From f5a4aa643ee968137eea902aa321c58c14c256c7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 1 Nov 2025 12:15:24 -0700 Subject: dmaengine: dw_edma: correct kernel-doc warnings in Use the correct enum name in its kernel-doc heading. Add ending ':' to struct member names. Drop the @id: kernel-doc entry since there is no struct member named 'id'. edma.h:46: warning: expecting prototype for struct dw_edma_core_ops. Prototype was for struct dw_edma_plat_ops instead Warning: edma.h:101 struct member 'ops' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'flags' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'reg_base' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'll_wr_cnt' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'll_rd_cnt' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'll_region_wr' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'll_region_rd' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'dt_region_wr' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'dt_region_rd' not described in 'dw_edma_chip' Warning: edma.h:101 struct member 'mf' not described in 'dw_edma_chip' Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20251101191524.1991135-1-rdunlap@infradead.org Signed-off-by: Vinod Koul --- include/linux/dma/edma.h | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h index 3080747689f6..270b5458aecf 100644 --- a/include/linux/dma/edma.h +++ b/include/linux/dma/edma.h @@ -27,7 +27,7 @@ struct dw_edma_region { }; /** - * struct dw_edma_core_ops - platform-specific eDMA methods + * struct dw_edma_plat_ops - platform-specific eDMA methods * @irq_vector: Get IRQ number of the passed eDMA channel. Note the * method accepts the channel id in the end-to-end * numbering with the eDMA write channels being placed @@ -63,19 +63,17 @@ enum dw_edma_chip_flags { /** * struct dw_edma_chip - representation of DesignWare eDMA controller hardware * @dev: struct device of the eDMA controller - * @id: instance ID * @nr_irqs: total number of DMA IRQs - * @ops DMA channel to IRQ number mapping - * @flags dw_edma_chip_flags - * @reg_base DMA register base address - * @ll_wr_cnt DMA write link list count - * @ll_rd_cnt DMA read link list count - * @rg_region DMA register region - * @ll_region_wr DMA descriptor link list memory for write channel - * @ll_region_rd DMA descriptor link list memory for read channel - * @dt_region_wr DMA data memory for write channel - * @dt_region_rd DMA data memory for read channel - * @mf DMA register map format + * @ops: DMA channel to IRQ number mapping + * @flags: dw_edma_chip_flags + * @reg_base: DMA register base address + * @ll_wr_cnt: DMA write link list count + * @ll_rd_cnt: DMA read link list count + * @ll_region_wr: DMA descriptor link list memory for write channel + * @ll_region_rd: DMA descriptor link list memory for read channel + * @dt_region_wr: DMA data memory for write channel + * @dt_region_rd: DMA data memory for read channel + * @mf: DMA register map format * @dw: struct dw_edma that is filled by dw_edma_probe() */ struct dw_edma_chip { -- cgit v1.2.3 From de4761fb57f6a71eeb5a4c1167ae3606b08d8f59 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Nov 2025 16:20:01 -0800 Subject: dmaengine: shdma: correct most kernel-doc issues in shdma-base.h Fix kernel-doc comments in include/linux/shdma-base.h to avoid most warnings: - prefix an enum name with "enum" - prefix enum values with '@' - prefix struct member names with '@' shdma-base.h:28: warning: cannot understand function prototype: 'enum shdma_pm_state ' Warning: shdma-base.h:103 struct member 'desc_completed' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'halt_channel' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'channel_busy' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'slave_addr' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'desc_setup' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'set_slave' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'setup_xfer' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'start_xfer' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'embedded_desc' not described in 'shdma_ops' Warning: shdma-base.h:103 struct member 'chan_irq' not described in 'shdma_ops' This one is not fixed: from 4f46f8ac80416: Warning: shdma-base.h:103 struct member 'get_partial' not described in 'shdma_ops' Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20251104002001.445297-1-rdunlap@infradead.org Signed-off-by: Vinod Koul --- include/linux/shdma-base.h | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h index 03ba4dab2ef7..b6827c06d332 100644 --- a/include/linux/shdma-base.h +++ b/include/linux/shdma-base.h @@ -19,11 +19,11 @@ #include /** - * shdma_pm_state - DMA channel PM state - * SHDMA_PM_ESTABLISHED: either idle or during data transfer - * SHDMA_PM_BUSY: during the transfer preparation, when we have to + * enum shdma_pm_state - DMA channel PM state + * @SHDMA_PM_ESTABLISHED: either idle or during data transfer + * @SHDMA_PM_BUSY: during the transfer preparation, when we have to * drop the lock temporarily - * SHDMA_PM_PENDING: transfers pending + * @SHDMA_PM_PENDING: transfers pending */ enum shdma_pm_state { SHDMA_PM_ESTABLISHED, @@ -74,18 +74,18 @@ struct shdma_chan { /** * struct shdma_ops - simple DMA driver operations - * desc_completed: return true, if this is the descriptor, that just has + * @desc_completed: return true, if this is the descriptor, that just has * completed (atomic) - * halt_channel: stop DMA channel operation (atomic) - * channel_busy: return true, if the channel is busy (atomic) - * slave_addr: return slave DMA address - * desc_setup: set up the hardware specific descriptor portion (atomic) - * set_slave: bind channel to a slave - * setup_xfer: configure channel hardware for operation (atomic) - * start_xfer: start the DMA transfer (atomic) - * embedded_desc: return Nth struct shdma_desc pointer from the + * @halt_channel: stop DMA channel operation (atomic) + * @channel_busy: return true, if the channel is busy (atomic) + * @slave_addr: return slave DMA address + * @desc_setup: set up the hardware specific descriptor portion (atomic) + * @set_slave: bind channel to a slave + * @setup_xfer: configure channel hardware for operation (atomic) + * @start_xfer: start the DMA transfer (atomic) + * @embedded_desc: return Nth struct shdma_desc pointer from the * descriptor array - * chan_irq: process channel IRQ, return true if a transfer has + * @chan_irq: process channel IRQ, return true if a transfer has * completed (atomic) */ struct shdma_ops { -- cgit v1.2.3 From 4dee13db29de6dd869af9b3827e1ff569644e838 Mon Sep 17 00:00:00 2001 From: Chaoyi Chen Date: Mon, 8 Dec 2025 09:54:51 +0800 Subject: usb: typec: Export typec bus and typec altmode device type The DRM may want to register a notifier on the typec bus to know when a typec altmode device is added, and distinguish between different types of typec altmode device. Export these things. Signed-off-by: Chaoyi Chen Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20251208015500.94-3-kernel@airkyi.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 3 +++ include/linux/usb/typec_altmode.h | 8 ++++++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index 309251572e2e..c6fd46902fce 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -20,12 +20,15 @@ struct typec_port; struct typec_altmode_ops; struct typec_cable_ops; +struct bus_type; struct fwnode_handle; struct device; struct usb_power_delivery; struct usb_power_delivery_desc; +extern const struct bus_type typec_bus; + enum typec_port_type { TYPEC_PORT_SRC, TYPEC_PORT_SNK, diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index f7db3bd4c90e..9197a4637a93 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -9,6 +9,14 @@ #define MODE_DISCOVERY_MAX 6 +extern const struct device_type typec_port_altmode_dev_type; +extern const struct device_type typec_plug_altmode_dev_type; +extern const struct device_type typec_partner_altmode_dev_type; + +#define is_typec_port_altmode(dev) ((dev)->type == &typec_port_altmode_dev_type) +#define is_typec_plug_altmode(dev) ((dev)->type == &typec_plug_altmode_dev_type) +#define is_typec_partner_altmode(dev) ((dev)->type == &typec_partner_altmode_dev_type) + struct typec_altmode_ops; /** -- cgit v1.2.3 From dd1fbe324a548e8057d5f3c72ce1a64a80f1753e Mon Sep 17 00:00:00 2001 From: Yi Cong Date: Tue, 2 Dec 2025 17:09:48 +0800 Subject: usb: linux/usb.h: Correct the description of the usb_device_driver member In the current kernel USB device driver code, only the name field is required to be provided; all other fields are optional. Correct this part of the description. Signed-off-by: Yi Cong Acked-by: Alan Stern Link: https://patch.msgid.link/20251202090948.334809-1-cong.yi@linux.dev Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index e85105939af8..fbfcc70b07fb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1295,8 +1295,7 @@ struct usb_driver { * resume and suspend functions will be called in addition to the driver's * own, so this part of the setup does not need to be replicated. * - * USB drivers must provide all the fields listed above except driver, - * match, and id_table. + * USB device drivers must provide a name, other driver fields are optional. */ struct usb_device_driver { const char *name; -- cgit v1.2.3 From 6d71c62b13c33ea858ab298fe20beaec5736edc7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 12 Dec 2025 09:09:06 +0100 Subject: serdev: Provide a bustype shutdown function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To prepare serdev driver to migrate away from struct device_driver::shutdown (and then eventually remove that callback) create a serdev driver shutdown callback and migration code to keep the existing behaviour. Note this introduces a warning for each driver at register time that isn't converted yet to that callback. Signed-off-by: Uwe Kleine-König Link: https://patch.msgid.link/ab518883e3ed0976a19cb5b5b5faf42bd3a655b7.1765526117.git.u.kleine-koenig@baylibre.com Signed-off-by: Greg Kroah-Hartman --- include/linux/serdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 34562eb99931..5654c58eb73c 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -65,6 +65,7 @@ struct serdev_device_driver { struct device_driver driver; int (*probe)(struct serdev_device *); void (*remove)(struct serdev_device *); + void (*shutdown)(struct serdev_device *); }; static inline struct serdev_device_driver *to_serdev_device_driver(struct device_driver *d) -- cgit v1.2.3 From 247a357a9101b76d832b7e19d85ba8dcfb3e3e8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Fri, 19 Dec 2025 15:28:14 +0000 Subject: iio: buffer-dma: Turn iio_dma_buffer_init() void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit iio_dma_buffer_init() always return 0. Therefore there's no point in returning int. While at it, fix a mismatch between the function declaration and definition regarding the struct device (dma_dev != dev). Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 4f33e6a39797..cd2ba4bb7501 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -157,8 +157,8 @@ int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd); int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length); int iio_dma_buffer_request_update(struct iio_buffer *buffer); -int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, - struct device *dma_dev, const struct iio_dma_buffer_ops *ops); +void iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, struct device *dev, + const struct iio_dma_buffer_ops *ops); void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue); void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue); -- cgit v1.2.3 From 0c1316b9521af0801e2502f390a89df5459094ed Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nuno=20S=C3=A1?= Date: Fri, 19 Dec 2025 15:28:15 +0000 Subject: iio: buffer-dma: Fix coding style complains MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Just making sure checkpatch is happy. No functional change intended. Signed-off-by: Nuno Sá Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index cd2ba4bb7501..ef8687a88b73 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -119,7 +119,12 @@ struct iio_dma_buffer_queue { struct device *dev; const struct iio_dma_buffer_ops *ops; + /* + * A mutex to protect accessing, configuring (eg: enqueuing DMA blocks) + * and do file IO on struct iio_dma_buffer_queue objects. + */ struct mutex lock; + /* A spin lock to protect adding/removing blocks to the queue list */ spinlock_t list_lock; struct list_head incoming; @@ -136,20 +141,19 @@ struct iio_dma_buffer_queue { */ struct iio_dma_buffer_ops { int (*submit)(struct iio_dma_buffer_queue *queue, - struct iio_dma_buffer_block *block); + struct iio_dma_buffer_block *block); void (*abort)(struct iio_dma_buffer_queue *queue); }; void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block); void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue, - struct list_head *list); + struct list_head *list); -int iio_dma_buffer_enable(struct iio_buffer *buffer, - struct iio_dev *indio_dev); +int iio_dma_buffer_enable(struct iio_buffer *buffer, struct iio_dev *indio_dev); int iio_dma_buffer_disable(struct iio_buffer *buffer, - struct iio_dev *indio_dev); + struct iio_dev *indio_dev); int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, - char __user *user_buffer); + char __user *user_buffer); int iio_dma_buffer_write(struct iio_buffer *buffer, size_t n, const char __user *user_buffer); size_t iio_dma_buffer_usage(struct iio_buffer *buffer); -- cgit v1.2.3 From 3285c471d0c0b991e5efc96c1a8bcc9ace17b9b8 Mon Sep 17 00:00:00 2001 From: James Clark Date: Fri, 28 Nov 2025 11:55:22 +0000 Subject: coresight: Remove misleading definitions ETM_OPT_* definitions duplicate the PMU format attributes that have always been published in sysfs. Hardcoding them here makes it misleading as to what the 'real' PMU API is and prevents attributes from being rearranged in the future. ETM4_CFG_BIT_* definitions just define what the Arm Architecture is which is not the responsibility of the kernel to do and doesn't scale to other registers or versions of ETM. It's not an actual software ABI/API and these definitions here mislead that it is. Any tools using the first ones would be broken anyway as they won't work when attributes are moved, so removing them is the right thing to do and will prompt a fix. Tools using the second ones can trivially redefine them locally. Perf also has its own copy of the headers so both of these things can be fixed up at a later date. Reviewed-by: Leo Yan Reviewed-by: Mike Leach Tested-by: Leo Yan Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20251128-james-cs-syncfreq-v8-10-4d319764cc58@linaro.org --- include/linux/coresight-pmu.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 89b0ac0014b0..2e179abe472a 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -21,30 +21,6 @@ */ #define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) -/* - * Below are the definition of bit offsets for perf option, and works as - * arbitrary values for all ETM versions. - * - * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore, - * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and - * directly use below macros as config bits. - */ -#define ETM_OPT_BRANCH_BROADCAST 8 -#define ETM_OPT_CYCACC 12 -#define ETM_OPT_CTXTID 14 -#define ETM_OPT_CTXTID2 15 -#define ETM_OPT_TS 28 -#define ETM_OPT_RETSTK 29 - -/* ETMv4 CONFIGR programming bits for the ETM OPTs */ -#define ETM4_CFG_BIT_BB 3 -#define ETM4_CFG_BIT_CYCACC 4 -#define ETM4_CFG_BIT_CTXTID 6 -#define ETM4_CFG_BIT_VMID 7 -#define ETM4_CFG_BIT_TS 11 -#define ETM4_CFG_BIT_RETSTK 12 -#define ETM4_CFG_BIT_VMID_OPT 15 - /* * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. * Used to associate a CPU with the CoreSight Trace ID. -- cgit v1.2.3 From 478f3890709a092a97a0218f61af19ac9b725573 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Mon, 15 Dec 2025 18:49:25 +0100 Subject: soundwire: Make remove function return no value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All remove functions return zero and the driver core ignores any other returned value (just emits a warning about it being ignored). So make all remove callbacks return void instead of an ignored int. This is in line with most other subsystems. Signed-off-by: Uwe Kleine-König Link: https://patch.msgid.link/20251215174925.1327021-5-u.kleine-koenig@baylibre.com Signed-off-by: Vinod Koul --- include/linux/soundwire/sdw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index e6a3476bcef1..f462717acf20 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -705,7 +705,7 @@ struct sdw_master_device { struct sdw_driver { int (*probe)(struct sdw_slave *sdw, const struct sdw_device_id *id); - int (*remove)(struct sdw_slave *sdw); + void (*remove)(struct sdw_slave *sdw); void (*shutdown)(struct sdw_slave *sdw); const struct sdw_device_id *id_table; -- cgit v1.2.3 From e715bc42e337b6f54ada7262e1bbc0b7860525c2 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Fri, 19 Dec 2025 18:16:15 +0100 Subject: usb: gadget: Constify struct configfs_item_operations and configfs_group_operations 'struct configfs_item_operations' and 'configfs_group_operations' are not modified in these drivers. Constifying these structures moves some data to a read-only section, so increases overall security, especially when the structure holds some function pointers. On a x86_64, with allmodconfig, as an example: Before: ====== text data bss dec hex filename 65061 20968 256 86285 1510d drivers/usb/gadget/configfs.o After: ===== text data bss dec hex filename 66181 19848 256 86285 1510d drivers/usb/gadget/configfs.o Signed-off-by: Christophe JAILLET Link: https://patch.msgid.link/49cec1cb84425f854de80b6d69b53a5a3cda8189.1766164523.git.christophe.jaillet@wanadoo.fr Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/gadget_configfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget_configfs.h b/include/linux/usb/gadget_configfs.h index 6b5d6838f865..23c1091e88c0 100644 --- a/include/linux/usb/gadget_configfs.h +++ b/include/linux/usb/gadget_configfs.h @@ -30,7 +30,7 @@ static ssize_t __struct##_##__name##_show(struct config_item *item, char *page) CONFIGFS_ATTR(struct_name##_, _name) #define USB_CONFIG_STRING_RW_OPS(struct_in) \ -static struct configfs_item_operations struct_in##_langid_item_ops = { \ +static const struct configfs_item_operations struct_in##_langid_item_ops = { \ .release = struct_in##_attr_release, \ }; \ \ @@ -86,7 +86,7 @@ static void struct_in##_strings_drop( \ config_item_put(item); \ } \ \ -static struct configfs_group_operations struct_in##_strings_ops = { \ +static const struct configfs_group_operations struct_in##_strings_ops = { \ .make_group = &struct_in##_strings_make, \ .drop_item = &struct_in##_strings_drop, \ }; \ -- cgit v1.2.3 From caad07ae07e3fb173e804abdd53fb96aa7186830 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 22 Dec 2025 21:22:48 +0100 Subject: phy: core: Discard pm_runtime_put() return values The PHY core defines phy_pm_runtime_put() to return an int, but that return value is never used. It also passes the return value of pm_runtime_put() to the caller which is not very useful. Returning an error code from pm_runtime_put() merely means that it has not queued up a work item to check whether or not the device can be suspended and there are many perfectly valid situations in which that can happen, like after writing "on" to the devices' runtime PM "control" attribute in sysfs for one example. Modify phy_pm_runtime_put() to discard the pm_runtime_put() return value and change its return type to void. Also drop the redundant pm_runtime_enabled() call from there. No intentional functional impact. This will facilitate a planned change of the pm_runtime_put() return type to void in the future. Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/2556645.jE0xQCEvom@rafael.j.wysocki Signed-off-by: Vinod Koul --- include/linux/phy/phy.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 2af0d01ebb39..ea47975e288a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -243,7 +243,7 @@ static inline void *phy_get_drvdata(struct phy *phy) #if IS_ENABLED(CONFIG_GENERIC_PHY) int phy_pm_runtime_get(struct phy *phy); int phy_pm_runtime_get_sync(struct phy *phy); -int phy_pm_runtime_put(struct phy *phy); +void phy_pm_runtime_put(struct phy *phy); int phy_pm_runtime_put_sync(struct phy *phy); int phy_init(struct phy *phy); int phy_exit(struct phy *phy); @@ -324,11 +324,8 @@ static inline int phy_pm_runtime_get_sync(struct phy *phy) return -ENOSYS; } -static inline int phy_pm_runtime_put(struct phy *phy) +static inline void phy_pm_runtime_put(struct phy *phy) { - if (!phy) - return 0; - return -ENOSYS; } static inline int phy_pm_runtime_put_sync(struct phy *phy) -- cgit v1.2.3 From a722de305eacb382a5d306f9f8e502f81bab682d Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Sun, 14 Dec 2025 11:51:34 +0000 Subject: soc: apple: Add hardware tunable support Various hardware, like the Type-C PHY or the Thunderbolt/USB4 NHI, present on Apple SoCs need machine-specific tunables passed from our bootloader m1n1 to the device tree. Add generic helpers so that we don't have to duplicate this across multiple drivers. Reviewed-by: Alyssa Rosenzweig Reviewed-by: Neal Gompa Reviewed-by: Janne Grunau Signed-off-by: Sven Peter Link: https://patch.msgid.link/20251214-b4-atcphy-v3-1-ba82b20e9459@kernel.org Signed-off-by: Vinod Koul --- include/linux/soc/apple/tunable.h | 62 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/soc/apple/tunable.h (limited to 'include/linux') diff --git a/include/linux/soc/apple/tunable.h b/include/linux/soc/apple/tunable.h new file mode 100644 index 000000000000..531ca814cd02 --- /dev/null +++ b/include/linux/soc/apple/tunable.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple Silicon hardware tunable support + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * Copyright (C) The Asahi Linux Contributors + */ + +#ifndef _LINUX_SOC_APPLE_TUNABLE_H_ +#define _LINUX_SOC_APPLE_TUNABLE_H_ + +#include +#include + +/** + * Struct to store an Apple Silicon hardware tunable. + * + * Each tunable is a list with each entry containing a offset into the MMIO + * region, a mask of bits to be cleared and a set of bits to be set. These + * tunables are passed along by the previous boot stages and vary from device + * to device such that they cannot be hardcoded in the individual drivers. + * + * @param sz Number of [offset, mask, value] tuples stored in values. + * @param values [offset, mask, value] array. + */ +struct apple_tunable { + size_t sz; + struct { + u32 offset; + u32 mask; + u32 value; + } values[] __counted_by(sz); +}; + +/** + * Parse an array of hardware tunables from the device tree. + * + * @dev: Device node used for devm_kzalloc internally. + * @np: Device node which contains the tunable array. + * @name: Name of the device tree property which contains the tunables. + * @res: Resource to which the tunables will be applied, used for bound checking + * + * @return: devres allocated struct on success or PTR_ERR on failure. + */ +struct apple_tunable *devm_apple_tunable_parse(struct device *dev, + struct device_node *np, + const char *name, + struct resource *res); + +/** + * Apply a previously loaded hardware tunable. + * + * @param regs: MMIO to which the tunable will be applied. + * @param tunable: Pointer to the tunable. + */ +void apple_tunable_apply(void __iomem *regs, struct apple_tunable *tunable); + +#endif -- cgit v1.2.3 From 031314bd37cb6ce352b1300ffd4e07a7bebce1ef Mon Sep 17 00:00:00 2001 From: Pritam Manohar Sutar Date: Mon, 24 Nov 2025 16:34:49 +0530 Subject: phy: exynos5-usbdrd: support HS phy for ExynosAutov920 Enable UTMI+ phy support for this SoC which is very similar to what the existing Exynos850 supports. Add required change in phy driver to support HS phy for this SoC. Reviewed-by: Alim Akhtar Signed-off-by: Pritam Manohar Sutar Link: https://patch.msgid.link/20251124110453.2887437-3-pritam.sutar@samsung.com Signed-off-by: Vinod Koul --- include/linux/soc/samsung/exynos-regs-pmu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index 532c6c2d1195..ab4d8be0e073 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -1015,4 +1015,6 @@ #define GS101_GRP2_INTR_BID_UPEND (0x0208) #define GS101_GRP2_INTR_BID_CLEAR (0x020c) +/* exynosautov920 */ +#define EXYNOSAUTOV920_PHY_CTRL_USB20 (0x0710) #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ -- cgit v1.2.3 From 2fdfc1bb752e393561cf532f5d54607d70e464bc Mon Sep 17 00:00:00 2001 From: Pritam Manohar Sutar Date: Mon, 24 Nov 2025 16:34:53 +0530 Subject: phy: exynos5-usbdrd: support SS combo phy for ExynosAutov920 Update phy driver to enable SS combo phy for this SoC. New registers' definitions, phy ops (init/exit), and dedicated phy driver data structure are added for SS combo phy. Add these changes in the driver to support SS combo phy for this SoC. Reviewed-by: Alim Akhtar Signed-off-by: Pritam Manohar Sutar Link: https://patch.msgid.link/20251124110453.2887437-7-pritam.sutar@samsung.com Signed-off-by: Vinod Koul --- include/linux/soc/samsung/exynos-regs-pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index ab4d8be0e073..db8a7ca81080 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -1017,4 +1017,5 @@ /* exynosautov920 */ #define EXYNOSAUTOV920_PHY_CTRL_USB20 (0x0710) +#define EXYNOSAUTOV920_PHY_CTRL_USB31 (0x0714) #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ -- cgit v1.2.3 From c0fef45dbab06238e96e221f7c0a8fd2d569f7dd Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 24 Nov 2025 11:39:52 +0100 Subject: char/mwave: drop it When I tried to clean up the driver a bit, Arnd noted: > According to thinkwiki.de, the 3780i modem was only used in a > couple of Thinkpad models that are now over 25 years old, using > Pentium II processors, and they all have a physical RS232 port > that can be used to connect an external modem instead. > > Maybe we can just retire this driver? So instead of the clean up, drop the driver altogether. Signed-off-by: Jiri Slaby (SUSE) Suggested-by: Arnd Bergmann Link: https://lore.kernel.org/all/b8834e5d-fdde-4b1a-8757-288dddc507a9@app.fastmail.com/ Link: https://patch.msgid.link/20251124103952.995229-1-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/miscdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 7d0aa718499c..fa9000f68523 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -52,7 +52,6 @@ #define PXA3XX_GCU_MINOR 197 #define TUN_MINOR 200 #define CUSE_MINOR 203 -#define MWAVE_MINOR 219 /* ACP/Mwave Modem */ #define MPT_MINOR 220 #define MPT2SAS_MINOR 221 #define MPT3SAS_MINOR 222 -- cgit v1.2.3 From 4a9ba211d0264131dcfca0cbc10bff5ff277ff0a Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 18 Dec 2025 22:21:45 +0530 Subject: bus: mhi: host: Drop the auto_queue support Now that the only user of the 'auto_queue' feature, (QRTR) has been converted to manage the buffers on its own, drop the code related to it. Signed-off-by: Manivannan Sadhasivam Reviewed-by: Loic Poulain Reviewed-by: Jeff Hugo Link: https://patch.msgid.link/20251218-qrtr-fix-v2-2-c7499bfcfbe0@oss.qualcomm.com --- include/linux/mhi.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mhi.h b/include/linux/mhi.h index dd372b0123a6..88ccb3e14f48 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -215,7 +215,6 @@ enum mhi_db_brst_mode { * @lpm_notify: The channel master requires low power mode notifications * @offload_channel: The client manages the channel completely * @doorbell_mode_switch: Channel switches to doorbell mode on M0 transition - * @auto_queue: Framework will automatically queue buffers for DL traffic * @wake-capable: Channel capable of waking up the system */ struct mhi_channel_config { @@ -232,7 +231,6 @@ struct mhi_channel_config { bool lpm_notify; bool offload_channel; bool doorbell_mode_switch; - bool auto_queue; bool wake_capable; }; @@ -743,18 +741,6 @@ void mhi_device_put(struct mhi_device *mhi_dev); */ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); -/** - * mhi_prepare_for_transfer_autoqueue - Setup UL and DL channels with auto queue - * buffers for DL traffic - * @mhi_dev: Device associated with the channels - * - * Allocate and initialize the channel context and also issue the START channel - * command to both channels. Channels can be started only if both host and - * device execution environments match and channels are in a DISABLED state. - * The MHI core will automatically allocate and queue buffers for the DL traffic. - */ -int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); - /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. * Issue the RESET channel command and let the -- cgit v1.2.3 From f7386f545e49e5e6229a14d92b39340d155b0b3f Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Mon, 3 Nov 2025 22:29:08 +0100 Subject: sysctl: Remove unused ctl_table forward declarations Remove superfluous forward declarations of ctl_table from header files where they are no longer needed. These declarations were left behind after sysctl code refactoring and cleanup. Reviewed-by: Jan Kara Acked-by: Muchun Song Reviewed-by: Petr Mladek Acked-by: Paolo Abeni Signed-off-by: Joel Granados --- include/linux/fs.h | 1 - include/linux/hugetlb.h | 2 -- include/linux/printk.h | 1 - 3 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 04ceeca12a0d..77f6302fdced 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3487,7 +3487,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); -struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 019a1c5281e4..18d1c4ecc4f9 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -16,8 +16,6 @@ #include #include -struct ctl_table; -struct user_struct; struct mmu_gather; struct node; diff --git a/include/linux/printk.h b/include/linux/printk.h index 45c663124c9b..63d516c873b4 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -78,7 +78,6 @@ extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE]; -struct ctl_table; extern int suppress_printk; -- cgit v1.2.3 From 6036dc03c39a3cb0df14899f29323b6b4b58dfe9 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Fri, 5 Dec 2025 11:18:43 +0100 Subject: sysctl: Add CONFIG_PROC_SYSCTL guards for converter macros Wrap sysctl converter macros with CONFIG_PROC_SYSCTL conditional compilation. When CONFIG_PROC_SYSCTL is disabled, provide stub implementations that return -ENOSYS to prevent link errors while maintaining API compatibility. This ensures converter macros are only compiled when procfs sysctl support is enabled in the kernel configuration. Signed-off-by: Joel Granados --- include/linux/sysctl.h | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 288fe0055cd5..0a64212a0ceb 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -73,6 +73,7 @@ extern const int sysctl_vals[]; #define SYSCTL_USER_TO_KERN(dir) (!!(dir)) #define SYSCTL_KERN_TO_USER(dir) (!dir) +#ifdef CONFIG_PROC_SYSCTL #define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \ int sysctl_user_to_kern_int_conv##name(const bool *negp, \ const unsigned long *u_ptr,\ @@ -173,6 +174,48 @@ int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr, \ return 0; \ } +#else // CONFIG_PROC_SYSCTL +#define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \ +int sysctl_user_to_kern_int_conv##name(const bool *negp, \ + const unsigned long *u_ptr,\ + int *k_ptr) \ +{ \ + return -ENOSYS; \ +} + +#define SYSCTL_KERN_TO_USER_INT_CONV(name, k_ptr_op) \ +int sysctl_kern_to_user_int_conv##name(bool *negp, \ + unsigned long *u_ptr, \ + const int *k_ptr) \ +{ \ + return -ENOSYS; \ +} + +#define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ + k_ptr_range_check) \ +int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ + int dir, const struct ctl_table *tbl) \ +{ \ + return -ENOSYS; \ +} + +#define SYSCTL_USER_TO_KERN_UINT_CONV(name, u_ptr_op) \ +int sysctl_user_to_kern_uint_conv##name(const unsigned long *u_ptr,\ + unsigned int *k_ptr) \ +{ \ + return -ENOSYS; \ +} + +#define SYSCTL_UINT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ + k_ptr_range_check) \ +int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr, \ + int dir, const struct ctl_table *tbl) \ +{ \ + return -ENOSYS; \ +} + +#endif // CONFIG_PROC_SYSCTL + extern const unsigned long sysctl_long_vals[]; -- cgit v1.2.3 From 8fc344a5af7e73178e6ac54d396327655e9ea358 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Fri, 28 Nov 2025 21:53:00 +0100 Subject: sysctl: Replace UINT converter macros with functions Replace the SYSCTL_USER_TO_KERN_UINT_CONV and SYSCTL_UINT_CONV_CUSTOM macros with functions with the same logic. This makes debugging easier and aligns with the functions preference described in coding-style.rst. Update the only user of this API: pipe.c. Signed-off-by: Joel Granados --- include/linux/sysctl.h | 63 ++++++-------------------------------------------- 1 file changed, 7 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 0a64212a0ceb..d712992789f0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -135,45 +135,6 @@ int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ return user_to_kern(negp, u_ptr, k_ptr); \ return 0; \ } - -#define SYSCTL_USER_TO_KERN_UINT_CONV(name, u_ptr_op) \ -int sysctl_user_to_kern_uint_conv##name(const unsigned long *u_ptr,\ - unsigned int *k_ptr) \ -{ \ - unsigned long u = u_ptr_op(*u_ptr); \ - if (u > UINT_MAX) \ - return -EINVAL; \ - WRITE_ONCE(*k_ptr, u); \ - return 0; \ -} - -#define SYSCTL_UINT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ - k_ptr_range_check) \ -int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr, \ - int dir, const struct ctl_table *tbl) \ -{ \ - if (SYSCTL_KERN_TO_USER(dir)) \ - return kern_to_user(u_ptr, k_ptr); \ - \ - if (k_ptr_range_check) { \ - unsigned int tmp_k; \ - int ret; \ - if (!tbl) \ - return -EINVAL; \ - ret = user_to_kern(u_ptr, &tmp_k); \ - if (ret) \ - return ret; \ - if ((tbl->extra1 && \ - *(unsigned int *)tbl->extra1 > tmp_k) || \ - (tbl->extra2 && \ - *(unsigned int *)tbl->extra2 < tmp_k)) \ - return -ERANGE; \ - WRITE_ONCE(*k_ptr, tmp_k); \ - } else \ - return user_to_kern(u_ptr, k_ptr); \ - return 0; \ -} - #else // CONFIG_PROC_SYSCTL #define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \ int sysctl_user_to_kern_int_conv##name(const bool *negp, \ @@ -199,24 +160,8 @@ int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ return -ENOSYS; \ } -#define SYSCTL_USER_TO_KERN_UINT_CONV(name, u_ptr_op) \ -int sysctl_user_to_kern_uint_conv##name(const unsigned long *u_ptr,\ - unsigned int *k_ptr) \ -{ \ - return -ENOSYS; \ -} - -#define SYSCTL_UINT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ - k_ptr_range_check) \ -int do_proc_uint_conv##name(unsigned long *u_ptr, unsigned int *k_ptr, \ - int dir, const struct ctl_table *tbl) \ -{ \ - return -ENOSYS; \ -} - #endif // CONFIG_PROC_SYSCTL - extern const unsigned long sysctl_long_vals[]; typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, @@ -239,6 +184,13 @@ int proc_douintvec_conv(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(unsigned long *lvalp, unsigned int *valp, int write, const struct ctl_table *table)); +int proc_uint_k2u_conv(ulong *u_ptr, const uint *k_ptr); +int proc_uint_u2k_conv_uop(const ulong *u_ptr, uint *k_ptr, + ulong (*u_ptr_op)(const ulong)); +int proc_uint_conv(ulong *u_ptr, uint *k_ptr, int dir, + const struct ctl_table *tbl, bool k_ptr_range_check, + int (*user_to_kern)(const ulong *u_ptr, uint *k_ptr), + int (*kern_to_user)(ulong *u_ptr, const uint *k_ptr)); int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); @@ -249,7 +201,6 @@ int proc_doulongvec_minmax_conv(const struct ctl_table *table, int dir, int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_do_static_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int sysctl_kern_to_user_uint_conv(unsigned long *u_ptr, const unsigned int *k_ptr); /* * Register a set of sysctl names by calling register_sysctl -- cgit v1.2.3 From ef153851af5b05c23b3484e7eebaadd18f2da6a9 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Wed, 3 Dec 2025 22:42:32 +0100 Subject: sysctl: Replace unidirectional INT converter macros with functions Replace SYSCTL_USER_TO_KERN_INT_CONV and SYSCTL_KERN_TO_USER_INT_CONV macros with function implementing the same logic.This makes debugging easier and aligns with the functions preference described in coding-style.rst. Update all jiffies converters to use explicit function implementations instead of macro-generated versions. Signed-off-by: Joel Granados --- include/linux/sysctl.h | 56 +++++++------------------------------------------- 1 file changed, 7 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index d712992789f0..655fb85ec292 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -74,40 +74,6 @@ extern const int sysctl_vals[]; #define SYSCTL_KERN_TO_USER(dir) (!dir) #ifdef CONFIG_PROC_SYSCTL -#define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \ -int sysctl_user_to_kern_int_conv##name(const bool *negp, \ - const unsigned long *u_ptr,\ - int *k_ptr) \ -{ \ - unsigned long u = u_ptr_op(*u_ptr); \ - if (*negp) { \ - if (u > (unsigned long) INT_MAX + 1) \ - return -EINVAL; \ - WRITE_ONCE(*k_ptr, -u); \ - } else { \ - if (u > (unsigned long) INT_MAX) \ - return -EINVAL; \ - WRITE_ONCE(*k_ptr, u); \ - } \ - return 0; \ -} - -#define SYSCTL_KERN_TO_USER_INT_CONV(name, k_ptr_op) \ -int sysctl_kern_to_user_int_conv##name(bool *negp, \ - unsigned long *u_ptr, \ - const int *k_ptr) \ -{ \ - int val = READ_ONCE(*k_ptr); \ - if (val < 0) { \ - *negp = true; \ - *u_ptr = -k_ptr_op((unsigned long)val); \ - } else { \ - *negp = false; \ - *u_ptr = k_ptr_op((unsigned long)val); \ - } \ - return 0; \ -} - /** * To range check on a converted value, use a temp k_ptr * When checking range, value should be within (tbl->extra1, tbl->extra2) @@ -135,22 +101,8 @@ int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ return user_to_kern(negp, u_ptr, k_ptr); \ return 0; \ } -#else // CONFIG_PROC_SYSCTL -#define SYSCTL_USER_TO_KERN_INT_CONV(name, u_ptr_op) \ -int sysctl_user_to_kern_int_conv##name(const bool *negp, \ - const unsigned long *u_ptr,\ - int *k_ptr) \ -{ \ - return -ENOSYS; \ -} -#define SYSCTL_KERN_TO_USER_INT_CONV(name, k_ptr_op) \ -int sysctl_kern_to_user_int_conv##name(bool *negp, \ - unsigned long *u_ptr, \ - const int *k_ptr) \ -{ \ - return -ENOSYS; \ -} +#else // CONFIG_PROC_SYSCTL #define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ k_ptr_range_check) \ @@ -170,6 +122,7 @@ typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); + int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_dointvec_minmax(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos); @@ -177,6 +130,11 @@ int proc_dointvec_conv(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(bool *negp, unsigned long *u_ptr, int *k_ptr, int dir, const struct ctl_table *table)); +int proc_int_k2u_conv_kop(ulong *u_ptr, const int *k_ptr, bool *negp, + ulong (*k_ptr_op)(const ulong)); +int proc_int_u2k_conv_uop(const ulong *u_ptr, int *k_ptr, const bool *negp, + ulong (*u_ptr_op)(const ulong)); + int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From d174174c6776a340f5c25aab1ac47a2dd950f380 Mon Sep 17 00:00:00 2001 From: Joel Granados Date: Thu, 4 Dec 2025 13:11:58 +0100 Subject: sysctl: replace SYSCTL_INT_CONV_CUSTOM macro with functions Remove SYSCTL_INT_CONV_CUSTOM and replace it with proc_int_conv. This converter function expects a negp argument as it can take on negative values. Update all jiffies converters to use explicit function calls. Remove SYSCTL_CONV_IDENTITY as it is no longer used. Signed-off-by: Joel Granados --- include/linux/sysctl.h | 46 ++++------------------------------------------ 1 file changed, 4 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 655fb85ec292..2886fbceb5d6 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -59,7 +59,6 @@ extern const int sysctl_vals[]; #define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) #define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) -#define SYSCTL_CONV_IDENTITY(val) (val) /** * * "dir" originates from read_iter (dir = 0) or write_iter (dir = 1) @@ -73,47 +72,6 @@ extern const int sysctl_vals[]; #define SYSCTL_USER_TO_KERN(dir) (!!(dir)) #define SYSCTL_KERN_TO_USER(dir) (!dir) -#ifdef CONFIG_PROC_SYSCTL -/** - * To range check on a converted value, use a temp k_ptr - * When checking range, value should be within (tbl->extra1, tbl->extra2) - */ -#define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ - k_ptr_range_check) \ -int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ - int dir, const struct ctl_table *tbl) \ -{ \ - if (SYSCTL_KERN_TO_USER(dir)) \ - return kern_to_user(negp, u_ptr, k_ptr); \ - \ - if (k_ptr_range_check) { \ - int tmp_k, ret; \ - if (!tbl) \ - return -EINVAL; \ - ret = user_to_kern(negp, u_ptr, &tmp_k); \ - if (ret) \ - return ret; \ - if ((tbl->extra1 && *(int *)tbl->extra1 > tmp_k) || \ - (tbl->extra2 && *(int *)tbl->extra2 < tmp_k)) \ - return -EINVAL; \ - WRITE_ONCE(*k_ptr, tmp_k); \ - } else \ - return user_to_kern(negp, u_ptr, k_ptr); \ - return 0; \ -} - -#else // CONFIG_PROC_SYSCTL - -#define SYSCTL_INT_CONV_CUSTOM(name, user_to_kern, kern_to_user, \ - k_ptr_range_check) \ -int do_proc_int_conv##name(bool *negp, unsigned long *u_ptr, int *k_ptr,\ - int dir, const struct ctl_table *tbl) \ -{ \ - return -ENOSYS; \ -} - -#endif // CONFIG_PROC_SYSCTL - extern const unsigned long sysctl_long_vals[]; typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, @@ -134,6 +92,10 @@ int proc_int_k2u_conv_kop(ulong *u_ptr, const int *k_ptr, bool *negp, ulong (*k_ptr_op)(const ulong)); int proc_int_u2k_conv_uop(const ulong *u_ptr, int *k_ptr, const bool *negp, ulong (*u_ptr_op)(const ulong)); +int proc_int_conv(bool *negp, ulong *u_ptr, int *k_ptr, int dir, + const struct ctl_table *tbl, bool k_ptr_range_check, + int (*user_to_kern)(const bool *negp, const ulong *u_ptr, int *k_ptr), + int (*kern_to_user)(bool *negp, ulong *u_ptr, const int *k_ptr)); int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *); int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, -- cgit v1.2.3 From 6e0e8375f2e6854e8c35faa638f4448e3b8209af Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Fri, 26 Dec 2025 02:02:37 +0200 Subject: usb: isp1362-hcd: remove Philips ISP1362 USB OTG controller driver The last user of the platform driver was a Blackfin BF533 powered board, and it was removed in commit 4ba66a976072 ("arch: remove blackfin port") along with the whole Blackfin architecture support 7 years ago. Signed-off-by: Vladimir Zapolskiy Link: https://patch.msgid.link/20251226000237.1440642-1-vz@mleia.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/isp1362.h | 47 --------------------------------------------- 1 file changed, 47 deletions(-) delete mode 100644 include/linux/usb/isp1362.h (limited to 'include/linux') diff --git a/include/linux/usb/isp1362.h b/include/linux/usb/isp1362.h deleted file mode 100644 index 5356c4ae386e..000000000000 --- a/include/linux/usb/isp1362.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * board initialization code should put one of these into dev->platform_data - * and place the isp1362 onto platform_bus. - */ - -#ifndef __LINUX_USB_ISP1362_H__ -#define __LINUX_USB_ISP1362_H__ - -struct isp1362_platform_data { - /* Enable internal pulldown resistors on downstream ports */ - unsigned sel15Kres:1; - /* Clock cannot be stopped */ - unsigned clknotstop:1; - /* On-chip overcurrent protection */ - unsigned oc_enable:1; - /* INT output polarity */ - unsigned int_act_high:1; - /* INT edge or level triggered */ - unsigned int_edge_triggered:1; - /* DREQ output polarity */ - unsigned dreq_act_high:1; - /* DACK input polarity */ - unsigned dack_act_high:1; - /* chip can be resumed via H_WAKEUP pin */ - unsigned remote_wakeup_connected:1; - /* Switch or not to switch (keep always powered) */ - unsigned no_power_switching:1; - /* Ganged port power switching (0) or individual port power switching (1) */ - unsigned power_switching_mode:1; - /* Given port_power, msec/2 after power on till power good */ - u8 potpg; - /* Hardware reset set/clear */ - void (*reset) (struct device *dev, int set); - /* Clock start/stop */ - void (*clock) (struct device *dev, int start); - /* Inter-io delay (ns). The chip is picky about access timings; it - * expects at least: - * 110ns delay between consecutive accesses to DATA_REG, - * 300ns delay between access to ADDR_REG and DATA_REG (registers) - * 462ns delay between access to ADDR_REG and DATA_REG (buffer memory) - * WE MUST NOT be activated during these intervals (even without CS!) - */ - void (*delay) (struct device *dev, unsigned int delay); -}; - -#endif -- cgit v1.2.3 From da142f3d373a6ddaca0119615a8db2175ddc4121 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 5 Dec 2025 15:26:55 -0800 Subject: KVM: Remove subtle "struct kvm_stats_desc" pseudo-overlay Remove KVM's internal pseudo-overlay of kvm_stats_desc, which subtly aliases the flexible name[] in the uAPI definition with a fixed-size array of the same name. The unusual embedded structure results in compiler warnings due to -Wflex-array-member-not-at-end, and also necessitates an extra level of dereferencing in KVM. To avoid the "overlay", define the uAPI structure to have a fixed-size name when building for the kernel. Opportunistically clean up the indentation for the stats macros, and replace spaces with tabs. No functional change intended. Reported-by: Gustavo A. R. Silva Closes: https://lore.kernel.org/all/aPfNKRpLfhmhYqfP@kspp Acked-by: Marc Zyngier Acked-by: Christian Borntraeger [..] Acked-by: Anup Patel Reviewed-by: Bibo Mao Acked-by: Gustavo A. R. Silva Link: https://patch.msgid.link/20251205232655.445294-1-seanjc@google.com Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 83 ++++++++++++++++++++---------------------------- 1 file changed, 35 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d93f75b05ae2..7428d9949382 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1927,56 +1927,43 @@ enum kvm_stat_kind { struct kvm_stat_data { struct kvm *kvm; - const struct _kvm_stats_desc *desc; + const struct kvm_stats_desc *desc; enum kvm_stat_kind kind; }; -struct _kvm_stats_desc { - struct kvm_stats_desc desc; - char name[KVM_STATS_NAME_SIZE]; -}; - -#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ - .flags = type | unit | base | \ - BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ - BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ - BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ - .exponent = exp, \ - .size = sz, \ +#define STATS_DESC_COMMON(type, unit, base, exp, sz, bsz) \ + .flags = type | unit | base | \ + BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) | \ + BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) | \ + BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK), \ + .exponent = exp, \ + .size = sz, \ .bucket_size = bsz -#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, generic.stat) \ - }, \ - .name = #stat, \ - } -#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vm_stat, stat) \ - }, \ - .name = #stat, \ - } -#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ - { \ - { \ - STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ - .offset = offsetof(struct kvm_vcpu_stat, stat) \ - }, \ - .name = #stat, \ - } +#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, generic.stat), \ + .name = #stat, \ +} +#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, generic.stat), \ + .name = #stat, \ +} +#define VM_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vm_stat, stat), \ + .name = #stat, \ +} +#define VCPU_STATS_DESC(stat, type, unit, base, exp, sz, bsz) \ +{ \ + STATS_DESC_COMMON(type, unit, base, exp, sz, bsz), \ + .offset = offsetof(struct kvm_vcpu_stat, stat), \ + .name = #stat, \ +} /* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */ #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz) \ SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz) @@ -2053,7 +2040,7 @@ struct _kvm_stats_desc { STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, - const struct _kvm_stats_desc *desc, + const struct kvm_stats_desc *desc, void *stats, size_t size_stats, char __user *user_buffer, size_t size, loff_t *offset); @@ -2098,9 +2085,9 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value) extern const struct kvm_stats_header kvm_vm_stats_header; -extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; +extern const struct kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; -extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; +extern const struct kvm_stats_desc kvm_vcpu_stats_desc[]; #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) -- cgit v1.2.3 From 80c70bfb95cdbe0c644070f4ca4754a60f0a4830 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 8 Jan 2026 11:50:12 +0100 Subject: scatterlist: introduce sg_nents_for_dma() helper Sometimes the user needs to split each entry on the mapped scatter list due to DMA length constrains. This helper returns a number of entities assuming that each of them is not bigger than supplied maximum length. Reviewed-by: Bjorn Andersson Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20260108105619.3513561-2-andriy.shevchenko@linux.intel.com Signed-off-by: Vinod Koul --- include/linux/scatterlist.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 29f6ceb98d74..6de1a2434299 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -441,6 +441,8 @@ static inline void sg_init_marker(struct scatterlist *sgl, int sg_nents(struct scatterlist *sg); int sg_nents_for_len(struct scatterlist *sg, u64 len); +int sg_nents_for_dma(struct scatterlist *sgl, unsigned int sglen, size_t len); + struct scatterlist *sg_last(struct scatterlist *s, unsigned int); void sg_init_table(struct scatterlist *, unsigned int); void sg_init_one(struct scatterlist *, const void *, unsigned int); -- cgit v1.2.3 From 5083dba0fde5446c00ee1a82a3911c8f88a2c72e Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 12 Jan 2026 14:46:09 +0100 Subject: units: Add HZ_PER_GHZ The is going to be a new user of the HZ_PER_GHZ definition besides possibly existing ones. Add that one to the header. While at it, split Hz and kHz groups of the multipliers for better maintenance and readability. Signed-off-by: Andy Shevchenko Reviewed-by: Andi Shyti Reviewed-by: Linus Walleij Reviewed-by: Wolfram Sang Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/20260112134900.4142954-2-andriy.shevchenko@linux.intel.com --- include/linux/units.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index 00e15de33eca..0c296a004e89 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -25,9 +25,12 @@ #define MICROHZ_PER_HZ 1000000UL #define MILLIHZ_PER_HZ 1000UL +/* Hz based multipliers */ #define HZ_PER_KHZ 1000UL #define HZ_PER_MHZ 1000000UL +#define HZ_PER_GHZ 1000000000UL +/* kHz based multipliers */ #define KHZ_PER_MHZ 1000UL #define KHZ_PER_GHZ 1000000UL -- cgit v1.2.3 From f8a6e5eac701369afb5d69aba875dc5fec93003d Mon Sep 17 00:00:00 2001 From: Vladimir Zapolskiy Date: Tue, 13 Jan 2026 17:11:40 +0200 Subject: Input: adp5589 - remove a leftover header file MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit 3bdbd0858df6 ("Input: adp5589: remove the driver") the last user of include/linux/input/adp5589.h was removed along with the whole driver, thus the header file can be also removed. Signed-off-by: Vladimir Zapolskiy Reviewed-by: Laurent Pinchart Reviewed-by: Nuno Sá Fixes: 3bdbd0858df6 ("Input: adp5589: remove the driver") Link: https://patch.msgid.link/20260113151140.3843753-1-vz@mleia.com Signed-off-by: Dmitry Torokhov --- include/linux/input/adp5589.h | 180 ------------------------------------------ 1 file changed, 180 deletions(-) delete mode 100644 include/linux/input/adp5589.h (limited to 'include/linux') diff --git a/include/linux/input/adp5589.h b/include/linux/input/adp5589.h deleted file mode 100644 index 0e4742c8c81e..000000000000 --- a/include/linux/input/adp5589.h +++ /dev/null @@ -1,180 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Analog Devices ADP5589/ADP5585 I/O Expander and QWERTY Keypad Controller - * - * Copyright 2010-2011 Analog Devices Inc. - */ - -#ifndef _ADP5589_H -#define _ADP5589_H - -/* - * ADP5589 specific GPI and Keymap defines - */ - -#define ADP5589_KEYMAPSIZE 88 - -#define ADP5589_GPI_PIN_ROW0 97 -#define ADP5589_GPI_PIN_ROW1 98 -#define ADP5589_GPI_PIN_ROW2 99 -#define ADP5589_GPI_PIN_ROW3 100 -#define ADP5589_GPI_PIN_ROW4 101 -#define ADP5589_GPI_PIN_ROW5 102 -#define ADP5589_GPI_PIN_ROW6 103 -#define ADP5589_GPI_PIN_ROW7 104 -#define ADP5589_GPI_PIN_COL0 105 -#define ADP5589_GPI_PIN_COL1 106 -#define ADP5589_GPI_PIN_COL2 107 -#define ADP5589_GPI_PIN_COL3 108 -#define ADP5589_GPI_PIN_COL4 109 -#define ADP5589_GPI_PIN_COL5 110 -#define ADP5589_GPI_PIN_COL6 111 -#define ADP5589_GPI_PIN_COL7 112 -#define ADP5589_GPI_PIN_COL8 113 -#define ADP5589_GPI_PIN_COL9 114 -#define ADP5589_GPI_PIN_COL10 115 -#define GPI_LOGIC1 116 -#define GPI_LOGIC2 117 - -#define ADP5589_GPI_PIN_ROW_BASE ADP5589_GPI_PIN_ROW0 -#define ADP5589_GPI_PIN_ROW_END ADP5589_GPI_PIN_ROW7 -#define ADP5589_GPI_PIN_COL_BASE ADP5589_GPI_PIN_COL0 -#define ADP5589_GPI_PIN_COL_END ADP5589_GPI_PIN_COL10 - -#define ADP5589_GPI_PIN_BASE ADP5589_GPI_PIN_ROW_BASE -#define ADP5589_GPI_PIN_END ADP5589_GPI_PIN_COL_END - -#define ADP5589_GPIMAPSIZE_MAX (ADP5589_GPI_PIN_END - ADP5589_GPI_PIN_BASE + 1) - -/* - * ADP5585 specific GPI and Keymap defines - */ - -#define ADP5585_KEYMAPSIZE 30 - -#define ADP5585_GPI_PIN_ROW0 37 -#define ADP5585_GPI_PIN_ROW1 38 -#define ADP5585_GPI_PIN_ROW2 39 -#define ADP5585_GPI_PIN_ROW3 40 -#define ADP5585_GPI_PIN_ROW4 41 -#define ADP5585_GPI_PIN_ROW5 42 -#define ADP5585_GPI_PIN_COL0 43 -#define ADP5585_GPI_PIN_COL1 44 -#define ADP5585_GPI_PIN_COL2 45 -#define ADP5585_GPI_PIN_COL3 46 -#define ADP5585_GPI_PIN_COL4 47 -#define GPI_LOGIC 48 - -#define ADP5585_GPI_PIN_ROW_BASE ADP5585_GPI_PIN_ROW0 -#define ADP5585_GPI_PIN_ROW_END ADP5585_GPI_PIN_ROW5 -#define ADP5585_GPI_PIN_COL_BASE ADP5585_GPI_PIN_COL0 -#define ADP5585_GPI_PIN_COL_END ADP5585_GPI_PIN_COL4 - -#define ADP5585_GPI_PIN_BASE ADP5585_GPI_PIN_ROW_BASE -#define ADP5585_GPI_PIN_END ADP5585_GPI_PIN_COL_END - -#define ADP5585_GPIMAPSIZE_MAX (ADP5585_GPI_PIN_END - ADP5585_GPI_PIN_BASE + 1) - -struct adp5589_gpi_map { - unsigned short pin; - unsigned short sw_evt; -}; - -/* scan_cycle_time */ -#define ADP5589_SCAN_CYCLE_10ms 0 -#define ADP5589_SCAN_CYCLE_20ms 1 -#define ADP5589_SCAN_CYCLE_30ms 2 -#define ADP5589_SCAN_CYCLE_40ms 3 - -/* RESET_CFG */ -#define RESET_PULSE_WIDTH_500us 0 -#define RESET_PULSE_WIDTH_1ms 1 -#define RESET_PULSE_WIDTH_2ms 2 -#define RESET_PULSE_WIDTH_10ms 3 - -#define RESET_TRIG_TIME_0ms (0 << 2) -#define RESET_TRIG_TIME_1000ms (1 << 2) -#define RESET_TRIG_TIME_1500ms (2 << 2) -#define RESET_TRIG_TIME_2000ms (3 << 2) -#define RESET_TRIG_TIME_2500ms (4 << 2) -#define RESET_TRIG_TIME_3000ms (5 << 2) -#define RESET_TRIG_TIME_3500ms (6 << 2) -#define RESET_TRIG_TIME_4000ms (7 << 2) - -#define RESET_PASSTHRU_EN (1 << 5) -#define RESET1_POL_HIGH (1 << 6) -#define RESET1_POL_LOW (0 << 6) -#define RESET2_POL_HIGH (1 << 7) -#define RESET2_POL_LOW (0 << 7) - -/* ADP5589 Mask Bits: - * C C C C C C C C C C C | R R R R R R R R - * 1 9 8 7 6 5 4 3 2 1 0 | 7 6 5 4 3 2 1 0 - * 0 - * ---------------- BIT ------------------ - * 1 1 1 1 1 1 1 1 1 0 0 | 0 0 0 0 0 0 0 0 - * 8 7 6 5 4 3 2 1 0 9 8 | 7 6 5 4 3 2 1 0 - */ - -#define ADP_ROW(x) (1 << (x)) -#define ADP_COL(x) (1 << (x + 8)) -#define ADP5589_ROW_MASK 0xFF -#define ADP5589_COL_MASK 0xFF -#define ADP5589_COL_SHIFT 8 -#define ADP5589_MAX_ROW_NUM 7 -#define ADP5589_MAX_COL_NUM 10 - -/* ADP5585 Mask Bits: - * C C C C C | R R R R R R - * 4 3 2 1 0 | 5 4 3 2 1 0 - * - * ---- BIT -- ----------- - * 1 0 0 0 0 | 0 0 0 0 0 0 - * 0 9 8 7 6 | 5 4 3 2 1 0 - */ - -#define ADP5585_ROW_MASK 0x3F -#define ADP5585_COL_MASK 0x1F -#define ADP5585_ROW_SHIFT 0 -#define ADP5585_COL_SHIFT 6 -#define ADP5585_MAX_ROW_NUM 5 -#define ADP5585_MAX_COL_NUM 4 - -#define ADP5585_ROW(x) (1 << ((x) & ADP5585_ROW_MASK)) -#define ADP5585_COL(x) (1 << (((x) & ADP5585_COL_MASK) + ADP5585_COL_SHIFT)) - -/* Put one of these structures in i2c_board_info platform_data */ - -struct adp5589_kpad_platform_data { - unsigned keypad_en_mask; /* Keypad (Rows/Columns) enable mask */ - const unsigned short *keymap; /* Pointer to keymap */ - unsigned short keymapsize; /* Keymap size */ - bool repeat; /* Enable key repeat */ - bool en_keylock; /* Enable key lock feature (ADP5589 only)*/ - unsigned char unlock_key1; /* Unlock Key 1 (ADP5589 only) */ - unsigned char unlock_key2; /* Unlock Key 2 (ADP5589 only) */ - unsigned char unlock_timer; /* Time in seconds [0..7] between the two unlock keys 0=disable (ADP5589 only) */ - unsigned char scan_cycle_time; /* Time between consecutive scan cycles */ - unsigned char reset_cfg; /* Reset config */ - unsigned short reset1_key_1; /* Reset Key 1 */ - unsigned short reset1_key_2; /* Reset Key 2 */ - unsigned short reset1_key_3; /* Reset Key 3 */ - unsigned short reset2_key_1; /* Reset Key 1 */ - unsigned short reset2_key_2; /* Reset Key 2 */ - unsigned debounce_dis_mask; /* Disable debounce mask */ - unsigned pull_dis_mask; /* Disable all pull resistors mask */ - unsigned pullup_en_100k; /* Pull-Up 100k Enable Mask */ - unsigned pullup_en_300k; /* Pull-Up 300k Enable Mask */ - unsigned pulldown_en_300k; /* Pull-Down 300k Enable Mask */ - const struct adp5589_gpi_map *gpimap; - unsigned short gpimapsize; - const struct adp5589_gpio_platform_data *gpio_data; -}; - -struct i2c_client; /* forward declaration */ - -struct adp5589_gpio_platform_data { - int gpio_start; /* GPIO Chip base # */ -}; - -#endif -- cgit v1.2.3 From f9de0dd246ed14996e62c731ebccf162cb015ff9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 7 Jan 2026 16:25:40 +0100 Subject: USB: HCD: remove logic about which hcd is loaded It turns out that warning about which USB host controller is loaded before another one doesn't really matter. All that really is needed is the PCI softdep module loading logic, which has been present in the kernel ever since commit 05c92da0c524 ("usb: ohci/uhci - add soft dependencies on ehci_pci") So remove the warning messages, they are not useful, not needed, and only confuse people. As can be seen in the discussion at https://lore.kernel.org/r/20251230080014.3934590-1-chenhuacai@loongson.cn Cc: Huacai Chen Suggested-by: Alan Stern Reviewed-by: Huacai Chen Link: https://patch.msgid.link/2026010739-diffuser-shelter-e31c@gregkh Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index ac95e7c89df5..181db044c4d2 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -760,12 +760,6 @@ static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb, */ extern struct rw_semaphore ehci_cf_port_reset_rwsem; -/* Keep track of which host controller drivers are loaded */ -#define USB_UHCI_LOADED 0 -#define USB_OHCI_LOADED 1 -#define USB_EHCI_LOADED 2 -extern unsigned long usb_hcds_loaded; - #endif /* __KERNEL__ */ #endif /* __USB_CORE_HCD_H */ -- cgit v1.2.3 From f47c1b77d0a2a9c0d49ec14302e74f933398d1a3 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 1 Dec 2025 10:42:26 +0100 Subject: clk: Move clk_{save,restore}_context() to COMMON_CLK section The clk_save_context() and clk_restore_context() helpers are only implemented by the Common Clock Framework. They are not available when using legacy clock frameworks. Dummy implementations are provided, but only if no clock support is available at all. Hence when CONFIG_HAVE_CLK=y, but CONFIG_COMMON_CLK is not enabled: m68k-linux-gnu-ld: drivers/net/phy/air_en8811h.o: in function `en8811h_resume': air_en8811h.c:(.text+0x83e): undefined reference to `clk_restore_context' m68k-linux-gnu-ld: drivers/net/phy/air_en8811h.o: in function `en8811h_suspend': air_en8811h.c:(.text+0x856): undefined reference to `clk_save_context' Fix this by moving forward declarations and dummy implementions from the HAVE_CLK to the COMMON_CLK section. Fixes: 8b95d1ce3300c411 ("clk: Add functions to save/restore clock context en-masse") Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202511301553.eaEz1nEW-lkp@intel.com/ Signed-off-by: Geert Uytterhoeven Signed-off-by: Stephen Boyd --- include/linux/clk.h | 48 ++++++++++++++++++++++++------------------------ 1 file changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index b607482ca77e..64ff118ffb1a 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -228,6 +228,23 @@ int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk); */ void clk_rate_exclusive_put(struct clk *clk); +/** + * clk_save_context - save clock context for poweroff + * + * Saves the context of the clock register for powerstates in which the + * contents of the registers will be lost. Occurs deep within the suspend + * code so locking is not necessary. + */ +int clk_save_context(void); + +/** + * clk_restore_context - restore clock context after poweroff + * + * This occurs with all clocks enabled. Occurs deep within the resume code + * so locking is not necessary. + */ +void clk_restore_context(void); + #else static inline int clk_notifier_register(struct clk *clk, @@ -293,6 +310,13 @@ static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *cl static inline void clk_rate_exclusive_put(struct clk *clk) {} +static inline int clk_save_context(void) +{ + return 0; +} + +static inline void clk_restore_context(void) {} + #endif #ifdef CONFIG_HAVE_CLK_PREPARE @@ -933,23 +957,6 @@ struct clk *clk_get_parent(struct clk *clk); */ struct clk *clk_get_sys(const char *dev_id, const char *con_id); -/** - * clk_save_context - save clock context for poweroff - * - * Saves the context of the clock register for powerstates in which the - * contents of the registers will be lost. Occurs deep within the suspend - * code so locking is not necessary. - */ -int clk_save_context(void); - -/** - * clk_restore_context - restore clock context after poweroff - * - * This occurs with all clocks enabled. Occurs deep within the resume code - * so locking is not necessary. - */ -void clk_restore_context(void); - #else /* !CONFIG_HAVE_CLK */ static inline struct clk *clk_get(struct device *dev, const char *id) @@ -1129,13 +1136,6 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) return NULL; } -static inline int clk_save_context(void) -{ - return 0; -} - -static inline void clk_restore_context(void) {} - #endif /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ -- cgit v1.2.3 From d94f0f096ccf83b1a212788c62122c4b97ac8907 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 1 Dec 2025 10:42:27 +0100 Subject: clk: Merge prepare and unprepare sections contains two consecutive #ifdef/#else/#endif sections that check for CONFIG_HAVE_CLK_PREPARE: one for prepare-related functionality, and a second for unprepare-related functionality. Reduce #ifdef clutter by merging them. Signed-off-by: Geert Uytterhoeven Signed-off-by: Stephen Boyd --- include/linux/clk.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 64ff118ffb1a..9e5291f37c50 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -329,8 +329,21 @@ static inline void clk_restore_context(void) {} * Must not be called from within atomic context. */ int clk_prepare(struct clk *clk); + +/** + * clk_unprepare - undo preparation of a clock source + * @clk: clock source + * + * This undoes a previously prepared clock. The caller must balance + * the number of prepare and unprepare calls. + * + * Must not be called from within atomic context. + */ +void clk_unprepare(struct clk *clk); + int __must_check clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks); +void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks); /** * clk_is_enabled_when_prepared - indicate if preparing a clock also enables it. @@ -355,41 +368,28 @@ static inline int clk_prepare(struct clk *clk) return 0; } -static inline int __must_check -clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks) +static inline void clk_unprepare(struct clk *clk) { might_sleep(); - return 0; } -static inline bool clk_is_enabled_when_prepared(struct clk *clk) -{ - return false; -} -#endif - -/** - * clk_unprepare - undo preparation of a clock source - * @clk: clock source - * - * This undoes a previously prepared clock. The caller must balance - * the number of prepare and unprepare calls. - * - * Must not be called from within atomic context. - */ -#ifdef CONFIG_HAVE_CLK_PREPARE -void clk_unprepare(struct clk *clk); -void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks); -#else -static inline void clk_unprepare(struct clk *clk) +static inline int __must_check +clk_bulk_prepare(int num_clks, const struct clk_bulk_data *clks) { might_sleep(); + return 0; } + static inline void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks) { might_sleep(); } + +static inline bool clk_is_enabled_when_prepared(struct clk *clk) +{ + return false; +} #endif #ifdef CONFIG_HAVE_CLK -- cgit v1.2.3 From abe368db117ea61ace90880c80a12ee3c0d619e6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 1 Dec 2025 10:42:28 +0100 Subject: clk: Annotate #else and #endif Annotate the #else and #endif keywords in large #ifdef/#else/#endif sections, to improve readability. Signed-off-by: Geert Uytterhoeven Signed-off-by: Stephen Boyd --- include/linux/clk.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index 9e5291f37c50..efb91604d3f6 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -245,7 +245,7 @@ int clk_save_context(void); */ void clk_restore_context(void); -#else +#else /* !CONFIG_COMMON_CLK */ static inline int clk_notifier_register(struct clk *clk, struct notifier_block *nb) @@ -317,7 +317,7 @@ static inline int clk_save_context(void) static inline void clk_restore_context(void) {} -#endif +#endif /* !CONFIG_COMMON_CLK */ #ifdef CONFIG_HAVE_CLK_PREPARE /** @@ -361,7 +361,7 @@ void clk_bulk_unprepare(int num_clks, const struct clk_bulk_data *clks); * to be right. */ bool clk_is_enabled_when_prepared(struct clk *clk); -#else +#else /* !CONFIG_HAVE_CLK_PREPARE */ static inline int clk_prepare(struct clk *clk) { might_sleep(); @@ -390,7 +390,7 @@ static inline bool clk_is_enabled_when_prepared(struct clk *clk) { return false; } -#endif +#endif /* !CONFIG_HAVE_CLK_PREPARE */ #ifdef CONFIG_HAVE_CLK /** @@ -1136,7 +1136,7 @@ static inline struct clk *clk_get_sys(const char *dev_id, const char *con_id) return NULL; } -#endif +#endif /* !CONFIG_HAVE_CLK */ /* clk_prepare_enable helps cases using clk_enable in non-atomic context. */ static inline int clk_prepare_enable(struct clk *clk) -- cgit v1.2.3 From 5a4326f2e3b1edfb3329c1bee59035dc9f048b59 Mon Sep 17 00:00:00 2001 From: Chris Brandt Date: Mon, 24 Nov 2025 08:10:02 -0500 Subject: clk: renesas: rzg2l: Remove DSI clock rate restrictions Convert the limited MIPI clock calculations to a full range of settings based on math including H/W limitation validation. Since the required DSI division setting must be specified from external sources before calculations, expose a new API to set it. Signed-off-by: Chris Brandt Reviewed-by: Biju Das Tested-by: Biju Das Reviewed-by: Hugo Villeneuve Tested-by: Hugo Villeneuve Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20251124131003.992554-2-chris.brandt@renesas.com Signed-off-by: Geert Uytterhoeven --- include/linux/clk/renesas.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h index 69d8159deee3..c360df9fa735 100644 --- a/include/linux/clk/renesas.h +++ b/include/linux/clk/renesas.h @@ -35,6 +35,17 @@ void cpg_mssr_detach_dev(struct generic_pm_domain *unused, struct device *dev); #define cpg_mssr_detach_dev NULL #endif +enum { + PLL5_TARGET_DPI, + PLL5_TARGET_DSI +}; + +#ifdef CONFIG_CLK_RZG2L +void rzg2l_cpg_dsi_div_set_divider(u8 divider, int target); +#else +static inline void rzg2l_cpg_dsi_div_set_divider(u8 divider, int target) { } +#endif + /** * struct rzv2h_pll_limits - PLL parameter constraints * -- cgit v1.2.3 From 578d62a2e51614ea117ccf05fce6aaa6257dfd60 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 14 Dec 2025 12:27:27 -0800 Subject: comedi: comedi_8254: correct kernel-doc warnings Correct typos in 3 struct member descriptions to eliminate all kernel-doc warnings in comedi_8254.h: Warning: include/linux/comedi/comedi_8254.h:112 struct member 'next_div' not described in 'comedi_8254' Warning: include/linux/comedi/comedi_8254.h:112 struct member 'clock_src' not described in 'comedi_8254' Warning: include/linux/comedi/comedi_8254.h:112 struct member 'gate_src' not described in 'comedi_8254' Signed-off-by: Randy Dunlap Reviewed-by: Ian Abbott Link: https://patch.msgid.link/20251214202727.2215461-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/comedi/comedi_8254.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/comedi/comedi_8254.h b/include/linux/comedi/comedi_8254.h index d527f04400df..91f5861061ec 100644 --- a/include/linux/comedi/comedi_8254.h +++ b/include/linux/comedi/comedi_8254.h @@ -83,11 +83,11 @@ typedef unsigned int comedi_8254_iocb_fn(struct comedi_8254 *i8254, int dir, * @divisor: divisor for single counter * @divisor1: divisor loaded into first cascaded counter * @divisor2: divisor loaded into second cascaded counter - * #next_div: next divisor for single counter + * @next_div: next divisor for single counter * @next_div1: next divisor to use for first cascaded counter * @next_div2: next divisor to use for second cascaded counter - * @clock_src; current clock source for each counter (driver specific) - * @gate_src; current gate source for each counter (driver specific) + * @clock_src: current clock source for each counter (driver specific) + * @gate_src: current gate source for each counter (driver specific) * @busy: flags used to indicate that a counter is "busy" * @insn_config: driver specific (*insn_config) callback */ -- cgit v1.2.3 From a2450bddb75f4c0da86ed02adbc9477e49edd311 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 14 Dec 2025 12:27:39 -0800 Subject: eeprom_93cx6: fix struct member kernel-doc Remove the function parameter parts of the struct member descriptions to prevent kernel-doc warnings: Warning: include/linux/eeprom_93cx6.h:64 struct member 'register_read' not described in 'eeprom_93cx6' Warning: ../include/linux/eeprom_93cx6.h:64 struct member 'register_write' not described in 'eeprom_93cx6' Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20251214202739.2216904-1-rdunlap@infradead.org Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93cx6.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eeprom_93cx6.h b/include/linux/eeprom_93cx6.h index 3a485cc0e0fa..194a4a49ff1d 100644 --- a/include/linux/eeprom_93cx6.h +++ b/include/linux/eeprom_93cx6.h @@ -31,10 +31,10 @@ * struct eeprom_93cx6 - control structure for setting the commands * for reading the eeprom data. * @data: private pointer for the driver. - * @register_read(struct eeprom_93cx6 *eeprom): handler to - * read the eeprom register, this function should set all reg_* fields. - * @register_write(struct eeprom_93cx6 *eeprom): handler to - * write to the eeprom register by using all reg_* fields. + * @register_read: handler to read the eeprom register; + * this function should set all reg_* fields. + * @register_write: handler to write to the eeprom register by using + * all reg_* fields. * @width: eeprom width, should be one of the PCI_EEPROM_WIDTH_* defines * @quirks: eeprom or controller quirks * @drive_data: Set if we're driving the data line. -- cgit v1.2.3 From 5f0bf80cc5e04d31eeb201683e0b477c24bd18e7 Mon Sep 17 00:00:00 2001 From: Matthew Schwartz Date: Sat, 3 Jan 2026 12:42:26 -0800 Subject: mmc: rtsx_pci: add quirk to disable MMC_CAP_AGGRESSIVE_PM for RTS525A Using MMC_CAP_AGGRESSIVE_PM on RTS525A card readers causes game performance issues when the card reader comes back from idle into active use. This can be observed in Hades II when loading new sections of the game or menu after the card reader puts itself into idle, and presents as a 1-2 second hang. Add EXTRA_CAPS_NO_AGGRESSIVE_PM quirk to allow cardreader drivers to opt-out of aggressive PM, and set it for RTS525A. Closes: https://lore.kernel.org/linux-mmc/ff9a7c20-f465-4afa-bf29-708d4a52974a@linux.dev/ Signed-off-by: Matthew Schwartz Link: https://patch.msgid.link/20260103204226.71752-1-matthew.schwartz@linux.dev Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index 3c5689356004..f6122349c00e 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1230,6 +1230,7 @@ struct rtsx_pcr { #define EXTRA_CAPS_MMC_8BIT (1 << 5) #define EXTRA_CAPS_NO_MMC (1 << 7) #define EXTRA_CAPS_SD_EXPRESS (1 << 8) +#define EXTRA_CAPS_NO_AGGRESSIVE_PM (1 << 9) u32 extra_caps; #define IC_VER_A 0 -- cgit v1.2.3 From eac85fbd0867c25ac517f58fae401d65c627edff Mon Sep 17 00:00:00 2001 From: Matthew Schwartz Date: Sun, 4 Jan 2026 22:02:35 -0800 Subject: mmc: rtsx: reset power state on suspend When rtsx_pci suspends, the card reader hardware powers off but the sdmmc driver's prev_power_state remains as MMC_POWER_ON. This causes sd_power_on to skip reinitialization on the next I/O request, leading to DMA transfer timeouts and errors on resume 20% of the time. Add a power_off slot callback so the PCR can notify the sdmmc driver during suspend. The sdmmc driver resets prev_power_state, and sd_request checks this to reinitialize the card before the next I/O. Signed-off-by: Matthew Schwartz Link: https://patch.msgid.link/20260105060236.400366-2-matthew.schwartz@linux.dev Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_common.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rtsx_common.h b/include/linux/rtsx_common.h index da9c8c6b5d50..f294f478f0c0 100644 --- a/include/linux/rtsx_common.h +++ b/include/linux/rtsx_common.h @@ -32,6 +32,7 @@ struct platform_device; struct rtsx_slot { struct platform_device *p_dev; void (*card_event)(struct platform_device *p_dev); + void (*power_off)(struct platform_device *p_dev); }; #endif -- cgit v1.2.3 From e48e16f3e37fac76e2f0c14c58df2b0398a323b0 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Sat, 10 Jan 2026 15:54:05 -0800 Subject: f2fs: support non-4KB block size without packed_ssa feature Currently, F2FS requires the packed_ssa feature to be enabled when utilizing non-4KB block sizes (e.g., 16KB). This restriction limits the flexibility of filesystem formatting options. This patch allows F2FS to support non-4KB block sizes even when the packed_ssa feature is disabled. It adjusts the SSA calculation logic to correctly handle summary entries in larger blocks without the packed layout. Cc: stable@kernel.org Fixes: 7ee8bc3942f2 ("f2fs: revert summary entry count from 2048 to 512 in 16kb block support") Signed-off-by: Daeho Jeong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 73 ++++++++++++++++++++++++++++++------------------- 1 file changed, 45 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index a7880787cad3..dc41722fcc9d 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -17,7 +17,6 @@ #define F2FS_LOG_SECTORS_PER_BLOCK (PAGE_SHIFT - 9) /* log number for sector/blk */ #define F2FS_BLKSIZE PAGE_SIZE /* support only block == page */ #define F2FS_BLKSIZE_BITS PAGE_SHIFT /* bits for F2FS_BLKSIZE */ -#define F2FS_SUM_BLKSIZE 4096 /* only support 4096 byte sum block */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ #define F2FS_EXTENSION_LEN 8 /* max size of extension */ @@ -442,10 +441,8 @@ struct f2fs_sit_block { * from node's page's beginning to get a data block address. * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node) */ -#define ENTRIES_IN_SUM (F2FS_SUM_BLKSIZE / 8) #define SUMMARY_SIZE (7) /* sizeof(struct f2fs_summary) */ #define SUM_FOOTER_SIZE (5) /* sizeof(struct summary_footer) */ -#define SUM_ENTRY_SIZE (SUMMARY_SIZE * ENTRIES_IN_SUM) /* a summary entry for a block in a segment */ struct f2fs_summary { @@ -468,22 +465,6 @@ struct summary_footer { __le32 check_sum; /* summary checksum */ } __packed; -#define SUM_JOURNAL_SIZE (F2FS_SUM_BLKSIZE - SUM_FOOTER_SIZE -\ - SUM_ENTRY_SIZE) -#define NAT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\ - sizeof(struct nat_journal_entry)) -#define NAT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ - sizeof(struct nat_journal_entry)) -#define SIT_JOURNAL_ENTRIES ((SUM_JOURNAL_SIZE - 2) /\ - sizeof(struct sit_journal_entry)) -#define SIT_JOURNAL_RESERVED ((SUM_JOURNAL_SIZE - 2) %\ - sizeof(struct sit_journal_entry)) - -/* Reserved area should make size of f2fs_extra_info equals to - * that of nat_journal and sit_journal. - */ -#define EXTRA_INFO_RESERVED (SUM_JOURNAL_SIZE - 2 - 8) - /* * frequently updated NAT/SIT entries can be stored in the spare area in * summary blocks @@ -498,9 +479,16 @@ struct nat_journal_entry { struct f2fs_nat_entry ne; } __packed; +/* + * The nat_journal structure is a placeholder whose actual size varies depending + * on the use of packed_ssa. Therefore, it must always be accessed only through + * specific sets of macros and fields, and size calculations should use + * size-related macros instead of sizeof(). + * Relevant macros: sbi->nat_journal_entries, nat_in_journal(), + * nid_in_journal(), MAX_NAT_JENTRIES(). + */ struct nat_journal { - struct nat_journal_entry entries[NAT_JOURNAL_ENTRIES]; - __u8 reserved[NAT_JOURNAL_RESERVED]; + struct nat_journal_entry entries[0]; } __packed; struct sit_journal_entry { @@ -508,14 +496,21 @@ struct sit_journal_entry { struct f2fs_sit_entry se; } __packed; +/* + * The sit_journal structure is a placeholder whose actual size varies depending + * on the use of packed_ssa. Therefore, it must always be accessed only through + * specific sets of macros and fields, and size calculations should use + * size-related macros instead of sizeof(). + * Relevant macros: sbi->sit_journal_entries, sit_in_journal(), + * segno_in_journal(), MAX_SIT_JENTRIES(). + */ struct sit_journal { - struct sit_journal_entry entries[SIT_JOURNAL_ENTRIES]; - __u8 reserved[SIT_JOURNAL_RESERVED]; + struct sit_journal_entry entries[0]; } __packed; struct f2fs_extra_info { __le64 kbytes_written; - __u8 reserved[EXTRA_INFO_RESERVED]; + __u8 reserved[]; } __packed; struct f2fs_journal { @@ -531,11 +526,33 @@ struct f2fs_journal { }; } __packed; -/* Block-sized summary block structure */ +/* + * Block-sized summary block structure + * + * The f2fs_summary_block structure is a placeholder whose actual size varies + * depending on the use of packed_ssa. Therefore, it must always be accessed + * only through specific sets of macros and fields, and size calculations should + * use size-related macros instead of sizeof(). + * Relevant macros: sbi->sum_blocksize, sbi->entries_in_sum, + * sbi->sum_entry_size, sum_entries(), sum_journal(), sum_footer(). + * + * Summary Block Layout + * + * +-----------------------+ <--- Block Start + * | struct f2fs_summary | + * | entries[0] | + * | ... | + * | entries[N-1] | + * +-----------------------+ + * | struct f2fs_journal | + * +-----------------------+ + * | struct summary_footer | + * +-----------------------+ <--- Block End + */ struct f2fs_summary_block { - struct f2fs_summary entries[ENTRIES_IN_SUM]; - struct f2fs_journal journal; - struct summary_footer footer; + struct f2fs_summary entries[0]; + // struct f2fs_journal journal; + // struct summary_footer footer; } __packed; /* -- cgit v1.2.3 From 439cf01b2e0030eed6020a03a7df4a528f8db7ba Mon Sep 17 00:00:00 2001 From: Kari Argillander Date: Fri, 19 Dec 2025 22:42:38 +0200 Subject: watchdog: Make API functions const correct Many watchdog API functions do not modify the watchdog_device nor device. Mark their arguments as const to reflect this and improve const-correctness of the API. No functional change intended. Signed-off-by: Kari Argillander Reviewed-by: Guenter Roeck Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- include/linux/watchdog.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h index 8c60687a3e55..62cdd26fd025 100644 --- a/include/linux/watchdog.h +++ b/include/linux/watchdog.h @@ -129,7 +129,7 @@ struct watchdog_device { #define WATCHDOG_NOWAYOUT_INIT_STATUS (WATCHDOG_NOWAYOUT << WDOG_NO_WAY_OUT) /* Use the following function to check whether or not the watchdog is active */ -static inline bool watchdog_active(struct watchdog_device *wdd) +static inline bool watchdog_active(const struct watchdog_device *wdd) { return test_bit(WDOG_ACTIVE, &wdd->status); } @@ -138,7 +138,7 @@ static inline bool watchdog_active(struct watchdog_device *wdd) * Use the following function to check whether or not the hardware watchdog * is running */ -static inline bool watchdog_hw_running(struct watchdog_device *wdd) +static inline bool watchdog_hw_running(const struct watchdog_device *wdd) { return test_bit(WDOG_HW_RUNNING, &wdd->status); } @@ -169,7 +169,8 @@ static inline void watchdog_stop_ping_on_suspend(struct watchdog_device *wdd) } /* Use the following function to check if a timeout value is invalid */ -static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigned int t) +static inline bool watchdog_timeout_invalid(const struct watchdog_device *wdd, + unsigned int t) { /* * The timeout is invalid if @@ -188,7 +189,7 @@ static inline bool watchdog_timeout_invalid(struct watchdog_device *wdd, unsigne } /* Use the following function to check if a pretimeout value is invalid */ -static inline bool watchdog_pretimeout_invalid(struct watchdog_device *wdd, +static inline bool watchdog_pretimeout_invalid(const struct watchdog_device *wdd, unsigned int t) { return t && wdd->timeout && t >= wdd->timeout; @@ -218,7 +219,8 @@ static inline void watchdog_notify_pretimeout(struct watchdog_device *wdd) /* drivers/watchdog/watchdog_core.c */ void watchdog_set_restart_priority(struct watchdog_device *wdd, int priority); extern int watchdog_init_timeout(struct watchdog_device *wdd, - unsigned int timeout_parm, struct device *dev); + unsigned int timeout_parm, + const struct device *dev); extern int watchdog_register_device(struct watchdog_device *); extern void watchdog_unregister_device(struct watchdog_device *); int watchdog_dev_suspend(struct watchdog_device *wdd); -- cgit v1.2.3 From b562abd956726f57bb78813b4c77db51d28933a9 Mon Sep 17 00:00:00 2001 From: Jjian Zhou Date: Mon, 13 Oct 2025 14:31:36 +0800 Subject: mailbox: mediatek: Add mtk-vcp-mailbox driver Add mtk-vcp-mailbox driver to support the communication with VCP remote microprocessor. Signed-off-by: Jjian Zhou Reviewed-by: Chen-Yu Tsai Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-vcp-mailbox.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/mailbox/mtk-vcp-mailbox.h (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-vcp-mailbox.h b/include/linux/mailbox/mtk-vcp-mailbox.h new file mode 100644 index 000000000000..16e59d6780a7 --- /dev/null +++ b/include/linux/mailbox/mtk-vcp-mailbox.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (c) 2025 MediaTek Inc. + */ + +#ifndef __MTK_VCP_MAILBOX_H__ +#define __MTK_VCP_MAILBOX_H__ + +#define MTK_VCP_MBOX_SLOT_MAX_SIZE 0x100 /* mbox max slot size */ + +/** + * struct mtk_ipi_info - mailbox message info for mtk-vcp-mailbox + * @msg: The share buffer between IPC and mailbox driver + * @len: Message length + * @id: This is for identification purposes and not actually used + * by the mailbox hardware. + * @index: The signal number of the mailbox message. + * @slot_ofs: Data slot offset. + * @irq_status: Captures incoming signals for the RX path. + * + * It is used between IPC with mailbox driver. + */ +struct mtk_ipi_info { + void *msg; + u32 len; + u32 id; + u32 index; + u32 slot_ofs; + u32 irq_status; +}; + +#endif -- cgit v1.2.3 From 7d834d5ce5cb780b926ea0484a80b47bafbb3b64 Mon Sep 17 00:00:00 2001 From: Jason-JH Lin Date: Fri, 31 Oct 2025 23:56:30 +0800 Subject: mailbox: mtk-cmdq: Add cmdq private data to cmdq_pkt for generating instruction Add the cmdq_mbox_priv structure to store the private data of GCE, such as the shift bits of the physical address. Then, include the cmdq_mbox_priv structure within the cmdq_pkt structure. This allows CMDQ users to utilize the private data in cmdq_pkt to generate GCE instructions when needed. Additionally, having cmdq_mbox_priv makes it easier to expand and reference other GCE private data in the future. Add cmdq_get_mbox_priv() for CMDQ users to get all the private data into the cmdq_mbox_priv of the cmdq_pkt. Signed-off-by: Jason-JH Lin Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index e1555e06e7e5..73b70be4a8a7 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -70,13 +70,31 @@ struct cmdq_cb_data { struct cmdq_pkt *pkt; }; +struct cmdq_mbox_priv { + u8 shift_pa; +}; + struct cmdq_pkt { void *va_base; dma_addr_t pa_base; size_t cmd_buf_size; /* command occupied size */ size_t buf_size; /* real buffer size */ + struct cmdq_mbox_priv priv; /* for generating instruction */ }; +/** + * cmdq_get_mbox_priv() - get the private data of mailbox channel + * @chan: mailbox channel + * @priv: pointer to store the private data of mailbox channel + * + * While generating the GCE instruction to command buffer, the private data + * of GCE hardware may need to be referenced, such as the shift bits of + * physical address. + * + * This function should be called before generating the GCE instruction. + */ +void cmdq_get_mbox_priv(struct mbox_chan *chan, struct cmdq_mbox_priv *priv); + /** * cmdq_get_shift_pa() - get the shift bits of physical address * @chan: mailbox channel -- cgit v1.2.3 From ddb5d0c941c64b51b003f62df3596682a6591c35 Mon Sep 17 00:00:00 2001 From: Jason-JH Lin Date: Fri, 31 Oct 2025 23:56:32 +0800 Subject: mailbox: mtk-cmdq: Add mminfra_offset configuration for DRAM transaction The GCE in MT8196 is placed in MMINFRA and requires all addresses in GCE instructions for DRAM transactions to be IOVA. Due to MMIO, if the GCE needs to access a hardware register at 0x1000_0000, but the SMMU is also mapping a DRAM block at 0x1000_0000, the MMINFRA will not know whether to write to the hardware register or the DRAM. To solve this, MMINFRA treats addresses greater than 2G as data paths and those less than 2G as config paths because the DRAM start address is currently at 2G (0x8000_0000). On the data path, MMINFRA remaps DRAM addresses by subtracting 2G, allowing SMMU to map DRAM addresses less than 2G. For example, if the DRAM start address 0x8000_0000 is mapped to IOVA=0x0, when GCE accesses IOVA=0x0, it must add a 2G offset to the address in the GCE instruction. MMINFRA will then see it as a data path (IOVA >= 2G) and subtract 2G, allowing GCE to access IOVA=0x0. Since the MMINFRA remap subtracting 2G is done in hardware and cannot be configured by software, the address of DRAM in GCE instruction must always add 2G to ensure proper access. After that, the shift functions do more than just shift addresses, so the APIs were renamed to cmdq_convert_gce_addr() and cmdq_revert_gce_addr(). This 2G adjustment is referred to as mminfra_offset in the CMDQ driver. CMDQ helper can get the mminfra_offset from the cmdq_mbox_priv of cmdq_pkt and add the mminfra_offset to the DRAM address in GCE instructions. Signed-off-by: Jason-JH Lin Reviewed-by: AngeloGioacchino Del Regno Signed-off-by: Jassi Brar --- include/linux/mailbox/mtk-cmdq-mailbox.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 73b70be4a8a7..07c1bfbdb8c4 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -72,6 +72,7 @@ struct cmdq_cb_data { struct cmdq_mbox_priv { u8 shift_pa; + dma_addr_t mminfra_offset; }; struct cmdq_pkt { -- cgit v1.2.3 From eb9eb4db98d68c680900d48ee672b92c59ffee71 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 8 Jan 2026 13:52:37 +0100 Subject: driver core: make pinctrl_bind_pins() private pinctrl_bind_pins() is only used by driver core (as it should). Move it out of the public header into base.h. Signed-off-by: Bartosz Golaszewski Reviewed-by: Greg Kroah-Hartman Acked-by: Danilo Krummrich Signed-off-by: Linus Walleij --- include/linux/pinctrl/devinfo.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/devinfo.h b/include/linux/pinctrl/devinfo.h index bb6653af4f92..de4228eea90a 100644 --- a/include/linux/pinctrl/devinfo.h +++ b/include/linux/pinctrl/devinfo.h @@ -43,7 +43,6 @@ struct dev_pin_info { #endif }; -extern int pinctrl_bind_pins(struct device *dev); extern int pinctrl_init_done(struct device *dev); static inline struct pinctrl *dev_pinctrl(struct device *dev) @@ -58,11 +57,6 @@ static inline struct pinctrl *dev_pinctrl(struct device *dev) /* Stubs if we're not using pinctrl */ -static inline int pinctrl_bind_pins(struct device *dev) -{ - return 0; -} - static inline int pinctrl_init_done(struct device *dev) { return 0; -- cgit v1.2.3 From 156442eb6e44d545f09559bd70c5b31fba39eb01 Mon Sep 17 00:00:00 2001 From: Joseph Chen Date: Mon, 12 Jan 2026 20:43:50 +0800 Subject: mfd: rk8xx: Add RK801 support The RK801 is a Power Management IC (PMIC) for multimedia and handheld devices. It contains the following components: - 4 BUCK - 2 LDO - 1 SWITCH Signed-off-by: Joseph Chen Link: https://patch.msgid.link/20260112124351.17707-3-chenjh@rock-chips.com Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 118 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 118 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 28170ee08898..7ffc904c864c 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -340,6 +340,123 @@ enum rk818_reg { #define RK818_USB_ILMIN_2000MA 0x7 #define RK818_USB_CHG_SD_VSEL_MASK 0x70 +/* RK801 */ +enum rk801_reg { + RK801_ID_DCDC1, + RK801_ID_DCDC2, + RK801_ID_DCDC4, + RK801_ID_DCDC3, + RK801_ID_LDO1, + RK801_ID_LDO2, + RK801_ID_SWITCH, + RK801_ID_MAX, +}; + +#define RK801_SLP_REG_OFFSET 5 +#define RK801_NUM_REGULATORS 7 + +#define RK801_HW_SYNC_US 32 + +/* RK801 Register Definitions */ +#define RK801_ID_MSB 0x00 +#define RK801_ID_LSB 0x01 +#define RK801_OTP_VER_REG 0x02 +#define RK801_POWER_EN0_REG 0x03 +#define RK801_POWER_EN1_REG 0x04 +#define RK801_POWER_SLP_EN_REG 0x05 +#define RK801_POWER_FPWM_EN_REG 0x06 +#define RK801_SLP_LP_CONFIG_REG 0x07 +#define RK801_BUCK_CONFIG_REG 0x08 +#define RK801_BUCK1_ON_VSEL_REG 0x09 +#define RK801_BUCK2_ON_VSEL_REG 0x0a +#define RK801_BUCK4_ON_VSEL_REG 0x0b +#define RK801_LDO1_ON_VSEL_REG 0x0c +#define RK801_LDO2_ON_VSEL_REG 0x0d +#define RK801_BUCK1_SLP_VSEL_REG 0x0e +#define RK801_BUCK2_SLP_VSEL_REG 0x0f +#define RK801_BUCK4_SLP_VSEL_REG 0x10 +#define RK801_LDO1_SLP_VSEL_REG 0x11 +#define RK801_LDO2_SLP_VSEL_REG 0x12 +#define RK801_LDO_SW_IMAX_REG 0x13 +#define RK801_SYS_STS_REG 0x14 +#define RK801_SYS_CFG0_REG 0x15 +#define RK801_SYS_CFG1_REG 0x16 +#define RK801_SYS_CFG2_REG 0x17 +#define RK801_SYS_CFG3_REG 0x18 +#define RK801_SYS_CFG4_REG 0x19 +#define RK801_SLEEP_CFG_REG 0x1a +#define RK801_ON_SOURCE_REG 0x1b +#define RK801_OFF_SOURCE_REG 0x1c +#define RK801_PWRON_KEY_REG 0x1d +#define RK801_INT_STS0_REG 0x1e +#define RK801_INT_MASK0_REG 0x1f +#define RK801_INT_CONFIG_REG 0x20 +#define RK801_CON_BACK1_REG 0x21 +#define RK801_CON_BACK2_REG 0x22 +#define RK801_DATA_CON0_REG 0x23 +#define RK801_DATA_CON1_REG 0x24 +#define RK801_DATA_CON2_REG 0x25 +#define RK801_DATA_CON3_REG 0x26 +#define RK801_POWER_EXIT_SLP_SEQ0_REG 0x27 +#define RK801_POWER_EXIT_SLP_SEQ1_REG 0x28 +#define RK801_POWER_EXIT_SLP_SEQ2_REG 0x29 +#define RK801_POWER_EXIT_SLP_SEQ3_REG 0x2a +#define RK801_POWER_ENTER_SLP_OR_SHTD_SEQ0_REG 0x2b +#define RK801_POWER_ENTER_SLP_OR_SHTD_SEQ1_REG 0x2c +#define RK801_POWER_ENTER_SLP_OR_SHTD_SEQ2_REG 0x2d +#define RK801_POWER_ENTER_SLP_OR_SHTD_SEQ3_REG 0x2e +#define RK801_BUCK_DEBUG1_REG 0x2f +#define RK801_BUCK_DEBUG2_REG 0x30 +#define RK801_BUCK_DEBUG3_REG 0x31 +#define RK801_BUCK_DEBUG4_REG 0x32 +#define RK801_BUCK_DEBUG5_REG 0x33 +#define RK801_BUCK_DEBUG7_REG 0x34 +#define RK801_OTP_EN_CON_REG 0x35 +#define RK801_TEST_CON_REG 0x36 +#define RK801_EFUSE_CONTROL_REG 0x37 +#define RK801_SYS_CFG3_OTP_REG 0x38 + +/* RK801 IRQ Definitions */ +#define RK801_IRQ_PWRON_FALL 0 +#define RK801_IRQ_PWRON_RISE 1 +#define RK801_IRQ_PWRON 2 +#define RK801_IRQ_PWRON_LP 3 +#define RK801_IRQ_HOTDIE 4 +#define RK801_IRQ_VDC_RISE 5 +#define RK801_IRQ_VDC_FALL 6 +#define RK801_IRQ_PWRON_FALL_MSK BIT(0) +#define RK801_IRQ_PWRON_RISE_MSK BIT(1) +#define RK801_IRQ_PWRON_MSK BIT(2) +#define RK801_IRQ_PWRON_LP_MSK BIT(3) +#define RK801_IRQ_HOTDIE_MSK BIT(4) +#define RK801_IRQ_VDC_RISE_MSK BIT(5) +#define RK801_IRQ_VDC_FALL_MSK BIT(6) +/* RK801_SLP_LP_CONFIG_REG */ +#define RK801_BUCK_SLP_LP_EN BIT(3) +#define RK801_PLDO_SLP_LP_EN BIT(1) +#define RK801_SLP_LP_MASK (RK801_PLDO_SLP_LP_EN | RK801_BUCK_SLP_LP_EN) +/* RK801_SLEEP_CFG_REG */ +#define RK801_SLEEP_FUN_MSK 0x3 +#define RK801_NONE_FUN 0x0 +#define RK801_SLEEP_FUN 0x1 +#define RK801_SHUTDOWN_FUN 0x2 +#define RK801_RESET_FUN 0x3 +/* RK801_SYS_CFG2_REG */ +#define RK801_SLEEP_POL_MSK BIT(1) +#define RK801_SLEEP_ACT_H BIT(1) +#define RK801_SLEEP_ACT_L 0 +#define RK801_RST_MSK (0x3 << 4) +#define RK801_RST_RESTART_PMU (0x0 << 4) +#define RK801_RST_RESTART_REG (0x1 << 4) +#define RK801_RST_RESTART_REG_RESETB (0x2 << 4) +/* RK801_INT_CONFIG_REG */ +#define RK801_INT_POL_MSK BIT(1) +#define RK801_INT_ACT_H BIT(1) +#define RK801_INT_ACT_L 0 +#define RK801_FPWM_MODE 1 +#define RK801_AUTO_PWM_MODE 0 +#define RK801_PLDO_HRDEC_EN BIT(6) + /* RK805 */ enum rk805_reg { RK805_ID_DCDC1, @@ -1332,6 +1449,7 @@ enum { }; enum { + RK801_ID = 0x8010, RK805_ID = 0x8050, RK806_ID = 0x8060, RK808_ID = 0x0000, -- cgit v1.2.3 From 41c6cac6decd5123db1da8ca240a9c808b0ae6ce Mon Sep 17 00:00:00 2001 From: Cristian Ciocaltea Date: Tue, 13 Jan 2026 01:20:48 +0200 Subject: phy: hdmi: Add HDMI 2.1 FRL configuration options The HDMI 2.1 specification introduced the Fixed Rate Link (FRL) mode, aiming to replace the older Transition-Minimized Differential Signaling (TMDS) mode used in previous HDMI versions to support much higher bandwidths (up to 48 Gbps) for modern video and audio formats. FRL has been designed to support ultra high resolution formats at high refresh rates like 8K@60Hz or 4K@120Hz, and eliminates the need for dynamic bandwidth adjustments, which reduces latency. It operates with 3 or 4 lanes at different link rates: 3Gbps, 6Gbps, 8Gbps, 10Gbps or 12Gbps. Add support for configuring the FRL mode for HDMI PHYs. Signed-off-by: Cristian Ciocaltea Link: https://patch.msgid.link/20260113-phy-hdptx-frl-v6-1-8d5f97419c0b@collabora.com Signed-off-by: Vinod Koul --- include/linux/phy/phy-hdmi.h | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy/phy-hdmi.h b/include/linux/phy/phy-hdmi.h index f0ec963c6e84..d4cf4430ee8f 100644 --- a/include/linux/phy/phy-hdmi.h +++ b/include/linux/phy/phy-hdmi.h @@ -6,16 +6,31 @@ #ifndef __PHY_HDMI_H_ #define __PHY_HDMI_H_ +#include + +enum phy_hdmi_mode { + PHY_HDMI_MODE_TMDS, + PHY_HDMI_MODE_FRL, +}; + /** * struct phy_configure_opts_hdmi - HDMI configuration set - * @tmds_char_rate: HDMI TMDS Character Rate in Hertz. * @bpc: Bits per color channel. + * @tmds_char_rate: HDMI TMDS Character Rate in Hertz. + * @frl.rate_per_lane: HDMI FRL Rate per Lane in Gbps. + * @frl.lanes: HDMI FRL lanes count. * * This structure is used to represent the configuration state of a HDMI phy. */ struct phy_configure_opts_hdmi { - unsigned long long tmds_char_rate; unsigned int bpc; + union { + unsigned long long tmds_char_rate; + struct { + u8 rate_per_lane; + u8 lanes; + } frl; + }; }; #endif /* __PHY_HDMI_H_ */ -- cgit v1.2.3 From c23f0550c05d40762b141808709667759291c938 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Jan 2026 15:50:36 +0100 Subject: Revert "mmc: rtsx: reset power state on suspend" This reverts commit eac85fbd0867c25ac517f58fae401d65c627edff. This is not the correct change, so revert it for now. Fixes: eac85fbd0867 ("mmc: rtsx: reset power state on suspend") Cc: Matthew Schwartz Cc: Ulf Hansson Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_common.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_common.h b/include/linux/rtsx_common.h index f294f478f0c0..da9c8c6b5d50 100644 --- a/include/linux/rtsx_common.h +++ b/include/linux/rtsx_common.h @@ -32,7 +32,6 @@ struct platform_device; struct rtsx_slot { struct platform_device *p_dev; void (*card_event)(struct platform_device *p_dev); - void (*power_off)(struct platform_device *p_dev); }; #endif -- cgit v1.2.3 From eb89b17f283b233ba721fce358fa0d15223ae69d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 21 Jan 2026 15:51:04 +0100 Subject: Revert "mmc: rtsx_pci: add quirk to disable MMC_CAP_AGGRESSIVE_PM for RTS525A" This reverts commit 5f0bf80cc5e04d31eeb201683e0b477c24bd18e7. This was asked to be reverted as it is not the correct way to do this. Fixes: 5f0bf80cc5e0 ("mmc: rtsx_pci: add quirk to disable MMC_CAP_AGGRESSIVE_PM for RTS525A") Cc: Matthew Schwartz Signed-off-by: Greg Kroah-Hartman --- include/linux/rtsx_pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtsx_pci.h b/include/linux/rtsx_pci.h index f6122349c00e..3c5689356004 100644 --- a/include/linux/rtsx_pci.h +++ b/include/linux/rtsx_pci.h @@ -1230,7 +1230,6 @@ struct rtsx_pcr { #define EXTRA_CAPS_MMC_8BIT (1 << 5) #define EXTRA_CAPS_NO_MMC (1 << 7) #define EXTRA_CAPS_SD_EXPRESS (1 << 8) -#define EXTRA_CAPS_NO_AGGRESSIVE_PM (1 << 9) u32 extra_caps; #define IC_VER_A 0 -- cgit v1.2.3 From ed30d0296373e354f35ffc14558f265934dfa790 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 24 Nov 2025 18:27:50 -0800 Subject: mfd: tps6105x: Fix kernel-doc warnings relating to the core struct and tps6105x_mode Fix spelling of an enum to fix a kernel-doc warning. Fix kernel-doc of struct tps6105x to prevent kernel-doc warnings. Warning: include/linux/mfd/tps6105x.h:68 Enum value 'TPS6105X_MODE_TORCH' not described in enum 'tps6105x_mode' Warning: include/linux/mfd/tps6105x.h:68 Excess enum value '%TPS61905X_MODE_TORCH' description in 'tps6105x_mode' Warning: include/linux/mfd/tps6105x.h:93 struct member 'pdata' not described in 'tps6105x' Warning: include/linux/mfd/tps6105x.h:93 struct member 'client' not described in 'tps6105x' Fixes: 798a8eee44da ("mfd: Add a core driver for TI TPS61050/TPS61052 chips v2") Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20251125022750.3165569-1-rdunlap@infradead.org Signed-off-by: Lee Jones --- include/linux/mfd/tps6105x.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/tps6105x.h b/include/linux/mfd/tps6105x.h index b1313411ef09..94e699896240 100644 --- a/include/linux/mfd/tps6105x.h +++ b/include/linux/mfd/tps6105x.h @@ -53,7 +53,7 @@ /** * enum tps6105x_mode - desired mode for the TPS6105x * @TPS6105X_MODE_SHUTDOWN: this instance is inactive, not used for anything - * @TPS61905X_MODE_TORCH: this instance is used as a LED, usually a while + * @TPS6105X_MODE_TORCH: this instance is used as a LED, usually a while * LED, for example as backlight or flashlight. If this is set, the * TPS6105X will register to the LED framework * @TPS6105X_MODE_TORCH_FLASH: this instance is used as a flashgun, usually @@ -82,7 +82,8 @@ struct tps6105x_platform_data { /** * struct tps6105x - state holder for the TPS6105x drivers - * @i2c_client: corresponding I2C client + * @pdata: associated platform data + * @client: corresponding I2C client * @regulator: regulator device if used in voltage mode * @regmap: used for i2c communcation on accessing registers */ -- cgit v1.2.3 From a71fee8421cf05d022880ae102983cd46535dac0 Mon Sep 17 00:00:00 2001 From: Andreas Kemnade Date: Sun, 7 Dec 2025 09:50:24 +0100 Subject: mfd: bd71828: Add some missing charger related registers As there are some registers missing which are required for future charger extensions, add them. Signed-off-by: Andreas Kemnade Reviewed-by: Matti Vaittinen Link: https://patch.msgid.link/20251207085024.7375-1-andreas@kemnade.info Signed-off-by: Lee Jones --- include/linux/mfd/rohm-bd71828.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index 73a71ef69152..39fe275a8117 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -249,6 +249,8 @@ enum { #define BD71828_REG_BATCAP_MON_LIMIT_U 0xcc #define BD71828_REG_CONF 0x64 +#define BD71828_REG_ILIM_STAT 0x6d +#define BD71828_REG_DCIN_SET 0x70 #define BD71828_REG_DCIN_CLPS 0x71 #define BD71828_REG_MEAS_CLEAR 0xaf -- cgit v1.2.3 From d3fcf276b501a82d4504fd5b1ed40249546530d1 Mon Sep 17 00:00:00 2001 From: "Kory Maincent (TI.com)" Date: Thu, 18 Dec 2025 16:06:28 +0100 Subject: mfd: tps65219: Implement LOCK register handling for TPS65214 The TPS65214 PMIC variant has a LOCK_REG register that prevents writes to nearly all registers when locked. Unlock the registers at probe time and leave them unlocked permanently. This approach is justified because: - Register locking is very uncommon in typical system operation - No code path is expected to lock the registers during runtime - Adding a custom regmap write function would add overhead to every register write, including voltage changes triggered by CPU OPP transitions from the cpufreq governor which could happen quite frequently Cc: stable@vger.kernel.org Fixes: 7947219ab1a2d ("mfd: tps65219: Add support for TI TPS65214 PMIC") Reviewed-by: Andrew Davis Signed-off-by: Kory Maincent (TI.com) Link: https://patch.msgid.link/20251218-fix_tps65219-v5-1-8bb511417f3a@bootlin.com Signed-off-by: Lee Jones --- include/linux/mfd/tps65219.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h index 55234e771ba7..3abf937191d0 100644 --- a/include/linux/mfd/tps65219.h +++ b/include/linux/mfd/tps65219.h @@ -149,6 +149,8 @@ enum pmic_id { #define TPS65215_ENABLE_LDO2_EN_MASK BIT(5) #define TPS65214_ENABLE_LDO1_EN_MASK BIT(5) #define TPS65219_ENABLE_LDO4_EN_MASK BIT(6) +/* Register Unlock */ +#define TPS65214_LOCK_ACCESS_CMD 0x5a /* power ON-OFF sequence slot */ #define TPS65219_BUCKS_LDOS_SEQUENCE_OFF_SLOT_MASK GENMASK(3, 0) #define TPS65219_BUCKS_LDOS_SEQUENCE_ON_SLOT_MASK GENMASK(7, 4) -- cgit v1.2.3 From f78263a87336056b5948396c646d7d8413a2c2ea Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Thu, 25 Dec 2025 16:02:40 +0800 Subject: mfd: axp20x: AXP717: Add type-C CC registers The AXP717 has some extra registers related to type-C CC pin negotiation. They were missing from the original submission. Add them for completeness. Signed-off-by: Chen-Yu Tsai Reviewed-by: Jernej Skrabec Link: https://patch.msgid.link/20251225080241.3153453-1-wens@kernel.org Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 3c5aecf1d4b5..b352661d99a1 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -174,6 +174,9 @@ enum axp20x_variants { #define AXP717_ADC_DATA_SEL 0xcd #define AXP717_ADC_DATA_H 0xce #define AXP717_ADC_DATA_L 0xcf +#define AXP717_TYPEC_CC_AA_EN 0xe1 +#define AXP717_TYPEC_CC_MODE_CONTROL 0xe3 +#define AXP717_TYPEC_CC_STATUS 0xe7 #define AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 -- cgit v1.2.3 From 88fd1f90792411226f49e5f285bf3faca5ac970b Mon Sep 17 00:00:00 2001 From: Kurt Borja Date: Tue, 20 Jan 2026 01:20:41 -0500 Subject: iio: core: Add and export __iio_dev_mode_lock() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add unconditional wrappers around the internal IIO mode lock. As mentioned in the documentation, this is not meant to be used by drivers, instead this will aid in the eventual addition of cleanup classes around conditional locks. Reviewed-by: David Lechner Reviewed-by: Nuno Sá Signed-off-by: Kurt Borja Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 872ebdf0dd77..aecda887d833 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -661,6 +661,9 @@ void iio_device_unregister(struct iio_dev *indio_dev); int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev, struct module *this_mod); int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp); + +void __iio_dev_mode_lock(struct iio_dev *indio_dev) __acquires(indio_dev); +void __iio_dev_mode_unlock(struct iio_dev *indio_dev) __releases(indio_dev); bool __iio_device_claim_direct(struct iio_dev *indio_dev); void __iio_device_release_direct(struct iio_dev *indio_dev); -- cgit v1.2.3 From c37ec9d507966a827913f42e06179e3475a00181 Mon Sep 17 00:00:00 2001 From: Kurt Borja Date: Tue, 20 Jan 2026 01:20:42 -0500 Subject: iio: core: Refactor iio_device_claim_direct() implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to eventually unify the locking API, implement iio_device_claim_direct() fully inline, with the use of __iio_dev_mode_lock(), which takes care of sparse annotations. Reviewed-by: David Lechner Reviewed-by: Nuno Sá Signed-off-by: Kurt Borja Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index aecda887d833..e263ab5eeccf 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -664,31 +664,47 @@ int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp); void __iio_dev_mode_lock(struct iio_dev *indio_dev) __acquires(indio_dev); void __iio_dev_mode_unlock(struct iio_dev *indio_dev) __releases(indio_dev); -bool __iio_device_claim_direct(struct iio_dev *indio_dev); -void __iio_device_release_direct(struct iio_dev *indio_dev); /* * Helper functions that allow claim and release of direct mode * in a fashion that doesn't generate many false positives from sparse. * Note this must remain static inline in the header so that sparse - * can see the __acquire() marking. Revisit when sparse supports - * __cond_acquires() + * can see the __acquires() and __releases() annotations. + */ + +/** + * iio_device_claim_direct() - Keep device in direct mode + * @indio_dev: the iio_dev associated with the device + * + * If the device is in direct mode it is guaranteed to stay + * that way until iio_device_release_direct() is called. + * + * Use with iio_device_release_direct(). + * + * Returns: true on success, false on failure. */ static inline bool iio_device_claim_direct(struct iio_dev *indio_dev) { - if (!__iio_device_claim_direct(indio_dev)) - return false; + __iio_dev_mode_lock(indio_dev); - __acquire(iio_dev); + if (iio_buffer_enabled(indio_dev)) { + __iio_dev_mode_unlock(indio_dev); + return false; + } return true; } -static inline void iio_device_release_direct(struct iio_dev *indio_dev) -{ - __iio_device_release_direct(indio_dev); - __release(indio_dev); -} +/** + * iio_device_release_direct() - Releases claim on direct mode + * @indio_dev: the iio_dev associated with the device + * + * Release the claim. Device is no longer guaranteed to stay + * in direct mode. + * + * Use with iio_device_claim_direct(). + */ +#define iio_device_release_direct(indio_dev) __iio_dev_mode_unlock(indio_dev) int iio_device_claim_buffer_mode(struct iio_dev *indio_dev); void iio_device_release_buffer_mode(struct iio_dev *indio_dev); -- cgit v1.2.3 From 2daee817df13fb539be01a6a8094d52667d402f6 Mon Sep 17 00:00:00 2001 From: Kurt Borja Date: Tue, 20 Jan 2026 01:20:43 -0500 Subject: iio: core: Match iio_device_claim_*() semantics and implementation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Implement iio_device_claim_buffer_mode() fully inline with the use of __iio_dev_mode_lock(), which takes care of sparse annotations. To completely match iio_device_claim_direct() semantics, we need to also change iio_device_claim_buffer_mode() return semantics to usual true/false conditional lock semantics. Additionally, to avoid silently breaking out-of-tree drivers, rename iio_device_claim_buffer_mode() to iio_device_claim_try_buffer_mode(). Reviewed-by: David Lechner Reviewed-by: Nuno Sá Signed-off-by: Kurt Borja Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e263ab5eeccf..36bd14e93a75 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -706,8 +706,39 @@ static inline bool iio_device_claim_direct(struct iio_dev *indio_dev) */ #define iio_device_release_direct(indio_dev) __iio_dev_mode_unlock(indio_dev) -int iio_device_claim_buffer_mode(struct iio_dev *indio_dev); -void iio_device_release_buffer_mode(struct iio_dev *indio_dev); +/** + * iio_device_try_claim_buffer_mode() - Keep device in buffer mode + * @indio_dev: the iio_dev associated with the device + * + * If the device is in buffer mode it is guaranteed to stay + * that way until iio_device_release_buffer_mode() is called. + * + * Use with iio_device_release_buffer_mode(). + * + * Returns: true on success, false on failure. + */ +static inline bool iio_device_try_claim_buffer_mode(struct iio_dev *indio_dev) +{ + __iio_dev_mode_lock(indio_dev); + + if (!iio_buffer_enabled(indio_dev)) { + __iio_dev_mode_unlock(indio_dev); + return false; + } + + return true; +} + +/** + * iio_device_release_buffer_mode() - releases claim on buffer mode + * @indio_dev: the iio_dev associated with the device + * + * Release the claim. Device is no longer guaranteed to stay + * in buffer mode. + * + * Use with iio_device_try_claim_buffer_mode(). + */ +#define iio_device_release_buffer_mode(indio_dev) __iio_dev_mode_unlock(indio_dev) extern const struct bus_type iio_bus_type; -- cgit v1.2.3 From 7a38b75da1dc38a8cd9563c41b87367b2475b975 Mon Sep 17 00:00:00 2001 From: Kurt Borja Date: Tue, 20 Jan 2026 01:20:44 -0500 Subject: iio: core: Add cleanup.h support for iio_device_claim_*() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add guard classes for iio_device_claim_*() conditional locks. This will aid drivers write safer and cleaner code when dealing with some common patterns. These classes are not meant to be used directly by drivers (hence the __priv__ prefix). Instead, documented wrapper macros are provided to enforce the use of ACQUIRE() or guard() semantics and avoid the problematic scoped guard. Suggested-by: Andy Shevchenko Reviewed-by: David Lechner Reviewed-by: Nuno Sá Acked-by: Andy Shevchenko Signed-off-by: Kurt Borja Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 65 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 36bd14e93a75..a9ecff191bd9 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -740,6 +741,70 @@ static inline bool iio_device_try_claim_buffer_mode(struct iio_dev *indio_dev) */ #define iio_device_release_buffer_mode(indio_dev) __iio_dev_mode_unlock(indio_dev) +/* + * These classes are not meant to be used directly by drivers (hence the + * __priv__ prefix). Instead, documented wrapper macros are provided below to + * enforce the use of ACQUIRE() or guard() semantics and avoid the problematic + * scoped guard variants. + */ +DEFINE_GUARD(__priv__iio_dev_mode_lock, struct iio_dev *, + __iio_dev_mode_lock(_T), __iio_dev_mode_unlock(_T)); +DEFINE_GUARD_COND(__priv__iio_dev_mode_lock, _try_direct, + iio_device_claim_direct(_T)); + +/** + * IIO_DEV_ACQUIRE_DIRECT_MODE() - Tries to acquire the direct mode lock with + * automatic release + * @dev: IIO device instance + * @claim: Variable identifier to store acquire result + * + * Tries to acquire the direct mode lock with cleanup ACQUIRE() semantics and + * automatically releases it at the end of the scope. It most be always paired + * with IIO_DEV_ACQUIRE_ERR(), for example (notice the scope braces):: + * + * switch() { + * case IIO_CHAN_INFO_RAW: { + * IIO_DEV_ACQUIRE_DIRECT_MODE(indio_dev, claim); + * if (IIO_DEV_ACQUIRE_FAILED(claim)) + * return -EBUSY; + * + * ... + * } + * case IIO_CHAN_INFO_SCALE: + * ... + * ... + * } + * + * Context: Can sleep + */ +#define IIO_DEV_ACQUIRE_DIRECT_MODE(dev, claim) \ + ACQUIRE(__priv__iio_dev_mode_lock_try_direct, claim)(dev) + +/** + * IIO_DEV_ACQUIRE_FAILED() - ACQUIRE_ERR() wrapper + * @claim: The claim variable passed to IIO_DEV_ACQUIRE_*_MODE() + * + * Return: true if failed to acquire the mode, otherwise false. + */ +#define IIO_DEV_ACQUIRE_FAILED(claim) \ + ACQUIRE_ERR(__priv__iio_dev_mode_lock_try_direct, &(claim)) + +/** + * IIO_DEV_GUARD_CURRENT_MODE() - Acquires the mode lock with automatic release + * @dev: IIO device instance + * + * Acquires the mode lock with cleanup guard() semantics. It is usually paired + * with iio_buffer_enabled(). + * + * This should *not* be used to protect internal driver state and it's use in + * general is *strongly* discouraged. Use any of the IIO_DEV_ACQUIRE_*_MODE() + * variants. + * + * Context: Can sleep + */ +#define IIO_DEV_GUARD_CURRENT_MODE(dev) \ + guard(__priv__iio_dev_mode_lock)(dev) + extern const struct bus_type iio_bus_type; /** -- cgit v1.2.3 From 404a3b4c36f2e1987ff28d1d61d309292d2e33cb Mon Sep 17 00:00:00 2001 From: Jonathan Santos Date: Wed, 14 Jan 2026 06:27:03 -0300 Subject: units: add conversion macros for percentage related units Add macros to convert between ratio and percentage related units, including percent (1/100), permille (1/1,000), permyriad (1/10,000, also equivalent to one Basis point) and per cent mille (1/100,000). Those are Used for precise fractional calculations in engineering, finance, and measurement applications. Signed-off-by: Jonathan Santos Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/units.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/units.h b/include/linux/units.h index 00e15de33eca..3471c5a38dcf 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -21,6 +21,25 @@ #define PICO 1000000000000ULL #define FEMTO 1000000000000000ULL +/* + * Percentage and related scaling units + * + * These macros define scaling factors used to convert between ratio and + * percentage-based representations with different decimal resolutions. + * They are used for precise fractional calculations in engineering, finance, + * and measurement applications. + * + * Examples: + * 1% = 0.01 = 1 / PERCENT + * 0.1% = 0.001 = 1 / PERMILLE + * 0.01% = 0.0001 = 1 / PERMYRIAD (1 basis point) + * 0.001% = 0.00001 = 1 / PERCENTMILLE + */ +#define PERCENT 100 +#define PERMILLE 1000 +#define PERMYRIAD 10000 +#define PERCENTMILLE 100000 + #define NANOHZ_PER_HZ 1000000000UL #define MICROHZ_PER_HZ 1000000UL #define MILLIHZ_PER_HZ 1000UL -- cgit v1.2.3 From dfd7b082c0a22ff0d697605a2a6bb62d9a4730a6 Mon Sep 17 00:00:00 2001 From: Andrei Kuchynski Date: Mon, 19 Jan 2026 13:18:18 +0000 Subject: usb: typec: Add mode_control field to port property This new field in the port properties dictates whether the Platform Policy Manager (PPM) allows the OS Policy Manager (OPM) to change the currently active, negotiated alternate mode. Signed-off-by: Andrei Kuchynski Reviewed-by: Heikki Krogerus Reviewed-by: Benson Leung Link: https://patch.msgid.link/20260119131824.2529334-2-akuchynski@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index c6fd46902fce..dbb259d88526 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -290,6 +290,7 @@ enum usb_pd_svdm_ver { * @prefer_role: Initial role preference (DRP ports). * @accessory: Supported Accessory Modes * @usb_capability: Supported USB Modes + * @no_mode_control: Ability to manage Alternate Modes * @fwnode: Optional fwnode of the port * @driver_data: Private pointer for driver specific info * @pd: Optional USB Power Delivery Support @@ -307,6 +308,7 @@ struct typec_capability { enum typec_accessory accessory[TYPEC_MAX_ACCESSORY]; unsigned int orientation_aware:1; u8 usb_capability; + bool no_mode_control; struct fwnode_handle *fwnode; void *driver_data; -- cgit v1.2.3 From 027b304ca3f6989f6946b5b3bcc727cf3f54774f Mon Sep 17 00:00:00 2001 From: Andrei Kuchynski Date: Mon, 19 Jan 2026 13:18:20 +0000 Subject: usb: typec: Expose alternate mode priority via sysfs This patch introduces a priority sysfs attribute to the USB Type-C alternate mode port interface. This new attribute allows user-space to configure the numeric priority of alternate modes managing their preferred order of operation. If a new priority value conflicts with an existing mode's priority, the priorities of the conflicting mode and all subsequent modes are automatically incremented to ensure uniqueness. Signed-off-by: Andrei Kuchynski Reviewed-by: Benson Leung Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260119131824.2529334-4-akuchynski@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_altmode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 9197a4637a93..7e6c02d74b54 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -36,6 +36,7 @@ struct typec_altmode { int mode; u32 vdo; unsigned int active:1; + u8 priority; char *desc; const struct typec_altmode_ops *ops; -- cgit v1.2.3 From fb2abc754672f769ca0bc36bdeb3c2f81927f446 Mon Sep 17 00:00:00 2001 From: Andrei Kuchynski Date: Mon, 19 Jan 2026 13:18:21 +0000 Subject: usb: typec: Implement mode selection The mode selection process is controlled by the following API functions, which allow to initiate and complete mode entry based on the priority of each mode: `typec_mode_selection_start` function compiles a priority list of supported Alternate Modes. `typec_altmode_state_update` function is invoked by the port driver to communicate the current mode of the Type-C connector. `typec_mode_selection_delete` function stops the currently running mode selection process and releases all associated system resources. `mode_selection_work_fn` task attempts to activate modes. The process stops on success; otherwise, it proceeds to the next mode after a timeout or error. Signed-off-by: Andrei Kuchynski Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260119131824.2529334-5-akuchynski@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec_altmode.h | 40 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 7e6c02d74b54..70026f5f8f99 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -240,4 +240,44 @@ void typec_altmode_unregister_driver(struct typec_altmode_driver *drv); module_driver(__typec_altmode_driver, typec_altmode_register_driver, \ typec_altmode_unregister_driver) +/** + * typec_mode_selection_start - Start an alternate mode selection process + * @partner: Handle to the Type-C partner device + * @delay: Delay between mode entry/exit attempts, ms + * @timeout: Timeout for a mode entry attempt, ms + * + * This function initiates the process of attempting to enter an Alternate Mode + * supported by the connected Type-C partner. + * Returns 0 on success, or a negative error code on failure. + */ +int typec_mode_selection_start(struct typec_partner *partner, + const unsigned int delay, const unsigned int timeout); + +/** + * typec_altmode_state_update - Report the current status of an Alternate Mode + * negotiation + * @partner: Handle to the Type-C partner device + * @svid: Standard or Vendor ID of the Alternate Mode. A value of 0 should be + * passed if no mode is currently active + * @result: Result of the entry operation. This should be 0 on success, or a + * negative error code if the negotiation failed + * + * This function should be called by an Alternate Mode driver to report the + * result of an asynchronous alternate mode entry request. It signals what the + * current active SVID is (or 0 if none) and the success or failure status of + * the last attempt. + */ +void typec_altmode_state_update(struct typec_partner *partner, const u16 svid, + const int result); + +/** + * typec_mode_selection_delete - Delete an alternate mode selection instance + * @partner: Handle to the Type-C partner device. + * + * This function cancels a pending alternate mode selection request that was + * previously started with typec_mode_selection_start(). + * This is typically called when the partner disconnects. + */ +void typec_mode_selection_delete(struct typec_partner *partner); + #endif /* __USB_TYPEC_ALTMODE_H */ -- cgit v1.2.3 From be727d4000669a64a3ce6697669150d78bb2d492 Mon Sep 17 00:00:00 2001 From: Andrei Kuchynski Date: Mon, 19 Jan 2026 13:18:22 +0000 Subject: usb: typec: Introduce mode_selection bit The port driver sets this bit for an alternate mode description to indicate support for the mode selection feature. Once set, individual Alt Mode drivers will no longer attempt to activate their respective modes within their probe functions. This prevents race conditions and non-prioritized activation. The bit is not set by default. If left unset, the system retains the current behavior where Alt Mode drivers manage their own activation logic. Signed-off-by: Andrei Kuchynski Reviewed-by: Heikki Krogerus Link: https://patch.msgid.link/20260119131824.2529334-6-akuchynski@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/typec.h | 1 + include/linux/usb/typec_altmode.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index dbb259d88526..d61ec38216fa 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -155,6 +155,7 @@ struct typec_altmode_desc { /* Only used with ports */ enum typec_port_data roles; bool inactive; + bool mode_selection; }; void typec_partner_set_pd_revision(struct typec_partner *partner, u16 pd_revision); diff --git a/include/linux/usb/typec_altmode.h b/include/linux/usb/typec_altmode.h index 70026f5f8f99..0513d333b797 100644 --- a/include/linux/usb/typec_altmode.h +++ b/include/linux/usb/typec_altmode.h @@ -37,6 +37,7 @@ struct typec_altmode { u32 vdo; unsigned int active:1; u8 priority; + bool mode_selection; char *desc; const struct typec_altmode_ops *ops; -- cgit v1.2.3 From 53cc2d90542cfee42bf73627c26318372e7ea50e Mon Sep 17 00:00:00 2001 From: Svyatoslav Ryhel Date: Thu, 22 Jan 2026 17:11:24 +0200 Subject: usb: phy: tegra: use phy type directly Refactor to directly use enum usb_phy_interface to determine the PHY mode. This change is in preparation for adding support for HSIC mode. Signed-off-by: Svyatoslav Ryhel Link: https://patch.msgid.link/20260122151125.7367-2-clamor95@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 40afcee8b4f5..fb5227353d3b 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -72,7 +72,7 @@ struct tegra_usb_phy { struct usb_phy *ulpi; struct usb_phy u_phy; bool is_legacy_phy; - bool is_ulpi_phy; + enum usb_phy_interface phy_type; struct gpio_desc *reset_gpio; struct reset_control *pad_rst; bool wakeup_enabled; -- cgit v1.2.3 From 8acc379b664ec987dcc7eca25a5f5c4a9a4eb9c4 Mon Sep 17 00:00:00 2001 From: Svyatoslav Ryhel Date: Thu, 22 Jan 2026 17:11:25 +0200 Subject: usb: phy: tegra: add HSIC support Add support for HSIC USB mode, which can be set for second USB controller and PHY on Tegra SoC along with already supported UTMI or ULPI. Signed-off-by: Svyatoslav Ryhel Link: https://patch.msgid.link/20260122151125.7367-3-clamor95@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index fb5227353d3b..6d57da13d395 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -23,6 +23,9 @@ struct gpio_desc; * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level * and hsdiscon_level should be set for adequate signal quality * requires_pmc_ao_power_up: true if USB AO is powered down by default + * uhsic_registers_shift: for Tegra30+ where HSIC registers were shifted + * comparing to Tegra20 by 0x400, since Tegra20 has no UTMIP on PHY2 + * uhsic_tx_rtune: fine tuned 50 Ohm termination resistor for NMOS/PMOS driver */ struct tegra_phy_soc_config { @@ -31,6 +34,8 @@ struct tegra_phy_soc_config { bool requires_usbmode_setup; bool requires_extra_tuning_parameters; bool requires_pmc_ao_power_up; + u32 uhsic_registers_shift; + u32 uhsic_tx_rtune; }; struct tegra_utmip_config { -- cgit v1.2.3 From d000422a46aad32217cf1be747eb61d641baae2f Mon Sep 17 00:00:00 2001 From: Xin Zhao Date: Tue, 23 Dec 2025 11:48:36 +0800 Subject: tty: tty_port: add workqueue to flip TTY buffer On the embedded platform, certain critical data, such as IMU data, is transmitted through UART. The tty_flip_buffer_push() interface in the TTY layer uses system_dfl_wq to handle the flipping of the TTY buffer. Although the unbound workqueue can create new threads on demand and wake up the kworker thread on an idle CPU, it may be preempted by real-time tasks or other high-prio tasks. flush_to_ldisc() needs to wake up the relevant data handle thread. When executing __wake_up_common_lock(), it calls spin_lock_irqsave(), which does not disable preemption but disables migration in RT-Linux. This prevents the kworker thread from being migrated to other cores by CPU's balancing logic, resulting in long delays. The call trace is as follows: __wake_up_common_lock __wake_up ep_poll_callback __wake_up_common __wake_up_common_lock __wake_up n_tty_receive_buf_common n_tty_receive_buf2 tty_ldisc_receive_buf tty_port_default_receive_buf flush_to_ldisc In our system, the processing interval for each frame of IMU data transmitted via UART can experience significant jitter due to this issue. Instead of the expected 10 to 15 ms frame processing interval, we see spikes up to 30 to 35 ms. Moreover, in just one or two hours, there can be 2 to 3 occurrences of such high jitter, which is quite frequent. This jitter exceeds the software's tolerable limit of 20 ms. Introduce flip_wq in tty_port which can be set by tty_port_link_wq() or as default linked to default workqueue allocated when tty_register_driver(). The default workqueue is allocated with flag WQ_SYSFS, so that cpumask and nice can be set dynamically. The execution timing of tty_port_link_wq() is not clearly restricted. The newly added function tty_port_link_driver_wq() checks whether the flip_wq of the tty_port has already been assigned when linking the default tty_driver's workqueue to the port. After the user has set a custom workqueue for a certain tty_port using tty_port_link_wq(), the system will only use this custom workqueue, even if tty_driver does not have %TTY_DRIVER_CUSTOM_WORKQUEUE flag. Introduce %TTY_DRIVER_CUSTOM_WORKQUEUE flag meaning not to create the default single tty_driver workqueue. Two reasons why need to introduce the %TTY_DRIVER_CUSTOM_WORKQUEUE flag: 1. If the WQ_SYSFS parameter is enabled, workqueue_sysfs_register() will fail when trying to create a workqueue with the same name. The pty is an example of this; if both CONFIG_LEGACY_PTYS and CONFIG_UNIX98_PTYS are enabled, the call to tty_register_driver() in unix98_pty_init() will fail. 2. Different tty ports may be used for different tasks, which may require separate core binding control via workqueues. In this case, the workqueue created by default in the tty driver is unnecessary. Enabling this flag prevents the creation of this redundant workqueue. After applying this patch, we can set the related UART TTY flip buffer workqueue by sysfs. We set the cpumask to CPU cores associated with the IMU tasks, and set the nice to -20. Testing has shown significant improvement in the previously described issue, with almost no stuttering occurring anymore. Signed-off-by: Xin Zhao Reviewed-by: Jiri Slaby Link: https://patch.msgid.link/20251223034836.2625547-1-jackzxcui1989@163.com Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_buffer.h | 1 + include/linux/tty_driver.h | 7 +++++++ include/linux/tty_port.h | 13 +++++++++++++ 3 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_buffer.h b/include/linux/tty_buffer.h index 31125e3be3c5..48adcb0e8ff3 100644 --- a/include/linux/tty_buffer.h +++ b/include/linux/tty_buffer.h @@ -34,6 +34,7 @@ static inline u8 *flag_buf_ptr(struct tty_buffer *b, unsigned int ofs) struct tty_bufhead { struct tty_buffer *head; /* Queue head */ + struct workqueue_struct *flip_wq; struct work_struct work; struct mutex lock; atomic_t priority; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 188ee9b768eb..9c65854f7d94 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -69,6 +69,10 @@ struct serial_struct; * Do not create numbered ``/dev`` nodes. For example, create * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a * driver for a single tty device is being allocated. + * + * @TTY_DRIVER_CUSTOM_WORKQUEUE: + * Do not create workqueue when tty_register_driver(). When set, flip + * buffer workqueue shall be set by tty_port_link_wq() for every port. */ enum tty_driver_flag { TTY_DRIVER_INSTALLED = BIT(0), @@ -79,6 +83,7 @@ enum tty_driver_flag { TTY_DRIVER_HARDWARE_BREAK = BIT(5), TTY_DRIVER_DYNAMIC_ALLOC = BIT(6), TTY_DRIVER_UNNUMBERED_NODE = BIT(7), + TTY_DRIVER_CUSTOM_WORKQUEUE = BIT(8), }; enum tty_driver_type { @@ -506,6 +511,7 @@ struct tty_operations { * @flags: tty driver flags (%TTY_DRIVER_) * @proc_entry: proc fs entry, used internally * @other: driver of the linked tty; only used for the PTY driver + * @flip_wq: workqueue to queue flip buffer work on * @ttys: array of active &struct tty_struct, set by tty_standard_install() * @ports: array of &struct tty_port; can be set during initialization by * tty_port_link_device() and similar @@ -539,6 +545,7 @@ struct tty_driver { unsigned long flags; struct proc_dir_entry *proc_entry; struct tty_driver *other; + struct workqueue_struct *flip_wq; /* * Pointer to the tty data structures diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index 660c254f1efe..c1b87f3c5603 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -138,6 +138,7 @@ struct tty_port { kernel */ void tty_port_init(struct tty_port *port); +void tty_port_link_wq(struct tty_port *port, struct workqueue_struct *flip_wq); void tty_port_link_device(struct tty_port *port, struct tty_driver *driver, unsigned index); struct device *tty_port_register_device(struct tty_port *port, @@ -165,6 +166,18 @@ static inline struct tty_port *tty_port_get(struct tty_port *port) return NULL; } +/* + * Never overwrite the workqueue set by tty_port_link_wq(). + * No effect when %TTY_DRIVER_CUSTOM_WORKQUEUE is set, as driver->flip_wq is + * %NULL. + */ +static inline void tty_port_link_driver_wq(struct tty_port *port, + struct tty_driver *driver) +{ + if (!port->buf.flip_wq) + port->buf.flip_wq = driver->flip_wq; +} + /* If the cts flow control is enabled, return true. */ static inline bool tty_port_cts_enabled(const struct tty_port *port) { -- cgit v1.2.3 From 2cddfc2e8fc78c13b0f5286ea5dd48cdf527ad41 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Fri, 26 Dec 2025 11:07:24 -0500 Subject: tracing: Add bitmask-list option for human-readable bitmask display Add support for displaying bitmasks in human-readable list format (e.g., 0,2-5,7) in addition to the default hexadecimal bitmap representation. This is particularly useful when tracing CPU masks and other large bitmasks where individual bit positions are more meaningful than their hexadecimal encoding. When the "bitmask-list" option is enabled, the printk "%*pbl" format specifier is used to render bitmasks as comma-separated ranges, making trace output easier to interpret for complex CPU configurations and large bitmask values. Link: https://patch.msgid.link/20251226160724.2246493-2-atomlin@atomlin.com Signed-off-by: Aaron Tomlin Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 8 ++++---- include/linux/trace_seq.h | 12 +++++++++++- 2 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3690221ba3d8..0a2b8229b999 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -38,7 +38,10 @@ const char *trace_print_symbols_seq_u64(struct trace_seq *p, *symbol_array); #endif -const char *trace_print_bitmask_seq(struct trace_seq *p, void *bitmask_ptr, +struct trace_iterator; +struct trace_event; + +const char *trace_print_bitmask_seq(struct trace_iterator *iter, void *bitmask_ptr, unsigned int bitmask_size); const char *trace_print_hex_seq(struct trace_seq *p, @@ -54,9 +57,6 @@ trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, bool ascii); -struct trace_iterator; -struct trace_event; - int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *event); extern __printf(2, 3) diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 4a0b8c172d27..697d619aafdc 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -114,7 +114,11 @@ extern void trace_seq_putmem_hex(struct trace_seq *s, const void *mem, extern int trace_seq_path(struct trace_seq *s, const struct path *path); extern void trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, - int nmaskbits); + int nmaskbits); + +extern void trace_seq_bitmask_list(struct trace_seq *s, + const unsigned long *maskp, + int nmaskbits); extern int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, int prefix_type, int rowsize, int groupsize, @@ -137,6 +141,12 @@ trace_seq_bitmask(struct trace_seq *s, const unsigned long *maskp, { } +static inline void +trace_seq_bitmask_list(struct trace_seq *s, const unsigned long *maskp, + int nmaskbits) +{ +} + static inline int trace_print_seq(struct seq_file *m, struct trace_seq *s) { return 0; -- cgit v1.2.3 From 0a15f43b92ddaa2fdb476891a12ac2e207c7fcd2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 27 Jan 2026 13:58:21 +0100 Subject: Revert "tty: tty_port: add workqueue to flip TTY buffer" This reverts commit d000422a46aad32217cf1be747eb61d641baae2f. It is reported by many to cause boot failures, so must be reverted. Cc: Xin Zhao Cc: Jiri Slaby Link: https://lore.kernel.org/r/d1942304-ee30-478d-90fb-279519f3ae81@samsung.com Reported-by: Marek Szyprowski Reported-by: Tommaso Merciai Reported-by: Geert Uytterhoeven Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_buffer.h | 1 - include/linux/tty_driver.h | 7 ------- include/linux/tty_port.h | 13 ------------- 3 files changed, 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_buffer.h b/include/linux/tty_buffer.h index 48adcb0e8ff3..31125e3be3c5 100644 --- a/include/linux/tty_buffer.h +++ b/include/linux/tty_buffer.h @@ -34,7 +34,6 @@ static inline u8 *flag_buf_ptr(struct tty_buffer *b, unsigned int ofs) struct tty_bufhead { struct tty_buffer *head; /* Queue head */ - struct workqueue_struct *flip_wq; struct work_struct work; struct mutex lock; atomic_t priority; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 9c65854f7d94..188ee9b768eb 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -69,10 +69,6 @@ struct serial_struct; * Do not create numbered ``/dev`` nodes. For example, create * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a * driver for a single tty device is being allocated. - * - * @TTY_DRIVER_CUSTOM_WORKQUEUE: - * Do not create workqueue when tty_register_driver(). When set, flip - * buffer workqueue shall be set by tty_port_link_wq() for every port. */ enum tty_driver_flag { TTY_DRIVER_INSTALLED = BIT(0), @@ -83,7 +79,6 @@ enum tty_driver_flag { TTY_DRIVER_HARDWARE_BREAK = BIT(5), TTY_DRIVER_DYNAMIC_ALLOC = BIT(6), TTY_DRIVER_UNNUMBERED_NODE = BIT(7), - TTY_DRIVER_CUSTOM_WORKQUEUE = BIT(8), }; enum tty_driver_type { @@ -511,7 +506,6 @@ struct tty_operations { * @flags: tty driver flags (%TTY_DRIVER_) * @proc_entry: proc fs entry, used internally * @other: driver of the linked tty; only used for the PTY driver - * @flip_wq: workqueue to queue flip buffer work on * @ttys: array of active &struct tty_struct, set by tty_standard_install() * @ports: array of &struct tty_port; can be set during initialization by * tty_port_link_device() and similar @@ -545,7 +539,6 @@ struct tty_driver { unsigned long flags; struct proc_dir_entry *proc_entry; struct tty_driver *other; - struct workqueue_struct *flip_wq; /* * Pointer to the tty data structures diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index c1b87f3c5603..660c254f1efe 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -138,7 +138,6 @@ struct tty_port { kernel */ void tty_port_init(struct tty_port *port); -void tty_port_link_wq(struct tty_port *port, struct workqueue_struct *flip_wq); void tty_port_link_device(struct tty_port *port, struct tty_driver *driver, unsigned index); struct device *tty_port_register_device(struct tty_port *port, @@ -166,18 +165,6 @@ static inline struct tty_port *tty_port_get(struct tty_port *port) return NULL; } -/* - * Never overwrite the workqueue set by tty_port_link_wq(). - * No effect when %TTY_DRIVER_CUSTOM_WORKQUEUE is set, as driver->flip_wq is - * %NULL. - */ -static inline void tty_port_link_driver_wq(struct tty_port *port, - struct tty_driver *driver) -{ - if (!port->buf.flip_wq) - port->buf.flip_wq = driver->flip_wq; -} - /* If the cts flow control is enabled, return true. */ static inline bool tty_port_cts_enabled(const struct tty_port *port) { -- cgit v1.2.3 From c86d39d6805474ab879c00ca6b938c6dd7e4d33f Mon Sep 17 00:00:00 2001 From: Tim Bird Date: Sat, 17 Jan 2026 13:00:38 -0700 Subject: kernel: debug: Add SPDX license ids to kdb files Add GPL-2.0 license id to some files related to kdb and kgdb, replacing references to GPL or COPYING. These files were introduced into the kernel in 2008 and 2010. Signed-off-by: Tim Bird Signed-off-by: Greg Kroah-Hartman --- include/linux/kdb.h | 5 +---- include/linux/kgdb.h | 4 +--- 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 741c58e86431..26fe4ab81b42 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -1,13 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KDB_H #define _KDB_H /* * Kernel Debugger Architecture Independent Global Headers * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * * Copyright (c) 2000-2007 Silicon Graphics, Inc. All Rights Reserved. * Copyright (C) 2000 Stephane Eranian * Copyright (C) 2009 Jason Wessel diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index 5eebbe7a3545..22b3f3839f30 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This provides the callbacks and functions that KGDB needs to share between * the core, I/O and arch-specific portions. @@ -6,9 +7,6 @@ * Tom Rini * * 2001-2004 (c) Amit S. Kale and 2003-2005 (c) MontaVista Software, Inc. - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. */ #ifndef _KGDB_H_ #define _KGDB_H_ -- cgit v1.2.3 From 18fa479b90c29a48481ee0aae98779278c51b96b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 9 Dec 2025 12:40:27 +0100 Subject: fsi: Provide thin wrappers around dev_[gs]et_data() for fsi devices MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Similar to wrappers for other subsystems provide inline functions for fsi devices to store driver data. Signed-off-by: Uwe Kleine-König Acked-by: Eddie James Link: https://patch.msgid.link/5de7a7cbb30918b3503235130bd8aa1a9a63d71c.1765279318.git.u.kleine-koenig@baylibre.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsi.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsi.h b/include/linux/fsi.h index adea1b432f2d..05be75869a69 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -19,6 +19,16 @@ struct fsi_device { uint32_t size; }; +static inline void *fsi_get_drvdata(struct fsi_device *fsi_dev) +{ + return dev_get_drvdata(&fsi_dev->dev); +} + +static inline void fsi_set_drvdata(struct fsi_device *fsi_dev, void *data) +{ + dev_set_drvdata(&fsi_dev->dev, data); +} + extern int fsi_device_read(struct fsi_device *dev, uint32_t addr, void *val, size_t size); extern int fsi_device_write(struct fsi_device *dev, uint32_t addr, -- cgit v1.2.3 From 68cc6588b52359ff9b48516525b463551a4bb315 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 9 Dec 2025 12:40:30 +0100 Subject: fsi: Make fsi_bus_type a private variable to the core MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no users of fsi_bus_type outside of fsi-core.c, so make that variable static, don't export it and drop the declaration from the public header file. As there is a usage of fsi_bus_type in fsi_create_device() the definition of that variable must happen further up in the file to not have to add a local declaration. Signed-off-by: Uwe Kleine-König Acked-by: Eddie James Link: https://patch.msgid.link/bfd83034dec04d5a6b01a234988377fc6224614d.1765279318.git.u.kleine-koenig@baylibre.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsi.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 05be75869a69..3e3a8f3adac3 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -78,7 +78,6 @@ extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr, extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr, const void *val, size_t size); -extern const struct bus_type fsi_bus_type; extern const struct device_type fsi_cdev_type; enum fsi_dev_type { -- cgit v1.2.3 From 69d4ca009005c14068fe358196c38281ec5ee316 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Tue, 9 Dec 2025 12:40:31 +0100 Subject: fsi: Create bus specific probe and remove functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a bus specific probe and remove function. For now this only allows to get rid of a cast of the generic device to an fsi device in the drivers and changes the remove prototype to return void---a non-zero return value is ignored anyhow. The objective is to get rid of users of struct device callbacks .probe(), .remove() and .shutdown() to eventually remove these. Until all fsi drivers are converted this results in a runtime warning about the drivers needing an update because there is a bus probe function and a driver probe function. Signed-off-by: Uwe Kleine-König Acked-by: Eddie James Link: https://patch.msgid.link/3b53adb75a5ae7894736d46cb6eb85f5ef36520e.1765279318.git.u.kleine-koenig@baylibre.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fsi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 3e3a8f3adac3..9c67c43f9e6c 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -49,6 +49,8 @@ struct fsi_device_id { .engine_type = (t), .version = (v), struct fsi_driver { + int (*probe)(struct fsi_device *fsidev); + void (*remove)(struct fsi_device *fsidev); struct device_driver drv; const struct fsi_device_id *id_table; }; -- cgit v1.2.3 From ca136b2553084120a1f864f14f4bc70f08cb6420 Mon Sep 17 00:00:00 2001 From: Remi Pommarel Date: Fri, 23 Jan 2026 15:48:07 +0100 Subject: wait: Introduce io_wait_event_killable() Add io_wait_event_killable(), a variant of wait_event_killable() that uses io_schedule() instead of schedule(). This is to be used in situation where waiting time is to be accounted as IO wait time. Signed-off-by: Remi Pommarel Acked-by: Peter Zijlstra (Intel) Message-ID: <1b2870001ecd34fe6c05be2ddfefb3c798b11701.1769179462.git.repk@triplefau.lt> Signed-off-by: Dominique Martinet --- include/linux/wait.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index f648044466d5..dce055e6add3 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -937,6 +937,21 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __io_wait_event_killable(wq, condition) \ + ___wait_event(wq, condition, TASK_KILLABLE, 0, 0, io_schedule()) + +/* + * wait_event_killable() - link wait_event_killable but with io_schedule() + */ +#define io_wait_event_killable(wq_head, condition) \ +({ \ + int __ret = 0; \ + might_sleep(); \ + if (!(condition)) \ + __ret = __io_wait_event_killable(wq_head, condition); \ + __ret; \ +}) + #define __wait_event_state(wq, condition, state) \ ___wait_event(wq, condition, state, 0, 0, schedule()) -- cgit v1.2.3 From 55fb177d3a0346106974749374ae2191ba250825 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Wed, 28 Jan 2026 14:24:05 +0100 Subject: fs: add helpers name_is_dot{,dot,_dotdot} Rename the helper is_dot_dotdot() into the name_ namespace and add complementary helpers to check for dot and dotdot names individually. Signed-off-by: Amir Goldstein Link: https://patch.msgid.link/20260128132406.23768-3-amir73il@gmail.com Reviewed-by: Eric Biggers Signed-off-by: Christian Brauner --- include/linux/fs.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 094b0adcb035..95bb9a15e109 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2844,12 +2844,22 @@ u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); extern char *file_path(struct file *, char *, int); +static inline bool name_is_dot(const char *name, size_t len) +{ + return unlikely(len == 1 && name[0] == '.'); +} + +static inline bool name_is_dotdot(const char *name, size_t len) +{ + return unlikely(len == 2 && name[0] == '.' && name[1] == '.'); +} + /** - * is_dot_dotdot - returns true only if @name is "." or ".." + * name_is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ -static inline bool is_dot_dotdot(const char *name, size_t len) +static inline bool name_is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); -- cgit v1.2.3 From 0e6b7eae1fded85f94a357d6132f07d64c614cfa Mon Sep 17 00:00:00 2001 From: Andrey Albershteyn Date: Mon, 26 Jan 2026 12:56:57 +0100 Subject: fs: add FS_XFLAG_VERITY for fs-verity files fs-verity introduced inode flag for inodes with enabled fs-verity on them. This patch adds FS_XFLAG_VERITY file attribute which can be retrieved with FS_IOC_FSGETXATTR ioctl() and file_getattr() syscall. This flag is read-only and can not be set with corresponding set ioctl() and file_setattr(). The FS_IOC_SETFLAGS requires file to be opened for writing which is not allowed for verity files. The FS_IOC_FSSETXATTR and file_setattr() clears this flag from the user input. As this is now common flag for both flag interfaces (flags/xflags) add it to overlapping flags list to exclude it from overwrite. Signed-off-by: Andrey Albershteyn Link: https://patch.msgid.link/20260126115658.27656-2-aalbersh@kernel.org Reviewed-by: Darrick J. Wong Signed-off-by: Christian Brauner --- include/linux/fileattr.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h index f89dcfad3f8f..3780904a63a6 100644 --- a/include/linux/fileattr.h +++ b/include/linux/fileattr.h @@ -7,16 +7,16 @@ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ - FS_PROJINHERIT_FL) + FS_PROJINHERIT_FL | FS_VERITY_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ - FS_XFLAG_PROJINHERIT) + FS_XFLAG_PROJINHERIT | FS_XFLAG_VERITY) /* Read-only inode flags */ #define FS_XFLAG_RDONLY_MASK \ - (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR) + (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR | FS_XFLAG_VERITY) /* Flags to indicate valid value of fsx_ fields */ #define FS_XFLAG_VALUES_MASK \ -- cgit v1.2.3 From a39162f77f49b618df5a721a1e48d8b903280fbd Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 29 Jan 2026 11:02:11 +0100 Subject: exportfs: clarify the documentation of open()/permission() expotrfs ops pidfs and nsfs recently gained support for encode/decode of file handles via name_to_handle_at(2)/open_by_handle_at(2). These special kernel filesystems have custom ->open() and ->permission() export methods, which nfsd does not respect and it was never meant to be used for exporting those filesystems by nfsd. Update kernel-doc comments to express the fact the those methods are for open_by_handle(2) system only and not compatible with nfsd. Reviewed-by: Jeff Layton Signed-off-by: Amir Goldstein Link: https://patch.msgid.link/20260129100212.49727-2-amir73il@gmail.com Reviewed-by: Chuck Lever Signed-off-by: Christian Brauner --- include/linux/exportfs.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 262e24d83313..0660953c3fb7 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -200,6 +200,10 @@ struct handle_to_path_ctx { * @get_parent: find the parent of a given directory * @commit_metadata: commit metadata changes to stable storage * + * Methods for open_by_handle(2) syscall with special kernel file systems: + * @permission: custom permission for opening a file by handle + * @open: custom open routine for opening file by handle + * * See Documentation/filesystems/nfs/exporting.rst for details on how to use * this interface correctly and the definition of the flags. * @@ -244,10 +248,14 @@ struct handle_to_path_ctx { * space cannot be allocated, a %ERR_PTR should be returned. * * @permission: - * Allow filesystems to specify a custom permission function. + * Allow filesystems to specify a custom permission function for the + * open_by_handle_at(2) syscall instead of the default permission check. + * This custom permission function is not respected by nfsd. * * @open: - * Allow filesystems to specify a custom open function. + * Allow filesystems to specify a custom open function for the + * open_by_handle_at(2) syscall instead of the default file_open_root(). + * This custom open function is not respected by nfsd. * * @commit_metadata: * @commit_metadata should commit metadata changes to stable storage. -- cgit v1.2.3 From b3c78bc53630d14a5770451ede3a30e7052f3b8b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 29 Jan 2026 11:02:12 +0100 Subject: nfsd: do not allow exporting of special kernel filesystems pidfs and nsfs recently gained support for encode/decode of file handles via name_to_handle_at(2)/open_by_handle_at(2). These special kernel filesystems have custom ->open() and ->permission() export methods, which nfsd does not respect and it was never meant to be used for exporting those filesystems by nfsd. Therefore, do not allow nfsd to export filesystems with custom ->open() or ->permission() methods. Fixes: b3caba8f7a34a ("pidfs: implement file handle support") Fixes: 5222470b2fbb3 ("nsfs: support file handles") Reviewed-by: Jeff Layton Signed-off-by: Amir Goldstein Link: https://patch.msgid.link/20260129100212.49727-3-amir73il@gmail.com Reviewed-by: Chuck Lever Signed-off-by: Christian Brauner --- include/linux/exportfs.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 0660953c3fb7..8bcdba28b406 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -338,6 +338,15 @@ static inline bool exportfs_can_decode_fh(const struct export_operations *nop) return nop && nop->fh_to_dentry; } +static inline bool exportfs_may_export(const struct export_operations *nop) +{ + /* + * Do not allow nfs export for filesystems with custom ->open() or + * ->permission() ops, which nfsd does not respect (e.g. pidfs, nsfs). + */ + return exportfs_can_decode_fh(nop) && !nop->open && !nop->permission; +} + static inline bool exportfs_can_encode_fh(const struct export_operations *nop, int fh_flags) { -- cgit v1.2.3 From bf870c97ce2b9b48f02184d317dab4cf5691ca0e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 28 Jan 2026 12:07:20 -0800 Subject: iio: buffer: buffer_impl.h: fix kernel-doc warnings Resolve all kernel-doc warnings in buffer_impl.h: Warning: include/linux/iio/buffer_impl.h:172 struct member 'direction' not described in 'iio_buffer' Warning: include/linux/iio/buffer_impl.h:184 No description found for return value of 'iio_update_buffers' Also correct one typo (word order switch) and remove one stray space in a kernel-doc comment. Signed-off-by: Randy Dunlap Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer_impl.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index c0b0e0992a85..9442c165561a 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -113,10 +113,10 @@ struct iio_buffer { /** @flags: File ops flags including busy flag. */ unsigned long flags; - /** @bytes_per_datum: Size of individual datum including timestamp. */ + /** @bytes_per_datum: Size of individual datum including timestamp. */ size_t bytes_per_datum; - /* @direction: Direction of the data stream (in/out). */ + /** @direction: Direction of the data stream (in/out). */ enum iio_buffer_direction direction; /** @@ -178,7 +178,9 @@ struct iio_buffer { * @insert_buffer: buffer to insert * @remove_buffer: buffer_to_remove * - * Note this will tear down the all buffering and build it up again + * Note this will tear down all the buffering and build it up again + * + * Returns: 0 on success or -errno on error */ int iio_update_buffers(struct iio_dev *indio_dev, struct iio_buffer *insert_buffer, -- cgit v1.2.3 From 2693ca2e02793fde06ff9d64175aed6f144f2287 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 27 Jan 2026 22:25:37 -0800 Subject: iio: frequency: ad9523: correct kernel-doc bad line warning Insert a "*" in the kernel-doc line to resolve a warning: Warning: include/linux/iio/frequency/ad9523.h:47 bad line: LSB = 1/2 of a period of the divider input clock. Signed-off-by: Randy Dunlap Reviewed-by: Andy Shevchenko Signed-off-by: Jonathan Cameron --- include/linux/iio/frequency/ad9523.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/frequency/ad9523.h b/include/linux/iio/frequency/ad9523.h index ff22a0ac15f5..236437a226b2 100644 --- a/include/linux/iio/frequency/ad9523.h +++ b/include/linux/iio/frequency/ad9523.h @@ -45,7 +45,7 @@ enum ref_sel_mode { * @output_dis: Disables, powers down the entire channel. * @driver_mode: Output driver mode (logic level family). * @divider_phase: Divider initial phase after a SYNC. Range 0..63 - LSB = 1/2 of a period of the divider input clock. + * LSB = 1/2 of a period of the divider input clock. * @channel_divider: 10-bit channel divider. * @extended_name: Optional descriptive channel name. */ -- cgit v1.2.3 From 0077e9b985482e5c020468c6257f8508f68aa0b2 Mon Sep 17 00:00:00 2001 From: Gwendal Grignou Date: Tue, 27 Jan 2026 19:27:02 -0800 Subject: iio: cros_ec: Allow enabling/disabling calibration mode 'calibrate' was a one-shot event sent to the sensor to calibrate itself. It is used on Bosch sensors (BMI160, BMA254). Light sensors work differently: They are first put in calibration mode, tests are run to collect information and calculate the calibration values to apply. Once done, the sensors are put back in normal mode. Accept boolean true and false (not just true) to enter/exit calibration state. Check "echo 0 > calibrate" is supported. Signed-off-by: Gwendal Grignou Reviewed-by: Nick Vaccaro Reviewed-by: Tzung-Bi Shih Signed-off-by: Jonathan Cameron --- include/linux/platform_data/cros_ec_commands.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index 69294f79cc88..d363d60bb8a3 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -2598,13 +2598,19 @@ struct ec_params_motion_sense { /* * Used for MOTIONSENSE_CMD_INFO, MOTIONSENSE_CMD_DATA - * and MOTIONSENSE_CMD_PERFORM_CALIB. */ struct __ec_todo_unpacked { uint8_t sensor_num; - } info, info_3, data, fifo_flush, perform_calib, - list_activities; + } info, info_3, data, fifo_flush, list_activities; + /* + * Used for MOTIONSENSE_CMD_PERFORM_CALIB: + * Allow entering/exiting the calibration mode. + */ + struct __ec_todo_unpacked { + uint8_t sensor_num; + uint8_t enable; + } perform_calib; /* * Used for MOTIONSENSE_CMD_EC_RATE, MOTIONSENSE_CMD_SENSOR_ODR * and MOTIONSENSE_CMD_SENSOR_RANGE. -- cgit v1.2.3 From d095d2dbcc8df60ede1674e28ce0f0a478d37535 Mon Sep 17 00:00:00 2001 From: Brian Masney Date: Mon, 12 Jan 2026 17:47:58 -0500 Subject: MIPS: copy pic32.h header file from asm/mach-pic32/ to include/platform-data/ There are currently some pic32 MIPS drivers that are in tree, and are only configured to be compiled on the pic32 platform. There's a risk of breaking some of these drivers when migrating drivers away from legacy APIs. It happened to me with a pic32 clk driver. Let's go ahead and copy the MIPS pic32.h header to include/linux/platform_data/, and make a minor update to allow compiling this on other architectures. This will make it easier, and cleaner to enable COMPILE_TEST for some of these pic32 drivers. The asm variant of the header file will be dropped once all drivers have been updated. Link: https://lore.kernel.org/linux-clk/CABx5tq+eOocJ41X-GSgkGy6S+s+Am1yCS099wqP695NtwALTmg@mail.gmail.com/T/ Signed-off-by: Brian Masney Signed-off-by: Thomas Bogendoerfer --- include/linux/platform_data/pic32.h | 39 +++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 include/linux/platform_data/pic32.h (limited to 'include/linux') diff --git a/include/linux/platform_data/pic32.h b/include/linux/platform_data/pic32.h new file mode 100644 index 000000000000..f0b395fdb784 --- /dev/null +++ b/include/linux/platform_data/pic32.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Joshua Henderson + * Copyright (C) 2015 Microchip Technology Inc. All rights reserved. + */ +#ifndef __LINUX_PLATFORM_DATA_PIC32_H +#define __LINUX_PLATFORM_DATA_PIC32_H + +#include + +/* + * PIC32 register offsets for SET/CLR/INV where supported. + */ +#define PIC32_CLR(_reg) ((_reg) + 0x04) +#define PIC32_SET(_reg) ((_reg) + 0x08) +#define PIC32_INV(_reg) ((_reg) + 0x0C) + +/* + * PIC32 Base Register Offsets + */ +#define PIC32_BASE_CONFIG 0x1f800000 +#define PIC32_BASE_OSC 0x1f801200 +#define PIC32_BASE_RESET 0x1f801240 +#define PIC32_BASE_PPS 0x1f801400 +#define PIC32_BASE_UART 0x1f822000 +#define PIC32_BASE_PORT 0x1f860000 +#define PIC32_BASE_DEVCFG2 0x1fc4ff44 + +#if defined(CONFIG_MACH_PIC32) +/* Register unlock sequence required for some register access. */ +void pic32_syskey_unlock_debug(const char *fn, const ulong ln); +#define pic32_syskey_unlock() \ + pic32_syskey_unlock_debug(__func__, __LINE__) +#else +/* COMPILE_TEST on all other architectures */ +#define pic32_syskey_unlock() +#endif + +#endif /* __LINUX_PLATFORM_DATA_PIC32_H */ -- cgit v1.2.3 From a46023d5616ed3ed781e56ca93400eb9490e3646 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 26 Jan 2026 18:11:48 -0500 Subject: tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast The current use of guard(preempt_notrace)() within __DECLARE_TRACE() to protect invocation of __DO_TRACE_CALL() means that BPF programs attached to tracepoints are non-preemptible. This is unhelpful in real-time systems, whose users apparently wish to use BPF while also achieving low latencies. (Who knew?) One option would be to use preemptible RCU, but this introduces many opportunities for infinite recursion, which many consider to be counterproductive, especially given the relatively small stacks provided by the Linux kernel. These opportunities could be shut down by sufficiently energetic duplication of code, but this sort of thing is considered impolite in some circles. Therefore, use the shiny new SRCU-fast API, which provides somewhat faster readers than those of preemptible RCU, at least on Paul E. McKenney's laptop, where task_struct access is more expensive than access to per-CPU variables. And SRCU-fast provides way faster readers than does SRCU, courtesy of being able to avoid the read-side use of smp_mb(). Also, it is quite straightforward to create srcu_read_{,un}lock_fast_notrace() functions. Link: https://lore.kernel.org/all/20250613152218.1924093-1-bigeasy@linutronix.de/ Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Sebastian Andrzej Siewior Cc: Alexei Starovoitov Link: https://patch.msgid.link/20260126231256.499701982@kernel.org Co-developed-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Signed-off-by: Steven Rostedt (Google) --- include/linux/tracepoint.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 8a56f3278b1b..22ca1c8b54f3 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -108,14 +108,15 @@ void for_each_tracepoint_in_module(struct module *mod, * An alternative is to use the following for batch reclaim associated * with a given tracepoint: * - * - tracepoint_is_faultable() == false: call_rcu() + * - tracepoint_is_faultable() == false: call_srcu() * - tracepoint_is_faultable() == true: call_rcu_tasks_trace() */ #ifdef CONFIG_TRACEPOINTS +extern struct srcu_struct tracepoint_srcu; static inline void tracepoint_synchronize_unregister(void) { synchronize_rcu_tasks_trace(); - synchronize_rcu(); + synchronize_srcu(&tracepoint_srcu); } static inline bool tracepoint_is_faultable(struct tracepoint *tp) { @@ -275,13 +276,13 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) return static_branch_unlikely(&__tracepoint_##name.key);\ } -#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ +#define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ __DECLARE_TRACE_COMMON(name, PARAMS(proto), PARAMS(args), PARAMS(data_proto)) \ static inline void __do_trace_##name(proto) \ { \ TRACEPOINT_CHECK(name) \ if (cond) { \ - guard(preempt_notrace)(); \ + guard(srcu_fast_notrace)(&tracepoint_srcu); \ __DO_TRACE_CALL(name, TP_ARGS(args)); \ } \ } \ -- cgit v1.2.3 From 17926aa1b62c6ddb1e2ddbda8b2ac46913c5311c Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 27 Jan 2026 11:32:06 +0100 Subject: pinctrl: core: Remove unused devm_pinctrl_unregister() There are no users, drop it for good. Signed-off-by: Andy Shevchenko Reviewed-by: Bartosz Golaszewski Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 1a8084e29405..c329cc693139 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -187,9 +187,6 @@ extern struct pinctrl_dev *devm_pinctrl_register(struct device *dev, const struct pinctrl_desc *pctldesc, void *driver_data); -extern void devm_pinctrl_unregister(struct device *dev, - struct pinctrl_dev *pctldev); - extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range); extern void pinctrl_add_gpio_ranges(struct pinctrl_dev *pctldev, -- cgit v1.2.3 From f4b830a5371914239756b0599e5dc9d4c328e387 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Duje=20Mihanovi=C4=87?= Date: Wed, 17 Dec 2025 19:14:23 +0100 Subject: leds: expresswire: Fix chip state breakage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is possible to put the KTD2801 chip in an unknown/undefined state by changing the brightness very rapidly (for example, with a brightness slider). When this happens, the brightness is stuck on max and cannot be changed until the chip is power cycled. Fix this by disabling interrupts while talking to the chip. While at it, make expresswire_power_off() use fsleep() and also unexport some functions meant to be internal. Fixes: 1368d06dd2c9 ("leds: Introduce ExpressWire library") Tested-by: Karel Balej Signed-off-by: Duje Mihanović Link: https://patch.msgid.link/20251217-expresswire-fix-v2-1-4a02b10acd96@dujemihanovic.xyz Signed-off-by: Lee Jones --- include/linux/leds-expresswire.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/leds-expresswire.h b/include/linux/leds-expresswire.h index a422921f4159..7f8c4795f69f 100644 --- a/include/linux/leds-expresswire.h +++ b/include/linux/leds-expresswire.h @@ -30,9 +30,6 @@ struct expresswire_common_props { void expresswire_power_off(struct expresswire_common_props *props); void expresswire_enable(struct expresswire_common_props *props); -void expresswire_start(struct expresswire_common_props *props); -void expresswire_end(struct expresswire_common_props *props); -void expresswire_set_bit(struct expresswire_common_props *props, bool bit); void expresswire_write_u8(struct expresswire_common_props *props, u8 val); #endif /* _LEDS_EXPRESSWIRE_H */ -- cgit v1.2.3 From aacad391440ecc4f25e8d2db0d944a74fd874dd2 Mon Sep 17 00:00:00 2001 From: Svyatoslav Ryhel Date: Mon, 2 Feb 2026 10:05:23 +0200 Subject: usb: phy: tegra: cosmetic fixes Change TEGRA_USB_HOSTPC1_DEVLC_PTS_HSIC to its literal value instead of using the BIT macro, as it is an enumeration. Correct the spelling in the comment and rename uhsic_registers_shift to uhsic_registers_offset. These changes are cosmetic and do not affect code behavior. Signed-off-by: Svyatoslav Ryhel Reviewed-by: Mikko Perttunen Link: https://patch.msgid.link/20260202080526.23487-2-clamor95@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 6d57da13d395..91420df25627 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -23,7 +23,7 @@ struct gpio_desc; * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level * and hsdiscon_level should be set for adequate signal quality * requires_pmc_ao_power_up: true if USB AO is powered down by default - * uhsic_registers_shift: for Tegra30+ where HSIC registers were shifted + * uhsic_registers_offset: for Tegra30+ where HSIC registers were offset * comparing to Tegra20 by 0x400, since Tegra20 has no UTMIP on PHY2 * uhsic_tx_rtune: fine tuned 50 Ohm termination resistor for NMOS/PMOS driver */ @@ -34,7 +34,7 @@ struct tegra_phy_soc_config { bool requires_usbmode_setup; bool requires_extra_tuning_parameters; bool requires_pmc_ao_power_up; - u32 uhsic_registers_shift; + u32 uhsic_registers_offset; u32 uhsic_tx_rtune; }; -- cgit v1.2.3 From 8dc7ab65bd15e3c774f60ca073158bcb9a26ee5b Mon Sep 17 00:00:00 2001 From: Svyatoslav Ryhel Date: Mon, 2 Feb 2026 10:05:25 +0200 Subject: usb: phy: tegra: parametrize HSIC PTS value The parallel transceiver select used in HSIC mode differs on Tegra20, where it uses the UTMI value (0), whereas Tegra30+ uses a dedicated HSIC value. Reflect this in the SoC config. Signed-off-by: Svyatoslav Ryhel Reviewed-by: Mikko Perttunen Link: https://patch.msgid.link/20260202080526.23487-4-clamor95@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 91420df25627..7209b7731c29 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -26,6 +26,7 @@ struct gpio_desc; * uhsic_registers_offset: for Tegra30+ where HSIC registers were offset * comparing to Tegra20 by 0x400, since Tegra20 has no UTMIP on PHY2 * uhsic_tx_rtune: fine tuned 50 Ohm termination resistor for NMOS/PMOS driver + * uhsic_pts_value: parallel transceiver select enumeration value */ struct tegra_phy_soc_config { @@ -36,6 +37,7 @@ struct tegra_phy_soc_config { bool requires_pmc_ao_power_up; u32 uhsic_registers_offset; u32 uhsic_tx_rtune; + u32 uhsic_pts_value; }; struct tegra_utmip_config { -- cgit v1.2.3 From e5b250214aa402e079de566e10f6e01223fd26bd Mon Sep 17 00:00:00 2001 From: Svyatoslav Ryhel Date: Mon, 2 Feb 2026 10:05:26 +0200 Subject: usb: phy: tegra: parametrize PORTSC1 register offset The PORTSC1 register has a different offset in Tegra20 compared to Tegra30+, yet they share a crucial set of registers required for HSIC functionality. Reflect this register offset change in the SoC config. Signed-off-by: Svyatoslav Ryhel Reviewed-by: Mikko Perttunen Link: https://patch.msgid.link/20260202080526.23487-5-clamor95@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/tegra_usb_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 7209b7731c29..6343f88df5de 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -27,6 +27,7 @@ struct gpio_desc; * comparing to Tegra20 by 0x400, since Tegra20 has no UTMIP on PHY2 * uhsic_tx_rtune: fine tuned 50 Ohm termination resistor for NMOS/PMOS driver * uhsic_pts_value: parallel transceiver select enumeration value + * portsc1_offset: register offset of PORTSC1 */ struct tegra_phy_soc_config { @@ -38,6 +39,7 @@ struct tegra_phy_soc_config { u32 uhsic_registers_offset; u32 uhsic_tx_rtune; u32 uhsic_pts_value; + u32 portsc1_offset; }; struct tegra_utmip_config { -- cgit v1.2.3 From 9c5a40f2922a5a6d6b42e7b3d4c8e253918c07a1 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Tue, 3 Feb 2026 16:17:07 +0000 Subject: pinctrl: generic: move function to amlogic-am4 driver pinconf_generic_dt_node_to_map_pinmux() is not actually a generic function, and really belongs in the amlogic-am4 driver. There are three reasons why. First, and least, of the reasons is that this function behaves differently to the other dt_node_to_map functions in a way that is not obvious from a first glance. This difference stems for the devicetree properties that the function is intended for use with, and how they are typically used. The other generic dt_node_to_map functions support platforms where the pins, groups and functions are described statically in the driver and require a function that will produce a mapping from dt nodes to these pre-established descriptions. No other code in the driver is require to be executed at runtime. pinconf_generic_dt_node_to_map_pinmux() on the other hand is intended for use with the pinmux property, where groups and functions are determined entirely from the devicetree. As a result, there are no statically defined groups and functions in the driver for this function to perform a mapping to. Other drivers that use the pinmux property (e.g. the k1) their dt_node_to_map function creates the groups and functions as the devicetree is parsed. Instead of that, pinconf_generic_dt_node_to_map_pinmux() requires that the devicetree is parsed twice, once by it and once at probe, so that the driver dynamically creates the groups and functions before the dt_node_to_map callback is executed. I don't believe this double parsing requirement is how developers would expect this to work and is not necessary given there are drivers that do not have this behaviour. Secondly and thirdly, the function bakes in some assumptions that only really match the amlogic platform about how the devicetree is constructed. These, to me, are problematic for something that claims to be generic. The other dt_node_to_map implementations accept a being called for either a node containing pin configuration properties or a node containing child nodes that each contain the configuration properties. IOW, they support the following two devicetree configurations: | cfg { | label: group { | pinmux = ; | config-item1; | }; | }; | label: cfg { | group1 { | pinmux = ; | config-item2; | }; | group2 { | pinmux = ; | config-item1; | }; | }; pinconf_generic_dt_node_to_map_pinmux() only supports the latter. The other assumption about devicetree configuration that the function makes is that the labeled node's parent is a "function node". The amlogic driver uses these "function nodes" to create the functions at probe time, and pinconf_generic_dt_node_to_map_pinmux() finds the parent of the node it is operating on's name as part of the mapping. IOW, it requires that the devicetree look like: | pinctrl@bla { | | func-foo { | label: group-default { | pinmuxes = ; | }; | }; | }; and couldn't be used if the nodes containing the pinmux and configuration properties are children of the pinctrl node itself: | pinctrl@bla { | | label: group-default { | pinmuxes = ; | }; | }; These final two reasons are mainly why I believe this is not suitable as a generic function, and should be moved into the driver that is the sole user and originator of the "generic" function. Signed-off-by: Conor Dooley Acked-by: Andy Shevchenko Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 1be4032071c2..89277808ea61 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -250,9 +250,4 @@ static inline int pinconf_generic_dt_node_to_map_all(struct pinctrl_dev *pctldev return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps, PIN_MAP_TYPE_INVALID); } - -int pinconf_generic_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev, - struct device_node *np, - struct pinctrl_map **map, - unsigned int *num_maps); #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */ -- cgit v1.2.3 From b7cc142dbafeaf6c053284ca9121b9f70b6d6d06 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 22 Dec 2025 20:41:27 +0100 Subject: libceph: add support for CEPH_CRYPTO_AES256KRB5 This is based on AES256-CTS-HMAC384-192 crypto algorithm per RFC 8009 (i.e. Kerberos 5, hence the name) with custom-defined key usage numbers. The implementation allows a given key to have/be linked to between one and three usage numbers. The existing CEPH_CRYPTO_AES remains in place and unchanged. The usage_slot parameter that needed to be added to ceph_crypt() and its wrappers is simply ignored there. Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 08e5dbe15ca4..69ac3e55a3fe 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -89,8 +89,9 @@ struct ceph_dir_layout { } __attribute__ ((packed)); /* crypto algorithms */ -#define CEPH_CRYPTO_NONE 0x0 -#define CEPH_CRYPTO_AES 0x1 +#define CEPH_CRYPTO_NONE 0x0 +#define CEPH_CRYPTO_AES 0x1 +#define CEPH_CRYPTO_AES256KRB5 0x2 /* AES256-CTS-HMAC384-192 */ #define CEPH_AES_IV "cephsageyudagreg" -- cgit v1.2.3 From 802182490445f6bcf5de0e0518fb967c2afb6da1 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 20 Jan 2026 15:52:35 +0100 Subject: pidfs: convert rb-tree to rhashtable Mateusz reported performance penalties [1] during task creation because pidfs uses pidmap_lock to add elements into the rbtree. Switch to an rhashtable to have separate fine-grained locking and to decouple from pidmap_lock moving all heavy manipulations outside of it. Convert the pidfs inode-to-pid mapping from an rb-tree with seqcount protection to an rhashtable. This removes the global pidmap_lock contention from pidfs_ino_get_pid() lookups and allows the hashtable insert to happen outside the pidmap_lock. pidfs_add_pid() is split. pidfs_prepare_pid() allocates inode number and initializes pid fields and is called inside pidmap_lock. pidfs_add_pid() inserts pid into rhashtable and is called outside pidmap_lock. Insertion into the rhashtable can fail and memory allocation may happen so we need to drop the spinlock. To guard against accidently opening an already reaped task pidfs_ino_get_pid() uses additional checks beyond pid_vnr(). If pid->attr is PIDFS_PID_DEAD or NULL the pid either never had a pidfd or it already went through pidfs_exit() aka the process as already reaped. If pid->attr is valid check PIDFS_ATTR_BIT_EXIT to figure out whether the task has exited. This slightly changes visibility semantics: pidfd creation is denied after pidfs_exit() runs, which is just before the pid number is removed from the via free_pid(). That should not be an issue though. Link: https://lore.kernel.org/20251206131955.780557-1-mjguzik@gmail.com [1] Link: https://patch.msgid.link/20260120-work-pidfs-rhashtable-v2-1-d593c4d0f576@kernel.org Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/pid.h | 4 ++-- include/linux/pidfs.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 003a1027d219..ce9b5cb7560b 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -6,6 +6,7 @@ #include #include #include +#include #include #include @@ -60,7 +61,7 @@ struct pid { spinlock_t lock; struct { u64 ino; - struct rb_node pidfs_node; + struct rhash_head pidfs_hash; struct dentry *stashed; struct pidfs_attr *attr; }; @@ -73,7 +74,6 @@ struct pid { struct upid numbers[]; }; -extern seqcount_spinlock_t pidmap_lock_seq; extern struct pid init_struct_pid; struct file; diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 3e08c33da2df..416bdff4d6ce 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -6,7 +6,8 @@ struct coredump_params; struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); -void pidfs_add_pid(struct pid *pid); +void pidfs_prepare_pid(struct pid *pid); +int pidfs_add_pid(struct pid *pid); void pidfs_remove_pid(struct pid *pid); void pidfs_exit(struct task_struct *tsk); #ifdef CONFIG_COREDUMP -- cgit v1.2.3 From 03aef0602f22f30aab0e42e7f3169b0a5920c461 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 20 Jan 2026 21:48:20 +0100 Subject: pid: reorder fields in pid_namespace to reduce false sharing alloc_pid() loads pid_cachep, level and pid_max prior to taking the lock. It dirties idr and pid_allocated with the lock. Some of these fields share the cacheline as is, split them up. No change in the size of the struct. Signed-off-by: Mateusz Guzik Link: https://patch.msgid.link/20260120204820.1497002-1-mjguzik@gmail.com Reviewed-by: Jan Kara Signed-off-by: Christian Brauner --- include/linux/pid_namespace.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 0e7ae12c96d2..b20baaa7e62b 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -27,6 +27,13 @@ struct pid_namespace { struct idr idr; struct rcu_head rcu; unsigned int pid_allocated; +#ifdef CONFIG_SYSCTL +#if defined(CONFIG_MEMFD_CREATE) + int memfd_noexec_scope; +#endif + struct ctl_table_set set; + struct ctl_table_header *sysctls; +#endif struct task_struct *child_reaper; struct kmem_cache *pid_cachep; unsigned int level; @@ -40,13 +47,6 @@ struct pid_namespace { int reboot; /* group exit code if this pidns was rebooted */ struct ns_common ns; struct work_struct work; -#ifdef CONFIG_SYSCTL - struct ctl_table_set set; - struct ctl_table_header *sysctls; -#if defined(CONFIG_MEMFD_CREATE) - int memfd_noexec_scope; -#endif -#endif } __randomize_layout; extern struct pid_namespace init_pid_ns; -- cgit v1.2.3 From c4d6d7829817f762dfdce829ffd0c14ea3bad7fe Mon Sep 17 00:00:00 2001 From: Harry Yoo Date: Tue, 10 Feb 2026 13:46:41 +0900 Subject: mm/slab: allow freeing kmalloc_nolock()'d objects using kfree[_rcu]() Slab objects that are allocated with kmalloc_nolock() must be freed using kfree_nolock() because only a subset of alloc hooks are called, since kmalloc_nolock() can't spin on a lock during allocation. This imposes a limitation: such objects cannot be freed with kfree_rcu(), forcing users to work around this limitation by calling call_rcu() with a callback that frees the object using kfree_nolock(). Remove this limitation by teaching kmemleak to gracefully ignore cases when kmemleak_free() or kmemleak_ignore() is called without a prior kmemleak_alloc(). Unlike kmemleak, kfence already handles this case, because, due to its design, only a subset of allocations are served from kfence. With this change, kfree() and kfree_rcu() can be used to free objects that are allocated using kmalloc_nolock(). Suggested-by: Alexei Starovoitov Acked-by: Alexei Starovoitov Reviewed-by: Catalin Marinas Signed-off-by: Harry Yoo Link: https://patch.msgid.link/20260210044642.139482-2-harry.yoo@oracle.com Signed-off-by: Vlastimil Babka --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c5b30054cd01..72ba681360ad 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1076,8 +1076,8 @@ static inline void rcu_read_unlock_migrate(void) * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * - * The object to be freed can be allocated either by kmalloc() or - * kmem_cache_alloc(). + * The object to be freed can be allocated either by kmalloc(), + * kmalloc_nolock(), or kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * -- cgit v1.2.3 From 27125df9a5d3b4cfd03bce3a8ec405a368cc9aae Mon Sep 17 00:00:00 2001 From: Harry Yoo Date: Tue, 10 Feb 2026 13:46:42 +0900 Subject: mm/slab: drop the OBJEXTS_NOSPIN_ALLOC flag from enum objext_flags OBJEXTS_NOSPIN_ALLOC was used to remember whether a slabobj_ext vector was allocated via kmalloc_nolock(), so that free_slab_obj_exts() could call kfree_nolock() instead of kfree(). Now that kfree() supports freeing kmalloc_nolock() objects, this flag is no longer needed. Instead, pass the allow_spin parameter down to free_slab_obj_exts() to determine whether kfree_nolock() or kfree() should be called in the free path, and free one bit in enum objext_flags. Acked-by: Alexei Starovoitov Signed-off-by: Harry Yoo Reviewed-by: Hao Li Link: https://patch.msgid.link/20260210044642.139482-3-harry.yoo@oracle.com Signed-off-by: Vlastimil Babka --- include/linux/memcontrol.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0651865a4564..bb789ec4a2a2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -359,8 +359,7 @@ enum objext_flags { * MEMCG_DATA_OBJEXTS. */ OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, - /* slabobj_ext vector allocated with kmalloc_nolock() */ - OBJEXTS_NOSPIN_ALLOC = __FIRST_OBJEXT_FLAG, + __OBJEXTS_FLAG_UNUSED = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; -- cgit v1.2.3 From 84f90ab5d3e859cced1d7b080adc4ea562ca2eaa Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 15 Oct 2025 14:36:33 +0200 Subject: pid: introduce task_ppid_vnr() helper Cosmetic change. Unlike all other similar helpers task_ppid_nr_ns() doesn't have a _vnr() version; add one for consistency. Signed-off-by: Oleg Nesterov Link: https://patch.msgid.link/20251015123633.GB9456@redhat.com Signed-off-by: Christian Brauner --- include/linux/pid.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index ce9b5cb7560b..ddaef0bbc8ba 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -310,6 +310,11 @@ static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_na return pid; } +static inline pid_t task_ppid_vnr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, NULL); +} + static inline pid_t task_ppid_nr(const struct task_struct *tsk) { return task_ppid_nr_ns(tsk, &init_pid_ns); -- cgit v1.2.3 From 9342bf3d670b1b3d3cfc77a9dc1cd0d6574e5cc6 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Tue, 10 Feb 2026 16:17:11 -0800 Subject: configfs-tsm-report: Increase TSM_REPORT_OUTBLOB_MAX to 16MB Confidential Computing (CoCo) attestation is evolving toward standardized models such as DICE (Device Identifier Composition Engine) and Post-Quantum Cryptography (PQC), which rely on layered certificate chains and larger cryptographic signatures. A typical PQC certificate can range from 5KB to 15KB, and DICE-based architectures accumulate these certificates across multiple boot stages. In such configurations, the total attestation evidence can reach several megabytes, exceeding the current 32KB limit. Increase TSM_REPORT_OUTBLOB_MAX to 16MB to accommodate these larger certificate chains. This provides sufficient headroom to handle evolving requirements without requiring frequent updates to the limit. TSM_REPORT_OUTBLOB_MAX is used by the configfs read interface to cap the maximum allowed binary blob size for outblob, auxblob and manifestblob attributes. Hence, the per-open-file worst case memory allocation increases from 32KB to 16MB. Multiple concurrent readers multiply this cost (e.g., N readers of an M-byte blob incur NxM bytes of vmalloc-backed memory). However, allocations are performed on demand and remain proportional to the actual blob length, not the configured maximum. Reviewed-by: Fang Peter Signed-off-by: Kuppuswamy Sathyanarayanan Link: https://patch.msgid.link/20260211001712.1531955-3-sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Dan Williams --- include/linux/tsm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tsm.h b/include/linux/tsm.h index a3b7ab668eff..7f72a154b6b2 100644 --- a/include/linux/tsm.h +++ b/include/linux/tsm.h @@ -8,7 +8,7 @@ #include #define TSM_REPORT_INBLOB_MAX 64 -#define TSM_REPORT_OUTBLOB_MAX SZ_32K +#define TSM_REPORT_OUTBLOB_MAX SZ_16M /* * Privilege level is a nested permission concept to allow confidential -- cgit v1.2.3 From b777b5e09eabeefc6ba80f4296366a4742701103 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 10 Feb 2026 17:02:25 +0000 Subject: time/jiffies: Inline jiffies_to_msecs() and jiffies_to_usecs() For common cases (HZ=100, 250 or 1000), these helpers are at most one multiply, so there is no point calling a tiny function. Keep them out of line for HZ=300 and others. This saves cycles in TCP fast path, among other things. $ scripts/bloat-o-meter -t vmlinux.old vmlinux.new add/remove: 0/8 grow/shrink: 25/89 up/down: 530/-3474 (-2944) ... nla_put_msecs 193 - -193 message_stats_print 2131 920 -1211 Total: Before=25365208, After=25362264, chg -0.01% Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260210170226.57209-1-edumazet@google.com --- include/linux/jiffies.h | 40 ++++++++++++++++++++++++++++++++++++++-- 1 file changed, 38 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fdef2c155c27..d1c3d4941854 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -434,8 +434,44 @@ extern unsigned long preset_lpj; /* * Convert various time units to each other: */ -extern unsigned int jiffies_to_msecs(const unsigned long j); -extern unsigned int jiffies_to_usecs(const unsigned long j); + +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) +/** + * jiffies_to_msecs - Convert jiffies to milliseconds + * @j: jiffies value + * + * This inline version takes care of HZ in {100,250,1000}. + * + * Return: milliseconds value + */ +static inline unsigned int jiffies_to_msecs(const unsigned long j) +{ + return (MSEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_msecs(const unsigned long j); +#endif + +#if !(USEC_PER_SEC % HZ) +/** + * jiffies_to_usecs - Convert jiffies to microseconds + * @j: jiffies value + * + * Return: microseconds value + */ +static inline unsigned int jiffies_to_usecs(const unsigned long j) +{ + /* + * Hz usually doesn't go much further MSEC_PER_SEC. + * jiffies_to_usecs() and usecs_to_jiffies() depend on that. + */ + BUILD_BUG_ON(HZ > USEC_PER_SEC); + + return (USEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_usecs(const unsigned long j); +#endif /** * jiffies_to_nsecs - Convert jiffies to nanoseconds -- cgit v1.2.3 From 7537bae8b6eb635583e0e6260f61d13ddbd52087 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Mon, 9 Feb 2026 15:43:09 -0800 Subject: powercap: intel_rapl: Remove incorrect CPU check in PMU context The RAPL MSR read path incorrectly validates CPU context when called from the PMU subsystem: if (atomic) { if (unlikely(smp_processor_id() != cpu)) return -EIO; rdmsrq(ra->reg.msr, ra->value); } This check fails for package-scoped MSRs like RAPL energy counters, which are readable from any CPU within the package. The perf tool avoids hitting this check by validating against /sys/bus/event_source/devices/power/cpumask before opening events. However, turbostat does not perform this validation and may attempt reads from non-lead CPUs, causing the check to fail and return zero power values. Since package-scoped MSRs are architecturally accessible from any CPU in the package, remove the CPU matching check. Also rename 'atomic' to 'pmu_ctx' to clarify this indicates PMU context where rdmsrq() can be used directly instead of rdmsrl_safe_on_cpu(). Fixes: 748d6ba43afd ("powercap: intel_rapl: Enable MSR-based RAPL PMU support") Signed-off-by: Kuppuswamy Sathyanarayanan Tested-by: Furquim Ulisses Reviewed-by: Srinivas Pandruvada Link: https://patch.msgid.link/20260209234310.1440722-2-sathyanarayanan.kuppuswamy@linux.intel.com Signed-off-by: Rafael J. Wysocki --- include/linux/intel_rapl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index f479ef5b3341..fa1f328d6712 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -152,7 +152,7 @@ struct rapl_if_priv { union rapl_reg reg_unit; union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; int limits[RAPL_DOMAIN_MAX]; - int (*read_raw)(int id, struct reg_action *ra, bool atomic); + int (*read_raw)(int id, struct reg_action *ra, bool pmu_ctx); int (*write_raw)(int id, struct reg_action *ra); void *defaults; void *rpi; -- cgit v1.2.3 From 453daece381e60df20da16c49ccc6a9bc5c6515a Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 11 Feb 2026 12:44:38 -0800 Subject: block: change return type to void Now that all the callers of __blkdev_issue_discard() have been changed to ignore its return value, change its return type from int to void. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 99ef8cd7673c..d463b9b5a0a5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1259,7 +1259,7 @@ extern void blk_io_schedule(void); int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); -int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, +void __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp); -- cgit v1.2.3 From 1aceed565ff172fc0331dd1d5e7e65139b711139 Mon Sep 17 00:00:00 2001 From: Bing Jiao Date: Wed, 14 Jan 2026 20:53:02 +0000 Subject: mm/vmscan: fix demotion targets checks in reclaim/demotion Patch series "mm/vmscan: fix demotion targets checks in reclaim/demotion", v9. This patch series addresses two issues in demote_folio_list(), can_demote(), and next_demotion_node() in reclaim/demotion. 1. demote_folio_list() and can_demote() do not correctly check demotion target against cpuset.mems_effective, which will cause (a) pages to be demoted to not-allowed nodes and (b) pages fail demotion even if the system still has allowed demotion nodes. Patch 1 fixes this bug by updating cpuset_node_allowed() and mem_cgroup_node_allowed() to return effective_mems, allowing directly logic-and operation against demotion targets. 2. next_demotion_node() returns a preferred demotion target, but it does not check the node against allowed nodes. Patch 2 ensures that next_demotion_node() filters against the allowed node mask and selects the closest demotion target to the source node. This patch (of 2): Fix two bugs in demote_folio_list() and can_demote() due to incorrect demotion target checks against cpuset.mems_effective in reclaim/demotion. Commit 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim") introduces the cpuset.mems_effective check and applies it to can_demote(). However: 1. It does not apply this check in demote_folio_list(), which leads to situations where pages are demoted to nodes that are explicitly excluded from the task's cpuset.mems. 2. It checks only the nodes in the immediate next demotion hierarchy and does not check all allowed demotion targets in can_demote(). This can cause pages to never be demoted if the nodes in the next demotion hierarchy are not set in mems_effective. These bugs break resource isolation provided by cpuset.mems. This is visible from userspace because pages can either fail to be demoted entirely or are demoted to nodes that are not allowed in multi-tier memory systems. To address these bugs, update cpuset_node_allowed() and mem_cgroup_node_allowed() to return effective_mems, allowing directly logic-and operation against demotion targets. Also update can_demote() and demote_folio_list() accordingly. Bug 1 reproduction: Assume a system with 4 nodes, where nodes 0-1 are top-tier and nodes 2-3 are far-tier memory. All nodes have equal capacity. Test script: echo 1 > /sys/kernel/mm/numa/demotion_enabled mkdir /sys/fs/cgroup/test echo +cpuset > /sys/fs/cgroup/cgroup.subtree_control echo "0-2" > /sys/fs/cgroup/test/cpuset.mems echo $$ > /sys/fs/cgroup/test/cgroup.procs swapoff -a # Expectation: Should respect node 0-2 limit. # Observation: Node 3 shows significant allocation (MemFree drops) stress-ng --oomable --vm 1 --vm-bytes 150% --mbind 0,1 Bug 2 reproduction: Assume a system with 6 nodes, where nodes 0-2 are top-tier, node 3 is a far-tier node, and nodes 4-5 are the farthest-tier nodes. All nodes have equal capacity. Test script: echo 1 > /sys/kernel/mm/numa/demotion_enabled mkdir /sys/fs/cgroup/test echo +cpuset > /sys/fs/cgroup/cgroup.subtree_control echo "0-2,4-5" > /sys/fs/cgroup/test/cpuset.mems echo $$ > /sys/fs/cgroup/test/cgroup.procs swapoff -a # Expectation: Pages are demoted to Nodes 4-5 # Observation: No pages are demoted before oom. stress-ng --oomable --vm 1 --vm-bytes 150% --mbind 0,1,2 Link: https://lkml.kernel.org/r/20260114205305.2869796-1-bingjiao@google.com Link: https://lkml.kernel.org/r/20260114205305.2869796-2-bingjiao@google.com Fixes: 7d709f49babc ("vmscan,cgroup: apply mems_effective to reclaim") Signed-off-by: Bing Jiao Acked-by: Shakeel Butt Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Gregory Price Cc: Johannes Weiner Cc: Joshua Hahn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Qi Zheng Cc: Roman Gushchin Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Vlastimil Babka Cc: Waiman Long Cc: Wei Xu Cc: Yuanchu Xie Cc: Signed-off-by: Andrew Morton --- include/linux/cpuset.h | 6 +++--- include/linux/memcontrol.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index a98d3330385c..631577384677 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -174,7 +174,7 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } -extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid); +extern void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask); #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -301,9 +301,9 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } -static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid) +static inline void cpuset_nodes_allowed(struct cgroup *cgroup, nodemask_t *mask) { - return true; + nodes_copy(*mask, node_states[N_MEMORY]); } #endif /* !CONFIG_CPUSETS */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ed4764e1a30e..b6c82c8f73e1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1736,7 +1736,7 @@ static inline void count_objcg_events(struct obj_cgroup *objcg, rcu_read_unlock(); } -bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid); +void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask); void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg); @@ -1807,9 +1807,9 @@ static inline ino_t page_cgroup_ino(struct page *page) return 0; } -static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid) +static inline void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, + nodemask_t *mask) { - return true; } static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) -- cgit v1.2.3 From 7ec9ecf217f8e565577bde8a47915a51491ef3a3 Mon Sep 17 00:00:00 2001 From: Bing Jiao Date: Wed, 14 Jan 2026 20:53:03 +0000 Subject: mm/vmscan: select the closest preferred node in demote_folio_list() The preferred demotion node (migration_target_control.nid) should be the one closest to the source node to minimize migration latency. Currently, a discrepancy exists where demote_folio_list() randomly selects an allowed node if the preferred node from next_demotion_node() is not set in mems_effective. To address it, update next_demotion_node() to select a preferred target against allowed nodes; and to return the closest demotion target if all preferred nodes are not in mems_effective via next_demotion_node(). It ensures that the preferred demotion target is consistently the closest available node to the source node. [akpm@linux-foundation.org: fix comment typo, per Shakeel] Link: https://lkml.kernel.org/r/20260114205305.2869796-3-bingjiao@google.com Signed-off-by: Bing Jiao Acked-by: Shakeel Butt Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Gregory Price Cc: Johannes Weiner Cc: Joshua Hahn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Muchun Song Cc: Qi Zheng Cc: Roman Gushchin Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Vlastimil Babka Cc: Waiman Long Cc: Wei Xu Cc: Yuanchu Xie Signed-off-by: Andrew Morton --- include/linux/memory-tiers.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 7a805796fcfd..96987d9d95a8 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -53,11 +53,11 @@ struct memory_dev_type *mt_find_alloc_memory_type(int adist, struct list_head *memory_types); void mt_put_memory_types(struct list_head *memory_types); #ifdef CONFIG_MIGRATION -int next_demotion_node(int node); +int next_demotion_node(int node, const nodemask_t *allowed_mask); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); bool node_is_toptier(int node); #else -static inline int next_demotion_node(int node) +static inline int next_demotion_node(int node, const nodemask_t *allowed_mask) { return NUMA_NO_NODE; } @@ -101,7 +101,7 @@ static inline void clear_node_memory_type(int node, struct memory_dev_type *memt } -static inline int next_demotion_node(int node) +static inline int next_demotion_node(int node, const nodemask_t *allowed_mask) { return NUMA_NO_NODE; } -- cgit v1.2.3 From bed76bec3111c956a9756643d759d5c7a2193b37 Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Wed, 21 Jan 2026 11:49:36 -0500 Subject: mm: relocate the page table ceiling and floor definitions Patch series " Remove XA_ZERO from error recovery of dup_mmap()", v3. It is possible that the dup_mmap() call fails on allocating or setting up a vma after the maple tree of the oldmm is copied. Today, that failure point is marked by inserting an XA_ZERO entry over the failure point so that the exact location does not need to be communicated through to exit_mmap(). However, a race exists in the tear down process because the dup_mmap() drops the mmap lock before exit_mmap() can remove the partially set up vma tree. This means that other tasks may get to the mm tree and find the invalid vma pointer (since it's an XA_ZERO entry), even though the mm is marked as MMF_OOM_SKIP and MMF_UNSTABLE. To remove the race fully, the tree must be cleaned up before dropping the lock. This is accomplished by extracting the vma cleanup in exit_mmap() and changing the required functions to pass through the vma search limit. Any other tree modifications would require extra cycles which should be spent on freeing memory. This does run the risk of increasing the possibility of finding no vmas (which is already possible!) in code that isn't careful. The final four patches are to address the excessive argument lists being passed between the functions. Using the struct unmap_desc also allows some special-case code to be removed in favour of the struct setup differences. This patch (of 11): pgtables.h defines a fallback for ceiling and floor of the page tables within the CONFIG_MMU section. Moving the definitions to outside the CONFIG_MMU allows for using them in generic code. [akpm@linux-foundation.org: remove stray newline, per SeongJae] Link: https://lkml.kernel.org/r/20260121164946.2093480-1-Liam.Howlett@oracle.com Link: https://lkml.kernel.org/r/20260121164946.2093480-2-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Suggested-by: Lorenzo Stoakes Suggested-by: SeongJae Park Cc: Baoquan He Cc: Barry Song Cc: Chris Li Cc: David Hildenbrand Cc: Jann Horn Cc: Kairui Song Cc: Kemeng Shi Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Nhat Pham Cc: Pedro Falcato Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/pgtable.h | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 827dca25c0bc..21b67d937555 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -22,25 +22,6 @@ #error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED #endif -/* - * On almost all architectures and configurations, 0 can be used as the - * upper ceiling to free_pgtables(): on many architectures it has the same - * effect as using TASK_SIZE. However, there is one configuration which - * must impose a more careful limit, to avoid freeing kernel pgtables. - */ -#ifndef USER_PGTABLES_CEILING -#define USER_PGTABLES_CEILING 0UL -#endif - -/* - * This defines the first usable user address. Platforms - * can override its value with custom FIRST_USER_ADDRESS - * defined in their respective . - */ -#ifndef FIRST_USER_ADDRESS -#define FIRST_USER_ADDRESS 0UL -#endif - /* * This defines the generic helper for accessing PMD page * table page. Although platforms can still override this @@ -1629,6 +1610,25 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end); #endif /* CONFIG_MMU */ +/* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + +/* + * This defines the first usable user address. Platforms + * can override its value with custom FIRST_USER_ADDRESS + * defined in their respective . + */ +#ifndef FIRST_USER_ADDRESS +#define FIRST_USER_ADDRESS 0UL +#endif + /* * No-op macros that just return the current protection value. Defined here * because these macros can be used even if CONFIG_MMU is not defined. -- cgit v1.2.3 From 0df5a8d3948da979b8ab811a692b34635e1b146d Mon Sep 17 00:00:00 2001 From: "Liam R. Howlett" Date: Wed, 21 Jan 2026 11:49:44 -0500 Subject: mm/vma: use unmap_desc in exit_mmap() and vms_clear_ptes() Convert vms_clear_ptes() to use unmap_desc to call unmap_vmas() instead of the large argument list. The UNMAP_STATE() cannot be used because the vma iterator in the vms does not point to the correct maple state (mas_detach), and the tree_end will be set incorrectly. Setting up the arguments manually avoids setting the struct up incorrectly and doing extra work to get the correct pagetable range. exit_mmap() also calls unmap_vmas() with many arguments. Using the unmap_all_init() function to set the unmap descriptor for all vmas makes this a bit easier to read. Update to the vma test code is necessary to ensure testing continues to function. No functional changes intended. Link: https://lkml.kernel.org/r/20260121164946.2093480-10-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett Cc: Baoquan He Cc: Barry Song Cc: Chris Li Cc: David Hildenbrand Cc: David Hildenbrand Cc: Jann Horn Cc: Kairui Song Cc: Kemeng Shi Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Nhat Pham Cc: Pedro Falcato Cc: SeongJae Park Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 2c6c6d00ed73..945902d23d47 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2625,10 +2625,6 @@ static inline void zap_vma_pages(struct vm_area_struct *vma) zap_page_range_single(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL); } -void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, - struct vm_area_struct *start_vma, unsigned long start, - unsigned long end, unsigned long tree_end); - struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, -- cgit v1.2.3 From a30de4c6b79a83944d0d6a54cd6ae63014b62ef7 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:10 +0000 Subject: mm/vma: remove __private sparse decoration from vma_flags_t Patch series "mm: add bitmap VMA flag helpers and convert all mmap_prepare to use them", v2. We introduced the bitmap VMA type vma_flags_t in the aptly named commit 9ea35a25d51b ("mm: introduce VMA flags bitmap type") in order to permit future growth in VMA flags and to prevent the asinine requirement that VMA flags be available to 64-bit kernels only if they happened to use a bit number about 32-bits. This is a long-term project as there are very many users of VMA flags within the kernel that need to be updated in order to utilise this new type. In order to further this aim, this series adds a number of helper functions to enable ordinary interactions with VMA flags - that is testing, setting and clearing them. In order to make working with VMA bit numbers less cumbersome this series introduces the mk_vma_flags() helper macro which generates a vma_flags_t from a variadic parameter list, e.g.: vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); It turns out that the compiler optimises this very well to the point that this is just as efficient as using VM_xxx pre-computed bitmap values. This series then introduces the following functions: bool vma_flags_test_mask(vma_flags_t flags, vma_flags_t to_test); bool vma_flags_test_all_mask(vma_flags_t flags, vma_flags_t to_test); void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set); void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear); Providing means of testing any flag, testing all flags, setting, and clearing a specific vma_flags_t mask. For convenience, helper macros are provided - vma_flags_test(), vma_flags_set() and vma_flags_clear(), each of which utilise mk_vma_flags() to make these operations easier, as well as an EMPTY_VMA_FLAGS macro to make initialisation of an empty vma_flags_t value easier, e.g.: vma_flags_t flags = EMPTY_VMA_FLAGS; vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); ... if (vma_flags_test(flags, VMA_READ_BIT)) { ... } ... if (vma_flags_test_all_mask(flags, VMA_REMAP_FLAGS)) { ... } ... vma_flags_clear(&flags, VMA_READ_BIT); Since callers are often dealing with a vm_area_struct (VMA) or vm_area_desc (VMA descriptor as used in .mmap_prepare) object, this series further provides helpers for these - firstly vma_set_flags_mask() and vma_set_flags() for a VMA: vma_flags_t flags = EMPTY_VMA_FLAGS: vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); ... vma_set_flags_mask(&vma, flags); ... vma_set_flags(&vma, VMA_DONTDUMP_BIT); Note that these do NOT ensure appropriate locks are taken and assume the callers takes care of this. For VMA descriptors this series adds vma_desc_[test, set, clear]_flags_mask() and vma_desc_[test, set, clear]_flags() for a VMA descriptor, e.g.: static int foo_mmap_prepare(struct vm_area_desc *desc) { ... vma_desc_set_flags(desc, VMA_SEQ_READ_BIT); vma_desc_clear_flags(desc, VMA_RAND_READ_BIT); ... if (vma_desc_test_flags(desc, VMA_SHARED_BIT) { ... } ... } With these helpers introduced, this series then updates all mmap_prepare users to make use of the vma_flags_t vm_area_desc->vma_flags field rather than the legacy vm_flags_t vm_area_desc->vm_flags field. In order to do so, several other related functions need to be updated, with separate patches for larger changes in hugetlbfs, secretmem and shmem before finally removing vm_area_desc->vm_flags altogether. This lays the foundations for future elimination of vm_flags_t and associated defines and functionality altogether in the long run, and elimination of the use of vm_flags_t in f_op->mmap() hooks in the near term as mmap_prepare replaces these. There is a useful synergy between the VMA flags and mmap_prepare work here as with this change in place, converting f_op->mmap() to f_op->mmap_prepare naturally also converts use of vm_flags_t to vma_flags_t in all drivers which declare mmap handlers. This accounts for the majority of the users of the legacy vm_flags_*() helpers and thus a large number of drivers which need to interact with VMA flags in general. This series also updates the userland VMA tests to account for the change, and adds unit tests for these helper functions to assert that they behave as expected. In order to faciliate this change in a sensible way, the series also separates out the VMA unit tests into - code that is duplicated from the kernel that should be kept in sync, code that is customised for test purposes and code that is stubbed out. We also separate out the VMA userland tests into separate files to make it easier to manage and to provide a sensible baseline for adding the userland tests for these helpers. This patch (of 13): We need to pass around these values and access them in a way that sparse does not allow, as __private implies noderef, i.e. disallowing dereference of the value, which manifests as sparse warnings even when passed around benignly. Link: https://lkml.kernel.org/r/cover.1769097829.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/64fa89f416f22a60ae74cfff8fd565e7677be192.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Pedro Falcato Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Signed-off-by: Andrew Morton --- include/linux/mm.h | 4 ++-- include/linux/mm_types.h | 14 ++++++++------ 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 945902d23d47..c27d79f6b8c0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -943,7 +943,7 @@ static inline void vm_flags_reset_once(struct vm_area_struct *vma, * system word. */ if (NUM_VMA_FLAG_BITS > BITS_PER_LONG) { - unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags); + unsigned long *bitmap = vma->flags.__vma_flags; bitmap_zero(&bitmap[1], NUM_VMA_FLAG_BITS - BITS_PER_LONG); } @@ -1006,7 +1006,7 @@ static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma, static inline void vma_flag_set_atomic(struct vm_area_struct *vma, vma_flag_t bit) { - unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags); + unsigned long *bitmap = vma->flags.__vma_flags; vma_assert_stabilised(vma); if (__vma_flag_atomic_valid(vma, bit)) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8731606d8d36..ed0e128361f7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -866,7 +866,7 @@ struct mmap_action { #define NUM_VMA_FLAG_BITS BITS_PER_LONG typedef struct { DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS); -} __private vma_flags_t; +} vma_flags_t; /* * Describes a VMA that is about to be mmap()'ed. Drivers may choose to @@ -1059,7 +1059,7 @@ struct vm_area_struct { /* Clears all bits in the VMA flags bitmap, non-atomically. */ static inline void vma_flags_clear_all(vma_flags_t *flags) { - bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS); + bitmap_zero(flags->__vma_flags, NUM_VMA_FLAG_BITS); } /* @@ -1070,7 +1070,9 @@ static inline void vma_flags_clear_all(vma_flags_t *flags) */ static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value) { - *ACCESS_PRIVATE(flags, __vma_flags) = value; + unsigned long *bitmap = flags->__vma_flags; + + bitmap[0] = value; } /* @@ -1081,7 +1083,7 @@ static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long va */ static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value) { - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + unsigned long *bitmap = flags->__vma_flags; WRITE_ONCE(*bitmap, value); } @@ -1089,7 +1091,7 @@ static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned lo /* Update the first system word of VMA flags setting bits, non-atomically. */ static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value) { - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + unsigned long *bitmap = flags->__vma_flags; *bitmap |= value; } @@ -1097,7 +1099,7 @@ static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value) /* Update the first system word of VMA flags clearing bits, non-atomically. */ static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value) { - unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags); + unsigned long *bitmap = flags->__vma_flags; *bitmap &= ~value; } -- cgit v1.2.3 From e388d31257eddc1077a02ed786513d606c9e3266 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:11 +0000 Subject: mm: rename vma_flag_test/set_atomic() to vma_test/set_atomic_flag() In order to stay consistent between functions which manipulate a vm_flags_t argument of the form of vma_flags_...() and those which manipulate a VMA (in this case the flags field of a VMA), rename vma_flag_[test/set]_atomic() to vma_[test/set]_atomic_flag(). This lays the groundwork for adding VMA flag manipulation functions in a subsequent commit. Link: https://lkml.kernel.org/r/033dcf12e819dee5064582bced9b12ea346d1607.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Pedro Falcato Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Cc: Pedro Falcato Signed-off-by: Andrew Morton --- include/linux/mm.h | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c27d79f6b8c0..67b80f0ea225 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -987,8 +987,7 @@ static inline void vm_flags_mod(struct vm_area_struct *vma, __vm_flags_mod(vma, set, clear); } -static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma, - vma_flag_t bit) +static inline bool __vma_atomic_valid_flag(struct vm_area_struct *vma, vma_flag_t bit) { const vm_flags_t mask = BIT((__force int)bit); @@ -1003,13 +1002,12 @@ static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma, * Set VMA flag atomically. Requires only VMA/mmap read lock. Only specific * valid flags are allowed to do this. */ -static inline void vma_flag_set_atomic(struct vm_area_struct *vma, - vma_flag_t bit) +static inline void vma_set_atomic_flag(struct vm_area_struct *vma, vma_flag_t bit) { unsigned long *bitmap = vma->flags.__vma_flags; vma_assert_stabilised(vma); - if (__vma_flag_atomic_valid(vma, bit)) + if (__vma_atomic_valid_flag(vma, bit)) set_bit((__force int)bit, bitmap); } @@ -1020,10 +1018,9 @@ static inline void vma_flag_set_atomic(struct vm_area_struct *vma, * This is necessarily racey, so callers must ensure that serialisation is * achieved through some other means, or that races are permissible. */ -static inline bool vma_flag_test_atomic(struct vm_area_struct *vma, - vma_flag_t bit) +static inline bool vma_test_atomic_flag(struct vm_area_struct *vma, vma_flag_t bit) { - if (__vma_flag_atomic_valid(vma, bit)) + if (__vma_atomic_valid_flag(vma, bit)) return test_bit((__force int)bit, &vma->vm_flags); return false; -- cgit v1.2.3 From 1c628004e0de0383a5a56facdb0bf28a54441b5f Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:12 +0000 Subject: mm: add mk_vma_flags() bitmap flag macro helper This patch introduces the mk_vma_flags() macro helper to allow easy manipulation of VMA flags utilising the new bitmap representation implemented of VMA flags defined by the vma_flags_t type. It is a variadic macro which provides a bitwise-or'd representation of all of each individual VMA flag specified. Note that, while we maintain VM_xxx flags for backwards compatibility until the conversion is complete, we define VMA flags of type vma_flag_t using VMA_xxx_BIT to avoid confusing the two. This helper macro therefore can be used thusly: vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT); Testing has demonstrated that the compiler optimises this code such that it generates the same assembly utilising this macro as it does if the flags were specified manually, for instance: vma_flags_t get_flags(void) { return mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); } Generates the same code as: vma_flags_t get_flags(void) { vma_flags_t flags; vma_flags_clear_all(&flags); vma_flag_set(&flags, VMA_READ_BIT); vma_flag_set(&flags, VMA_WRITE_BIT); vma_flag_set(&flags, VMA_EXEC_BIT); return flags; } And: vma_flags_t get_flags(void) { vma_flags_t flags; unsigned long *bitmap = ACCESS_PRIVATE(&flags, __vma_flags); *bitmap = 1UL << (__force int)VMA_READ_BIT; *bitmap |= 1UL << (__force int)VMA_WRITE_BIT; *bitmap |= 1UL << (__force int)VMA_EXEC_BIT; return flags; } That is: get_flags: movl $7, %eax ret Link: https://lkml.kernel.org/r/fde00df6ff7fb8c4b42cc0defa5a4924c7a1943a.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Suggested-by: Jason Gunthorpe Reviewed-by: Pedro Falcato Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Signed-off-by: Andrew Morton --- include/linux/mm.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 67b80f0ea225..d3d10c769d6f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2,6 +2,7 @@ #ifndef _LINUX_MM_H #define _LINUX_MM_H +#include #include #include #include @@ -1026,6 +1027,38 @@ static inline bool vma_test_atomic_flag(struct vm_area_struct *vma, vma_flag_t b return false; } +/* Set an individual VMA flag in flags, non-atomically. */ +static inline void vma_flag_set(vma_flags_t *flags, vma_flag_t bit) +{ + unsigned long *bitmap = flags->__vma_flags; + + __set_bit((__force int)bit, bitmap); +} + +static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits) +{ + vma_flags_t flags; + int i; + + vma_flags_clear_all(&flags); + for (i = 0; i < count; i++) + vma_flag_set(&flags, bits[i]); + return flags; +} + +/* + * Helper macro which bitwise-or combines the specified input flags into a + * vma_flags_t bitmap value. E.g.: + * + * vma_flags_t flags = mk_vma_flags(VMA_IO_BIT, VMA_PFNMAP_BIT, + * VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT); + * + * The compiler cleverly optimises away all of the work and this ends up being + * equivalent to aggregating the values manually. + */ +#define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \ + (const vma_flag_t []){__VA_ARGS__}) + static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; -- cgit v1.2.3 From bae0ba7c7c0a022287d8b093da63ebcb794d77ea Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:14 +0000 Subject: mm: add basic VMA flag operation helper functions Now we have the mk_vma_flags() macro helper which permits easy specification of any number of VMA flags, add helper functions which operate with vma_flags_t parameters. This patch provides vma_flags_test[_mask](), vma_flags_set[_mask]() and vma_flags_clear[_mask]() respectively testing, setting and clearing flags with the _mask variants accepting vma_flag_t parameters, and the non-mask variants implemented as macros which accept a list of flags. This allows us to trivially test/set/clear aggregate VMA flag values as necessary, for instance: if (vma_flags_test(&flags, VMA_READ_BIT, VMA_WRITE_BIT)) goto readwrite; vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT); vma_flags_clear(&flags, VMA_READ_BIT, VMA_WRITE_BIT); We also add a function for testing that ALL flags are set for convenience, e.g.: if (vma_flags_test_all(&flags, VMA_READ_BIT, VMA_MAYREAD_BIT)) { /* Both READ and MAYREAD flags set */ ... } The compiler generates optimal assembly for each such that they behave as if the caller were setting the bitmap flags manually. This is important for e.g. drivers which manipulate flag values rather than a VMA's specific flag values. We also add helpers for testing, setting and clearing flags for VMA's and VMA descriptors to reduce boilerplate. Also add the EMPTY_VMA_FLAGS define to aid initialisation of empty flags. Finally, update the userland VMA tests to add the helpers there so they can be utilised as part of userland testing. Link: https://lkml.kernel.org/r/885d4897d67a6a57c0b07fa182a7055ad752df11.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Pedro Falcato Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Signed-off-by: Andrew Morton --- include/linux/mm.h | 165 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 4 +- 2 files changed, 168 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index d3d10c769d6f..aa99b28e7a8a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1059,6 +1059,171 @@ static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits) #define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \ (const vma_flag_t []){__VA_ARGS__}) +/* Test each of to_test flags in flags, non-atomically. */ +static __always_inline bool vma_flags_test_mask(const vma_flags_t *flags, + vma_flags_t to_test) +{ + const unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_test = to_test.__vma_flags; + + return bitmap_intersects(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); +} + +/* + * Test whether any specified VMA flag is set, e.g.: + * + * if (vma_flags_test(flags, VMA_READ_BIT, VMA_MAYREAD_BIT)) { ... } + */ +#define vma_flags_test(flags, ...) \ + vma_flags_test_mask(flags, mk_vma_flags(__VA_ARGS__)) + +/* Test that ALL of the to_test flags are set, non-atomically. */ +static __always_inline bool vma_flags_test_all_mask(const vma_flags_t *flags, + vma_flags_t to_test) +{ + const unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_test = to_test.__vma_flags; + + return bitmap_subset(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS); +} + +/* + * Test whether ALL specified VMA flags are set, e.g.: + * + * if (vma_flags_test_all(flags, VMA_READ_BIT, VMA_MAYREAD_BIT)) { ... } + */ +#define vma_flags_test_all(flags, ...) \ + vma_flags_test_all_mask(flags, mk_vma_flags(__VA_ARGS__)) + +/* Set each of the to_set flags in flags, non-atomically. */ +static __always_inline void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set) +{ + unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_set = to_set.__vma_flags; + + bitmap_or(bitmap, bitmap, bitmap_to_set, NUM_VMA_FLAG_BITS); +} + +/* + * Set all specified VMA flags, e.g.: + * + * vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); + */ +#define vma_flags_set(flags, ...) \ + vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__)) + +/* Clear all of the to-clear flags in flags, non-atomically. */ +static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear) +{ + unsigned long *bitmap = flags->__vma_flags; + const unsigned long *bitmap_to_clear = to_clear.__vma_flags; + + bitmap_andnot(bitmap, bitmap, bitmap_to_clear, NUM_VMA_FLAG_BITS); +} + +/* + * Clear all specified individual flags, e.g.: + * + * vma_flags_clear(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT); + */ +#define vma_flags_clear(flags, ...) \ + vma_flags_clear_mask(flags, mk_vma_flags(__VA_ARGS__)) + +/* + * Helper to test that ALL specified flags are set in a VMA. + * + * Note: appropriate locks must be held, this function does not acquire them for + * you. + */ +static inline bool vma_test_all_flags_mask(const struct vm_area_struct *vma, + vma_flags_t flags) +{ + return vma_flags_test_all_mask(&vma->flags, flags); +} + +/* + * Helper macro for checking that ALL specified flags are set in a VMA, e.g.: + * + * if (vma_test_all_flags(vma, VMA_READ_BIT, VMA_MAYREAD_BIT) { ... } + */ +#define vma_test_all_flags(vma, ...) \ + vma_test_all_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) + +/* + * Helper to set all VMA flags in a VMA. + * + * Note: appropriate locks must be held, this function does not acquire them for + * you. + */ +static inline void vma_set_flags_mask(struct vm_area_struct *vma, + vma_flags_t flags) +{ + vma_flags_set_mask(&vma->flags, flags); +} + +/* + * Helper macro for specifying VMA flags in a VMA, e.g.: + * + * vma_set_flags(vma, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, + * VMA_DONTDUMP_BIT); + * + * Note: appropriate locks must be held, this function does not acquire them for + * you. + */ +#define vma_set_flags(vma, ...) \ + vma_set_flags_mask(vma, mk_vma_flags(__VA_ARGS__)) + +/* Helper to test all VMA flags in a VMA descriptor. */ +static inline bool vma_desc_test_flags_mask(const struct vm_area_desc *desc, + vma_flags_t flags) +{ + return vma_flags_test_mask(&desc->vma_flags, flags); +} + +/* + * Helper macro for testing VMA flags for an input pointer to a struct + * vm_area_desc object describing a proposed VMA, e.g.: + * + * if (vma_desc_test_flags(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, + * VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT)) { ... } + */ +#define vma_desc_test_flags(desc, ...) \ + vma_desc_test_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + +/* Helper to set all VMA flags in a VMA descriptor. */ +static inline void vma_desc_set_flags_mask(struct vm_area_desc *desc, + vma_flags_t flags) +{ + vma_flags_set_mask(&desc->vma_flags, flags); +} + +/* + * Helper macro for specifying VMA flags for an input pointer to a struct + * vm_area_desc object describing a proposed VMA, e.g.: + * + * vma_desc_set_flags(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, + * VMA_DONTDUMP_BIT); + */ +#define vma_desc_set_flags(desc, ...) \ + vma_desc_set_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + +/* Helper to clear all VMA flags in a VMA descriptor. */ +static inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc, + vma_flags_t flags) +{ + vma_flags_clear_mask(&desc->vma_flags, flags); +} + +/* + * Helper macro for clearing VMA flags for an input pointer to a struct + * vm_area_desc object describing a proposed VMA, e.g.: + * + * vma_desc_clear_flags(desc, VMA_IO_BIT, VMA_PFNMAP_BIT, VMA_DONTEXPAND_BIT, + * VMA_DONTDUMP_BIT); + */ +#define vma_desc_clear_flags(desc, ...) \ + vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__)) + static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ed0e128361f7..9b4311cfd5e8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -844,7 +844,7 @@ struct mmap_action { /* * If specified, this hook is invoked when an error occurred when - * attempting the selection action. + * attempting the selected action. * * The hook can return an error code in order to filter the error, but * it is not valid to clear the error here. @@ -868,6 +868,8 @@ typedef struct { DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS); } vma_flags_t; +#define EMPTY_VMA_FLAGS ((vma_flags_t){ }) + /* * Describes a VMA that is about to be mmap()'ed. Drivers may choose to * manipulate mutable fields which will cause those fields to be updated in the -- cgit v1.2.3 From 097e8db5e22b03d6791abc243183f597d0f76a7b Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:15 +0000 Subject: mm: update hugetlbfs to use VMA flags on mmap_prepare In order to update all mmap_prepare users to utilising the new VMA flags type vma_flags_t and associated helper functions, we start by updating hugetlbfs which has a lot of additional logic that requires updating to make this change. This is laying the groundwork for eliminating the vm_flags_t from struct vm_area_desc and using vma_flags_t only, which further lays the ground for removing the deprecated vm_flags_t type altogether. No functional changes intended. Link: https://lkml.kernel.org/r/9226bec80c9aa3447cc2b83354f733841dba8a50.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Cc: Pedro Falcato Signed-off-by: Andrew Morton --- include/linux/hugetlb.h | 6 +++--- include/linux/hugetlb_inline.h | 10 ++++++++++ 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 94a03591990c..4e72bf66077e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -150,7 +150,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ long hugetlb_reserve_pages(struct inode *inode, long from, long to, - struct vm_area_desc *desc, vm_flags_t vm_flags); + struct vm_area_desc *desc, vma_flags_t vma_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list); @@ -529,7 +529,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) } extern const struct vm_operations_struct hugetlb_vm_ops; -struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, +struct file *hugetlb_file_setup(const char *name, size_t size, vma_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) @@ -545,7 +545,7 @@ static inline struct hstate *hstate_inode(struct inode *i) #define is_file_hugepages(file) false static inline struct file * -hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, +hugetlb_file_setup(const char *name, size_t size, vma_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h index a27aa0162918..593f5d4e108b 100644 --- a/include/linux/hugetlb_inline.h +++ b/include/linux/hugetlb_inline.h @@ -11,6 +11,11 @@ static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) return !!(vm_flags & VM_HUGETLB); } +static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) +{ + return vma_flags_test(flags, VMA_HUGETLB_BIT); +} + #else static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) @@ -18,6 +23,11 @@ static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags) return false; } +static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags) +{ + return false; +} + #endif static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma) -- cgit v1.2.3 From 590d356aa433074ece2b0d02faa5f959b26d54d6 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:17 +0000 Subject: mm: update shmem_[kernel]_file_*() functions to use vma_flags_t In order to be able to use only vma_flags_t in vm_area_desc we must adjust shmem file setup functions to operate in terms of vma_flags_t rather than vm_flags_t. This patch makes this change and updates all callers to use the new functions. No functional changes intended. [akpm@linux-foundation.org: comment fixes, per Baolin] Link: https://lkml.kernel.org/r/736febd280eb484d79cef5cf55b8a6f79ad832d2.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Baolin Wang Reviewed-by: Jarkko Sakkinen Reviewed-by: Liam R. Howlett Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: "Darrick J. Wong" Cc: Damien Le Moal Cc: Yury Norov Cc: Chris Mason Cc: Pedro Falcato Signed-off-by: Andrew Morton --- include/linux/shmem_fs.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index e2069b3179c4..a8273b32e041 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -102,12 +102,10 @@ static inline struct shmem_inode_info *SHMEM_I(struct inode *inode) extern const struct fs_parameter_spec shmem_fs_parameters[]; extern void shmem_init(void); extern int shmem_init_fs_context(struct fs_context *fc); -extern struct file *shmem_file_setup(const char *name, - loff_t size, unsigned long flags); -extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, - unsigned long flags); +struct file *shmem_file_setup(const char *name, loff_t size, vma_flags_t flags); +struct file *shmem_kernel_file_setup(const char *name, loff_t size, vma_flags_t vma_flags); extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, - const char *name, loff_t size, unsigned long flags); + const char *name, loff_t size, vma_flags_t flags); int shmem_zero_setup(struct vm_area_struct *vma); int shmem_zero_setup_desc(struct vm_area_desc *desc); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, -- cgit v1.2.3 From 5bd2c0650a9030007af5c2cf2a01dccdc67a6991 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:18 +0000 Subject: mm: update all remaining mmap_prepare users to use vma_flags_t We will be shortly removing the vm_flags_t field from vm_area_desc so we need to update all mmap_prepare users to only use the dessc->vma_flags field. This patch achieves that and makes all ancillary changes required to make this possible. This lays the groundwork for future work to eliminate the use of vm_flags_t in vm_area_desc altogether and more broadly throughout the kernel. While we're here, we take the opportunity to replace VM_REMAP_FLAGS with VMA_REMAP_FLAGS, the vma_flags_t equivalent. No functional changes intended. Link: https://lkml.kernel.org/r/fb1f55323799f09fe6a36865b31550c9ec67c225.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Acked-by: Damien Le Moal [zonefs] Acked-by: "Darrick J. Wong" Acked-by: Pedro Falcato Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Liam Howlett Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Signed-off-by: Andrew Morton --- include/linux/dax.h | 8 ++++---- include/linux/mm.h | 24 +++++++++++++++++++----- 2 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 9d624f4d9df6..bf103f317cac 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -65,11 +65,11 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, /* * Check if given mapping is supported by the file / underlying device. */ -static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, +static inline bool daxdev_mapping_supported(const struct vm_area_desc *desc, const struct inode *inode, struct dax_device *dax_dev) { - if (!(vm_flags & VM_SYNC)) + if (!vma_desc_test_flags(desc, VMA_SYNC_BIT)) return true; if (!IS_DAX(inode)) return false; @@ -111,11 +111,11 @@ static inline void set_dax_nomc(struct dax_device *dax_dev) static inline void set_dax_synchronous(struct dax_device *dax_dev) { } -static inline bool daxdev_mapping_supported(vm_flags_t vm_flags, +static inline bool daxdev_mapping_supported(const struct vm_area_desc *desc, const struct inode *inode, struct dax_device *dax_dev) { - return !(vm_flags & VM_SYNC); + return !vma_desc_test_flags(desc, VMA_SYNC_BIT); } static inline size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) diff --git a/include/linux/mm.h b/include/linux/mm.h index aa99b28e7a8a..05d950805701 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -550,17 +550,18 @@ enum { /* * Physically remapped pages are special. Tell the * rest of the world about it: - * VM_IO tells people not to look at these pages + * IO tells people not to look at these pages * (accesses can have side effects). - * VM_PFNMAP tells the core MM that the base pages are just + * PFNMAP tells the core MM that the base pages are just * raw PFN mappings, and do not have a "struct page" associated * with them. - * VM_DONTEXPAND + * DONTEXPAND * Disable vma merging and expanding with mremap(). - * VM_DONTDUMP + * DONTDUMP * Omit vma from core dump, even when VM_IO turned off. */ -#define VM_REMAP_FLAGS (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP) +#define VMA_REMAP_FLAGS mk_vma_flags(VMA_IO_BIT, VMA_PFNMAP_BIT, \ + VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT) /* This mask prevents VMA from being scanned with khugepaged */ #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB) @@ -1925,6 +1926,14 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +static inline bool vma_desc_is_cow_mapping(struct vm_area_desc *desc) +{ + const vma_flags_t *flags = &desc->vma_flags; + + return vma_flags_test(flags, VMA_MAYWRITE_BIT) && + !vma_flags_test(flags, VMA_SHARED_BIT); +} + #ifndef CONFIG_MMU static inline bool is_nommu_shared_mapping(vm_flags_t flags) { @@ -1938,6 +1947,11 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags) */ return flags & (VM_MAYSHARE | VM_MAYOVERLAY); } + +static inline bool is_nommu_shared_vma_flags(const vma_flags_t *flags) +{ + return vma_flags_test(flags, VMA_MAYSHARE_BIT, VMA_MAYOVERLAY_BIT); +} #endif #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) -- cgit v1.2.3 From 53f1d936445131cb5da2212c2b60884a25cb0330 Mon Sep 17 00:00:00 2001 From: Lorenzo Stoakes Date: Thu, 22 Jan 2026 16:06:19 +0000 Subject: mm: make vm_area_desc utilise vma_flags_t only Now we have eliminated all uses of vm_area_desc->vm_flags, eliminate this field, and have mmap_prepare users utilise the vma_flags_t vm_area_desc->vma_flags field only. As part of this change we alter is_shared_maywrite() to accept a vma_flags_t parameter, and introduce is_shared_maywrite_vm_flags() for use with legacy vm_flags_t flags. We also update struct mmap_state to add a union between vma_flags and vm_flags temporarily until the mmap logic is also converted to using vma_flags_t. Also update the VMA userland tests to reflect this change. Link: https://lkml.kernel.org/r/fd2a2938b246b4505321954062b1caba7acfc77a.1769097829.git.lorenzo.stoakes@oracle.com Signed-off-by: Lorenzo Stoakes Reviewed-by: Pedro Falcato Reviewed-by: Liam R. Howlett Cc: Baolin Wang Cc: Barry Song Cc: David Hildenbrand Cc: Dev Jain Cc: Jason Gunthorpe Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Zi Yan Cc: Damien Le Moal Cc: "Darrick J. Wong" Cc: Jarkko Sakkinen Cc: Yury Norov Cc: Chris Mason Signed-off-by: Andrew Morton --- include/linux/mm.h | 9 +++++++-- include/linux/mm_types.h | 5 +---- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 05d950805701..f8a8fd47399c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1290,15 +1290,20 @@ static inline bool vma_is_accessible(const struct vm_area_struct *vma) return vma->vm_flags & VM_ACCESS_FLAGS; } -static inline bool is_shared_maywrite(vm_flags_t vm_flags) +static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags) { return (vm_flags & (VM_SHARED | VM_MAYWRITE)) == (VM_SHARED | VM_MAYWRITE); } +static inline bool is_shared_maywrite(const vma_flags_t *flags) +{ + return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT); +} + static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma) { - return is_shared_maywrite(vma->vm_flags); + return is_shared_maywrite(&vma->flags); } static inline diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9b4311cfd5e8..3cc8ae722886 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -887,10 +887,7 @@ struct vm_area_desc { /* Mutable fields. Populated with initial state. */ pgoff_t pgoff; struct file *vm_file; - union { - vm_flags_t vm_flags; - vma_flags_t vma_flags; - }; + vma_flags_t vma_flags; pgprot_t page_prot; /* Write-only fields. */ -- cgit v1.2.3 From 52e054f7184097bea009963e033cdd54af7bf8a2 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 9 Feb 2026 22:07:24 +0800 Subject: mm: rmap: support batched checks of the references for large folios Patch series "support batch checking of references and unmapping for large folios", v6. Currently, folio_referenced_one() always checks the young flag for each PTE sequentially, which is inefficient for large folios. This inefficiency is especially noticeable when reclaiming clean file-backed large folios, where folio_referenced() is observed as a significant performance hotspot. Moreover, on Arm architecture, which supports contiguous PTEs, there is already an optimization to clear the young flags for PTEs within a contiguous range. However, this is not sufficient. We can extend this to perform batched operations for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE). Similar to folio_referenced_one(), we can also apply batched unmapping for large file folios to optimize the performance of file folio reclamation. By supporting batched checking of the young flags, flushing TLB entries, and unmapping, I can observed a significant performance improvements in my performance tests for file folios reclamation. Please check the performance data in the commit message of each patch. This patch (of 5): Currently, folio_referenced_one() always checks the young flag for each PTE sequentially, which is inefficient for large folios. This inefficiency is especially noticeable when reclaiming clean file-backed large folios, where folio_referenced() is observed as a significant performance hotspot. Moreover, on Arm64 architecture, which supports contiguous PTEs, there is already an optimization to clear the young flags for PTEs within a contiguous range. However, this is not sufficient. We can extend this to perform batched operations for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE). Introduce a new API: clear_flush_young_ptes() to facilitate batched checking of the young flags and flushing TLB entries, thereby improving performance during large folio reclamation. And it will be overridden by the architecture that implements a more efficient batch operation in the following patches. While we are at it, rename ptep_clear_flush_young_notify() to clear_flush_young_ptes_notify() to indicate that this is a batch operation. Link: https://lkml.kernel.org/r/cover.1770645603.git.baolin.wang@linux.alibaba.com Link: https://lkml.kernel.org/r/12132694536834262062d1fb304f8f8a064b6750.1770645603.git.baolin.wang@linux.alibaba.com Signed-off-by: Baolin Wang Reviewed-by: Harry Yoo Reviewed-by: Ryan Roberts Acked-by: David Hildenbrand (Arm) Cc: Catalin Marinas Cc: Jann Horn Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Rik van Riel Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Will Deacon Cc: Barry Song Signed-off-by: Andrew Morton --- include/linux/mmu_notifier.h | 9 +++++---- include/linux/pgtable.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d1094c2d5fb6..07a2bbaf86e9 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -515,16 +515,17 @@ static inline void mmu_notifier_range_init_owner( range->owner = owner; } -#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ +#define clear_flush_young_ptes_notify(__vma, __address, __ptep, __nr) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ - __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ + unsigned int ___nr = __nr; \ + __young = clear_flush_young_ptes(___vma, ___address, __ptep, ___nr); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ - PAGE_SIZE); \ + ___nr * PAGE_SIZE); \ __young; \ }) @@ -650,7 +651,7 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) #define mmu_notifier_range_update_to_read_only(r) false -#define ptep_clear_flush_young_notify ptep_clear_flush_young +#define clear_flush_young_ptes_notify clear_flush_young_ptes #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 21b67d937555..a50df42a893f 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1068,6 +1068,41 @@ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, } #endif +#ifndef clear_flush_young_ptes +/** + * clear_flush_young_ptes - Mark PTEs that map consecutive pages of the same + * folio as old and flush the TLB. + * @vma: The virtual memory area the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear access bit. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_clear_flush_young(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline int clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr) +{ + int young = 0; + + for (;;) { + young |= ptep_clear_flush_young(vma, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } + + return young; +} +#endif + /* * On some architectures hardware does not set page access bit when accessing * memory page, it is responsibility of software setting this bit. It brings -- cgit v1.2.3 From 68eeb0871e986ae5462439dae881e3a27bcef85f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 21 Dec 2025 17:57:40 +0100 Subject: fbdev: Use device_create_with_groups() to fix sysfs groups registration race The fbdev sysfs attributes are registered after sending the uevent for the device creation, leaving a race window where e.g. udev rules may not be able to access the sysfs attributes because the registration is not done yet. Fix this by switching to device_create_with_groups(). This also results in a nice cleanup. After switching to device_create_with_groups() all that is left of fb_init_device() is setting the drvdata and that can be passed to device_create[_with_groups]() too. After which fb_init_device() can be completely removed. Dropping fb_init_device() + fb_cleanup_device() in turn allows removing fb_info.class_flag as they were the only user of this field. Fixes: 5fc830d6aca1 ("fbdev: Register sysfs groups through device_add_group") Cc: stable@vger.kernel.org Cc: Shixiong Ou Signed-off-by: Hans de Goede Signed-off-by: Helge Deller --- include/linux/fb.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 65fb70382675..aaa50b81f1d2 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -493,7 +493,6 @@ struct fb_info { #if defined(CONFIG_FB_DEVICE) struct device *dev; /* This is this fb device */ #endif - int class_flag; /* private sysfs flags */ #ifdef CONFIG_FB_TILEBLITTING struct fb_tile_ops *tileops; /* Tile Blitting */ #endif -- cgit v1.2.3 From 39b65316fe9d6d3f730632408ace28d49c5845a4 Mon Sep 17 00:00:00 2001 From: Chintan Patel Date: Tue, 6 Jan 2026 20:42:54 -0800 Subject: fb: Add dev_of_fbinfo() helper for optional sysfs support Add dev_of_fbinfo() to return the framebuffer struct device when CONFIG_FB_DEVICE is enabled, or NULL otherwise. This allows fbdev drivers to use sysfs interfaces via runtime checks instead of CONFIG_FB_DEVICE ifdefs, keeping the code clean while remaining fully buildable. Suggested-by: Helge Deller Reviewed-by: Helge Deller Reviewed-by: Andy Shevchenko Signed-off-by: Chintan Patel Reviewed-by: Thomas Zimmermann Signed-off-by: Helge Deller --- include/linux/fb.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index aaa50b81f1d2..e70ee58d689e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -623,6 +623,15 @@ static inline void unlock_fb_info(struct fb_info *info) mutex_unlock(&info->lock); } +static inline struct device *dev_of_fbinfo(const struct fb_info *info) +{ +#ifdef CONFIG_FB_DEVICE + return info->dev; +#else + return NULL; +#endif +} + static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 s_pitch, u32 height) { -- cgit v1.2.3 From 3092718e1280fcbdfc4f4b4a3258be8992a0c244 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 8 Jan 2026 20:04:54 +0100 Subject: video/logo: remove logo_mac_clut224 The logo_mac_clut224 depends on the runtime value MACH_IS_MAC being true to be displayed. This makes that logo a one-of-a-kind, as it is the only one whose selection can not be decided at compile time. This dynamic logo selection logic conflicts with our upcoming plans to simplify the logo selection code. Considering that the logo_mac_clut224 is only used by the Macintosh 68k, a machine whose sales ended some thirty years ago and which thus represents a very small user base, it is preferable to resolve the conflict in favour of code simplicity. Remove the logo_mac_clut224 so that the logo selection can be statically determined at compile time. The users who wish to continue using that logo can still download it from [1] and add: CONFIG_LOGO_LINUX_CLUT224=y CONFIG_LOGO_LINUX_CLUT224_FILE="/path/to/logo_mac_clut224.ppm" to their configuration file to restore it. [1] logo_mac_clut224.ppm file Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/plain/drivers/video/logo/logo_mac_clut224.ppm?h=v6.18 Signed-off-by: Vincent Mailhol Signed-off-by: Helge Deller --- include/linux/linux_logo.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index e37699b7e839..1f04adc853a9 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -34,7 +34,6 @@ extern const struct linux_logo logo_linux_mono; extern const struct linux_logo logo_linux_vga16; extern const struct linux_logo logo_linux_clut224; extern const struct linux_logo logo_dec_clut224; -extern const struct linux_logo logo_mac_clut224; extern const struct linux_logo logo_parisc_clut224; extern const struct linux_logo logo_sgi_clut224; extern const struct linux_logo logo_sun_clut224; -- cgit v1.2.3 From ac6d088b3b20f9efb883e8302288276db3bdc2b8 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 8 Jan 2026 20:04:55 +0100 Subject: video/logo: move logo selection logic to Kconfig Now that the path to the logo file can be directly entered in Kbuild, there is no more need to handle all the logo file selection in the Makefile and the C files. The only exception is the logo_spe_clut224 which is only used by the Cell processor (found for example in the Playstation 3) [1]. This extra logo uses its own different image which shows up on a separate line just below the normal logo. Because the extra logo uses a different image, it can not be factorized under the custom logo logic. Move all the logo file selection logic to Kbuild (except from the logo_spe_clut224.ppm), this done, clean-up the C code to only leave one entry for each logo type (monochrome, 16-colors and 224-colors). [1] Cell SPE logos Link: https://lore.kernel.org/all/20070710122702.765654000@pademelon.sonytel.be/ Signed-off-by: Vincent Mailhol Signed-off-by: Helge Deller --- include/linux/linux_logo.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index 1f04adc853a9..1e727a2cb4c1 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -33,13 +33,6 @@ struct linux_logo { extern const struct linux_logo logo_linux_mono; extern const struct linux_logo logo_linux_vga16; extern const struct linux_logo logo_linux_clut224; -extern const struct linux_logo logo_dec_clut224; -extern const struct linux_logo logo_parisc_clut224; -extern const struct linux_logo logo_sgi_clut224; -extern const struct linux_logo logo_sun_clut224; -extern const struct linux_logo logo_superh_mono; -extern const struct linux_logo logo_superh_vga16; -extern const struct linux_logo logo_superh_clut224; extern const struct linux_logo logo_spe_clut224; extern const struct linux_logo *fb_find_logo(int depth); -- cgit v1.2.3 From 8e9bf8b9e8c0a3e1ef16dd48260a113f65ed01d2 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 26 Jan 2026 19:08:36 +0100 Subject: printk, vt, fbcon: Remove console_conditional_schedule() do_con_write(), fbcon_redraw.*() invoke console_conditional_schedule() which is a conditional scheduling point based on printk's internal variables console_may_schedule. It may only be used if the console lock is acquired for instance via console_lock() or console_trylock(). Prinkt sets the internal variable to 1 (and allows to schedule) if the console lock has been acquired via console_lock(). The trylock does not allow it. The console_conditional_schedule() invocation in do_con_write() is invoked shortly before console_unlock(). The console_conditional_schedule() invocation in fbcon_redraw.*() original from fbcon_scroll() / vt's con_scroll() which originate from a line feed. In console_unlock() the variable is set to 0 (forbids to schedule) and it tries to schedule while making progress printing. This is brand new compared to when console_conditional_schedule() was added in v2.4.9.11. In v2.6.38-rc3, console_unlock() (started its existence) iterated over all consoles and flushed them with disabled interrupts. A scheduling attempt here was not possible, it relied that a long print scheduled before console_unlock(). Since commit 8d91f8b15361d ("printk: do cond_resched() between lines while outputting to consoles"), which appeared in v4.5-rc1, console_unlock() attempts to schedule if it was allowed to schedule while during console_lock(). Each record is idealy one line so after every line feed. This console_conditional_schedule() is also only relevant on PREEMPT_NONE and PREEMPT_VOLUNTARY builds. In other configurations cond_resched() becomes a nop and has no impact. I'm bringing this all up just proof that it is not required anymore. It becomes a problem on a PREEMPT_RT build with debug code enabled because that might_sleep() in cond_resched() remains and triggers a warnings. This is due to legacy_kthread_func-> console_flush_one_record -> vt_console_print-> lf -> con_scroll -> fbcon_scroll and vt_console_print() acquires a spinlock_t which does not allow a voluntary schedule. There is no need to fb_scroll() to schedule since console_flush_one_record() attempts to schedule after each line. !PREEMPT_RT is not affected because the legacy printing thread is only enabled on PREEMPT_RT builds. Therefore I suggest to remove console_conditional_schedule(). Cc: Simona Vetter Cc: Helge Deller Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Fixes: 5f53ca3ff83b4 ("printk: Implement legacy printer kthread for PREEMPT_RT") Signed-off-by: Sebastian Andrzej Siewior Acked-by: Greg Kroah-Hartman Acked-by: Petr Mladek # from printk() POV Signed-off-by: Helge Deller --- include/linux/console.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/console.h b/include/linux/console.h index 1346f0b4cd8b..5520e4477ad7 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -697,7 +697,6 @@ extern int unregister_console(struct console *); extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); -extern void console_conditional_schedule(void); extern void console_unblank(void); extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); -- cgit v1.2.3 From a86039b76e5d1e886d42ec28f569a9ef76409750 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Tue, 10 Feb 2026 10:43:32 +0100 Subject: fbcon: Declare struct fb_info.fbcon_par as of type struct fbcon_par The only correct type for the field fbcon_par in struct fb_info is struct fbcon_par. Declare is as such. The field is a pointer to fbcon-private data. Signed-off-by: Thomas Zimmermann Signed-off-by: Helge Deller --- include/linux/fb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index e70ee58d689e..6d4a58084fd5 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -18,6 +18,7 @@ struct backlight_device; struct device; struct device_node; struct fb_info; +struct fbcon_par; struct file; struct i2c_adapter; struct inode; @@ -505,7 +506,7 @@ struct fb_info { #define FBINFO_STATE_RUNNING 0 #define FBINFO_STATE_SUSPENDED 1 u32 state; /* Hardware state i.e suspend */ - void *fbcon_par; /* fbcon use-only private area */ + struct fbcon_par *fbcon_par; /* fbcon use-only private area */ /* From here on everything is device dependent */ void *par; -- cgit v1.2.3 From 11506b3c233fcead6eba2842d17ec29c84f550d4 Mon Sep 17 00:00:00 2001 From: Andreas Hindborg Date: Sat, 14 Feb 2026 10:12:54 +0100 Subject: block: update docs for bio and bvec_iter The documentation for bio and bvec_iter refers to a vector named bvl_vec. This does not exist. Update the documentation comment with correct use. Also update documentation comments for remaining fields of `bvec_iter` to improve readability. The fields of `bvec_iter` is using a mix of tabs and spaces for indentation. While at it, change them all to tabs, which is most prevalent in this struct definition. Signed-off-by: Andreas Hindborg Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 +++++++- include/linux/bvec.h | 29 +++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d59553324a84..397602606f74 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -273,7 +273,13 @@ struct bio { * Everything starting with bi_max_vecs will be preserved by bio_reset() */ - unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ + /* + * Number of elements in `bi_io_vec` that were allocated for this bio. + * Only used by the bio submitter to make `bio_add_page` fail once full + * and to free the `bi_io_vec` allocation. Must not be used in drivers + * and does not hold a useful value for cloned bios. + */ + unsigned short bi_max_vecs; atomic_t __bi_cnt; /* pin count */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 3fc0efa0825b..06fb60471aaf 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -75,14 +75,27 @@ static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr, } struct bvec_iter { - sector_t bi_sector; /* device address in 512 byte - sectors */ - unsigned int bi_size; /* residual I/O count */ - - unsigned int bi_idx; /* current index into bvl_vec */ - - unsigned int bi_bvec_done; /* number of bytes completed in - current bvec */ + /* + * Current device address in 512 byte sectors. Only updated by the bio + * iter wrappers and not the bvec iterator helpers themselves. + */ + sector_t bi_sector; + + /* + * Remaining size in bytes. + */ + unsigned int bi_size; + + /* + * Current index into the bvec array. This indexes into `bi_io_vec` when + * iterating a bvec array that is part of a `bio`. + */ + unsigned int bi_idx; + + /* + * Current offset in the bvec entry pointed to by `bi_idx`. + */ + unsigned int bi_bvec_done; } __packed __aligned(4); struct bvec_iter_all { -- cgit v1.2.3 From 4c431a76a288ce958aaa114d8ea6fc0968942832 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 15 Feb 2026 21:29:41 -0800 Subject: block: fix enum descriptions kernel-doc Fix all kernel-doc warnings in blk_types.h: Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_READ' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_WRITE' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_FLUSH' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_DISCARD' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_SECURE_ERASE' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_APPEND' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_WRITE_ZEROES' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_OPEN' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_CLOSE' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_FINISH' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_RESET' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_ZONE_RESET_ALL' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_DRV_IN' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_DRV_OUT' not described in enum 'req_op' Warning: include/linux/blk_types.h:371 Enum value 'REQ_OP_LAST' not described in enum 'req_op' Signed-off-by: Randy Dunlap Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 397602606f74..8808ee76e73c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -345,32 +345,33 @@ typedef __u32 __bitwise blk_mq_req_flags_t; * meaning. */ enum req_op { - /* read sectors from the device */ + /** @REQ_OP_READ: read sectors from the device */ REQ_OP_READ = (__force blk_opf_t)0, - /* write sectors to the device */ + /** @REQ_OP_WRITE: write sectors to the device */ REQ_OP_WRITE = (__force blk_opf_t)1, - /* flush the volatile write cache */ + /** @REQ_OP_FLUSH: flush the volatile write cache */ REQ_OP_FLUSH = (__force blk_opf_t)2, - /* discard sectors */ + /** @REQ_OP_DISCARD: discard sectors */ REQ_OP_DISCARD = (__force blk_opf_t)3, - /* securely erase sectors */ + /** @REQ_OP_SECURE_ERASE: securely erase sectors */ REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, - /* write data at the current zone write pointer */ + /** @REQ_OP_ZONE_APPEND: write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = (__force blk_opf_t)7, - /* write the zero filled sector many times */ + /** @REQ_OP_WRITE_ZEROES: write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, - /* Open a zone */ + /** @REQ_OP_ZONE_OPEN: Open a zone */ REQ_OP_ZONE_OPEN = (__force blk_opf_t)11, - /* Close a zone */ + /** @REQ_OP_ZONE_CLOSE: Close a zone */ REQ_OP_ZONE_CLOSE = (__force blk_opf_t)13, - /* Transition a zone to full */ + /** @REQ_OP_ZONE_FINISH: Transition a zone to full */ REQ_OP_ZONE_FINISH = (__force blk_opf_t)15, - /* reset a zone write pointer */ + /** @REQ_OP_ZONE_RESET: reset a zone write pointer */ REQ_OP_ZONE_RESET = (__force blk_opf_t)17, - /* reset all the zone present on the device */ + /** @REQ_OP_ZONE_RESET_ALL: reset all the zone present on the device */ REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)19, /* Driver private requests */ + /* private: */ REQ_OP_DRV_IN = (__force blk_opf_t)34, REQ_OP_DRV_OUT = (__force blk_opf_t)35, -- cgit v1.2.3 From ce9e40a9a5e5cff0b1b0d2fa582b3d71a8ce68e8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 6 Feb 2026 15:48:16 +0000 Subject: irqchip/gic-v3-its: Limit number of per-device MSIs to the range the ITS supports The ITS driver blindly assumes that EventIDs are in abundant supply, to the point where it never checks how many the hardware actually supports. It turns out that some pretty esoteric integrations make it so that only a few bits are available, all the way down to a single bit. Enforce the advertised limitation at the point of allocating the device structure, and hope that the endpoint driver can deal with such limitation. Fixes: 84a6a2e7fc18d ("irqchip: GICv3: ITS: device allocation and configuration") Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Reviewed-by: Robin Murphy Reviewed-by: Zenghui Yu Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260206154816.3582887-1-maz@kernel.org --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 70c0948f978e..0225121f3013 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -394,6 +394,7 @@ #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 #define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) +#define GITS_TYPER_IDBITS GENMASK_ULL(12, 8) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) -- cgit v1.2.3 From 07919126ecfc392102555a70016db3e591abcb3d Mon Sep 17 00:00:00 2001 From: Sun Jian Date: Thu, 5 Feb 2026 20:30:17 +0800 Subject: netfilter: annotate NAT helper hook pointers with __rcu The NAT helper hook pointers are updated and dereferenced under RCU rules, but lack the proper __rcu annotation. This makes sparse report address space mismatches when the hooks are used with rcu_dereference(). Add the missing __rcu annotations to the global hook pointer declarations and definitions in Amanda, FTP, IRC, SNMP and TFTP. No functional change intended. Suggested-by: Florian Westphal Signed-off-by: Sun Jian Signed-off-by: Florian Westphal --- include/linux/netfilter/nf_conntrack_amanda.h | 2 +- include/linux/netfilter/nf_conntrack_ftp.h | 2 +- include/linux/netfilter/nf_conntrack_irc.h | 2 +- include/linux/netfilter/nf_conntrack_snmp.h | 2 +- include/linux/netfilter/nf_conntrack_tftp.h | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 6f0ac896fcc9..dfe89f38d1f7 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -7,7 +7,7 @@ #include #include -extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, +extern unsigned int (__rcu *nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int protoff, unsigned int matchoff, diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 0e38302820b9..f31292642035 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -26,7 +26,7 @@ struct nf_ct_ftp_master { /* For NAT to hook in when we find a packet which describes what other * connection we should expect. */ -extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, +extern unsigned int (__rcu *nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, unsigned int protoff, diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index d02255f721e1..4f3ca5621998 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -8,7 +8,7 @@ #define IRC_PORT 6667 -extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, +extern unsigned int (__rcu *nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, unsigned int protoff, unsigned int matchoff, diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h index 87e4f33eb55f..99107e4f5234 100644 --- a/include/linux/netfilter/nf_conntrack_snmp.h +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -5,7 +5,7 @@ #include #include -extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, +extern int (__rcu *nf_nat_snmp_hook)(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo); diff --git a/include/linux/netfilter/nf_conntrack_tftp.h b/include/linux/netfilter/nf_conntrack_tftp.h index dc4c1b9beac0..1490b68dd7d1 100644 --- a/include/linux/netfilter/nf_conntrack_tftp.h +++ b/include/linux/netfilter/nf_conntrack_tftp.h @@ -19,7 +19,7 @@ struct tftphdr { #define TFTP_OPCODE_ACK 4 #define TFTP_OPCODE_ERROR 5 -extern unsigned int (*nf_nat_tftp_hook)(struct sk_buff *skb, +extern unsigned int (__rcu *nf_nat_tftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, struct nf_conntrack_expect *exp); -- cgit v1.2.3 From 5959495449caf325a0394602568e287f2b829818 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 17 Feb 2026 17:06:30 -0800 Subject: fsverity: remove fsverity_verify_page() Now that fsverity_verify_page() has no callers, remove it. Suggested-by: Linus Torvalds Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20260218010630.7407-4-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index fed91023bea9..6de3ddf0b148 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -282,12 +282,6 @@ static inline bool fsverity_verify_folio(struct fsverity_info *vi, return fsverity_verify_blocks(vi, folio, folio_size(folio), 0); } -static inline bool fsverity_verify_page(struct fsverity_info *vi, - struct page *page) -{ - return fsverity_verify_blocks(vi, page_folio(page), PAGE_SIZE, 0); -} - /** * fsverity_file_open() - prepare to open a verity file * @inode: the inode being opened -- cgit v1.2.3 From 693680b9add63dbebb2505a553ff52f8c706c8c0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 17 Feb 2026 17:22:44 -0800 Subject: fsverity: fix build error by adding fsverity_readahead() stub hppa-linux-gcc 9.5.0 generates a call to fsverity_readahead() in f2fs_readahead() when CONFIG_FS_VERITY=n, because it fails to do the expected dead code elimination based on vi always being NULL. Fix the build error by adding an inline stub for fsverity_readahead(). Since it's just for opportunistic readahead, just make it a no-op. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202602180838.pwICdY2r-lkp@intel.com/ Fixes: 45dcb3ac9832 ("f2fs: consolidate fsverity_info lookup") Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20260218012244.18536-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/fsverity.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index 6de3ddf0b148..a8f9aa75b792 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -195,6 +195,8 @@ int fsverity_ioctl_read_metadata(struct file *filp, const void __user *uarg); /* verify.c */ +void fsverity_readahead(struct fsverity_info *vi, pgoff_t index, + unsigned long nr_pages); bool fsverity_verify_blocks(struct fsverity_info *vi, struct folio *folio, size_t len, size_t offset); void fsverity_verify_bio(struct fsverity_info *vi, struct bio *bio); @@ -255,6 +257,11 @@ static inline int fsverity_ioctl_read_metadata(struct file *filp, /* verify.c */ +static inline void fsverity_readahead(struct fsverity_info *vi, pgoff_t index, + unsigned long nr_pages) +{ +} + static inline bool fsverity_verify_blocks(struct fsverity_info *vi, struct folio *folio, size_t len, size_t offset) @@ -303,8 +310,6 @@ static inline int fsverity_file_open(struct inode *inode, struct file *filp) } void fsverity_cleanup_inode(struct inode *inode); -void fsverity_readahead(struct fsverity_info *vi, pgoff_t index, - unsigned long nr_pages); struct page *generic_read_merkle_tree_page(struct inode *inode, pgoff_t index); void generic_readahead_merkle_tree(struct inode *inode, pgoff_t index, -- cgit v1.2.3 From 249013e673fce3506c61063c7cbedd75b4c668d8 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 18 Feb 2026 22:09:21 -0800 Subject: fsnotify: drop unused helper Remove this helper now that all users have been converted to fserror_report_metadata as of 7.0-rc1. Cc: jack@suse.cz Cc: amir73il@gmail.com Signed-off-by: Darrick J. Wong Link: https://patch.msgid.link/177148129543.716249.980530449513340111.stgit@frogsfrogsfrogs Reviewed-by: Christoph Hellwig Signed-off-by: Christian Brauner --- include/linux/fsnotify.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 28a9cb13fbfa..079c18bcdbde 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -495,19 +495,6 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } -static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, - int error) -{ - struct fs_error_report report = { - .error = error, - .inode = inode, - .sb = sb, - }; - - return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, - NULL, NULL, NULL, 0); -} - static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); -- cgit v1.2.3 From ea129e55c9e06a51a93c3f5ef3e32a6cfa3f8ec7 Mon Sep 17 00:00:00 2001 From: Govindarajulu Varadarajan Date: Wed, 18 Feb 2026 20:59:30 -0800 Subject: io_uring: Add size check for sqe->cmd For SQE128, sqe->cmd provides 80 bytes for uring_cmd. Add macro to check if size of user struct does not exceed 80 bytes at compile time. User doesn't have to track this manually during development. Replace io_uring_sqe_cmd() inline func with macro and add io_uring_sqe128_cmd() which checks struct size for 16 bytes cmd and 80 bytes cmd respectively. Signed-off-by: Govindarajulu Varadarajan Reviewed-by: Caleb Sander Mateos Signed-off-by: Jens Axboe --- include/linux/io_uring/cmd.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 375fd048c4cb..331dcbefe72f 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -20,10 +20,17 @@ struct io_uring_cmd { u8 unused[8]; }; -static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) -{ - return sqe->cmd; -} +#define io_uring_sqe128_cmd(sqe, type) ({ \ + BUILD_BUG_ON(sizeof(type) > ((2 * sizeof(struct io_uring_sqe)) - \ + offsetof(struct io_uring_sqe, cmd))); \ + (const type *)(sqe)->cmd; \ +}) + +#define io_uring_sqe_cmd(sqe, type) ({ \ + BUILD_BUG_ON(sizeof(type) > (sizeof(struct io_uring_sqe) - \ + offsetof(struct io_uring_sqe, cmd))); \ + (const type *)(sqe)->cmd; \ +}) static inline void io_uring_cmd_private_sz_check(size_t cmd_sz) { -- cgit v1.2.3 From 47bf2e813817159f4d195be83a9b5a640ee6baec Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 18 Feb 2026 09:28:59 +0200 Subject: net/mlx5: Fix multiport device check over light SFs Driver is using num_vhca_ports capability to distinguish between multiport master device and multiport slave device. num_vhca_ports is a capability the driver sets according to the MAX num_vhca_ports capability reported by FW. On the other hand, light SFs doesn't set the above capbility. This leads to wrong results whenever light SFs is checking whether he is a multiport master or slave. Therefore, use the MAX capability to distinguish between master and slave devices. Fixes: e71383fb9cd1 ("net/mlx5: Light probe local SFs") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Tariq Toukan Reviewed-by: Jacob Keller Link: https://patch.msgid.link/20260218072904.1764634-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/mlx5/driver.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e2d067b1e67b..04dcd09f7517 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1282,12 +1282,12 @@ static inline bool mlx5_rl_is_supported(struct mlx5_core_dev *dev) static inline int mlx5_core_is_mp_slave(struct mlx5_core_dev *dev) { return MLX5_CAP_GEN(dev, affiliate_nic_vport_criteria) && - MLX5_CAP_GEN(dev, num_vhca_ports) <= 1; + MLX5_CAP_GEN_MAX(dev, num_vhca_ports) <= 1; } static inline int mlx5_core_is_mp_master(struct mlx5_core_dev *dev) { - return MLX5_CAP_GEN(dev, num_vhca_ports) > 1; + return MLX5_CAP_GEN_MAX(dev, num_vhca_ports) > 1; } static inline int mlx5_core_mp_enabled(struct mlx5_core_dev *dev) -- cgit v1.2.3 From f4ff9f646a4d373f9e895c2f0073305da288bc0a Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Feb 2026 10:42:44 -0500 Subject: fgraph: Do not call handlers direct when not using ftrace_ops The function graph tracer was modified to us the ftrace_ops of the function tracer. This simplified the code as well as allowed more features of the function graph tracer. Not all architectures were converted over as it required the implementation of HAVE_DYNAMIC_FTRACE_WITH_ARGS to implement. For those architectures, it still did it the old way where the function graph tracer handle was called by the function tracer trampoline. The handler then had to check the hash to see if the registered handlers wanted to be called by that function or not. In order to speed up the function graph tracer that used ftrace_ops, if only one callback was registered with function graph, it would call its function directly via a static call. Now, if the architecture does not support the use of using ftrace_ops and still has the ftrace function trampoline calling the function graph handler, then by doing a direct call it removes the check against the handler's hash (list of functions it wants callbacks to), and it may call that handler for functions that the handler did not request calls for. On 32bit x86, which does not support the ftrace_ops use with function graph tracer, it shows the issue: ~# trace-cmd start -p function -l schedule ~# trace-cmd show # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 2) * 11898.94 us | schedule(); 3) # 1783.041 us | schedule(); 1) | schedule() { ------------------------------------------ 1) bash-8369 => kworker-7669 ------------------------------------------ 1) | schedule() { ------------------------------------------ 1) kworker-7669 => bash-8369 ------------------------------------------ 1) + 97.004 us | } 1) | schedule() { [..] Now by starting the function tracer is another instance: ~# trace-cmd start -B foo -p function This causes the function graph tracer to trace all functions (because the function trace calls the function graph tracer for each on, and the function graph trace is doing a direct call): ~# trace-cmd show # tracer: function_graph # # CPU DURATION FUNCTION CALLS # | | | | | | | 1) 1.669 us | } /* preempt_count_sub */ 1) + 10.443 us | } /* _raw_spin_unlock_irqrestore */ 1) | tick_program_event() { 1) | clockevents_program_event() { 1) 1.044 us | ktime_get(); 1) 6.481 us | lapic_next_event(); 1) + 10.114 us | } 1) + 11.790 us | } 1) ! 181.223 us | } /* hrtimer_interrupt */ 1) ! 184.624 us | } /* __sysvec_apic_timer_interrupt */ 1) | irq_exit_rcu() { 1) 0.678 us | preempt_count_sub(); When it should still only be tracing the schedule() function. To fix this, add a macro FGRAPH_NO_DIRECT to be set to 0 when the architecture does not support function graph use of ftrace_ops, and set to 1 otherwise. Then use this macro to know to allow function graph tracer to call the handlers directly or not. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Mark Rutland Link: https://patch.msgid.link/20260218104244.5f14dade@gandalf.local.home Fixes: cc60ee813b503 ("function_graph: Use static_call and branch to optimize entry function") Signed-off-by: Steven Rostedt (Google) --- include/linux/ftrace.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 1a4d36fc9085..c242fe49af4c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -1092,10 +1092,17 @@ static inline bool is_ftrace_trampoline(unsigned long addr) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #ifndef ftrace_graph_func -#define ftrace_graph_func ftrace_stub -#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB +# define ftrace_graph_func ftrace_stub +# define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB +/* + * The function graph is called every time the function tracer is called. + * It must always test the ops hash and cannot just directly call + * the handler. + */ +# define FGRAPH_NO_DIRECT 1 #else -#define FTRACE_OPS_GRAPH_STUB 0 +# define FTRACE_OPS_GRAPH_STUB 0 +# define FGRAPH_NO_DIRECT 0 #endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -- cgit v1.2.3 From 9678e53179aa7e907360f5b5b275769008a69b80 Mon Sep 17 00:00:00 2001 From: Petr Pavlu Date: Thu, 19 Feb 2026 17:27:02 +0100 Subject: tracing: Wake up poll waiters for hist files when removing an event The event_hist_poll() function attempts to verify whether an event file is being removed, but this check may not occur or could be unnecessarily delayed. This happens because hist_poll_wakeup() is currently invoked only from event_hist_trigger() when a hist command is triggered. If the event file is being removed, no associated hist command will be triggered and a waiter will be woken up only after an unrelated hist command is triggered. Fix the issue by adding a call to hist_poll_wakeup() in remove_event_file_dir() after setting the EVENT_FILE_FL_FREED flag. This ensures that a task polling on a hist file is woken up and receives EPOLLERR. Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Cc: Tom Zanussi Acked-by: Masami Hiramatsu (Google) Link: https://patch.msgid.link/20260219162737.314231-3-petr.pavlu@suse.com Fixes: 1bd13edbbed6 ("tracing/hist: Add poll(POLLIN) support on hist file") Signed-off-by: Petr Pavlu Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_events.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 0a2b8229b999..37eb2f0f3dd8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -683,6 +683,11 @@ static inline void hist_poll_wakeup(void) #define hist_poll_wait(file, wait) \ poll_wait(file, &hist_poll_wq, wait) + +#else +static inline void hist_poll_wakeup(void) +{ +} #endif #define __TRACE_EVENT_FLAGS(name, value) \ -- cgit v1.2.3 From 7bd27439a578bb7724a9f09f240337ab95d68d2b Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Thu, 20 Feb 2025 02:03:57 +0000 Subject: NTB/msi: Remove unused functions ntbm_msi_free_irq() and ntb_msi_peer_addr() were both added in 2019's commit 26b3a37b9284 ("NTB: Introduce MSI library") but have remained unused. Remove them, and the ntbm_msi_callback_match() helper that was used by ntbm_msi_free_irq(). Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Jon Mason --- include/linux/ntb.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 191b524e5c0d..8ff9d663096b 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -1647,12 +1647,8 @@ int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler, irq_handler_t thread_fn, const char *name, void *dev_id, struct ntb_msi_desc *msi_desc); -void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, void *dev_id); int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, struct ntb_msi_desc *desc); -int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, - struct ntb_msi_desc *desc, - phys_addr_t *msi_addr); #else /* not CONFIG_NTB_MSI */ @@ -1674,21 +1670,11 @@ static inline int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, { return -EOPNOTSUPP; } -static inline void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, - void *dev_id) {} static inline int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, struct ntb_msi_desc *desc) { return -EOPNOTSUPP; } -static inline int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, - struct ntb_msi_desc *desc, - phys_addr_t *msi_addr) -{ - return -EOPNOTSUPP; - -} - #endif /* CONFIG_NTB_MSI */ static inline int ntbm_msi_request_irq(struct ntb_dev *ntb, -- cgit v1.2.3 From d39a1d7486d98668dd34aaa6732aad7977c45f5a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 20 Feb 2026 13:15:58 -0800 Subject: compiler_types: Disable __builtin_counted_by_ref for Clang Unfortunately, there is a corner case of __builtin_counted_by_ref() usage that crashes[1] Clang since support was introduced in Clang 19. Disable it prior to Clang 22. Found while tested kmalloc_obj treewide refactoring (via kmalloc_flex() usage). Link: https://github.com/llvm/llvm-project/issues/182575 [1] Signed-off-by: Kees Cook --- include/linux/compiler_types.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b1b141394d13..890076d0974b 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -552,7 +552,8 @@ struct ftrace_likely_data { * gcc: https://gcc.gnu.org/onlinedocs/gcc/Other-Builtins.html#index-_005f_005fbuiltin_005fcounted_005fby_005fref * clang: https://clang.llvm.org/docs/LanguageExtensions.html#builtin-counted-by-ref */ -#if __has_builtin(__builtin_counted_by_ref) +#if __has_builtin(__builtin_counted_by_ref) && \ + !defined(CONFIG_CC_HAS_BROKEN_COUNTED_BY_REF) /** * __flex_counter() - Get pointer to counter member for the given * flexible array, if it was annotated with __counted_by() -- cgit v1.2.3 From 69050f8d6d075dc01af7a5f2f550a8067510366f Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 20 Feb 2026 23:49:23 -0800 Subject: treewide: Replace kmalloc with kmalloc_obj for non-scalar types This is the result of running the Coccinelle script from scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to avoid scalar types (which need careful case-by-case checking), and instead replace kmalloc-family calls that allocate struct or union object instances: Single allocations: kmalloc(sizeof(TYPE), ...) are replaced with: kmalloc_obj(TYPE, ...) Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...) are replaced with: kmalloc_objs(TYPE, COUNT, ...) Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...) are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...) (where TYPE may also be *VAR) The resulting allocations no longer return "void *", instead returning "TYPE *". Signed-off-by: Kees Cook --- include/linux/acpi.h | 2 +- include/linux/bpf.h | 2 +- include/linux/crash_dump.h | 2 +- include/linux/dma-fence-chain.h | 2 +- include/linux/gameport.h | 2 +- include/linux/io-mapping.h | 2 +- include/linux/kvm_host.h | 2 +- include/linux/skmsg.h | 3 +-- include/linux/spi/spi.h | 2 +- 9 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3a412dcebc29..8b1d8993793d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -66,7 +66,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; - fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); + fwnode = kzalloc_obj(struct fwnode_handle, GFP_KERNEL); if (!fwnode) return NULL; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cd9b96434904..b78b53198a2e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2299,7 +2299,7 @@ static inline bool bpf_map_flags_access_ok(u32 access_flags) static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map) { - return kzalloc(sizeof(*map->owner), GFP_ATOMIC); + return kzalloc_obj(*map->owner, GFP_ATOMIC); } static inline void bpf_map_owner_free(struct bpf_map *map) diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index dd6fc3b2133b..2cb211617ecc 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -136,7 +136,7 @@ struct vmcore_range { static inline int vmcore_alloc_add_range(struct list_head *list, unsigned long long paddr, unsigned long long size) { - struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL); + struct vmcore_range *m = kzalloc_obj(*m, GFP_KERNEL); if (!m) return -ENOMEM; diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 68c3c1e41014..3267ab0e8c54 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -91,7 +91,7 @@ dma_fence_chain_contained(struct dma_fence *fence) * intentional to enforce typesafety. */ #define dma_fence_chain_alloc() \ - ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) + ((struct dma_fence_chain *) kmalloc_obj(struct dma_fence_chain, GFP_KERNEL)) /** * dma_fence_chain_free diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 86d62fdafd7a..09a1a59034e0 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -97,7 +97,7 @@ void gameport_set_phys(struct gameport *gameport, const char *fmt, ...) static inline struct gameport *gameport_allocate_port(void) { - struct gameport *gameport = kzalloc(sizeof(struct gameport), GFP_KERNEL); + struct gameport *gameport = kzalloc_obj(struct gameport, GFP_KERNEL); return gameport; } diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index c16353cc6e3c..ff9012c6a93a 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -206,7 +206,7 @@ io_mapping_create_wc(resource_size_t base, { struct io_mapping *iomap; - iomap = kmalloc(sizeof(*iomap), GFP_KERNEL); + iomap = kmalloc_obj(*iomap, GFP_KERNEL); if (!iomap) return NULL; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d42a95cbcfbc..dde605cb894e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1664,7 +1664,7 @@ void kvm_arch_create_vm_debugfs(struct kvm *kvm); */ static inline struct kvm *kvm_arch_alloc_vm(void) { - return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); + return kzalloc_obj(struct kvm, GFP_KERNEL_ACCOUNT); } #endif diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 829b281d6c9c..a8513e401760 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -460,8 +460,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, * intentional to enforce typesafety. */ #define sk_psock_init_link() \ - ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ - GFP_ATOMIC | __GFP_NOWARN)) + ((struct sk_psock_link *) kzalloc_obj(struct sk_psock_link, GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index fd8dce4169f7..af7cfee7b8f6 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -1309,7 +1309,7 @@ static inline struct spi_message *spi_message_alloc(unsigned ntrans, gfp_t flags } *mwt; unsigned i; - mwt = kzalloc(struct_size(mwt, t, ntrans), flags); + mwt = kzalloc_flex(*mwt, t, ntrans, flags); if (!mwt) return NULL; -- cgit v1.2.3 From 7a70c15bd1449f1eb30991772edce37b41e496fb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 21 Feb 2026 00:12:19 -0800 Subject: kmalloc_obj: Clean up after treewide replacements Coccinelle doesn't handle re-indenting line escapes. Fix the 2 places where these got misaligned. Remove 2 now-redundant type casts, found with: $ git grep -P 'struct (\S+).*\)\s*k\S+alloc_(objs?|flex)\(struct \1' Signed-off-by: Kees Cook --- include/linux/dma-fence-chain.h | 2 +- include/linux/skmsg.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 3267ab0e8c54..e5f4451a6375 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -91,7 +91,7 @@ dma_fence_chain_contained(struct dma_fence *fence) * intentional to enforce typesafety. */ #define dma_fence_chain_alloc() \ - ((struct dma_fence_chain *) kmalloc_obj(struct dma_fence_chain, GFP_KERNEL)) + kmalloc_obj(struct dma_fence_chain, GFP_KERNEL) /** * dma_fence_chain_free diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index a8513e401760..19f4f253b4f9 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -460,7 +460,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, * intentional to enforce typesafety. */ #define sk_psock_init_link() \ - ((struct sk_psock_link *) kzalloc_obj(struct sk_psock_link, GFP_ATOMIC | __GFP_NOWARN)) + kzalloc_obj(struct sk_psock_link, GFP_ATOMIC | __GFP_NOWARN) static inline void sk_psock_free_link(struct sk_psock_link *link) { -- cgit v1.2.3 From fa5c82f4d2bbde10e9fd3a32aecacfe3813919ba Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Feb 2026 15:12:09 -0800 Subject: slab.h: disable completely broken overflow handling in flex allocations Commit 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types") started using the new allocation helpers, and in the process showed that they were completely non-working. The overflow logic in overflows_flex_counter_type() is completely the wrong way around, and that broke __alloc_flex() completely. By chance, the resulting code was then such a mess that clang generated sufficiently garbage code that objtool warned about it all. Which made it somewhat quicker to narrow things down. While fixing overflows_flex_counter_type() would presumably fix this all, I'm excising the whole broken overflow logic from __alloc_flex(), because we don't want that kind of code in basic allocation functions anyway. That (no longer) broken overflows_flex_counter_type() thing needs to be inserted into the actual __set_flex_counter() logic in the unlikely case that we ever want this at all. And made conditional. Fixes: 81cee9166a90 ("compiler_types: Introduce __flex_counter() and family") Fixes: 69050f8d6d07 ("treewide: Replace kmalloc with kmalloc_obj for non-scalar types") Cc: Kees Cook Link: https://lore.kernel.org/all/CAHk-=whEd020BYzGTzYrENjD9Z5_82xx6h8HsQvH5xDSnv0=Hw@mail.gmail.com/ Signed-off-by: Linus Torvalds --- include/linux/overflow.h | 2 +- include/linux/slab.h | 6 +----- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index a5e95dbce220..eddd987a8513 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -570,7 +570,7 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) * @FAM is not annotated with __counted_by(), always returns true. */ #define overflows_flex_counter_type(TYPE, FAM, COUNT) \ - (!overflows_type(COUNT, typeof_flex_counter(((TYPE *)NULL)->FAM))) + (overflows_type(COUNT, typeof_flex_counter(((TYPE *)NULL)->FAM))) /** * __set_flex_counter() - Set the counter associated with the given flexible diff --git a/include/linux/slab.h b/include/linux/slab.h index c5fde8740281..1270320b59c8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1003,11 +1003,7 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); ({ \ const size_t __count = (COUNT); \ const size_t __obj_size = struct_size_t(TYPE, FAM, __count); \ - TYPE *__obj_ptr; \ - if (WARN_ON_ONCE(overflows_flex_counter_type(TYPE, FAM, __count))) \ - __obj_ptr = NULL; \ - else \ - __obj_ptr = KMALLOC(__obj_size, GFP); \ + TYPE *__obj_ptr = KMALLOC(__obj_size, GFP); \ if (__obj_ptr) \ __set_flex_counter(__obj_ptr->FAM, __count); \ __obj_ptr; \ -- cgit v1.2.3 From e19e1b480ac73c3e62ffebbca1174f0f511f43e7 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Feb 2026 16:14:11 -0800 Subject: add default_gfp() helper macro and use it in the new *alloc_obj() helpers Most simple allocations use GFP_KERNEL, and with the new allocation helpers being introduced, let's just take advantage of that to simplify that default case. It's a numbers game: git grep 'alloc_obj(' | sed 's/.*\(GFP_[_A-Z]*\).*/\1/' | sort | uniq -c | sort -n | tail shows that about 90% of all those new allocator instances just use that standard GFP_KERNEL. Those helpers are already macros, and we can easily just make it be the default case when the gfp argument is missing. And yes, we could do that for all the legacy interfaces too, but let's keep it to just the new ones at least for now, since those all got converted recently anyway, so this is not any "extra" noise outside of that limited conversion. And, in fact, I want to do this before doing the -rc1 release, exactly so that we don't get extra merge conflicts. Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++++ include/linux/slab.h | 48 ++++++++++++++++++++++++------------------------ 2 files changed, 28 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6ecf6dda93e0..2b30a0529d48 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -13,6 +13,10 @@ struct vm_area_struct; struct mempolicy; +/* Helper macro to avoid gfp flags if they are the default one */ +#define __default_gfp(a,...) a +#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL) + /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 diff --git a/include/linux/slab.h b/include/linux/slab.h index 1270320b59c8..a5a5e4108ae5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1017,8 +1017,8 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); * Returns: newly allocated pointer to a @VAR_OR_TYPE on success, or NULL * on failure. */ -#define kmalloc_obj(VAR_OR_TYPE, GFP) \ - __alloc_objs(kmalloc, GFP, typeof(VAR_OR_TYPE), 1) +#define kmalloc_obj(VAR_OR_TYPE, ...) \ + __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), 1) /** * kmalloc_objs - Allocate an array of the given type @@ -1029,8 +1029,8 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); * Returns: newly allocated pointer to array of @VAR_OR_TYPE on success, * or NULL on failure. */ -#define kmalloc_objs(VAR_OR_TYPE, COUNT, GFP) \ - __alloc_objs(kmalloc, GFP, typeof(VAR_OR_TYPE), COUNT) +#define kmalloc_objs(VAR_OR_TYPE, COUNT, ...) \ + __alloc_objs(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), COUNT) /** * kmalloc_flex - Allocate a single instance of the given flexible structure @@ -1044,32 +1044,32 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); * will immediately fail if @COUNT is larger than what the type of the * struct's counter variable can represent. */ -#define kmalloc_flex(VAR_OR_TYPE, FAM, COUNT, GFP) \ - __alloc_flex(kmalloc, GFP, typeof(VAR_OR_TYPE), FAM, COUNT) +#define kmalloc_flex(VAR_OR_TYPE, FAM, COUNT, ...) \ + __alloc_flex(kmalloc, default_gfp(__VA_ARGS__), typeof(VAR_OR_TYPE), FAM, COUNT) /* All kzalloc aliases for kmalloc_(obj|objs|flex). */ -#define kzalloc_obj(P, GFP) \ - __alloc_objs(kzalloc, GFP, typeof(P), 1) -#define kzalloc_objs(P, COUNT, GFP) \ - __alloc_objs(kzalloc, GFP, typeof(P), COUNT) -#define kzalloc_flex(P, FAM, COUNT, GFP) \ - __alloc_flex(kzalloc, GFP, typeof(P), FAM, COUNT) +#define kzalloc_obj(P, ...) \ + __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) +#define kzalloc_objs(P, COUNT, ...) \ + __alloc_objs(kzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) +#define kzalloc_flex(P, FAM, COUNT, ...) \ + __alloc_flex(kzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvmalloc aliases for kmalloc_(obj|objs|flex). */ -#define kvmalloc_obj(P, GFP) \ - __alloc_objs(kvmalloc, GFP, typeof(P), 1) -#define kvmalloc_objs(P, COUNT, GFP) \ - __alloc_objs(kvmalloc, GFP, typeof(P), COUNT) -#define kvmalloc_flex(P, FAM, COUNT, GFP) \ - __alloc_flex(kvmalloc, GFP, typeof(P), FAM, COUNT) +#define kvmalloc_obj(P, ...) \ + __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), 1) +#define kvmalloc_objs(P, COUNT, ...) \ + __alloc_objs(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) +#define kvmalloc_flex(P, FAM, COUNT, ...) \ + __alloc_flex(kvmalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) /* All kvzalloc aliases for kmalloc_(obj|objs|flex). */ -#define kvzalloc_obj(P, GFP) \ - __alloc_objs(kvzalloc, GFP, typeof(P), 1) -#define kvzalloc_objs(P, COUNT, GFP) \ - __alloc_objs(kvzalloc, GFP, typeof(P), COUNT) -#define kvzalloc_flex(P, FAM, COUNT, GFP) \ - __alloc_flex(kvzalloc, GFP, typeof(P), FAM, COUNT) +#define kvzalloc_obj(P, ...) \ + __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), 1) +#define kvzalloc_objs(P, COUNT, ...) \ + __alloc_objs(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), COUNT) +#define kvzalloc_flex(P, FAM, COUNT, ...) \ + __alloc_flex(kvzalloc, default_gfp(__VA_ARGS__), typeof(P), FAM, COUNT) #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) -- cgit v1.2.3 From bf4afc53b77aeaa48b5409da5c8da6bb4eff7f43 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 21 Feb 2026 16:37:42 -0800 Subject: Convert 'alloc_obj' family to use the new default GFP_KERNEL argument This was done entirely with mindless brute force, using git grep -l '\ --- include/linux/acpi.h | 2 +- include/linux/crash_dump.h | 2 +- include/linux/dma-fence-chain.h | 2 +- include/linux/gameport.h | 2 +- include/linux/io-mapping.h | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 8b1d8993793d..4d2f0bed7a06 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -66,7 +66,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; - fwnode = kzalloc_obj(struct fwnode_handle, GFP_KERNEL); + fwnode = kzalloc_obj(struct fwnode_handle); if (!fwnode) return NULL; diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 2cb211617ecc..8315270e27b7 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -136,7 +136,7 @@ struct vmcore_range { static inline int vmcore_alloc_add_range(struct list_head *list, unsigned long long paddr, unsigned long long size) { - struct vmcore_range *m = kzalloc_obj(*m, GFP_KERNEL); + struct vmcore_range *m = kzalloc_obj(*m); if (!m) return -ENOMEM; diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index e5f4451a6375..5cd3ba53b4a1 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -91,7 +91,7 @@ dma_fence_chain_contained(struct dma_fence *fence) * intentional to enforce typesafety. */ #define dma_fence_chain_alloc() \ - kmalloc_obj(struct dma_fence_chain, GFP_KERNEL) + kmalloc_obj(struct dma_fence_chain) /** * dma_fence_chain_free diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 09a1a59034e0..9625347c7ac0 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -97,7 +97,7 @@ void gameport_set_phys(struct gameport *gameport, const char *fmt, ...) static inline struct gameport *gameport_allocate_port(void) { - struct gameport *gameport = kzalloc_obj(struct gameport, GFP_KERNEL); + struct gameport *gameport = kzalloc_obj(struct gameport); return gameport; } diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index ff9012c6a93a..e5a884e72f29 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -206,7 +206,7 @@ io_mapping_create_wc(resource_size_t base, { struct io_mapping *iomap; - iomap = kmalloc_obj(*iomap, GFP_KERNEL); + iomap = kmalloc_obj(*iomap); if (!iomap) return NULL; -- cgit v1.2.3 From 6e3c0a4e1ad1e0455b7880fad02b3ee179f56c09 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 22 Apr 2025 12:16:28 +0200 Subject: sched/fair: Fix lag clamp Vincent reported that he was seeing undue lag clamping in a mixed slice workload. Implement the max_slice tracking as per the todo comment. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Reported-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Tested-by: Vincent Guittot Tested-by: K Prateek Nayak Tested-by: Shubhang Kaushik Link: https://patch.msgid.link/20250422101628.GA33555@noisy.programming.kicks-ass.net --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 074ad4ef3d81..a7b4a980eb2f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -579,6 +579,7 @@ struct sched_entity { u64 deadline; u64 min_vruntime; u64 min_slice; + u64 max_slice; struct list_head group_node; unsigned char on_rq; -- cgit v1.2.3 From 4c652a47722f69c6f2685f05b17490ea97f643a8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 6 Feb 2026 08:41:13 +0100 Subject: rseq: Mark rseq_arm_slice_extension_timer() __always_inline objtool warns about this function being called inside of a uaccess section: kernel/entry/common.o: warning: objtool: irqentry_exit+0x1dc: call to rseq_arm_slice_extension_timer() with UACCESS enabled Interestingly, this happens with CONFIG_RSEQ_SLICE_EXTENSION disabled, so this is an empty function, as the normal implementation is already marked __always_inline. I could reproduce this multiple times with gcc-11 but not with gcc-15, so the compiler probably got better at identifying the trivial function. Mark all the empty helpers for !RSEQ_SLICE_EXTENSION as __always_inline for consistency, avoiding this warning. Fixes: 0ac3b5c3dc45 ("rseq: Implement time slice extension enforcement timer") Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260206074122.709580-1-arnd@kernel.org --- include/linux/rseq_entry.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index cbc4a791618b..c6831c93cd6e 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -216,10 +216,10 @@ efault: } #else /* CONFIG_RSEQ_SLICE_EXTENSION */ -static inline bool rseq_slice_extension_enabled(void) { return false; } -static inline bool rseq_arm_slice_extension_timer(void) { return false; } -static inline void rseq_slice_clear_grant(struct task_struct *t) { } -static inline bool rseq_grant_slice_extension(bool work_pending) { return false; } +static __always_inline bool rseq_slice_extension_enabled(void) { return false; } +static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } +static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } +static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; } #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); -- cgit v1.2.3 From 3b68df978133ac3d46d570af065a73debbb68248 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Fri, 20 Feb 2026 15:06:41 -0500 Subject: rseq: slice ext: Ensure rseq feature size differs from original rseq size Before rseq became extensible, its original size was 32 bytes even though the active rseq area was only 20 bytes. This had the following impact in terms of userspace ecosystem evolution: * The GNU libc between 2.35 and 2.39 expose a __rseq_size symbol set to 32, even though the size of the active rseq area is really 20. * The GNU libc 2.40 changes this __rseq_size to 20, thus making it express the active rseq area. * Starting from glibc 2.41, __rseq_size corresponds to the AT_RSEQ_FEATURE_SIZE from getauxval(3). This means that users of __rseq_size can always expect it to correspond to the active rseq area, except for the value 32, for which the active rseq area is 20 bytes. Exposing a 32 bytes feature size would make life needlessly painful for userspace. Therefore, add a reserved field at the end of the rseq area to bump the feature size to 33 bytes. This reserved field is expected to be replaced with whatever field will come next, expecting that this field will be larger than 1 byte. The effect of this change is to increase the size from 32 to 64 bytes before we actually have fields using that memory. Clarify the allocation size and alignment requirements in the struct rseq uapi comment. Change the value returned by getauxval(AT_RSEQ_ALIGN) to return the value of the active rseq area size rounded up to next power of 2, which guarantees that the rseq structure will always be aligned on the nearest power of two large enough to contain it, even as it grows. Change the alignment check in the rseq registration accordingly. This will minimize the amount of ABI corner-cases we need to document and require userspace to play games with. The rule stays simple when __rseq_size != 32: #define rseq_field_available(field) (__rseq_size >= offsetofend(struct rseq_abi, field)) Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Link: https://patch.msgid.link/20260220200642.1317826-3-mathieu.desnoyers@efficios.com --- include/linux/rseq.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 7a01a0760405..b9d62fc2140d 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags) t->rseq = current->rseq; } +/* + * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq + * registration. This is the active rseq area size rounded up to next + * power of 2, which guarantees that the rseq structure will always be + * aligned on the nearest power of two large enough to contain it, even + * as it grows. + */ +static inline unsigned int rseq_alloc_align(void) +{ + return 1U << get_count_order(offsetof(struct rseq, end)); +} + #else /* CONFIG_RSEQ */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } -- cgit v1.2.3 From 901084c51a0a8fb42a3f37d2e9c62083c495f824 Mon Sep 17 00:00:00 2001 From: Penghe Geng Date: Thu, 19 Feb 2026 15:29:54 -0500 Subject: mmc: core: Avoid bitfield RMW for claim/retune flags Move claimed and retune control flags out of the bitfield word to avoid unrelated RMW side effects in asynchronous contexts. The host->claimed bit shared a word with retune flags. Writes to claimed in __mmc_claim_host() or retune_now in mmc_mq_queue_rq() can overwrite other bits when concurrent updates happen in other contexts, triggering spurious WARN_ON(!host->claimed). Convert claimed, can_retune, retune_now and retune_paused to bool to remove shared-word coupling. Fixes: 6c0cedd1ef952 ("mmc: core: Introduce host claiming by context") Fixes: 1e8e55b67030c ("mmc: block: Add CQE support") Cc: stable@vger.kernel.org Suggested-by: Adrian Hunter Signed-off-by: Penghe Geng Acked-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e0e2c265e5d1..ba84f02c2a10 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -486,14 +486,12 @@ struct mmc_host { struct mmc_ios ios; /* current io bus settings */ + bool claimed; /* host exclusively claimed */ + /* group bitfields together to minimize padding */ unsigned int use_spi_crc:1; - unsigned int claimed:1; /* host exclusively claimed */ unsigned int doing_init_tune:1; /* initial tuning in progress */ - unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ - unsigned int retune_now:1; /* do re-tuning at next req */ - unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ @@ -508,6 +506,9 @@ struct mmc_host { int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ + bool can_retune; /* re-tuning can be used */ + bool retune_now; /* do re-tuning at next req */ + bool retune_paused; /* re-tuning is temporarily disabled */ int need_retune; /* re-tuning is needed */ int hold_retune; /* hold off re-tuning */ unsigned int retune_period; /* re-tuning period in secs */ -- cgit v1.2.3 From 3afd8df024339c7da1a5a0302f3987866dd16e40 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 22 Dec 2025 21:36:25 +0100 Subject: PM: runtime: Change pm_runtime_put() return type to void The primary role of pm_runtime_put() is to decrement the runtime PM usage counter of the given device. It always does that regardless of the value returned by it later. In addition, if the runtime PM usage counter after decrementation turns out to be zero, a work item is queued up to check whether or not the device can be suspended. This is not guaranteed to succeed though and even if it is successful, the device may still not be suspended going forward. There are multiple valid reasons why pm_runtime_put() may not decide to queue up the work item mentioned above, including, but not limited to, the case when user space has written "on" to the device's runtime PM "control" file in sysfs. In all of those cases, pm_runtime_put() returns a negative error code (even though the device's runtime PM usage counter has been successfully decremented by it) which is very confusing. In fact, its return value should only be used for debug purposes and care should be taken when doing it even in that case. Accordingly, to avoid the confusion mentioned above, change the return type of pm_runtime_put() to void. Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson Reviewed-by: Brian Norris Link: https://patch.msgid.link/14387202.RDIVbhacDa@rafael.j.wysocki --- include/linux/pm_runtime.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 41037c513f06..64921b10ac74 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev) * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). - * - * Return: - * * 1: Success. Usage counter dropped to zero, but device was already suspended. - * * 0: Success. - * * -EINVAL: Runtime PM error. - * * -EACCES: Runtime PM disabled. - * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status - * change ongoing. - * * -EBUSY: Runtime PM child_count non-zero. - * * -EPERM: Device PM QoS resume latency 0. - * * -EINPROGRESS: Suspend already in progress. - * * -ENOSYS: CONFIG_PM not enabled. */ -static inline int pm_runtime_put(struct device *dev) +static inline void pm_runtime_put(struct device *dev) { - return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); + __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** -- cgit v1.2.3 From 2a7b7652b1bb3fadc3bd47d622bfb127a93ab6b0 Mon Sep 17 00:00:00 2001 From: Leif Skunberg Date: Tue, 10 Feb 2026 14:21:29 +0100 Subject: platform/x86: int3472: Handle GPIO type 0x10 (DOVDD) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Lenovo ThinkPad X1 Fold 16 Gen 1 has an OV5675 sensor (ACPI HID OVTI5675) behind an INT3472 discrete PMIC controller. The INT3472 _DSM returns GPIO type 0x10 for one of the pins, which controls the DOVDD (digital I/O power) regulator enable. Type 0x10 is not currently handled by the driver, causing the GPIO to be ignored with a warning. Add INT3472_GPIO_TYPE_DOVDD (0x10) and handle it as a regulator with con_id "dovdd" to match the supply name used by sensor drivers (e.g. ov5675). Also increase GPIO_SUPPLY_NAME_LENGTH from 5 to 6 to accommodate the "dovdd" name (5 chars + null terminator). Signed-off-by: Leif Skunberg Reviewed-by: Hans de Goede Link: https://patch.msgid.link/20260210132129.17943-1-diamondback@cohunt.app Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- include/linux/platform_data/x86/int3472.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index b1b837583d54..dbe745dc88d5 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -26,6 +26,7 @@ #define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b #define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c #define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d +#define INT3472_GPIO_TYPE_DOVDD 0x10 #define INT3472_GPIO_TYPE_HANDSHAKE 0x12 #define INT3472_GPIO_TYPE_HOTPLUG_DETECT 0x13 @@ -33,8 +34,8 @@ #define INT3472_MAX_SENSOR_GPIOS 3 #define INT3472_MAX_REGULATORS 3 -/* E.g. "avdd\0" */ -#define GPIO_SUPPLY_NAME_LENGTH 5 +/* E.g. "dovdd\0" */ +#define GPIO_SUPPLY_NAME_LENGTH 6 /* 12 chars for acpi_dev_name() + "-", e.g. "ABCD1234:00-" */ #define GPIO_REGULATOR_NAME_LENGTH (12 + GPIO_SUPPLY_NAME_LENGTH) /* lower- and upper-case mapping */ -- cgit v1.2.3 From 551d44200152cb26f75d2ef990aeb6185b7e37fd Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 23 Feb 2026 09:33:08 -0800 Subject: default_gfp(): avoid using the "newfangled" __VA_OPT__ trick The default_gfp() helper that I added is not wrong, but it turns out that it causes unnecessary headaches for 'sparse' which doesn't support the use of __VA_OPT__ (introduced in C++20 and C23, and supported by gcc and clang for a long time). We do already use __VA_OPT__ in some other cases in the kernel (drm/xe and btrfs), but it has been fairly limited. Now it triggers for pretty much everything, and sparse ends up not working at all. We can use the traditional gcc ',##__VA_ARGS__' syntax instead: it may not be the "C standard" way and is slightly less natural in this context, but it is the traditional model for this and avoids the sparse problem. Reported-and-tested-by: Ricardo Ribalda Reported-and-tested-by: Richard Fitzgerald Reported-by: Ben Dooks Fixes: e19e1b480ac7 ("add default_gfp() helper macro and use it in the new *alloc_obj() helpers") Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2b30a0529d48..90536b2bc42e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -14,8 +14,8 @@ struct vm_area_struct; struct mempolicy; /* Helper macro to avoid gfp flags if they are the default one */ -#define __default_gfp(a,...) a -#define default_gfp(...) __default_gfp(__VA_ARGS__ __VA_OPT__(,) GFP_KERNEL) +#define __default_gfp(a,b,...) b +#define default_gfp(...) __default_gfp(,##__VA_ARGS__,GFP_KERNEL) /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) -- cgit v1.2.3 From eb9549346f7578eda3755683ac2cfb4d94c0675f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Feb 2026 13:17:44 +0100 Subject: mm: change vma_alloc_folio_noprof() macro to inline function In a few rare configurations with extra warnings eanbled, the new drm_pagemap_migrate_populate_ram_pfn() calls vma_alloc_folio_noprof() but that does not use all the arguments, leading to a harmless warning: drivers/gpu/drm/drm_pagemap.c: In function 'drm_pagemap_migrate_populate_ram_pfn': drivers/gpu/drm/drm_pagemap.c:701:63: error: parameter 'addr' set but not used [-Werror=unused-but-set-parameter=] 701 | unsigned long addr) | ~~~~~~~~~~~~~~^~~~ Replace the macro with an inline function so the compiler can see how the argument would be used, but is still able to optimize out the assignments. Link: https://lkml.kernel.org/r/20260216121751.2378374-1-arnd@kernel.org Signed-off-by: Arnd Bergmann Reviewed-by: Lorenzo Stoakes Acked-by: Zi Yan Reviewed-by: Suren Baghdasaryan Cc: Alexei Starovoitov Cc: Brendan Jackman Cc: David Hildenbrand Cc: Johannes Weiner Cc: Joshua Hahn Cc: Kefeng Wang Cc: Liam Howlett Cc: Michal Hocko Cc: Mike Rapoport Cc: Shakeel Butt Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/gfp.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2b30a0529d48..f82d74a77cad 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde { return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ - folio_alloc_noprof(gfp, order) +static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, + struct vm_area_struct *vma, unsigned long addr) +{ + return folio_alloc_noprof(gfp, order); +} #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) -- cgit v1.2.3 From f85b1c6af5bc3872f994df0a5688c1162de07a62 Mon Sep 17 00:00:00 2001 From: "Pratyush Yadav (Google)" Date: Mon, 16 Feb 2026 14:22:19 +0100 Subject: liveupdate: luo_file: remember retrieve() status LUO keeps track of successful retrieve attempts on a LUO file. It does so to avoid multiple retrievals of the same file. Multiple retrievals cause problems because once the file is retrieved, the serialized data structures are likely freed and the file is likely in a very different state from what the code expects. The retrieve boolean in struct luo_file keeps track of this, and is passed to the finish callback so it knows what work was already done and what it has left to do. All this works well when retrieve succeeds. When it fails, luo_retrieve_file() returns the error immediately, without ever storing anywhere that a retrieve was attempted or what its error code was. This results in an errored LIVEUPDATE_SESSION_RETRIEVE_FD ioctl to userspace, but nothing prevents it from trying this again. The retry is problematic for much of the same reasons listed above. The file is likely in a very different state than what the retrieve logic normally expects, and it might even have freed some serialization data structures. Attempting to access them or free them again is going to break things. For example, if memfd managed to restore 8 of its 10 folios, but fails on the 9th, a subsequent retrieve attempt will try to call kho_restore_folio() on the first folio again, and that will fail with a warning since it is an invalid operation. Apart from the retry, finish() also breaks. Since on failure the retrieved bool in luo_file is never touched, the finish() call on session close will tell the file handler that retrieve was never attempted, and it will try to access or free the data structures that might not exist, much in the same way as the retry attempt. There is no sane way of attempting the retrieve again. Remember the error retrieve returned and directly return it on a retry. Also pass this status code to finish() so it can make the right decision on the work it needs to do. This is done by changing the bool to an integer. A value of 0 means retrieve was never attempted, a positive value means it succeeded, and a negative value means it failed and the error code is the value. Link: https://lkml.kernel.org/r/20260216132221.987987-1-pratyush@kernel.org Fixes: 7c722a7f44e0 ("liveupdate: luo_file: implement file systems callbacks") Signed-off-by: Pratyush Yadav (Google) Reviewed-by: Mike Rapoport (Microsoft) Cc: Pasha Tatashin Cc: Signed-off-by: Andrew Morton --- include/linux/liveupdate.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h index fe82a6c3005f..dd11fdc76a5f 100644 --- a/include/linux/liveupdate.h +++ b/include/linux/liveupdate.h @@ -23,8 +23,11 @@ struct file; /** * struct liveupdate_file_op_args - Arguments for file operation callbacks. * @handler: The file handler being called. - * @retrieved: The retrieve status for the 'can_finish / finish' - * operation. + * @retrieve_status: The retrieve status for the 'can_finish / finish' + * operation. A value of 0 means the retrieve has not been + * attempted, a positive value means the retrieve was + * successful, and a negative value means the retrieve failed, + * and the value is the error code of the call. * @file: The file object. For retrieve: [OUT] The callback sets * this to the new file. For other ops: [IN] The caller sets * this to the file being operated on. @@ -40,7 +43,7 @@ struct file; */ struct liveupdate_file_op_args { struct liveupdate_file_handler *handler; - bool retrieved; + int retrieve_status; struct file *file; u64 serialized_data; void *private_data; -- cgit v1.2.3 From 4b44cbb264d0ed3f2f2bc2659db6ce45882f4670 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 24 Feb 2026 15:24:52 -0800 Subject: overflow: Make sure size helpers are always inlined With kmalloc_obj() performing implicit size calculations, the embedded size_mul() calls, while marked inline, were not always being inlined. I noticed a couple places where allocations were making a call out for things that would otherwise be compile-time calculated. Force the compilers to always inline these calculations. Reviewed-by: Gustavo A. R. Silva Link: https://patch.msgid.link/20260224232451.work.614-kees@kernel.org Signed-off-by: Kees Cook --- include/linux/overflow.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/overflow.h b/include/linux/overflow.h index eddd987a8513..a8cb6319b4fb 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -42,7 +42,7 @@ * both the type-agnostic benefits of the macros while also being able to * enforce that the return value is, in fact, checked. */ -static inline bool __must_check __must_check_overflow(bool overflow) +static __always_inline bool __must_check __must_check_overflow(bool overflow) { return unlikely(overflow); } @@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow) * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_mul(size_t factor1, size_t factor2) +static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; @@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_add(size_t addend1, size_t addend2) +static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; @@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2) * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). * The lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) +static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; -- cgit v1.2.3 From 28aaa9c39945b7925a1cc1d513c8f21ed38f5e4f Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 10:43:55 +0100 Subject: kthread: consolidate kthread exit paths to prevent use-after-free Guillaume reported crashes via corrupted RCU callback function pointers during KUnit testing. The crash was traced back to the pidfs rhashtable conversion which replaced the 24-byte rb_node with an 8-byte rhash_head in struct pid, shrinking it from 160 to 144 bytes. struct kthread (without CONFIG_BLK_CGROUP) is also 144 bytes. With CONFIG_SLAB_MERGE_DEFAULT and SLAB_HWCACHE_ALIGN both round up to 192 bytes and share the same slab cache. struct pid.rcu.func and struct kthread.affinity_node both sit at offset 0x78. When a kthread exits via make_task_dead() it bypasses kthread_exit() and misses the affinity_node cleanup. free_kthread_struct() frees the memory while the node is still linked into the global kthread_affinity_list. A subsequent list_del() by another kthread writes through dangling list pointers into the freed and reused memory, corrupting the pid's rcu.func pointer. Instead of patching free_kthread_struct() to handle the missed cleanup, consolidate all kthread exit paths. Turn kthread_exit() into a macro that calls do_exit() and add kthread_do_exit() which is called from do_exit() for any task with PF_KTHREAD set. This guarantees that kthread-specific cleanup always happens regardless of the exit path - make_task_dead(), direct do_exit(), or kthread_exit(). Replace __to_kthread() with a new tsk_is_kthread() accessor in the public header. Export do_exit() since module code using the kthread_exit() macro now needs it directly. Reported-by: Guillaume Tucker Tested-by: Guillaume Tucker Tested-by: Mark Brown Tested-by: David Gow Cc: Link: https://lore.kernel.org/all/20260224-mittlerweile-besessen-2738831ae7f6@brauner Co-developed-by: Linus Torvalds Fixes: 4d13f4304fa4 ("kthread: Implement preferred affinity") Signed-off-by: Linus Torvalds Signed-off-by: Christian Brauner --- include/linux/kthread.h | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c92c1149ee6e..a01a474719a7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -7,6 +7,24 @@ struct mm_struct; +/* opaque kthread data */ +struct kthread; + +/* + * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will + * always remain a kthread. For kthreads p->worker_private always + * points to a struct kthread. For tasks that are not kthreads + * p->worker_private is used to point to other things. + * + * Return NULL for any task that is not a kthread. + */ +static inline struct kthread *tsk_is_kthread(struct task_struct *p) +{ + if (p->flags & PF_KTHREAD) + return p->worker_private; + return NULL; +} + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_exit(long result) __noreturn; +#define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); +void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; -- cgit v1.2.3 From f3ec502b6755a3bfb12c1c47025ef989ff9efc72 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Wed, 25 Feb 2026 08:34:07 -0800 Subject: mm/slab: mark alloc tags empty for sheaves allocated with __GFP_NO_OBJ_EXT alloc_empty_sheaf() allocates sheaves from SLAB_KMALLOC caches using __GFP_NO_OBJ_EXT to avoid recursion, however it does not mark their allocation tags empty before freeing, which results in a warning when CONFIG_MEM_ALLOC_PROFILING_DEBUG is set. Fix this by marking allocation tags for such sheaves as empty. The problem was technically introduced in commit 4c0a17e28340 but only becomes possible to hit with commit 913ffd3a1bf5. Fixes: 4c0a17e28340 ("slab: prevent recursive kmalloc() in alloc_empty_sheaf()") Fixes: 913ffd3a1bf5 ("slab: handle kmalloc sheaves bootstrap") Reported-by: David Wang <00107082@163.com> Closes: https://lore.kernel.org/all/20260223155128.3849-1-00107082@163.com/ Analyzed-by: Harry Yoo Signed-off-by: Suren Baghdasaryan Reviewed-by: Harry Yoo Tested-by: Harry Yoo Tested-by: David Wang <00107082@163.com> Link: https://patch.msgid.link/20260225163407.2218712-1-surenb@google.com Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/gfp_types.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 814bb2892f99..6c75df30a281 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -139,6 +139,8 @@ enum { * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. * * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. + * mark_obj_codetag_empty() should be called upon freeing for objects allocated + * with this flag to indicate that their NULL tags are expected and normal. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) -- cgit v1.2.3 From 2b351ea42820a7ecc2e8305724536512984f4419 Mon Sep 17 00:00:00 2001 From: Sanjay Chitroda Date: Thu, 26 Feb 2026 11:17:12 +0530 Subject: mm/slub: drop duplicate kernel-doc for ksize() The implementation of ksize() was updated with kernel-doc by commit fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c") However, the public header still contains a kernel-doc comment attached to the ksize() prototype. Having documentation both in the header and next to the implementation causes Sphinx to treat the function as being documented twice, resulting in the warning: WARNING: Duplicate C declaration, also defined at core-api/mm-api:521 Declaration is '.. c:function:: size_t ksize(const void *objp)' Kernel-doc guidelines recommend keeping the documentation with the function implementation. Therefore remove the redundant kernel-doc block from include/linux/slab.h so that the implementation in slub.c remains the canonical source for documentation. No functional change. Fixes: fab0694646d7 ("mm/slab: move [__]ksize and slab_ksize() to mm/slub.c") Signed-off-by: Sanjay Chitroda Link: https://patch.msgid.link/20260226054712.3610744-1-sanjayembedded@gmail.com Signed-off-by: Vlastimil Babka (SUSE) --- include/linux/slab.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index a5a5e4108ae5..15a60b501b95 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) -/** - * ksize - Report actual allocation size of associated object - * - * @objp: Pointer returned from a prior kmalloc()-family allocation. - * - * This should not be used for writing beyond the originally requested - * allocation size. Either use krealloc() or round up the allocation size - * with kmalloc_size_roundup() prior to allocation. If this is used to - * access beyond the originally requested allocation size, UBSAN_BOUNDS - * and/or FORTIFY_SOURCE may trip, since they only know about the - * originally allocated size via the __alloc_size attribute. - */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK -- cgit v1.2.3 From 3350c2b3f2b8a3b985a020a4ef4f2f050a4b6a1d Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 25 Feb 2026 21:12:29 -0800 Subject: platform_data/mlxreg: mlxreg.h: fix all kernel-doc warnings MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the correct kernel-doc format & notation to eliminate kernel-doc warnings: Warning: include/linux/platform_data/mlxreg.h:24 Enum value 'MLX_WDT_TYPE1' not described in enum 'mlxreg_wdt_type' Warning: include/linux/platform_data/mlxreg.h:24 Enum value 'MLX_WDT_TYPE2' not described in enum 'mlxreg_wdt_type' Warning: include/linux/platform_data/mlxreg.h:24 Enum value 'MLX_WDT_TYPE3' not described in enum 'mlxreg_wdt_type' Warning: include/linux/platform_data/mlxreg.h:37 bad line: PHYs ready / unready state; Warning: include/linux/platform_data/mlxreg.h:153 struct member 'np' not described in 'mlxreg_core_data' Warning: include/linux/platform_data/mlxreg.h:153 struct member 'hpdev' not described in 'mlxreg_core_data' Signed-off-by: Randy Dunlap Link: https://patch.msgid.link/20260226051232.549537-1-rdunlap@infradead.org Reviewed-by: Ilpo Järvinen Signed-off-by: Ilpo Järvinen --- include/linux/platform_data/mlxreg.h | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index f6cca7a035c7..50b6be57da66 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -13,10 +13,10 @@ /** * enum mlxreg_wdt_type - type of HW watchdog * - * TYPE1 HW watchdog implementation exist in old systems. - * All new systems have TYPE2 HW watchdog. - * TYPE3 HW watchdog can exist on all systems with new CPLD. - * TYPE3 is selected by WD capability bit. + * @MLX_WDT_TYPE1: HW watchdog implementation in old systems. + * @MLX_WDT_TYPE2: All new systems have TYPE2 HW watchdog. + * @MLX_WDT_TYPE3: HW watchdog that can exist on all systems with new CPLD. + * TYPE3 is selected by WD capability bit. */ enum mlxreg_wdt_type { MLX_WDT_TYPE1, @@ -35,7 +35,7 @@ enum mlxreg_wdt_type { * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming * after hardware-firmware synchronization handshake; * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card - PHYs ready / unready state; + * PHYs ready / unready state; * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware * availability / unavailability for the ports on line card; * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive @@ -123,8 +123,8 @@ struct mlxreg_hotplug_device { * @reg_pwr: attribute power register; * @reg_ena: attribute enable register; * @mode: access mode; - * @np - pointer to node platform associated with attribute; - * @hpdev - hotplug device data; + * @np: pointer to node platform associated with attribute; + * @hpdev: hotplug device data; * @notifier: pointer to event notifier block; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; -- cgit v1.2.3 From e6b899f08066e744f89df16ceb782e06868bd148 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:50:09 +0100 Subject: nsfs: tighten permission checks for ns iteration ioctls Even privileged services should not necessarily be able to see other privileged service's namespaces so they can't leak information to each other. Use may_see_all_namespaces() helper that centralizes this policy until the nstree adapts. Link: https://patch.msgid.link/20260226-work-visibility-fixes-v1-1-d2c2853313bd@kernel.org Fixes: a1d220d9dafa ("nsfs: iterate through mount namespaces") Reviewed-by: Jeff Layton Cc: stable@kernel.org # v6.12+ Signed-off-by: Christian Brauner --- include/linux/ns_common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 825f5865bfc5..c8e227a3f9e2 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +bool may_see_all_namespaces(void); + static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); -- cgit v1.2.3 From 1df97a7453eec80c1912c2d0360290a3970a7671 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:01 -0800 Subject: bpf: Register dtor for freeing special fields There is a race window where BPF hash map elements can leak special fields if the program with access to the map value recreates these special fields between the check_and_free_fields done on the map value and its eventual return to the memory allocator. Several ways were explored prior to this patch, most notably [0] tried to use a poison value to reject attempts to recreate special fields for map values that have been logically deleted but still accessible to BPF programs (either while sitting in the free list or when reused). While this approach works well for task work, timers, wq, etc., it is harder to apply the idea to kptrs, which have a similar race and failure mode. Instead, we change bpf_mem_alloc to allow registering destructor for allocated elements, such that when they are returned to the allocator, any special fields created while they were accessible to programs in the mean time will be freed. If these values get reused, we do not free the fields again before handing the element back. The special fields thus may remain initialized while the map value sits in a free list. When bpf_mem_alloc is retired in the future, a similar concept can be introduced to kmalloc_nolock-backed kmem_cache, paired with the existing idea of a constructor. Note that the destructor registration happens in map_check_btf, after the BTF record is populated and (at that point) avaiable for inspection and duplication. Duplication is necessary since the freeing of embedded bpf_mem_alloc can be decoupled from actual map lifetime due to logic introduced to reduce the cost of rcu_barrier()s in mem alloc free path in 9f2c6e96c65e ("bpf: Optimize rcu_barrier usage between hash map and bpf_mem_alloc."). As such, once all callbacks are done, we must also free the duplicated record. To remove dependency on the bpf_map itself, also stash the key size of the map to obtain value from htab_elem long after the map is gone. [0]: https://lore.kernel.org/bpf/20260216131341.1285427-1-mykyta.yatsenko5@gmail.com Fixes: 14a324f6a67e ("bpf: Wire up freeing of referenced kptr") Fixes: 1bfbc267ec91 ("bpf: Enable bpf_timer and bpf_wq in any context") Reported-by: Alexei Starovoitov Tested-by: syzbot@syzkaller.appspotmail.com Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_mem_alloc.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index e45162ef59bb..4ce0d27f8ea2 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -14,6 +14,8 @@ struct bpf_mem_alloc { struct obj_cgroup *objcg; bool percpu; struct work_struct work; + void (*dtor_ctx_free)(void *ctx); + void *dtor_ctx; }; /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects. @@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg /* The percpu allocation with a specific unit size. */ int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, + void (*dtor)(void *obj, void *ctx), + void (*dtor_ctx_free)(void *ctx), + void *ctx); /* Check the allocation size for kmalloc equivalent allocator */ int bpf_mem_alloc_check_size(bool percpu, size_t size); -- cgit v1.2.3 From ae51772b1e94ba1d76db19085957dbccac189c1c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Fri, 27 Feb 2026 14:48:02 -0800 Subject: bpf: Lose const-ness of map in map_check_btf() BPF hash map may now use the map_check_btf() callback to decide whether to set a dtor on its bpf_mem_alloc or not. Unlike C++ where members can opt out of const-ness using mutable, we must lose the const qualifier on the callback such that we can avoid the ugly cast. Make the change and adjust all existing users, and lose the comment in hashtab.c. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20260227224806.646888-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- include/linux/bpf_local_storage.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b78b53198a2e..05b34a6355b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -124,7 +124,7 @@ struct bpf_map_ops { u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); - int (*map_check_btf)(const struct bpf_map *map, + int (*map_check_btf)(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); @@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map) map->ops->map_seq_show_elem; } -int map_check_no_btf(const struct bpf_map *map, +int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 85efa9772530..8157e8da61d4 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache); -int bpf_local_storage_map_check_btf(const struct bpf_map *map, +int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); -- cgit v1.2.3 From 76e954155b45294c502e3d3a9e15757c858ca55e Mon Sep 17 00:00:00 2001 From: Harishankar Vishwanathan Date: Fri, 27 Feb 2026 22:32:21 +0100 Subject: bpf: Introduce tnum_step to step through tnum's members This commit introduces tnum_step(), a function that, when given t, and a number z returns the smallest member of t larger than z. The number z must be greater or equal to the smallest member of t and less than the largest member of t. The first step is to compute j, a number that keeps all of t's known bits, and matches all unknown bits to z's bits. Since j is a member of the t, it is already a candidate for result. However, we want our result to be (minimally) greater than z. There are only two possible cases: (1) Case j <= z. In this case, we want to increase the value of j and make it > z. (2) Case j > z. In this case, we want to decrease the value of j while keeping it > z. (Case 1) j <= z t = xx11x0x0 z = 10111101 (189) j = 10111000 (184) ^ k (Case 1.1) Let's first consider the case where j < z. We will address j == z later. Since z > j, there had to be a bit position that was 1 in z and a 0 in j, beyond which all positions of higher significance are equal in j and z. Further, this position could not have been unknown in a, because the unknown positions of a match z. This position had to be a 1 in z and known 0 in t. Let k be position of the most significant 1-to-0 flip. In our example, k = 3 (starting the count at 1 at the least significant bit). Setting (to 1) the unknown bits of t in positions of significance smaller than k will not produce a result > z. Hence, we must set/unset the unknown bits at positions of significance higher than k. Specifically, we look for the next larger combination of 1s and 0s to place in those positions, relative to the combination that exists in z. We can achieve this by concatenating bits at unknown positions of t into an integer, adding 1, and writing the bits of that result back into the corresponding bit positions previously extracted from z. >From our example, considering only positions of significance greater than k: t = xx..x z = 10..1 + 1 ----- 11..0 This is the exact combination 1s and 0s we need at the unknown bits of t in positions of significance greater than k. Further, our result must only increase the value minimally above z. Hence, unknown bits in positions of significance smaller than k should remain 0. We finally have, result = 11110000 (240) (Case 1.2) Now consider the case when j = z, for example t = 1x1x0xxx z = 10110100 (180) j = 10110100 (180) Matching the unknown bits of the t to the bits of z yielded exactly z. To produce a number greater than z, we must set/unset the unknown bits in t, and *all* the unknown bits of t candidates for being set/unset. We can do this similar to Case 1.1, by adding 1 to the bits extracted from the masked bit positions of z. Essentially, this case is equivalent to Case 1.1, with k = 0. t = 1x1x0xxx z = .0.1.100 + 1 --------- .0.1.101 This is the exact combination of bits needed in the unknown positions of t. After recalling the known positions of t, we get result = 10110101 (181) (Case 2) j > z t = x00010x1 z = 10000010 (130) j = 10001011 (139) ^ k Since j > z, there had to be a bit position which was 0 in z, and a 1 in j, beyond which all positions of higher significance are equal in j and z. This position had to be a 0 in z and known 1 in t. Let k be the position of the most significant 0-to-1 flip. In our example, k = 4. Because of the 0-to-1 flip at position k, a member of t can become greater than z if the bits in positions greater than k are themselves >= to z. To make that member *minimally* greater than z, the bits in positions greater than k must be exactly = z. Hence, we simply match all of t's unknown bits in positions more significant than k to z's bits. In positions less significant than k, we set all t's unknown bits to 0 to retain minimality. In our example, in positions of greater significance than k (=4), t=x000. These positions are matched with z (1000) to produce 1000. In positions of lower significance than k, t=10x1. All unknown bits are set to 0 to produce 1001. The final result is: result = 10001001 (137) This concludes the computation for a result > z that is a member of t. The procedure for tnum_step() in this commit implements the idea described above. As a proof of correctness, we verified the algorithm against a logical specification of tnum_step. The specification asserts the following about the inputs t, z and output res that: 1. res is a member of t, and 2. res is strictly greater than z, and 3. there does not exist another value res2 such that 3a. res2 is also a member of t, and 3b. res2 is greater than z 3c. res2 is smaller than res We checked the implementation against this logical specification using an SMT solver. The verification formula in SMTLIB format is available at [1]. The verification returned an "unsat": indicating that no input assignment exists for which the implementation and the specification produce different outputs. In addition, we also automatically generated the logical encoding of the C implementation using Agni [2] and verified it against the same specification. This verification also returned an "unsat", confirming that the implementation is equivalent to the specification. The formula for this check is also available at [3]. Link: https://pastebin.com/raw/2eRWbiit [1] Link: https://github.com/bpfverif/agni [2] Link: https://pastebin.com/raw/EztVbBJ2 [3] Co-developed-by: Srinivas Narayana Signed-off-by: Srinivas Narayana Co-developed-by: Santosh Nagarakatte Signed-off-by: Santosh Nagarakatte Signed-off-by: Harishankar Vishwanathan Link: https://lore.kernel.org/r/93fdf71910411c0f19e282ba6d03b4c65f9c5d73.1772225741.git.paul.chaignon@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/tnum.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index fa4654ffb621..ca2cfec8de08 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a) return !(tnum_subreg(a)).mask; } +/* Returns the smallest member of t larger than z */ +u64 tnum_step(struct tnum t, u64 z); + #endif /* _LINUX_TNUM_H */ -- cgit v1.2.3 From 15fba71533bcdfaa8eeba69a5a5a2927afdf664a Mon Sep 17 00:00:00 2001 From: Valentin Spreckels Date: Thu, 26 Feb 2026 20:54:09 +0100 Subject: net: usb: r8152: add TRENDnet TUC-ET2G The TRENDnet TUC-ET2G is a RTL8156 based usb ethernet adapter. Add its vendor and product IDs. Signed-off-by: Valentin Spreckels Link: https://patch.msgid.link/20260226195409.7891-2-valentin@spreckels.dev Signed-off-by: Jakub Kicinski --- include/linux/usb/r8152.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); -- cgit v1.2.3 From 407fd8b8d8cce03856aa67329715de48b254b529 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 11 Feb 2026 19:03:03 +0100 Subject: KVM: remove CONFIG_KVM_GENERIC_MMU_NOTIFIER All architectures now use MMU notifier for KVM page table management. Remove the Kconfig symbol and the code that is used when it is disabled. Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dde605cb894e..34759a262b28 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,7 +253,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { unsigned long attributes; }; @@ -275,7 +274,6 @@ struct kvm_gfn_range { bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -#endif enum { OUTSIDE_GUEST_MODE, @@ -849,13 +847,12 @@ struct kvm { struct hlist_head irq_ack_notifier_list; #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; -#endif + struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; @@ -2118,7 +2115,6 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) @@ -2196,7 +2192,6 @@ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } -#endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -- cgit v1.2.3 From b570f37a2ce480be26c665345c5514686a8a0274 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Date: Tue, 10 Feb 2026 12:56:53 +0100 Subject: mm: Fix a hmm_range_fault() livelock / starvation problem MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If hmm_range_fault() fails a folio_trylock() in do_swap_page, trying to acquire the lock of a device-private folio for migration, to ram, the function will spin until it succeeds grabbing the lock. However, if the process holding the lock is depending on a work item to be completed, which is scheduled on the same CPU as the spinning hmm_range_fault(), that work item might be starved and we end up in a livelock / starvation situation which is never resolved. This can happen, for example if the process holding the device-private folio lock is stuck in migrate_device_unmap()->lru_add_drain_all() sinc lru_add_drain_all() requires a short work-item to be run on all online cpus to complete. A prerequisite for this to happen is: a) Both zone device and system memory folios are considered in migrate_device_unmap(), so that there is a reason to call lru_add_drain_all() for a system memory folio while a folio lock is held on a zone device folio. b) The zone device folio has an initial mapcount > 1 which causes at least one migration PTE entry insertion to be deferred to try_to_migrate(), which can happen after the call to lru_add_drain_all(). c) No or voluntary only preemption. This all seems pretty unlikely to happen, but indeed is hit by the "xe_exec_system_allocator" igt test. Resolve this by waiting for the folio to be unlocked if the folio_trylock() fails in do_swap_page(). Rename migration_entry_wait_on_locked() to softleaf_entry_wait_unlock() and update its documentation to indicate the new use-case. Future code improvements might consider moving the lru_add_drain_all() call in migrate_device_unmap() to be called *after* all pages have migration entries inserted. That would eliminate also b) above. v2: - Instead of a cond_resched() in hmm_range_fault(), eliminate the problem by waiting for the folio to be unlocked in do_swap_page() (Alistair Popple, Andrew Morton) v3: - Add a stub migration_entry_wait_on_locked() for the !CONFIG_MIGRATION case. (Kernel Test Robot) v4: - Rename migrate_entry_wait_on_locked() to softleaf_entry_wait_on_locked() and update docs (Alistair Popple) v5: - Add a WARN_ON_ONCE() for the !CONFIG_MIGRATION version of softleaf_entry_wait_on_locked(). - Modify wording around function names in the commit message (Andrew Morton) Suggested-by: Alistair Popple Fixes: 1afaeb8293c9 ("mm/migrate: Trylock device page in do_swap_page") Cc: Ralph Campbell Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: Andrew Morton Cc: Matthew Brost Cc: John Hubbard Cc: Alistair Popple Cc: linux-mm@kvack.org Cc: Signed-off-by: Thomas Hellström Cc: # v6.15+ Reviewed-by: John Hubbard #v3 Reviewed-by: Alistair Popple Link: https://patch.msgid.link/20260210115653.92413-1-thomas.hellstrom@linux.intel.com (cherry picked from commit a69d1ab971a624c6f112cea61536569d579c3215) Signed-off-by: Rodrigo Vivi --- include/linux/migrate.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 26ca00c325d9..d5af2b7f577b 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -65,7 +65,7 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list); int migrate_huge_page_move_mapping(struct address_space *mapping, struct folio *dst, struct folio *src); -void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) +void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, @@ -97,6 +97,14 @@ static inline int set_movable_ops(const struct movable_operations *ops, enum pag return -ENOSYS; } +static inline void softleaf_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl) + __releases(ptl) +{ + WARN_ON_ONCE(1); + + spin_unlock(ptl); +} + #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING -- cgit v1.2.3 From af4e9ef3d78420feb8fe58cd9a1ab80c501b3c08 Mon Sep 17 00:00:00 2001 From: David Laight Date: Mon, 2 Mar 2026 13:27:51 +0000 Subject: uaccess: Fix scoped_user_read_access() for 'pointer to const' If a 'const struct foo __user *ptr' is used for the address passed to scoped_user_read_access() then you get a warning/error uaccess.h:691:1: error: initialization discards 'const' qualifier from pointer target type [-Werror=discarded-qualifiers] for the void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl) assignment. Fix by using 'auto' for both _tmpptr and the redeclaration of uptr. Replace the CLASS() with explicit __cleanup() functions on uptr. Fixes: e497310b4ffb ("uaccess: Provide scoped user access regions") Signed-off-by: David Laight Reviewed-and-tested-by: Christophe Leroy (CS GROUP) Signed-off-by: Linus Torvalds --- include/linux/uaccess.h | 54 ++++++++++++++++++------------------------------- 1 file changed, 20 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..809e4f7dfdbd 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { } /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) -#define user_rw_access_end() user_access_end() /* Scoped user access */ -#define USER_ACCESS_GUARD(_mode) \ -static __always_inline void __user * \ -class_user_##_mode##_begin(void __user *ptr) \ -{ \ - return ptr; \ -} \ - \ -static __always_inline void \ -class_user_##_mode##_end(void __user *ptr) \ -{ \ - user_##_mode##_access_end(); \ -} \ - \ -DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ - class_user_##_mode##_end(_T), \ - class_user_##_mode##_begin(ptr), void __user *ptr) \ - \ -static __always_inline class_user_##_mode##_access_t \ -class_user_##_mode##_access_ptr(void __user *scope) \ -{ \ - return scope; \ -} -USER_ACCESS_GUARD(read) -USER_ACCESS_GUARD(write) -USER_ACCESS_GUARD(rw) -#undef USER_ACCESS_GUARD +/* Cleanup wrapper functions */ +static __always_inline void __scoped_user_read_access_end(const void *p) +{ + user_read_access_end(); +}; +static __always_inline void __scoped_user_write_access_end(const void *p) +{ + user_write_access_end(); +}; +static __always_inline void __scoped_user_rw_access_end(const void *p) +{ + user_access_end(); +}; /** * __scoped_user_access_begin - Start a scoped user access @@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw) * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ -#define __scoped_user_access(mode, uptr, size, elbl) \ -for (bool done = false; !done; done = true) \ - for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ - !done; done = true) \ - for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ - /* Force modified pointer usage within the scope */ \ - for (const typeof(uptr) uptr = _tmpptr; !done; done = true) +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ + _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size -- cgit v1.2.3 From 710f5c76580306cdb9ec51fac8fcf6a8faff7821 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 27 Feb 2026 17:26:03 +0000 Subject: indirect_call_wrapper: do not reevaluate function pointer We have an increasing number of READ_ONCE(xxx->function) combined with INDIRECT_CALL_[1234]() helpers. Unfortunately this forces INDIRECT_CALL_[1234]() to read xxx->function many times, which is not what we wanted. Fix these macros so that xxx->function value is not reloaded. $ scripts/bloat-o-meter -t vmlinux.0 vmlinux add/remove: 0/0 grow/shrink: 1/65 up/down: 122/-1084 (-962) Function old new delta ip_push_pending_frames 59 181 +122 ip6_finish_output 687 681 -6 __udp_enqueue_schedule_skb 1078 1072 -6 ioam6_output 2319 2312 -7 xfrm4_rcv_encap_finish2 64 56 -8 xfrm4_output 297 289 -8 vrf_ip_local_out 278 270 -8 vrf_ip6_local_out 278 270 -8 seg6_input_finish 64 56 -8 rpl_output 700 692 -8 ipmr_forward_finish 124 116 -8 ip_forward_finish 143 135 -8 ip6mr_forward2_finish 100 92 -8 ip6_forward_finish 73 65 -8 input_action_end_bpf 1091 1083 -8 dst_input 52 44 -8 __xfrm6_output 801 793 -8 __xfrm4_output 83 75 -8 bpf_input 500 491 -9 __tcp_check_space 530 521 -9 input_action_end_dt6 291 280 -11 vti6_tnl_xmit 1634 1622 -12 bpf_xmit 1203 1191 -12 rpl_input 497 483 -14 rawv6_send_hdrinc 1355 1341 -14 ndisc_send_skb 1030 1016 -14 ipv6_srh_rcv 1377 1363 -14 ip_send_unicast_reply 1253 1239 -14 ip_rcv_finish 226 212 -14 ip6_rcv_finish 300 286 -14 input_action_end_x_core 205 191 -14 input_action_end_x 355 341 -14 input_action_end_t 205 191 -14 input_action_end_dx6_finish 127 113 -14 input_action_end_dx4_finish 373 359 -14 input_action_end_dt4 426 412 -14 input_action_end_core 186 172 -14 input_action_end_b6_encap 292 278 -14 input_action_end_b6 198 184 -14 igmp6_send 1332 1318 -14 ip_sublist_rcv 864 848 -16 ip6_sublist_rcv 1091 1075 -16 ipv6_rpl_srh_rcv 1937 1920 -17 xfrm_policy_queue_process 1246 1228 -18 seg6_output_core 903 885 -18 mld_sendpack 856 836 -20 NF_HOOK 756 736 -20 vti_tunnel_xmit 1447 1426 -21 input_action_end_dx6 664 642 -22 input_action_end 1502 1480 -22 sock_sendmsg_nosec 134 111 -23 ip6mr_forward2 388 364 -24 sock_recvmsg_nosec 134 109 -25 seg6_input_core 836 810 -26 ip_send_skb 172 146 -26 ip_local_out 140 114 -26 ip6_local_out 140 114 -26 __sock_sendmsg 162 136 -26 __ip_queue_xmit 1196 1170 -26 __ip_finish_output 405 379 -26 ipmr_queue_fwd_xmit 373 346 -27 sock_recvmsg 173 145 -28 ip6_xmit 1635 1607 -28 xfrm_output_resume 1418 1389 -29 ip_build_and_send_pkt 625 591 -34 dst_output 504 432 -72 Total: Before=25217686, After=25216724, chg -0.00% Fixes: 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up indirect calls of builtin") Signed-off-by: Eric Dumazet Reviewed-by: Kuniyuki Iwashima Link: https://patch.msgid.link/20260227172603.1700433-1-edumazet@google.com Signed-off-by: Paolo Abeni --- include/linux/indirect_call_wrapper.h | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f -- cgit v1.2.3 From 9de68394a61528d40f575c3e6719cc75c56f62c3 Mon Sep 17 00:00:00 2001 From: Danilo Krummrich Date: Mon, 2 Mar 2026 01:25:44 +0100 Subject: Revert "driver core: enforce device_lock for driver_match_device()" This reverts commit dc23806a7c47 ("driver core: enforce device_lock for driver_match_device()") and commit 289b14592cef ("driver core: fix inverted "locked" suffix of driver_match_device()"). While technically correct, there is a major downside to this approach: When a device is already present in the system and a driver is registered on the same bus, we iterate over all devices registered on this bus to see if one of them matches. If we come across an already bound one where the corresponding driver crashed while holding the device lock (e.g. in probe()) we can't make any progress anymore. However, drivers are typically the least tested code in the kernel and hence it is a case that is likely to happen regularly. Besides hurting developer ergonomics, it potentially decreases chances of shutting things down cleanly and obtaining logs in production environments as well [1]. This came up in the context of a firewire bug, which only in combination with the reverted commit, caused the machine to hang [2]. Additionally, it was observed in [3]. Thus, revert commit dc23806a7c47 ("driver core: enforce device_lock for driver_match_device()") and add a brief note clarifying that an implementer of struct bus_type must not expect match() to be called with the device lock held. Link: https://lore.kernel.org/driver-core/DGRGTIRHA62X.3RY09D9SOK77P@kernel.org/ [1] Link: https://lore.kernel.org/all/67f655bb-4d81-4609-b008-68d200255dd2@davidgow.net/ [2] Link: https://lore.kernel.org/lkml/CALbr=LZ4v7N=tO1vgOsyj9AS+XuNbn6kG-QcF+PacdMjSo0iyw@mail.gmail.com/ [3] Reported-by: Linus Torvalds Closes: https://lore.kernel.org/driver-core/CAHk-=wgJ_L1C=HjcYJotg_zrZEmiLFJaoic+PWthjuQrutrfJw@mail.gmail.com/ Reviewed-by: Gui-Dong Han Acked-by: Greg Kroah-Hartman Link: https://patch.msgid.link/20260302002545.19389-1-dakr@kernel.org [ Add additional Link: reference. - Danilo ] Signed-off-by: Danilo Krummrich --- include/linux/device/bus.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 99c3c83ea520..63de5f053c33 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -35,6 +35,8 @@ struct fwnode_handle; * otherwise. It may also return error code if determining that * the driver supports the device is not possible. In case of * -EPROBE_DEFER it will queue the device for deferred probing. + * Note: This callback may be invoked with or without the device + * lock held. * @uevent: Called when a device is added, removed, or a few other things * that generate uevents to add the environment variables. * @probe: Called when a new device or driver add to this bus, and callback -- cgit v1.2.3 From e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e Mon Sep 17 00:00:00 2001 From: Qing Wang Date: Fri, 27 Feb 2026 10:58:42 +0800 Subject: tracing: Fix WARN_ON in tracing_buffers_mmap_close When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON. Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork. Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Vincent Donnefort Cc: Lorenzo Stoakes Link: https://patch.msgid.link/20260227025842.1085206-1-wangqing7171@gmail.com Fixes: cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer") Reported-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=3b5dd2030fe08afdf65d Tested-by: syzbot+3b5dd2030fe08afdf65d@syzkaller.appspotmail.com Signed-off-by: Qing Wang Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 876358cfe1b1..d862fa610270 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); int ring_buffer_map(struct trace_buffer *buffer, int cpu, struct vm_area_struct *vma); +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu); int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ -- cgit v1.2.3 From 2d28ed588f8d7d0d41b0a4fad7f0d05e4bbf1797 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 24 Feb 2026 16:24:34 -0800 Subject: Revert "ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()" This change swapped out mod_node_page_state for lruvec_stat_add_folio. But, these two APIs are not interchangeable: the lruvec version also increments memcg stats, in addition to "global" pgdat stats. So after this change, the "pagetables" memcg stat in memory.stat always yields "0", which is a userspace visible regression. I tried to look for a refactor where we add a variant of lruvec_stat_mod_folio which takes a pgdat and a memcg instead of a folio, to try to adhere to the spirit of the original patch. But at the end of the day this just means we have to call folio_memcg(ptdesc_folio(ptdesc)) anyway, which doesn't really accomplish much. This regression is visible in master as well as 6.18 stable, so CC stable too. Link: https://lkml.kernel.org/r/20260225002434.2953895-1-axelrasmussen@google.com Fixes: f0c92726e89f ("ptdesc: remove references to folios from __pagetable_ctor() and pagetable_dtor()") Signed-off-by: Axel Rasmussen Acked-by: Shakeel Butt Acked-by: Johannes Weiner Reviewed-by: Vishal Moola (Oracle) Cc: David Hildenbrand Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Roman Gushchin Cc: Muchun Song Cc: Signed-off-by: Andrew Morton --- include/linux/mm.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 5be3d8a8f806..abb4963c1f06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3514,26 +3514,21 @@ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} #endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */ -static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc) -{ - return compound_nr(ptdesc_page(ptdesc)); -} - static inline void __pagetable_ctor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); - __SetPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc)); + __folio_set_pgtable(folio); + lruvec_stat_add_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor(struct ptdesc *ptdesc) { - pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags)); + struct folio *folio = ptdesc_folio(ptdesc); ptlock_free(ptdesc); - __ClearPageTable(ptdesc_page(ptdesc)); - mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc)); + __folio_clear_pgtable(folio); + lruvec_stat_sub_folio(folio, NR_PAGETABLE); } static inline void pagetable_dtor_free(struct ptdesc *ptdesc) -- cgit v1.2.3 From 7392f8e4ea632622b2cd2086675ba022db238b3a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Mar 2026 16:52:29 -0800 Subject: uaccess: correct kernel-doc parameter format Use the correct kernel-doc function parameter format to avoid kernel-doc warnings: Warning: include/linux/uaccess.h:814 function parameter 'uptr' not described in 'scoped_user_rw_access_size' Warning: include/linux/uaccess.h:826 function parameter 'uptr' not described in 'scoped_user_rw_access' Link: https://lkml.kernel.org/r/20260302005229.3471955-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton --- include/linux/uaccess.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..001cfef21b61 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -806,7 +806,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access_size - Start a scoped user read/write access with given size - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @size: Size of the access starting from @uptr * @elbl: Error label to goto when the access region is rejected * @@ -817,7 +817,7 @@ for (bool done = false; !done; done = true) \ /** * scoped_user_rw_access - Start a scoped user read/write access - * @uptr Pointer to the user space address to read from and write to + * @uptr: Pointer to the user space address to read from and write to * @elbl: Error label to goto when the access region is rejected * * The size of the access starting from @uptr is determined via sizeof(*@uptr)). -- cgit v1.2.3 From 599b4e290c8766b19378d85d4310c6ec8f90ade4 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Mar 2026 16:52:22 -0800 Subject: mm/mmu_notifier: clean up mmu_notifier.h kernel-doc Eliminate kernel-doc warnings in mmu_notifier.h: - add a missing struct short description - use the correct format for function parameters - add missing function return comment sections Warning: include/linux/mmu_notifier.h:236 missing initial short description on line: * struct mmu_interval_notifier_ops Warning: include/linux/mmu_notifier.h:325 function parameter 'interval_sub' not described in 'mmu_interval_set_seq' Warning: include/linux/mmu_notifier.h:325 function parameter 'cur_seq' not described in 'mmu_interval_set_seq' Warning: include/linux/mmu_notifier.h:346 function parameter 'interval_sub' not described in 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:346 function parameter 'seq' not described in 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:346 No description found for return value of 'mmu_interval_read_retry' Warning: include/linux/mmu_notifier.h:370 function parameter 'interval_sub' not described in 'mmu_interval_check_retry' Warning: include/linux/mmu_notifier.h:370 function parameter 'seq' not described in 'mmu_interval_check_retry' Warning: include/linux/mmu_notifier.h:370 No description found for return value of 'mmu_interval_check_retry' Link: https://lkml.kernel.org/r/20260302005222.3470783-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reviewed-by: Jason Gunthorpe Cc: David Hildenbrand Cc: "Liam R. Howlett" Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Mike Rapoport Cc: Randy Dunlap Cc: Suren Baghdasaryan Cc: Vlastimil Babka Signed-off-by: Andrew Morton --- include/linux/mmu_notifier.h | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 07a2bbaf86e9..8450e18a87c2 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -234,7 +234,7 @@ struct mmu_notifier { }; /** - * struct mmu_interval_notifier_ops + * struct mmu_interval_notifier_ops - callback for range notification * @invalidate: Upon return the caller must stop using any SPTEs within this * range. This function can sleep. Return false only if sleeping * was required but mmu_notifier_range_blockable(range) is false. @@ -309,8 +309,8 @@ void mmu_interval_notifier_remove(struct mmu_interval_notifier *interval_sub); /** * mmu_interval_set_seq - Save the invalidation sequence - * @interval_sub - The subscription passed to invalidate - * @cur_seq - The cur_seq passed to the invalidate() callback + * @interval_sub: The subscription passed to invalidate + * @cur_seq: The cur_seq passed to the invalidate() callback * * This must be called unconditionally from the invalidate callback of a * struct mmu_interval_notifier_ops under the same lock that is used to call @@ -329,8 +329,8 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_read_retry - End a read side critical section against a VA range - * interval_sub: The subscription - * seq: The return of the paired mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the paired mmu_interval_read_begin() * * This MUST be called under a user provided lock that is also held * unconditionally by op->invalidate() when it calls mmu_interval_set_seq(). @@ -338,7 +338,7 @@ mmu_interval_set_seq(struct mmu_interval_notifier *interval_sub, * Each call should be paired with a single mmu_interval_read_begin() and * should be used to conclude the read side. * - * Returns true if an invalidation collided with this critical section, and + * Returns: true if an invalidation collided with this critical section, and * the caller should retry. */ static inline bool @@ -350,20 +350,21 @@ mmu_interval_read_retry(struct mmu_interval_notifier *interval_sub, /** * mmu_interval_check_retry - Test if a collision has occurred - * interval_sub: The subscription - * seq: The return of the matching mmu_interval_read_begin() + * @interval_sub: The subscription + * @seq: The return of the matching mmu_interval_read_begin() * * This can be used in the critical section between mmu_interval_read_begin() - * and mmu_interval_read_retry(). A return of true indicates an invalidation - * has collided with this critical region and a future - * mmu_interval_read_retry() will return true. - * - * False is not reliable and only suggests a collision may not have - * occurred. It can be called many times and does not have to hold the user - * provided lock. + * and mmu_interval_read_retry(). * * This call can be used as part of loops and other expensive operations to * expedite a retry. + * It can be called many times and does not have to hold the user + * provided lock. + * + * Returns: true indicates an invalidation has collided with this critical + * region and a future mmu_interval_read_retry() will return true. + * False is not reliable and only suggests a collision may not have + * occurred. */ static inline bool mmu_interval_check_retry(struct mmu_interval_notifier *interval_sub, -- cgit v1.2.3 From b824c3e16c1904bf80df489e293d1e3cbf98896d Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 2 Mar 2026 17:26:31 +0100 Subject: net: Provide a PREEMPT_RT specific check for netdev_queue::_xmit_lock After acquiring netdev_queue::_xmit_lock the number of the CPU owning the lock is recorded in netdev_queue::xmit_lock_owner. This works as long as the BH context is not preemptible. On PREEMPT_RT the softirq context is preemptible and without the softirq-lock it is possible to have multiple user in __dev_queue_xmit() submitting a skb on the same CPU. This is fine in general but this means also that the current CPU is recorded as netdev_queue::xmit_lock_owner. This in turn leads to the recursion alert and the skb is dropped. Instead checking the for CPU number, that owns the lock, PREEMPT_RT can check if the lockowner matches the current task. Add netif_tx_owned() which returns true if the current context owns the lock by comparing the provided CPU number with the recorded number. This resembles the current check by negating the condition (the current check returns true if the lock is not owned). On PREEMPT_RT use rt_mutex_owner() to return the lock owner and compare the current task against it. Use the new helper in __dev_queue_xmit() and netif_local_xmit_active() which provides a similar check. Update comments regarding pairing READ_ONCE(). Reported-by: Bert Karwatzki Closes: https://lore.kernel.org/all/20260216134333.412332-1-spasswolf@web.de Fixes: 3253cb49cbad4 ("softirq: Allow to drop the softirq-BKL lock on PREEMPT_RT") Signed-off-by: Sebastian Andrzej Siewior Reported-by: Bert Karwatzki Signed-off-by: Sebastian Andrzej Siewior Link: https://patch.msgid.link/20260302162631.uGUyIqDT@linutronix.de Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..67e25f6d15a4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; -- cgit v1.2.3 From 55f854dd5bdd8e19b936a00ef1f8d776ac32c7b0 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Wed, 4 Mar 2026 14:43:38 +0100 Subject: qmi_wwan: allow max_mtu above hard_mtu to control rx_urb_size Commit c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu") capped net->max_mtu to the device's hard_mtu in usbnet_probe(). While this correctly prevents oversized packets on standard USB network devices, it breaks the qmi_wwan driver. qmi_wwan relies on userspace (e.g. ModemManager) setting a large MTU on the wwan0 interface to configure rx_urb_size via usbnet_change_mtu(). QMI modems negotiate USB transfer sizes of 16,383 or 32,767 bytes, and the USB receive buffers must be sized accordingly. With max_mtu capped to hard_mtu (~1500 bytes), userspace can no longer raise the MTU, the receive buffers remain small, and download speeds drop from >300 Mbps to ~0.8 Mbps. Introduce a FLAG_NOMAXMTU driver flag that allows individual usbnet drivers to opt out of the max_mtu cap. Set this flag in qmi_wwan's driver_info structures to restore the previous behavior for QMI devices, while keeping the safety fix in place for all other usbnet drivers. Fixes: c7159e960f14 ("usbnet: limit max_mtu based on device's hard_mtu") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/CAPh3n803k8JcBPV5qEzUB-oKzWkAs-D5CU7z=Vd_nLRCr5ZqQg@mail.gmail.com/ Reported-by: Koen Vandeputte Tested-by: Daniele Palmas Signed-off-by: Laurent Vivier Link: https://patch.msgid.link/20260304134338.1785002-1-lvivier@redhat.com Signed-off-by: Jakub Kicinski --- include/linux/usb/usbnet.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0e84896e6ac..bbf799ccf3b3 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -132,6 +132,7 @@ struct driver_info { #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ #define FLAG_NOARP 0x8000 /* device can't do ARP */ +#define FLAG_NOMAXMTU 0x10000 /* allow max_mtu above hard_mtu */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); -- cgit v1.2.3 From 1954c4f012206147c34acda8da04f827aa7d3ee3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 7 Mar 2026 20:07:15 +0000 Subject: eventpoll: Convert epoll_put_uevent() to scoped user access Saves two function calls, and one stac/clac pair. stac/clac is rather expensive on older cpus like Zen 2. A synthetic network stress test gives a ~1.5% increase of pps on AMD Zen 2. Signed-off-by: Eric Dumazet Cc: Christophe Leroy Cc: Dave Hansen Cc: Kuniyuki Iwashima Signed-off-by: Linus Torvalds --- include/linux/eventpoll.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index ccb478eb174b..ea9ca0e4172a 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -82,11 +82,14 @@ static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { - if (__put_user(revents, &uevent->events) || - __put_user(data, &uevent->data)) - return NULL; - + scoped_user_write_access_size(uevent, sizeof(*uevent), efault) { + unsafe_put_user(revents, &uevent->events, efault); + unsafe_put_user(data, &uevent->data, efault); + } return uevent+1; + +efault: + return NULL; } #endif -- cgit v1.2.3 From 6f1a9140ecda3baba3d945b9a6155af4268aafc4 Mon Sep 17 00:00:00 2001 From: Weiming Shi Date: Sat, 7 Mar 2026 00:01:34 +0800 Subject: net: add xmit recursion limit to tunnel xmit functions Tunnel xmit functions (iptunnel_xmit, ip6tunnel_xmit) lack their own recursion limit. When a bond device in broadcast mode has GRE tap interfaces as slaves, and those GRE tunnels route back through the bond, multicast/broadcast traffic triggers infinite recursion between bond_xmit_broadcast() and ip_tunnel_xmit()/ip6_tnl_xmit(), causing kernel stack overflow. The existing XMIT_RECURSION_LIMIT (8) in the no-qdisc path is not sufficient because tunnel recursion involves route lookups and full IP output, consuming much more stack per level. Use a lower limit of 4 (IP_TUNNEL_RECURSION_LIMIT) to prevent overflow. Add recursion detection using dev_xmit_recursion helpers directly in iptunnel_xmit() and ip6tunnel_xmit() to cover all IPv4/IPv6 tunnel paths including UDP encapsulated tunnels (VXLAN, Geneve, etc.). Move dev_xmit_recursion helpers from net/core/dev.h to public header include/linux/netdevice.h so they can be used by tunnel code. BUG: KASAN: stack-out-of-bounds in blake2s.constprop.0+0xe7/0x160 Write of size 32 at addr ffff88810033fed0 by task kworker/0:1/11 Workqueue: mld mld_ifc_work Call Trace: __build_flow_key.constprop.0 (net/ipv4/route.c:515) ip_rt_update_pmtu (net/ipv4/route.c:1073) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:84) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) ip_finish_output2 (net/ipv4/ip_output.c:237) ip_output (net/ipv4/ip_output.c:438) iptunnel_xmit (net/ipv4/ip_tunnel_core.c:86) ip_tunnel_xmit (net/ipv4/ip_tunnel.c:847) gre_tap_xmit (net/ipv4/ip_gre.c:779) dev_hard_start_xmit (net/core/dev.c:3887) sch_direct_xmit (net/sched/sch_generic.c:347) __dev_queue_xmit (net/core/dev.c:4802) bond_dev_queue_xmit (drivers/net/bonding/bond_main.c:312) bond_xmit_broadcast (drivers/net/bonding/bond_main.c:5279) bond_start_xmit (drivers/net/bonding/bond_main.c:5530) dev_hard_start_xmit (net/core/dev.c:3887) __dev_queue_xmit (net/core/dev.c:4841) mld_sendpack mld_ifc_work process_one_work worker_thread Fixes: 745e20f1b626 ("net: add a recursion limit in xmit path") Reported-by: Xiang Mei Signed-off-by: Weiming Shi Link: https://patch.msgid.link/20260306160133.3852900-2-bestswngs@gmail.com Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67e25f6d15a4..ae269a2e7f4d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3576,17 +3576,49 @@ struct page_pool_bh { }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); +#define XMIT_RECURSION_LIMIT 8 + #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } + +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} #endif void __netif_schedule(struct Qdisc *q); -- cgit v1.2.3 From fa655a9ca73f7df32b8ca4d14ce11742f9578288 Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Tue, 3 Mar 2026 22:31:01 +0100 Subject: nvme: Annotate struct nvme_dhchap_key with __counted_by Add the __counted_by() compiler attribute to the flexible array member 'key' to improve access bounds-checking via CONFIG_UBSAN_BOUNDS and CONFIG_FORTIFY_SOURCE. Reviewed-by: Christoph Hellwig Signed-off-by: Thorsten Blum Signed-off-by: Keith Busch --- include/linux/nvme-auth.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h index 60e069a6757f..e75c29c51464 100644 --- a/include/linux/nvme-auth.h +++ b/include/linux/nvme-auth.h @@ -11,7 +11,7 @@ struct nvme_dhchap_key { size_t len; u8 hash; - u8 key[]; + u8 key[] __counted_by(len); }; u32 nvme_auth_get_seqnum(void); -- cgit v1.2.3 From 22fd7f7fed2ae3702f90d1985c326354e86b9c75 Mon Sep 17 00:00:00 2001 From: Muhammad Amirul Asyraf Mohamad Jamian Date: Thu, 5 Mar 2026 01:31:51 -0800 Subject: firmware: stratix10-svc: Add Multi SVC clients support In the current implementation, SVC client drivers such as socfpga-hwmon, intel_fcs, stratix10-soc, stratix10-rsu each send an SMC command that triggers a single thread in the stratix10-svc driver. Upon receiving a callback, the initiating client driver sends a stratix10-svc-done signal, terminating the thread without waiting for other pending SMC commands to complete. This leads to a timeout issue in the firmware SVC mailbox service when multiple client drivers send SMC commands concurrently. To resolve this issue, a dedicated thread is now created per channel. The stratix10-svc driver will support up to the number of channels defined by SVC_NUM_CHANNEL. Thread synchronization is handled using a mutex to prevent simultaneous issuance of SMC commands by multiple threads. SVC_NUM_DATA_IN_FIFO is reduced from 32 to 8, since each channel now has its own dedicated FIFO and the SDM processes commands one at a time. 8 entries per channel is sufficient while keeping the total aggregate capacity the same (4 channels x 8 = 32 entries). Additionally, a thread task is now validated before invoking kthread_stop when the user aborts, ensuring safe termination. Timeout values have also been adjusted to accommodate the increased load from concurrent client driver activity. Fixes: 7ca5ce896524 ("firmware: add Intel Stratix10 service layer driver") Cc: stable@vger.kernel.org Signed-off-by: Ang Tien Sung Signed-off-by: Fong, Yan Kei Signed-off-by: Muhammad Amirul Asyraf Mohamad Jamian Link: https://lore.kernel.org/all/20260305093151.2678-1-muhammad.amirul.asyraf.mohamad.jamian@altera.com Signed-off-by: Dinh Nguyen --- include/linux/firmware/intel/stratix10-svc-client.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index d290060f4c73..91013161e9db 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -68,12 +68,12 @@ * timeout value used in Stratix10 FPGA manager driver. * timeout value used in RSU driver */ -#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 300 -#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 720 -#define SVC_RSU_REQUEST_TIMEOUT_MS 300 +#define SVC_RECONFIG_REQUEST_TIMEOUT_MS 5000 +#define SVC_RECONFIG_BUFFER_TIMEOUT_MS 5000 +#define SVC_RSU_REQUEST_TIMEOUT_MS 2000 #define SVC_FCS_REQUEST_TIMEOUT_MS 2000 #define SVC_COMPLETED_TIMEOUT_MS 30000 -#define SVC_HWMON_REQUEST_TIMEOUT_MS 300 +#define SVC_HWMON_REQUEST_TIMEOUT_MS 2000 struct stratix10_svc_chan; -- cgit v1.2.3 From 6ffd853b0b10e1e292cef0bfd0997986471254de Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 1 Mar 2026 16:51:44 -0800 Subject: build_bug.h: correct function parameters names in kernel-doc Use the correct function (or macro) names to avoid kernel-doc warnings: Warning: include/linux/build_bug.h:38 function parameter 'cond' not described in 'BUILD_BUG_ON_MSG' Warning: include/linux/build_bug.h:38 function parameter 'msg' not described in 'BUILD_BUG_ON_MSG' Warning: include/linux/build_bug.h:76 function parameter 'expr' not described in 'static_assert' Link: https://lkml.kernel.org/r/20260302005144.3467019-1-rdunlap@infradead.org Signed-off-by: Randy Dunlap Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton --- include/linux/build_bug.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 2cfbb4c65c78..d3dc5dc5f916 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -32,7 +32,8 @@ /** * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied * error message. - * @condition: the condition which the compiler should know is false. + * @cond: the condition which the compiler should know is false. + * @msg: build-time error message * * See BUILD_BUG_ON for description. */ @@ -60,6 +61,7 @@ /** * static_assert - check integer constant expression at build time + * @expr: expression to be checked * * static_assert() is a wrapper for the C11 _Static_assert, with a * little macro magic to make the message optional (defaulting to the -- cgit v1.2.3 From b2e48c429ec54715d16fefa719dd2fbded2e65be Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:28:53 +0100 Subject: sched/mmcid: Prevent CID stalls due to concurrent forks A newly forked task is accounted as MMCID user before the task is visible in the process' thread list and the global task list. This creates the following problem: CPU1 CPU2 fork() sched_mm_cid_fork(tnew1) tnew1->mm.mm_cid_users++; tnew1->mm_cid.cid = getcid() -> preemption fork() sched_mm_cid_fork(tnew2) tnew2->mm.mm_cid_users++; // Reaches the per CPU threshold mm_cid_fixup_tasks_to_cpus() for_each_other(current, p) .... As tnew1 is not visible yet, this fails to fix up the already allocated CID of tnew1. As a consequence a subsequent schedule in might fail to acquire a (transitional) CID and the machine stalls. Move the invocation of sched_mm_cid_fork() after the new task becomes visible in the thread and the task list to prevent this. This also makes it symmetrical vs. exit() where the task is removed as CID user before the task is removed from the thread and task lists. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202525.969061974@kernel.org --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a7b4a980eb2f..5a5d3dbc9cdf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2354,7 +2354,6 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #ifdef CONFIG_SCHED_MM_CID void sched_mm_cid_before_execve(struct task_struct *t); void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); void sched_mm_cid_exit(struct task_struct *t); static __always_inline int task_mm_cid(struct task_struct *t) { @@ -2363,7 +2362,6 @@ static __always_inline int task_mm_cid(struct task_struct *t) #else static inline void sched_mm_cid_before_execve(struct task_struct *t) { } static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } static inline void sched_mm_cid_exit(struct task_struct *t) { } static __always_inline int task_mm_cid(struct task_struct *t) { -- cgit v1.2.3 From 192d852129b1b7c4f0ddbab95d0de1efd5ee1405 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 10 Mar 2026 21:29:09 +0100 Subject: sched/mmcid: Avoid full tasklist walks Chasing vfork()'ed tasks on a CID ownership mode switch requires a full task list walk, which is obviously expensive on large systems. Avoid that by keeping a list of tasks using a mm MMCID entity in mm::mm_cid and walk this list instead. This removes the proven to be flaky counting logic and avoids a full task list walk in the case of vfork()'ed tasks. Fixes: fbd0e71dc370 ("sched/mmcid: Provide CID ownership mode fixup functions") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Tested-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20260310202526.183824481@kernel.org --- include/linux/rseq_types.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index da5fa6f40294..0b42045988db 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -133,10 +133,12 @@ struct rseq_data { }; * @active: MM CID is active for the task * @cid: The CID associated to the task either permanently or * borrowed from the CPU + * @node: Queued in the per MM MMCID list */ struct sched_mm_cid { unsigned int active; unsigned int cid; + struct hlist_node node; }; /** @@ -157,6 +159,7 @@ struct mm_cid_pcpu { * @work: Regular work to handle the affinity mode change case * @lock: Spinlock to protect against affinity setting which can't take @mutex * @mutex: Mutex to serialize forks and exits related to this mm + * @user_list: List of the MM CID users of a MM * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map * is growth only. * @users: The number of tasks sharing this MM. Separate from mm::mm_users @@ -177,13 +180,14 @@ struct mm_mm_cid { raw_spinlock_t lock; struct mutex mutex; + struct hlist_head user_list; /* Low frequency modified */ unsigned int nr_cpus_allowed; unsigned int users; unsigned int pcpu_thrs; unsigned int update_deferred; -}____cacheline_aligned_in_smp; +} ____cacheline_aligned; #else /* CONFIG_SCHED_MM_CID */ struct mm_mm_cid { }; struct sched_mm_cid { }; -- cgit v1.2.3 From 416909962e7cdf29fd01ac523c953f37708df93d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 17 Feb 2026 22:07:47 -0500 Subject: USB: usbcore: Introduce usb_bulk_msg_killable() The synchronous message API in usbcore (usb_control_msg(), usb_bulk_msg(), and so on) uses uninterruptible waits. However, drivers may call these routines in the context of a user thread, which means it ought to be possible to at least kill them. For this reason, introduce a new usb_bulk_msg_killable() function which behaves the same as usb_bulk_msg() except for using wait_for_completion_killable_timeout() instead of wait_for_completion_timeout(). The same can be done later for usb_control_msg() later on, if it turns out to be needed. Signed-off-by: Alan Stern Suggested-by: Oliver Neukum Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Link: https://patch.msgid.link/248628b4-cc83-4e81-a620-3ce4e0376d41@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index fbfcc70b07fb..57ceeb02a7cb 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1868,8 +1868,9 @@ extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, extern int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout); extern int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, - void *data, int len, int *actual_length, - int timeout); + void *data, int len, int *actual_length, int timeout); +extern int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, + void *data, int len, int *actual_length, int timeout); /* wrappers around usb_control_msg() for the most common standard requests */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, -- cgit v1.2.3 From 1015c27a5e1a63efae2b18a9901494474b4d1dc3 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Tue, 17 Feb 2026 22:10:32 -0500 Subject: USB: core: Limit the length of unkillable synchronous timeouts The usb_control_msg(), usb_bulk_msg(), and usb_interrupt_msg() APIs in usbcore allow unlimited timeout durations. And since they use uninterruptible waits, this leaves open the possibility of hanging a task for an indefinitely long time, with no way to kill it short of unplugging the target device. To prevent this sort of problem, enforce a maximum limit on the length of these unkillable timeouts. The limit chosen here, somewhat arbitrarily, is 60 seconds. On many systems (although not all) this is short enough to avoid triggering the kernel's hung-task detector. In addition, clear up the ambiguity of negative timeout values by treating them the same as 0, i.e., using the maximum allowed timeout. Signed-off-by: Alan Stern Link: https://lore.kernel.org/linux-usb/3acfe838-6334-4f6d-be7c-4bb01704b33d@rowland.harvard.edu/ Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") CC: stable@vger.kernel.org Link: https://patch.msgid.link/15fc9773-a007-47b0-a703-df89a8cf83dd@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 57ceeb02a7cb..04277af4bb9d 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1862,6 +1862,9 @@ void usb_free_noncoherent(struct usb_device *dev, size_t size, * SYNCHRONOUS CALL SUPPORT * *-------------------------------------------------------------------*/ +/* Maximum value allowed for timeout in synchronous routines below */ +#define USB_MAX_SYNCHRONOUS_TIMEOUT 60000 /* ms */ + extern int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout); -- cgit v1.2.3 From 9f6a983cfa22ac662c86e60816d3a357d4b551e9 Mon Sep 17 00:00:00 2001 From: Jie Deng Date: Fri, 27 Feb 2026 16:49:31 +0800 Subject: usb: core: new quirk to handle devices with zero configurations Some USB devices incorrectly report bNumConfigurations as 0 in their device descriptor, which causes the USB core to reject them during enumeration. logs: usb 1-2: device descriptor read/64, error -71 usb 1-2: no configurations usb 1-2: can't read configurations, error -22 However, these devices actually work correctly when treated as having a single configuration. Add a new quirk USB_QUIRK_FORCE_ONE_CONFIG to handle such devices. When this quirk is set, assume the device has 1 configuration instead of failing with -EINVAL. This quirk is applied to the device with VID:PID 5131:2007 which exhibits this behavior. Signed-off-by: Jie Deng Link: https://patch.msgid.link/20260227084931.1527461-1-dengjie03@kylinos.cn Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/quirks.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 2f7bd2fdc616..b3cc7beab4a3 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -78,4 +78,7 @@ /* skip BOS descriptor request */ #define USB_QUIRK_NO_BOS BIT(17) +/* Device claims zero configurations, forcing to 1 */ +#define USB_QUIRK_FORCE_ONE_CONFIG BIT(18) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 96189080265e6bb5dde3a4afbaf947af493e3f82 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 9 Mar 2026 14:21:37 -0600 Subject: io_uring: ensure ctx->rings is stable for task work flags manipulation If DEFER_TASKRUN | SETUP_TASKRUN is used and task work is added while the ring is being resized, it's possible for the OR'ing of IORING_SQ_TASKRUN to happen in the small window of swapping into the new rings and the old rings being freed. Prevent this by adding a 2nd ->rings pointer, ->rings_rcu, which is protected by RCU. The task work flags manipulation is inside RCU already, and if the resize ring freeing is done post an RCU synchronize, then there's no need to add locking to the fast path of task work additions. Note: this is only done for DEFER_TASKRUN, as that's the only setup mode that supports ring resizing. If this ever changes, then they too need to use the io_ctx_mark_taskrun() helper. Link: https://lore.kernel.org/io-uring/20260309062759.482210-1-naup96721@gmail.com/ Cc: stable@vger.kernel.org Fixes: 79cfe9e59c2a ("io_uring/register: add IORING_REGISTER_RESIZE_RINGS") Reported-by: Hao-Yu Yang Suggested-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 3e4a82a6f817..dd1420bfcb73 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -388,6 +388,7 @@ struct io_ring_ctx { * regularly bounce b/w CPUs. */ struct { + struct io_rings __rcu *rings_rcu; struct llist_head work_llist; struct llist_head retry_llist; unsigned long check_cq; -- cgit v1.2.3 From 94a4b1f959989de9c54d43c3a102fb1ee92e1414 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Sat, 7 Mar 2026 17:50:53 -0300 Subject: ipv6: move the disable_ipv6_mod knob to core code From: Jakub Kicinski Make sure disable_ipv6_mod itself is not part of the IPv6 module, in case core code wants to refer to it. We will remove support for IPv6=m soon, this change helps make fixes we commit before that less messy. Link: https://patch.msgid.link/20260307-net-nd_tbl_fixes-v4-1-e2677e85628c@suse.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 443053a76dcf..a7421382a916 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,7 +333,12 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -bool ipv6_mod_enabled(void); +extern int disable_ipv6_mod; + +static inline bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { -- cgit v1.2.3 From 7a3ac62473f2bd213557e41aaab7a8f144037dfd Mon Sep 17 00:00:00 2001 From: Lucas Zampieri Date: Sat, 14 Mar 2026 01:05:29 +0000 Subject: HID: input: Introduce struct hid_battery and refactor battery code Introduce struct hid_battery to encapsulate individual battery state, preparing for future multi-battery support. The new structure contains all battery-related fields previously stored directly in hid_device (capacity, min, max, report_type, report_id, charge_status, etc.). The hid_device->battery pointer type changes from struct power_supply* to struct hid_battery*, and all battery functions are refactored accordingly. A hid_get_battery() helper is added for external drivers, with hid-apple.c and hid-magicmouse.c updated to use the new API. The hid-input-test.c KUnit tests are also updated for the new structure. No functional changes for single-battery devices. Signed-off-by: Lucas Zampieri Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 52 +++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 39 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 31324609af4d..e4e2a5643bda 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -634,6 +634,36 @@ enum hid_battery_status { HID_BATTERY_REPORTED, /* Device sent unsolicited battery strength report */ }; +/** + * struct hid_battery - represents a single battery power supply + * @dev: pointer to the parent hid_device + * @ps: the power supply instance + * @min: minimum battery value from HID descriptor + * @max: maximum battery value from HID descriptor + * @report_type: HID report type (input/feature) + * @report_id: HID report ID for this battery + * @charge_status: current charging status + * @status: battery reporting status + * @capacity: current battery capacity (0-100) + * @avoid_query: if true, avoid querying battery (e.g., for stylus) + * @present: if true, battery is present (may be dynamic) + * @ratelimit_time: rate limiting for battery reports + */ +struct hid_battery { + struct hid_device *dev; + struct power_supply *ps; + __s32 min; + __s32 max; + __s32 report_type; + __s32 report_id; + __s32 charge_status; + enum hid_battery_status status; + __s32 capacity; + bool avoid_query; + bool present; + ktime_t ratelimit_time; +}; + struct hid_driver; struct hid_ll_driver; @@ -670,20 +700,9 @@ struct hid_device { #ifdef CONFIG_HID_BATTERY_STRENGTH /* * Power supply information for HID devices which report - * battery strength. power_supply was successfully registered if - * battery is non-NULL. + * battery strength. battery is non-NULL if successfully registered. */ - struct power_supply *battery; - __s32 battery_capacity; - __s32 battery_min; - __s32 battery_max; - __s32 battery_report_type; - __s32 battery_report_id; - __s32 battery_charge_status; - enum hid_battery_status battery_status; - bool battery_avoid_query; - bool battery_present; - ktime_t battery_ratelimit_time; + struct hid_battery *battery; #endif unsigned long status; /* see STAT flags above */ @@ -744,6 +763,13 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) dev_set_drvdata(&hdev->dev, data); } +#ifdef CONFIG_HID_BATTERY_STRENGTH +static inline struct hid_battery *hid_get_battery(struct hid_device *hdev) +{ + return hdev->battery; +} +#endif + #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 -- cgit v1.2.3 From 4a58ae85c3f9b142ffba023d0f976978ade57d1b Mon Sep 17 00:00:00 2001 From: Lucas Zampieri Date: Sat, 14 Mar 2026 01:05:30 +0000 Subject: HID: input: Add support for multiple batteries per device Add support for HID devices that report multiple batteries, each identified by its report ID. The hid_device->battery pointer is replaced with a batteries list. Batteries are named using the pattern hid-{uniq}-battery-{report_id}. The hid_get_battery() helper returns the first battery in the list for backwards compatibility with single-battery drivers. Signed-off-by: Lucas Zampieri Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index e4e2a5643bda..fb1a3f3ad9fa 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -648,6 +648,7 @@ enum hid_battery_status { * @avoid_query: if true, avoid querying battery (e.g., for stylus) * @present: if true, battery is present (may be dynamic) * @ratelimit_time: rate limiting for battery reports + * @list: list node for linking into hid_device's battery list */ struct hid_battery { struct hid_device *dev; @@ -662,6 +663,7 @@ struct hid_battery { bool avoid_query; bool present; ktime_t ratelimit_time; + struct list_head list; }; struct hid_driver; @@ -700,9 +702,10 @@ struct hid_device { #ifdef CONFIG_HID_BATTERY_STRENGTH /* * Power supply information for HID devices which report - * battery strength. battery is non-NULL if successfully registered. + * battery strength. Each battery is tracked separately in the + * batteries list. */ - struct hid_battery *battery; + struct list_head batteries; #endif unsigned long status; /* see STAT flags above */ @@ -766,7 +769,9 @@ static inline void hid_set_drvdata(struct hid_device *hdev, void *data) #ifdef CONFIG_HID_BATTERY_STRENGTH static inline struct hid_battery *hid_get_battery(struct hid_device *hdev) { - return hdev->battery; + if (list_empty(&hdev->batteries)) + return NULL; + return list_first_entry(&hdev->batteries, struct hid_battery, list); } #endif -- cgit v1.2.3