { + if (bus->resource[i] == res) { + bus->resource[i] = NULL; + return; + } + } + + list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { + if (bus_res->res == res) { + list_del(&bus_res->list); + kfree(bus_res); + return; + } + } +} + void pci_bus_remove_resources(struct pci_bus *bus) { int i; diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..b50e5c79f7e3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1438,6 +1438,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); -- cgit v1.2.3 From 934ef33ee75c3846f605f18b65048acd147e3918 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 13 Mar 2023 15:45:48 +0100 Subject: x86/PVH: obtain VGA console info in Dom0 A new platform-op was added to Xen to allow obtaining the same VGA console information PV Dom0 is handed. Invoke the new function and have the output data processed by xen_init_vga(). Signed-off-by: Jan Beulich Reviewed-by: Juergen Gross Link: https://lore.kernel.org/r/8f315e92-7bda-c124-71cc-478ab9c5e610@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/Makefile | 2 +- arch/x86/xen/enlighten_pv.c | 3 ++- arch/x86/xen/enlighten_pvh.c | 13 +++++++++++++ arch/x86/xen/vga.c | 5 ++--- arch/x86/xen/xen-ops.h | 7 ++++--- include/xen/interface/platform.h | 3 +++ 6 files changed, 25 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3c5b52fbe4a7..a9ec8c9f5c5d 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -45,6 +45,6 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o obj-$(CONFIG_XEN_DEBUG_FS) += debugfs.o -obj-$(CONFIG_XEN_PV_DOM0) += vga.o +obj-$(CONFIG_XEN_DOM0) += vga.o obj-$(CONFIG_XEN_EFI) += efi.o diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5b1379662877..68f5f5d209df 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1389,7 +1389,8 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) x86_platform.set_legacy_features = xen_dom0_set_legacy_features; - xen_init_vga(info, xen_start_info->console.dom0.info_size); + xen_init_vga(info, xen_start_info->console.dom0.info_size, + &boot_params.screen_info); xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bcae606bbc5c..1da44aca896c 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -43,6 +43,19 @@ void __init xen_pvh_init(struct boot_params *boot_params) x86_init.oem.banner = xen_banner; xen_efi_init(boot_params); + + if (xen_initial_domain()) { + struct xen_platform_op op = { + .cmd = XENPF_get_dom0_console, + }; + long ret = HYPERVISOR_platform_op(&op); + + if (ret > 0) + xen_init_vga(&op.u.dom0_console, + min(ret * sizeof(char), + sizeof(op.u.dom0_console)), + &boot_params->screen_info); + } } void __init mem_map_via_hcall(struct boot_params *boot_params_p) diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index 14ea32e734d5..d97adab8420f 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -9,10 +9,9 @@ #include "xen-ops.h" -void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size) +void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size, + struct screen_info *screen_info) { - struct screen_info *screen_info = &boot_params.screen_info; - /* This is drawn from a dump from vgacon:startup in * standard Linux. */ screen_info->orig_video_mode = 3; diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9a8bb972193d..a10903785a33 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -108,11 +108,12 @@ static inline void xen_uninit_lock_cpu(int cpu) struct dom0_vga_console_info; -#ifdef CONFIG_XEN_PV_DOM0 -void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size); +#ifdef CONFIG_XEN_DOM0 +void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size, + struct screen_info *); #else static inline void __init xen_init_vga(const struct dom0_vga_console_info *info, - size_t size) + size_t size, struct screen_info *si) { } #endif diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h index 655d92e803e1..79a443c65ea9 100644 --- a/include/xen/interface/platform.h +++ b/include/xen/interface/platform.h @@ -483,6 +483,8 @@ struct xenpf_symdata { }; DEFINE_GUEST_HANDLE_STRUCT(xenpf_symdata); +#define XENPF_get_dom0_console 64 + struct xen_platform_op { uint32_t cmd; uint32_t interface_version; /* XENPF_INTERFACE_VERSION */ @@ -506,6 +508,7 @@ struct xen_platform_op { struct xenpf_mem_hotadd mem_add; struct xenpf_core_parking core_parking; struct xenpf_symdata symdata; + struct dom0_vga_console_info dom0_console; uint8_t pad[128]; } u; }; -- cgit v1.2.3 From 34e0a279a993debaff03158fc2fbf6a00c093643 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Mar 2023 10:30:02 +0100 Subject: block: do not reverse request order when flushing plug list Commit 26fed4ac4eab ("block: flush plug based on hardware and software queue order") changed flushing of plug list to submit requests one device at a time. However while doing that it also started using list_add_tail() instead of list_add() used previously thus effectively submitting requests in reverse order. Also when forming a rq_list with remaining requests (in case two or more devices are used), we effectively reverse the ordering of the plug list for each device we process. Submitting requests in reverse order has negative impact on performance for rotational disks (when BFQ is not in use). We observe 10-25% regression in random 4k write throughput, as well as ~20% regression in MariaDB OLTP benchmark on rotational storage on btrfs filesystem. Fix the problem by preserving ordering of the plug list when inserting requests into the queuelist as well as by appending to requeue_list instead of prepending to it. Fixes: 26fed4ac4eab ("block: flush plug based on hardware and software queue order") Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230313093002.11756-1-jack@suse.cz Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- include/linux/blk-mq.h | 6 ++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/block/blk-mq.c b/block/blk-mq.c index d0cb2ef18fe2..cf1a39adf9a5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2725,6 +2725,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; + struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; LIST_HEAD(list); @@ -2735,10 +2736,10 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { - rq_list_add(&requeue_list, rq); + rq_list_add_tail(&requeue_lastp, rq); continue; } - list_add_tail(&rq->queuelist, &list); + list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list)); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dd5ce1137f04..de0b0c3e7395 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -228,6 +228,12 @@ static inline unsigned short req_get_ioprio(struct request *req) *(listptr) = rq; \ } while (0) +#define rq_list_add_tail(lastpptr, rq) do { \ + (rq)->rq_next = NULL; \ + **(lastpptr) = rq; \ + *(lastpptr) = &rq->rq_next; \ +} while (0) + #define rq_list_pop(listptr) \ ({ \ struct request *__req = NULL; \ -- cgit v1.2.3 From c2679254b9c9980d9045f0f722cf093a2b1f7590 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 10 Mar 2023 17:28:56 -0500 Subject: tracing: Make tracepoint lockdep check actually test something A while ago where the trace events had the following: rcu_read_lock_sched_notrace(); rcu_dereference_sched(...); rcu_read_unlock_sched_notrace(); If the tracepoint is enabled, it could trigger RCU issues if called in the wrong place. And this warning was only triggered if lockdep was enabled. If the tracepoint was never enabled with lockdep, the bug would not be caught. To handle this, the above sequence was done when lockdep was enabled regardless if the tracepoint was enabled or not (although the always enabled code really didn't do anything, it would still trigger a warning). But a lot has changed since that lockdep code was added. One is, that sequence no longer triggers any warning. Another is, the tracepoint when enabled doesn't even do that sequence anymore. The main check we care about today is whether RCU is "watching" or not. So if lockdep is enabled, always check if rcu_is_watching() which will trigger a warning if it is not (tracepoints require RCU to be watching). Note, that old sequence did add a bit of overhead when lockdep was enabled, and with the latest kernel updates, would cause the system to slow down enough to trigger kernel "stalled" warnings. Link: http://lore.kernel.org/lkml/20140806181801.GA4605@redhat.com Link: http://lore.kernel.org/lkml/20140807175204.C257CAC5@viggo.jf.intel.com Link: https://lore.kernel.org/lkml/20230307184645.521db5c9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20230310172856.77406446@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Dave Hansen Cc: "Paul E. McKenney" Cc: Mathieu Desnoyers Cc: Joel Fernandes Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (Google) --- include/linux/tracepoint.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index fa1004fcf810..2083f2d2f05b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -231,12 +231,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -249,9 +248,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ -- cgit v1.2.3 From 4b397c06cb987935b1b097336532aa6b4210e091 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Mar 2023 19:11:09 +0000 Subject: net: tunnels: annotate lockless accesses to dev->needed_headroom IP tunnels can apparently update dev->needed_headroom in their xmit path. This patch takes care of three tunnels xmit, and also the core LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EXTRA() helpers. More changes might be needed for completeness. BUG: KCSAN: data-race in ip_tunnel_xmit / ip_tunnel_xmit read to 0xffff88815b9da0ec of 2 bytes by task 888 on cpu 1: ip_tunnel_xmit+0x1270/0x1730 net/ipv4/ip_tunnel.c:803 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 write to 0xffff88815b9da0ec of 2 bytes by task 2379 on cpu 0: ip_tunnel_xmit+0x1294/0x1730 net/ipv4/ip_tunnel.c:804 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x9bc/0xc50 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x39a/0x4e0 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0xeb/0x220 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] mld_sendpack+0x438/0x6a0 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x519/0x7b0 net/ipv6/mcast.c:2653 process_one_work+0x3e6/0x750 kernel/workqueue.c:2390 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2537 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0dd4 -> 0x0e14 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2379 Comm: kworker/0:0 Not tainted 6.3.0-rc1-syzkaller-00002-g8ca09d5fa354-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Workqueue: mld mld_ifc_work Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230310191109.2384387-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++-- net/ipv4/ip_tunnel.c | 12 ++++++------ net/ipv6/ip6_tunnel.c | 4 ++-- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a14b7b11766..470085b121d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -297,9 +297,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index de90b09dfe78..2541083d49ad 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -614,10 +614,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -800,10 +800,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 47b6607a1370..5e80e517f071 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1240,8 +1240,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) -- cgit v1.2.3 From 0d3c9333d976af41d7dbc6bf4d9d2e95fbdf9c89 Mon Sep 17 00:00:00 2001 From: Liu Ying Date: Tue, 14 Mar 2023 13:50:35 +0800 Subject: drm/bridge: Fix returned array size name for atomic_get_input_bus_fmts kdoc The returned array size for input formats is set through atomic_get_input_bus_fmts()'s 'num_input_fmts' argument, so use 'num_input_fmts' to represent the array size in the function's kdoc, not 'num_output_fmts'. Fixes: 91ea83306bfa ("drm/bridge: Fix the bridge kernel doc") Fixes: f32df58acc68 ("drm/bridge: Add the necessary bits to support bus format negotiation") Signed-off-by: Liu Ying Reviewed-by: Robert Foss Signed-off-by: Neil Armstrong Link: https://patchwork.freedesktop.org/patch/msgid/20230314055035.3731179-1-victor.liu@nxp.com --- include/drm/drm_bridge.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 42f86327b40a..bf964cdfb330 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -423,11 +423,11 @@ struct drm_bridge_funcs { * * The returned array must be allocated with kmalloc() and will be * freed by the caller. If the allocation fails, NULL should be - * returned. num_output_fmts must be set to the returned array size. + * returned. num_input_fmts must be set to the returned array size. * Formats listed in the returned array should be listed in decreasing * preference order (the core will try all formats until it finds one * that works). When the format is not supported NULL should be - * returned and num_output_fmts should be set to 0. + * returned and num_input_fmts should be set to 0. * * This method is called on all elements of the bridge chain as part of * the bus format negotiation process that happens in -- cgit v1.2.3 From 8e19b87cfce2de2125f11363d7dea3d08f16ccae Mon Sep 17 00:00:00 2001 From: Minwoo Im Date: Thu, 9 Mar 2023 23:31:18 +0900 Subject: nvme-trace: show more opcode names We have more commands to show in the trace. Sync up. Signed-off-by: Minwoo Im Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..779507ac750b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -812,6 +812,7 @@ enum nvme_opcode { nvme_opcode_name(nvme_cmd_compare), \ nvme_opcode_name(nvme_cmd_write_zeroes), \ nvme_opcode_name(nvme_cmd_dsm), \ + nvme_opcode_name(nvme_cmd_verify), \ nvme_opcode_name(nvme_cmd_resv_register), \ nvme_opcode_name(nvme_cmd_resv_report), \ nvme_opcode_name(nvme_cmd_resv_acquire), \ @@ -1144,10 +1145,14 @@ enum nvme_admin_opcode { nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ nvme_admin_opcode_name(nvme_admin_activate_fw), \ nvme_admin_opcode_name(nvme_admin_download_fw), \ + nvme_admin_opcode_name(nvme_admin_dev_self_test), \ nvme_admin_opcode_name(nvme_admin_ns_attach), \ nvme_admin_opcode_name(nvme_admin_keep_alive), \ nvme_admin_opcode_name(nvme_admin_directive_send), \ nvme_admin_opcode_name(nvme_admin_directive_recv), \ + nvme_admin_opcode_name(nvme_admin_virtual_mgmt), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_send), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_recv), \ nvme_admin_opcode_name(nvme_admin_dbbuf), \ nvme_admin_opcode_name(nvme_admin_format_nvm), \ nvme_admin_opcode_name(nvme_admin_security_send), \ -- cgit v1.2.3 From 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 23 Feb 2023 17:12:26 +0800 Subject: block: count 'ios' and 'sectors' when io is done for bio-based device While using iostat for raid, I observed very strange 'await' occasionally, and turns out it's due to that 'ios' and 'sectors' is counted in bdev_start_io_acct(), while 'nsecs' is counted in bdev_end_io_acct(). I'm not sure why they are ccounted like that but I think this behaviour is obviously wrong because user will get wrong disk stats. Fix the problem by counting 'ios' and 'sectors' when io is done, like what rq-based device does. Fixes: 394ffa503bc4 ("blk: introduce generic io stat accounting help function") Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-core.c | 16 ++++++---------- drivers/md/dm.c | 6 +++--- drivers/nvme/host/multipath.c | 8 ++++---- include/linux/blkdev.h | 5 ++--- 4 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..42926e6cb83c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -959,16 +959,11 @@ again: } } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { - const int sgrp = op_stat_group(op); - part_stat_lock(); update_io_ticks(bdev, start_time, false); - part_stat_inc(bdev, ios[sgrp]); - part_stat_add(bdev, sectors[sgrp], sectors); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -984,13 +979,12 @@ EXPORT_SYMBOL(bdev_start_io_acct); */ unsigned long bio_start_io_acct(struct bio *bio) { - return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time) + unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); @@ -998,6 +992,8 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op, part_stat_lock(); update_io_ticks(bdev, now, true); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -1007,7 +1003,7 @@ EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { - bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index eace45a18d45..f5cc330bb549 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -512,10 +512,10 @@ static void dm_io_acct(struct dm_io *io, bool end) sectors = io->sectors; if (!end) - bdev_start_io_acct(bio->bi_bdev, sectors, bio_op(bio), - start_time); + bdev_start_io_acct(bio->bi_bdev, bio_op(bio), start_time); else - bdev_end_io_acct(bio->bi_bdev, bio_op(bio), start_time); + bdev_end_io_acct(bio->bi_bdev, bio_op(bio), sectors, + start_time); if (static_branch_unlikely(&stats_enabled) && unlikely(dm_stats_used(&md->stats))) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63..9171452e2f6d 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -123,9 +123,8 @@ void nvme_mpath_start_request(struct request *rq) return; nvme_req(rq)->flags |= NVME_MPATH_IO_STATS; - nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, - blk_rq_bytes(rq) >> SECTOR_SHIFT, - req_op(rq), jiffies); + nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq), + jiffies); } EXPORT_SYMBOL_GPL(nvme_mpath_start_request); @@ -136,7 +135,8 @@ void nvme_mpath_end_request(struct request *rq) if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS)) return; bdev_end_io_acct(ns->head->disk->part0, req_op(rq), - nvme_req(rq)->start_time); + blk_rq_bytes(rq) >> SECTOR_SHIFT, + nvme_req(rq)->start_time); } void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1aee08f8c18..941304f17492 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, -- cgit v1.2.3 From 4e16b6a748df52800c90f3ab181aef8129bd332f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 15 Mar 2023 16:03:50 -0700 Subject: ynl: broaden the license even more I relicensed Netlink spec code to GPL-2.0 OR BSD-3-Clause but we still put a slightly different license on the uAPI header than the rest of the code. Use the Linux-syscall-note on all the specs and all generated code. It's moot for kernel code, but should not hurt. This way the licenses match everywhere. Cc: Chuck Lever Fixes: 37d9df224d1e ("ynl: re-license uniformly under GPL-2.0 OR BSD-3-Clause") Reviewed-by: Chuck Lever Signed-off-by: Jakub Kicinski --- Documentation/netlink/genetlink-c.yaml | 2 +- Documentation/netlink/genetlink-legacy.yaml | 2 +- Documentation/netlink/genetlink.yaml | 2 +- Documentation/netlink/specs/ethtool.yaml | 2 +- Documentation/netlink/specs/fou.yaml | 2 +- Documentation/netlink/specs/netdev.yaml | 2 +- Documentation/userspace-api/netlink/specs.rst | 3 ++- include/uapi/linux/fou.h | 2 +- include/uapi/linux/netdev.h | 2 +- net/core/netdev-genl-gen.c | 2 +- net/core/netdev-genl-gen.h | 2 +- net/ipv4/fou_nl.c | 2 +- net/ipv4/fou_nl.h | 2 +- tools/include/uapi/linux/netdev.h | 2 +- tools/net/ynl/ynl-gen-c.py | 8 ++++---- 15 files changed, 19 insertions(+), 18 deletions(-) (limited to 'include') diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index f082a5ad7cf1..5c3642b3f802 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-c.yaml# diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index c6b8c77f7d12..5e98c6d2b9aa 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-legacy.yaml# diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index b2d56ab9e615..d35dcd6f8d82 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) %YAML 1.2 --- $id: http://kernel.org/schemas/netlink/genetlink-legacy.yaml# diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 18ecb7d90cbe..4727c067e2ba 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) name: ethtool diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml index cff104288723..3e13826a3fdf 100644 --- a/Documentation/netlink/specs/fou.yaml +++ b/Documentation/netlink/specs/fou.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) name: fou diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 753e5914a8b7..b99e7ffef7a1 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -1,4 +1,4 @@ -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) name: netdev diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst index 2122e0c4a399..a22442ba1d30 100644 --- a/Documentation/userspace-api/netlink/specs.rst +++ b/Documentation/userspace-api/netlink/specs.rst @@ -24,7 +24,8 @@ YAML specifications can be found under ``Documentation/netlink/specs/`` This document describes details of the schema. See :doc:`intro-specs` for a practical starting guide. -All specs must be licensed under ``GPL-2.0-only OR BSD-3-Clause`` +All specs must be licensed under +``((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)`` to allow for easy adoption in user space code. Compatibility levels diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h index 5041c3598493..b5cd3e7b3775 100644 --- a/include/uapi/linux/fou.h +++ b/include/uapi/linux/fou.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN uapi header */ diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index ed134fbdfd32..639524b59930 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 9e10802587fc..3abab70d66dd 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel source */ diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 2c5fc7d1e8a7..74d74fc23167 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN kernel header */ diff --git a/net/ipv4/fou_nl.c b/net/ipv4/fou_nl.c index 5c14fe030eda..6c37c4f98cca 100644 --- a/net/ipv4/fou_nl.c +++ b/net/ipv4/fou_nl.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel source */ diff --git a/net/ipv4/fou_nl.h b/net/ipv4/fou_nl.h index 58b1e1ed4b3b..dbd0780a5d34 100644 --- a/net/ipv4/fou_nl.h +++ b/net/ipv4/fou_nl.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/fou.yaml */ /* YNL-GEN kernel header */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index ed134fbdfd32..639524b59930 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* Do not edit directly, auto-generated from: */ /* Documentation/netlink/specs/netdev.yaml */ /* YNL-GEN uapi header */ diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index d47376f19de7..3b4d03a50fc1 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1,5 +1,5 @@ #!/usr/bin/env python3 -# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) import argparse import collections @@ -2068,12 +2068,12 @@ def main(): _, spec_kernel = find_kernel_root(args.spec) if args.mode == 'uapi': - cw.p('/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */') + cw.p('/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */') else: if args.header: - cw.p('/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */') + cw.p('/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */') else: - cw.p('// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause') + cw.p('// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)') cw.p("/* Do not edit directly, auto-generated from: */") cw.p(f"/*\t{spec_kernel} */") cw.p(f"/* YNL-GEN {args.mode} {'header' if args.header else 'source'} */") -- cgit v1.2.3 From 2f59823fe696caa844249a90bb3f9aeda69cfe5c Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Thu, 16 Mar 2023 11:37:53 +0800 Subject: net/sched: act_api: add specific EXT_WARN_MSG for tc action In my previous commit 0349b8779cc9 ("sched: add new attr TCA_EXT_WARN_MSG to report tc extact message") I didn't notice the tc action use different enum with filter. So we can't use TCA_EXT_WARN_MSG directly for tc action. Let's add a TCA_ROOT_EXT_WARN_MSG for tc action specifically and put this param before going to the TCA_ACT_TAB nest. Fixes: 0349b8779cc9 ("sched: add new attr TCA_EXT_WARN_MSG to report tc extact message") Signed-off-by: Hangbin Liu Acked-by: Jamal Hadi Salim Signed-off-by: Jakub Kicinski --- include/uapi/linux/rtnetlink.h | 1 + net/sched/act_api.c | 8 ++++---- 2 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 25a0af57dd5e..51c13cf9c5ae 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -789,6 +789,7 @@ enum { TCA_ROOT_FLAGS, TCA_ROOT_COUNT, TCA_ROOT_TIME_DELTA, /* in msecs */ + TCA_ROOT_EXT_WARN_MSG, __TCA_ROOT_MAX, #define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) }; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fce522886099..296fc1afedd8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1589,6 +1589,10 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], t->tca__pad1 = 0; t->tca__pad2 = 0; + if (extack && extack->_msg && + nla_put_string(skb, TCA_ROOT_EXT_WARN_MSG, extack->_msg)) + goto out_nlmsg_trim; + nest = nla_nest_start_noflag(skb, TCA_ACT_TAB); if (!nest) goto out_nlmsg_trim; @@ -1598,10 +1602,6 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], nla_nest_end(skb, nest); - if (extack && extack->_msg && - nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) - goto out_nlmsg_trim; - nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From 6e2a3a324aab9d76e6b864eb6ebc60b197b5141a Mon Sep 17 00:00:00 2001 From: Or Har-Toov Date: Sun, 19 Mar 2023 14:59:30 +0200 Subject: net/mlx5: Expose bits for enabling out-of-order by default Add needed HW bits for enabling out-of-order by default and use go_back_n when out-of-order is not needed. Signed-off-by: Or Har-Toov Signed-off-by: Leon Romanovsky Link: https://lore.kernel.org/r/75d6dfe263989a05c08c43406132b336ea12d00a.1679230449.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 66d76e97a087..62039b147432 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1077,7 +1077,9 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x17]; + u8 reserved_at_7[0x1]; + u8 qp_ooo_transmit_default[0x1]; + u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1493,7 +1495,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0x7]; + u8 reserved_at_b3[0x6]; + u8 go_back_n[0x1]; u8 shampo[0x1]; u8 reserved_at_bb[0x5]; @@ -3261,7 +3264,8 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x3]; + u8 reserved_at_55[0x1]; + u8 retry_mode[0x2]; u8 ts_format[0x2]; u8 reserved_at_5a[0x1]; u8 rlky[0x1]; -- cgit v1.2.3