6.4.4-rc1 review
Subsystems (13)
Greg Kroah-Hartman
maintainerPATCH 1/800 start_kernel: Add __no_stack_protector function attribute
In reply to Greg Kroah-HartmanFrom: [email protected] <[email protected]>
commit 514ca14ed5444b911de59ed3381dfd195d99fe4b upstream.
Back during the discussion of
commit a9a3ed1eff36 ("x86: Fix early boot crash on gcc-10, third try") we discussed the need for a function attribute to control the omission of stack protectors on a per-function basis; at the time Clang had support for no_stack_protector but GCC did not. This was fixed in gcc-11. Now that the function attribute is available, let's start using it.
Callers of boot_init_stack_canary need to use this function attribute unless they're compiled with -fno-stack-protector, otherwise the canary stored in the stack slot of the caller will differ upon the call to boot_init_stack_canary. This will lead to a call to __stack_chk_fail() then panic.
--- arch/powerpc/kernel/smp.c | 1 + include/linux/compiler_attributes.h | 12 ++++++++++++ init/main.c | 3 ++- 3 files changed, 15 insertions(+), 1 deletion(-)
arch/powerpc/kernel/smp.c +1 -0
@@ -1605,6 +1605,7 @@ static void add_cpu_to_masks(int cpu) }/* Activate a secondary processor. */ +__no_stack_protector void start_secondary(void *unused) {unsigned int cpu =raw_smp_processor_id ();
include/linux/compiler_attributes.h +12 -0
@@ -256,6 +256,18 @@#define __noreturn __attribute__((__noreturn__))/* +* Optional: only supported since GCC >= 11.1, clang >= 7.0. +* +* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fstack_005fprotector-function-attribute +* clang: https://clang.llvm.org/docs/AttributeReference.html#no-stack-protector-safebuffers +*/ +#if __has_attribute (__no_stack_protector__) +# define __no_stack_protector __attribute__((__no_stack_protector__)) +#else +# define __no_stack_protector +#endif + +/* * Optional: not supported by gcc. * * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable
init/main.c +2 -1
@@ -877,7 +877,8 @@ static void __init print_unknown_bootoptmemblock_free (unknown_options, len); } -asmlinkage __visible void __init __no_sanitize_address __noreturn start_kernel(void) +asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector +void start_kernel (void ) {char *command_line;char *after_dashes;
Greg Kroah-Hartman
maintainerPATCH 10/800 iio: accel: fxls8962af: errata bug only applicable for FXLS8962AF
In reply to Greg Kroah-HartmanFrom: Sean Nyekjaer <[email protected]>
commit b410a9307bc3a7cdee3c930c98f6fc9cf1d2c484 upstream.
Remove special errata handling if FXLS8964AF is used.
--- drivers/iio/accel/fxls8962af-core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/iio/accel/fxls8962af-core.c +3 -2
@@ -904,9 +904,10 @@ static int fxls8962af_fifo_transfer(struint total_length = samples * sample_length;int ret; -if (i2c_verify_client (dev)) +if (i2c_verify_client (dev) && + data->chip_info->chip_id ==FXLS8962AF_DEVICE_ID )/* -* Due to errata bug: +* Due to errata bug (only applicable on fxls8962af): * E3: FIFO burst read operation error using I2C interface * We have to avoid burst reads on I2C.. */
Greg Kroah-Hartman
maintainerPATCH 11/800 iio: accel: fxls8962af: fixup buffer scan element type
In reply to Greg Kroah-HartmanFrom: Sean Nyekjaer <[email protected]>
commit d1cfbd52ede5e5fabc09992894c5733b4057f159 upstream.
Scan elements for x,y,z channels is little endian and requires no bit shifts. LE vs. BE is controlled in register SENS_CONFIG2 and bit LE_BE, default value is LE.
--- drivers/iio/accel/fxls8962af-core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/iio/accel/fxls8962af-core.c +1 -2
@@ -724,8 +724,7 @@ static const struct iio_event_spec fxls8 .sign = 's', \ .realbits = 12, \ .storagebits = 16, \ - .shift = 4, \ - .endianness = IIO_BE, \ + .endianness = IIO_LE, \ }, \ .event_spec = fxls8962af_event, \ .num_event_specs = ARRAY_SIZE(fxls8962af_event), \
Greg Kroah-Hartman
maintainerPATCH 12/800 Revert "drm/amd/display: edp do not add non-edid timings"
In reply to Greg Kroah-HartmanFrom: Hersen Wu <[email protected]>
commit d6149086b45e150c170beaa4546495fd1880724c upstream.
This change causes regression when eDP and external display in mirror mode. When external display supports low resolution than eDP, use eDP timing to driver external display may cause corruption on external display.
This reverts commit e749dd10e5f292061ad63d2b030194bf7d7d452c.
--- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +1 -7
@@ -7196,13 +7196,7 @@ static int amdgpu_dm_connector_get_modesdrm_add_modes_noedid (connector,1920 ,1080 ); }else {amdgpu_dm_connector_ddc_get_modes (connector, edid); -/* most eDP supports only timings from its edid, -* usually only detailed timings are available -* from eDP edid. timings which are not from edid -* may damage eDP -*/ -if (connector->connector_type != DRM_MODE_CONNECTOR_eDP) -amdgpu_dm_connector_add_common_modes (encoder, connector); +amdgpu_dm_connector_add_common_modes (encoder, connector);amdgpu_dm_connector_add_freesync_modes (connector, edid); }amdgpu_dm_fbc_init (connector);
Greg Kroah-Hartman
maintainerPATCH 13/800 fs: pipe: reveal missing function protoypes
In reply to Greg Kroah-HartmanFrom: Arnd Bergmann <[email protected]>
[ Upstream commit 247c8d2f9837a3e29e3b6b7a4aa9c36c37659dd4 ]
A couple of functions from fs/pipe.c are used both internally and for the watch queue code, but the declaration is only visible when the latter is enabled:
fs/pipe.c:1254:5: error: no previous prototype for 'pipe_resize_ring' fs/pipe.c:758:15: error: no previous prototype for 'account_pipe_buffers' fs/pipe.c:764:6: error: no previous prototype for 'too_many_pipe_buffers_soft' fs/pipe.c:771:6: error: no previous prototype for 'too_many_pipe_buffers_hard' fs/pipe.c:777:6: error: no previous prototype for 'pipe_is_unprivileged_user'
Make the visible unconditionally to avoid these warnings.
Message-Id: <[email protected]>
--- include/linux/pipe_fs_i.h | 4 ---- 1 file changed, 4 deletions(-)
include/linux/pipe_fs_i.h +0 -4
@@ -261,18 +261,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -#ifdef CONFIG_WATCH_QUEUE unsigned long account_pipe_buffers (struct user_struct *user,unsigned long old,unsigned long new);bool too_many_pipe_buffers_soft (unsigned long user_bufs);bool too_many_pipe_buffers_hard (unsigned long user_bufs);bool pipe_is_unprivileged_user (void ); -#endif /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ -#ifdef CONFIG_WATCH_QUEUE int pipe_resize_ring (struct pipe_inode_info *pipe,unsigned int nr_slots); -#endif long pipe_fcntl (struct file *,unsigned int ,unsigned long arg);struct pipe_inode_info *get_pipe_info (struct file *file,bool for_splice);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 14/800 s390/kasan: fix insecure W+X mapping warning
In reply to Greg Kroah-HartmanFrom: Alexander Gordeev <[email protected]>
[ Upstream commit 2ed8b509753a0454b52b2d72e982265472c8d861 ]
Since commit 3b5c3f000c2e ("s390/kasan: move shadow mapping to decompressor") the decompressor establishes mappings for the shadow memory and sets initial protection attributes to RWX. The decompressed kernel resets protection to RW+NX later on.
In case a shadow memory range is not aligned on page boundary (e.g. as result of mem= kernel command line parameter use), the "Checked W+X mappings: FAILED, 1 W+X pages found" warning hits.
--- arch/s390/mm/vmem.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
arch/s390/mm/vmem.c +10 -4
@@ -667,7 +667,15 @@ static void __init memblock_region_swap(void *a, void *b, int size)#ifdef CONFIG_KASAN #define __sha (x) ((unsigned long)kasan_mem_to_shadow((void *)x)) + +static inline int set_memory_kasan (unsigned long start,unsigned long end) +{ + start =PAGE_ALIGN_DOWN (__sha (start)); + end =PAGE_ALIGN (__sha (end)); +return set_memory_rwnx (start, (end - start) >>PAGE_SHIFT ); +}#endif +/* * map whole physical memory to virtual memory (identity mapping) * we reserve enough space in the vmalloc area for vmemmap to hotplug
@@ -737,10 +745,8 @@ void __init vmem_map_init(void) }#ifdef CONFIG_KASAN -for_each_mem_range (i, &base, &end) { -set_memory_rwnx (__sha (base), - (__sha (end) -__sha (base)) >>PAGE_SHIFT ); - } +for_each_mem_range (i, &base, &end) +set_memory_kasan (base, end);#endif set_memory_rox ((unsigned long )_stext, (unsigned long )(_etext - _stext) >>PAGE_SHIFT );
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 15/800 blk-mq: dont queue plugged passthrough requests into scheduler
In reply to Greg Kroah-HartmanFrom: Ming Lei <[email protected]>
[ Upstream commit d97217e7f024bbe9aa62aea070771234c2879358 ]
Passthrough requests should never be queued to the I/O scheduler, as scheduling these opaque requests doesn't make sense, and I/O schedulers might require req->bio to be always valid.
We never let passthrough requests insert into the scheduler before commit 1c2d2fff6dc0 ("block: wire-up support for passthrough plugging"), restore this behavior even for passthrough requests issued under a plug.
[hch: use blk_mq_insert_requests for passthrough requests,
fix up the commit message and comments]
--- block/blk-mq.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
block/blk-mq.c +6 -2
@@ -2711,6 +2711,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)struct request *requeue_list =NULL ;struct request **requeue_lastp = &requeue_list;unsigned int depth =0 ; +bool is_passthrough = false;LIST_HEAD (list); do {
@@ -2719,7 +2720,9 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)if (!this_hctx) { this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; - }else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { + is_passthrough =blk_rq_is_passthrough (rq); + }else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx || + is_passthrough !=blk_rq_is_passthrough (rq)) {rq_list_add_tail (&requeue_lastp, rq);continue ; }
@@ -2731,7 +2734,8 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)trace_block_unplug (this_hctx->queue, depth, !from_sched);percpu_ref_get (&this_hctx->queue->q_usage_counter); -if (this_hctx->queue->elevator) { +/* passthrough requests should never be issued to the I/O scheduler */ +if (this_hctx->queue->elevator && !is_passthrough) { this_hctx->queue->elevator->type->ops.insert_requests (this_hctx, &list,0 );blk_mq_run_hw_queue (this_hctx, from_sched);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 16/800 block: Fix the type of the second bdev_op_is_zoned_write() argument
In reply to Greg Kroah-HartmanFrom: Bart Van Assche <[email protected]>
[ Upstream commit 3ddbe2a7e0d4a155a805f69c906c9beed30d4cc4 ]
Change the type of the second argument of bdev_op_is_zoned_write() from blk_opf_t into enum req_op because this function expects an operation without flags as second argument.
--- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/linux/blkdev.h +1 -1
@@ -1282,7 +1282,7 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) }static inline bool bdev_op_is_zoned_write (struct block_device *bdev, -blk_opf_t op) +enum req_op op) {if (!bdev_is_zoned (bdev))return false;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 17/800 block/rq_qos: protect rq_qos apis with a new lock
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit a13bd91be22318768d55470cbc0b0f4488ef9edf ]
commit 50e34d78815e ("block: disable the elevator int del_gendisk") move rq_qos_exit() from disk_release() to del_gendisk(), this will introduce some problems:
1) If rq_qos_add() is triggered by enabling iocost/iolatency through cgroupfs, then it can concurrent with del_gendisk(), it's not safe to write 'q->rq_qos' concurrently.
2) Activate cgroup policy that is relied on rq_qos will call rq_qos_add() and blkcg_activate_policy(), and if rq_qos_exit() is called in the middle, null-ptr-dereference will be triggered in blkcg_activate_policy().
3) blkg_conf_open_bdev() can call blkdev_get_no_open() first to find the disk, then if rq_qos_exit() from del_gendisk() is done before rq_qos_add(), then memory will be leaked.
This patch add a new disk level mutex 'rq_qos_mutex':
1) The lock will protect rq_qos_exit() directly.
2) For wbt that doesn't relied on blk-cgroup, rq_qos_add() can only be called from disk initialization for now because wbt can't be destructed until rq_qos_exit(), so it's safe not to protect wbt for now. Hoever, in case that rq_qos dynamically destruction is supported in the furture, this patch also protect rq_qos_add() from wbt_init() directly, this is enough because blk-sysfs already synchronize writers with disk removal.
3) For iocost and iolatency, in order to synchronize disk removal and cgroup configuration, the lock is held after blkdev_get_no_open() from blkg_conf_open_bdev(), and is released in blkg_conf_exit(). In order to fix the above memory leak, disk_live() is checked after holding the new lock.
--- block/blk-cgroup.c | 9 +++++++++ block/blk-core.c | 1 + block/blk-rq-qos.c | 20 ++++++-------------- block/blk-wbt.c | 2 ++ include/linux/blkdev.h | 1 + 5 files changed, 19 insertions(+), 14 deletions(-)
block/blk-cgroup.c +9 -0
@@ -762,6 +762,13 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)return -ENODEV ; } +mutex_lock (&bdev->bd_queue->rq_qos_mutex); +if (!disk_live (bdev->bd_disk)) { +blkdev_put_no_open (bdev); +mutex_unlock (&bdev->bd_queue->rq_qos_mutex); +return -ENODEV ; + } + ctx->body = input; ctx->bdev = bdev;return 0 ;
@@ -906,6 +913,7 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);*/ void blkg_conf_exit (struct blkg_conf_ctx *ctx) __releases(&ctx->bdev->bd_queue->queue_lock) + __releases(&ctx->bdev->bd_queue->rq_qos_mutex) {if (ctx->blkg) {spin_unlock_irq (&bdev_get_queue (ctx->bdev)->queue_lock);
@@ -913,6 +921,7 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx) }if (ctx->bdev) { +mutex_unlock (&ctx->bdev->bd_queue->rq_qos_mutex);blkdev_put_no_open (ctx->bdev); ctx->body =NULL ; ctx->bdev =NULL ;
block/blk-core.c +1 -0
@@ -420,6 +420,7 @@ struct request_queue *blk_alloc_queue(int node_id)mutex_init (&q->debugfs_mutex);mutex_init (&q->sysfs_lock);mutex_init (&q->sysfs_dir_lock); +mutex_init (&q->rq_qos_mutex);spin_lock_init (&q->queue_lock);init_waitqueue_head (&q->mq_freeze_wq);
block/blk-rq-qos.c +6 -14
@@ -288,11 +288,13 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,void rq_qos_exit (struct request_queue *q) { +mutex_lock (&q->rq_qos_mutex);while (q->rq_qos) {struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; rqos->ops->exit (rqos); } +mutex_unlock (&q->rq_qos_mutex); } int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
@@ -300,6 +302,8 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, {struct request_queue *q = disk->queue; +lockdep_assert_held (&q->rq_qos_mutex); + rqos->disk = disk; rqos->id = id; rqos->ops = ops;
@@ -307,18 +311,13 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,/* * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. -* -* Reuse ->queue_lock for protecting against other concurrent -* rq_qos adding/deleting */ blk_mq_freeze_queue (q); -spin_lock_irq (&q->queue_lock);if (rq_qos_id (q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; -spin_unlock_irq (&q->queue_lock);blk_mq_unfreeze_queue (q);
@@ -330,7 +329,6 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,return 0 ; ebusy: -spin_unlock_irq (&q->queue_lock);blk_mq_unfreeze_queue (q);return -EBUSY ; }
@@ -340,21 +338,15 @@ void rq_qos_del(struct rq_qos *rqos)struct request_queue *q = rqos->disk->queue;struct rq_qos **cur; -/* -* See comment in rq_qos_add() about freezing queue & using -* ->queue_lock. -*/ -blk_mq_freeze_queue (q); +lockdep_assert_held (&q->rq_qos_mutex); -spin_lock_irq (&q->queue_lock); +blk_mq_freeze_queue (q);for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {if (*cur == rqos) { *cur = rqos->next;break ; } } -spin_unlock_irq (&q->queue_lock); -blk_mq_unfreeze_queue (q);mutex_lock (&q->debugfs_mutex);
block/blk-wbt.c +2 -0
@@ -944,7 +944,9 @@ int wbt_init(struct gendisk *disk)/* * Assign rwb and add the stats callback. */ +mutex_lock (&q->rq_qos_mutex); ret =rq_qos_add (&rwb->rqos, disk,RQ_QOS_WBT , &wbt_rqos_ops); +mutex_unlock (&q->rq_qos_mutex);if (ret) goto err_free;
include/linux/blkdev.h +1 -0
@@ -392,6 +392,7 @@ struct request_queue {struct blk_queue_stats *stats;struct rq_qos *rq_qos; +struct mutex rq_qos_mutex;const struct blk_mq_ops *mq_ops;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 18/800 splice: Fix filemap_splice_read() to use the correct inode
In reply to Greg Kroah-HartmanFrom: David Howells <[email protected]>
[ Upstream commit c37222082f23c456664d1c3182a714670ab8f9a4 ]
Fix filemap_splice_read() to use file->f_mapping->host, not file->f_inode, as the source of the file size because in the case of a block device, file->f_inode points to the block-special file (which is typically 0 length) and not the backing store.
--- mm/filemap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
mm/filemap.c +2 -2
@@ -2906,7 +2906,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, do { cond_resched(); - if (*ppos >= i_size_read(file_inode(in))) + if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos;
@@ -2922,7 +2922,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,* part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ - isize =i_size_read (file_inode (in)); + isize =i_size_read (in->f_mapping->host);if (unlikely (*ppos >= isize))break ; end_offset =min_t (loff_t, isize, *ppos + len);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 19/800 erofs: kill hooked chains to avoid loops on deduplicated compressed images
In reply to Greg Kroah-HartmanFrom: Gao Xiang <[email protected]>
[ Upstream commit 967c28b23f6c89bb8eef6a046ea88afe0d7c1029 ]
After heavily stressing EROFS with several images which include a hand-crafted image of repeated patterns for more than 46 days, I found two chains could be linked with each other almost simultaneously and form a loop so that the entire loop won't be submitted. As a consequence, the corresponding file pages will remain locked forever.
It can be _only_ observed on data-deduplicated compressed images. For example, consider two chains with five pclusters in total:
Chain 1: 2->3->4->5 -- The tail pcluster is 5;
Chain 2: 5->1->2 -- The tail pcluster is 2.Chain 2 could link to Chain 1 with pcluster 5; and Chain 1 could link to Chain 2 at the same time with pcluster 2.
Since hooked chains are all linked locklessly now, I have no idea how to simply avoid the race. Instead, let's avoid hooked chains completely until I could work out a proper way to fix this and end users finally tell us that it's needed to add it back.
Actually, this optimization can be found with multi-threaded workloads (especially even more often on deduplicated compressed images), yet I'm not sure about the overall system impacts of not having this compared with implementation complexity.
--- fs/erofs/zdata.c | 72 ++++++++---------------------------------------- 1 file changed, 11 insertions(+), 61 deletions(-)
fs/erofs/zdata.c +11 -61
@@ -94,11 +94,8 @@ struct z_erofs_pcluster {/* let's avoid the valid 32-bit kernel addresses */ -/* the chained workgroup has't submitted io (still open) */ +/* the end of a chain of pclusters */ #define Z_EROFS_PCLUSTER_TAIL ((void *)0x5F0ECAFE) -/* the chained workgroup has already submitted io */ -#define Z_EROFS_PCLUSTER_TAIL_CLOSED ((void *)0x5F0EDEAD) -#define Z_EROFS_PCLUSTER_NIL (NULL)struct z_erofs_decompressqueue {
@@ -499,20 +496,6 @@ int __init z_erofs_init_zip_subsystem(void)enum z_erofs_pclustermode {Z_EROFS_PCLUSTER_INFLIGHT , -/* -* The current pclusters was the tail of an exist chain, in addition -* that the previous processed chained pclusters are all decided to -* be hooked up to it. -* A new chain will be created for the remaining pclusters which are -* not processed yet, so different from Z_EROFS_PCLUSTER_FOLLOWED, -* the next pcluster cannot reuse the whole page safely for inplace I/O -* in the following scenario: -* ________________________________________________________________ -* | tail (partial) page | head (partial) page | -* | (belongs to the next pcl) | (belongs to the current pcl) | -* |_______PCLUSTER_FOLLOWED______|________PCLUSTER_HOOKED__________| -*/ -Z_EROFS_PCLUSTER_HOOKED ,/* * a weak form of Z_EROFS_PCLUSTER_FOLLOWED, the difference is that it * could be dispatched into bypass queue later due to uptodated managed
@@ -530,8 +513,8 @@ enum z_erofs_pclustermode {* ________________________________________________________________ * | tail (partial) page | head (partial) page | * | (of the current cl) | (of the previous collection) | -* | PCLUSTER_FOLLOWED or | | -* |_____PCLUSTER_HOOKED__|___________PCLUSTER_FOLLOWED____________| +* | | | +* |__PCLUSTER_FOLLOWED___|___________PCLUSTER_FOLLOWED____________| * * [ (*) the above page can be used as inplace I/O. ] */
@@ -544,7 +527,7 @@ struct z_erofs_decompress_frontend {struct z_erofs_bvec_iter biter;struct page *candidate_bvpage; -struct z_erofs_pcluster *pcl, *tailpcl; +struct z_erofs_pcluster *pcl;z_erofs_next_pcluster_t owned_head;enum z_erofs_pclustermode mode;
@@ -750,19 +733,7 @@ static void z_erofs_try_to_claim_pcluster(struct z_erofs_decompress_frontend *f)return ; } -/* -* type 2, link to the end of an existing open chain, be careful -* that its submission is controlled by the original attached chain. -*/ -if (*owned_head != &pcl->next && pcl != f->tailpcl && -cmpxchg (&pcl->next,Z_EROFS_PCLUSTER_TAIL , - *owned_head) ==Z_EROFS_PCLUSTER_TAIL ) { - *owned_head =Z_EROFS_PCLUSTER_TAIL ; - f->mode =Z_EROFS_PCLUSTER_HOOKED ; - f->tailpcl =NULL ; -return ; - } -/* type 3, it belongs to a chain, but it isn't the end of the chain */ +/* type 2, it belongs to an ongoing chain */ f->mode =Z_EROFS_PCLUSTER_INFLIGHT ; }
@@ -823,9 +794,6 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) goto err_out; } } -/* used to check tail merging loop due to corrupted images */ -if (fe->owned_head ==Z_EROFS_PCLUSTER_TAIL ) - fe->tailpcl = pcl; fe->owned_head = &pcl->next; fe->pcl = pcl;return 0 ;
@@ -846,7 +814,6 @@ static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe)/* must be Z_EROFS_PCLUSTER_TAIL or pointed to previous pcluster */ DBG_BUGON (fe->owned_head ==Z_EROFS_PCLUSTER_NIL ); -DBG_BUGON (fe->owned_head ==Z_EROFS_PCLUSTER_TAIL_CLOSED );if (!(map->m_flags &EROFS_MAP_META )) { grp = erofs_find_workgroup(fe->inode->i_sb,
@@ -865,10 +832,6 @@ static int z_erofs_collector_begin(struct z_erofs_decompress_frontend *fe)if (ret == -EEXIST ) {mutex_lock (&fe->pcl->lock); -/* used to check tail merging loop due to corrupted images */ -if (fe->owned_head ==Z_EROFS_PCLUSTER_TAIL ) - fe->tailpcl = fe->pcl; -z_erofs_try_to_claim_pcluster (fe); }else if (ret) {return ret;
@@ -1025,8 +988,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,* those chains are handled asynchronously thus the page cannot be used * for inplace I/O or bvpage (should be processed in a strict order.) */ - tight &= (fe->mode >=Z_EROFS_PCLUSTER_HOOKED && - fe->mode !=Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE ); + tight &= (fe->mode >Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE ); cur = end - min_t(unsigned int, offset + end - map->m_la, end);if (!(map->m_flags &EROFS_MAP_MAPPED )) {
@@ -1404,10 +1366,7 @@ static void z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, };z_erofs_next_pcluster_t owned = io->head; -while (owned !=Z_EROFS_PCLUSTER_TAIL_CLOSED ) { -/* impossible that 'owned' equals Z_EROFS_WORK_TPTR_TAIL */ -DBG_BUGON (owned ==Z_EROFS_PCLUSTER_TAIL ); -/* impossible that 'owned' equals Z_EROFS_PCLUSTER_NIL */ +while (owned !=Z_EROFS_PCLUSTER_TAIL ) {DBG_BUGON (owned ==Z_EROFS_PCLUSTER_NIL ); be.pcl = container_of(owned, struct z_erofs_pcluster, next);
@@ -1424,7 +1383,7 @@ static void z_erofs_decompressqueue_work(struct work_struct *work) container_of(work, struct z_erofs_decompressqueue, u.work);struct page *pagepool =NULL ; -DBG_BUGON (bgq->head ==Z_EROFS_PCLUSTER_TAIL_CLOSED ); +DBG_BUGON (bgq->head ==Z_EROFS_PCLUSTER_TAIL );z_erofs_decompress_queue (bgq, &pagepool);erofs_release_pages (&pagepool);kvfree (bgq);
@@ -1612,7 +1571,7 @@ static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb, q->sync = true; } q->sb = sb; - q->head =Z_EROFS_PCLUSTER_TAIL_CLOSED ; + q->head =Z_EROFS_PCLUSTER_TAIL ;return q; }
@@ -1630,11 +1589,7 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,z_erofs_next_pcluster_t *const submit_qtail = qtail[JQ_SUBMIT ];z_erofs_next_pcluster_t *const bypass_qtail = qtail[JQ_BYPASS ]; -DBG_BUGON (owned_head ==Z_EROFS_PCLUSTER_TAIL_CLOSED ); -if (owned_head ==Z_EROFS_PCLUSTER_TAIL ) - owned_head =Z_EROFS_PCLUSTER_TAIL_CLOSED ; - -WRITE_ONCE (pcl->next,Z_EROFS_PCLUSTER_TAIL_CLOSED ); +WRITE_ONCE (pcl->next,Z_EROFS_PCLUSTER_TAIL );WRITE_ONCE (*submit_qtail, owned_head);WRITE_ONCE (*bypass_qtail, &pcl->next);
@@ -1705,15 +1660,10 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,unsigned int i =0 ;bool bypass = true; -/* no possible 'owned_head' equals the following */ -DBG_BUGON (owned_head ==Z_EROFS_PCLUSTER_TAIL_CLOSED );DBG_BUGON (owned_head ==Z_EROFS_PCLUSTER_NIL ); - pcl = container_of(owned_head, struct z_erofs_pcluster, next); + owned_head =READ_ONCE (pcl->next); -/* close the main owned chain at first */ - owned_head =cmpxchg (&pcl->next,Z_EROFS_PCLUSTER_TAIL , -Z_EROFS_PCLUSTER_TAIL_CLOSED );if (z_erofs_is_inline_pcluster (pcl)) {move_to_bypass_jobqueue (pcl, qtail, owned_head);continue ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 2/800 USB: serial: option: add LARA-R6 01B PIDs
In reply to Greg Kroah-HartmanFrom: Davide Tronchin <[email protected]>
commit ffa5f7a3bf28c1306eef85d4056539c2d4b8eb09 upstream.
The new LARA-R6 product variant identified by the "01B" string can be configured (by AT interface) in three different USB modes:
* Default mode (Vendor ID: 0x1546 Product ID: 0x1311) with 4 serial interfaces
* RmNet mode (Vendor ID: 0x1546 Product ID: 0x1312) with 4 serial interfaces and 1 RmNet virtual network interface
* CDC-ECM mode (Vendor ID: 0x1546 Product ID: 0x1313) with 4 serial interface and 1 CDC-ECM virtual network interface
The first 4 interfaces of all the 3 USB configurations (default, RmNet, CDC-ECM) are the same.
In default mode LARA-R6 01B exposes the following interfaces:
If 0: Diagnostic
If 1: AT parser
If 2: AT parser
If 3: AT parser/alternative functions
In RmNet mode LARA-R6 01B exposes the following interfaces:
If 0: Diagnostic
If 1: AT parser
If 2: AT parser
If 3: AT parser/alternative functions
If 4: RMNET interface
In CDC-ECM mode LARA-R6 01B exposes the following interfaces:
If 0: Diagnostic
If 1: AT parser
If 2: AT parser
If 3: AT parser/alternative functions
If 4: CDC-ECM interface
--- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/usb/serial/option.c +4 -0
@@ -1151,6 +1151,10 @@ static const struct usb_device_id option { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x90fa), .driver_info = RSVD(3) },/* u-blox products */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1311) }, /* u-blox LARA-R6 01B */ + { USB_DEVICE(UBLOX_VENDOR_ID, 0x1312), /* u-blox LARA-R6 01B (RMNET) */ + .driver_info = RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(UBLOX_VENDOR_ID, 0x1313, 0xff) }, /* u-blox LARA-R6 01B (ECM) */ { USB_DEVICE(UBLOX_VENDOR_ID, 0x1341) }, /* u-blox LARA-L6 */ { USB_DEVICE(UBLOX_VENDOR_ID, 0x1342), /* u-blox LARA-L6 (RMNET) */ .driver_info = RSVD(4) },
Greg Kroah-Hartman
maintainerPATCH 20/800 x86/resctrl: Only show tasks pid in current pid namespace
In reply to Greg Kroah-HartmanFrom: Shawn Wang <[email protected]>
[ Upstream commit 2997d94b5dd0e8b10076f5e0b6f18410c73e28bd ]
When writing a task id to the "tasks" file in an rdtgroup, rdtgroup_tasks_write() treats the pid as a number in the current pid namespace. But when reading the "tasks" file, rdtgroup_tasks_show() shows the list of global pids from the init namespace, which is confusing and incorrect.
To be more robust, let the "tasks" file only show pids in the current pid namespace.
--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +6 -2
@@ -726,11 +726,15 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,static void show_rdt_tasks (struct rdtgroup *r,struct seq_file *s) {struct task_struct *p, *t; +pid_t pid;rcu_read_lock ();for_each_process_thread (p, t) { -if (is_closid_match (t, r) ||is_rmid_match (t, r)) -seq_printf (s,"%d\n" , t->pid); +if (is_closid_match (t, r) ||is_rmid_match (t, r)) { + pid =task_pid_vnr (t); +if (pid) +seq_printf (s,"%d\n" , pid); + } }rcu_read_unlock (); }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 21/800 fsverity: use shash API instead of ahash API
In reply to Greg Kroah-HartmanFrom: Eric Biggers <[email protected]>
[ Upstream commit 8fcd94add6c5c93ed3b9314456e8420914401530 ]
The "ahash" API, like the other scatterlist-based crypto APIs such as "skcipher", comes with some well-known limitations. First, it can't easily be used with vmalloc addresses. Second, the request struct can't be allocated on the stack. This adds complexity and a possible failure point that needs to be worked around, e.g. using a mempool.
The only benefit of ahash over "shash" is that ahash is needed to access traditional memory-to-memory crypto accelerators, i.e. drivers/crypto/. However, this style of crypto acceleration has largely fallen out of favor and been superseded by CPU-based acceleration or inline crypto engines. Also, ahash needs to be used asynchronously to take full advantage of such hardware, but fs/verity/ has never done this.
On all systems that aren't actually using one of these ahash-only crypto accelerators, ahash just adds unnecessary overhead as it sits between the user and the underlying shash algorithms.
Also, XFS is planned to cache fsverity Merkle tree blocks in the existing XFS buffer cache. As a result, it will be possible for a single Merkle tree block to be split across discontiguous pages
(https://lore.kernel.org/r/[email protected]).
This data will need to be hashed. It is easiest to work with a vmapped address in this case. However, ahash is incompatible with this.
Therefore, let's convert fs/verity/ from ahash to shash. This simplifies the code, and it should also slightly improve performance for everyone who wasn't actually using one of these ahash-only crypto accelerators, i.e. almost everyone (or maybe even everyone)!
Stable-dep-of: d1f0c5ea04cd ("fsverity: don't use bio_first_page_all() in fsverity_verify_bio()")
--- fs/verity/enable.c | 19 ++--- fs/verity/fsverity_private.h | 13 +--- fs/verity/hash_algs.c | 131 ++++++----------------------------- fs/verity/verify.c | 109 +++++++++++------------------ 4 files changed, 71 insertions(+), 201 deletions(-)
fs/verity/enable.c +6 -13
@@ -7,6 +7,7 @@#include "fsverity_private.h" +#include <crypto/hash.h> #include <linux/mount.h> #include <linux/sched/signal.h> #include <linux/uaccess.h>
@@ -20,7 +21,7 @@ struct block_buffer {/* Hash a block, writing the result to the next level's pending block buffer. */ static int hash_one_block (struct inode *inode,const struct merkle_tree_params *params, -struct ahash_request *req,struct block_buffer *cur) +struct block_buffer *cur) {struct block_buffer *next = cur +1 ;int err;
@@ -36,8 +37,7 @@ static int hash_one_block(struct inode *inode,/* Zero-pad the block if it's shorter than the block size. */ memset (&cur->data[cur->filled],0 , params->block_size - cur->filled); - err =fsverity_hash_block (params, inode, req,virt_to_page (cur->data), -offset_in_page (cur->data), + err =fsverity_hash_block (params, inode, cur->data, &next->data[next->filled]);if (err)return err;
@@ -76,7 +76,6 @@ static int build_merkle_tree(struct file *filp,struct inode *inode =file_inode (filp);const u64 data_size = inode->i_size;const int num_levels = params->num_levels; -struct ahash_request *req;struct block_buffer _buffers[1 +FS_VERITY_MAX_LEVELS +1 ] = {};struct block_buffer *buffers = &_buffers[1 ];unsigned long level_offset[FS_VERITY_MAX_LEVELS ];
@@ -90,9 +89,6 @@ static int build_merkle_tree(struct file *filp,return 0 ; } -/* This allocation never fails, since it's mempool-backed. */ - req =fsverity_alloc_hash_request (params->hash_alg,GFP_KERNEL ); -/* * Allocate the block buffers. Buffer "-1" is for data blocks. * Buffers 0 <= level < num_levels are for the actual tree levels.
@@ -130,7 +126,7 @@ static int build_merkle_tree(struct file *filp,fsverity_err (inode,"Short read of file data" ); goto out; } - err =hash_one_block (inode, params, req, &buffers[-1 ]); + err =hash_one_block (inode, params, &buffers[-1 ]);if (err) goto out;for (level =0 ; level < num_levels; level++) {
@@ -141,8 +137,7 @@ static int build_merkle_tree(struct file *filp, }/* Next block at @level is full */ - err =hash_one_block (inode, params, req, - &buffers[level]); + err =hash_one_block (inode, params, &buffers[level]);if (err) goto out; err = write_merkle_tree_block(inode,
@@ -162,8 +157,7 @@ static int build_merkle_tree(struct file *filp,/* Finish all nonempty pending tree blocks. */ for (level =0 ; level < num_levels; level++) {if (buffers[level].filled !=0 ) { - err =hash_one_block (inode, params, req, - &buffers[level]); + err =hash_one_block (inode, params, &buffers[level]);if (err) goto out; err = write_merkle_tree_block(inode,
@@ -183,7 +177,6 @@ static int build_merkle_tree(struct file *filp, out:for (level =-1 ; level < num_levels; level++)kfree (buffers[level].data); -fsverity_free_hash_request (params->hash_alg, req);return err; }
fs/verity/fsverity_private.h +2 -11
@@ -11,9 +11,6 @@#define pr_fmt (fmt) "fs-verity: " fmt#include <linux/fsverity.h> -#include <linux/mempool.h> - -struct ahash_request ;/* * Implementation limit: maximum depth of the Merkle tree. For now 8 is plenty;
@@ -23,11 +20,10 @@ struct ahash_request;/* A hash algorithm supported by fs-verity */ struct fsverity_hash_alg { -struct crypto_ahash *tfm;/* hash tfm, allocated on demand */ +struct crypto_shash *tfm;/* hash tfm, allocated on demand */ const char *name;/* crypto API name, e.g. sha256 */ unsigned int digest_size;/* digest size in bytes, e.g. 32 for SHA-256 */ unsigned int block_size;/* block size in bytes, e.g. 64 for SHA-256 */ -mempool_t req_pool;/* mempool with a preallocated hash request */ /* * The HASH_ALGO_* constant for this algorithm. This is different from * FS_VERITY_HASH_ALG_*, which uses a different numbering scheme.
@@ -85,15 +81,10 @@ extern struct fsverity_hash_alg fsverity_hash_algs[];struct fsverity_hash_alg *fsverity_get_hash_alg (const struct inode *inode,unsigned int num); -struct ahash_request *fsverity_alloc_hash_request (struct fsverity_hash_alg *alg, -gfp_t gfp_flags); -void fsverity_free_hash_request (struct fsverity_hash_alg *alg, -struct ahash_request *req);const u8 *fsverity_prepare_hash_state (struct fsverity_hash_alg *alg,const u8 *salt,size_t salt_size);int fsverity_hash_block (const struct merkle_tree_params *params, -const struct inode *inode,struct ahash_request *req, -struct page *page,unsigned int offset,u8 *out); +const struct inode *inode,const void *data,u8 *out);int fsverity_hash_buffer (struct fsverity_hash_alg *alg,const void *data,size_t size,u8 *out);void __init fsverity_check_hash_algs (void );
fs/verity/hash_algs.c +21 -110
237 lines not on this page · raw message
fs/verity/verify.c +42 -67
228 lines not on this page · raw message
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 3/800 usb: dwc3: gadget: Propagate core init errors to UDC during pullup
In reply to Greg Kroah-HartmanFrom: Krishna Kurapati <[email protected]>
commit c0aabed9cabe057309779a9e26fe86a113d24dad upstream.
In scenarios where pullup relies on resume (get sync) to initialize the controller and set the run stop bit, then core_init is followed by gadget_resume which will eventually set run stop bit.
But in cases where the core_init fails, the return value is not sent back to udc appropriately. So according to UDC the controller has started but in reality we never set the run stop bit.
On systems like Android, there are uevents sent to HAL depending on whether the configfs_bind / configfs_disconnect were invoked. In the above mentioned scnenario, if the core init fails, the run stop won't be set and the cable plug-out won't result in generation of any disconnect event and userspace would never get any uevent regarding cable plug out and we never call pullup(0) again. Furthermore none of the next Plug-In/Plug-Out's would be known to configfs.
Return back the appropriate result to UDC to let the userspace/ configfs know that the pullup failed so they can take appropriate action.
Message-ID: <[email protected]>
--- drivers/usb/dwc3/gadget.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/usb/dwc3/gadget.c +3 -1
@@ -2744,7 +2744,9 @@ static int dwc3_gadget_pullup(struct usb ret =pm_runtime_get_sync (dwc->dev);if (!ret || ret <0 ) {pm_runtime_put (dwc->dev); -return 0 ; +if (ret <0 ) +pm_runtime_set_suspended (dwc->dev); +return ret; }if (dwc->pullups_connected == is_on) {
Greg Kroah-Hartman
maintainerPATCH 4/800 phy: tegra: xusb: Clear the driver reference in usb-phy dev
In reply to Greg Kroah-HartmanFrom: EJ Hsu <[email protected]>
commit c0c2fcb1325d0d4f3b322b5ee49385f8eca2560d upstream.
For the dual-role port, it will assign the phy dev to usb-phy dev and use the port dev driver as the dev driver of usb-phy.
When we try to destroy the port dev, it will destroy its dev driver as well. But we did not remove the reference from usb-phy dev. This might cause the use-after-free issue in KASAN.
--- drivers/phy/tegra/xusb.c | 1 + 1 file changed, 1 insertion(+)
drivers/phy/tegra/xusb.c +1 -0
@@ -568,6 +568,7 @@ static void tegra_xusb_port_unregister(susb_role_switch_unregister (port->usb_role_sw);cancel_work_sync (&port->usb_phy_work);usb_remove_phy (&port->usb_phy); + port->usb_phy.dev->driver =NULL ; }if (port->ops->remove)
Greg Kroah-Hartman
maintainerPATCH 5/800 extcon: usbc-tusb320: Unregister typec port on driver removal
In reply to Greg Kroah-HartmanFrom: Alvin Šipraga <[email protected]>
commit 3adbaa30d973093a4f37927baf9596cca51b593d upstream.
The driver can register a typec port if suitable firmware properties are present. But if the driver is removed through sysfs unbind, rmmod or similar, then it does not clean up after itself and the typec port device remains registered. This can be seen in sysfs, where stale typec ports get left over in /sys/class/typec.
In order to fix this we have to add an i2c_driver remove function and call typec_unregister_port(), which is a no-op in the case where no typec port is created and the pointer remains NULL.
In the process we should also put the fwnode_handle when the typec port isn't registered anymore, including if an error occurs during probe. The typec subsystem does not increase or decrease the reference counter for us, so we track it in the driver's private data.
Note that the conditional check on TYPEC_PWR_MODE_PD was removed in the probe path because a call to tusb320_set_adv_pwr_mode() will perform an even more robust validation immediately after, hence there is no functional change here.
--- drivers/extcon/extcon-usbc-tusb320.c | 42 ++++++++++++++++++++++++++++------- 1 file changed, 34 insertions(+), 8 deletions(-)
drivers/extcon/extcon-usbc-tusb320.c +34 -8
@@ -78,6 +78,7 @@ struct tusb320_priv {struct typec_capability cap;enum typec_port_type port_type;enum typec_pwr_opmode pwr_opmode; +struct fwnode_handle *connector_fwnode; };static const char *const tusb_attached_states[] = {
@@ -391,27 +392,25 @@ static int tusb320_typec_probe(struct i2/* Type-C connector found. */ ret =typec_get_fw_cap (&priv->cap, connector);if (ret) -return ret; + goto err_put; priv->port_type = priv->cap.type;/* This goes into register 0x8 field CURRENT_MODE_ADVERTISE */ ret =fwnode_property_read_string (connector,"typec-power-opmode" , &cap_str);if (ret) -return ret; + goto err_put; ret =typec_find_pwr_opmode (cap_str);if (ret <0 ) -return ret; -if (ret ==TYPEC_PWR_MODE_PD ) -return -EINVAL ; + goto err_put; priv->pwr_opmode = ret;/* Initialize the hardware with the devicetree settings. */ ret =tusb320_set_adv_pwr_mode (priv);if (ret) -return ret; + goto err_put; priv->cap.revision =USB_TYPEC_REV_1_1 ; priv->cap.accessory[0 ] =TYPEC_ACCESSORY_AUDIO ;
@@ -422,10 +421,25 @@ static int tusb320_typec_probe(struct i2 priv->cap.fwnode = connector; priv->port =typec_register_port (&client->dev, &priv->cap); -if (IS_ERR (priv->port)) -return PTR_ERR (priv->port); +if (IS_ERR (priv->port)) { + ret =PTR_ERR (priv->port); + goto err_put; + } + + priv->connector_fwnode = connector;return 0 ; + +err_put: +fwnode_handle_put (connector); + +return ret; +} + +static void tusb320_typec_remove (struct tusb320_priv *priv) +{ +typec_unregister_port (priv->port); +fwnode_handle_put (priv->connector_fwnode); }static int tusb320_probe (struct i2c_client *client)
@@ -438,7 +452,9 @@ static int tusb320_probe(struct i2c_clie priv =devm_kzalloc (&client->dev,sizeof (*priv),GFP_KERNEL );if (!priv)return -ENOMEM ; + priv->dev = &client->dev; +i2c_set_clientdata (client, priv); priv->regmap =devm_regmap_init_i2c (client, &tusb320_regmap_config);if (IS_ERR (priv->regmap))
@@ -489,10 +505,19 @@ static int tusb320_probe(struct i2c_clie tusb320_irq_handler,IRQF_TRIGGER_FALLING |IRQF_ONESHOT , client->name, priv); +if (ret) +tusb320_typec_remove (priv);return ret; } +static void tusb320_remove (struct i2c_client *client) +{ +struct tusb320_priv *priv =i2c_get_clientdata (client); + +tusb320_typec_remove (priv); +} +static const struct of_device_id tusb320_extcon_dt_match[] = { { .compatible ="ti,tusb320" , .data = &tusb320_ops, }, { .compatible ="ti,tusb320l" , .data = &tusb320l_ops, },
@@ -502,6 +527,7 @@ MODULE_DEVICE_TABLE(of, tusb320_extcon_dstatic struct i2c_driver tusb320_extcon_driver = { .probe_new = tusb320_probe, + .remove = tusb320_remove, .driver = { .name ="extcon-tusb320" , .of_match_table = tusb320_extcon_dt_match,
Greg Kroah-Hartman
maintainerPATCH 6/800 dt-bindings: iio: ad7192: Add mandatory reference voltage source
In reply to Greg Kroah-HartmanFrom: Fabrizio Lamarque <[email protected]>
commit c6dab7245604862d86f0b6d764919f470584d24f upstream.
Add required reference voltage (VRef) supply regulator.
AD7192 requires three independent voltage sources: DVdd, AVdd and VRef (on REFINx pin pairs).
--- Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml | 5 +++++ 1 file changed, 5 insertions(+)
Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml +5 -0
@@ -47,6 +47,9 @@ properties: avdd-supply: description: AVdd voltage supply + vref-supply: + description: VRef voltage supply + adi,rejection-60-Hz-enable: description: | This bit enables a notch at 60 Hz when the first notch of the sinc
@@ -89,6 +92,7 @@ required: - interrupts - dvdd-supply - avdd-supply + - vref-supply - spi-cpol - spi-cpha
@@ -115,6 +119,7 @@ examples: interrupt-parent = <&gpio>; dvdd-supply = <&dvdd>; avdd-supply = <&avdd>; + vref-supply = <&vref>; adi,refin2-pins-enable; adi,rejection-60-Hz-enable;
Greg Kroah-Hartman
maintainerPATCH 7/800 iio: addac: ad74413: dont set DIN_SINK for functions other than digital input
In reply to Greg Kroah-HartmanFrom: Rasmus Villemoes <[email protected]>
commit a4cba07e64e6ec22d9504a1a45d29afa863dc19c upstream.
Apparently, despite the name Digital Input Configuration Register, the settings in the DIN_CONFIGx registers also affect other channel functions. In particular, setting a non-zero value in the DIN_SINK field breaks the resistance measurement function.
Now, one can of course argue that specifying a drive-strength-microamp property along with a adi,ch-func which is not one of the digital input functions is a bug in the device tree. However, we have a rather complicated setup with instances of ad74412r on external hardware modules, and have set a default drive-strength-microamp in our DT fragments describing those, merely modifying the adi,ch-func settings to reflect however the modules have been wired up. And restricting this setting to just being done for digital input doesn't make the driver any more complex.
--- drivers/iio/addac/ad74413r.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/iio/addac/ad74413r.c +6 -5
@@ -1317,13 +1317,14 @@ static int ad74413r_setup_gpios(struct ad74413r_state *st) }if (config->func ==CH_FUNC_DIGITAL_INPUT_LOGIC || - config->func ==CH_FUNC_DIGITAL_INPUT_LOOP_POWER ) + config->func ==CH_FUNC_DIGITAL_INPUT_LOOP_POWER ) { st->comp_gpio_offsets[comp_gpio_i++] = i; - strength = config->drive_strength; - ret =ad74413r_set_comp_drive_strength (st, i, strength); -if (ret) -return ret; + strength = config->drive_strength; + ret =ad74413r_set_comp_drive_strength (st, i, strength); +if (ret) +return ret; + } ret =ad74413r_set_gpo_config (st, i, gpo_config);if (ret)
Signature · 1 line
2.41.0
Greg Kroah-Hartman
maintainerPATCH 8/800 iio: adc: ad7192: Fix null ad7192_state pointer access
In reply to Greg Kroah-HartmanFrom: Fabrizio Lamarque <[email protected]>
commit 9e58e3a6f8e1c483c86a04903b7b7aa0923e4426 upstream.
Pointer to indio_dev structure is obtained via spi_get_drvdata() at the beginning of function ad7192_setup(), but the spi->dev->driver_data member is not initialized, hence a NULL pointer is returned.
Fix by changing ad7192_setup() signature to take pointer to struct iio_dev, and get ad7192_state pointer via st = iio_priv(indio_dev);
--- drivers/iio/adc/ad7192.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/iio/adc/ad7192.c +3 -3
@@ -380,9 +380,9 @@ static int ad7192_of_clock_select(structreturn clock_sel; } -static int ad7192_setup (struct ad7192_state *st,struct device_node *np) +static int ad7192_setup (struct iio_dev *indio_dev,struct device_node *np) { -struct iio_dev *indio_dev =spi_get_drvdata (st->sd.spi); +struct ad7192_state *st =iio_priv (indio_dev);bool rej60_en, refin2_en;bool buf_en, bipolar, burnout_curr_en;unsigned long long scale_uv;
@@ -1069,7 +1069,7 @@ static int ad7192_probe(struct spi_devic } } - ret =ad7192_setup (st, spi->dev.of_node); + ret =ad7192_setup (indio_dev, spi->dev.of_node);if (ret)return ret;
Greg Kroah-Hartman
maintainerPATCH 9/800 iio: adc: ad7192: Fix internal/external clock selection
In reply to Greg Kroah-HartmanFrom: Fabrizio Lamarque <[email protected]>
commit f7d9e21dd274b97dc0a8dbc136a2ea8506063a96 upstream.
Fix wrong selection of internal clock when mclk is defined.
Resolve a logical inversion introduced in c9ec2cb328e3.
--- drivers/iio/adc/ad7192.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/iio/adc/ad7192.c +1 -1
@@ -367,7 +367,7 @@ static int ad7192_of_clock_select(struct clock_sel =AD7192_CLK_INT ;/* use internal clock */ -if (st->mclk) { +if (!st->mclk) {if (of_property_read_bool (np,"adi,int-clock-output-enable" )) clock_sel =AD7192_CLK_INT_CO ; }else {
Greg Kroah-Hartman
maintainercover 6.4.4-rc1 review
This is the start of the stable review cycle for the 6.4.4 release. There are 800 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Tue, 18 Jul 2023 19:48:07 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.4.4-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.4.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <[email protected]>
Linux 6.4.4-rc1
Andres Freund <[email protected]>
io_uring: Use io_schedule* in cqring wait
Sherry Sun <[email protected]>
tty: serial: fsl_lpuart: add earlycon for imx8ulp platform
Jason A. Donenfeld <[email protected]>
wireguard: netlink: send staged packets when setting initial private key
Jason A. Donenfeld <[email protected]>
wireguard: queueing: use saner cpu selection wrapping
Thadeu Lima de Souza Cascardo <[email protected]>
netfilter: nf_tables: prevent OOB access in nft_byteorder_eval
Thadeu Lima de Souza Cascardo <[email protected]>
netfilter: nf_tables: do not ignore genmask when looking up chain by id
Florent Revest <[email protected]>
netfilter: conntrack: Avoid nf_ct_helper_hash uses after free
Tao Zhou <[email protected]>
drm/amdgpu: check RAS irq existence for VCN/JPEG
Kenneth Feng <[email protected]>
drm/amd/pm: add abnormal fan detection for smu 13.0.0
Alex Deucher <[email protected]>
drm/amdgpu/sdma4: set align mask to 255
Evan Quan <[email protected]>
drm/amd/pm: revise the ASPM settings for thunderbolt attached scenario
Jiadong Zhu <[email protected]>
drm/amdgpu: Skip mark offset for high priority rings
Christian König <[email protected]>
drm/amdgpu: make sure that BOs have a backing store
Christian König <[email protected]>
drm/amdgpu: make sure BOs are locked in amdgpu_vm_get_memory
WANG Xuerui <[email protected]>
LoongArch: Include KBUILD_CPPFLAGS in CHECKFLAGS invocation
Zhihao Cheng <[email protected]>
ovl: fix null pointer dereference in ovl_get_acl_rcu()
Zhihao Cheng <[email protected]>
ovl: let helper ovl_i_path_real() return the realinode
Zhihao Cheng <[email protected]>
ovl: fix null pointer dereference in ovl_permission()
Masahiro Yamada <[email protected]>
kbuild: add $(CLANG_FLAGS) to KBUILD_CPPFLAGS
Nathan Chancellor <[email protected]>
kbuild: Add KBUILD_CPPFLAGS to as-option invocation
Nathan Chancellor <[email protected]>
kbuild: Add CLANG_FLAGS to as-instr
Nathan Chancellor <[email protected]>
powerpc/vdso: Include CLANG_FLAGS explicitly in ldflags-y
Nathan Chancellor <[email protected]>
mips: Include KBUILD_CPPFLAGS in CHECKFLAGS invocation
Arnd Bergmann <[email protected]>
Input: ads7846 - fix pointer cast warning
Jan Kara <[email protected]>
fs: no need to check source
Yu Kuai <[email protected]>
md/raid1-10: fix casting from randomized structure in raid1_submit_write()
Linus Walleij <[email protected]>
Input: ads7846 - Fix usage of match data
Yu Kuai <[email protected]>
blktrace: use inline function for blk_trace_remove() while blktrace is disabled
Christian Marangi <[email protected]>
leds: trigger: netdev: Recheck NETDEV_LED_MODE_LINKUP on dev rename
Arnd Bergmann <[email protected]>
ARM: orion5x: fix d2net gpio initialization
Krzysztof Kozlowski <[email protected]>
ARM: dts: qcom: ipq4019: fix broken NAND controller properties override
Linus Walleij <[email protected]>
ARM: dts: qcom: msm8660: Fix regulator node names
Krzysztof Kozlowski <[email protected]>
regulator: tps65219: Fix matching interrupts for their regulators
Ricardo Ribalda Delgado <[email protected]>
ASoC: mediatek: mt8173: Fix snd_soc_component_initialize error path
Ricardo Ribalda Delgado <[email protected]>
ASoC: mediatek: mt8173: Fix irq error path
Filipe Manana <[email protected]>
btrfs: do not BUG_ON() on tree mod log failure at __btrfs_cow_block()
Filipe Manana <[email protected]>
btrfs: fix extent buffer leak after tree mod log failure at split_node()
Filipe Manana <[email protected]>
btrfs: add missing error handling when logging operation while COWing extent buffer
Filipe Manana <[email protected]>
btrfs: fix race when deleting quota root from the dirty cow roots list
Naohiro Aota <[email protected]>
btrfs: move out now unused BG from the reclaim list
Naohiro Aota <[email protected]>
btrfs: reinsert BGs failed to reclaim
David Sterba <[email protected]>
btrfs: add block-group tree to lockdep classes
Naohiro Aota <[email protected]>
btrfs: bail out reclaim process if filesystem is read-only
Naohiro Aota <[email protected]>
btrfs: delete unused BGs while reclaiming BGs
Boris Burkov <[email protected]>
btrfs: warn on invalid slot in tree mod log rewind
Boris Burkov <[email protected]>
btrfs: insert tree mod log move in push_node_left
Christoph Hellwig <[email protected]>
btrfs: fix dirty_metadata_bytes for redirtied buffers
Matt Corallo <[email protected]>
btrfs: add handling for RAID1C23/DUP to btrfs_reduce_alloc_profile
Abhijeet Rastogi <[email protected]>
ipvs: increase ip_vs_conn_tab_bits range for 64BIT
Mario Limonciello <[email protected]>
usb: typec: ucsi: Mark dGPUs as DEVICE scope
Jan Kara <[email protected]>
fs: Lock moved directories
Jan Kara <[email protected]>
fs: Establish locking order for unrelated directories
Jan Kara <[email protected]>
Revert "udf: Protect rename against modification of moved directory"
Jan Kara <[email protected]>
Revert "f2fs: fix potential corruption when moving a directory"
Jan Kara <[email protected]>
ext4: Remove ext4 locking of moved directory
Thomas Weißschuh <[email protected]>
fs: avoid empty option when generating legacy mount string
Fabian Frederick <[email protected]>
jffs2: reduce stack usage in jffs2_build_xattr_subsystem()
Christian Brauner <[email protected]>
nfsd: use vfs setgid helper
Roberto Sassu <[email protected]>
shmem: use ramfs_kill_sb() for kill_sb method of ramfs-based tmpfs
Ryan Roberts <[email protected]>
mm/damon/ops-common: atomically test and clear young on ptes and pmds
Arnd Bergmann <[email protected]>
autofs: use flexible array in ioctl structure
Tianjia Zhang <[email protected]>
integrity: Fix possible multiple allocation in integrity_inode_get()
Kees Cook <[email protected]>
um: Use HOST_DIR for mrproper
Siddh Raman Pant <[email protected]>
watch_queue: prevent dangling pipe pointer
Zheng Wang <[email protected]>
bcache: Fix __bch_btree_node_alloc to make the failure behavior consistent
Zheng Wang <[email protected]>
bcache: Remove unnecessary NULL point check in node allocations
Mingzhe Zou <[email protected]>
bcache: fixup btree_cache_wait list damage
Quan Zhou <[email protected]>
wifi: mt76: mt7921e: fix init command fail with enabled device
Felix Fietkau <[email protected]>
wifi: cfg80211: fix receiving mesh packets without RFC1042 header
Alexander Wetzel <[email protected]>
wifi: ath10k: Serialize wake_tx_queue ops
Johannes Berg <[email protected]>
wifi: cfg80211: fix regulatory disconnect for non-MLO
Chevron Li <[email protected]>
mmc: sdhci: fix DMA configure compatibility issue when 64bit DMA mode is used.
Ulf Hansson <[email protected]>
mmc: mmci: Set PROBE_PREFER_ASYNCHRONOUS
Robert Marko <[email protected]>
mmc: core: disable TRIM on Micron MTFC4GACAJCN-1M
Robert Marko <[email protected]>
mmc: core: disable TRIM on Kingston EMMC04G-M627
Yu Zhao <[email protected]>
mm/mglru: make memcg_lru->lock irq safe
Jens Axboe <[email protected]>
io_uring: wait interruptibly for request completions on exit
Jianmin Lv <[email protected]>
irqchip/loongson-pch-pic: Fix initialization of HT vector register
Dai Ngo <[email protected]>
NFSD: add encoding of op_recall flag for write delegation
Liu Peibao <[email protected]>
irqchip/loongson-pch-pic: Fix potential incorrect hwirq assignment
Jeff Layton <[email protected]>
nfsd: move init of percpu reply_cache_stats counters back to nfsd_init_net
Jianmin Lv <[email protected]>
irqchip/loongson-liointc: Fix IRQ trigger polarity
Mark Brown <[email protected]>
arm64/signal: Restore TPIDR2 register rather than memory state
Daniel Miess <[email protected]>
Revert "drm/amd/display: Move DCN314 DOMAIN power control to DMCUB"
Geert Uytterhoeven <[email protected]>
lib: dhry: fix sleeping allocations inside non-preemptable section
Matthew Wilcox (Oracle) <[email protected]>
writeback: account the number of pages written back
Robert Hancock <[email protected]>
i2c: xiic: Don't try to handle more interrupt events after error
John Johansen <[email protected]>
apparmor: fix profile verification and enable it
John Johansen <[email protected]>
apparmor: fix policy_compat permission remap with extended permissions
John Johansen <[email protected]>
apparmor: add missing failure check in compute_xmatch_perms
Danila Chernetsov <[email protected]>
apparmor: fix missing error check for rhashtable_insert_fast
Artur Rojek <[email protected]>
sh: dma: Fix DMA channel offset calculation
Marc Zyngier <[email protected]>
risc-v: Fix order of IPI enablement vs RCU startup
Thorsten Winkler <[email protected]>
s390/qeth: Fix vipa deletion
David Howells <[email protected]>
afs: Fix accidental truncation when storing data
Hariprasad Kelam <[email protected]>
octeontx-af: fix hardware timestamp configuration
Vladimir Oltean <[email protected]>
net: dsa: sja1105: always enable the send_meta options
Vladimir Oltean <[email protected]>
net: dsa: tag_sja1105: fix MAC DA patching from meta frames
Guillaume Nault <[email protected]>
pptp: Fix fib lookup calls.
Woody Zhang <[email protected]>
riscv: move memblock_allow_resize() after linear mapping is ready
Amir Goldstein <[email protected]>
fanotify: disallow mount/sb marks on kernel internal pseudo fs
Ville Syrjälä <[email protected]>
drm/i915/psr: Fix BDW PSR AUX CH data register offsets
Lin Ma <[email protected]>
net/sched: act_pedit: Add size check for TCA_PEDIT_PARMS_EX
Ilya Maximets <[email protected]>
xsk: Honor SO_BINDTODEVICE on bind
SeongJae Park <[email protected]>
bpf, btf: Warn but return no error for NULL btf from __register_btf_kfunc_id_set()
Maxime Coquelin <[email protected]>
vduse: fix NULL pointer dereference
Eric Dumazet <[email protected]>
tcp: annotate data races in __tcp_oow_rate_limited()
Eric Dumazet <[email protected]>
net: fix net_dev_start_xmit trace event vs skb_transport_offset()
Vladimir Oltean <[email protected]>
net: dsa: tag_sja1105: fix source port decoding in vlan_filtering=0 bridge mode
Vladimir Oltean <[email protected]>
net: bridge: keep ports without IFF_UNICAST_FLT in BR_PROMISC mode
Pali Rohár <[email protected]>
powerpc: dts: turris1x.dts: Fix PCIe MEM size for pci2 node
Randy Dunlap <[email protected]>
powerpc: allow PPC_EARLY_DEBUG_CPM only when SERIAL_CPM=y
Zeng Heng <[email protected]>
ntfs: Fix panic about slab-out-of-bounds caused by ntfs_listxattr()
Hariprasad Kelam <[email protected]>
octeontx2-af: Reset MAC features in FLR
Hariprasad Kelam <[email protected]>
octeontx2-af: Add validation before accessing cgx and lmac
Hariprasad Kelam <[email protected]>
octeontx2-af: Fix mapping for NIX block from CGX connection
Hariprasad Kelam <[email protected]>
octeontx2-af: cn10kb: fix interrupt csr addresses
Chao Yu <[email protected]>
f2fs: fix error path handling in truncate_dnode()
Nishanth Menon <[email protected]>
mailbox: ti-msgmgr: Fill non-message tx data fields with 0x0
Mario Limonciello <[email protected]>
drm/amd: Don't try to enable secure display TA multiple times
Christian König <[email protected]>
drm/amdgpu: fix number of fence calculations
Jonas Gorski <[email protected]>
spi: bcm-qspi: return error if neither hif_mspi nor mspi is available
Zhengchao Shao <[email protected]>
mlxsw: minimal: fix potential memory leak in mlxsw_m_linecards_init
Pawel Dembicki <[email protected]>
net: dsa: vsc73xx: fix MTU configuration
Nick Child <[email protected]>
ibmvnic: Do not reset dql stats on NON_FATAL err
Martin Habets <[email protected]>
sfc: support for devlink port requires MAE access
Luiz Augusto von Dentz <[email protected]>
Bluetooth: MGMT: Fix marking SCAN_RSP as not connectable
Pauli Virtanen <[email protected]>
Bluetooth: ISO: use hci_sync for setting CIG parameters
Johan Hovold <[email protected]>
Bluetooth: fix invalid-bdaddr quirk for non-persistent setup
Tobias Heider <[email protected]>
Add MODULE_FIRMWARE() for FIRMWARE_TG357766.
Vladimir Oltean <[email protected]>
net: dsa: tag_sja1105: always prefer source port information from INCL_SRCPT
Vladimir Oltean <[email protected]>
net: dsa: sja1105: always enable the INCL_SRCPT option
Vladimir Oltean <[email protected]>
net: dsa: felix: don't drop PTP frames with tag_8021q when RX timestamping is disabled
Vladimir Oltean <[email protected]>
net: mscc: ocelot: don't keep PTP configuration of all ports in single structure
Vladimir Oltean <[email protected]>
net: mscc: ocelot: don't report that RX timestamping is enabled by default
Dmitry Baryshkov <[email protected]>
spi: spi-geni-qcom: enable SPI_CONTROLLER_MUST_TX for GPI DMA mode
Florian Westphal <[email protected]>
net/sched: act_ipt: zero skb->cb before calling target
Florian Westphal <[email protected]>
net/sched: act_ipt: add sanity checks on skb before calling target
Florian Westphal <[email protected]>
net/sched: act_ipt: add sanity checks on table name and hook locations
Chengfeng Ye <[email protected]>
sctp: fix potential deadlock on &net->sctp.addr_wq_lock
Randy Dunlap <[email protected]>
media: cec: i2c: ch7322: also select REGMAP
Arnd Bergmann <[email protected]>
media: tc358746: select CONFIG_GENERIC_PHY
Peng Fan <[email protected]>
tools/virtio: fix build break for aarch64
Dragos Tatulea <[email protected]>
virtio-vdpa: Fix unchecked call to NULL set_vq_affinity
Chao Yu <[email protected]>
f2fs: check return value of freeze_super()
Vinay Belgaumkar <[email protected]>
drm/i915/guc/slpc: Apply min softlimit correctly
Jouni Högander <[email protected]>
drm/i915/psr: Use hw.adjusted mode when calculating io/fast wake times
Christophe JAILLET <[email protected]>
rtc: st-lpc: Release some resources in st_rtc_probe() in case of error
Jinke Han <[email protected]>
blk-throttle: Fix io statistics for cgroup v1
Ian Rogers <[email protected]>
perf bpf: Move the declaration of struct rq
Li Nan <[email protected]>
md/raid10: fix the condition to call bio_end_io_acct()
Shuijing Li <[email protected]>
pwm: mtk_disp: Fix the disable flow of disp_pwm
Dan Carpenter <[email protected]>
pwm: ab8500: Fix error code in probe()
Marek Vasut <[email protected]>
pwm: sysfs: Do not apply state to already disabled PWMs
Fancy Fang <[email protected]>
pwm: imx-tpm: force 'real_period' to be zero in suspend
Yury Norov <[email protected]>
lib/bitmap: drop optimization of bitmap_{from,to}_arr64
Claudiu Beznea <[email protected]>
phy: tegra: xusb: check return value of devm_kzalloc()
Christophe JAILLET <[email protected]>
mfd: stmpe: Only disable the regulators if they are enabled
Neil Armstrong <[email protected]>
phy: qcom: qmp-combo: fix Display Port PHY configuration for SM8550
Yicong Yang <[email protected]>
hwtracing: hisi_ptt: Fix potential sleep in atomic context
Dmitry Baryshkov <[email protected]>
clk: qcom: mmcc-msm8974: fix MDSS_GDSC power flags
Claudiu Beznea <[email protected]>
misc: fastrpc: check return value of devm_kasprintf()
Daniel Golle <[email protected]>
cpufreq: mediatek: correct voltages for MT7622 and MT7623
Christian Borntraeger <[email protected]>
KVM: s390/diag: fix racy access of physical cpu number in diag 9c handler
Pierre Morel <[email protected]>
KVM: s390: vsie: fix the length of APCB bitmap
Amelie Delaunay <[email protected]>
mfd: stmfx: Nullify stmfx->vdd in case of error
Amelie Delaunay <[email protected]>
mfd: stmfx: Fix error path in stmfx_chip_init
Laurentiu Tudor <[email protected]>
bus: fsl-mc: don't assume child devices are all fsl-mc devices
Phil Elwell <[email protected]>
nvmem: rmem: Use NVMEM_DEVID_AUTO
Mirsad Goran Todorovac <[email protected]>
test_firmware: return ENOMEM instead of ENOSPC on failed memory allocation
Alexander Stein <[email protected]>
nvmem: imx-ocotp: Reverse MAC addresses on all i.MX derivates
Yi Yingao <[email protected]>
nvmem: sunplus-ocotp: release otp->clk before return
Nipun Gupta <[email protected]>
cdx: fix driver managed dma support
Matti Vaittinen <[email protected]>
drivers: fwnode: fix fwnode_irq_get[_byname]()
Tony Lindgren <[email protected]>
serial: 8250_omap: Use force_suspend and resume for system suspend
Greg Kroah-Hartman <[email protected]>
Revert "usb: common: usb-conn-gpio: Set last role to unknown before initial detection"
Jiasheng Jiang <[email protected]>
mfd: intel-lpss: Add missing check for platform_get_resource
Christophe JAILLET <[email protected]>
mfd: wcd934x: Fix an error handling path in wcd934x_slim_probe()
Daniel Bristot de Oliveira <[email protected]>
rtla/hwnoise: Reduce runtime to 75%
Christophe JAILLET <[email protected]>
usb: dwc3-meson-g12a: Fix an error handling path in dwc3_meson_g12a_probe()
Prashanth K <[email protected]>
usb: common: usb-conn-gpio: Set last role to unknown before initial detection
Christophe JAILLET <[email protected]>
usb: dwc3: qcom: Fix an error handling path in dwc3_qcom_probe()
Christophe JAILLET <[email protected]>
usb: dwc3: qcom: Release the correct resources in dwc3_qcom_remove()
Nico Boehr <[email protected]>
KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes
Chao Yu <[email protected]>
f2fs: flush error flags in workqueue
Jaegeuk Kim <[email protected]>
f2fs: fix the wrong condition to determine atomic context
Chao Yu <[email protected]>
f2fs: support errors=remount-ro|continue|panic mountoption
Chao Yu <[email protected]>
f2fs: fix to avoid NULL pointer dereference f2fs_write_end_io()
Chao Yu <[email protected]>
f2fs: fix potential deadlock due to unpaired node_write lock use
Bob Peterson <[email protected]>
gfs2: Fix duplicate should_fault_in_pages() call
Sergey Shtylyov <[email protected]>
sh: Avoid using IRQ0 on SH3 and SH4
Hans de Goede <[email protected]>
media: atomisp: ov2680: Stop using half pixelclock for binned modes
Dan Carpenter <[email protected]>
media: atomisp: gmin_platform: fix out_len in gmin_get_config_dsm_var()
Hans de Goede <[email protected]>
media: atomisp: gc0310: Fix double free in gc0310_remove()
Rikard Falkeborn <[email protected]>
media: venus: helpers: Fix ALIGN() of non power of two
Stephan Gerhold <[email protected]>
mfd: rt5033: Drop rt5033-battery sub-device
ChiYuan Huang <[email protected]>
power: supply: rt9467: Make charger-enable control as logic level
Mike Leach <[email protected]>
coresight: etm4x: Fix missing trctraceidr file in sysfs
James Clark <[email protected]>
coresight: Fix loss of connection info when a module is unloaded
Clark Wang <[email protected]>
i3c: master: svc: fix cpu schedule in spin lock
Yue Zhao <[email protected]>
lkdtm: replace ll_rw_block with submit_bh
Muchun Song <[email protected]>
kernfs: fix missing kernfs_idr_lock to remove an ID from the IDR
John Ogness <[email protected]>
serial: 8250: lock port for UART_IER access in omap8250_irq()
John Ogness <[email protected]>
serial: core: lock port for start_rx() in uart_resume_port()
John Ogness <[email protected]>
serial: 8250: lock port for stop_rx() in omap8250_irq()
John Ogness <[email protected]>
serial: core: lock port for stop_rx() in uart_suspend_port()
Bhupesh Sharma <[email protected]>
usb: misc: eud: Fix eud sysfs path (use 'qcom_eud')
Arnd Bergmann <[email protected]>
usb: hide unused usbfs_notify_suspend/resume functions
Li Yang <[email protected]>
usb: phy: phy-tahvo: fix memory leak in tahvo_usb_probe()
Andy Shevchenko <[email protected]>
extcon: Fix kernel doc of property capability fields to avoid warnings
Andy Shevchenko <[email protected]>
extcon: Fix kernel doc of property fields to avoid warnings
Prashanth K <[email protected]>
usb: gadget: u_serial: Add null pointer check in gserial_suspend
Vladislav Efanov <[email protected]>
usb: dwc3: qcom: Fix potential memory leak
Krzysztof Kozlowski <[email protected]>
soundwire: debugfs: fix unbalanced pm_runtime_put()
Krzysztof Kozlowski <[email protected]>
soundwire: qcom: fix unbalanced pm_runtime_put()
Krzysztof Kozlowski <[email protected]>
soundwire: qcom: use consistently 'ctrl' as state variable name
Arnd Bergmann <[email protected]>
staging: vchiq_arm: mark vchiq_platform_init() static
Dmitry Baryshkov <[email protected]>
clk: qcom: mmcc-msm8974: use clk_rcg2_shared_ops for mdp_clk_src clock
Kathiravan T <[email protected]>
clk: qcom: ipq5332: fix the order of SLEEP_CLK and XO clock
Kathiravan T <[email protected]>
clk: qcom: ipq5332: fix the src parameter in ftbl_gcc_apss_axi_clk_src
Konrad Dybcio <[email protected]>
clk: qcom: dispcc-qcm2290: Fix GPLL0_OUT_DIV handling
Konrad Dybcio <[email protected]>
clk: qcom: dispcc-qcm2290: Fix BI_TCXO_AO handling
Robert Marko <[email protected]>
clk: qcom: ipq6018: fix networking resets
Yunfei Dong <[email protected]>
media: mediatek: vcodec: using decoder status instead of core work count
Martin Kepplinger <[email protected]>
media: hi846: fix usage of pm_runtime_get_if_in_use()
Geert Uytterhoeven <[email protected]>
media: renesas: fdp1: Identify R-Car Gen2 versions
Daniel Scally <[email protected]>
media: i2c: Correct format propagation for st-mipid02
Dan Carpenter <[email protected]>
media: i2c: imx296: fix error checking in imx296_read_temperature()
Duoming Zhou <[email protected]>
media: usb: siano: Fix warning due to null work_func_t function pointer
Marek Vasut <[email protected]>
media: videodev2.h: Fix struct v4l2_input tuner index comment
Ming Qian <[email protected]>
media: amphion: initiate a drain of the capture queue in dynamic resolution change
Daniel Lundberg Pedersen <[email protected]>
media: videodev2.h: Fix p_s32 and p_s64 pointer types
Christophe JAILLET <[email protected]>
media: common: saa7146: Avoid a leak in vmalloc_to_sg()
Ming Qian <[email protected]>
media: amphion: drop repeated codec data for vc1g format
Ming Qian <[email protected]>
media: amphion: drop repeated codec data for vc1l format
Daniil Dulov <[email protected]>
media: usb: Check az6007_read() return value
Konrad Dybcio <[email protected]>
clk: qcom: gcc-qcm2290: Mark RCGs shared where applicable
Mantas Pucka <[email protected]>
clk: qcom: gcc-ipq6018: Use floor ops for sdcc clocks
Taniya Das <[email protected]>
clk: qcom: camcc-sc7180: Add parent dependency to all camera GDSCs
Dmitry Baryshkov <[email protected]>
clk: qcom: mmcc-msm8974: remove oxili_ocmemgx_clk
Kathiravan T <[email protected]>
clk: qcom: gcc: ipq5332: Use floor ops for SDCC clocks
Konrad Dybcio <[email protected]>
interconnect: qcom: rpm: Don't use clk_get_optional for bus clocks anymore
Konrad Dybcio <[email protected]>
interconnect: qcom: rpm: Rename icc provider num_clocks to num_bus_clocks
Tony Lindgren <[email protected]>
serial: 8250: omap: Fix freeing of resources on failed register
Christophe JAILLET <[email protected]>
usb: dwc2: Fix some error handling paths
Basavaraj Natikar <[email protected]>
xhci: Improve the XHCI system resume time
Basavaraj Natikar <[email protected]>
USB: Extend pci resume function to handle PM events
Christophe JAILLET <[email protected]>
cpufreq: tegra194: Fix an error handling path in tegra194_cpufreq_probe()
John Paul Adrian Glaubitz <[email protected]>
sh: j2: Use ioremap() to translate device tree address into kernel memory
Yangtao Li <[email protected]>
f2fs: do not allow to defragment files have FI_COMPRESS_RELEASED
Konrad Dybcio <[email protected]>
dt-bindings: power: reset: qcom-pon: Only allow reboot-mode pre-pmk8350
Dan Carpenter <[email protected]>
w1: fix loop in w1_fini()
Stefan Wahren <[email protected]>
w1: w1_therm: fix locking behavior in convert_t
Thomas Gleixner <[email protected]>
x86/efi: Make efi_set_virtual_address_map IBT safe
Will Deacon <[email protected]>
arm64: sme: Use STR P to clear FFR context field in streaming SVE mode
Arnd Bergmann <[email protected]>
ksmbd: avoid field overflow warning
Paulo Alcantara <[email protected]>
smb: client: fix shared DFS root mounts with different prefixes
Paulo Alcantara <[email protected]>
smb: client: fix broken file attrs with nodfs mounts
Shyam Prasad N <[email protected]>
cifs: do all necessary checks for credits within or before locking
Shyam Prasad N <[email protected]>
cifs: prevent use-after-free by freeing the cfile later
Ard Biesheuvel <[email protected]>
efi/libstub: Disable PCI DMA before grabbing the EFI memory map
Masahiro Yamada <[email protected]>
kbuild: deb-pkg: remove the CONFIG_MODULES check in buildeb
Josh Triplett <[email protected]>
kbuild: builddeb: always make modules_install, to install modules.builtin*
Vishal Verma <[email protected]>
tools/testing/cxl: Fix command effects for inject/clear poison
Dan Williams <[email protected]>
cxl/region: Fix state transitions after reset failure
Dan Williams <[email protected]>
cxl/region: Flag partially torn down regions as unusable
Dan Williams <[email protected]>
cxl/region: Move cache invalidation before region teardown, and before setup
Sami Tolvanen <[email protected]>
kbuild: Disable GCOV for *.mod.o
Sami Tolvanen <[email protected]>
kbuild: Fix CFI failures with GCOV
Ding Hui <[email protected]>
SUNRPC: Fix UAF in svc_tcp_listen_data_ready()
Filipe Manana <[email protected]>
btrfs: do not BUG_ON() on tree mod log failure at balance_level()
Filipe Manana <[email protected]>
btrfs: fix race when deleting free space root from the dirty cow roots list
Christian Loehle <[email protected]>
mmc: block: ioctl: do write error check for spi
Demi Marie Obenour <[email protected]>
block: increment diskseq on all media change events
Michael Schmitz <[email protected]>
block: change all __u32 annotations to __be32 in affs_hardblocks.h
Michael Schmitz <[email protected]>
block: add overflow checks for Amiga partition support
Michael Schmitz <[email protected]>
block: fix signed int overflow in Amiga partition support
John Johansen <[email protected]>
apparmor: fix: kzalloc perms tables for shared dfas
Takashi Iwai <[email protected]>
ALSA: pcm: Fix potential data race at PCM memory allocation helpers
Takashi Iwai <[email protected]>
ALSA: jack: Fix mutex call in snd_jack_report()
Werner Sembach <[email protected]>
ALSA: hda/realtek: Add quirk for Clevo NPx0SNx
Andy Chi <[email protected]>
ALSA: hda/realtek: Enable mute/micmute LEDs and limit mic boost on EliteBook
Martin Kaiser <[email protected]>
hwrng: st - keep clock enabled while hwrng is registered
Tarun Sahu <[email protected]>
dax/kmem: Pass valid argument to memory_group_register_static
Dan Williams <[email protected]>
dax: Introduce alloc_dev_dax_id()
Dan Williams <[email protected]>
dax: Fix dax_mapping_release() use after free
Bharath SM <[email protected]>
SMB3: Do not send lease break acknowledgment if all file handles have been closed
Olga Kornievskaia <[email protected]>
NFSv4.1: freeze the session table upon receiving NFS4ERR_BADSESSION
Qi Zheng <[email protected]>
NFSv4.2: fix wrong shrinker_id
Hareshx Sankar Raj <[email protected]>
crypto: qat - unmap buffers before free for RSA
Hareshx Sankar Raj <[email protected]>
crypto: qat - unmap buffer before free for DH
Masahiro Yamada <[email protected]>
ARC: define ASM_NL and __ALIGN(_STR) outside #ifdef __ASSEMBLY__ guard
Dan Carpenter <[email protected]>
modpost: fix off by one in is_executable_section()
Pierre-Clément Tosi <[email protected]>
scripts/mksysmap: Fix badly escaped '$'
Bhupesh Sharma <[email protected]>
dt-bindings: qcom-qce: Fix compatible combinations for SM8150 and IPQ4019 SoCs
Stephan Müller <[email protected]>
crypto: jitter - correct health test during initialization
Arnd Bergmann <[email protected]>
crypto: marvell/cesa - Fix type mismatch warning
Masahiro Yamada <[email protected]>
modpost: fix section mismatch message for R_ARM_{PC24,CALL,JUMP24}Masahiro Yamada <[email protected]>
modpost: fix section mismatch message for R_ARM_ABS32
Randy Dunlap <[email protected]>
crypto: nx - fix build warnings when DEBUG_FS is not enabled
Masahiro Yamada <[email protected]>
modpost: remove broken calculation of exception_table_entry size
Herbert Xu <[email protected]>
hwrng: virtio - Fix race on data_avail and actual data
Eric Farman <[email protected]>
vfio/mdev: Move the compat_class initialization to module init
Xinghui Li <[email protected]>
PCI: vmd: Fix uninitialized variable usage in vmd_enable_domain()
Yoshihiro Shimoda <[email protected]>
PCI: endpoint: functions/pci-epf-test: Fix dma_chan direction
Shunsuke Mie <[email protected]>
PCI: endpoint: Fix a Kconfig prompt of vNTB driver
Song Shuai <[email protected]>
riscv: hibernate: remove WARN_ON in save_processor_state
Namhyung Kim <[email protected]>
perf test: Set PERF_EXEC_PATH for script execution
Aneesh Kumar K.V <[email protected]>
powerpc/mm/dax: Fix the condition when checking if altmap vmemap can cross-boundary
Aneesh Kumar K.V <[email protected]>
powerpc/book3s64/mm: Fix DirectMap stats in /proc/meminfo
Tiezhu Yang <[email protected]>
riscv: uprobes: Restore thread.bad_cause
Xi Pardee <[email protected]>
platform/x86:intel/pmc: Update maps for Meteor Lake P/M platforms
Manivannan Sadhasivam <[email protected]>
PCI: qcom: Disable write access to read only registers for IP v2.9.0
Manivannan Sadhasivam <[email protected]>
PCI: qcom: Use DWC helpers for modifying the read-only DBI registers
Song Shuai <[email protected]>
riscv: hibernation: Remove duplicate call of suspend_restore_csrs
Aditya Gupta <[email protected]>
powerpc: update ppc_save_regs to save current r1 in pt_regs
Colin Ian King <[email protected]>
powerpc/powernv/sriov: perform null check on iov before dereferencing iov
Stanley Chu <[email protected]>
scsi: ufs: core: mcq: Fix the incorrect OCS value for the device command
Bart Van Assche <[email protected]>
scsi: ufs: core: Remove a ufshcd_add_command_trace() call
Namhyung Kim <[email protected]>
perf stat: Reset aggr stats for each run
Claudiu Beznea <[email protected]>
pinctrl: at91-pio4: check return value of devm_kasprintf()
Claudiu Beznea <[email protected]>
pinctrl: microchip-sgpio: check return value of devm_kasprintf()
Xiaolei Wang <[email protected]>
pinctrl: freescale: Fix a memory out of bounds when num_configs is 1
Nicholas Piggin <[email protected]>
powerpc/64s: Fix VAS mm use after free
Ian Rogers <[email protected]>
perf tool x86: Fix perf_env memory leak
Ravi Bangoria <[email protected]>
perf tool x86: Consolidate is_amd check into single function
Michal Wilczynski <[email protected]>
platform/x86/dell/dell-rbtn: Fix resources leaking on error path
Aditya Gupta <[email protected]>
perf tests task_analyzer: Skip tests if no libtraceevent support
Aditya Gupta <[email protected]>
perf tests task_analyzer: Fix bad substitution ${$1}Kan Liang <[email protected]>
perf metric: Fix no group check
Namhyung Kim <[email protected]>
perf dwarf-aux: Fix off-by-one in die_get_varname()
David E. Box <[email protected]>
platform/x86/intel/pmc/mtl: Put devices in D3 during resume
David E. Box <[email protected]>
platform/x86/intel/pmc: Add resume callback
Mark Pearson <[email protected]>
platform/x86: thinkpad_acpi: Fix lkp-tests warnings for platform profiles
Arnaldo Carvalho de Melo <[email protected]>
perf script: Fix allocation of evsel->priv related to per-event dump files
Christophe Leroy <[email protected]>
powerpc/signal32: Force inlining of __unsafe_save_user_regs() and save_tm_user_regs_unsafe()
Christophe Leroy <[email protected]>
powerpc/interrupt: Don't read MSR from interrupt_exit_kernel_prepare()
Christophe Leroy <[email protected]>
kcsan: Don't expect 64 bits atomic builtins from 32 bits architectures
Jiasheng Jiang <[email protected]>
pinctrl: npcm7xx: Add missing check for ioremap
Wells Lu <[email protected]>
pinctrl:sunplus: Add check for kmalloc
Mark Pearson <[email protected]>
platform/x86: think-lmi: Correct NVME password handling
Mark Pearson <[email protected]>
platform/x86: think-lmi: Correct System password interface
Mark Pearson <[email protected]>
platform/x86: think-lmi: mutex protection around multiple WMI calls
Xi Pardee <[email protected]>
platform/x86:intel/pmc: Remove Meteor Lake S platform support
Andy Shevchenko <[email protected]>
pinctrl: cherryview: Return correct value if pin in push-pull mode
Arnaldo Carvalho de Melo <[email protected]>
perf bench: Add missing setlocale() call to allow usage of %'d style formatting
Thierry Reding <[email protected]>
pinctrl: tegra: Duplicate pinmux functions table
Bart Van Assche <[email protected]>
scsi: ufs: core: Fix handling of lrbp->cmd
Bart Van Assche <[email protected]>
scsi: ufs: core: Increase the START STOP UNIT timeout from one to ten seconds
Justin Tee <[email protected]>
scsi: lpfc: Revise NPIV ELS unsol rcv cmpl logic to drop ndlp based on nlp_state
Sui Jingfeng <[email protected]>
PCI: Add pci_clear_master() stub for non-CONFIG_PCI
Bart Van Assche <[email protected]>
scsi: ufs: Declare ufshcd_{hold,release}() once
Wells Lu <[email protected]>
pinctrl: sunplus: Add check for kmalloc
Junyan Ye <[email protected]>
PCI: ftpci100: Release the clock resources
Ian Rogers <[email protected]>
perf evsel: Don't let for_each_group() treat the head of the list as one of its nodes
Rongguang Wei <[email protected]>
PCI: pciehp: Cancel bringup sequence if card is not present
Dan Carpenter <[email protected]>
pinctrl: at91: fix a couple NULL vs IS_ERR() checks
Yuchen Yang <[email protected]>
scsi: 3w-xxxx: Add error handling for initialization failure in tw_probe()
Ding Hui <[email protected]>
PCI/ASPM: Disable ASPM on MFD function removal to avoid use-after-free
Hans de Goede <[email protected]>
platform/x86: lenovo-yogabook: Set default keyboard backligh brightness on probe()
Hans de Goede <[email protected]>
platform/x86: lenovo-yogabook: Reprobe devices on remove()
Hans de Goede <[email protected]>
platform/x86: lenovo-yogabook: Fix work race on remove()
Christophe JAILLET <[email protected]>
pinctrl: bcm2835: Handle gpiochip_add_pin_range() errors
Jinhong Zhu <[email protected]>
scsi: qedf: Fix NULL dereference in error handling
Nirmal Patel <[email protected]>
PCI: vmd: Reset VMD config register between soft reboots
Siddharth Vadapalli <[email protected]>
PCI: cadence: Fix Gen2 Link Retraining process
Jason Gunthorpe <[email protected]>
iommufd: Call iopt_area_contig_done() under the lock
Jason Gunthorpe <[email protected]>
iommufd: Do not access the area pointer after unlocking
Paul Cercueil <[email protected]>
MIPS: DTS: CI20: Raise VDDCORE voltage to 1.125 volts
Paul Cercueil <[email protected]>
MIPS: DTS: CI20: Add parent supplies to ACT8600 regulators
Syed Saba Kareem <[email protected]>
ASoC: amd: acp: clear pdm dma interrupt mask
Michael Walle <[email protected]>
ARM: dts: lan966x: kontron-d10: fix SPI CS
Michael Walle <[email protected]>
ARM: dts: lan966x: kontron-d10: fix board reset
Fei Shao <[email protected]>
clk: Fix memory leak in devm_clk_notifier_register()
Claudiu Beznea <[email protected]>
ASoC: imx-audmix: check return value of devm_kasprintf()
Amir Goldstein <[email protected]>
ovl: update of dentry revalidate flags after copy up
Alexey Romanov <[email protected]>
drivers: meson: secure-pwrc: always enable DMA domain
Claudiu Beznea <[email protected]>
clk: clocking-wizard: check return value of devm_kasprintf()
Claudiu Beznea <[email protected]>
clk: ti: clkctrl: check return value of kasprintf()
Claudiu Beznea <[email protected]>
clk: keystone: sci-clk: check return value of kasprintf()
Claudiu Beznea <[email protected]>
clk: si5341: free unused memory on probe failure
Claudiu Beznea <[email protected]>
clk: si5341: check return value of {devm_}kasprintf()
Claudiu Beznea <[email protected]>
clk: si5341: return error if one synth clock registration fails
Claudiu Beznea <[email protected]>
clk: cdce925: check return value of kasprintf()
Claudiu Beznea <[email protected]>
clk: vc5: check memory returned by kasprintf()
AngeloGioacchino Del Regno <[email protected]>
clk: mediatek: clk-mt8173-apmixedsys: Fix iomap not released issue
AngeloGioacchino Del Regno <[email protected]>
clk: mediatek: clk-mt8173-apmixedsys: Fix return value for of_iomap() error
AngeloGioacchino Del Regno <[email protected]>
clk: mediatek: clk-mtk: Grab iomem pointer for divider clocks
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: correct MERGE_3D length
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: fix sc7280 and sc7180 PINGPONG done interrupts
Marijn Suijten <[email protected]>
drm/msm/dpu: Disable pingpong TE on DPU 5.0.0 and above
Marijn Suijten <[email protected]>
drm/msm/dpu: Move autorefresh disable from CMD encoder to pingpong
Marijn Suijten <[email protected]>
drm/msm/dpu: Drop unused poll_timeout_wr_ptr PINGPONG callback
Luben Tuikov <[email protected]>
drm/amdgpu: Fix usage of UMC fill record in RAS
Srinivasan Shanmugam <[email protected]>
drm/amdgpu: Fix memcpy() in sienna_cichlid_append_powerplay_table function.
Daniel Golle <[email protected]>
arm64: dts: mt7986: increase bl2 partition on NAND of Bananapi R3
Nícolas F. R. A. Prado <[email protected]>
arm64: dts: mediatek: mt8192: Fix CPUs capacity-dmips-mhz
Allen-KH Cheng <[email protected]>
arm64: dts: mediatek: Add cpufreq nodes for MT8192
Bjorn Andersson <[email protected]>
drm/msm/dp: Free resources after unregistering them
Bjorn Andersson <[email protected]>
drm/msm/dp: Drop aux devices together with DP controller
Jessica Zhang <[email protected]>
drm/msm/dsi: Remove incorrect references to slice_count
Jessica Zhang <[email protected]>
drm/msm/dpu: Fix slice_last_group_size calculation
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: do not enable color-management if DSPPs are not available
Su Hui <[email protected]>
ALSA: ac97: Fix possible NULL dereference in snd_ac97_mixer
Nishanth Menon <[email protected]>
arm64: dts: ti: k3-am69-sk: Fix main_i2c0 alias
Thejasvi Konduru <[email protected]>
arm64: dts: ti: k3-j784s4: Fix wakeup pinmux range and pinctrl node offsets
Nishanth Menon <[email protected]>
arm64: dts: ti: k3-j784s4-evm: Fix main_i2c0 alias
Andrew Davis <[email protected]>
arm64: dts: ti: k3-j721e-beagleboneai64: Fix mailbox node status
Yuan Can <[email protected]>
clk: tegra: tegra124-emc: Fix potential memory leak
Dan Carpenter <[email protected]>
clk: clocking-wizard: Fix Oops in clk_wzrd_register_divider()
Dan Carpenter <[email protected]>
clk: bcm: rpi: Fix off by one in raspberrypi_discover_clocks()
Abel Vesa <[email protected]>
arm64: dts: qcom: sm8550: Add missing interconnect path to USB HC
Marijn Suijten <[email protected]>
arm64: dts: qcom: sm8250-edo: Panel framebuffer is 2.5k instead of 4k
Konrad Dybcio <[email protected]>
arm64: dts: qcom: sm8550: Flush RSC sleep & wake votes
Konrad Dybcio <[email protected]>
arm64: dts: qcom: sdm845: Flush RSC sleep & wake votes
Konrad Dybcio <[email protected]>
arm64: dts: qcom: sdm670: Flush RSC sleep & wake votes
Konrad Dybcio <[email protected]>
arm64: dts: qcom: qdu1000: Flush RSC sleep & wake votes
Bosi Zhang <[email protected]>
clk: mediatek: fix of_iomap memory leak
Yuxing Liu <[email protected]>
clk: imx: clk-imx8mp: improve error handling in imx8mp_clocks_probe()
Zhanhao Hu <[email protected]>
clk: imx93: fix memory leak and missing unwind goto in imx93_clocks_probe
Hao Luo <[email protected]>
clk: imx: clk-imx8mn: fix memory leak in imx8mn_clocks_probe
Kai Ma <[email protected]>
clk: imx: clk-imxrt1050: fix memory leak in imxrt1050_clocks_probe
Adam Ford <[email protected]>
clk: imx: composite-8m: Add imx8m_divider_determine_rate
Kashyap Desai <[email protected]>
RDMA/bnxt_re: Avoid calling wake_up threads from spin_lock context
Kashyap Desai <[email protected]>
RDMA/bnxt_re: wraparound mbox producer index
Dmitry Baryshkov <[email protected]>
drm/msm/a5xx: really check for A510 in a5xx_gpu_init
Dmitry Baryshkov <[email protected]>
drm/msm/a6xx: don't set IO_PGTABLE_QUIRK_ARM_OUTER_WBWA with coherent SMMU
Chia-I Wu <[email protected]>
amdgpu: validate offset_in_bo of drm_amdgpu_gem_va
Bob Pearson <[email protected]>
RDMA/rxe: Fix access checks in rxe_check_bind_mw
Geert Uytterhoeven <[email protected]>
HID: uclogic: Modular KUnit tests should not depend on KUNIT=y
Nikita Zhandarovich <[email protected]>
drm/radeon: fix possible division-by-zero errors
Aurabindo Pillai <[email protected]>
drm/amd/display: Fix artifacting on eDP panels when engaging freesync video mode
Chen-Yu Tsai <[email protected]>
soc: mediatek: SVS: Fix MT8192 GPU node name
Daniil Dulov <[email protected]>
drm/amdkfd: Fix potential deallocation of previously deallocated memory.
Christophe JAILLET <[email protected]>
drm/amd/display: Fix a test dml32_rq_dlg_get_rq_reg()
Christophe JAILLET <[email protected]>
drm/amd/display: Fix a test CalculatePrefetchSchedule()
Paul Cercueil <[email protected]>
MIPS: DTS: CI20: Fix ACT8600 regulator node names
Maxime Ripard <[email protected]>
clk: Export clk_hw_forward_rate_request()
Christian Lamparter <[email protected]>
ARM: dts: BCM5301X: fix duplex-full => full-duplex
Guenter Roeck <[email protected]>
hwmon: (pmbus/adm1275) Fix problems with temperature monitoring on ADM1272
Tim Harvey <[email protected]>
hwmon: (gsc-hwmon) fix fan pwm temperature scaling
Olivier Moysan <[email protected]>
ARM: dts: stm32: fix i2s endpoint format property for stm32mp15xx-dkx
Dan Carpenter <[email protected]>
accel/habanalabs: fix gaudi2_get_tpc_idle_status() return
Marek Vasut <[email protected]>
ARM: dts: stm32: Fix audio routing on STM32MP15xx DHCOM PDK2
Chris Morgan <[email protected]>
arm64: dts: rockchip: Fix compatible for Bluetooth on rk3566-anbernic
Caleb Connolly <[email protected]>
Input: pm8941-powerkey - fix debounce on gen2+ PMICs
Keerthy <[email protected]>
arm64: dts: ti: k3-j7200: Fix physical address of pin
Cristian Ciocaltea <[email protected]>
arm64: dts: rockchip: Assign ES8316 MCLK rate on rk3588-rock-5b
Ville Syrjälä <[email protected]>
drm/i915: No 10bit gamma on desktop gen3 parts
Matt Roper <[email protected]>
drm/i915/display: Make display responsible for probing its own IP
Matt Roper <[email protected]>
drm/i915/display: Move display runtime info to display structure
Matt Roper <[email protected]>
drm/i915: Convert INTEL_INFO()->display to a pointer
Matt Roper <[email protected]>
drm/i915/display: Move display device info to header under display/
Jani Nikula <[email protected]>
drm/i915: hide mkwrite_device_info() better
Ville Syrjälä <[email protected]>
drm/i915: Fix limited range csc matrix
Bjorn Andersson <[email protected]>
dt-bindings: arm-smmu: Fix SC8280XP Adreno binding
Christophe JAILLET <[email protected]>
fbdev: omapfb: lcd_mipid: Fix an error handling path in mipid_spi_probe()
Kuogee Hsieh <[email protected]>
drm/msm/dpu: always clear every individual pending flush mask
Kuogee Hsieh <[email protected]>
drm/msm/dpu: set DSC flush bit correctly at MDP CTL flush register
Wolfram Sang <[email protected]>
arm64: dts: renesas: ulcb-kf: Remove flow control for SCIF1
Geert Uytterhoeven <[email protected]>
ARM: dts: iwg20d-q7-common: Fix backlight pwm specifier
Chengchang Tang <[email protected]>
RDMA/hns: Fix hns_roce_table_get return value
Brendan Cunningham <[email protected]>
IB/hfi1: Fix wrong mmu_node used for user SDMA packet after invalidate
Arnd Bergmann <[email protected]>
RDMA/irdma: avoid fortify-string warning in irdma_clr_wqes
Randy Dunlap <[email protected]>
soc/fsl/qe: fix usb.c build errors
Martin Blumenstingl <[email protected]>
ARM: dts: meson8: correct uart_B and uart_C clock references
Cristian Ciocaltea <[email protected]>
ASoC: es8316: Do not set rate constraints for unsupported MCLKs
Cristian Ciocaltea <[email protected]>
ASoC: es8316: Increment max value for ALC Capture Target Volume control
Dmitry Baryshkov <[email protected]>
ARM: dts: qcom: apq8074-dragonboard: Set DMA as remotely controlled
Krzysztof Kozlowski <[email protected]>
memory: brcmstb_dpfe: fix testing array offset after use
Marek Vasut <[email protected]>
ARM: dts: stm32: Shorten the AV96 HDMI sound card name
Douglas Anderson <[email protected]>
arm64: dts: mediatek: mt8195: Add mediatek,broken-save-restore-fw to cherry
Douglas Anderson <[email protected]>
arm64: dts: mediatek: mt8192: Add mediatek,broken-save-restore-fw to asurada
Douglas Anderson <[email protected]>
arm64: dts: mediatek: mt8183: Add mediatek,broken-save-restore-fw to kukui
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: apq8096: fix fixed regulator name property
Luca Weiss <[email protected]>
arm64: dts: qcom: pm7250b: add missing spmi-vadc include
Arnd Bergmann <[email protected]>
ARM: omap2: fix missing tick_broadcast() prototype
Arnd Bergmann <[email protected]>
ARM: ep93xx: fix missing-prototype warnings
Dario Binacchi <[email protected]>
drm/panel: simple: fix active size for Ampire AM-480272H3TMQW-T01H
Adam Ford <[email protected]>
drm: bridge: samsung-dsim: Fix PMS Calculator on imx8m[mnp]
Frieder Schrempf <[email protected]>
drm/bridge: ti-sn65dsi83: Fix enable/disable flow to meet spec
Stephan Gerhold <[email protected]>
arm64: dts: qcom: apq8016-sbc: Fix 1.8V power rail on LS expansion
Stephan Gerhold <[email protected]>
arm64: dts: qcom: apq8016-sbc: Fix regulator constraints
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sdm845-polaris: add missing touchscreen child node reg
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8550: correct pinctrl unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8550: correct crypto unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8350: correct USB phy unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8350: correct PCI phy unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm8350: correct DMA controller unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sm6115: correct thermal-sensor unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sdm845: correct camss unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: sdm630: correct camss unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8996: correct camss unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8994: correct SPMI unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8976: correct MMC unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8953: correct WCNSS unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8953: correct IOMMU unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8916: correct WCNSS unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8916: correct MMC unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: msm8916: correct camss unit address
Krzysztof Kozlowski <[email protected]>
arm64: dts: qcom: ipq6018: correct qrng unit address
Dmitry Baryshkov <[email protected]>
arm64: dts: qcom: pm8998: don't use GIC_SPI for SPMI interrupts
Krzysztof Kozlowski <[email protected]>
ARM: dts: qcom: msm8974: do not use underscore in node name (again)
Linus Walleij <[email protected]>
ARM/musb: omap2: Remove global GPIO numbers from TUSB6010
Linus Walleij <[email protected]>
ARM: omap2: Rewrite WLAN quirk to use GPIO descriptors
Linus Walleij <[email protected]>
ARM: omap2: Get USB hub reset GPIO from descriptor
Linus Walleij <[email protected]>
ARM/gpio: Push OMAP2 quirk down into TWL4030 driver
Linus Walleij <[email protected]>
ARM: omap1: Exorcise the legacy GPIO header
Linus Walleij <[email protected]>
ARM: omap1: Make serial wakeup GPIOs use descriptors
Linus Walleij <[email protected]>
ARM: omap1: Fix up the Nokia 770 board device IRQs
Linus Walleij <[email protected]>
ARM/mmc: Convert old mmci-omap to GPIO descriptors
Linus Walleij <[email protected]>
Input: ads7846 - Convert to use software nodes
Linus Walleij <[email protected]>
ARM: omap1: Remove reliance on GPIO numbers from SX1
Linus Walleij <[email protected]>
ARM: omap1: Remove reliance on GPIO numbers from PalmTE
Linus Walleij <[email protected]>
ARM: omap1: Drop header on AMS Delta
Linus Walleij <[email protected]>
ARM/mfd/gpio: Fixup TPS65010 regression on OMAP1 OSK1
Nícolas F. R. A. Prado <[email protected]>
drm/bridge: anx7625: Prevent endless probe loop
Bhupesh Sharma <[email protected]>
arm64: dts: qcom: qrb4210-rb2: Fix CD gpio for SDHC2
Tony Lindgren <[email protected]>
ARM: dts: gta04: Move model property out of pinctrl node
Biju Das <[email protected]>
clk: renesas: rzg2l: Fix CPG_SIPLL5_CLK1 register write
Jean-Philippe Brucker <[email protected]>
iommu/virtio: Return size mapped for a detached domain
Jean-Philippe Brucker <[email protected]>
iommu/virtio: Detach domain on endpoint release
Arnd Bergmann <[email protected]>
drm/nouveau: dispnv50: fix missing-prototypes warning
Konrad Dybcio <[email protected]>
drm/msm/dpu: Set DPU_DATA_HCTL_EN for in INTF_SC7180_MASK
Marijn Suijten <[email protected]>
drm/msm/dpu: Use V4.0 PCC DSPP sub-block in SC7[12]80
Arnaud Vrac <[email protected]>
drm/msm/dpu: fix cursor block register bit offset in msm8998 hw catalog
Dmitry Baryshkov <[email protected]>
drm/msm/dsi: don't allow enabling 14nm VCO with unprogrammed rate
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: enable DSPP_2/3 for LM_2/3 on sm8450
Kalesh AP <[email protected]>
RDMA/bnxt_re: Fix to remove an unnecessary log
Kalesh AP <[email protected]>
RDMA/bnxt_re: Remove a redundant check inside bnxt_re_update_gid
Kalesh AP <[email protected]>
RDMA/bnxt_re: Use unique names while registering interrupts
Kalesh AP <[email protected]>
RDMA/bnxt_re: Fix to remove unnecessary return labels
Selvin Xavier <[email protected]>
RDMA/bnxt_re: Disable/kill tasklet only if it is enabled
Nikita Zhandarovich <[email protected]>
hwmon: (f71882fg) prevent possible division by zero
Dan Carpenter <[email protected]>
clk: imx: scu: use _safe list iterator to avoid a use after free
Devi Priya <[email protected]>
arm64: dts: qcom: ipq9574: Update the size of GICC & GICV regions
Alexander Stein <[email protected]>
drm/bridge: tc358767: Switch to devm MIPI-DSI helpers
Robert Marko <[email protected]>
arm64: dts: microchip: sparx5: do not use PSCI on reference boards
Tony Lindgren <[email protected]>
bus: ti-sysc: Fix dispc quirk masking bool variables
Marek Vasut <[email protected]>
ARM: dts: stm32: Move ethernet MAC EEPROM from SoM to carrier boards
Maíra Canal <[email protected]>
drm/vkms: Fix RGB565 pixel conversion
Maíra Canal <[email protected]>
drm: Add fixed-point helper to get rounded integer values
Maíra Canal <[email protected]>
drm/vkms: isolate pixel conversion functionality
Bard Liao <[email protected]>
ASoC: Intel: sof_sdw: start set codec init function with an adr index
Bard Liao <[email protected]>
ASoC: Intel: sof_sdw: remove SOF_SDW_TGL_HDMI for MeteorLake devices
Trevor Wu <[email protected]>
ASoC: dt-bindings: mediatek,mt8188-afe: correct clock name
Dan Carpenter <[email protected]>
driver: soc: xilinx: use _safe loop iterator to avoid a use after free
Dmitry Baryshkov <[email protected]>
drm/panel: sharp-ls043t1le01: adjust mode settings
XuDong Liu <[email protected]>
drm: sun4i_tcon: use devm_clk_get_enabled in sun4i_tcon_init_clocks
Marek Vasut <[email protected]>
Input: adxl34x - do not hardcode interrupt trigger type
Marek Vasut <[email protected]>
clk: rs9: Fix .driver_data content in i2c_device_id
Marek Vasut <[email protected]>
clk: vc7: Fix .driver_data content in i2c_device_id
Marek Vasut <[email protected]>
clk: vc5: Fix .driver_data content in i2c_device_id
[email protected] <[email protected]>
ARM: dts: meson8b: correct uart_B and uart_C clock references
Rafał Miłecki <[email protected]>
ARM: dts: BCM5301X: Drop "clock-names" from the SPI node
Luc Ma <[email protected]>
drm/vram-helper: fix function names in vram helper doc
Dmitry Torokhov <[email protected]>
Input: tests - fix input_test_match_device_id test
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix THS_TRAILCNT computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix TXTAGOCNT computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix THS_ZEROCNT computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix TCLK_TRAILCNT computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: Add atomic_get_input_bus_fmts() implementation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix TCLK_ZEROCNT computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix PLL target frequency
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: fix PLL parameters computation
Francesco Dolcini <[email protected]>
drm/bridge: tc358768: always enable HS video mode
Alexander Stein <[email protected]>
drm/bridge: ti-sn65dsi83: Fix enable error path
Geert Uytterhoeven <[email protected]>
Input: tests - modular KUnit tests should not depend on KUNIT=y
Geert Uytterhoeven <[email protected]>
Input: tests - fix use-after-free and refcount underflow in input_test_exit()
Duoming Zhou <[email protected]>
Input: cyttsp4_core - change del_timer_sync() to timer_shutdown_sync()
Luca Weiss <[email protected]>
Input: drv260x - sleep between polling GO bit
Markus Elfring <[email protected]>
drm/bridge: it6505: Move a variable assignment behind a null pointer check in receive_timing_debugfs_show()
Vinay Belgaumkar <[email protected]>
drm/i915/guc/slpc: Provide sysfs for efficient freq
Nicholas Kazlauskas <[email protected]>
drm/amd/display: Explicitly specify update type per plane info change
Nikita Zhandarovich <[email protected]>
radeon: avoid double free in ci_dpm_init()
Arnd Bergmann <[email protected]>
drm/amd/display: fix is_timing_changed() prototype
Wesley Chalmers <[email protected]>
drm/amd/display: Add logging for display MALL refresh setting
Srinivasan Shanmugam <[email protected]>
drm/amd/display: Unconditionally print when DP sink power state fails
Dan Carpenter <[email protected]>
drm/imx/lcdc: fix a NULL vs IS_ERR() bug in probe
Kuniyuki Iwashima <[email protected]>
netlink: Add __sock_i_ino() for __netlink_diag_dump().
Vladimir Oltean <[email protected]>
net: dsa: avoid suspicious RCU usage for synced VLAN-aware MAC addresses
Cambda Zhu <[email protected]>
ipvlan: Fix return value of ipvlan_queue_xmit()
Pablo Neira Ayuso <[email protected]>
netfilter: nf_tables: fix underflow in chain reference counter
Pablo Neira Ayuso <[email protected]>
netfilter: nf_tables: unbind non-anonymous set if rule construction fails
Ilia.Gavrilov <[email protected]>
netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value.
Florian Westphal <[email protected]>
netfilter: conntrack: dccp: copy entire header to stack buffer, not just basic one
Jeremy Sowden <[email protected]>
lib/ts_bm: reset initial match offset for every block of text
Lin Ma <[email protected]>
net: nfc: Fix use-after-free caused by nfc_llcp_find_local
Edward Cree <[email protected]>
sfc: fix crash when reading stats while NIC is resetting
David Howells <[email protected]>
ocfs2: Fix use of slab data with sendpage
Maxim Kochetkov <[email protected]>
net: axienet: Move reset before 64-bit DMA detection
Kuniyuki Iwashima <[email protected]>
gtp: Fix use-after-free in __gtp_encap_destroy().
Sabrina Dubroca <[email protected]>
selftests: rtnetlink: remove netdevsim device after ipsec offload test
Eric Dumazet <[email protected]>
sch_netem: fix issues in netem_change() vs get_dist_table()
Eric Dumazet <[email protected]>
bonding: do not assume skb mac_header is set
Eric Dumazet <[email protected]>
netlink: do not hard code device address lenth in fdb dumps
Eric Dumazet <[email protected]>
netlink: fix potential deadlock in netlink_set_err()
Bartosz Golaszewski <[email protected]>
net: stmmac: fix double serdes powerdown
Vinicius Costa Gomes <[email protected]>
igc: Work around HW bug causing missing timestamps
Vinicius Costa Gomes <[email protected]>
igc: Retrieve TX timestamp during interrupt handling
Vinicius Costa Gomes <[email protected]>
igc: Check if hardware TX timestamping is enabled earlier
Vinicius Costa Gomes <[email protected]>
igc: Fix race condition in PTP tx code
Jimmy Assarsson <[email protected]>
can: kvaser_pciefd: Set hardware timestamp on transmitted packets
Jimmy Assarsson <[email protected]>
can: kvaser_pciefd: Add function to set skb hwtstamps
Vincent Mailhol <[email protected]>
can: length: fix bitstuffing count
Gilad Sever <[email protected]>
bpf: Fix bpf socket lookup from tc/xdp to respect socket VRF bindings
Gilad Sever <[email protected]>
bpf: Call __bpf_sk_lookup()/__bpf_skc_lookup() directly via TC hookpoint
Gilad Sever <[email protected]>
bpf: Factor out socket lookup functions for the TC hookpoint.
Dmitry Antipov <[email protected]>
wifi: ath9k: convert msecs to jiffies where needed
Johannes Berg <[email protected]>
wifi: iwlwifi: mvm: check only affected links
Johannes Berg <[email protected]>
wifi: iwlwifi: mvm: indicate HW decrypt for beacon protection
Marek Vasut <[email protected]>
mmc: Add MMC_QUIRK_BROKEN_SD_CACHE for Kingston Canvas Go Plus from 11/2019
Douglas Anderson <[email protected]>
watchdog/hardlockup: keep kernel.nmi_watchdog sysctl as 0444 if probe fails
Lecopzer Chen <[email protected]>
watchdog/perf: adapt the watchdog_perf interface for async model
Douglas Anderson <[email protected]>
watchdog/hardlockup: rename some "NMI watchdog" constants/function
Douglas Anderson <[email protected]>
watchdog/hardlockup: move perf hardlockup checking/panic to common watchdog.c
Lecopzer Chen <[email protected]>
watchdog/hardlockup: change watchdog_nmi_enable() to void
Lecopzer Chen <[email protected]>
watchdog: remove WATCHDOG_DEFAULT
Mathieu Desnoyers <[email protected]>
mm: move mm_count into its own cache line
Ilan Peer <[email protected]>
wifi: ieee80211: Fix the common size calculation for reconfiguration ML
Johannes Berg <[email protected]>
wifi: cfg80211: fix regulatory disconnect with OCB/NAN
Benjamin Berg <[email protected]>
wifi: cfg80211: drop incorrect nontransmitted BSS update code
Benjamin Berg <[email protected]>
wifi: cfg80211: rewrite merging of inherited elements
Nicolas Cavallari <[email protected]>
wifi: mac80211: Remove "Missing iftype sband data/EHT cap" spam
Anjaneyulu <[email protected]>
wifi: iwlwifi: pcie: fix NULL pointer dereference in iwl_pcie_irq_rx_msix_handler()
Johannes Berg <[email protected]>
wifi: iwlwifi: pull from TXQs with softirqs disabled
Johannes Berg <[email protected]>
wifi: iwlwifi: mvm: correctly access HE/EHT sband capa
Gregory Greenman <[email protected]>
wifi: iwlwifi: mvm: add support for Extra EHT LTF
Johannes Berg <[email protected]>
wifi: mac80211: add helpers to access sband iftype data
Ziyang Huang <[email protected]>
wifi: ath11k: Add missing hw_ops->get_ring_selector() for IPQ5018
Ziyang Huang <[email protected]>
wifi: ath11k: Restart firmware after cold boot calibration for IPQ5018
Ziyang Huang <[email protected]>
wifi: ath11k: Add missing ops config for IPQ5018 in ath11k_ahb_probe()
Jiasheng Jiang <[email protected]>
wifi: ath11k: Add missing check for ioremap
Edwin Peer <[email protected]>
rtnetlink: extend RTEXT_FILTER_SKIP_STATS to IFLA_VF_INFO
Mukesh Sisodiya <[email protected]>
wifi: iwlwifi: fw: print PC register value instead of address
Mukesh Sisodiya <[email protected]>
wifi: iwlwifi: mvm: Handle return value for iwl_mvm_sta_init
Ilan Peer <[email protected]>
wifi: mac80211: Fix permissions for valid_links debugfs entry
Eduard Zingerman <[email protected]>
bpf: Verify scalar ids mapping in regsafe() using check_ids()
Eduard Zingerman <[email protected]>
bpf: Use scalar ids in mark_chain_precision()
Remi Pommarel <[email protected]>
wifi: ath9k: Fix possible stall on ath9k_txq_list_has_key()
Eduard Zingerman <[email protected]>
selftests/bpf: Fix invalid pointer check in get_xlated_program()
Arnd Bergmann <[email protected]>
memstick r592: make memstick_debug_get_tpc_name() static
Douglas Anderson <[email protected]>
mmc: mediatek: Avoid ugly error message when SDIO wakeup IRQ isn't used
Zhen Lei <[email protected]>
kexec: fix a memory leak in crash_shrink_memory()
Douglas Anderson <[email protected]>
watchdog/perf: more properly prevent false positives with turbo modes
Douglas Anderson <[email protected]>
watchdog/perf: define dummy watchdog_update_hrtimer_threshold() on correct config
Haifeng Xu <[email protected]>
selftests: cgroup: fix unexpected failure on test_memcg_low
Karol Kolacinski <[email protected]>
ice: handle extts in the miscellaneous interrupt thread
Marek Vasut <[email protected]>
wifi: rsi: Do not set MMC_PM_KEEP_POWER in shutdown
Marek Vasut <[email protected]>
wifi: rsi: Do not configure WoWlan in shutdown hook if not enabled
Vijaya Krishna Nivarthi <[email protected]>
spi: spi-geni-qcom: Do not do DMA map/unmap inside driver, use framework instead
Vijaya Krishna Nivarthi <[email protected]>
soc: qcom: geni-se: Add interfaces geni_se_tx_init_dma() and geni_se_rx_init_dma()
Jesper Dangaard Brouer <[email protected]>
selftests/bpf: Fix check_mtu using wrong variable type
Johannes Berg <[email protected]>
wifi: mac80211: recalc min chandef for new STA links
Johannes Berg <[email protected]>
wifi: iwlwifi: mvm: send time sync only if needed
Viktor Malik <[email protected]>
tools/resolve_btfids: Fix setting HOSTCFLAGS
Dave Marchevsky <[email protected]>
bpf: Make bpf_refcount_acquire fallible for non-owning refs
Dave Marchevsky <[email protected]>
bpf: Fix __bpf_{list,rbtree}_add's beginning-of-node calculation
Dave Marchevsky <[email protected]>
bpf: Set kptr_struct_meta for node param to list and rbtree insert funcs
Dave Marchevsky <[email protected]>
bpf: Remove anonymous union in bpf_kfunc_call_arg_meta
Youghandhar Chintala <[email protected]>
wifi: ath10k: Trigger STA disconnect after reconfig complete on hardware restart
Jesper Dangaard Brouer <[email protected]>
samples/bpf: xdp1 and xdp2 reduce XDPBUFSIZE to 60
Sascha Hauer <[email protected]>
wifi: rtw88: usb: silence log flooding error message
Fedor Pchelkin <[email protected]>
wifi: ath9k: don't allow to overwrite ENDPOINT0 attributes
Christophe JAILLET <[email protected]>
wifi: ray_cs: Fix an error handling path in ray_probe()
Christophe JAILLET <[email protected]>
wifi: wl3501_cs: Fix an error handling path in wl3501_probe()
Christophe JAILLET <[email protected]>
wifi: atmel: Fix an error handling path in atmel_probe()
Christophe JAILLET <[email protected]>
wifi: orinoco: Fix an error handling path in orinoco_cs_probe()
Christophe JAILLET <[email protected]>
wifi: orinoco: Fix an error handling path in spectrum_cs_probe()
Geert Uytterhoeven <[email protected]>
regulator: core: Streamline debugfs operations
Geert Uytterhoeven <[email protected]>
regulator: core: Fix more error checking for debugfs_create_dir()
Sebastian Reichel <[email protected]>
regulator: rk808: fix asynchronous probing
Alexey Gladkov <[email protected]>
selftests/bpf: Do not use sign-file as testcase
Yafang Shao <[email protected]>
bpf: Fix memleak due to fentry attach failure
Yafang Shao <[email protected]>
bpf: Remove bpf trampoline selector
Alan Maguire <[email protected]>
bpftool: JIT limited misreported as negative value on aarch64
Krzysztof Kozlowski <[email protected]>
nfc: llcp: fix possible use of uninitialized variable in nfc_llcp_send_connect()
Joy Chakraborty <[email protected]>
spi: dw: Round of n_bytes to power of 2
Stanislav Fomichev <[email protected]>
bpf: Don't EFAULT for {g,s}setsockopt with wrong optlen
Andrii Nakryiko <[email protected]>
libbpf: fix offsetof() and container_of() to work with CO-RE
Edward Cree <[email protected]>
sfc: release encap match in efx_tc_flow_free()
Alexander Mikhalitsyn <[email protected]>
sctp: add bpf_bypass_getsockopt proto callback
Chuck Lever <[email protected]>
net/handshake: Unpin sock->file if a handshake is cancelled
Christophe JAILLET <[email protected]>
wifi: mwifiex: Fix the size of a memory allocation in mwifiex_ret_802_11_scan()
Dan Carpenter <[email protected]>
wifi: rtw88: unlock on error path in rtw_ops_add_interface()
Amisha Patel <[email protected]>
wifi: wilc1000: fix for absent RSN capabilities WFA testcase
Vijaya Krishna Nivarthi <[email protected]>
spi: spi-geni-qcom: Correct CS_TOGGLE bit in SPI_TRANS_CFG
Pengcheng Yang <[email protected]>
samples/bpf: Fix buffer overflow in tcp_basertt
Dan Carpenter <[email protected]>
wifi: rtw89: fix rtw89_read_chip_ver() for RTL8852B and RTL8851B
Andrii Nakryiko <[email protected]>
bpf: fix propagate_precision() logic for inner frames
Andrii Nakryiko <[email protected]>
bpf: maintain bitmasks across all active frames in __mark_chain_precision
Andrii Nakryiko <[email protected]>
bpf: improve precision backtrack logging
Andrii Nakryiko <[email protected]>
bpf: encapsulate precision backtracking bookkeeping
Martin KaFai Lau <[email protected]>
libbpf: btf_dump_type_data_check_overflow needs to consider BTF_MEMBER_BITFIELD_SIZE
Fedor Pchelkin <[email protected]>
wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx
Peter Seiderer <[email protected]>
wifi: ath9k: fix AR9003 mac hardware hang check register offset calculation
Jesper Dangaard Brouer <[email protected]>
igc: Enable and fix RX hash usage by netstack
Hao Jia <[email protected]>
sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
Jiasheng Jiang <[email protected]>
pstore/ram: Add check for kstrdup
Roberto Sassu <[email protected]>
ima: Fix build warnings
Roberto Sassu <[email protected]>
evm: Fix build warnings
Roberto Sassu <[email protected]>
evm: Complete description of evm_inode_setattr()
Mark Rutland <[email protected]>
locking/atomic: arm: fix sync ops
Tetsuo Handa <[email protected]>
reiserfs: Initialize sec->length in reiserfs_security_init().
Juergen Gross <[email protected]>
x86/mm: Fix __swp_entry_to_pte() for Xen PV guests
Ravi Bangoria <[email protected]>
perf/ibs: Fix interface via core pmu events
Mark Brown <[email protected]>
selftests/ftace: Fix KTAP output ordering
Colin Ian King <[email protected]>
kselftest: vDSO: Fix accumulation of uninitialized ret when CLOCK_REALTIME is undefined
Thomas Weißschuh <[email protected]>
tools/nolibc: ensure fast64 integer types have 64 bits
Juergen Gross <[email protected]>
x86/xen: Set MTRR state when running as Xen PV initial domain
Juergen Gross <[email protected]>
x86/mtrr: Replace size_or_mask and size_and_mask with a much easier concept
Juergen Gross <[email protected]>
x86/hyperv: Set MTRR state when running as SEV-SNP Hyper-V guest
Juergen Gross <[email protected]>
x86/mtrr: Support setting MTRR state for software defined MTRRs
Juergen Gross <[email protected]>
x86/mtrr: Remove physical address size calculation
Qiuxu Zhuo <[email protected]>
rcu/rcuscale: Stop kfree_scale_thread thread(s) after unloading rcuscale
Qiuxu Zhuo <[email protected]>
rcu/rcuscale: Move rcu_scale_*() after kfree_scale_cleanup()
Paul E. McKenney <[email protected]>
rcutorture: Correct name of use_softirq module parameter
Paul E. McKenney <[email protected]>
rcu-tasks: Stop rcu_tasks_invoke_cbs() from using never-onlined CPUs
Paul E. McKenney <[email protected]>
rcu: Make rcu_cpu_starting() rely on interrupts being disabled
Daniel Latypov <[email protected]>
kunit: tool: undo type subscripts for subprocess.Popen
Peng Fan <[email protected]>
thermal/drivers/qoriq: Only enable supported sensors
Christophe JAILLET <[email protected]>
thermal/drivers/sun8i: Fix some error handling paths in sun8i_ths_probe()
Stephan Gerhold <[email protected]>
thermal/drivers/qcom/tsens-v0_1: Add mdm9607 correction offsets
Stephan Gerhold <[email protected]>
thermal/drivers/qcom/tsens-v0_1: Fix mdm9607 slope values
Matti Lehtimäki <[email protected]>
thermal/drivers/qcom/tsens-v0_1: Add support for MSM8226
Tero Kristo <[email protected]>
cpufreq: intel_pstate: Fix energy_performance_preference for passive
Arnd Bergmann <[email protected]>
ARM: 9303/1: kprobes: avoid missing-declaration warnings
Ulf Hansson <[email protected]>
PM: domains: Move the verification of in-params from genpd_add_device()
Zhang Rui <[email protected]>
powercap: RAPL: Fix CONFIG_IOSF_MBI dependency
Sumeet Pawnikar <[email protected]>
powercap: RAPL: fix invalid initialization for pl4_supported field
Li Yang <[email protected]>
APEI: GHES: correctly return NULL for ghes_get_devices()
Robin Murphy <[email protected]>
perf/arm_cspmu: Fix event attribute type
Ilkka Koskinen <[email protected]>
perf: arm_cspmu: Set irq affinitiy only if overflow interrupt is used
Junhao He <[email protected]>
drivers/perf: hisi: Don't migrate perf to the CPU going to teardown
Kirill A. Shutemov <[email protected]>
x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()
Kirill A. Shutemov <[email protected]>
x86/mm: Allow guest.enc_status_change_prepare() to fail
Marc Zyngier <[email protected]>
drivers/perf: apple_m1: Force 63bit counters for M2 CPUs
Robin Murphy <[email protected]>
perf/arm-cmn: Fix DTC reset
Nikita Zhandarovich <[email protected]>
PM: domains: fix integer overflow issues in genpd_parse_state()
Feng Mingxi <[email protected]>
clocksource/drivers/cadence-ttc: Fix memory leak in ttc_timer_probe
Ming Lei <[email protected]>
blk-mq: don't insert passthrough request into sw queue
Christoph Hellwig <[email protected]>
btrfs: fix file_offset for REQ_BTRFS_ONE_ORDERED bios that get split
Christoph Hellwig <[email protected]>
btrfs: don't treat zoned writeback as being from an async helper thread
Christoph Hellwig <[email protected]>
btrfs: only call __extent_writepage_io from extent_write_locked_range
Christoph Hellwig <[email protected]>
btrfs: don't fail writeback when allocating the compression context fails
Christoph Hellwig <[email protected]>
btrfs: fix range_end calculation in extent_write_locked_range
Christoph Hellwig <[email protected]>
btrfs: submit a writeback bio per extent_buffer
Christoph Hellwig <[email protected]>
btrfs: return bool from lock_extent_buffer_for_io
Christoph Hellwig <[email protected]>
btrfs: don't use btrfs_bio_ctrl for extent buffer reading
Christoph Hellwig <[email protected]>
btrfs: always read the entire extent_buffer
Sebastian Andrzej Siewior <[email protected]>
tracing/timer: Add missing hrtimer modes to decode_hrtimer_mode().
Wen Yang <[email protected]>
tick/rcu: Fix bogus ratelimit condition
Thomas Gleixner <[email protected]>
posix-timers: Prevent RT livelock in itimer_delete()
Gao Xiang <[email protected]>
erofs: fix compact 4B support for 16k block size
Chuck Lever <[email protected]>
svcrdma: Prevent page release when nothing was received
John Paul Adrian Glaubitz <[email protected]>
irqchip/jcore-aic: Fix missing allocation of IRQ descriptors
Antonio Borneo <[email protected]>
irqchip/stm32-exti: Fix warning on initialized field overwritten
Christoph Hellwig <[email protected]>
splice: don't call file_accessed in copy_splice_read
Jianmin Lv <[email protected]>
irqchip/loongson-eiointc: Fix irq affinity setting during resume
Yu Kuai <[email protected]>
block: fix blktrace debugfs entries leakage
Yu Kuai <[email protected]>
md/raid1-10: submit write io directly if bitmap is not enabled
Yu Kuai <[email protected]>
md/raid1-10: factor out a helper to submit normal write
Yu Kuai <[email protected]>
md/raid1-10: factor out a helper to add bio to plug
Li Nan <[email protected]>
md/raid10: fix io loss while replacement replace rdev
Li Nan <[email protected]>
md/raid10: fix null-ptr-deref of mreplace in raid10_sync_request
Li Nan <[email protected]>
md/raid10: fix wrong setting of max_corr_read_errors
Li Nan <[email protected]>
md/raid10: fix overflow of md/safe_mode_delay
Li Nan <[email protected]>
md/raid10: check slab-out-of-bounds in md_bitmap_get_counter
Chaitanya Kulkarni <[email protected]>
nvme-core: fix dev_pm_qos memleak
Chaitanya Kulkarni <[email protected]>
nvme-core: add missing fault-injection cleanup
Chaitanya Kulkarni <[email protected]>
nvme-core: fix memory leak in dhchap_ctrl_secret
Chaitanya Kulkarni <[email protected]>
nvme-core: fix memory leak in dhchap_secret_store
NeilBrown <[email protected]>
lockd: drop inappropriate svc_get() from locked_get()
Yu Kuai <[email protected]>
blk-mq: fix potential io hang by wrong 'wake_batch'
Arnd Bergmann <[email protected]>
virt: sevguest: Add CONFIG_CRYPTO dependency
Waiman Long <[email protected]>
blk-cgroup: Reinit blkg_iostat_set after clearing in blkcg_reset_stats()
Tom Lendacky <[email protected]>
x86/sev: Fix calculation of end address based on number of pages
Li Nan <[email protected]>
blk-iocost: use spin_lock_irqsave in adjust_inuse_and_calc_cost
Eric Biggers <[email protected]>
fsverity: don't use bio_first_page_all() in fsverity_verify_bio()
Eric Biggers <[email protected]>
fsverity: use shash API instead of ahash API
Shawn Wang <[email protected]>
x86/resctrl: Only show tasks' pid in current pid namespace
Gao Xiang <[email protected]>
erofs: kill hooked chains to avoid loops on deduplicated compressed images
David Howells <[email protected]>
splice: Fix filemap_splice_read() to use the correct inode
Yu Kuai <[email protected]>
block/rq_qos: protect rq_qos apis with a new lock
Bart Van Assche <[email protected]>
block: Fix the type of the second bdev_op_is_zoned_write() argument
Ming Lei <[email protected]>
blk-mq: don't queue plugged passthrough requests into scheduler
Alexander Gordeev <[email protected]>
s390/kasan: fix insecure W+X mapping warning
Arnd Bergmann <[email protected]>
fs: pipe: reveal missing function protoypes
Hersen Wu <[email protected]>
Revert "drm/amd/display: edp do not add non-edid timings"
Sean Nyekjaer <[email protected]>
iio: accel: fxls8962af: fixup buffer scan element type
Sean Nyekjaer <[email protected]>
iio: accel: fxls8962af: errata bug only applicable for FXLS8962AF
Fabrizio Lamarque <[email protected]>
iio: adc: ad7192: Fix internal/external clock selection
Fabrizio Lamarque <[email protected]>
iio: adc: ad7192: Fix null ad7192_state pointer access
Rasmus Villemoes <[email protected]>
iio: addac: ad74413: don't set DIN_SINK for functions other than digital input
Fabrizio Lamarque <[email protected]>
dt-bindings: iio: ad7192: Add mandatory reference voltage source
Alvin Šipraga <[email protected]>
extcon: usbc-tusb320: Unregister typec port on driver removal
EJ Hsu <[email protected]>
phy: tegra: xusb: Clear the driver reference in usb-phy dev
Krishna Kurapati <[email protected]>
usb: dwc3: gadget: Propagate core init errors to UDC during pullup
Davide Tronchin <[email protected]>
USB: serial: option: add LARA-R6 01B PIDs
[email protected] <[email protected]>
start_kernel: Add __no_stack_protector function attribute
-------------
Diffstat:
Documentation/ABI/testing/sysfs-driver-eud | 2 +- .../devicetree/bindings/crypto/qcom-qce.yaml | 6 + .../devicetree/bindings/iio/adc/adi,ad7192.yaml | 5 + .../devicetree/bindings/iommu/arm,smmu.yaml | 6 +- .../devicetree/bindings/power/reset/qcom,pon.yaml | 4 +- .../bindings/sound/mediatek,mt8188-afe.yaml | 36 +- Documentation/fault-injection/provoke-crashes.rst | 2 +- Documentation/filesystems/autofs-mount-control.rst | 2 +- Documentation/filesystems/autofs.rst | 2 +- Documentation/filesystems/directory-locking.rst | 26 +- Documentation/filesystems/f2fs.rst | 16 + Documentation/networking/af_xdp.rst | 9 + Makefile | 4 +- arch/arc/include/asm/linkage.h | 8 +- arch/arm/boot/dts/bcm53015-meraki-mr26.dts | 2 +- arch/arm/boot/dts/bcm53016-meraki-mr32.dts | 2 +- arch/arm/boot/dts/bcm5301x.dtsi | 1 - arch/arm/boot/dts/iwg20d-q7-common.dtsi | 2 +- .../boot/dts/lan966x-kontron-kswitch-d10-mmt.dtsi | 16 +- arch/arm/boot/dts/meson8.dtsi | 4 +- arch/arm/boot/dts/meson8b.dtsi | 4 +- arch/arm/boot/dts/omap3-gta04a5one.dts | 4 +- arch/arm/boot/dts/qcom-apq8060-dragonboard.dts | 4 +- arch/arm/boot/dts/qcom-apq8074-dragonboard.dts | 4 + arch/arm/boot/dts/qcom-ipq4019-ap.dk04.1-c1.dts | 8 +- arch/arm/boot/dts/qcom-ipq4019-ap.dk04.1.dtsi | 10 +- arch/arm/boot/dts/qcom-ipq4019-ap.dk07.1.dtsi | 12 +- arch/arm/boot/dts/qcom-msm8974.dtsi | 2 +- arch/arm/boot/dts/stm32mp15xx-dhcom-pdk2.dtsi | 11 +- arch/arm/boot/dts/stm32mp15xx-dhcor-avenger96.dtsi | 8 +- .../boot/dts/stm32mp15xx-dhcor-drc-compact.dtsi | 6 + arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi | 6 - arch/arm/boot/dts/stm32mp15xx-dhcor-testbench.dtsi | 8 + arch/arm/boot/dts/stm32mp15xx-dkx.dtsi | 2 +- arch/arm/include/asm/assembler.h | 17 + arch/arm/include/asm/sync_bitops.h | 29 +- arch/arm/lib/bitops.h | 14 +- arch/arm/lib/testchangebit.S | 4 + arch/arm/lib/testclearbit.S | 4 + arch/arm/lib/testsetbit.S | 4 + arch/arm/mach-ep93xx/timer-ep93xx.c | 3 +- arch/arm/mach-omap1/board-ams-delta.c | 1 - arch/arm/mach-omap1/board-nokia770.c | 207 +++--- arch/arm/mach-omap1/board-osk.c | 146 +++-- arch/arm/mach-omap1/board-palmte.c | 51 +- arch/arm/mach-omap1/board-sx1-mmc.c | 1 - arch/arm/mach-omap1/board-sx1.c | 40 +- arch/arm/mach-omap1/devices.c | 1 - arch/arm/mach-omap1/gpio15xx.c | 1 - arch/arm/mach-omap1/gpio16xx.c | 1 - arch/arm/mach-omap1/irq.c | 1 - arch/arm/mach-omap1/serial.c | 30 +- arch/arm/mach-omap2/board-generic.c | 1 + arch/arm/mach-omap2/board-n8x0.c | 156 ++--- arch/arm/mach-omap2/omap_device.c | 1 - arch/arm/mach-omap2/pdata-quirks.c | 132 ++-- arch/arm/mach-omap2/usb-tusb6010.c | 20 +- arch/arm/mach-omap2/usb-tusb6010.h | 12 + arch/arm/mach-orion5x/board-dt.c | 3 + arch/arm/mach-orion5x/common.h | 6 + arch/arm/mach-pxa/spitz.c | 11 +- arch/arm/probes/kprobes/checkers-common.c | 2 +- arch/arm/probes/kprobes/core.c | 2 +- arch/arm/probes/kprobes/opt-arm.c | 2 - arch/arm/probes/kprobes/test-core.c | 2 +- arch/arm/probes/kprobes/test-core.h | 4 + .../dts/mediatek/mt7986a-bananapi-bpi-r3-nand.dtso | 6 +- arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi | 4 + arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi | 4 + arch/arm64/boot/dts/mediatek/mt8192.dtsi | 22 +- arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi | 4 + arch/arm64/boot/dts/microchip/sparx5.dtsi | 2 +- .../boot/dts/microchip/sparx5_pcb_common.dtsi | 12 + arch/arm64/boot/dts/qcom/apq8016-sbc.dts | 78 ++- arch/arm64/boot/dts/qcom/apq8096-ifc6640.dts | 4 +- arch/arm64/boot/dts/qcom/ipq6018.dtsi | 2 +- arch/arm64/boot/dts/qcom/ipq9574.dtsi | 6 +- arch/arm64/boot/dts/qcom/msm8916.dtsi | 8 +- arch/arm64/boot/dts/qcom/msm8953.dtsi | 4 +- arch/arm64/boot/dts/qcom/msm8976.dtsi | 6 +- arch/arm64/boot/dts/qcom/msm8994.dtsi | 2 +- arch/arm64/boot/dts/qcom/msm8996.dtsi | 2 +- arch/arm64/boot/dts/qcom/pm7250b.dtsi | 1 + arch/arm64/boot/dts/qcom/pm8998.dtsi | 2 +- arch/arm64/boot/dts/qcom/qdu1000.dtsi | 1 + arch/arm64/boot/dts/qcom/qrb4210-rb2.dts | 3 +- arch/arm64/boot/dts/qcom/sdm630.dtsi | 2 +- arch/arm64/boot/dts/qcom/sdm670.dtsi | 1 + arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts | 1 + arch/arm64/boot/dts/qcom/sdm845.dtsi | 3 +- arch/arm64/boot/dts/qcom/sm6115.dtsi | 2 +- .../boot/dts/qcom/sm8250-sony-xperia-edo.dtsi | 7 +- arch/arm64/boot/dts/qcom/sm8350.dtsi | 6 +- arch/arm64/boot/dts/qcom/sm8550.dtsi | 9 +- arch/arm64/boot/dts/renesas/ulcb-kf.dtsi | 3 +- .../boot/dts/rockchip/rk3566-anbernic-rgxx3.dtsi | 2 +- arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts | 2 + arch/arm64/boot/dts/ti/k3-am69-sk.dts | 2 +- .../boot/dts/ti/k3-j7200-common-proc-board.dts | 28 +- arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts | 5 + arch/arm64/boot/dts/ti/k3-j784s4-evm.dts | 32 +- arch/arm64/boot/dts/ti/k3-j784s4-mcu-wakeup.dtsi | 29 +- arch/arm64/include/asm/fpsimdmacros.h | 6 +- arch/arm64/kernel/signal.c | 2 +- arch/loongarch/Makefile | 2 +- arch/mips/Makefile | 2 +- arch/mips/alchemy/devboards/db1000.c | 11 +- arch/mips/boot/dts/ingenic/ci20.dts | 38 +- arch/powerpc/Kconfig.debug | 2 +- arch/powerpc/boot/dts/turris1x.dts | 6 +- arch/powerpc/include/asm/nmi.h | 4 +- arch/powerpc/kernel/interrupt.c | 3 +- arch/powerpc/kernel/ppc_save_regs.S | 6 +- arch/powerpc/kernel/signal_32.c | 15 +- arch/powerpc/kernel/smp.c | 1 + arch/powerpc/kernel/vdso/Makefile | 2 +- arch/powerpc/kernel/watchdog.c | 12 +- arch/powerpc/mm/book3s64/radix_pgtable.c | 34 +- arch/powerpc/mm/init_64.c | 2 +- arch/powerpc/platforms/powernv/pci-sriov.c | 6 +- arch/powerpc/platforms/powernv/vas-window.c | 2 +- arch/powerpc/platforms/pseries/mobility.c | 4 +- arch/powerpc/platforms/pseries/vas.c | 2 +- arch/riscv/kernel/hibernate-asm.S | 1 - arch/riscv/kernel/hibernate.c | 1 - arch/riscv/kernel/probes/uprobes.c | 2 + arch/riscv/kernel/smpboot.c | 5 +- arch/riscv/mm/init.c | 4 +- arch/s390/kvm/diag.c | 8 +- arch/s390/kvm/kvm-s390.c | 4 + arch/s390/kvm/vsie.c | 6 +- arch/s390/mm/vmem.c | 14 +- arch/sh/drivers/dma/dma-sh.c | 37 +- arch/sh/include/mach-common/mach/highlander.h | 2 +- arch/sh/include/mach-common/mach/r2d.h | 2 +- arch/sh/include/mach-dreamcast/mach/sysasic.h | 2 +- arch/sh/include/mach-se/mach/se7724.h | 2 +- arch/sh/kernel/cpu/sh2/probe.c | 2 +- arch/sh/kernel/cpu/sh3/entry.S | 4 +- arch/sparc/kernel/nmi.c | 10 +- arch/um/Makefile | 2 +- arch/x86/coco/tdx/tdx.c | 51 +- arch/x86/events/amd/core.c | 2 +- arch/x86/events/amd/ibs.c | 53 +- arch/x86/hyperv/ivm.c | 4 + arch/x86/include/asm/mtrr.h | 40 +- arch/x86/include/asm/perf_event.h | 2 + arch/x86/include/asm/pgtable_64.h | 4 +- arch/x86/include/asm/sev.h | 16 +- arch/x86/include/asm/x86_init.h | 2 +- arch/x86/include/uapi/asm/mtrr.h | 8 - arch/x86/kernel/cpu/mtrr/cleanup.c | 18 +- arch/x86/kernel/cpu/mtrr/generic.c | 124 +++- arch/x86/kernel/cpu/mtrr/mtrr.c | 73 +-- arch/x86/kernel/cpu/mtrr/mtrr.h | 4 +- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 8 +- arch/x86/kernel/setup.c | 2 + arch/x86/kernel/sev.c | 14 +- arch/x86/kernel/x86_init.c | 2 +- arch/x86/mm/mem_encrypt_amd.c | 4 +- arch/x86/mm/pat/set_memory.c | 3 +- arch/x86/platform/efi/efi_64.c | 6 +- arch/x86/xen/enlighten_pv.c | 52 ++ block/blk-cgroup.c | 20 +- block/blk-core.c | 1 + block/blk-iocost.c | 7 +- block/blk-mq-debugfs.c | 2 +- block/blk-mq-tag.c | 15 +- block/blk-mq.c | 13 +- block/blk-mq.h | 3 +- block/blk-rq-qos.c | 20 +- block/blk-throttle.c | 6 - block/blk-throttle.h | 9 + block/blk-wbt.c | 2 + block/disk-events.c | 1 + block/genhd.c | 5 +- block/partitions/amiga.c | 102 ++- crypto/jitterentropy.c | 9 +- drivers/accel/habanalabs/gaudi2/gaudi2.c | 2 +- drivers/acpi/apei/ghes.c | 2 + drivers/base/power/domain.c | 15 +- drivers/base/property.c | 12 +- drivers/bus/fsl-mc/dprc-driver.c | 6 + drivers/bus/ti-sysc.c | 4 +- drivers/cdx/cdx.c | 18 + drivers/char/hw_random/st-rng.c | 21 +- drivers/char/hw_random/virtio-rng.c | 10 +- drivers/clk/bcm/clk-raspberrypi.c | 4 +- drivers/clk/clk-cdce925.c | 12 + drivers/clk/clk-renesas-pcie.c | 4 +- drivers/clk/clk-si5341.c | 38 +- drivers/clk/clk-versaclock5.c | 45 +- drivers/clk/clk-versaclock7.c | 2 +- drivers/clk/clk.c | 2 + drivers/clk/imx/clk-composite-8m.c | 31 + drivers/clk/imx/clk-imx8mn.c | 8 +- drivers/clk/imx/clk-imx8mp.c | 24 +- drivers/clk/imx/clk-imx93.c | 15 +- drivers/clk/imx/clk-imxrt1050.c | 22 +- drivers/clk/imx/clk-scu.c | 4 +- drivers/clk/keystone/sci-clk.c | 2 + drivers/clk/mediatek/clk-mt8173-apmixedsys.c | 7 +- drivers/clk/mediatek/clk-mtk.c | 13 +- drivers/clk/qcom/camcc-sc7180.c | 19 +- drivers/clk/qcom/dispcc-qcm2290.c | 12 +- drivers/clk/qcom/gcc-ipq5332.c | 6 +- drivers/clk/qcom/gcc-ipq6018.c | 34 +- drivers/clk/qcom/gcc-qcm2290.c | 62 +- drivers/clk/qcom/mmcc-msm8974.c | 23 +- drivers/clk/renesas/rzg2l-cpg.c | 6 +- drivers/clk/renesas/rzg2l-cpg.h | 3 - drivers/clk/tegra/clk-tegra124-emc.c | 2 + drivers/clk/ti/clkctrl.c | 7 + drivers/clk/xilinx/clk-xlnx-clock-wizard.c | 7 +- drivers/clocksource/timer-cadence-ttc.c | 19 +- drivers/cpufreq/intel_pstate.c | 2 + drivers/cpufreq/mediatek-cpufreq.c | 13 +- drivers/cpufreq/tegra194-cpufreq.c | 6 +- .../crypto/intel/qat/qat_common/qat_asym_algs.c | 14 +- drivers/crypto/marvell/cesa/cipher.c | 2 +- drivers/crypto/nx/Makefile | 2 +- drivers/crypto/nx/nx.h | 4 +- drivers/cxl/core/region.c | 102 +-- drivers/cxl/cxl.h | 16 +- drivers/dax/bus.c | 61 +- drivers/dax/dax-private.h | 4 +- drivers/dax/kmem.c | 2 +- drivers/extcon/extcon-usbc-tusb320.c | 42 +- drivers/extcon/extcon.c | 8 + drivers/firmware/efi/libstub/efi-stub-helper.c | 6 +- drivers/gpio/gpio-twl4030.c | 52 +- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 11 +- drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 +- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c | 3 + drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 3 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 85 +-- drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c | 11 +- drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 4 +- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 13 +- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 +- .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 5 +- .../dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c | 3 + drivers/gpu/drm/amd/display/dc/core/dc.c | 3 - drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 6 +- drivers/gpu/drm/amd/display/dc/dc.h | 3 + .../gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c | 23 - .../gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h | 2 - .../gpu/drm/amd/display/dc/dcn314/dcn314_init.c | 2 +- .../amd/display/dc/dml/dcn21/display_mode_vba_21.c | 2 +- .../display/dc/dml/dcn32/display_rq_dlg_calc_32.c | 2 +- .../display/dc/link/protocols/link_dp_capability.c | 4 +- .../drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 18 +- .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 1 + drivers/gpu/drm/bridge/analogix/anx7625.c | 128 ++-- drivers/gpu/drm/bridge/ite-it6505.c | 3 +- drivers/gpu/drm/bridge/samsung-dsim.c | 22 +- drivers/gpu/drm/bridge/tc358767.c | 4 +- drivers/gpu/drm/bridge/tc358768.c | 93 ++- drivers/gpu/drm/bridge/ti-sn65dsi83.c | 20 +- drivers/gpu/drm/drm_gem_vram_helper.c | 6 +- drivers/gpu/drm/i915/Makefile | 2 + drivers/gpu/drm/i915/display/intel_color.c | 36 +- drivers/gpu/drm/i915/display/intel_crtc.c | 2 +- drivers/gpu/drm/i915/display/intel_cursor.c | 4 +- drivers/gpu/drm/i915/display/intel_display.c | 2 +- drivers/gpu/drm/i915/display/intel_display.h | 10 +- .../gpu/drm/i915/display/intel_display_device.c | 728 +++++++++++++++++++++ .../gpu/drm/i915/display/intel_display_device.h | 86 +++ drivers/gpu/drm/i915/display/intel_display_power.c | 6 +- .../gpu/drm/i915/display/intel_display_reg_defs.h | 14 +- drivers/gpu/drm/i915/display/intel_fb_pin.c | 2 +- drivers/gpu/drm/i915/display/intel_fbc.c | 6 +- drivers/gpu/drm/i915/display/intel_hdcp.c | 2 +- drivers/gpu/drm/i915/display/intel_hti.c | 2 +- drivers/gpu/drm/i915/display/intel_psr.c | 4 +- drivers/gpu/drm/i915/display/intel_psr_regs.h | 2 +- drivers/gpu/drm/i915/display/skl_universal_plane.c | 2 +- drivers/gpu/drm/i915/display/skl_watermark.c | 8 +- drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c | 35 + drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 40 +- drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h | 1 + drivers/gpu/drm/i915/gt/uc/intel_guc_slpc_types.h | 1 + drivers/gpu/drm/i915/i915_driver.c | 12 +- drivers/gpu/drm/i915/i915_drv.h | 52 +- drivers/gpu/drm/i915/i915_pci.c | 384 +---------- drivers/gpu/drm/i915/i915_reg.h | 33 - drivers/gpu/drm/i915/intel_device_info.c | 140 ++-- drivers/gpu/drm/i915/intel_device_info.h | 69 +- drivers/gpu/drm/i915/intel_step.c | 8 +- drivers/gpu/drm/imx/lcdc/imx-lcdc.c | 4 +- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 3 +- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 3 +- .../drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h | 12 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h | 8 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h | 12 +- .../drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 12 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h | 12 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h | 10 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h | 2 +- .../drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h | 2 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h | 18 +- .../gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h | 4 +- drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 5 +- .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c | 60 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c | 36 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 5 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c | 5 +- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c | 75 ++- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h | 31 +- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h | 4 + drivers/gpu/drm/msm/dp/dp_display.c | 16 +- drivers/gpu/drm/msm/dsi/dsi_host.c | 26 +- drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c | 3 + drivers/gpu/drm/nouveau/dispnv50/disp.c | 1 + drivers/gpu/drm/nouveau/nv50_display.h | 4 +- drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c | 11 +- drivers/gpu/drm/panel/panel-simple.c | 4 +- drivers/gpu/drm/radeon/ci_dpm.c | 28 +- drivers/gpu/drm/radeon/cypress_dpm.c | 8 +- drivers/gpu/drm/radeon/ni_dpm.c | 8 +- drivers/gpu/drm/radeon/rv740_dpm.c | 8 +- drivers/gpu/drm/sun4i/sun4i_tcon.c | 19 +- drivers/gpu/drm/vkms/vkms_composer.c | 4 +- drivers/gpu/drm/vkms/vkms_drv.h | 4 +- drivers/gpu/drm/vkms/vkms_formats.c | 131 ++-- drivers/gpu/drm/vkms/vkms_formats.h | 2 +- drivers/gpu/drm/vkms/vkms_plane.c | 2 +- drivers/hid/Kconfig | 2 +- drivers/hwmon/f71882fg.c | 7 +- drivers/hwmon/gsc-hwmon.c | 6 +- drivers/hwmon/pmbus/adm1275.c | 52 +- drivers/hwtracing/coresight/coresight-core.c | 9 +- .../hwtracing/coresight/coresight-etm4x-sysfs.c | 27 +- drivers/hwtracing/ptt/hisi_ptt.c | 12 +- drivers/hwtracing/ptt/hisi_ptt.h | 2 + drivers/i2c/busses/i2c-designware-pcidrv.c | 13 +- drivers/i2c/busses/i2c-nvidia-gpu.c | 3 + drivers/i2c/busses/i2c-xiic.c | 2 + drivers/i3c/master/svc-i3c-master.c | 19 +- drivers/iio/accel/fxls8962af-core.c | 8 +- drivers/iio/adc/ad7192.c | 8 +- drivers/iio/addac/ad74413r.c | 11 +- drivers/infiniband/hw/bnxt_re/main.c | 20 +- drivers/infiniband/hw/bnxt_re/qplib_fp.c | 40 +- drivers/infiniband/hw/bnxt_re/qplib_fp.h | 2 +- drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 46 +- drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 1 + drivers/infiniband/hw/hfi1/ipoib_tx.c | 4 +- drivers/infiniband/hw/hfi1/mmu_rb.c | 101 +-- drivers/infiniband/hw/hfi1/mmu_rb.h | 3 + drivers/infiniband/hw/hfi1/sdma.c | 23 +- drivers/infiniband/hw/hfi1/sdma.h | 47 +- drivers/infiniband/hw/hfi1/sdma_txreq.h | 2 + drivers/infiniband/hw/hfi1/user_sdma.c | 137 ++-- drivers/infiniband/hw/hfi1/user_sdma.h | 1 - drivers/infiniband/hw/hfi1/vnic_sdma.c | 4 +- drivers/infiniband/hw/hns/hns_roce_hem.c | 7 +- drivers/infiniband/hw/irdma/uk.c | 10 +- drivers/infiniband/sw/rxe/rxe_mw.c | 17 +- drivers/input/Kconfig | 2 +- drivers/input/misc/adxl34x.c | 3 +- drivers/input/misc/drv260x.c | 1 + drivers/input/misc/pm8941-pwrkey.c | 19 +- drivers/input/tests/input_test.c | 6 +- drivers/input/touchscreen/ads7846.c | 114 ++-- drivers/input/touchscreen/cyttsp4_core.c | 3 +- drivers/interconnect/qcom/icc-rpm.c | 12 +- drivers/interconnect/qcom/icc-rpm.h | 4 +- drivers/iommu/iommufd/device.c | 2 +- drivers/iommu/iommufd/io_pagetable.c | 14 +- drivers/iommu/virtio-iommu.c | 57 +- drivers/irqchip/irq-jcore-aic.c | 7 + drivers/irqchip/irq-loongson-eiointc.c | 2 +- drivers/irqchip/irq-loongson-liointc.c | 12 +- drivers/irqchip/irq-loongson-pch-pic.c | 10 +- drivers/irqchip/irq-stm32-exti.c | 12 + drivers/leds/trigger/ledtrig-netdev.c | 3 + drivers/mailbox/ti-msgmgr.c | 12 +- drivers/md/bcache/btree.c | 25 +- drivers/md/bcache/btree.h | 1 + drivers/md/bcache/super.c | 4 +- drivers/md/bcache/writeback.c | 10 + drivers/md/md-bitmap.c | 21 +- drivers/md/md-bitmap.h | 7 + drivers/md/md.c | 9 +- drivers/md/raid1-10.c | 42 ++ drivers/md/raid1.c | 25 +- drivers/md/raid10.c | 75 +-- drivers/media/cec/i2c/Kconfig | 1 + drivers/media/common/saa7146/saa7146_core.c | 6 +- drivers/media/i2c/Kconfig | 1 + drivers/media/i2c/hi846.c | 3 +- drivers/media/i2c/imx296.c | 4 +- drivers/media/i2c/st-mipid02.c | 9 +- drivers/media/platform/amphion/vdec.c | 7 +- drivers/media/platform/amphion/venc.c | 4 +- drivers/media/platform/amphion/vpu_malone.c | 12 + drivers/media/platform/amphion/vpu_v4l2.c | 5 +- drivers/media/platform/amphion/vpu_v4l2.h | 2 +- .../platform/mediatek/vcodec/vdec_msg_queue.c | 33 +- .../platform/mediatek/vcodec/vdec_msg_queue.h | 16 +- drivers/media/platform/qcom/venus/helpers.c | 4 +- drivers/media/platform/renesas/rcar_fdp1.c | 5 + drivers/media/usb/dvb-usb-v2/az6007.c | 3 +- drivers/media/usb/siano/smsusb.c | 3 +- drivers/memory/brcmstb_dpfe.c | 4 +- drivers/memstick/host/r592.c | 4 +- drivers/mfd/intel-lpss-acpi.c | 3 + drivers/mfd/rt5033.c | 3 - drivers/mfd/stmfx.c | 7 +- drivers/mfd/stmpe.c | 4 +- drivers/mfd/tps65010.c | 14 +- drivers/mfd/wcd934x.c | 9 +- drivers/misc/fastrpc.c | 3 + drivers/misc/lkdtm/core.c | 2 +- drivers/mmc/core/block.c | 6 + drivers/mmc/core/card.h | 30 +- drivers/mmc/core/quirks.h | 27 + drivers/mmc/core/sd.c | 2 +- drivers/mmc/host/mmci.c | 1 + drivers/mmc/host/mtk-sd.c | 2 +- drivers/mmc/host/omap.c | 46 +- drivers/mmc/host/sdhci.c | 4 +- drivers/net/bonding/bond_main.c | 2 +- drivers/net/can/kvaser_pciefd.c | 39 +- drivers/net/dsa/ocelot/felix.c | 12 + drivers/net/dsa/sja1105/sja1105.h | 2 +- drivers/net/dsa/sja1105/sja1105_main.c | 14 +- drivers/net/dsa/sja1105/sja1105_ptp.c | 48 +- drivers/net/dsa/vitesse-vsc73xx-core.c | 6 +- drivers/net/ethernet/broadcom/tg3.c | 1 + drivers/net/ethernet/ibm/ibmvnic.c | 9 +- drivers/net/ethernet/intel/ice/ice.h | 7 + drivers/net/ethernet/intel/ice/ice_main.c | 29 +- drivers/net/ethernet/intel/ice/ice_ptp.c | 12 +- drivers/net/ethernet/intel/ice/ice_ptp.h | 4 +- drivers/net/ethernet/intel/igc/igc.h | 36 +- drivers/net/ethernet/intel/igc/igc_main.c | 45 +- drivers/net/ethernet/intel/igc/igc_ptp.c | 142 ++-- drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 33 +- drivers/net/ethernet/marvell/octeontx2/af/cgx.h | 2 + .../ethernet/marvell/octeontx2/af/lmac_common.h | 3 + drivers/net/ethernet/marvell/octeontx2/af/rpm.c | 32 +- drivers/net/ethernet/marvell/octeontx2/af/rpm.h | 5 +- drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 1 + drivers/net/ethernet/marvell/octeontx2/af/rvu.h | 12 + .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c | 22 +- drivers/net/ethernet/mellanox/mlxsw/minimal.c | 1 + drivers/net/ethernet/mscc/ocelot.c | 1 - drivers/net/ethernet/mscc/ocelot_ptp.c | 66 +- drivers/net/ethernet/sfc/ef10.c | 13 +- drivers/net/ethernet/sfc/efx_devlink.c | 3 + drivers/net/ethernet/sfc/tc.c | 32 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 - drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 10 +- drivers/net/gtp.c | 2 + drivers/net/ipvlan/ipvlan_core.c | 9 +- drivers/net/ppp/pptp.c | 31 +- drivers/net/wireguard/netlink.c | 14 +- drivers/net/wireguard/queueing.c | 1 + drivers/net/wireguard/queueing.h | 25 +- drivers/net/wireguard/receive.c | 2 +- drivers/net/wireguard/send.c | 2 +- drivers/net/wireless/ath/ath10k/core.c | 12 +- drivers/net/wireless/ath/ath10k/core.h | 3 + drivers/net/wireless/ath/ath10k/mac.c | 13 +- drivers/net/wireless/ath/ath11k/ahb.c | 1 + drivers/net/wireless/ath/ath11k/core.c | 1 + drivers/net/wireless/ath/ath11k/hw.c | 2 +- drivers/net/wireless/ath/ath11k/qmi.c | 5 + drivers/net/wireless/ath/ath9k/ar9003_hw.c | 27 +- drivers/net/wireless/ath/ath9k/htc_hst.c | 8 +- drivers/net/wireless/ath/ath9k/main.c | 11 +- drivers/net/wireless/ath/ath9k/wmi.c | 4 + drivers/net/wireless/atmel/atmel_cs.c | 13 +- drivers/net/wireless/intel/iwlwifi/fw/api/rs.h | 2 + drivers/net/wireless/intel/iwlwifi/fw/dump.c | 7 +- drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 2 + drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 8 +- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 9 +- drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 10 +- drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c | 58 +- drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 9 +- drivers/net/wireless/intel/iwlwifi/mvm/sta.c | 2 + drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 5 +- drivers/net/wireless/intersil/orinoco/orinoco_cs.c | 13 +- .../net/wireless/intersil/orinoco/spectrum_cs.c | 13 +- drivers/net/wireless/legacy/ray_cs.c | 16 +- drivers/net/wireless/legacy/wl3501_cs.c | 16 +- drivers/net/wireless/marvell/mwifiex/scan.c | 6 +- drivers/net/wireless/mediatek/mt76/mt7921/dma.c | 4 - drivers/net/wireless/mediatek/mt76/mt7921/mcu.c | 8 - drivers/net/wireless/mediatek/mt76/mt7921/pci.c | 8 + drivers/net/wireless/microchip/wilc1000/hif.c | 8 +- drivers/net/wireless/realtek/rtw88/mac80211.c | 4 +- drivers/net/wireless/realtek/rtw88/usb.c | 2 +- drivers/net/wireless/realtek/rtw89/core.c | 2 +- drivers/net/wireless/rsi/rsi_91x_sdio.c | 9 +- drivers/nvme/host/core.c | 16 +- drivers/nvmem/imx-ocotp.c | 8 +- drivers/nvmem/rmem.c | 1 + drivers/nvmem/sunplus-ocotp.c | 9 +- drivers/pci/controller/cadence/pcie-cadence-host.c | 27 + drivers/pci/controller/dwc/pcie-qcom.c | 11 +- drivers/pci/controller/pci-ftpci100.c | 14 +- drivers/pci/controller/vmd.c | 11 +- drivers/pci/endpoint/functions/Kconfig | 2 +- drivers/pci/endpoint/functions/pci-epf-test.c | 2 +- drivers/pci/hotplug/pciehp_ctrl.c | 8 + drivers/pci/pcie/aspm.c | 21 +- drivers/perf/apple_m1_cpu_pmu.c | 30 +- drivers/perf/arm-cmn.c | 7 +- drivers/perf/arm_cspmu/arm_cspmu.c | 11 +- drivers/perf/arm_pmu.c | 2 + drivers/perf/hisilicon/hisi_pcie_pmu.c | 2 +- drivers/phy/Kconfig | 1 + drivers/phy/qualcomm/phy-qcom-qmp-combo.c | 8 +- drivers/phy/tegra/xusb.c | 4 + drivers/pinctrl/bcm/pinctrl-bcm2835.c | 6 +- drivers/pinctrl/freescale/pinctrl-scu.c | 3 +- drivers/pinctrl/intel/pinctrl-cherryview.c | 15 +- drivers/pinctrl/nuvoton/pinctrl-npcm7xx.c | 2 + drivers/pinctrl/pinctrl-at91-pio4.c | 2 + drivers/pinctrl/pinctrl-at91.c | 8 +- drivers/pinctrl/pinctrl-microchip-sgpio.c | 3 + drivers/pinctrl/sunplus/sppctl.c | 23 +- drivers/pinctrl/tegra/pinctrl-tegra.c | 15 +- drivers/pinctrl/tegra/pinctrl-tegra.h | 3 +- drivers/pinctrl/tegra/pinctrl-tegra114.c | 7 +- drivers/pinctrl/tegra/pinctrl-tegra124.c | 7 +- drivers/pinctrl/tegra/pinctrl-tegra194.c | 7 +- drivers/pinctrl/tegra/pinctrl-tegra20.c | 7 +- drivers/pinctrl/tegra/pinctrl-tegra210.c | 7 +- drivers/pinctrl/tegra/pinctrl-tegra30.c | 7 +- drivers/platform/x86/dell/dell-rbtn.c | 13 +- drivers/platform/x86/intel/pmc/core.c | 15 +- drivers/platform/x86/intel/pmc/core.h | 31 +- drivers/platform/x86/intel/pmc/mtl.c | 475 +++++++++++++- drivers/platform/x86/lenovo-yogabook-wmi.c | 34 +- drivers/platform/x86/think-lmi.c | 20 +- drivers/platform/x86/thinkpad_acpi.c | 6 +- drivers/power/supply/rt9467-charger.c | 2 +- drivers/powercap/Kconfig | 4 +- drivers/powercap/intel_rapl_msr.c | 17 +- drivers/pwm/pwm-ab8500.c | 2 +- drivers/pwm/pwm-imx-tpm.c | 7 + drivers/pwm/pwm-mtk-disp.c | 13 +- drivers/pwm/sysfs.c | 17 + drivers/regulator/core.c | 30 +- drivers/regulator/rk808-regulator.c | 1 + drivers/regulator/tps65219-regulator.c | 6 +- drivers/rtc/rtc-st-lpc.c | 2 +- drivers/s390/net/qeth_l3_sys.c | 2 +- drivers/scsi/3w-xxxx.c | 4 +- drivers/scsi/lpfc/lpfc_els.c | 14 +- drivers/scsi/qedf/qedf_main.c | 3 +- drivers/soc/amlogic/meson-secure-pwrc.c | 2 +- drivers/soc/fsl/qe/Kconfig | 1 + drivers/soc/mediatek/mtk-svs.c | 4 +- drivers/soc/qcom/qcom-geni-se.c | 67 +- drivers/soc/xilinx/xlnx_event_manager.c | 6 +- drivers/soundwire/debugfs.c | 3 +- drivers/soundwire/qcom.c | 179 ++--- drivers/spi/spi-bcm-qspi.c | 10 +- drivers/spi/spi-dw-core.c | 5 +- drivers/spi/spi-geni-qcom.c | 111 ++-- drivers/staging/media/atomisp/i2c/atomisp-gc0310.c | 2 +- drivers/staging/media/atomisp/i2c/atomisp-ov2680.c | 8 +- drivers/staging/media/atomisp/i2c/ov2680.h | 1 + .../media/atomisp/pci/atomisp_gmin_platform.c | 2 +- .../vc04_services/interface/vchiq_arm/vchiq_arm.c | 4 +- drivers/thermal/qcom/tsens-v0_1.c | 56 +- drivers/thermal/qcom/tsens.c | 19 +- drivers/thermal/qcom/tsens.h | 6 +- drivers/thermal/qoriq_thermal.c | 30 +- drivers/thermal/sun8i_thermal.c | 55 +- drivers/tty/serial/8250/8250_omap.c | 25 +- drivers/tty/serial/fsl_lpuart.c | 1 + drivers/tty/serial/serial_core.c | 10 +- drivers/ufs/core/ufshcd-priv.h | 3 - drivers/ufs/core/ufshcd.c | 21 +- drivers/usb/core/devio.c | 2 + drivers/usb/core/hcd-pci.c | 24 +- drivers/usb/dwc2/platform.c | 16 +- drivers/usb/dwc3/dwc3-meson-g12a.c | 5 +- drivers/usb/dwc3/dwc3-qcom.c | 17 +- drivers/usb/dwc3/gadget.c | 4 +- drivers/usb/gadget/function/u_serial.c | 13 +- drivers/usb/host/ehci-pci.c | 3 +- drivers/usb/host/ohci-pci.c | 8 +- drivers/usb/host/uhci-pci.c | 7 +- drivers/usb/host/xhci-histb.c | 2 +- drivers/usb/host/xhci-pci.c | 4 +- drivers/usb/host/xhci-plat.c | 4 +- drivers/usb/host/xhci-tegra.c | 2 +- drivers/usb/host/xhci.c | 5 +- drivers/usb/host/xhci.h | 2 +- drivers/usb/musb/musb_core.c | 1 - drivers/usb/musb/musb_core.h | 2 - drivers/usb/musb/tusb6010.c | 53 +- drivers/usb/phy/phy-tahvo.c | 2 +- drivers/usb/serial/option.c | 4 + drivers/usb/typec/ucsi/psy.c | 14 + drivers/vdpa/vdpa_user/vduse_dev.c | 6 +- drivers/vfio/mdev/mdev_core.c | 23 +- drivers/video/fbdev/omap/lcd_mipid.c | 16 +- drivers/virt/coco/sev-guest/Kconfig | 1 + drivers/virtio/virtio_vdpa.c | 4 +- drivers/w1/slaves/w1_therm.c | 31 +- drivers/w1/w1.c | 4 +- fs/afs/write.c | 8 +- fs/btrfs/bio.c | 3 +- fs/btrfs/block-group.c | 41 +- fs/btrfs/ctree.c | 49 +- fs/btrfs/disk-io.c | 7 +- fs/btrfs/extent_io.c | 333 ++++------ fs/btrfs/extent_io.h | 5 +- fs/btrfs/free-space-tree.c | 3 + fs/btrfs/inode.c | 92 ++- fs/btrfs/locking.c | 5 +- fs/btrfs/qgroup.c | 2 + fs/btrfs/tree-mod-log.c | 115 +++- fs/erofs/zdata.c | 72 +- fs/erofs/zmap.c | 6 +- fs/ext4/namei.c | 17 +- fs/f2fs/checkpoint.c | 7 +- fs/f2fs/compress.c | 11 +- fs/f2fs/data.c | 11 +- fs/f2fs/f2fs.h | 23 +- fs/f2fs/file.c | 13 +- fs/f2fs/gc.c | 27 +- fs/f2fs/namei.c | 16 +- fs/f2fs/node.c | 7 +- fs/f2fs/super.c | 160 ++++- fs/fs_context.c | 3 +- fs/gfs2/file.c | 2 +- fs/inode.c | 42 ++ fs/internal.h | 2 + fs/jffs2/build.c | 5 +- fs/jffs2/xattr.c | 13 +- fs/jffs2/xattr.h | 4 +- fs/kernfs/dir.c | 2 + fs/lockd/svc.c | 1 - fs/namei.c | 25 +- fs/nfs/nfs42xattr.c | 79 ++- fs/nfs/nfs4proc.c | 1 + fs/nfsd/cache.h | 2 + fs/nfsd/nfs4xdr.c | 2 +- fs/nfsd/nfscache.c | 25 +- fs/nfsd/nfsctl.c | 10 +- fs/nfsd/vfs.c | 4 +- fs/notify/fanotify/fanotify_user.c | 14 + fs/ntfs3/xattr.c | 3 + fs/ocfs2/cluster/tcp.c | 23 +- fs/overlayfs/copy_up.c | 2 + fs/overlayfs/dir.c | 3 +- fs/overlayfs/export.c | 3 +- fs/overlayfs/inode.c | 17 +- fs/overlayfs/namei.c | 3 +- fs/overlayfs/overlayfs.h | 8 +- fs/overlayfs/super.c | 2 +- fs/overlayfs/util.c | 31 +- fs/pstore/ram_core.c | 2 + fs/ramfs/inode.c | 2 +- fs/reiserfs/xattr_security.c | 1 + fs/smb/client/cifs_debug.c | 16 +- fs/smb/client/cifsglob.h | 10 +- fs/smb/client/cifsproto.h | 2 +- fs/smb/client/connect.c | 70 +- fs/smb/client/dfs.c | 55 +- fs/smb/client/dfs.h | 19 +- fs/smb/client/dfs_cache.c | 8 +- fs/smb/client/file.c | 25 +- fs/smb/client/misc.c | 38 +- fs/smb/client/smb2inode.c | 9 +- fs/smb/client/smb2ops.c | 19 +- fs/smb/client/transport.c | 20 +- fs/smb/server/smb_common.c | 2 +- fs/splice.c | 1 - fs/udf/namei.c | 14 +- fs/verity/enable.c | 19 +- fs/verity/fsverity_private.h | 13 +- fs/verity/hash_algs.c | 131 +--- fs/verity/verify.c | 113 ++-- include/drm/bridge/samsung-dsim.h | 3 + include/drm/drm_fixed.h | 6 + include/linux/bitmap.h | 8 +- include/linux/blk-mq.h | 3 +- include/linux/blkdev.h | 3 +- include/linux/blktrace_api.h | 6 +- include/linux/bpf.h | 1 - include/linux/bpf_verifier.h | 52 +- include/linux/can/length.h | 14 +- include/linux/compiler_attributes.h | 12 + include/linux/dsa/sja1105.h | 4 - include/linux/ieee80211.h | 6 +- include/linux/mfd/tps65010.h | 11 +- include/linux/mfd/twl.h | 3 - include/linux/mm_types.h | 23 +- include/linux/mmc/card.h | 1 + include/linux/netdevice.h | 9 + include/linux/nmi.h | 35 +- include/linux/pci.h | 1 + include/linux/perf/arm_pmu.h | 2 + include/linux/pipe_fs_i.h | 4 - include/linux/platform_data/lcd-mipid.h | 2 - include/linux/platform_data/mmc-omap.h | 2 - include/linux/ramfs.h | 1 + include/linux/sh_intc.h | 6 +- include/linux/soc/qcom/geni-se.h | 4 + include/linux/spi/ads7846.h | 2 - include/linux/usb/hcd.h | 2 +- include/linux/usb/musb.h | 13 - include/linux/watch_queue.h | 3 +- include/net/bluetooth/mgmt.h | 1 + include/net/dsa.h | 12 +- include/net/mac80211.h | 44 +- include/net/regulatory.h | 13 +- include/net/sock.h | 1 + include/soc/mscc/ocelot.h | 10 +- include/trace/events/net.h | 3 +- include/trace/events/timer.h | 6 +- include/uapi/linux/affs_hardblocks.h | 68 +- include/uapi/linux/auto_dev-ioctl.h | 2 +- include/uapi/linux/videodev2.h | 6 +- include/ufs/ufshcd.h | 1 - init/Makefile | 1 + init/main.c | 3 +- io_uring/io_uring.c | 35 +- kernel/bpf/btf.c | 6 +- kernel/bpf/cgroup.c | 15 + kernel/bpf/helpers.c | 12 +- kernel/bpf/trampoline.c | 32 +- kernel/bpf/verifier.c | 716 +++++++++++++++----- kernel/kcsan/core.c | 2 + kernel/kexec_core.c | 5 +- kernel/rcu/rcu.h | 6 + kernel/rcu/rcuscale.c | 199 +++--- kernel/rcu/tasks.h | 7 +- kernel/rcu/tree.c | 23 +- kernel/sched/fair.c | 18 + kernel/sched/sched.h | 22 + kernel/time/posix-timers.c | 43 +- kernel/time/tick-sched.c | 2 +- kernel/watch_queue.c | 12 +- kernel/watchdog.c | 302 ++++++--- kernel/watchdog_hld.c | 48 +- lib/bitmap.c | 2 +- lib/dhry_1.c | 11 +- lib/test_firmware.c | 12 +- lib/ts_bm.c | 4 +- mm/damon/ops-common.c | 16 +- mm/damon/ops-common.h | 4 +- mm/damon/paddr.c | 4 +- mm/damon/vaddr.c | 4 +- mm/filemap.c | 4 +- mm/page-writeback.c | 8 +- mm/shmem.c | 2 +- mm/vmscan.c | 13 +- net/bluetooth/hci_conn.c | 47 +- net/bluetooth/hci_event.c | 15 +- net/bluetooth/hci_sync.c | 28 +- net/bridge/br_if.c | 5 +- net/core/filter.c | 126 +++- net/core/rtnetlink.c | 104 +-- net/core/sock.c | 17 +- net/dsa/dsa.c | 2 +- net/dsa/slave.c | 84 ++- net/dsa/switch.c | 4 +- net/dsa/switch.h | 3 + net/dsa/tag_sja1105.c | 90 +-- net/handshake/handshake.h | 1 + net/handshake/request.c | 4 + net/ipv4/tcp_input.c | 12 +- net/mac80211/debugfs_netdev.c | 2 +- net/mac80211/eht.c | 5 +- net/mac80211/he.c | 3 +- net/mac80211/mlme.c | 30 +- net/mac80211/sta_info.c | 2 + net/mac80211/util.c | 15 +- net/netfilter/ipvs/Kconfig | 27 +- net/netfilter/ipvs/ip_vs_conn.c | 4 +- net/netfilter/nf_conntrack_helper.c | 4 + net/netfilter/nf_conntrack_proto_dccp.c | 52 +- net/netfilter/nf_conntrack_sip.c | 2 +- net/netfilter/nf_tables_api.c | 17 +- net/netfilter/nft_byteorder.c | 14 +- net/netlink/af_netlink.c | 5 +- net/netlink/diag.c | 7 +- net/nfc/llcp.h | 1 - net/nfc/llcp_commands.c | 15 +- net/nfc/llcp_core.c | 49 +- net/nfc/llcp_sock.c | 18 +- net/nfc/netlink.c | 20 +- net/nfc/nfc.h | 1 + net/sched/act_ipt.c | 70 +- net/sched/act_pedit.c | 1 + net/sched/sch_netem.c | 59 +- net/sctp/socket.c | 22 +- net/sunrpc/svcsock.c | 23 +- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 12 +- net/wireless/core.c | 16 - net/wireless/reg.c | 16 +- net/wireless/scan.c | 367 ++++------- net/wireless/util.c | 2 + net/xdp/xsk.c | 5 + samples/bpf/tcp_basertt_kern.c | 2 +- samples/bpf/xdp1_kern.c | 2 +- samples/bpf/xdp2_kern.c | 2 +- scripts/Makefile.clang | 3 +- scripts/Makefile.compiler | 4 +- scripts/Makefile.modfinal | 2 +- scripts/Makefile.vmlinux | 1 + scripts/mksysmap | 4 +- scripts/mod/modpost.c | 86 +-- scripts/package/builddeb | 14 +- security/apparmor/policy.c | 13 + security/apparmor/policy_compat.c | 20 +- security/apparmor/policy_unpack.c | 100 +-- security/integrity/evm/evm_crypto.c | 2 +- security/integrity/evm/evm_main.c | 4 +- security/integrity/iint.c | 15 +- security/integrity/ima/ima_modsig.c | 3 + security/integrity/ima/ima_policy.c | 3 +- sound/core/jack.c | 15 +- sound/core/pcm_memory.c | 44 +- sound/pci/ac97/ac97_codec.c | 4 +- sound/pci/hda/patch_realtek.c | 7 +- sound/soc/amd/acp/acp-pdm.c | 2 +- sound/soc/codecs/es8316.c | 23 +- sound/soc/fsl/imx-audmix.c | 9 + sound/soc/intel/boards/sof_sdw.c | 18 +- sound/soc/mediatek/mt8173/mt8173-afe-pcm.c | 13 +- tools/bpf/bpftool/feature.c | 24 +- tools/bpf/resolve_btfids/Makefile | 4 +- tools/include/nolibc/stdint.h | 10 +- tools/lib/bpf/bpf_helpers.h | 15 +- tools/lib/bpf/btf_dump.c | 22 +- tools/perf/arch/x86/util/Build | 1 + tools/perf/arch/x86/util/env.c | 19 + tools/perf/arch/x86/util/env.h | 7 + tools/perf/arch/x86/util/evsel.c | 16 +- tools/perf/arch/x86/util/mem-events.c | 19 +- tools/perf/builtin-bench.c | 2 + tools/perf/builtin-script.c | 16 +- tools/perf/builtin-stat.c | 2 + tools/perf/tests/shell/test_task_analyzer.sh | 26 +- tools/perf/util/bpf_skel/lock_contention.bpf.c | 2 - tools/perf/util/bpf_skel/vmlinux.h | 10 + tools/perf/util/dwarf-aux.c | 2 +- tools/perf/util/evsel.h | 24 +- tools/perf/util/evsel_fprintf.c | 1 + tools/perf/util/metricgroup.c | 2 +- tools/testing/cxl/test/mem.c | 4 +- tools/testing/kunit/kunit_kernel.py | 6 +- tools/testing/kunit/mypy.ini | 6 + tools/testing/kunit/run_checks.py | 2 +- tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/prog_tests/check_mtu.c | 2 +- .../testing/selftests/bpf/progs/refcounted_kptr.c | 2 + .../selftests/bpf/progs/refcounted_kptr_fail.c | 4 +- tools/testing/selftests/bpf/test_verifier.c | 24 +- tools/testing/selftests/bpf/verifier/precise.c | 106 +-- tools/testing/selftests/cgroup/test_memcontrol.c | 4 +- tools/testing/selftests/ftrace/ftracetest | 2 +- tools/testing/selftests/net/rtnetlink.sh | 1 + tools/testing/selftests/nolibc/nolibc-test.c | 6 +- .../rcutorture/configs/rcu/BUSTED-BOOST.boot | 2 +- .../selftests/rcutorture/configs/rcu/TREE03.boot | 2 +- .../selftests/vDSO/vdso_test_clock_getres.c | 4 +- tools/testing/selftests/wireguard/netns.sh | 30 +- tools/tracing/rtla/src/osnoise_top.c | 8 +- tools/virtio/Makefile | 13 +- 877 files changed, 10447 insertions(+), 6356 deletions(-)
Greg Kroah-Hartman
maintainerPATCH 23/800 blk-iocost: use spin_lock_irqsave in adjust_inuse_and_calc_cost
From: Li Nan <[email protected]>
[ Upstream commit 8d211554679d0b23702bd32ba04aeac0c1c4f660 ]
adjust_inuse_and_calc_cost() use spin_lock_irq() and IRQ will be enabled when unlock. DEADLOCK might happen if we have held other locks and disabled IRQ before invoking it.
Fix it by using spin_lock_irqsave() instead, which can keep IRQ state consistent with before when unlock.
================================
WARNING: inconsistent lock state
5.10.0-02758-g8e5f91fd772f #26 Not tainted
--------------------------------
inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. kworker/2:3/388 [HC0[0]:SC0[0]:HE0:SE1] takes:
ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390 {IN-HARDIRQ-W} state was registered at:
__lock_acquire+0x3d7/0x1070
lock_acquire+0x197/0x4a0
__raw_spin_lock_irqsave
_raw_spin_lock_irqsave+0x3b/0x60
bfq_idle_slice_timer_body
bfq_idle_slice_timer+0x53/0x1d0
__run_hrtimer+0x477/0xa70
__hrtimer_run_queues+0x1c6/0x2d0
hrtimer_interrupt+0x302/0x9e0
local_apic_timer_interrupt
__sysvec_apic_timer_interrupt+0xfd/0x420
run_sysvec_on_irqstack_cond
sysvec_apic_timer_interrupt+0x46/0xa0
asm_sysvec_apic_timer_interrupt+0x12/0x20
irq event stamp: 837522
hardirqs last enabled at (837521): [<ffffffff84b9419d>] __raw_spin_unlock_irqrestore
hardirqs last enabled at (837521): [<ffffffff84b9419d>] _raw_spin_unlock_irqrestore+0x3d/0x40
hardirqs last disabled at (837522): [<ffffffff84b93fa3>] __raw_spin_lock_irq
hardirqs last disabled at (837522): [<ffffffff84b93fa3>] _raw_spin_lock_irq+0x43/0x50
softirqs last enabled at (835852): [<ffffffff84e00558>] __do_softirq+0x558/0x8ec
softirqs last disabled at (835845): [<ffffffff84c010ff>] asm_call_irq_on_stack+0xf/0x20other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&bfqd->lock);
<Interrupt>
lock(&bfqd->lock);*** DEADLOCK ***
3 locks held by kworker/2:3/388:
#0: ffff888107af0f38 ((wq_completion)kthrotld){+.+.}-{0:0}, at: process_one_work+0x742/0x13f0 #1: ffff8881176bfdd8 ((work_completion)(&td->dispatch_work)){+.+.}-{0:0}, at: process_one_work+0x777/0x13f0 #2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: spin_lock_irq
#2: ffff888118c00c28 (&bfqd->lock){?.-.}-{2:2}, at: bfq_bio_merge+0x141/0x390
stack backtrace: CPU: 2 PID: 388 Comm: kworker/2:3 Not tainted 5.10.0-02758-g8e5f91fd772f #26 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Workqueue: kthrotld blk_throtl_dispatch_work_fn Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x107/0x167 print_usage_bug valid_state mark_lock_irq.cold+0x32/0x3a mark_lock+0x693/0xbc0 mark_held_locks+0x9e/0xe0 __trace_hardirqs_on_caller lockdep_hardirqs_on_prepare.part.0+0x151/0x360 trace_hardirqs_on+0x5b/0x180 __raw_spin_unlock_irq _raw_spin_unlock_irq+0x24/0x40 spin_unlock_irq adjust_inuse_and_calc_cost+0x4fb/0x970 ioc_rqos_merge+0x277/0x740 __rq_qos_merge+0x62/0xb0 rq_qos_merge bio_attempt_back_merge+0x12c/0x4a0 blk_mq_sched_try_merge+0x1b6/0x4d0 bfq_bio_merge+0x24a/0x390 __blk_mq_sched_bio_merge+0xa6/0x460 blk_mq_sched_bio_merge blk_mq_submit_bio+0x2e7/0x1ee0 __submit_bio_noacct_mq+0x175/0x3b0 submit_bio_noacct+0x1fb/0x270 blk_throtl_dispatch_work_fn+0x1ef/0x2b0 process_one_work+0x83e/0x13f0 process_scheduled_works worker_thread+0x7e3/0xd80 kthread+0x353/0x470 ret_from_fork+0x1f/0x30
--- block/blk-iocost.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
block/blk-iocost.c +4 -3
@@ -2455,6 +2455,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,u32 hwi, adj_step;s64 margin;u64 cost, new_inuse; +unsigned long flags;current_hweight (iocg,NULL , &hwi); old_hwi = hwi;
@@ -2473,11 +2474,11 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, iocg->inuse == iocg->active)return cost; -spin_lock_irq (&ioc->lock); +spin_lock_irqsave (&ioc->lock, flags);/* we own inuse only when @iocg is in the normal active state */ if (iocg->abs_vdebt ||list_empty (&iocg->active_list)) { -spin_unlock_irq (&ioc->lock); +spin_unlock_irqrestore (&ioc->lock, flags);return cost; }
@@ -2498,7 +2499,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime, }while (time_after64 (vtime + cost, now->vnow) && iocg->inuse != iocg->active); -spin_unlock_irq (&ioc->lock); +spin_unlock_irqrestore (&ioc->lock, flags);TRACE_IOCG_PATH (inuse_adjust, iocg, now, old_inuse, iocg->inuse, old_hwi, hwi);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 32/800 nvme-core: fix dev_pm_qos memleak
In reply to Greg Kroah-HartmanFrom: Chaitanya Kulkarni <[email protected]>
[ Upstream commit 7ed5cf8e6d9bfb6a78d0471317edff14f0f2b4dd ]
Call dev_pm_qos_hide_latency_tolerance() in the error unwind patch to avoid following kmemleak:-
blktests (master) # kmemleak-clear; ./check nvme/044; blktests (master) # kmemleak-scan ; kmemleak-show
nvme/044 (Test bi-directional authentication) [passed]
runtime 2.111s ... 2.124s
unreferenced object 0xffff888110c46240 (size 96):
comm "nvme", pid 33461, jiffies 4345365353 (age 75.586s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<0000000069ac2cec>] kmalloc_trace+0x25/0x90
[<000000006acc66d5>] dev_pm_qos_update_user_latency_tolerance+0x6f/0x100
[<00000000cc376ea7>] nvme_init_ctrl+0x38e/0x410 [nvme_core]
[<000000007df61b4b>] 0xffffffffc05e88b3
[<00000000d152b985>] 0xffffffffc05744cb
[<00000000f04a4041>] vfs_write+0xc5/0x3c0
[<00000000f9491baf>] ksys_write+0x5f/0xe0
[<000000001c46513d>] do_syscall_64+0x3b/0x90
[<00000000ecf348fe>] entry_SYSCALL_64_after_hwframe+0x72/0xdc--- drivers/nvme/host/core.c | 1 + 1 file changed, 1 insertion(+)
drivers/nvme/host/core.c +1 -0
@@ -5250,6 +5250,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,return 0 ; out_free_cdev:nvme_fault_inject_fini (&ctrl->fault_inject); +dev_pm_qos_hide_latency_tolerance (ctrl->device);cdev_device_del (&ctrl->cdev, ctrl->device); out_free_name:nvme_put_ctrl (ctrl);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 33/800 md/raid10: check slab-out-of-bounds in md_bitmap_get_counter
In reply to Greg Kroah-HartmanFrom: Li Nan <[email protected]>
[ Upstream commit 301867b1c16805aebbc306aafa6ecdc68b73c7e5 ]
If we write a large number to md/bitmap_set_bits, md_bitmap_checkpage() will return -EINVAL because 'page >= bitmap->pages', but the return value was not checked immediately in md_bitmap_get_counter() in order to set *blocks value and slab-out-of-bounds occurs.
Move check of 'page >= bitmap->pages' to md_bitmap_get_counter() and return directly if true.
--- drivers/md/md-bitmap.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-)
drivers/md/md-bitmap.c +9 -8
@@ -54,14 +54,7 @@ __acquires(bitmap->lock) {unsigned char *mappage; -if (page >= bitmap->pages) { -/* This can happen if bitmap_start_sync goes beyond -* End-of-device while looking for a whole page. -* It is harmless. -*/ -return -EINVAL ; - } - +WARN_ON_ONCE (page >= bitmap->pages);if (bitmap->bp[page].hijacked)/* it's hijacked, don't try to alloc */ return 0 ;
@@ -1387,6 +1380,14 @@ __acquires(bitmap->lock)sector_t csize;int err; +if (page >= bitmap->pages) { +/* +* This can happen if bitmap_start_sync goes beyond +* End-of-device while looking for a whole page or +* user set a huge number to sysfs bitmap_set_bits. +*/ +return NULL ; + } err =md_bitmap_checkpage (bitmap, page, create,0 ); if (bitmap->bp[page].hijacked ||
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 34/800 md/raid10: fix overflow of md/safe_mode_delay
In reply to Greg Kroah-HartmanFrom: Li Nan <[email protected]>
[ Upstream commit 6beb489b2eed25978523f379a605073f99240c50 ]
There is no input check when echo md/safe_mode_delay in safe_delay_store(). And msec might also overflow when HZ < 1000 in safe_delay_show(), Fix it by checking overflow in safe_delay_store() and use unsigned long conversion in safe_delay_show().
--- drivers/md/md.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/md/md.c +4 -3
@@ -3794,8 +3794,9 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale)static ssize_t safe_delay_show (struct mddev *mddev,char *page) { -int msec = (mddev->safemode_delay*1000 )/HZ ; -return sprintf (page,"%d.%03d\n" , msec/1000 , msec%1000 ); +unsigned int msec = ((unsigned long )mddev->safemode_delay*1000 )/HZ ; + +return sprintf (page,"%u.%03u\n" , msec/1000 , msec%1000 ); }static ssize_t safe_delay_store (struct mddev *mddev,const char *cbuf,size_t len)
@@ -3807,7 +3808,7 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)return -EINVAL ; } -if (strict_strtoul_scaled (cbuf, &msec,3 ) <0 ) +if (strict_strtoul_scaled (cbuf, &msec,3 ) <0 || msec >UINT_MAX /HZ )return -EINVAL ;if (msec ==0 ) mddev->safemode_delay =0 ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 35/800 md/raid10: fix wrong setting of max_corr_read_errors
In reply to Greg Kroah-HartmanFrom: Li Nan <[email protected]>
[ Upstream commit f8b20a405428803bd9881881d8242c9d72c6b2b2 ]
There is no input check when echo md/max_read_errors and overflow might occur. Add check of input number.
--- drivers/md/md.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/md/md.c +2 -0
@@ -4478,6 +4478,8 @@ max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len rv =kstrtouint (buf,10 , &n);if (rv <0 )return rv; +if (n >INT_MAX ) +return -EINVAL ;atomic_set (&mddev->max_corr_read_errors, n);return len; }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 36/800 md/raid10: fix null-ptr-deref of mreplace in raid10_sync_request
In reply to Greg Kroah-HartmanFrom: Li Nan <[email protected]>
[ Upstream commit 34817a2441747b48e444cb0e05d84e14bc9443da ]
There are two check of 'mreplace' in raid10_sync_request(). In the first check, 'need_replace' will be set and 'mreplace' will be used later if no-Faulty 'mreplace' exists, In the second check, 'mreplace' will be set to NULL if it is Faulty, but 'need_replace' will not be changed accordingly. null-ptr-deref occurs if Faulty is set between two check.
Fix it by merging two checks into one. And replace 'need_replace' with 'mreplace' because their values are always the same.
--- drivers/md/raid10.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-)
drivers/md/raid10.c +5 -9
@@ -3438,7 +3438,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,int must_sync;int any_working;int need_recover =0 ; -int need_replace =0 ;struct raid10_info *mirror = &conf->mirrors[i];struct md_rdev *mrdev, *mreplace;
@@ -3450,11 +3449,10 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, !test_bit(Faulty, &mrdev->flags) && !test_bit(In_sync, &mrdev->flags)) need_recover =1 ; -if (mreplace !=NULL && - !test_bit (Faulty, &mreplace->flags)) - need_replace =1 ; +if (mreplace &&test_bit (Faulty, &mreplace->flags)) + mreplace =NULL ; -if (!need_recover && !need_replace) { +if (!need_recover && !mreplace) {rcu_read_unlock ();continue ; }
@@ -3470,8 +3468,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,rcu_read_unlock ();continue ; } -if (mreplace &&test_bit (Faulty, &mreplace->flags)) - mreplace =NULL ;/* Unless we are doing a full sync, or a replacement * we only need to recover the block if it is set in * the bitmap
@@ -3594,11 +3590,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1 ].repl_bio;if (bio) bio->bi_end_io =NULL ; -/* Note: if need_replace, then bio +/* Note: if replace is not NULL, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. */ -if (!need_replace) +if (!mreplace)break ; bio->bi_next = biolist; biolist = bio;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 37/800 md/raid10: fix io loss while replacement replace rdev
In reply to Greg Kroah-HartmanFrom: Li Nan <[email protected]>
[ Upstream commit 2ae6aaf76912bae53c74b191569d2ab484f24bf3 ]
When removing a disk with replacement, the replacement will be used to replace rdev. During this process, there is a brief window in which both rdev and replacement are read as NULL in raid10_write_request(). This will result in io not being submitted but it should be.
//remove //write
raid10_remove_disk raid10_write_request
mirror->rdev = NULL
read rdev -> NULL mirror->rdev = mirror->replacement mirror->replacement = NULL read replacement -> NULL
Fix it by reading replacement first and rdev later, meanwhile, use smp_mb() to prevent memory reordering.
--- drivers/md/raid10.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-)
drivers/md/raid10.c +18 -4
@@ -779,8 +779,16 @@ static struct md_rdev *read_balance(struct r10conf *conf, disk = r10_bio->devs[slot].devnum; rdev =rcu_dereference (conf->mirrors[disk].replacement);if (rdev ==NULL ||test_bit (Faulty, &rdev->flags) || - r10_bio->devs[slot].addr + sectors > rdev->recovery_offset) + r10_bio->devs[slot].addr + sectors > + rdev->recovery_offset) { +/* +* Read replacement first to prevent reading both rdev +* and replacement as NULL during replacement replace +* rdev. +*/ +smp_mb (); rdev =rcu_dereference (conf->mirrors[disk].rdev); + }if (rdev ==NULL ||test_bit (Faulty, &rdev->flags))continue ;
@@ -1479,9 +1487,15 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,for (i =0 ; i < conf->copies; i++) {int d = r10_bio->devs[i].devnum; -struct md_rdev *rdev =rcu_dereference (conf->mirrors[d].rdev); -struct md_rdev *rrdev =rcu_dereference ( - conf->mirrors[d].replacement); +struct md_rdev *rdev, *rrdev; + + rrdev =rcu_dereference (conf->mirrors[d].replacement); +/* +* Read replacement first to prevent reading both rdev and +* replacement as NULL during replacement replace rdev. +*/ +smp_mb (); + rdev =rcu_dereference (conf->mirrors[d].rdev);if (rdev == rrdev) rrdev =NULL ;if (rdev && (test_bit (Faulty, &rdev->flags)))
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 38/800 md/raid1-10: factor out a helper to add bio to plug
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit 5ec6ca140a034682e421e2e808ef5ddfdfd65242 ]
The code in raid1 and raid10 is identical, prepare to limit the number of plugged bios.
Stable-dep-of: 7db922bae3ab ("md/raid1-10: submit write io directly if bitmap is not enabled")
--- drivers/md/raid1-10.c | 16 ++++++++++++++++ drivers/md/raid1.c | 12 +----------- drivers/md/raid10.c | 11 +---------- 3 files changed, 18 insertions(+), 21 deletions(-)
drivers/md/raid1-10.c +16 -0
@@ -109,3 +109,19 @@ static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp, size -= len; }while (idx++ <RESYNC_PAGES && size >0 ); } + +static inline bool raid1_add_bio_to_plug (struct mddev *mddev,struct bio *bio, +blk_plug_cb_fn unplug) +{ +struct raid1_plug_cb *plug =NULL ; +struct blk_plug_cb *cb =blk_check_plugged (unplug, mddev, +sizeof (*plug)); + +if (!cb) +return false; + + plug = container_of(cb, struct raid1_plug_cb, cb); +bio_list_add (&plug->pending, bio); + +return true; +}
drivers/md/raid1.c +1 -11
@@ -1343,8 +1343,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,struct bitmap *bitmap = mddev->bitmap;unsigned long flags;struct md_rdev *blocked_rdev; -struct blk_plug_cb *cb; -struct raid1_plug_cb *plug =NULL ;int first_clone;int max_sectors;bool write_behind = false;
@@ -1573,15 +1571,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->sector);/* flush_pending_writes() needs access to the rdev so...*/ mbio->bi_bdev = (void *)rdev; - - cb =blk_check_plugged (raid1_unplug, mddev,sizeof (*plug)); -if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); -else - plug =NULL ; -if (plug) { -bio_list_add (&plug->pending, mbio); - }else { +if (!raid1_add_bio_to_plug (mddev, mbio, raid1_unplug)) {spin_lock_irqsave (&conf->device_lock, flags);bio_list_add (&conf->pending_bio_list, mbio);spin_unlock_irqrestore (&conf->device_lock, flags);
drivers/md/raid10.c +1 -10
@@ -1290,8 +1290,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,const blk_opf_t do_sync = bio->bi_opf &REQ_SYNC ;const blk_opf_t do_fua = bio->bi_opf &REQ_FUA ;unsigned long flags; -struct blk_plug_cb *cb; -struct raid1_plug_cb *plug =NULL ;struct r10conf *conf = mddev->private;struct md_rdev *rdev;int devnum = r10_bio->devs[n_copy].devnum;
@@ -1331,14 +1329,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,atomic_inc (&r10_bio->remaining); - cb =blk_check_plugged (raid10_unplug, mddev,sizeof (*plug)); -if (cb) - plug = container_of(cb, struct raid1_plug_cb, cb); -else - plug =NULL ; -if (plug) { -bio_list_add (&plug->pending, mbio); - }else { +if (!raid1_add_bio_to_plug (mddev, mbio, raid10_unplug)) {spin_lock_irqsave (&conf->device_lock, flags);bio_list_add (&conf->pending_bio_list, mbio);spin_unlock_irqrestore (&conf->device_lock, flags);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 39/800 md/raid1-10: factor out a helper to submit normal write
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit 8295efbe68c080047e98d9c0eb5cb933b238a8cb ]
There are multiple places to do the same thing, factor out a helper to prevent redundant code, and the helper will be used in following patch as well.
Stable-dep-of: 7db922bae3ab ("md/raid1-10: submit write io directly if bitmap is not enabled")
--- drivers/md/raid1-10.c | 17 +++++++++++++++++ drivers/md/raid1.c | 13 ++----------- drivers/md/raid10.c | 26 ++++---------------------- 3 files changed, 23 insertions(+), 33 deletions(-)
drivers/md/raid1-10.c +17 -0
@@ -110,6 +110,23 @@ static void md_bio_reset_resync_pages(struct bio *bio, struct resync_pages *rp, }while (idx++ <RESYNC_PAGES && size >0 ); } + +static inline void raid1_submit_write (struct bio *bio) +{ +struct md_rdev *rdev = (struct md_rdev *)bio->bi_bdev; + + bio->bi_next =NULL ; +bio_set_dev (bio, rdev->bdev); +if (test_bit (Faulty, &rdev->flags)) +bio_io_error (bio); +else if (unlikely (bio_op (bio) ==REQ_OP_DISCARD && + !bdev_max_discard_sectors (bio->bi_bdev))) +/* Just ignore it */ +bio_endio (bio); +else +submit_bio_noacct (bio); +} +static inline bool raid1_add_bio_to_plug (struct mddev *mddev,struct bio *bio,blk_plug_cb_fn unplug) {
drivers/md/raid1.c +2 -11
@@ -799,17 +799,8 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)while (bio) {/* submit pending writes */ struct bio *next = bio->bi_next; -struct md_rdev *rdev = (void *)bio->bi_bdev; - bio->bi_next =NULL ; -bio_set_dev (bio, rdev->bdev); -if (test_bit (Faulty, &rdev->flags)) { -bio_io_error (bio); - }else if (unlikely ((bio_op (bio) ==REQ_OP_DISCARD ) && - !bdev_max_discard_sectors (bio->bi_bdev))) -/* Just ignore it */ -bio_endio (bio); -else -submit_bio_noacct (bio); + +raid1_submit_write (bio); bio = next;cond_resched (); }
drivers/md/raid10.c +4 -22
@@ -917,17 +917,8 @@ static void flush_pending_writes(struct r10conf *conf)while (bio) {/* submit pending writes */ struct bio *next = bio->bi_next; -struct md_rdev *rdev = (void *)bio->bi_bdev; - bio->bi_next =NULL ; -bio_set_dev (bio, rdev->bdev); -if (test_bit (Faulty, &rdev->flags)) { -bio_io_error (bio); - }else if (unlikely ((bio_op (bio) ==REQ_OP_DISCARD ) && - !bdev_max_discard_sectors (bio->bi_bdev))) -/* Just ignore it */ -bio_endio (bio); -else -submit_bio_noacct (bio); + +raid1_submit_write (bio); bio = next; }blk_finish_plug (&plug);
@@ -1138,17 +1129,8 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)while (bio) {/* submit pending writes */ struct bio *next = bio->bi_next; -struct md_rdev *rdev = (void *)bio->bi_bdev; - bio->bi_next =NULL ; -bio_set_dev (bio, rdev->bdev); -if (test_bit (Faulty, &rdev->flags)) { -bio_io_error (bio); - }else if (unlikely ((bio_op (bio) ==REQ_OP_DISCARD ) && - !bdev_max_discard_sectors (bio->bi_bdev))) -/* Just ignore it */ -bio_endio (bio); -else -submit_bio_noacct (bio); + +raid1_submit_write (bio); bio = next; }kfree (plug);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 40/800 md/raid1-10: submit write io directly if bitmap is not enabled
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit 7db922bae3abdf0a1db81ef7228cc0b996a0c1e3 ]
Commit 6cce3b23f6f8 ("[PATCH] md: write intent bitmap support for raid10") add bitmap support, and it changed that write io is submitted through daemon thread because bitmap need to be updated before write io. And later, plug is used to fix performance regression because all the write io will go to demon thread, which means io can't be issued concurrently.
However, if bitmap is not enabled, the write io should not go to daemon thread in the first place, and plug is not needed as well.
--- drivers/md/md-bitmap.c | 4 +--- drivers/md/md-bitmap.h | 7 +++++++ drivers/md/raid1-10.c | 13 +++++++++++-- 3 files changed, 19 insertions(+), 5 deletions(-)
drivers/md/md-bitmap.c +1 -3
@@ -1016,7 +1016,6 @@ static int md_bitmap_file_test_bit(struct bitmap *bitmap, sector_t block)return set; } -/* this gets called when the md device is ready to unplug its underlying * (slave) device queues -- before we let any writes go down, we need to * sync the dirty pages of the bitmap file to disk */
@@ -1026,8 +1025,7 @@ void md_bitmap_unplug(struct bitmap *bitmap)int dirty, need_write;int writing =0 ; -if (!bitmap || !bitmap->storage.filemap || -test_bit (BITMAP_STALE , &bitmap->flags)) +if (!md_bitmap_enabled (bitmap))return ;/* look at each page to see if there are any set bits that need to be
drivers/md/md-bitmap.h +7 -0
@@ -273,6 +273,13 @@ int md_bitmap_copy_from_slot(struct mddev *mddev, int slot, sector_t *lo, sector_t *hi, bool clear_bits);void md_bitmap_free (struct bitmap *bitmap);void md_bitmap_wait_behind_writes (struct mddev *mddev); + +static inline bool md_bitmap_enabled (struct bitmap *bitmap) +{ +return bitmap && bitmap->storage.filemap && + !test_bit (BITMAP_STALE , &bitmap->flags); +} +#endif #endif
drivers/md/raid1-10.c +11 -2
@@ -131,9 +131,18 @@ static inline bool raid1_add_bio_to_plug(struct mddev *mddev, struct bio *bio, blk_plug_cb_fn unplug) {struct raid1_plug_cb *plug =NULL ; -struct blk_plug_cb *cb =blk_check_plugged (unplug, mddev, -sizeof (*plug)); +struct blk_plug_cb *cb; + +/* +* If bitmap is not enabled, it's safe to submit the io directly, and +* this can get optimal performance. +*/ +if (!md_bitmap_enabled (mddev->bitmap)) { +raid1_submit_write (bio); +return true; + } + cb =blk_check_plugged (unplug, mddev,sizeof (*plug));if (!cb)return false;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 41/800 block: fix blktrace debugfs entries leakage
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit dd7de3704af9989b780693d51eaea49a665bd9c2 ]
Commit 99d055b4fd4b ("block: remove per-disk debugfs files in blk_unregister_queue") moves blk_trace_shutdown() from blk_release_queue() to blk_unregister_queue(), this is safe if blktrace is created through sysfs, however, there is a regression in corner case.
blktrace can still be enabled after del_gendisk() through ioctl if the disk is opened before del_gendisk(), and if blktrace is not shutdown through ioctl before closing the disk, debugfs entries will be leaked.
Fix this problem by shutdown blktrace in disk_release(), this is safe because blk_trace_remove() is reentrant.
--- block/genhd.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
block/genhd.c +4 -1
@@ -25,8 +25,9 @@#include <linux/pm_runtime.h> #include <linux/badblocks.h> #include <linux/part_stat.h> -#include "blk-throttle.h" +#include <linux/blktrace_api.h> +#include "blk-throttle.h" #include "blk.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h"
@@ -1171,6 +1172,8 @@ static void disk_release(struct device *dev)might_sleep ();WARN_ON_ONCE (disk_live (disk)); +blk_trace_remove (disk->queue); +/* * To undo the all initialization from blk_mq_init_allocated_queue in * case of a probe failure where add_disk is never called we have to
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 24/800 x86/sev: Fix calculation of end address based on number of pages
In reply to Greg Kroah-HartmanFrom: Tom Lendacky <[email protected]>
[ Upstream commit 5dee19b6b2b194216919b99a1f5af2949a754016 ]
When calculating an end address based on an unsigned int number of pages, any value greater than or equal to 0x100000 that is shift PAGE_SHIFT bits results in a 0 value, resulting in an invalid end address. Change the number of pages variable in various routines from an unsigned int to an unsigned long to calculate the end address correctly.
--- arch/x86/include/asm/sev.h | 16 ++++++++-------- arch/x86/kernel/sev.c | 14 +++++++------- 2 files changed, 15 insertions(+), 15 deletions(-)
arch/x86/include/asm/sev.h +8 -8
@@ -192,12 +192,12 @@ struct snp_guest_request_ioctl;void setup_ghcb (void );void __init early_snp_set_memory_private (unsigned long vaddr,unsigned long paddr, -unsigned int npages); +unsigned long npages);void __init early_snp_set_memory_shared (unsigned long vaddr,unsigned long paddr, -unsigned int npages); +unsigned long npages);void __init snp_prep_memory (unsigned long paddr,unsigned int sz,enum psc_op op); -void snp_set_memory_shared (unsigned long vaddr,unsigned int npages); -void snp_set_memory_private (unsigned long vaddr,unsigned int npages); +void snp_set_memory_shared (unsigned long vaddr,unsigned long npages); +void snp_set_memory_private (unsigned long vaddr,unsigned long npages);void snp_set_wakeup_secondary_cpu (void );bool snp_init (struct boot_params *bp);void __init __noreturn snp_abort (void );
@@ -212,12 +212,12 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)static inline int rmpadjust (unsigned long vaddr,bool rmp_psize,unsigned long attrs) {return 0 ; }static inline void setup_ghcb (void ) { }static inline void __init -early_snp_set_memory_private (unsigned long vaddr,unsigned long paddr,unsigned int npages) { } +early_snp_set_memory_private (unsigned long vaddr,unsigned long paddr,unsigned long npages) { }static inline void __init -early_snp_set_memory_shared (unsigned long vaddr,unsigned long paddr,unsigned int npages) { } +early_snp_set_memory_shared (unsigned long vaddr,unsigned long paddr,unsigned long npages) { }static inline void __init snp_prep_memory (unsigned long paddr,unsigned int sz,enum psc_op op) { } -static inline void snp_set_memory_shared (unsigned long vaddr,unsigned int npages) { } -static inline void snp_set_memory_private (unsigned long vaddr,unsigned int npages) { } +static inline void snp_set_memory_shared (unsigned long vaddr,unsigned long npages) { } +static inline void snp_set_memory_private (unsigned long vaddr,unsigned long npages) { }static inline void snp_set_wakeup_secondary_cpu (void ) { }static inline bool snp_init (struct boot_params *bp) {return false; }static inline void snp_abort (void ) { }
arch/x86/kernel/sev.c +7 -7
@@ -645,7 +645,7 @@ static u64 __init get_jump_table_addr(void)return ret; } -static void pvalidate_pages (unsigned long vaddr,unsigned int npages,bool validate) +static void pvalidate_pages (unsigned long vaddr,unsigned long npages,bool validate) {unsigned long vaddr_end;int rc;
@@ -662,7 +662,7 @@ static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool valid } } -static void __init early_set_pages_state (unsigned long paddr,unsigned int npages,enum psc_op op) +static void __init early_set_pages_state (unsigned long paddr,unsigned long npages,enum psc_op op) {unsigned long paddr_end;u64 val;
@@ -701,7 +701,7 @@ static void __init early_set_pages_state(unsigned long paddr, unsigned int npage }void __init early_snp_set_memory_private (unsigned long vaddr,unsigned long paddr, -unsigned int npages) +unsigned long npages) {/* * This can be invoked in early boot while running identity mapped, so
@@ -723,7 +723,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd }void __init early_snp_set_memory_shared (unsigned long vaddr,unsigned long paddr, -unsigned int npages) +unsigned long npages) {/* * This can be invoked in early boot while running identity mapped, so
@@ -879,7 +879,7 @@ static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,sev_es_terminate (SEV_TERM_SET_LINUX ,GHCB_TERM_PSC ); } -static void set_pages_state (unsigned long vaddr,unsigned int npages,int op) +static void set_pages_state (unsigned long vaddr,unsigned long npages,int op) {unsigned long vaddr_end, next_vaddr;struct snp_psc_desc *desc;
@@ -904,7 +904,7 @@ static void set_pages_state(unsigned long vaddr, unsigned int npages, int op)kfree (desc); } -void snp_set_memory_shared (unsigned long vaddr,unsigned int npages) +void snp_set_memory_shared (unsigned long vaddr,unsigned long npages) {if (!cc_platform_has (CC_ATTR_GUEST_SEV_SNP ))return ;
@@ -914,7 +914,7 @@ void snp_set_memory_shared(unsigned long vaddr, unsigned int npages)set_pages_state (vaddr, npages,SNP_PAGE_STATE_SHARED ); } -void snp_set_memory_private (unsigned long vaddr,unsigned int npages) +void snp_set_memory_private (unsigned long vaddr,unsigned long npages) {if (!cc_platform_has (CC_ATTR_GUEST_SEV_SNP ))return ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 42/800 irqchip/loongson-eiointc: Fix irq affinity setting during resume
In reply to Greg Kroah-HartmanFrom: Jianmin Lv <[email protected]>
[ Upstream commit fb07b8f83441febeb0daf199b5f18c6de9bbab03 ]
The hierarchy of PCH PIC, PCH PCI MSI and EIONTC is as following:
PCH PIC ------->|
|---->EIOINTC
PCH PCI MSI --->|so the irq_data list of irq_desc for IRQs on PCH PIC and PCH PCI MSI is like this:
irq_desc->irq_data(domain: PCH PIC)->parent_data(domain: EIOINTC) irq_desc->irq_data(domain: PCH PCI MSI)->parent_data(domain: EIOINTC)
In eiointc_resume(), the irq_data passed into eiointc_set_irq_affinity() should be matched to EIOINTC domain instead of PCH PIC or PCH PCI MSI domain, so fix it.
--- drivers/irqchip/irq-loongson-eiointc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/irqchip/irq-loongson-eiointc.c +1 -1
@@ -314,7 +314,7 @@ static void eiointc_resume(void) desc =irq_resolve_mapping (eiointc_priv[i]->eiointc_domain, j);if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) {raw_spin_lock (&desc->lock); - irq_data = &desc->irq_data; + irq_data =irq_domain_get_irq_data (eiointc_priv[i]->eiointc_domain,irq_desc_get_irq (desc));eiointc_set_irq_affinity (irq_data, irq_data->common->affinity,0 );raw_spin_unlock (&desc->lock); }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 43/800 splice: dont call file_accessed in copy_splice_read
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 0b24be4691c9e6ea13ca70050d42a9f9032fa788 ]
copy_splice_read calls into ->read_iter to read the data, which already calls file_accessed.
--- fs/splice.c | 1 - 1 file changed, 1 deletion(-)
fs/splice.c +0 -1
@@ -355,7 +355,6 @@ ssize_t direct_splice_read(struct file *in, loff_t *ppos, reclaim -= ret; remain = ret; *ppos = kiocb.ki_pos; -file_accessed (in); }else if (ret <0 ) {/* * callers of ->splice_read() expect -EAGAIN on
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 44/800 irqchip/stm32-exti: Fix warning on initialized field overwritten
In reply to Greg Kroah-HartmanFrom: Antonio Borneo <[email protected]>
[ Upstream commit 48f31e496488a25f443c0df52464da446fb1d10c ]
While compiling with W=1, both gcc and clang complain about a tricky way to initialize an array by filling it with a non-zero value and then overrride some of the array elements. In this case the override is intentional, so just disable the specific warning for only this part of the code.
Note: the flag "-Woverride-init" is recognized by both compilers, but the warning msg from clang reports "-Winitializer-overrides". The doc of clang clarifies that the two flags are synonyms, so use here only the flag name common on both compilers.
--- drivers/irqchip/irq-stm32-exti.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
drivers/irqchip/irq-stm32-exti.c +12 -0
@@ -173,6 +173,16 @@ static struct irq_chip stm32_exti_h_chip_direct;#define EXTI_INVALID_IRQ U8_MAX#define STM32MP1_DESC_IRQ_SIZE (ARRAY_SIZE(stm32mp1_exti_banks) * IRQS_PER_BANK) +/* +* Use some intentionally tricky logic here to initialize the whole array to +* EXTI_INVALID_IRQ, but then override certain fields, requiring us to indicate +* that we "know" that there are overrides in this structure, and we'll need to +* disable that warning from W=1 builds. +*/ +__diag_push (); +__diag_ignore_all ("-Woverride-init" , +"logic to initialize all and then override some is OK" ); +static const u8 stm32mp1_desc_irq[] = {/* default value */ [0 ... (STM32MP1_DESC_IRQ_SIZE -1 )] =EXTI_INVALID_IRQ ,
@@ -266,6 +276,8 @@ static const u8 stm32mp13_desc_irq[] = { [70 ] =98 , }; +__diag_pop (); +static const struct stm32_exti_drv_data stm32mp1_drv_data = { .exti_banks = stm32mp1_exti_banks, .bank_nr =ARRAY_SIZE (stm32mp1_exti_banks),
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 45/800 irqchip/jcore-aic: Fix missing allocation of IRQ descriptors
In reply to Greg Kroah-HartmanFrom: John Paul Adrian Glaubitz <[email protected]>
[ Upstream commit 4848229494a323eeaab62eee5574ef9f7de80374 ]
The initialization function for the J-Core AIC aic_irq_of_init() is currently missing the call to irq_alloc_descs() which allocates and initializes all the IRQ descriptors. Add missing function call and return the error code from irq_alloc_descs() in case the allocation fails.
--- drivers/irqchip/irq-jcore-aic.c | 7 +++++++ 1 file changed, 7 insertions(+)
drivers/irqchip/irq-jcore-aic.c +7 -0
@@ -68,6 +68,7 @@ static int __init aic_irq_of_init(struct device_node *node,unsigned min_irq =JCORE_AIC2_MIN_HWIRQ ;unsigned dom_sz =JCORE_AIC_MAX_HWIRQ +1 ;struct irq_domain *domain; +int ret;pr_info ("Initializing J-Core AIC\n" );
@@ -100,6 +101,12 @@ static int __init aic_irq_of_init(struct device_node *node, jcore_aic.irq_unmask = noop; jcore_aic.name ="AIC" ; + ret =irq_alloc_descs (-1 , min_irq, dom_sz - min_irq, +of_node_to_nid (node)); + +if (ret <0 ) +return ret; + domain =irq_domain_add_legacy (node, dom_sz - min_irq, min_irq, min_irq, &jcore_aic_irqdomain_ops, &jcore_aic);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 46/800 svcrdma: Prevent page release when nothing was received
In reply to Greg Kroah-HartmanFrom: Chuck Lever <[email protected]>
[ Upstream commit baf6d18b116b7dc84ed5e212c3a89f17cdc3f28c ]
I noticed that svc_rqst_release_pages() was still unnecessarily releasing a page when svc_rdma_recvfrom() returns zero.
--- net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +6 -6
@@ -796,6 +796,12 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)struct svc_rdma_recv_ctxt *ctxt;int ret; +/* Prevent svc_xprt_release() from releasing pages in rq_pages +* when returning 0 or an error. +*/ + rqstp->rq_respages = rqstp->rq_pages; + rqstp->rq_next_page = rqstp->rq_respages; + rqstp->rq_xprt_ctxt =NULL ; ctxt =NULL ;
@@ -819,12 +825,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) DMA_FROM_DEVICE);svc_rdma_build_arg_xdr (rqstp, ctxt); -/* Prevent svc_xprt_release from releasing pages in rq_pages -* if we return 0 or an error. -*/ - rqstp->rq_respages = rqstp->rq_pages; - rqstp->rq_next_page = rqstp->rq_respages; - ret =svc_rdma_xdr_decode_req (&rqstp->rq_arg, ctxt);if (ret <0 ) goto out_err;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 47/800 erofs: fix compact 4B support for 16k block size
In reply to Greg Kroah-HartmanFrom: Gao Xiang <[email protected]>
[ Upstream commit 001b8ccd0650727e54ec16ef72bf1b8eeab7168e ]
In compact 4B, two adjacent lclusters are packed together as a unit to form on-disk indexes for effective random access, as below:
(amortized = 4, vcnt = 2)
_____________________________________________
|___@_____ encoded bits __________|_ blkaddr _|
0 . amortized * vcnt = 8
. .
. . amortized * vcnt - 4 = 4
. .
.____________________________.
|_type (2 bits)_|_clusterofs_|Therefore, encoded bits for each pack are 32 bits (4 bytes). IOWs, since each lcluster can get 16 bits for its type and clusterofs, the maximum supported lclustersize for compact 4B format is 16k (14 bits).
Fix this to enable compact 4B format for 16k lclusters (blocks), which is tested on an arm64 server with 16k page size.
--- fs/erofs/zmap.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)
fs/erofs/zmap.c +1 -5
@@ -129,7 +129,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,u8 *in, type;bool big_pcluster; -if (1 << amortizedshift ==4 ) +if (1 << amortizedshift ==4 && lclusterbits <=14 ) vcnt =2 ;else if (1 << amortizedshift ==2 && lclusterbits ==12 ) vcnt =16 ;
@@ -231,7 +231,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, {struct inode *const inode = m->inode;struct erofs_inode *const vi =EROFS_I (inode); -const unsigned int lclusterbits = vi->z_logical_clusterbits;const erofs_off_t ebase =sizeof (struct z_erofs_map_header ) +ALIGN (erofs_iloc (inode) + vi->inode_isize + vi->xattr_isize,8 );unsigned int totalidx =erofs_iblks (inode);
@@ -239,9 +238,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m,unsigned int amortizedshift;erofs_off_t pos; -if (lclusterbits !=12 ) -return -EOPNOTSUPP ; -if (lcn >= totalidx)return -EINVAL ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 48/800 posix-timers: Prevent RT livelock in itimer_delete()
In reply to Greg Kroah-HartmanFrom: Thomas Gleixner <[email protected]>
[ Upstream commit 9d9e522010eb5685d8b53e8a24320653d9d4cbbf ]
itimer_delete() has a retry loop when the timer is concurrently expired. On non-RT kernels this just spin-waits until the timer callback has completed, except for posix CPU timers which have HAVE_POSIX_CPU_TIMERS_TASK_WORK enabled.
In that case and on RT kernels the existing task could live lock when preempting the task which does the timer delivery.
Replace spin_unlock() with an invocation of timer_wait_running() to handle it the same way as the other retry loops in the posix timer code.
--- kernel/time/posix-timers.c | 43 +++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 8 deletions(-)
kernel/time/posix-timers.c +35 -8
@@ -1037,27 +1037,52 @@ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) }/* -* return timer owned by the process, used by exit_itimers +* Delete a timer if it is armed, remove it from the hash and schedule it +* for RCU freeing. */ static void itimer_delete (struct k_itimer *timer) { -retry_delete: -spin_lock_irq (&timer->it_lock); +unsigned long flags; + +/* +* irqsave is required to make timer_wait_running() work. +*/ +spin_lock_irqsave (&timer->it_lock, flags); +retry_delete: +/* +* Even if the timer is not longer accessible from other tasks +* it still might be armed and queued in the underlying timer +* mechanism. Worse, that timer mechanism might run the expiry +* function concurrently. +*/ if (timer_delete_hook (timer) ==TIMER_RETRY ) { -spin_unlock_irq (&timer->it_lock); +/* +* Timer is expired concurrently, prevent livelocks +* and pointless spinning on RT. +* +* timer_wait_running() drops timer::it_lock, which opens +* the possibility for another task to delete the timer. +* +* That's not possible here because this is invoked from +* do_exit() only for the last thread of the thread group. +* So no other task can access and delete that timer. +*/ +if (WARN_ON_ONCE (timer_wait_running (timer, &flags) != timer)) +return ; + goto retry_delete; }list_del (&timer->list); -spin_unlock_irq (&timer->it_lock); +spin_unlock_irqrestore (&timer->it_lock, flags);release_posix_timer (timer,IT_ID_SET ); }/* -* This is called by do_exit or de_thread, only when nobody else can -* modify the signal->posix_timers list. Yet we need sighand->siglock -* to prevent the race with /proc/pid/timers. +* Invoked from do_exit() when the last thread of a thread group exits. +* At that point no other task can access the timers of the dying +* task anymore. */ void exit_itimers (struct task_struct *tsk) {
@@ -1067,10 +1092,12 @@ void exit_itimers(struct task_struct *tsk)if (list_empty (&tsk->signal->posix_timers))return ; +/* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq (&tsk->sighand->siglock);list_replace_init (&tsk->signal->posix_timers, &timers);spin_unlock_irq (&tsk->sighand->siglock); +/* The timers are not longer accessible via tsk::signal */ while (!list_empty (&timers)) { tmr = list_first_entry(&timers, struct k_itimer, list);itimer_delete (tmr);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 49/800 tick/rcu: Fix bogus ratelimit condition
In reply to Greg Kroah-HartmanFrom: Wen Yang <[email protected]>
[ Upstream commit a7e282c77785c7eabf98836431b1f029481085ad ]
The ratelimit logic in report_idle_softirq() is broken because the exit condition is always true:
static int ratelimit; if (ratelimit < 10) return false; ---> always returns here ratelimit++; ---> no chance to run
Make it check for >= 10 instead.
--- kernel/time/tick-sched.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/time/tick-sched.c +1 -1
@@ -1041,7 +1041,7 @@ static bool report_idle_softirq(void)return false; } -if (ratelimit <10 ) +if (ratelimit >=10 )return false;/* On RT, softirqs handling may be waiting on some lock */
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 50/800 tracing/timer: Add missing hrtimer modes to decode_hrtimer_mode().
In reply to Greg Kroah-HartmanFrom: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit 2951580ba6adb082bb6b7154a5ecb24e7c1f7569 ]
The trace output for the HRTIMER_MODE_.*_HARD modes is seen as a number since these modes are not decoded. The author was not aware of the fancy decoding function which makes the life easier.
Extend decode_hrtimer_mode() with the additional HRTIMER_MODE_.*_HARD modes.
--- include/trace/events/timer.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
include/trace/events/timer.h +5 -1
@@ -158,7 +158,11 @@ DEFINE_EVENT(timer_class, timer_cancel, { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ - { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) + { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ + { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ + { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ + { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ + { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" })/** * hrtimer_init - called when the hrtimer is initialized
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 51/800 btrfs: always read the entire extent_buffer
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit e95382834cf885b478dbe14a66451b863eb35c94 ]
Currently read_extent_buffer_pages skips pages that are already uptodate when reading in an extent_buffer. While this reduces the amount of data read, it increases the number of I/O operations as we now need to do multiple I/Os when reading an extent buffer with one or more uptodate pages in the middle of it. On any modern storage device, be that hard drives or SSDs this actually decreases I/O performance. Fortunately this case is pretty rare as the pages are always initially read together and then aged the same way. Besides simplifying the code a bit as-is this will allow for major simplifications to the I/O completion handler later on.
Note that the case where all pages are uptodate is still handled by an optimized fast path that does not read any data from disk.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-)
fs/btrfs/extent_io.c +5 -12
@@ -4314,7 +4314,6 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,int locked_pages =0 ;int all_uptodate =1 ;int num_pages; -unsigned long num_reads =0 ;struct btrfs_bio_ctrl bio_ctrl = { .opf =REQ_OP_READ , .mirror_num = mirror_num,
@@ -4360,10 +4359,8 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,*/ for (i =0 ; i < num_pages; i++) { page = eb->pages[i]; -if (!PageUptodate (page)) { - num_reads++; +if (!PageUptodate (page)) all_uptodate =0 ; - } }if (all_uptodate) {
@@ -4373,7 +4370,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,clear_bit (EXTENT_BUFFER_READ_ERR , &eb->bflags); eb->read_mirror =0 ; -atomic_set (&eb->io_pages, num_reads); +atomic_set (&eb->io_pages, num_pages);/* * It is possible for release_folio to clear the TREE_REF bit before we * set io_pages. See check_buffer_tree_ref for a more detailed comment.
@@ -4383,13 +4380,9 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,for (i =0 ; i < num_pages; i++) { page = eb->pages[i]; -if (!PageUptodate (page)) { -ClearPageError (page); -submit_extent_page (&bio_ctrl,page_offset (page), page, -PAGE_SIZE ,0 ); - }else { -unlock_page (page); - } +ClearPageError (page); +submit_extent_page (&bio_ctrl,page_offset (page), page, +PAGE_SIZE ,0 ); }submit_one_bio (&bio_ctrl);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 25/800 blk-cgroup: Reinit blkg_iostat_set after clearing in blkcg_reset_stats()
In reply to Greg Kroah-HartmanFrom: Waiman Long <[email protected]>
[ Upstream commit 3d2af77e31ade05ff7ccc3658c3635ec1bea0979 ]
When blkg_alloc() is called to allocate a blkcg_gq structure with the associated blkg_iostat_set's, there are 2 fields within blkg_iostat_set that requires proper initialization - blkg & sync. The former field was introduced by commit 3b8cc6298724 ("blk-cgroup:
Optimize blkcg_rstat_flush()") while the later one was introduced by commit f73316482977 ("blk-cgroup: reimplement basic IO stats using cgroup rstat").
Unfortunately those fields in the blkg_iostat_set's are not properly re-initialized when they are cleared in v1's blkcg_reset_stats(). This can lead to a kernel panic due to NULL pointer access of the blkg pointer. The missing initialization of sync is less problematic and can be a problem in a debug kernel due to missing lockdep initialization.
Fix these problems by re-initializing them after memory clearing.
--- block/blk-cgroup.c | 5 +++++ 1 file changed, 5 insertions(+)
block/blk-cgroup.c +5 -0
@@ -624,8 +624,13 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,struct blkg_iostat_set *bis =per_cpu_ptr (blkg->iostat_cpu, cpu);memset (bis,0 ,sizeof (*bis)); + +/* Re-initialize the cleared blkg_iostat_set */ +u64_stats_init (&bis->sync); + bis->blkg = blkg; }memset (&blkg->iostat,0 ,sizeof (blkg->iostat)); +u64_stats_init (&blkg->iostat.sync);for (i =0 ; i <BLKCG_MAX_POLS ; i++) {struct blkcg_policy *pol = blkcg_policy[i];
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 26/800 virt: sevguest: Add CONFIG_CRYPTO dependency
In reply to Greg Kroah-HartmanFrom: Arnd Bergmann <[email protected]>
[ Upstream commit 84b9b44b99780d35fe72ac63c4724f158771e898 ]
This driver fails to link when CRYPTO is disabled, or in a loadable module:
WARNING: unmet direct dependencies detected for CRYPTO_GCM
WARNING: unmet direct dependencies detected for CRYPTO_AEAD2
Depends on [m]: CRYPTO [=m]
Selected by [y]:
- SEV_GUEST [=y] && VIRT_DRIVERS [=y] && AMD_MEM_ENCRYPT [=y]
x86_64-linux-ld: crypto/aead.o: in function `crypto_register_aeads':
--- drivers/virt/coco/sev-guest/Kconfig | 1 + 1 file changed, 1 insertion(+)
drivers/virt/coco/sev-guest/Kconfig +1 -0
@@ -2,6 +2,7 @@ config SEV_GUEST tristate "AMD SEV Guest driver" default m depends on AMD_MEM_ENCRYPT + select CRYPTO select CRYPTO_AEAD2 select CRYPTO_GCM help
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 27/800 blk-mq: fix potential io hang by wrong wake_batch
In reply to Greg Kroah-HartmanFrom: Yu Kuai <[email protected]>
[ Upstream commit 4f1731df60f9033669f024d06ae26a6301260b55 ]
In __blk_mq_tag_busy/idle(), updating 'active_queues' and calculating 'wake_batch' is not atomic:
t1: t2:_blk_mq_tag_busy blk_mq_tag_busy
inc active_queues
// assume 1->2
inc active_queues // 2 -> 3 blk_mq_update_wake_batch // calculate based on 3
blk_mq_update_wake_batch
/* calculate based on 2, while active_queues is actually 3. */
Fix this problem by protecting them wih 'tags->lock', this is not a hot path, so performance should not be concerned. And now that all writers are inside the lock, switch 'actives_queues' from atomic to unsigned int.
--- block/blk-mq-debugfs.c | 2 +- block/blk-mq-tag.c | 15 ++++++++++----- block/blk-mq.h | 3 +-- include/linux/blk-mq.h | 3 +-- 4 files changed, 13 insertions(+), 10 deletions(-)
block/blk-mq-debugfs.c +1 -1
@@ -399,7 +399,7 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m,seq_printf (m,"nr_tags=%u\n" , tags->nr_tags);seq_printf (m,"nr_reserved_tags=%u\n" , tags->nr_reserved_tags);seq_printf (m,"active_queues=%d\n" , -atomic_read (&tags->active_queues)); +READ_ONCE (tags->active_queues));seq_puts (m,"\nbitmap_tags:\n" );sbitmap_queue_show (&tags->bitmap_tags, m);
block/blk-mq-tag.c +10 -5
@@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,void __blk_mq_tag_busy (struct blk_mq_hw_ctx *hctx) {unsigned int users; +struct blk_mq_tags *tags = hctx->tags;/* * calling test_bit() prior to test_and_set_bit() is intentional,
@@ -55,9 +56,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)return ; } - users =atomic_inc_return (&hctx->tags->active_queues); - -blk_mq_update_wake_batch (hctx->tags, users); +spin_lock_irq (&tags->lock); + users = tags->active_queues +1 ; +WRITE_ONCE (tags->active_queues, users); +blk_mq_update_wake_batch (tags, users); +spin_unlock_irq (&tags->lock); }/*
@@ -90,9 +93,11 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx)return ; } - users =atomic_dec_return (&tags->active_queues); - +spin_lock_irq (&tags->lock); + users = tags->active_queues -1 ; +WRITE_ONCE (tags->active_queues, users);blk_mq_update_wake_batch (tags, users); +spin_unlock_irq (&tags->lock);blk_mq_tag_wakeup_all (tags, false); }
block/blk-mq.h +1 -2
@@ -417,8 +417,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,return true; } - users =atomic_read (&hctx->tags->active_queues); - + users =READ_ONCE (hctx->tags->active_queues);if (!users)return true;
include/linux/blk-mq.h +1 -2
@@ -746,8 +746,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,struct blk_mq_tags {unsigned int nr_tags;unsigned int nr_reserved_tags; - -atomic_t active_queues; +unsigned int active_queues;struct sbitmap_queue bitmap_tags;struct sbitmap_queue breserved_tags;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 28/800 lockd: drop inappropriate svc_get() from locked_get()
In reply to Greg Kroah-HartmanFrom: NeilBrown <[email protected]>
[ Upstream commit 665e89ab7c5af1f2d260834c861a74b01a30f95f ]
The below-mentioned patch was intended to simplify refcounting on the svc_serv used by locked. The goal was to only ever have a single reference from the single thread. To that end we dropped a call to lockd_start_svc() (except when creating thread) which would take a reference, and dropped the svc_put(serv) that would drop that reference.
Unfortunately we didn't also remove the svc_get() from lockd_create_svc() in the case where the svc_serv already existed. So after the patch:
- on the first call the svc_serv was allocated and the one reference was given to the thread, so there are no extra references
- on subsequent calls svc_get() was called so there is now an extra reference.
This is clearly not consistent.
The inconsistency is also clear in the current code in lockd_get() takes *two* references, one on nlmsvc_serv and one by incrementingnlmsvc_users. This clearly does not match lockd_put().
So: drop that svc_get() from lockd_get() (which used to be in lockd_create_svc().
--- fs/lockd/svc.c | 1 - 1 file changed, 1 deletion(-)
fs/lockd/svc.c +0 -1
@@ -355,7 +355,6 @@ static int lockd_get(void)int error;if (nlmsvc_serv) { -svc_get (nlmsvc_serv); nlmsvc_users++;return 0 ; }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 29/800 nvme-core: fix memory leak in dhchap_secret_store
In reply to Greg Kroah-HartmanFrom: Chaitanya Kulkarni <[email protected]>
[ Upstream commit a836ca33c5b07d34dd5347af9f64d25651d12674 ]
Free dhchap_secret in nvme_ctrl_dhchap_secret_store() before we return fix following kmemleack:-
unreferenced object 0xffff8886376ea800 (size 64):
comm "check", pid 22048, jiffies 4344316705 (age 92.199s) hex dump (first 32 bytes):
44 48 48 43 2d 31 3a 30 30 3a 6e 78 72 35 4b 67 DHHC-1:00:nxr5Kg
75 58 34 75 6f 41 78 73 4a 61 34 63 2f 68 75 4c uX4uoAxsJa4c/huL
backtrace:
[<0000000030ce5d4b>] __kmalloc+0x4b/0x130
[<000000009be1cdc1>] nvme_ctrl_dhchap_secret_store+0x8f/0x160 [nvme_core]
[<00000000ac06c96a>] kernfs_fop_write_iter+0x12b/0x1c0
[<00000000437e7ced>] vfs_write+0x2ba/0x3c0
[<00000000f9491baf>] ksys_write+0x5f/0xe0
[<000000001c46513d>] do_syscall_64+0x3b/0x90
[<00000000ecf348fe>] entry_SYSCALL_64_after_hwframe+0x72/0xdc
unreferenced object 0xffff8886376eaf00 (size 64):
comm "check", pid 22048, jiffies 4344316736 (age 92.168s)
hex dump (first 32 bytes):
44 48 48 43 2d 31 3a 30 30 3a 6e 78 72 35 4b 67 DHHC-1:00:nxr5Kg
75 58 34 75 6f 41 78 73 4a 61 34 63 2f 68 75 4c uX4uoAxsJa4c/huL
backtrace:
[<0000000030ce5d4b>] __kmalloc+0x4b/0x130
[<000000009be1cdc1>] nvme_ctrl_dhchap_secret_store+0x8f/0x160 [nvme_core]
[<00000000ac06c96a>] kernfs_fop_write_iter+0x12b/0x1c0
[<00000000437e7ced>] vfs_write+0x2ba/0x3c0
[<00000000f9491baf>] ksys_write+0x5f/0xe0
[<000000001c46513d>] do_syscall_64+0x3b/0x90
[<00000000ecf348fe>] entry_SYSCALL_64_after_hwframe+0x72/0xdc--- drivers/nvme/host/core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/nvme/host/core.c +5 -2
@@ -3872,8 +3872,10 @@ static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev,int ret; ret =nvme_auth_generate_key (dhchap_secret, &key); -if (ret) +if (ret) { +kfree (dhchap_secret);return ret; + }kfree (opts->dhchap_secret); opts->dhchap_secret = dhchap_secret; host_key = ctrl->host_key;
@@ -3881,7 +3883,8 @@ static ssize_t nvme_ctrl_dhchap_secret_store(struct device *dev, ctrl->host_key = key;mutex_unlock (&ctrl->dhchap_auth_mutex);nvme_auth_free_key (host_key); - } + }else +kfree (dhchap_secret);/* Start re-authentication */ dev_info (ctrl->device,"re-authenticating controller\n" );queue_work (nvme_wq, &ctrl->dhchap_auth_work);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 30/800 nvme-core: fix memory leak in dhchap_ctrl_secret
In reply to Greg Kroah-HartmanFrom: Chaitanya Kulkarni <[email protected]>
[ Upstream commit 99c2dcc8ffc24e210a3aa05c204d92f3ef460b05 ]
Free dhchap_secret in nvme_ctrl_dhchap_ctrl_secret_store() before we return when nvme_auth_generate_key() returns error.
--- drivers/nvme/host/core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/nvme/host/core.c +5 -2
@@ -3929,8 +3929,10 @@ static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev,int ret; ret =nvme_auth_generate_key (dhchap_secret, &key); -if (ret) +if (ret) { +kfree (dhchap_secret);return ret; + }kfree (opts->dhchap_ctrl_secret); opts->dhchap_ctrl_secret = dhchap_secret; ctrl_key = ctrl->ctrl_key;
@@ -3938,7 +3940,8 @@ static ssize_t nvme_ctrl_dhchap_ctrl_secret_store(struct device *dev, ctrl->ctrl_key = key;mutex_unlock (&ctrl->dhchap_auth_mutex);nvme_auth_free_key (ctrl_key); - } + }else +kfree (dhchap_secret);/* Start re-authentication */ dev_info (ctrl->device,"re-authenticating controller\n" );queue_work (nvme_wq, &ctrl->dhchap_auth_work);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 31/800 nvme-core: add missing fault-injection cleanup
In reply to Greg Kroah-HartmanFrom: Chaitanya Kulkarni <[email protected]>
[ Upstream commit 3a12a0b868a512fcada564699d00f5e652c0998c ]
Add missing fault-injection cleanup in nvme_init_ctrl() in the error unwind path that also fixes following message for blktests:-
linux-block (for-next) # grep debugfs debugfs-err.log
[ 147.853464] debugfs: Directory 'nvme1' with parent '/' already present! [ 147.853973] nvme1: failed to create debugfs attr [ 148.802490] debugfs: Directory 'nvme1' with parent '/' already present! [ 148.803244] nvme1: failed to create debugfs attr [ 148.877304] debugfs: Directory 'nvme1' with parent '/' already present! [ 148.877775] nvme1: failed to create debugfs attr [ 149.816652] debugfs: Directory 'nvme1' with parent '/' already present! [ 149.818011] nvme1: failed to create debugfs attr
Stable-dep-of: 7ed5cf8e6d9b ("nvme-core: fix dev_pm_qos memleak")
--- drivers/nvme/host/core.c | 1 + 1 file changed, 1 insertion(+)
drivers/nvme/host/core.c +1 -0
@@ -5249,6 +5249,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,return 0 ; out_free_cdev: +nvme_fault_inject_fini (&ctrl->fault_inject);cdev_device_del (&ctrl->cdev, ctrl->device); out_free_name:nvme_put_ctrl (ctrl);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 22/800 fsverity: dont use bio_first_page_all() in fsverity_verify_bio()
In reply to Greg Kroah-HartmanFrom: Eric Biggers <[email protected]>
[ Upstream commit d1f0c5ea04cd0a93309de0246278f0b22394692d ]
bio_first_page_all(bio)->mapping->host is not compatible with large folios, since the first page of the bio is not necessarily the head page of the folio, and therefore it might not have the mapping pointer set.
Therefore, move the dereference of ->mapping->host into verify_data_blocks(), which works with a folio.
(Like the commit that this Fixes, this hasn't actually been tested with large folios yet, since the filesystems that use fs/verity/ don't support that yet. But based on code review, I think this is needed.)
--- fs/verity/verify.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
fs/verity/verify.c +5 -5
@@ -256,9 +256,10 @@ verify_data_block(struct inode *inode, struct fsverity_info *vi, }static bool -verify_data_blocks (struct inode *inode,struct folio *data_folio, -size_t len,size_t offset,unsigned long max_ra_pages) +verify_data_blocks (struct folio *data_folio,size_t len,size_t offset, +unsigned long max_ra_pages) { +struct inode *inode = data_folio->mapping->host;struct fsverity_info *vi = inode->i_verity_info;const unsigned int block_size = vi->tree_params.block_size;u64 pos = (u64 )data_folio->index <<PAGE_SHIFT ;
@@ -298,7 +299,7 @@ verify_data_blocks(struct inode *inode, struct folio *data_folio,*/ bool fsverity_verify_blocks (struct folio *folio,size_t len,size_t offset) { -return verify_data_blocks (folio->mapping->host, folio, len, offset,0 ); +return verify_data_blocks (folio, len, offset,0 ); }EXPORT_SYMBOL_GPL (fsverity_verify_blocks);
@@ -319,7 +320,6 @@ EXPORT_SYMBOL_GPL(fsverity_verify_blocks);*/ void fsverity_verify_bio (struct bio *bio) { -struct inode *inode =bio_first_page_all (bio)->mapping->host;struct folio_iter fi;unsigned long max_ra_pages =0 ;
@@ -337,7 +337,7 @@ void fsverity_verify_bio(struct bio *bio) }bio_for_each_folio_all (fi, bio) { -if (!verify_data_blocks (inode, fi.folio, fi.length, fi.offset, +if (!verify_data_blocks (fi.folio, fi.length, fi.offset, max_ra_pages)) { bio->bi_status =BLK_STS_IOERR ;break ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 53/800 btrfs: return bool from lock_extent_buffer_for_io
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 9fdd160160f002ac2604c5b8f90598febad44ae7 ]
lock_extent_buffer_for_io never returns a negative error value, so switch the return value to a simple bool.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 37 +++++++++++-------------------------- 1 file changed, 11 insertions(+), 26 deletions(-)
fs/btrfs/extent_io.c +11 -26
@@ -1671,18 +1671,17 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)* * May try to flush write bio if we can't get the lock. * -* Return 0 if the extent buffer doesn't need to be submitted. -* (E.g. the extent buffer is not dirty) -* Return >0 is the extent buffer is submitted to bio. -* Return <0 if something went wrong, no page is locked. +* Return %false if the extent buffer doesn't need to be submitted (e.g. the +* extent buffer is not dirty) +* Return %true is the extent buffer is submitted to bio. */ -static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *eb, +static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eb,struct btrfs_bio_ctrl *bio_ctrl) {struct btrfs_fs_info *fs_info = eb->fs_info;int i, num_pages;int flush =0 ; -int ret =0 ; +bool ret = false;if (!btrfs_try_tree_write_lock (eb)) {submit_write_bio (bio_ctrl,0 );
@@ -1693,7 +1692,7 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *ebif (test_bit (EXTENT_BUFFER_WRITEBACK , &eb->bflags)) {btrfs_tree_unlock (eb);if (bio_ctrl->wbc->sync_mode !=WB_SYNC_ALL ) -return 0 ; +return false;if (!flush) {submit_write_bio (bio_ctrl,0 ); flush =1 ;
@@ -1720,7 +1719,7 @@ static noinline_for_stack int lock_extent_buffer_for_io(struct extent_buffer *ebpercpu_counter_add_batch (&fs_info->dirty_metadata_bytes, -eb->len, fs_info->dirty_metadata_batch); - ret =1 ; + ret = true; }else {spin_unlock (&eb->refs_lock); }
@@ -2053,7 +2052,6 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)u64 page_start =page_offset (page);int bit_start =0 ;int sectors_per_node = fs_info->nodesize >> fs_info->sectorsize_bits; -int ret;/* Lock and write each dirty extent buffers in the range */ while (bit_start < fs_info->subpage_info->bitmap_nr_bits) {
@@ -2099,25 +2097,13 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)if (!eb)continue ; - ret =lock_extent_buffer_for_io (eb, bio_ctrl); -if (ret ==0 ) { -free_extent_buffer (eb); -continue ; +if (lock_extent_buffer_for_io (eb, bio_ctrl)) { +write_one_subpage_eb (eb, bio_ctrl); + submitted++; } -if (ret <0 ) { -free_extent_buffer (eb); - goto cleanup; - } -write_one_subpage_eb (eb, bio_ctrl);free_extent_buffer (eb); - submitted++; }return submitted; - -cleanup: -/* We hit error, end bio for the submitted extent buffers */ -submit_write_bio (bio_ctrl, ret); -return ret; }/*
@@ -2196,8 +2182,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, *eb_context = eb; - ret =lock_extent_buffer_for_io (eb, bio_ctrl); -if (ret <=0 ) { +if (!lock_extent_buffer_for_io (eb, bio_ctrl)) {btrfs_revert_meta_write_pointer (cache, eb);if (cache)btrfs_put_block_group (cache);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 62/800 PM: domains: fix integer overflow issues in genpd_parse_state()
In reply to Greg Kroah-HartmanFrom: Nikita Zhandarovich <[email protected]>
[ Upstream commit e5d1c8722083f0332dcd3c85fa1273d85fb6bed8 ]
Currently, while calculating residency and latency values, right operands may overflow if resulting values are big enough.
To prevent this, albeit unlikely case, play it safe and convert right operands to left ones' type s64.
Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE.
--- drivers/base/power/domain.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/base/power/domain.c +3 -3
@@ -2939,10 +2939,10 @@ static int genpd_parse_state(struct genpd_power_state *genpd_state, err =of_property_read_u32 (state_node,"min-residency-us" , &residency);if (!err) - genpd_state->residency_ns =1000 * residency; + genpd_state->residency_ns =1000LL * residency; - genpd_state->power_on_latency_ns =1000 * exit_latency; - genpd_state->power_off_latency_ns =1000 * entry_latency; + genpd_state->power_on_latency_ns =1000LL * exit_latency; + genpd_state->power_off_latency_ns =1000LL * entry_latency; genpd_state->fwnode = &state_node->fwnode;return 0 ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 63/800 perf/arm-cmn: Fix DTC reset
In reply to Greg Kroah-HartmanFrom: Robin Murphy <[email protected]>
[ Upstream commit 71746c995cac92fcf6a65661b51211cf2009d7f0 ]
It turns out that my naive DTC reset logic fails to work as intended, since, after checking with the hardware designers, the PMU actually needs to be fully enabled in order to correctly clear any pending overflows. Therefore, invert the sequence to start with turning on both enables so that we can reliably get the DTCs into a known state, then moving to our normal counters-stopped state from there. Since all the DTM counters have already been unpaired during the initial discovery pass, we just need to additionally reset the cycle counters to ensure that no other unexpected overflows occur during this period.
--- drivers/perf/arm-cmn.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/perf/arm-cmn.c +4 -3
@@ -1899,9 +1899,10 @@ static int arm_cmn_init_dtc(struct arm_cmn *cmn, struct arm_cmn_node *dn, int idif (dtc->irq <0 )return dtc->irq; -writel_relaxed (0 , dtc->base +CMN_DT_PMCR ); +writel_relaxed (CMN_DT_DTC_CTL_DT_EN , dtc->base +CMN_DT_DTC_CTL ); +writel_relaxed (CMN_DT_PMCR_PMU_EN |CMN_DT_PMCR_OVFL_INTR_EN , dtc->base +CMN_DT_PMCR ); +writeq_relaxed (0 , dtc->base +CMN_DT_PMCCNTR );writel_relaxed (0x1ff , dtc->base +CMN_DT_PMOVSR_CLR ); -writel_relaxed (CMN_DT_PMCR_OVFL_INTR_EN , dtc->base +CMN_DT_PMCR );return 0 ; }
@@ -1961,7 +1962,7 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn) dn->type =CMN_TYPE_CCLA ; } -writel_relaxed (CMN_DT_DTC_CTL_DT_EN , cmn->dtc[0 ].base +CMN_DT_DTC_CTL ); +arm_cmn_set_state (cmn,CMN_STATE_DISABLED );return 0 ; }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 64/800 drivers/perf: apple_m1: Force 63bit counters for M2 CPUs
In reply to Greg Kroah-HartmanFrom: Marc Zyngier <[email protected]>
[ Upstream commit 8be3593b9efa8903d2ee7bb9cdf57a8e56c66f36 ]
Sidharth reports that on M2, the PMU never generates any interrupt when using 'perf record', which is a annoying as you get no sample. I'm temped to say "no sample, no problem", but others may have a different opinion.
Upon investigation, it appears that the counters on M2 are significantly different from the ones on M1, as they count on 64 bits instead of 48. Which of course, in the fine M1 tradition, means that we can only use 63 bits, as the top bit is used to signal the interrupt...
This results in having to introduce yet another flag to indicate yet another odd counter width. Who knows what the next crazy implementation will do...
With this, perf can work out the correct offset, and 'perf record' works as intended.
Tested on M2 and M2-Pro CPUs.
--- drivers/perf/apple_m1_cpu_pmu.c | 30 ++++++++++++++++++++++++------ drivers/perf/arm_pmu.c | 2 ++ include/linux/perf/arm_pmu.h | 2 ++ 3 files changed, 28 insertions(+), 6 deletions(-)
drivers/perf/apple_m1_cpu_pmu.c +24 -6
@@ -493,6 +493,17 @@ static int m1_pmu_map_event(struct perf_event *event)return armpmu_map_event (event, &m1_pmu_perf_map,NULL ,M1_PMU_CFG_EVENT ); } +static int m2_pmu_map_event (struct perf_event *event) +{ +/* +* Same deal as the above, except that M2 has 64bit counters. +* Which, as far as we're concerned, actually means 63 bits. +* Yes, this is getting awkward. +*/ + event->hw.flags |=ARMPMU_EVT_63BIT ; +return armpmu_map_event (event, &m1_pmu_perf_map,NULL ,M1_PMU_CFG_EVENT ); +} +static void m1_pmu_reset (void *info) {int i;
@@ -525,7 +536,7 @@ static int m1_pmu_set_event_filter(struct hw_perf_event *event,return 0 ; } -static int m1_pmu_init (struct arm_pmu *cpu_pmu) +static int m1_pmu_init (struct arm_pmu *cpu_pmu,u32 flags) { cpu_pmu->handle_irq = m1_pmu_handle_irq; cpu_pmu->enable = m1_pmu_enable_event;
@@ -536,7 +547,14 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->clear_event_idx = m1_pmu_clear_event_idx; cpu_pmu->start = m1_pmu_start; cpu_pmu->stop = m1_pmu_stop; - cpu_pmu->map_event = m1_pmu_map_event; + +if (flags &ARMPMU_EVT_47BIT ) + cpu_pmu->map_event = m1_pmu_map_event; +else if (flags &ARMPMU_EVT_63BIT ) + cpu_pmu->map_event = m2_pmu_map_event; +else +return WARN_ON (-EINVAL ); + cpu_pmu->reset = m1_pmu_reset; cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
@@ -550,25 +568,25 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu)static int m1_pmu_ice_init (struct arm_pmu *cpu_pmu) { cpu_pmu->name ="apple_icestorm_pmu" ; -return m1_pmu_init (cpu_pmu); +return m1_pmu_init (cpu_pmu,ARMPMU_EVT_47BIT ); }static int m1_pmu_fire_init (struct arm_pmu *cpu_pmu) { cpu_pmu->name ="apple_firestorm_pmu" ; -return m1_pmu_init (cpu_pmu); +return m1_pmu_init (cpu_pmu,ARMPMU_EVT_47BIT ); }static int m2_pmu_avalanche_init (struct arm_pmu *cpu_pmu) { cpu_pmu->name ="apple_avalanche_pmu" ; -return m1_pmu_init (cpu_pmu); +return m1_pmu_init (cpu_pmu,ARMPMU_EVT_63BIT ); }static int m2_pmu_blizzard_init (struct arm_pmu *cpu_pmu) { cpu_pmu->name ="apple_blizzard_pmu" ; -return m1_pmu_init (cpu_pmu); +return m1_pmu_init (cpu_pmu,ARMPMU_EVT_63BIT ); }static const struct of_device_id m1_pmu_of_device_ids[] = {
drivers/perf/arm_pmu.c +2 -0
@@ -109,6 +109,8 @@ static inline u64 arm_pmu_event_max_period(struct perf_event *event) {if (event->hw.flags &ARMPMU_EVT_64BIT )return GENMASK_ULL (63 ,0 ); +else if (event->hw.flags &ARMPMU_EVT_63BIT ) +return GENMASK_ULL (62 ,0 );else if (event->hw.flags &ARMPMU_EVT_47BIT )return GENMASK_ULL (46 ,0 );else
include/linux/perf/arm_pmu.h +2 -0
@@ -26,9 +26,11 @@*/ #define ARMPMU_EVT_64BIT 0x00001/* Event uses a 64bit counter */ #define ARMPMU_EVT_47BIT 0x00002/* Event uses a 47bit counter */ +#define ARMPMU_EVT_63BIT 0x00004/* Event uses a 63bit counter */ static_assert ((PERF_EVENT_FLAG_ARCH &ARMPMU_EVT_64BIT ) ==ARMPMU_EVT_64BIT );static_assert ((PERF_EVENT_FLAG_ARCH &ARMPMU_EVT_47BIT ) ==ARMPMU_EVT_47BIT ); +static_assert ((PERF_EVENT_FLAG_ARCH &ARMPMU_EVT_63BIT ) ==ARMPMU_EVT_63BIT );#define HW_OP_UNSUPPORTED 0xFFFF#define C (_x) PERF_COUNT_HW_CACHE_##_x
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 65/800 x86/mm: Allow guest.enc_status_change_prepare() to fail
In reply to Greg Kroah-HartmanFrom: Kirill A. Shutemov <[email protected]>
[ Upstream commit 3f6819dd192ef4f0c568ec3e9d6d408b3fa1ad3d ]
TDX code is going to provide guest.enc_status_change_prepare() that is able to fail. TDX will use the call to convert the GPA range from shared to private. This operation can fail.
Add a way to return an error from the callback.
Stable-dep-of: 195edce08b63 ("x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()")
--- arch/x86/include/asm/x86_init.h | 2 +- arch/x86/kernel/x86_init.c | 2 +- arch/x86/mm/mem_encrypt_amd.c | 4 +++- arch/x86/mm/pat/set_memory.c | 3 ++- 4 files changed, 7 insertions(+), 4 deletions(-)
arch/x86/include/asm/x86_init.h +1 -1
@@ -150,7 +150,7 @@ struct x86_init_acpi {* @enc_cache_flush_required Returns true if a cache flush is needed before changing page encryption status */ struct x86_guest { -void (*enc_status_change_prepare)(unsigned long vaddr,int npages,bool enc); +bool (*enc_status_change_prepare)(unsigned long vaddr,int npages,bool enc);bool (*enc_status_change_finish)(unsigned long vaddr,int npages,bool enc);bool (*enc_tlb_flush_required)(bool enc);bool (*enc_cache_flush_required)(void );
arch/x86/kernel/x86_init.c +1 -1
@@ -130,7 +130,7 @@ struct x86_cpuinit_ops x86_cpuinit = {static void default_nmi_init (void ) { }; -static void enc_status_change_prepare_noop (unsigned long vaddr,int npages,bool enc) { } +static bool enc_status_change_prepare_noop (unsigned long vaddr,int npages,bool enc) {return true; }static bool enc_status_change_finish_noop (unsigned long vaddr,int npages,bool enc) {return false; }static bool enc_tlb_flush_required_noop (bool enc) {return false; }static bool enc_cache_flush_required_noop (void ) {return false; }
arch/x86/mm/mem_encrypt_amd.c +3 -1
@@ -319,7 +319,7 @@ static void enc_dec_hypercall(unsigned long vaddr, int npages, bool enc)#endif } -static void amd_enc_status_change_prepare (unsigned long vaddr,int npages,bool enc) +static bool amd_enc_status_change_prepare (unsigned long vaddr,int npages,bool enc) {/* * To maintain the security guarantees of SEV-SNP guests, make sure
@@ -327,6 +327,8 @@ static void amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool*/ if (cc_platform_has (CC_ATTR_GUEST_SEV_SNP ) && !enc)snp_set_memory_shared (vaddr, npages); + +return true; }/* Return true unconditionally: return value doesn't matter for the SEV side */
arch/x86/mm/pat/set_memory.c +2 -1
@@ -2151,7 +2151,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)cpa_flush (&cpa, x86_platform.guest.enc_cache_flush_required ());/* Notify hypervisor that we are about to set/clr encryption attribute. */ - x86_platform.guest.enc_status_change_prepare (addr, numpages, enc); +if (!x86_platform.guest.enc_status_change_prepare (addr, numpages, enc)) +return -EIO ; ret =__change_page_attr_set_clr (&cpa,1 );
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 66/800 x86/tdx: Fix race between set_memory_encrypted() and load_unaligned_zeropad()
In reply to Greg Kroah-HartmanFrom: Kirill A. Shutemov <[email protected]>
[ Upstream commit 195edce08b63d293377f615f4f7f086715d2d212 ]
tl;dr: There is a race in the TDX private<=>shared conversion code
which could kill the TDX guest. Fix it by changing conversion ordering to eliminate the window.
TDX hardware maintains metadata to track which pages are private and shared. Additionally, TDX guests use the guest x86 page tables to specify whether a given mapping is intended to be private or shared. Bad things happen when the intent and metadata do not match.
So there are two thing in play:
1. "the page" -- the physical TDX page metadata
2. "the mapping" -- the guest-controlled x86 page table intent
For instance, an unrecoverable exit to VMM occurs if a guest touches a private mapping that points to a shared physical page.
In summary:
* Private mapping => Private Page == OK (obviously)
* Shared mapping => Shared Page == OK (obviously)
* Private mapping => Shared Page == BIG BOOM!
* Shared mapping => Private Page == OK-ish
(It will read generate a recoverable #VE via handle_mmio())
Enter load_unaligned_zeropad(). It can touch memory that is adjacent but otherwise unrelated to the memory it needs to touch. It will cause one of those unrecoverable exits (aka. BIG BOOM) if it blunders into a shared mapping pointing to a private page.
This is a problem when __set_memory_enc_pgtable() converts pages from shared to private. It first changes the mapping and second modifies the TDX page metadata. It's moving from:
* Shared mapping => Shared Page == OK
to:
* Private mapping => Shared Page == BIG BOOM!
This means that there is a window with a shared mapping pointing to a private page where load_unaligned_zeropad() can strike.
Add a TDX handler for guest.enc_status_change_prepare(). This converts the page from shared to private *before* the page becomes private. This ensures that there is never a private mapping to a shared page.
Leave a guest.enc_status_change_finish() in place but only use it for private=>shared conversions. This will delay updating the TDX metadata marking the page private until *after* the mapping matches the metadata. This also ensures that there is never a private mapping to a shared page.
[ dhansen: rewrite changelog ]
--- arch/x86/coco/tdx/tdx.c | 51 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 48 insertions(+), 3 deletions(-)
arch/x86/coco/tdx/tdx.c +48 -3
@@ -840,6 +840,30 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)return true; } +static bool tdx_enc_status_change_prepare (unsigned long vaddr,int numpages, +bool enc) +{ +/* +* Only handle shared->private conversion here. +* See the comment in tdx_early_init(). +*/ +if (enc) +return tdx_enc_status_changed (vaddr, numpages, enc); +return true; +} + +static bool tdx_enc_status_change_finish (unsigned long vaddr,int numpages, +bool enc) +{ +/* +* Only handle private->shared conversion here. +* See the comment in tdx_early_init(). +*/ +if (!enc) +return tdx_enc_status_changed (vaddr, numpages, enc); +return true; +} +void __init tdx_early_init (void ) {u64 cc_mask;
@@ -867,9 +891,30 @@ void __init tdx_early_init(void)*/ physical_mask &= cc_mask -1 ; - x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; - x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required; - x86_platform.guest.enc_status_change_finish = tdx_enc_status_changed; +/* +* The kernel mapping should match the TDX metadata for the page. +* load_unaligned_zeropad() can touch memory *adjacent* to that which is +* owned by the caller and can catch even _momentary_ mismatches. Bad +* things happen on mismatch: +* +* - Private mapping => Shared Page == Guest shutdown +* - Shared mapping => Private Page == Recoverable #VE +* +* guest.enc_status_change_prepare() converts the page from +* shared=>private before the mapping becomes private. +* +* guest.enc_status_change_finish() converts the page from +* private=>shared after the mapping becomes private. +* +* In both cases there is a temporary shared mapping to a private page, +* which can result in a #VE. But, there is never a private mapping to +* a shared page. +*/ + x86_platform.guest.enc_status_change_prepare = tdx_enc_status_change_prepare; + x86_platform.guest.enc_status_change_finish = tdx_enc_status_change_finish; + + x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required; + x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;pr_info ("Guest detected\n" ); }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 67/800 drivers/perf: hisi: Dont migrate perf to the CPU going to teardown
In reply to Greg Kroah-HartmanFrom: Junhao He <[email protected]>
[ Upstream commit 7a6a9f1c5a0a875a421db798d4b2ee022dc1ee1a ]
The driver needs to migrate the perf context if the current using CPU going to teardown. By the time calling the cpuhp::teardown() callback the cpu_online_mask() hasn't updated yet and still includes the CPU going to teardown. In current driver's implementation we may migrate the context to the teardown CPU and leads to the below calltrace:
...
[ 368.104662][ T932] task:cpuhp/0 state:D stack: 0 pid: 15 ppid: 2 flags:0x00000008 [ 368.113699][ T932] Call trace: [ 368.116834][ T932] __switch_to+0x7c/0xbc [ 368.120924][ T932] __schedule+0x338/0x6f0 [ 368.125098][ T932] schedule+0x50/0xe0 [ 368.128926][ T932] schedule_preempt_disabled+0x18/0x24 [ 368.134229][ T932] __mutex_lock.constprop.0+0x1d4/0x5dc [ 368.139617][ T932] __mutex_lock_slowpath+0x1c/0x30 [ 368.144573][ T932] mutex_lock+0x50/0x60 [ 368.148579][ T932] perf_pmu_migrate_context+0x84/0x2b0 [ 368.153884][ T932] hisi_pcie_pmu_offline_cpu+0x90/0xe0 [hisi_pcie_pmu] [ 368.160579][ T932] cpuhp_invoke_callback+0x2a0/0x650 [ 368.165707][ T932] cpuhp_thread_fun+0xe4/0x190 [ 368.170316][ T932] smpboot_thread_fn+0x15c/0x1a0 [ 368.175099][ T932] kthread+0x108/0x13c [ 368.179012][ T932] ret_from_fork+0x10/0x18
...
Use function cpumask_any_but() to find one correct active cpu to fixes this issue.
--- drivers/perf/hisilicon/hisi_pcie_pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/perf/hisilicon/hisi_pcie_pmu.c +1 -1
@@ -683,7 +683,7 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) pcie_pmu->on_cpu =-1 ;/* Choose a new CPU from all online cpus. */ - target =cpumask_first (cpu_online_mask); + target =cpumask_any_but (cpu_online_mask, cpu);if (target >= nr_cpu_ids) {pci_err (pcie_pmu->pdev,"There is no CPU to set\n" );return 0 ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 68/800 perf: arm_cspmu: Set irq affinitiy only if overflow interrupt is used
In reply to Greg Kroah-HartmanFrom: Ilkka Koskinen <[email protected]>
[ Upstream commit 225d757012e0afa673d8c862e6fb39ed2f429b4d ]
Don't try to set irq affinity if PMU doesn't have an overflow interrupt.
--- drivers/perf/arm_cspmu/arm_cspmu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/perf/arm_cspmu/arm_cspmu.c +2 -1
@@ -1232,7 +1232,8 @@ static struct platform_driver arm_cspmu_driver = {static void arm_cspmu_set_active_cpu (int cpu,struct arm_cspmu *cspmu) {cpumask_set_cpu (cpu, &cspmu->active_cpu); -WARN_ON (irq_set_affinity (cspmu->irq, &cspmu->active_cpu)); +if (cspmu->irq) +WARN_ON (irq_set_affinity (cspmu->irq, &cspmu->active_cpu)); }static int arm_cspmu_cpu_online (unsigned int cpu,struct hlist_node *node)
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 69/800 perf/arm_cspmu: Fix event attribute type
In reply to Greg Kroah-HartmanFrom: Robin Murphy <[email protected]>
[ Upstream commit 71e0cb32d5fc61468e83ed962379af71bba8237e ]
ARM_CSPMU_EVENT_ATTR() defines a struct perf_pmu_events_attr, so arm_cspmu_sysfs_event_show() should not be interpreting it as struct dev_ext_attribute.
--- drivers/perf/arm_cspmu/arm_cspmu.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/perf/arm_cspmu/arm_cspmu.c +4 -4
@@ -189,10 +189,10 @@ static inline bool use_64b_counter_reg(const struct arm_cspmu *cspmu)ssize_t arm_cspmu_sysfs_event_show (struct device *dev,struct device_attribute *attr,char *buf) { -struct dev_ext_attribute *eattr = - container_of(attr, struct dev_ext_attribute, attr); -return sysfs_emit (buf,"event=0x%llx\n" , - (unsigned long long )eattr->var); +struct perf_pmu_events_attr *pmu_attr; + + pmu_attr =container_of (attr,typeof (*pmu_attr), attr); +return sysfs_emit (buf,"event=0x%llx\n" , pmu_attr->id); }EXPORT_SYMBOL_GPL (arm_cspmu_sysfs_event_show);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 70/800 APEI: GHES: correctly return NULL for ghes_get_devices()
In reply to Greg Kroah-HartmanFrom: Li Yang <[email protected]>
[ Upstream commit 9368aa1882ac7178adcd936cee5f0899dbf76dc4 ]
Since 315bada690e0 ("EDAC: Check for GHES preference in the chipset-specific EDAC drivers"), vendor specific EDAC driver will not probe correctly when CONFIG_ACPI_APEI_GHES is enabled but no GHES device is present. Make ghes_get_devices() return NULL when the GHES device list is empty to fix the problem.
--- drivers/acpi/apei/ghes.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/acpi/apei/ghes.c +2 -0
@@ -1544,6 +1544,8 @@ struct list_head *ghes_get_devices(void)pr_warn_once ("Force-loading ghes_edac on an unsupported platform. You're on your own!\n" ); } + }else if (list_empty (&ghes_devs)) { +return NULL ; }return &ghes_devs;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 71/800 powercap: RAPL: fix invalid initialization for pl4_supported field
In reply to Greg Kroah-HartmanFrom: Sumeet Pawnikar <[email protected]>
[ Upstream commit d05b5e0baf424c8c4b4709ac11f66ab726c8deaf ]
The current initialization of the struct x86_cpu_id via pl4_support_ids[] is partial and wrong. It is initializing "stepping" field with "X86_FEATURE_ANY" instead of "feature" field.
Use X86_MATCH_INTEL_FAM6_MODEL macro instead of initializing each field of the struct x86_cpu_id for pl4_supported list of CPUs. This X86_MATCH_INTEL_FAM6_MODEL macro internally uses another macro X86_MATCH_VENDOR_FAM_MODEL_FEATURE for X86 based CPU matching with appropriate initialized values.
--- drivers/powercap/intel_rapl_msr.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)
drivers/powercap/intel_rapl_msr.c +8 -8
@@ -137,14 +137,14 @@ static int rapl_msr_write_raw(int cpu, struct reg_action *ra)/* List of verified CPUs. */ static const struct x86_cpu_id pl4_support_ids[] = { - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_TIGERLAKE_L ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_ALDERLAKE ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_ALDERLAKE_L ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_ALDERLAKE_N ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_RAPTORLAKE ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_RAPTORLAKE_P ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_METEORLAKE ,X86_FEATURE_ANY }, - {X86_VENDOR_INTEL ,6 ,INTEL_FAM6_METEORLAKE_L ,X86_FEATURE_ANY }, +X86_MATCH_INTEL_FAM6_MODEL (TIGERLAKE_L ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (ALDERLAKE ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (ALDERLAKE_L ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (ALDERLAKE_N ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (RAPTORLAKE ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (RAPTORLAKE_P ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (METEORLAKE ,NULL ), +X86_MATCH_INTEL_FAM6_MODEL (METEORLAKE_L ,NULL ), {} };
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 54/800 btrfs: submit a writeback bio per extent_buffer
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 50b21d7a066f9a702b1d54ca11fc577302e875cb ]
Stop trying to cluster writes of multiple extent_buffers into a single bio. There is no need for that as the blk_plug mechanism used all the way up in writeback_inodes_wb gives us the same I/O pattern even with multiple bios. Removing the clustering simplifies lock_extent_buffer_for_io a lot and will also allow passing the eb as private data to the end I/O handler.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 102 ++++++++++++++++--------------------------- 1 file changed, 37 insertions(+), 65 deletions(-)
fs/btrfs/extent_io.c +37 -65
@@ -1669,41 +1669,24 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)/* * Lock extent buffer status and pages for writeback. * -* May try to flush write bio if we can't get the lock. -* * Return %false if the extent buffer doesn't need to be submitted (e.g. the * extent buffer is not dirty) * Return %true is the extent buffer is submitted to bio. */ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eb, -struct btrfs_bio_ctrl *bio_ctrl) +struct writeback_control *wbc) {struct btrfs_fs_info *fs_info = eb->fs_info; -int i, num_pages; -int flush =0 ;bool ret = false; +int i; -if (!btrfs_try_tree_write_lock (eb)) { -submit_write_bio (bio_ctrl,0 ); - flush =1 ; -btrfs_tree_lock (eb); - } - -if (test_bit (EXTENT_BUFFER_WRITEBACK , &eb->bflags)) { +btrfs_tree_lock (eb); +while (test_bit (EXTENT_BUFFER_WRITEBACK , &eb->bflags)) {btrfs_tree_unlock (eb); -if (bio_ctrl->wbc->sync_mode !=WB_SYNC_ALL ) +if (wbc->sync_mode !=WB_SYNC_ALL )return false; -if (!flush) { -submit_write_bio (bio_ctrl,0 ); - flush =1 ; - } -while (1 ) { -wait_on_extent_buffer_writeback (eb); -btrfs_tree_lock (eb); -if (!test_bit (EXTENT_BUFFER_WRITEBACK , &eb->bflags)) -break ; -btrfs_tree_unlock (eb); - } +wait_on_extent_buffer_writeback (eb); +btrfs_tree_lock (eb); }/*
@@ -1735,19 +1718,8 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eif (!ret || fs_info->nodesize <PAGE_SIZE )return ret; - num_pages =num_extent_pages (eb); -for (i =0 ; i < num_pages; i++) { -struct page *p = eb->pages[i]; - -if (!trylock_page (p)) { -if (!flush) { -submit_write_bio (bio_ctrl,0 ); - flush =1 ; - } -lock_page (p); - } - } - +for (i =0 ; i <num_extent_pages (eb); i++) +lock_page (eb->pages[i]);return ret; }
@@ -1977,11 +1949,16 @@ static void prepare_eb_write(struct extent_buffer *eb)* Page locking is only utilized at minimum to keep the VMM code happy. */ static void write_one_subpage_eb (struct extent_buffer *eb, -struct btrfs_bio_ctrl *bio_ctrl) +struct writeback_control *wbc) {struct btrfs_fs_info *fs_info = eb->fs_info;struct page *page = eb->pages[0 ];bool no_dirty_ebs = false; +struct btrfs_bio_ctrl bio_ctrl = { + .wbc = wbc, + .opf =REQ_OP_WRITE |wbc_to_write_flags (wbc), + .end_io_func = end_bio_subpage_eb_writepage, + };prepare_eb_write (eb);
@@ -1995,40 +1972,43 @@ static void write_one_subpage_eb(struct extent_buffer *eb,if (no_dirty_ebs)clear_page_dirty_for_io (page); - bio_ctrl->end_io_func = end_bio_subpage_eb_writepage; - -submit_extent_page (bio_ctrl, eb->start, page, eb->len, +submit_extent_page (&bio_ctrl, eb->start, page, eb->len, eb->start -page_offset (page));unlock_page (page); +submit_one_bio (&bio_ctrl);/* * Submission finished without problem, if no range of the page is * dirty anymore, we have submitted a page. Update nr_written in wbc. */ if (no_dirty_ebs) - bio_ctrl->wbc->nr_to_write--; + wbc->nr_to_write--; } static noinline_for_stack void write_one_eb(struct extent_buffer *eb, -struct btrfs_bio_ctrl *bio_ctrl) +struct writeback_control *wbc) {u64 disk_bytenr = eb->start;int i, num_pages; +struct btrfs_bio_ctrl bio_ctrl = { + .wbc = wbc, + .opf =REQ_OP_WRITE |wbc_to_write_flags (wbc), + .end_io_func = end_bio_extent_buffer_writepage, + };prepare_eb_write (eb); - bio_ctrl->end_io_func = end_bio_extent_buffer_writepage; - num_pages =num_extent_pages (eb);for (i =0 ; i < num_pages; i++) {struct page *p = eb->pages[i];clear_page_dirty_for_io (p);set_page_writeback (p); -submit_extent_page (bio_ctrl, disk_bytenr, p,PAGE_SIZE ,0 ); +submit_extent_page (&bio_ctrl, disk_bytenr, p,PAGE_SIZE ,0 ); disk_bytenr +=PAGE_SIZE ; - bio_ctrl->wbc->nr_to_write--; + wbc->nr_to_write--;unlock_page (p); } +submit_one_bio (&bio_ctrl); }/*
@@ -2045,7 +2025,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,* Return >=0 for the number of submitted extent buffers. * Return <0 for fatal error. */ -static int submit_eb_subpage (struct page *page,struct btrfs_bio_ctrl *bio_ctrl) +static int submit_eb_subpage (struct page *page,struct writeback_control *wbc) {struct btrfs_fs_info *fs_info =btrfs_sb (page->mapping->host->i_sb);int submitted =0 ;
@@ -2097,8 +2077,8 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)if (!eb)continue ; -if (lock_extent_buffer_for_io (eb, bio_ctrl)) { -write_one_subpage_eb (eb, bio_ctrl); +if (lock_extent_buffer_for_io (eb, wbc)) { +write_one_subpage_eb (eb, wbc); submitted++; }free_extent_buffer (eb);
@@ -2126,7 +2106,7 @@ static int submit_eb_subpage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl)* previous call. * Return <0 for fatal error. */ -static int submit_eb_page (struct page *page,struct btrfs_bio_ctrl *bio_ctrl, +static int submit_eb_page (struct page *page,struct writeback_control *wbc,struct extent_buffer **eb_context) {struct address_space *mapping = page->mapping;
@@ -2138,7 +2118,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,return 0 ;if (btrfs_sb (page->mapping->host->i_sb)->nodesize <PAGE_SIZE ) -return submit_eb_subpage (page, bio_ctrl); +return submit_eb_subpage (page, wbc);spin_lock (&mapping->private_lock);if (!PagePrivate (page)) {
@@ -2171,8 +2151,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,* If for_sync, this hole will be filled with * trasnsaction commit. */ -if (bio_ctrl->wbc->sync_mode ==WB_SYNC_ALL && - !bio_ctrl->wbc->for_sync) +if (wbc->sync_mode ==WB_SYNC_ALL && !wbc->for_sync) ret = -EAGAIN ;else ret =0 ;
@@ -2182,12 +2161,12 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl, *eb_context = eb; -if (!lock_extent_buffer_for_io (eb, bio_ctrl)) { +if (!lock_extent_buffer_for_io (eb, wbc)) {btrfs_revert_meta_write_pointer (cache, eb);if (cache)btrfs_put_block_group (cache);free_extent_buffer (eb); -return ret; +return 0 ; }if (cache) {/*
@@ -2196,7 +2175,7 @@ static int submit_eb_page(struct page *page, struct btrfs_bio_ctrl *bio_ctrl,btrfs_schedule_zone_finish_bg (cache, eb);btrfs_put_block_group (cache); } -write_one_eb (eb, bio_ctrl); +write_one_eb (eb, wbc);free_extent_buffer (eb);return 1 ; }
@@ -2205,11 +2184,6 @@ int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) {struct extent_buffer *eb_context =NULL ; -struct btrfs_bio_ctrl bio_ctrl = { - .wbc = wbc, - .opf =REQ_OP_WRITE |wbc_to_write_flags (wbc), - .extent_locked =0 , - };struct btrfs_fs_info *fs_info =BTRFS_I (mapping->host)->root->fs_info;int ret =0 ;int done =0 ;
@@ -2251,7 +2225,7 @@ int btree_write_cache_pages(struct address_space *mapping,for (i =0 ; i < nr_folios; i++) {struct folio *folio = fbatch.folios[i]; - ret =submit_eb_page (&folio->page, &bio_ctrl, &eb_context); + ret =submit_eb_page (&folio->page, wbc, &eb_context);if (ret ==0 )continue ;if (ret <0 ) {
@@ -2312,8 +2286,6 @@ int btree_write_cache_pages(struct address_space *mapping, ret =0 ;if (!ret &&BTRFS_FS_ERROR (fs_info)) ret = -EROFS ; -submit_write_bio (&bio_ctrl, ret); -btrfs_zoned_meta_io_unlock (fs_info);return ret; }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 72/800 powercap: RAPL: Fix CONFIG_IOSF_MBI dependency
In reply to Greg Kroah-HartmanFrom: Zhang Rui <[email protected]>
[ Upstream commit 4658fe81b3f8afe8adf37734ec5fe595d90415c6 ]
After commit 3382388d7148 ("intel_rapl: abstract RAPL common code"), accessing to IOSF_MBI interface is done in the RAPL common code.
Thus it is the CONFIG_INTEL_RAPL_CORE that has dependency of CONFIG_IOSF_MBI, while CONFIG_INTEL_RAPL_MSR does not.
This problem was not exposed previously because all the previous RAPL common code users, aka, the RAPL MSR and MMIO I/F drivers, have CONFIG_IOSF_MBI selected.
Fix the CONFIG_IOSF_MBI dependency in RAPL code. This also fixes a build time failure when the RAPL TPMI I/F driver is introduced without selecting CONFIG_IOSF_MBI.
x86_64-linux-ld: vmlinux.o: in function `set_floor_freq_atom':
intel_rapl_common.c:(.text+0x2dac9b8): undefined reference to `iosf_mbi_write'
x86_64-linux-ld: intel_rapl_common.c:(.text+0x2daca66): undefined reference to `iosf_mbi_read'
Reference to iosf_mbi.h is also removed from the RAPL MSR I/F driver.
--- drivers/powercap/Kconfig | 4 +++- drivers/powercap/intel_rapl_msr.c | 1 - 2 files changed, 3 insertions(+), 2 deletions(-)
drivers/powercap/Kconfig +3 -1
@@ -18,10 +18,12 @@ if POWERCAP # Client driver configurations go here. config INTEL_RAPL_CORE tristate + depends on PCI + select IOSF_MBI config INTEL_RAPL tristate "Intel RAPL Support via MSR Interface" - depends on X86 && IOSF_MBI + depends on X86 && PCI select INTEL_RAPL_CORE help This enables support for the Intel Running Average Power Limit (RAPL)
drivers/powercap/intel_rapl_msr.c +0 -1
@@ -22,7 +22,6 @@#include <linux/processor.h> #include <linux/platform_device.h> -#include <asm/iosf_mbi.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h>
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 73/800 PM: domains: Move the verification of in-params from genpd_add_device()
In reply to Greg Kroah-HartmanFrom: Ulf Hansson <[email protected]>
[ Upstream commit 4384a70c8813e8573d1841fd94eee873f80a7e1a ]
Commit f38d1a6d0025 ("PM: domains: Allocate governor data dynamically based on a genpd governor") started to use the in-parameters in genpd_add_device(), without first doing a verification of them.
This isn't really a big problem, as most callers do a verification already.
Therefore, let's drop the verification from genpd_add_device() and make sure all the callers take care of it instead.
--- drivers/base/power/domain.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/base/power/domain.c +6 -3
@@ -1632,9 +1632,6 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,dev_dbg (dev,"%s()\n" , __func__); -if (IS_ERR_OR_NULL (genpd) ||IS_ERR_OR_NULL (dev)) -return -EINVAL ; - gpd_data =genpd_alloc_dev_data (dev, gd);if (IS_ERR (gpd_data))return PTR_ERR (gpd_data);
@@ -1676,6 +1673,9 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) {int ret; +if (!genpd || !dev) +return -EINVAL ; +mutex_lock (&gpd_list_lock); ret =genpd_add_device (genpd, dev, dev);mutex_unlock (&gpd_list_lock);
@@ -2523,6 +2523,9 @@ int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev)struct generic_pm_domain *genpd;int ret; +if (!dev) +return -EINVAL ; +mutex_lock (&gpd_list_lock); genpd =genpd_get_from_provider (genpdspec);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 74/800 ARM: 9303/1: kprobes: avoid missing-declaration warnings
In reply to Greg Kroah-HartmanFrom: Arnd Bergmann <[email protected]>
[ Upstream commit 1b9c3ddcec6a55e15d3e38e7405e2d078db02020 ]
checker_stack_use_t32strd() and kprobe_handler() can be made static since they are not used from other files, while coverage_start_registers() and __kprobes_test_case() are used from assembler code, and just need a declaration to avoid a warning with the global definition.
arch/arm/probes/kprobes/checkers-common.c:43:18: error: no previous prototype for 'checker_stack_use_t32strd' arch/arm/probes/kprobes/core.c:236:16: error: no previous prototype for 'kprobe_handler' arch/arm/probes/kprobes/test-core.c:723:10: error: no previous prototype for 'coverage_start_registers' arch/arm/probes/kprobes/test-core.c:918:14: error: no previous prototype for '__kprobes_test_case_start' arch/arm/probes/kprobes/test-core.c:952:14: error: no previous prototype for '__kprobes_test_case_end_16' arch/arm/probes/kprobes/test-core.c:967:14: error: no previous prototype for '__kprobes_test_case_end_32'
--- arch/arm/probes/kprobes/checkers-common.c | 2 +- arch/arm/probes/kprobes/core.c | 2 +- arch/arm/probes/kprobes/opt-arm.c | 2 -- arch/arm/probes/kprobes/test-core.c | 2 +- arch/arm/probes/kprobes/test-core.h | 4 ++++ 5 files changed, 7 insertions(+), 5 deletions(-)
arch/arm/probes/kprobes/checkers-common.c +1 -1
@@ -40,7 +40,7 @@ enum probes_insn checker_stack_use_imm_0xx(probes_opcode_t insn,* Different from other insn uses imm8, the real addressing offset of * STRD in T32 encoding should be imm8 * 4. See ARMARM description. */ -enum probes_insn checker_stack_use_t32strd (probes_opcode_t insn, +static enum probes_insn checker_stack_use_t32strd (probes_opcode_t insn,struct arch_probes_insn *asi,const struct decode_header *h) {
arch/arm/probes/kprobes/core.c +1 -1
@@ -233,7 +233,7 @@ singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)* kprobe, and that level is reserved for user kprobe handlers, so we can't * risk encountering a new kprobe in an interrupt handler. */ -void __kprobes kprobe_handler (struct pt_regs *regs) +static void __kprobes kprobe_handler (struct pt_regs *regs) {struct kprobe *p, *cur;struct kprobe_ctlblk *kcb;
arch/arm/probes/kprobes/opt-arm.c +0 -2
@@ -145,8 +145,6 @@ __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) } } -extern void kprobe_handler (struct pt_regs *regs); -static void optimized_callback (struct optimized_kprobe *op,struct pt_regs *regs) {
arch/arm/probes/kprobes/test-core.c +1 -1
@@ -720,7 +720,7 @@ static const char coverage_register_lookup[16] = { [REG_TYPE_NOSPPCX] = COVERAGE_ANY_REG | COVERAGE_SP, }; -unsigned coverage_start_registers (const struct decode_header *h) +static unsigned coverage_start_registers (const struct decode_header *h) {unsigned regs =0 ;int i;
arch/arm/probes/kprobes/test-core.h +4 -0
@@ -454,3 +454,7 @@ void kprobe_thumb32_test_cases(void);#else void kprobe_arm_test_cases (void );#endif + +void __kprobes_test_case_start (void ); +void __kprobes_test_case_end_16 (void ); +void __kprobes_test_case_end_32 (void );
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 75/800 cpufreq: intel_pstate: Fix energy_performance_preference for passive
In reply to Greg Kroah-HartmanFrom: Tero Kristo <[email protected]>
[ Upstream commit 03f44ffb3d5be2fceda375d92c70ab6de4df7081 ]
If the intel_pstate driver is set to passive mode, then writing the same value to the energy_performance_preference sysfs twice will fail. This is caused by the wrong return value used (index of the matched energy_perf_string), instead of the length of the passed in parameter. Fix by forcing the internal return value to zero when the same preference is passed in by user. This same issue is not present when active mode is used for the driver.
--- drivers/cpufreq/intel_pstate.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/cpufreq/intel_pstate.c +2 -0
@@ -824,6 +824,8 @@ static ssize_t store_energy_performance_preference( err =cpufreq_start_governor (policy);if (!ret) ret = err; + }else { + ret =0 ; } }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 76/800 thermal/drivers/qcom/tsens-v0_1: Add support for MSM8226
In reply to Greg Kroah-HartmanFrom: Matti Lehtimäki <[email protected]>
[ Upstream commit 598e1afca47fdbb302ce8d288b06bcc8728efc6c ]
The MSM8226 TSENS IP has 6 thermal sensors in a TSENS v0.1 block. The thermal sensors use non-standard slope values.
Stable-dep-of: 6812d1dfbca9 ("thermal/drivers/qcom/tsens-v0_1: Fix mdm9607 slope values")
--- drivers/thermal/qcom/tsens-v0_1.c | 27 ++++++++++++++++++++++++++- drivers/thermal/qcom/tsens.c | 3 +++ drivers/thermal/qcom/tsens.h | 2 +- 3 files changed, 30 insertions(+), 2 deletions(-)
drivers/thermal/qcom/tsens-v0_1.c +26 -1
@@ -243,6 +243,18 @@ static int calibrate_8974(struct tsens_priv *priv)return 0 ; } +static int __init init_8226 (struct tsens_priv *priv) +{ + priv->sensor[0 ].slope =2901 ; + priv->sensor[1 ].slope =2846 ; + priv->sensor[2 ].slope =3038 ; + priv->sensor[3 ].slope =2955 ; + priv->sensor[4 ].slope =2901 ; + priv->sensor[5 ].slope =2846 ; + +return init_common (priv); +} +static int __init init_8939 (struct tsens_priv *priv) { priv->sensor[0 ].slope =2911 ; priv->sensor[1 ].slope =2789 ;
@@ -258,7 +270,7 @@ static int __init init_8939(struct tsens_priv *priv) {return init_common (priv); } -/* v0.1: 8916, 8939, 8974, 9607 */ +/* v0.1: 8226, 8916, 8939, 8974, 9607 */ static struct tsens_features tsens_v0_1_feat = { .ver_major =VER_0_1 ,
@@ -313,6 +325,19 @@ static const struct tsens_ops ops_v0_1 = { .get_temp = get_temp_common, }; +static const struct tsens_ops ops_8226 = { + .init = init_8226, + .calibrate = tsens_calibrate_common, + .get_temp = get_temp_common, +}; + +struct tsens_plat_data data_8226 = { + .num_sensors =6 , + .ops = &ops_8226, + .feat = &tsens_v0_1_feat, + .fields = tsens_v0_1_regfields, +}; +static const struct tsens_ops ops_8916 = { .init = init_common, .calibrate = calibrate_8916,
drivers/thermal/qcom/tsens.c +3 -0
@@ -1095,6 +1095,9 @@ static const struct of_device_id tsens_table[] = { }, { .compatible = "qcom,mdm9607-tsens", .data = &data_9607, + }, { + .compatible = "qcom,msm8226-tsens", + .data = &data_8226, }, { .compatible = "qcom,msm8916-tsens", .data = &data_8916,
drivers/thermal/qcom/tsens.h +1 -1
@@ -635,7 +635,7 @@ int get_temp_common(const struct tsens_sensor *s, int *temp);extern struct tsens_plat_data data_8960;/* TSENS v0.1 targets */ -extern struct tsens_plat_data data_8916, data_8939, data_8974, data_9607; +extern struct tsens_plat_data data_8226, data_8916, data_8939, data_8974, data_9607;/* TSENS v1 targets */ extern struct tsens_plat_data data_tsens_v1, data_8976, data_8956;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 77/800 thermal/drivers/qcom/tsens-v0_1: Fix mdm9607 slope values
In reply to Greg Kroah-HartmanFrom: Stephan Gerhold <[email protected]>
[ Upstream commit 6812d1dfbca99cd5032683354bf50e0002b2aa02 ]
According to the msm-3.18 vendor kernel from Qualcomm [1], mdm9607 uses a non-standard slope value of 3000 (instead of 3200) for all sensors. Fill it properly similar to the 8939 code added recently.
--- drivers/thermal/qcom/tsens-v0_1.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)
drivers/thermal/qcom/tsens-v0_1.c +17 -1
@@ -270,6 +270,16 @@ static int __init init_8939(struct tsens_priv *priv) {return init_common (priv); } +static int __init init_9607 (struct tsens_priv *priv) +{ +int i; + +for (i =0 ; i < priv->num_sensors; ++i) + priv->sensor[i].slope =3000 ; + +return init_common (priv); +} +/* v0.1: 8226, 8916, 8939, 8974, 9607 */ static struct tsens_features tsens_v0_1_feat = {
@@ -381,9 +391,15 @@ struct tsens_plat_data data_8974 = { .fields = tsens_v0_1_regfields, }; +static const struct tsens_ops ops_9607 = { + .init = init_9607, + .calibrate = tsens_calibrate_common, + .get_temp = get_temp_common, +}; +struct tsens_plat_data data_9607 = { .num_sensors =5 , - .ops = &ops_v0_1, + .ops = &ops_9607, .feat = &tsens_v0_1_feat, .fields = tsens_v0_1_regfields, };
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 78/800 thermal/drivers/qcom/tsens-v0_1: Add mdm9607 correction offsets
In reply to Greg Kroah-HartmanFrom: Stephan Gerhold <[email protected]>
[ Upstream commit b6f739da0070c36655118618a173a59fa14c7adc ]
According to the msm-3.18 vendor kernel from Qualcomm, mdm9607 needs "correction factors" to adjust for additional offsets observed after the factory calibration values in the fuses [1, 2].
The fixed offsets should be applied unless there is a special calibration mode value that indicates that no offsets are needed [3].
Note that the new calibration mode values are called differently in this patch compared to the vendor kernel:
- TSENS_TWO_POINT_CALIB_N_WA -> ONE_PT_CALIB2_NO_OFFSET
- TSENS_TWO_POINT_CALIB_N_OFFSET_WA -> TWO_PT_CALIB_NO_OFFSET
This is because close inspection of the calibration function [3] reveals that TSENS_TWO_POINT_CALIB_N_WA is actually a "one point" calibration because the if statements skip all "point2" related code for it.
[1]: https://git.codelinaro.org/clo/la/kernel/msm-3.18/-/commit/d9d2db1b82bf3f72f5de0803d55e6849eb5b671e
[2]: https://git.codelinaro.org/clo/la/kernel/msm-3.18/-/commit/d75aef53a760e8ff7bac54049d00c8b2ee1b193e
[3]: https://git.codelinaro.org/clo/la/kernel/msm-3.18/-/blob/LE.UM.4.3.2.r1-04200-9x07/drivers/thermal/msm-tsens.c#L2987-3136
--- drivers/thermal/qcom/tsens-v0_1.c | 11 +++++++++++ drivers/thermal/qcom/tsens.c | 16 +++++++++++++++- drivers/thermal/qcom/tsens.h | 4 ++++ 3 files changed, 30 insertions(+), 1 deletion(-)
drivers/thermal/qcom/tsens-v0_1.c +11 -0
@@ -277,6 +277,17 @@ static int __init init_9607(struct tsens_priv *priv)for (i =0 ; i < priv->num_sensors; ++i) priv->sensor[i].slope =3000 ; + priv->sensor[0 ].p1_calib_offset =1 ; + priv->sensor[0 ].p2_calib_offset =1 ; + priv->sensor[1 ].p1_calib_offset =-4 ; + priv->sensor[1 ].p2_calib_offset =-2 ; + priv->sensor[2 ].p1_calib_offset =4 ; + priv->sensor[2 ].p2_calib_offset =8 ; + priv->sensor[3 ].p1_calib_offset =-3 ; + priv->sensor[3 ].p2_calib_offset =-5 ; + priv->sensor[4 ].p1_calib_offset =-4 ; + priv->sensor[4 ].p2_calib_offset =-4 ; +return init_common (priv); }
drivers/thermal/qcom/tsens.c +15 -1
@@ -134,10 +134,12 @@ int tsens_read_calibration(struct tsens_priv *priv, int shift, u32 *p1, u32 *p2, p1[i] = p1[i] + (base1 << shift);break ;case TWO_PT_CALIB : +case TWO_PT_CALIB_NO_OFFSET :for (i =0 ; i < priv->num_sensors; i++) p2[i] = (p2[i] + base2) << shift; fallthrough;case ONE_PT_CALIB2 : +case ONE_PT_CALIB2_NO_OFFSET :for (i =0 ; i < priv->num_sensors; i++) p1[i] = (p1[i] + base1) << shift;break ;
@@ -149,6 +151,18 @@ int tsens_read_calibration(struct tsens_priv *priv, int shift, u32 *p1, u32 *p2, } } +/* Apply calibration offset workaround except for _NO_OFFSET modes */ +switch (mode) { +case TWO_PT_CALIB : +for (i =0 ; i < priv->num_sensors; i++) + p2[i] += priv->sensor[i].p2_calib_offset; + fallthrough; +case ONE_PT_CALIB2 : +for (i =0 ; i < priv->num_sensors; i++) + p1[i] += priv->sensor[i].p1_calib_offset; +break ; + } +return mode; }
@@ -254,7 +268,7 @@ void compute_intercept_slope(struct tsens_priv *priv, u32 *p1,if (!priv->sensor[i].slope) priv->sensor[i].slope =SLOPE_DEFAULT ; -if (mode ==TWO_PT_CALIB ) { +if (mode ==TWO_PT_CALIB || mode ==TWO_PT_CALIB_NO_OFFSET ) {/* * slope (m) = adc_code2 - adc_code1 (y2 - y1)/ * temp_120_degc - temp_30_degc (x2 - x1)
drivers/thermal/qcom/tsens.h +4 -0
@@ -10,6 +10,8 @@#define ONE_PT_CALIB 0x1#define ONE_PT_CALIB2 0x2#define TWO_PT_CALIB 0x3 +#define ONE_PT_CALIB2_NO_OFFSET 0x6 +#define TWO_PT_CALIB_NO_OFFSET 0x7#define CAL_DEGC_PT1 30#define CAL_DEGC_PT2 120#define SLOPE_FACTOR 1000
@@ -57,6 +59,8 @@ struct tsens_sensor {unsigned int hw_id;int slope;u32 status; +int p1_calib_offset; +int p2_calib_offset; };/**
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 79/800 thermal/drivers/sun8i: Fix some error handling paths in sun8i_ths_probe()
In reply to Greg Kroah-HartmanFrom: Christophe JAILLET <[email protected]>
[ Upstream commit 89382022b370dfd34eaae9c863baa123fcd4d132 ]
Should an error occur after calling sun8i_ths_resource_init() in the probe function, some resources need to be released, as already done in the .remove() function.
Switch to the devm_clk_get_enabled() helper and add a new devm_action to turn sun8i_ths_resource_init() into a fully managed function.
Move the place where reset_control_deassert() is called so that the recommended order of reset release/clock enable steps is kept. A64 manual states that:
3.3.6.4. Gating and reset Make sure that the reset signal has been released before the release of module clock gating;
This fixes the issue and removes some LoC at the same time.
--- drivers/thermal/sun8i_thermal.c | 55 +++++++++++---------------------- 1 file changed, 18 insertions(+), 37 deletions(-)
drivers/thermal/sun8i_thermal.c +18 -37
@@ -319,6 +319,11 @@ static int sun8i_ths_calibrate(struct ths_device *tmdev)return ret; } +static void sun8i_ths_reset_control_assert (void *data) +{ +reset_control_assert (data); +} +static int sun8i_ths_resource_init (struct ths_device *tmdev) {struct device *dev = tmdev->dev;
@@ -339,47 +344,35 @@ static int sun8i_ths_resource_init(struct ths_device *tmdev)if (IS_ERR (tmdev->reset))return PTR_ERR (tmdev->reset); - tmdev->bus_clk =devm_clk_get (&pdev->dev,"bus" ); + ret =reset_control_deassert (tmdev->reset); +if (ret) +return ret; + + ret =devm_add_action_or_reset (dev, sun8i_ths_reset_control_assert, + tmdev->reset); +if (ret) +return ret; + + tmdev->bus_clk =devm_clk_get_enabled (&pdev->dev,"bus" );if (IS_ERR (tmdev->bus_clk))return PTR_ERR (tmdev->bus_clk); }if (tmdev->chip->has_mod_clk) { - tmdev->mod_clk =devm_clk_get (&pdev->dev,"mod" ); + tmdev->mod_clk =devm_clk_get_enabled (&pdev->dev,"mod" );if (IS_ERR (tmdev->mod_clk))return PTR_ERR (tmdev->mod_clk); } - ret =reset_control_deassert (tmdev->reset); -if (ret) -return ret; - - ret =clk_prepare_enable (tmdev->bus_clk); -if (ret) - goto assert_reset; - ret =clk_set_rate (tmdev->mod_clk,24000000 );if (ret) - goto bus_disable; - - ret =clk_prepare_enable (tmdev->mod_clk); -if (ret) - goto bus_disable; +return ret; ret =sun8i_ths_calibrate (tmdev);if (ret) - goto mod_disable; +return ret;return 0 ; - -mod_disable: -clk_disable_unprepare (tmdev->mod_clk); -bus_disable: -clk_disable_unprepare (tmdev->bus_clk); -assert_reset: -reset_control_assert (tmdev->reset); - -return ret; }static int sun8i_h3_thermal_init (struct ths_device *tmdev)
@@ -530,17 +523,6 @@ static int sun8i_ths_probe(struct platform_device *pdev)return 0 ; } -static int sun8i_ths_remove (struct platform_device *pdev) -{ -struct ths_device *tmdev =platform_get_drvdata (pdev); - -clk_disable_unprepare (tmdev->mod_clk); -clk_disable_unprepare (tmdev->bus_clk); -reset_control_assert (tmdev->reset); - -return 0 ; -} -static const struct ths_thermal_chip sun8i_a83t_ths = { .sensor_num =3 , .scale =705 ,
@@ -642,7 +624,6 @@ MODULE_DEVICE_TABLE(of, of_ths_match);static struct platform_driver ths_driver = { .probe = sun8i_ths_probe, - .remove = sun8i_ths_remove, .driver = { .name ="sun8i-thermal" , .of_match_table = of_ths_match,
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 80/800 thermal/drivers/qoriq: Only enable supported sensors
In reply to Greg Kroah-HartmanFrom: Peng Fan <[email protected]>
[ Upstream commit 9301575df2509ecf8bd66f601046afaff606b1d5 ]
There are MAX 16 sensors, but not all of them supported. Such as i.MX8MQ, there are only 3 sensors. Enabling all 16 sensors will touch reserved bits from i.MX8MQ reference mannual, and TMU will stuck, temperature will not update anymore.
--- drivers/thermal/qoriq_thermal.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-)
drivers/thermal/qoriq_thermal.c +19 -11
@@ -31,7 +31,6 @@#define TMR_DISABLE 0x0#define TMR_ME 0x80000000#define TMR_ALPF 0x0c000000 -#define TMR_MSITE_ALL GENMASK(15, 0)#define REGS_TMTMIR 0x008/* Temperature measurement interval Register */ #define TMTMIR_DEFAULT 0x0000000f
@@ -105,6 +104,11 @@ static int tmu_get_temp(struct thermal_zone_device *tz, int *temp)* within sensor range. TEMP is an 9 bit value representing * temperature in KelVin. */ + +regmap_read (qdata->regmap,REGS_TMR , &val); +if (!(val &TMR_ME )) +return -EAGAIN ; + if (regmap_read_poll_timeout(qdata->regmap, REGS_TRITSR(qsensor->id), val,
@@ -128,15 +132,7 @@ static const struct thermal_zone_device_ops tmu_tz_ops = {static int qoriq_tmu_register_tmu_zone (struct device *dev,struct qoriq_tmu_data *qdata) { -int id; - -if (qdata->ver ==TMU_VER1 ) { -regmap_write (qdata->regmap,REGS_TMR , -TMR_MSITE_ALL |TMR_ME |TMR_ALPF ); - }else { -regmap_write (qdata->regmap,REGS_V2_TMSR ,TMR_MSITE_ALL ); -regmap_write (qdata->regmap,REGS_TMR ,TMR_ME |TMR_ALPF_V2 ); - } +int id, sites =0 ;for (id =0 ; id <SITES_MAX ; id++) {struct thermal_zone_device *tzd;
@@ -153,14 +149,26 @@ static int qoriq_tmu_register_tmu_zone(struct device *dev,if (ret == -ENODEV )continue ; -regmap_write (qdata->regmap,REGS_TMR ,TMR_DISABLE );return ret; } +if (qdata->ver ==TMU_VER1 ) + sites |=0x1 << (15 - id); +else + sites |=0x1 << id; +if (devm_thermal_add_hwmon_sysfs (dev, tzd))dev_warn (dev,"Failed to add hwmon sysfs attributes\n" ); + } +if (sites) { +if (qdata->ver ==TMU_VER1 ) { +regmap_write (qdata->regmap,REGS_TMR ,TMR_ME |TMR_ALPF | sites); + }else { +regmap_write (qdata->regmap,REGS_V2_TMSR , sites); +regmap_write (qdata->regmap,REGS_TMR ,TMR_ME |TMR_ALPF_V2 ); + } }return 0 ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 81/800 kunit: tool: undo type subscripts for subprocess.Popen
In reply to Greg Kroah-HartmanFrom: Daniel Latypov <[email protected]>
[ Upstream commit e30f65c4b3d671115bf2a9d9ef142285387f2aff ]
Writing subprocess.Popen[str] requires python 3.9+. kunit.py has an assertion that the python version is 3.7+, so we should try to stay backwards compatible.
This conflicts a bit with commit 1da2e6220e11 ("kunit: tool: fix pre-existing mypy --strict errors and update run_checks.py"), since mypy complains like so
Quoted 1 line
kunit_kernel.py:95: error: Missing type parameters for generic type "Popen" [type-arg]
Note: mypy --strict --python-version 3.7 does not work.
We could annotate each file with comments like
`# mypy: disable-error-code="type-arg"
but then we might still get nudged to break back-compat in other files.
This patch adds a mypy.ini file since it seems like the only way to disable specific error codes for all our files.
Note: run_checks.py doesn't need to specify --config_file mypy.ini, but I think being explicit is better, particularly since most kernel devs won't be familiar with how mypy works.
--- tools/testing/kunit/kunit_kernel.py | 6 +++--- tools/testing/kunit/mypy.ini | 6 ++++++ tools/testing/kunit/run_checks.py | 2 +- 3 files changed, 10 insertions(+), 4 deletions(-) create mode 100644 tools/testing/kunit/mypy.ini
tools/testing/kunit/kunit_kernel.py +3 -3
@@ -92,7 +92,7 @@ class LinuxSourceTreeOperations: if stderr: # likely only due to build warnings print(stderr.decode()) - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: raise RuntimeError('not implemented!')
@@ -113,7 +113,7 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: kernel_path = os.path.join(build_dir, self._kernel_path) qemu_command = ['qemu-system-' + self._qemu_arch, '-nodefaults',
@@ -142,7 +142,7 @@ class LinuxSourceTreeOperationsUml(LinuxSourceTreeOperations): kconfig.merge_in_entries(base_kunitconfig) return kconfig - def start(self, params: List[str], build_dir: str) -> subprocess.Popen[str]: + def start(self, params: List[str], build_dir: str) -> subprocess.Popen: """Runs the Linux UML binary. Must be named 'linux'.""" linux_bin = os.path.join(build_dir, 'linux') params.extend(['mem=1G', 'console=tty', 'kunit_shutdown=halt'])
tools/testing/kunit/mypy.ini new file +6 -0
@@ -0,0 +1,6 @@ +[mypy] +strict = True + +# E.g. we can't write subprocess.Popen[str] until Python 3.9+. +# But kunit.py tries to support Python 3.7+, so let's disable it. +disable_error_code = type-arg
tools/testing/kunit/run_checks.py +1 -1
@@ -23,7 +23,7 @@ commands: Dict[str, Sequence[str]] = { 'kunit_tool_test.py': ['./kunit_tool_test.py'], 'kunit smoke test': ['./kunit.py', 'run', '--kunitconfig=lib/kunit', '--build_dir=kunit_run_checks'], 'pytype': ['/bin/sh', '-c', 'pytype *.py'], - 'mypy': ['mypy', '--strict', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], + 'mypy': ['mypy', '--config-file', 'mypy.ini', '--exclude', '_test.py$', '--exclude', 'qemu_configs/', '.'], } # The user might not have mypy or pytype installed, skip them if so.
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 55/800 btrfs: fix range_end calculation in extent_write_locked_range
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 36614a3beba33a05ad78d4dcb9aa1d00e8a7d01f ]
The range_end field in struct writeback_control is inclusive, just like the end parameter passed to extent_write_locked_range. Not doing this could cause extra writeout, which is harmless but suboptimal.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/btrfs/extent_io.c +1 -1
@@ -2468,7 +2468,7 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)struct writeback_control wbc_writepages = { .sync_mode =WB_SYNC_ALL , .range_start = start, - .range_end = end +1 , + .range_end = end, .no_cgroup_owner =1 , };struct btrfs_bio_ctrl bio_ctrl = {
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 56/800 btrfs: dont fail writeback when allocating the compression context fails
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 973fb26e81a9f59dfe45b079a698c0e238f7bf69 ]
If cow_file_range_async fails to allocate the asynchronous writeback context, it currently returns an error and entirely fails the writeback. This is not a good idea as a writeback failure is a non-temporary error condition that will make the file system unusable. Just fall back to synchronous uncompressed writeback instead. This requires us to delay setting the BTRFS_INODE_HAS_ASYNC_EXTENT flag until we've committed to the async writeback.
The compression checks INODE_NOCOMPRESS and FORCE_COMPRESS are moved from cow_file_range_async to the preceding checks btrfs_run_delalloc_range().
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/inode.c | 74 ++++++++++++++++++------------------------------ 1 file changed, 28 insertions(+), 46 deletions(-)
fs/btrfs/inode.c +28 -46
@@ -1521,58 +1521,36 @@ static noinline void async_cow_free(struct btrfs_work *work)kvfree (async_cow); } -static int cow_file_range_async (struct btrfs_inode *inode, -struct writeback_control *wbc, -struct page *locked_page, -u64 start,u64 end,int *page_started, -unsigned long *nr_written) +static bool cow_file_range_async (struct btrfs_inode *inode, +struct writeback_control *wbc, +struct page *locked_page, +u64 start,u64 end,int *page_started, +unsigned long *nr_written) {struct btrfs_fs_info *fs_info = inode->root->fs_info;struct cgroup_subsys_state *blkcg_css =wbc_blkcg_css (wbc);struct async_cow *ctx;struct async_chunk *async_chunk;unsigned long nr_pages; -u64 cur_end;u64 num_chunks =DIV_ROUND_UP (end - start,SZ_512K );int i; -bool should_compress;unsigned nofs_flag;const blk_opf_t write_flags =wbc_to_write_flags (wbc); -unlock_extent (&inode->io_tree, start, end,NULL ); - -if (inode->flags &BTRFS_INODE_NOCOMPRESS && - !btrfs_test_opt (fs_info,FORCE_COMPRESS )) { - num_chunks =1 ; - should_compress = false; - }else { - should_compress = true; - } - nofs_flag =memalloc_nofs_save (); ctx =kvmalloc (struct_size (ctx, chunks, num_chunks),GFP_KERNEL );memalloc_nofs_restore (nofs_flag); +if (!ctx) +return false; -if (!ctx) { -unsigned clear_bits =EXTENT_LOCKED |EXTENT_DELALLOC | -EXTENT_DELALLOC_NEW |EXTENT_DEFRAG | -EXTENT_DO_ACCOUNTING ; -unsigned long page_ops =PAGE_UNLOCK |PAGE_START_WRITEBACK | -PAGE_END_WRITEBACK |PAGE_SET_ERROR ; - -extent_clear_unlock_delalloc (inode, start, end, locked_page, - clear_bits, page_ops); -return -ENOMEM ; - } +unlock_extent (&inode->io_tree, start, end,NULL ); +set_bit (BTRFS_INODE_HAS_ASYNC_EXTENT , &inode->runtime_flags); async_chunk = ctx->chunks;atomic_set (&ctx->num_chunks, num_chunks);for (i =0 ; i < num_chunks; i++) { -if (should_compress) - cur_end =min (end, start +SZ_512K -1 ); -else - cur_end = end; +u64 cur_end =min (end, start +SZ_512K -1 );/* * igrab is called higher up in the call chain, take only the
@@ -1633,7 +1611,7 @@ static int cow_file_range_async(struct btrfs_inode *inode, start = cur_end +1 ; } *page_started =1 ; -return 0 ; +return true; } static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
@@ -2214,7 +2192,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page u64 start, u64 end, int *page_started, unsigned long *nr_written, struct writeback_control *wbc) { - int ret; + int ret = 0;const bool zoned =btrfs_is_zoned (inode->root->fs_info);/*
@@ -2235,19 +2213,23 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_pageASSERT (!zoned ||btrfs_is_data_reloc_root (inode->root)); ret =run_delalloc_nocow (inode, locked_page, start, end, page_started, nr_written); - }else if (!btrfs_inode_can_compress (inode) || - !inode_need_compress (inode, start, end)) { -if (zoned) - ret =run_delalloc_zoned (inode, locked_page, start, end, - page_started, nr_written); -else - ret =cow_file_range (inode, locked_page, start, end, - page_started, nr_written,1 ,NULL ); - }else { -set_bit (BTRFS_INODE_HAS_ASYNC_EXTENT , &inode->runtime_flags); - ret =cow_file_range_async (inode, wbc, locked_page, start, end, - page_started, nr_written); + goto out; } + +if (btrfs_inode_can_compress (inode) && +inode_need_compress (inode, start, end) && +cow_file_range_async (inode, wbc, locked_page, start, + end, page_started, nr_written)) + goto out; + +if (zoned) + ret =run_delalloc_zoned (inode, locked_page, start, end, + page_started, nr_written); +else + ret =cow_file_range (inode, locked_page, start, end, + page_started, nr_written,1 ,NULL ); + +out:ASSERT (ret <=0 );if (ret) btrfs_cleanup_ordered_extents(inode, locked_page, start,
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 57/800 btrfs: only call __extent_writepage_io from extent_write_locked_range
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit eb34dceace983e304e00d4bf711cec0a603959ac ]
__extent_writepage does a lot of things that make no sense for extent_write_locked_range, given that extent_write_locked_range itself is called from __extent_writepage either directly or through a workqueue, and all this work has already been done in the first invocation and the pages haven't been unlocked since. Call __extent_writepage_io directly instead and open code the logic tracked in btrfs_bio_ctrl::extent_locked.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 65 ++++++++++++++++++-------------------------- 1 file changed, 26 insertions(+), 39 deletions(-)
fs/btrfs/extent_io.c +26 -39
@@ -103,12 +103,6 @@ struct btrfs_bio_ctrl {blk_opf_t opf;btrfs_bio_end_io_t end_io_func;struct writeback_control *wbc; - -/* -* Tell writepage not to lock the state bits for this range, it still -* does the unlocking. -*/ -bool extent_locked; };static void submit_one_bio (struct btrfs_bio_ctrl *bio_ctrl)
@@ -1550,7 +1544,6 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl {struct folio *folio =page_folio (page);struct inode *inode = page->mapping->host; -struct btrfs_fs_info *fs_info =btrfs_sb (inode->i_sb);const u64 page_start =page_offset (page);const u64 page_end = page_start +PAGE_SIZE -1 ;int ret;
@@ -1583,13 +1576,11 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl goto done; } -if (!bio_ctrl->extent_locked) { - ret =writepage_delalloc (BTRFS_I (inode), page, bio_ctrl->wbc); -if (ret ==1 ) -return 0 ; -if (ret) - goto done; - } + ret =writepage_delalloc (BTRFS_I (inode), page, bio_ctrl->wbc); +if (ret ==1 ) +return 0 ; +if (ret) + goto done; ret =__extent_writepage_io (BTRFS_I (inode), page, bio_ctrl, i_size, &nr);if (ret ==1 )
@@ -1634,21 +1625,7 @@ static int __extent_writepage(struct page *page, struct btrfs_bio_ctrl *bio_ctrl*/ if (PageError (page))end_extent_writepage (page, ret, page_start, page_end); -if (bio_ctrl->extent_locked) { -struct writeback_control *wbc = bio_ctrl->wbc; - -/* -* If bio_ctrl->extent_locked, it's from extent_write_locked_range(), -* the page can either be locked by lock_page() or -* process_one_page(). -* Let btrfs_page_unlock_writer() handle both cases. -*/ -ASSERT (wbc); -btrfs_page_unlock_writer (fs_info, page, wbc->range_start, - wbc->range_end +1 - wbc->range_start); - }else { -unlock_page (page); - } +unlock_page (page);ASSERT (ret <=0 );return ret; }
@@ -2461,10 +2438,10 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)int first_error =0 ;int ret =0 ;struct address_space *mapping = inode->i_mapping; -struct page *page; +struct btrfs_fs_info *fs_info =btrfs_sb (inode->i_sb); +const u32 sectorsize = fs_info->sectorsize; +loff_t i_size =i_size_read (inode);u64 cur = start; -unsigned long nr_pages; -const u32 sectorsize =btrfs_sb (inode->i_sb)->sectorsize;struct writeback_control wbc_writepages = { .sync_mode =WB_SYNC_ALL , .range_start = start,
@@ -2476,17 +2453,15 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)/* We're called from an async helper function */ .opf = REQ_OP_WRITE | REQ_BTRFS_CGROUP_PUNT | wbc_to_write_flags(&wbc_writepages), - .extent_locked = 1, };ASSERT (IS_ALIGNED (start, sectorsize) &&IS_ALIGNED (end +1 , sectorsize)); - nr_pages = (round_up (end,PAGE_SIZE ) -round_down (start,PAGE_SIZE )) >> -PAGE_SHIFT ; - wbc_writepages.nr_to_write = nr_pages *2 ;wbc_attach_fdatawrite_inode (&wbc_writepages, inode);while (cur <= end) {u64 cur_end =min (round_down (cur,PAGE_SIZE ) +PAGE_SIZE -1 , end); +struct page *page; +int nr =0 ; page =find_get_page (mapping, cur >>PAGE_SHIFT );/*
@@ -2497,12 +2472,25 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)ASSERT (PageLocked (page));ASSERT (PageDirty (page));clear_page_dirty_for_io (page); - ret =__extent_writepage (page, &bio_ctrl); -ASSERT (ret <=0 ); + + ret =__extent_writepage_io (BTRFS_I (inode), page, &bio_ctrl, + i_size, &nr); +if (ret ==1 ) + goto next_page; + +/* Make sure the mapping tag for page dirty gets cleared. */ +if (nr ==0 ) { +set_page_writeback (page); +end_page_writeback (page); + } +if (ret) +end_extent_writepage (page, ret, cur, cur_end); +btrfs_page_unlock_writer (fs_info, page, cur, cur_end +1 - cur);if (ret <0 ) { found_error = true; first_error = ret; } +next_page:put_page (page); cur = cur_end +1 ; }
@@ -2523,7 +2511,6 @@ int extent_writepages(struct address_space *mapping,struct btrfs_bio_ctrl bio_ctrl = { .wbc = wbc, .opf =REQ_OP_WRITE |wbc_to_write_flags (wbc), - .extent_locked =0 , };/*
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 58/800 btrfs: dont treat zoned writeback as being from an async helper thread
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit 7027f87108ce3d23ea542e1a9a79056530db4a87 ]
When extent_write_locked_range was originally added, it was only used writing back compressed pages from an async helper thread. But it is now also used for writing back pages on zoned devices, where it is called directly from the ->writepage context. In this case we want to be able to pass on the writeback_control instead of creating a new one, and more importantly want to use all the normal cgroup interaction instead of potentially deferring writeback to another helper.
--- fs/btrfs/extent_io.c | 20 +++++++------------- fs/btrfs/extent_io.h | 3 ++- fs/btrfs/inode.c | 20 +++++++++++++++----- 3 files changed, 24 insertions(+), 19 deletions(-)
fs/btrfs/extent_io.c +7 -13
@@ -2432,7 +2432,8 @@ static int extent_write_cache_pages(struct address_space *mapping,* already been ran (aka, ordered extent inserted) and all pages are still * locked. */ -int extent_write_locked_range (struct inode *inode,u64 start,u64 end) +int extent_write_locked_range (struct inode *inode,u64 start,u64 end, +struct writeback_control *wbc) {bool found_error = false;int first_error =0 ;
@@ -2442,22 +2443,16 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)const u32 sectorsize = fs_info->sectorsize;loff_t i_size =i_size_read (inode);u64 cur = start; -struct writeback_control wbc_writepages = { - .sync_mode =WB_SYNC_ALL , - .range_start = start, - .range_end = end, - .no_cgroup_owner =1 , - };struct btrfs_bio_ctrl bio_ctrl = { - .wbc = &wbc_writepages, -/* We're called from an async helper function */ - .opf =REQ_OP_WRITE |REQ_BTRFS_CGROUP_PUNT | -wbc_to_write_flags (&wbc_writepages), + .wbc = wbc, + .opf =REQ_OP_WRITE |wbc_to_write_flags (wbc), }; +if (wbc->no_cgroup_owner) + bio_ctrl.opf |=REQ_BTRFS_CGROUP_PUNT ; +ASSERT (IS_ALIGNED (start, sectorsize) &&IS_ALIGNED (end +1 , sectorsize)); -wbc_attach_fdatawrite_inode (&wbc_writepages, inode);while (cur <= end) {u64 cur_end =min (round_down (cur,PAGE_SIZE ) +PAGE_SIZE -1 , end);struct page *page;
@@ -2497,7 +2492,6 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)submit_write_bio (&bio_ctrl, found_error ? ret :0 ); -wbc_detach_inode (&wbc_writepages);if (found_error)return first_error;return ret;
fs/btrfs/extent_io.h +2 -1
@@ -179,7 +179,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask);int try_release_extent_buffer (struct page *page);int btrfs_read_folio (struct file *file,struct folio *folio); -int extent_write_locked_range (struct inode *inode,u64 start,u64 end); +int extent_write_locked_range (struct inode *inode,u64 start,u64 end, +struct writeback_control *wbc);int extent_writepages (struct address_space *mapping,struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping,
fs/btrfs/inode.c +15 -5
@@ -934,6 +934,12 @@ static int submit_uncompressed_range(struct btrfs_inode *inode,unsigned long nr_written =0 ;int page_started =0 ;int ret; +struct writeback_control wbc = { + .sync_mode =WB_SYNC_ALL , + .range_start = start, + .range_end = end, + .no_cgroup_owner =1 , + };/* * Call cow_file_range() to run the delalloc range directly, since we
@@ -965,7 +971,10 @@ static int submit_uncompressed_range(struct btrfs_inode *inode, }/* All pages will be unlocked, including @locked_page */ -return extent_write_locked_range (&inode->vfs_inode, start, end); +wbc_attach_fdatawrite_inode (&wbc, &inode->vfs_inode); + ret =extent_write_locked_range (&inode->vfs_inode, start, end, &wbc); +wbc_detach_inode (&wbc); +return ret; } static int submit_one_async_extent(struct btrfs_inode *inode,
@@ -1617,7 +1626,8 @@ static bool cow_file_range_async(struct btrfs_inode *inode, static noinline int run_delalloc_zoned(struct btrfs_inode *inode,struct page *locked_page,u64 start,u64 end,int *page_started, -unsigned long *nr_written) +unsigned long *nr_written, +struct writeback_control *wbc) {u64 done_offset = end;int ret;
@@ -1649,8 +1659,8 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,account_page_redirty (locked_page); } locked_page_done = true; -extent_write_locked_range (&inode->vfs_inode, start, done_offset); - +extent_write_locked_range (&inode->vfs_inode, start, done_offset, + wbc); start = done_offset +1 ; }
@@ -2224,7 +2234,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_pageif (zoned) ret =run_delalloc_zoned (inode, locked_page, start, end, - page_started, nr_written); + page_started, nr_written, wbc);else ret =cow_file_range (inode, locked_page, start, end, page_started, nr_written,1 ,NULL );
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 59/800 btrfs: fix file_offset for REQ_BTRFS_ONE_ORDERED bios that get split
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit c731cd0b6d255e4855a7cac9f276864032ab2387 ]
If a bio gets split, it needs to have a proper file_offset for checksum validation and repair to work properly.
Based on feedback from Josef, commit 852eee62d31a ("btrfs: allow btrfs_submit_bio to split bios") skipped this adjustment for ONE_ORDERED bios. But if we actually ever need to split a ONE_ORDERED read bio, this will lead to a wrong file offset in the repair code. Right now the only user of the file_offset is logging of an error message so this is mostly harmless, but the wrong offset might be more problematic for additional users in the future.
--- fs/btrfs/bio.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
fs/btrfs/bio.c +1 -2
@@ -95,8 +95,7 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,btrfs_bio_init (bbio, fs_info,NULL , orig_bbio); bbio->inode = orig_bbio->inode; bbio->file_offset = orig_bbio->file_offset; -if (!(orig_bbio->bio.bi_opf &REQ_BTRFS_ONE_ORDERED )) - orig_bbio->file_offset += map_length; + orig_bbio->file_offset += map_length;atomic_inc (&orig_bbio->pending_ios);return bbio;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 60/800 blk-mq: dont insert passthrough request into sw queue
In reply to Greg Kroah-HartmanFrom: Ming Lei <[email protected]>
[ Upstream commit 2293cae703cda162684ae966db6b1b4a11b5e88f ]
In case of real io scheduler, q->elevator is set, so blk_mq_run_hw_queue() may just check if scheduler queue has request to dispatch, see __blk_mq_sched_dispatch_requests(). Then IO hang may be caused because all passthorugh requests may stay in sw queue.
And any passthrough request should have been inserted to hctx->dispatch always.
--- block/blk-mq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
block/blk-mq.c +6 -1
@@ -2735,7 +2735,12 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched)percpu_ref_get (&this_hctx->queue->q_usage_counter);/* passthrough requests should never be issued to the I/O scheduler */ -if (this_hctx->queue->elevator && !is_passthrough) { +if (is_passthrough) { +spin_lock (&this_hctx->lock); +list_splice_tail_init (&list, &this_hctx->dispatch); +spin_unlock (&this_hctx->lock); +blk_mq_run_hw_queue (this_hctx, from_sched); + }else if (this_hctx->queue->elevator) { this_hctx->queue->elevator->type->ops.insert_requests (this_hctx, &list,0 );blk_mq_run_hw_queue (this_hctx, from_sched);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 61/800 clocksource/drivers/cadence-ttc: Fix memory leak in ttc_timer_probe
In reply to Greg Kroah-HartmanFrom: Feng Mingxi <[email protected]>
[ Upstream commit 8b5bf64c89c7100c921bd807ba39b2eb003061ab ]
Smatch reports:drivers/clocksource/timer-cadence-ttc.c:529 ttc_timer_probe()
warn: 'timer_baseaddr' from of_iomap() not released on lines: 498,508,516.
timer_baseaddr may have the problem of not being released after use, I replaced it with the devm_of_iomap() function and added the clk_put() function to cleanup the "clk_ce" and "clk_cs".
--- drivers/clocksource/timer-cadence-ttc.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)
drivers/clocksource/timer-cadence-ttc.c +13 -6
@@ -486,10 +486,10 @@ static int __init ttc_timer_probe(struct platform_device *pdev)* and use it. Note that the event timer uses the interrupt and it's the * 2nd TTC hence the irq_of_parse_and_map(,1) */ - timer_baseaddr =of_iomap (timer,0 ); -if (!timer_baseaddr) { + timer_baseaddr =devm_of_iomap (&pdev->dev, timer,0 ,NULL ); +if (IS_ERR (timer_baseaddr)) {pr_err ("ERROR: invalid timer base address\n" ); -return -ENXIO ; +return PTR_ERR (timer_baseaddr); } irq =irq_of_parse_and_map (timer,1 );
@@ -513,20 +513,27 @@ static int __init ttc_timer_probe(struct platform_device *pdev) clk_ce =of_clk_get (timer, clksel);if (IS_ERR (clk_ce)) {pr_err ("ERROR: timer input clock not found\n" ); -return PTR_ERR (clk_ce); + ret =PTR_ERR (clk_ce); + goto put_clk_cs; } ret =ttc_setup_clocksource (clk_cs, timer_baseaddr, timer_width);if (ret) -return ret; + goto put_clk_ce; ret =ttc_setup_clockevent (clk_ce, timer_baseaddr +4 , irq);if (ret) -return ret; + goto put_clk_ce;pr_info ("%pOFn #0 at %p, irq=%d\n" , timer, timer_baseaddr, irq);return 0 ; + +put_clk_ce: +clk_put (clk_ce); +put_clk_cs: +clk_put (clk_cs); +return ret; }static const struct of_device_id ttc_timer_of_match[] = {
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 52/800 btrfs: dont use btrfs_bio_ctrl for extent buffer reading
In reply to Greg Kroah-HartmanFrom: Christoph Hellwig <[email protected]>
[ Upstream commit b78b98e06fb7f9860da5a7c28e1edbaefc2f7be1 ]
The btrfs_bio_ctrl machinery is overkill for reading extent_buffers as we always operate on PAGE_SIZE chunks (or one smaller one for the subpage case) that are contiguous and are guaranteed to fit into a single bio. Replace it with open coded btrfs_bio_alloc, __bio_add_page and btrfs_submit_bio calls in a helper function shared between the subpage and node size >= PAGE_SIZE cases.
Stable-dep-of: 7027f87108ce ("btrfs: don't treat zoned writeback as being from an async helper thread")
--- fs/btrfs/extent_io.c | 99 ++++++++++++++++---------------------------- 1 file changed, 36 insertions(+), 63 deletions(-)
fs/btrfs/extent_io.c +36 -63
@@ -98,22 +98,12 @@ void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info)*/ struct btrfs_bio_ctrl {struct btrfs_bio *bbio; -int mirror_num;enum btrfs_compression_type compress_type;u32 len_to_oe_boundary;blk_opf_t opf;btrfs_bio_end_io_t end_io_func;struct writeback_control *wbc; -/* -* This is for metadata read, to provide the extra needed verification -* info. This has to be provided for submit_one_bio(), as -* submit_one_bio() can submit a bio if it ends at stripe boundary. If -* no such parent_check is provided, the metadata can hit false alert at -* endio time. -*/ -struct btrfs_tree_parent_check *parent_check; -/* * Tell writepage not to lock the state bits for this range, it still * does the unlocking.
@@ -124,7 +114,6 @@ struct btrfs_bio_ctrl {static void submit_one_bio (struct btrfs_bio_ctrl *bio_ctrl) {struct btrfs_bio *bbio = bio_ctrl->bbio; -int mirror_num = bio_ctrl->mirror_num;if (!bbio)return ;
@@ -132,25 +121,14 @@ static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl)/* Caller should ensure the bio has at least some range added */ ASSERT (bbio->bio.bi_iter.bi_size); -if (!is_data_inode (&bbio->inode->vfs_inode)) { -if (btrfs_op (&bbio->bio) !=BTRFS_MAP_WRITE ) { -/* -* For metadata read, we should have the parent_check, -* and copy it to bbio for metadata verification. -*/ -ASSERT (bio_ctrl->parent_check); -memcpy (&bbio->parent_check, - bio_ctrl->parent_check, -sizeof (struct btrfs_tree_parent_check )); - } +if (!is_data_inode (&bbio->inode->vfs_inode)) bbio->bio.bi_opf |=REQ_META ; - }if (btrfs_op (&bbio->bio) ==BTRFS_MAP_READ && bio_ctrl->compress_type !=BTRFS_COMPRESS_NONE ) -btrfs_submit_compressed_read (bbio, mirror_num); +btrfs_submit_compressed_read (bbio,0 );else -btrfs_submit_bio (bbio, mirror_num); +btrfs_submit_bio (bbio,0 );/* The bbio is owned by the end_io handler now */ bio_ctrl->bbio =NULL ;
@@ -4242,6 +4220,36 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb) } } +static void __read_extent_buffer_pages (struct extent_buffer *eb,int mirror_num, +struct btrfs_tree_parent_check *check) +{ +int num_pages =num_extent_pages (eb), i; +struct btrfs_bio *bbio; + +clear_bit (EXTENT_BUFFER_READ_ERR , &eb->bflags); + eb->read_mirror =0 ; +atomic_set (&eb->io_pages, num_pages); +check_buffer_tree_ref (eb); + + bbio =btrfs_bio_alloc (INLINE_EXTENT_BUFFER_PAGES , +REQ_OP_READ |REQ_META , eb->fs_info, + end_bio_extent_readpage,NULL ); + bbio->bio.bi_iter.bi_sector = eb->start >>SECTOR_SHIFT ; + bbio->inode =BTRFS_I (eb->fs_info->btree_inode); + bbio->file_offset = eb->start; +memcpy (&bbio->parent_check, check,sizeof (*check)); +if (eb->fs_info->nodesize <PAGE_SIZE ) { +__bio_add_page (&bbio->bio, eb->pages[0 ], eb->len, + eb->start -page_offset (eb->pages[0 ])); + }else { +for (i =0 ; i < num_pages; i++) { +ClearPageError (eb->pages[i]); +__bio_add_page (&bbio->bio, eb->pages[i],PAGE_SIZE ,0 ); + } + } +btrfs_submit_bio (bbio, mirror_num); +} +static int read_extent_buffer_subpage (struct extent_buffer *eb,int wait,int mirror_num,struct btrfs_tree_parent_check *check)
@@ -4250,11 +4258,6 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,struct extent_io_tree *io_tree;struct page *page = eb->pages[0 ];struct extent_state *cached_state =NULL ; -struct btrfs_bio_ctrl bio_ctrl = { - .opf =REQ_OP_READ , - .mirror_num = mirror_num, - .parent_check = check, - };int ret;ASSERT (!test_bit (EXTENT_BUFFER_UNMAPPED , &eb->bflags));
@@ -4282,18 +4285,10 @@ static int read_extent_buffer_subpage(struct extent_buffer *eb, int wait,return 0 ; } -clear_bit (EXTENT_BUFFER_READ_ERR , &eb->bflags); - eb->read_mirror =0 ; -atomic_set (&eb->io_pages,1 ); -check_buffer_tree_ref (eb); - bio_ctrl.end_io_func = end_bio_extent_readpage; -btrfs_subpage_clear_error (fs_info, page, eb->start, eb->len); -btrfs_subpage_start_reader (fs_info, page, eb->start, eb->len); -submit_extent_page (&bio_ctrl, eb->start, page, eb->len, - eb->start -page_offset (page)); -submit_one_bio (&bio_ctrl); + +__read_extent_buffer_pages (eb, mirror_num, check);if (wait !=WAIT_COMPLETE ) {free_extent_state (cached_state);return 0 ;
@@ -4314,11 +4309,6 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num,int locked_pages =0 ;int all_uptodate =1 ;int num_pages; -struct btrfs_bio_ctrl bio_ctrl = { - .opf =REQ_OP_READ , - .mirror_num = mirror_num, - .parent_check = check, - };if (test_bit (EXTENT_BUFFER_UPTODATE , &eb->bflags))return 0 ;
@@ -4368,24 +4358,7 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, goto unlock_exit; } -clear_bit (EXTENT_BUFFER_READ_ERR , &eb->bflags); - eb->read_mirror =0 ; -atomic_set (&eb->io_pages, num_pages); -/* -* It is possible for release_folio to clear the TREE_REF bit before we -* set io_pages. See check_buffer_tree_ref for a more detailed comment. -*/ -check_buffer_tree_ref (eb); - bio_ctrl.end_io_func = end_bio_extent_readpage; -for (i =0 ; i < num_pages; i++) { - page = eb->pages[i]; - -ClearPageError (page); -submit_extent_page (&bio_ctrl,page_offset (page), page, -PAGE_SIZE ,0 ); - } - -submit_one_bio (&bio_ctrl); +__read_extent_buffer_pages (eb, mirror_num, check);if (wait !=WAIT_COMPLETE )return 0 ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 83/800 rcu-tasks: Stop rcu_tasks_invoke_cbs() from using never-onlined CPUs
In reply to Greg Kroah-HartmanFrom: Paul E. McKenney <[email protected]>
[ Upstream commit 401b0de3ae4fa49d1014c8941e26d9a25f37e7cf ]
The rcu_tasks_invoke_cbs() function relies on queue_work_on() to silently fall back to WORK_CPU_UNBOUND when the specified CPU is offline. However, the queue_work_on() function's silent fallback mechanism relies on that CPU having been online at some time in the past. When queue_work_on() is passed a CPU that has never been online, workqueue lockups ensue, which can be bad for your kernel's general health and well-being.
This commit therefore checks whether a given CPU has ever been online, and, if not substitutes WORK_CPU_UNBOUND in the subsequent call to queue_work_on(). Why not simply omit the queue_work_on() call entirely? Because this function is flooding callback-invocation notifications to all CPUs, and must deal with possibilities that include a sparse cpu_possible_mask.
This commit also moves the setting of the rcu_data structure's ->beenonline field to rcu_cpu_starting(), which executes on the incoming CPU before that CPU has ever enabled interrupts. This ensures that the required workqueues are present. In addition, because the incoming CPU has not yet enabled its interrupts, there cannot yet have been any softirq handlers running on this CPU, which means that the WARN_ON_ONCE(!rdp->beenonline) within the RCU_SOFTIRQ handler cannot have triggered yet.
--- kernel/rcu/rcu.h | 6 ++++++ kernel/rcu/tasks.h | 7 +++++-- kernel/rcu/tree.c | 12 +++++++++++- 3 files changed, 22 insertions(+), 3 deletions(-)
kernel/rcu/rcu.h +6 -0
@@ -642,4 +642,10 @@ void show_rcu_tasks_trace_gp_kthread(void);static inline void show_rcu_tasks_trace_gp_kthread (void ) {}#endif +#ifdef CONFIG_TINY_RCU +static inline bool rcu_cpu_beenfullyonline (int cpu) {return true; } +#else +bool rcu_cpu_beenfullyonline (int cpu); +#endif +#endif /* __LINUX_RCU_H */
kernel/rcu/tasks.h +5 -2
@@ -463,6 +463,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu {int cpu;int cpunext; +int cpuwq;unsigned long flags;int len;struct rcu_head *rhp;
@@ -473,11 +474,13 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu cpunext = cpu *2 +1 ;if (cpunext <smp_load_acquire (&rtp->percpu_dequeue_lim)) { rtpcp_next =per_cpu_ptr (rtp->rtpcpu, cpunext); -queue_work_on (cpunext, system_wq, &rtpcp_next->rtp_work); + cpuwq =rcu_cpu_beenfullyonline (cpunext) ? cpunext :WORK_CPU_UNBOUND ; +queue_work_on (cpuwq, system_wq, &rtpcp_next->rtp_work); cpunext++;if (cpunext <smp_load_acquire (&rtp->percpu_dequeue_lim)) { rtpcp_next =per_cpu_ptr (rtp->rtpcpu, cpunext); -queue_work_on (cpunext, system_wq, &rtpcp_next->rtp_work); + cpuwq =rcu_cpu_beenfullyonline (cpunext) ? cpunext :WORK_CPU_UNBOUND ; +queue_work_on (cpuwq, system_wq, &rtpcp_next->rtp_work); } }
kernel/rcu/tree.c +11 -1
@@ -4283,7 +4283,6 @@ int rcutree_prepare_cpu(unsigned int cpu)*/ rnp = rdp->mynode;raw_spin_lock_rcu_node (rnp);/* irqs already disabled. */ - rdp->beenonline = true;/* We have now been online. */ rdp->gp_seq =READ_ONCE (rnp->gp_seq); rdp->gp_seq_needed = rdp->gp_seq; rdp->cpu_no_qs.b.norm = true;
@@ -4310,6 +4309,16 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoing)rcu_boost_kthread_setaffinity (rdp->mynode, outgoing); } +/* +* Has the specified (known valid) CPU ever been fully online? +*/ +bool rcu_cpu_beenfullyonline (int cpu) +{ +struct rcu_data *rdp =per_cpu_ptr (&rcu_data, cpu); + +return smp_load_acquire (&rdp->beenonline); +} +/* * Near the end of the CPU-online process. Pretty much all services * enabled, and the CPU is now very much alive.
@@ -4413,6 +4422,7 @@ void rcu_cpu_starting(unsigned int cpu)raw_spin_unlock_rcu_node (rnp); }arch_spin_unlock (&rcu_state.ofl_lock); +smp_store_release (&rdp->beenonline, true);smp_mb ();/* Ensure RCU read-side usage follows above initialization. */ }
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 92/800 tools/nolibc: ensure fast64 integer types have 64 bits
In reply to Greg Kroah-HartmanFrom: Thomas Weißschuh <[email protected]>
[ Upstream commit f9bf5944d37b75b8238349d4fb5b7a97bbecfc9d ]
On 32bit platforms size_t is not enough to represent [u]int_fast64_t.
--- tools/include/nolibc/stdint.h | 10 +++++----- tools/testing/selftests/nolibc/nolibc-test.c | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-)
tools/include/nolibc/stdint.h +5 -5
@@ -36,8 +36,8 @@ typedef ssize_t int_fast16_t;typedef size_t uint_fast16_t ;typedef ssize_t int_fast32_t ;typedef size_t uint_fast32_t ; -typedef ssize_t int_fast64_t ; -typedef size_t uint_fast64_t ; +typedef int64_t int_fast64_t ; +typedef uint64_t uint_fast64_t ;typedef int64_t intmax_t ;typedef uint64_t uintmax_t ;
@@ -84,16 +84,16 @@ typedef uint64_t uintmax_t;#define INT_FAST8_MIN INT8_MIN#define INT_FAST16_MIN INTPTR_MIN#define INT_FAST32_MIN INTPTR_MIN -#define INT_FAST64_MIN INTPTR_MIN +#define INT_FAST64_MIN INT64_MIN#define INT_FAST8_MAX INT8_MAX#define INT_FAST16_MAX INTPTR_MAX#define INT_FAST32_MAX INTPTR_MAX -#define INT_FAST64_MAX INTPTR_MAX +#define INT_FAST64_MAX INT64_MAX#define UINT_FAST8_MAX UINT8_MAX#define UINT_FAST16_MAX SIZE_MAX#define UINT_FAST32_MAX SIZE_MAX -#define UINT_FAST64_MAX SIZE_MAX +#define UINT_FAST64_MAX UINT64_MAX#endif /* _NOLIBC_STDINT_H */
tools/testing/selftests/nolibc/nolibc-test.c +3 -3
@@ -639,9 +639,9 @@ int run_stdlib(int min, int max)CASE_TEST (limit_int_fast32_min);EXPECT_EQ (1 ,INT_FAST32_MIN , (int_fast32_t )INTPTR_MIN );break ;CASE_TEST (limit_int_fast32_max);EXPECT_EQ (1 ,INT_FAST32_MAX , (int_fast32_t )INTPTR_MAX );break ;CASE_TEST (limit_uint_fast32_max);EXPECT_EQ (1 ,UINT_FAST32_MAX , (uint_fast32_t )UINTPTR_MAX );break ; -CASE_TEST (limit_int_fast64_min);EXPECT_EQ (1 ,INT_FAST64_MIN , (int_fast64_t )INTPTR_MIN );break ; -CASE_TEST (limit_int_fast64_max);EXPECT_EQ (1 ,INT_FAST64_MAX , (int_fast64_t )INTPTR_MAX );break ; -CASE_TEST (limit_uint_fast64_max);EXPECT_EQ (1 ,UINT_FAST64_MAX , (uint_fast64_t )UINTPTR_MAX );break ; +CASE_TEST (limit_int_fast64_min);EXPECT_EQ (1 ,INT_FAST64_MIN , (int_fast64_t )INT64_MIN );break ; +CASE_TEST (limit_int_fast64_max);EXPECT_EQ (1 ,INT_FAST64_MAX , (int_fast64_t )INT64_MAX );break ; +CASE_TEST (limit_uint_fast64_max);EXPECT_EQ (1 ,UINT_FAST64_MAX , (uint_fast64_t )UINT64_MAX );break ;#if __SIZEOF_LONG__ ==8 CASE_TEST (limit_intptr_min);EXPECT_EQ (1 ,INTPTR_MIN , (intptr_t )0x8000000000000000LL );break ;CASE_TEST (limit_intptr_max);EXPECT_EQ (1 ,INTPTR_MAX , (intptr_t )0x7fffffffffffffffLL );break ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 93/800 kselftest: vDSO: Fix accumulation of uninitialized ret when CLOCK_REALTIME is undefined
In reply to Greg Kroah-HartmanFrom: Colin Ian King <[email protected]>
[ Upstream commit 375b9ff53cb6f9c042817b75f2be0a650626dc4f ]
In the unlikely case that CLOCK_REALTIME is not defined, variable ret is not initialized and further accumulation of return values to ret can leave ret in an undefined state. Fix this by initialized ret to zero and changing the assignment of ret to an accumulation for the CLOCK_REALTIME case.
--- tools/testing/selftests/vDSO/vdso_test_clock_getres.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/vDSO/vdso_test_clock_getres.c +2 -2
@@ -84,12 +84,12 @@ static inline int vdso_test_clock(unsigned int clock_id)int main (int argc,char **argv) { -int ret; +int ret =0 ;#if _POSIX_TIMERS >0 #ifdef CLOCK_REALTIME - ret =vdso_test_clock (CLOCK_REALTIME ); + ret +=vdso_test_clock (CLOCK_REALTIME );#endif #ifdef CLOCK_BOOTTIME
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 94/800 selftests/ftace: Fix KTAP output ordering
In reply to Greg Kroah-HartmanFrom: Mark Brown <[email protected]>
[ Upstream commit 8cd0d8633e2de4e6dd9ddae7980432e726220fdb ]
The KTAP parser I used to test the KTAP output for ftracetest was overly robust and did not notice that the test number and pass/fail result were reversed. Fix this.
--- tools/testing/selftests/ftrace/ftracetest | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/ftrace/ftracetest +1 -1
@@ -301,7 +301,7 @@ ktaptest() { # result comment comment="# $comment" fi - echo $CASENO $result $INSTANCE$CASENAME $comment + echo $result $CASENO $INSTANCE$CASENAME $comment } eval_result() { # sigval
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 95/800 perf/ibs: Fix interface via core pmu events
In reply to Greg Kroah-HartmanFrom: Ravi Bangoria <[email protected]>
[ Upstream commit 2fad201fe38ff9a692acedb1990ece2c52a29f95 ]
Although, IBS pmus can be invoked via their own interface, indirect IBS invocation via core pmu events is also supported with fixed set of events: cpu-cycles:p, r076:p (same as cpu-cycles:p) and r0C1:p (micro-ops) for user convenience.
This indirect IBS invocation is broken since commit 66d258c5b048 ("perf/core: Optimize perf_init_event()"), which added RAW pmu under 'pmu_idr' list and thus if event_init() fails with RAW pmu, it started returning error instead of trying other pmus.
Forward precise events from core pmu to IBS by overwriting 'type' and 'config' in the kernel copy of perf_event_attr. Overwriting will cause perf_init_event() to retry with updated 'type' and 'config', which will automatically forward event to IBS pmu.
Without patch:
$ sudo ./perf record -C 0 -e r076:p -- sleep 1 Error: The r076:p event is not supported.
With patch:
$ sudo ./perf record -C 0 -e r076:p -- sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.341 MB perf.data (37 samples) ]
--- arch/x86/events/amd/core.c | 2 +- arch/x86/events/amd/ibs.c | 53 +++++++++++++++---------------- arch/x86/include/asm/perf_event.h | 2 ++ 3 files changed, 29 insertions(+), 28 deletions(-)
arch/x86/events/amd/core.c +1 -1
@@ -374,7 +374,7 @@ static int amd_pmu_hw_config(struct perf_event *event)/* pass precise event sampling to ibs: */ if (event->attr.precise_ip &&get_ibs_caps ()) -return -ENOENT ; +return forward_event_to_ibs (event);if (has_branch_stack (event) && !x86_pmu.lbr_nr)return -EOPNOTSUPP ;
arch/x86/events/amd/ibs.c +26 -27
80 lines not on this page · raw message
arch/x86/include/asm/perf_event.h +2 -0
@@ -478,8 +478,10 @@ struct pebs_xmm {#ifdef CONFIG_X86_LOCAL_APIC extern u32 get_ibs_caps (void ); +extern int forward_event_to_ibs (struct perf_event *event);#else static inline u32 get_ibs_caps (void ) {return 0 ; } +static inline int forward_event_to_ibs (struct perf_event *event) {return -ENOENT ; }#endif #ifdef CONFIG_PERF_EVENTS
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 96/800 x86/mm: Fix __swp_entry_to_pte() for Xen PV guests
In reply to Greg Kroah-HartmanFrom: Juergen Gross <[email protected]>
[ Upstream commit 0f88130e8a6fd185b0aeb5d8e286083735f2585a ]
Normally __swp_entry_to_pte() is never called with a value translating to a valid PTE. The only known exception is pte_swap_tests(), resulting in a WARN splat in Xen PV guests, as __pte_to_swp_entry() did translate the PFN of the valid PTE to a guest local PFN, while __swp_entry_to_pte() doesn't do the opposite translation.
Fix that by using __pte() in __swp_entry_to_pte() instead of open coding the native variant of it.
For correctness do the similar conversion for __swp_entry_to_pmd().
--- arch/x86/include/asm/pgtable_64.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/include/asm/pgtable_64.h +2 -2
@@ -237,8 +237,8 @@ static inline void native_pgd_clear(pgd_t *pgd)#define __pte_to_swp_entry (pte) ((swp_entry_t) { pte_val((pte)) })#define __pmd_to_swp_entry (pmd) ((swp_entry_t) { pmd_val((pmd)) }) -#define __swp_entry_to_pte (x) ((pte_t) { .pte = (x).val }) -#define __swp_entry_to_pmd (x) ((pmd_t) { .pmd = (x).val }) +#define __swp_entry_to_pte (x) (__pte((x).val)) +#define __swp_entry_to_pmd (x) (__pmd((x).val))extern void cleanup_highmap (void );
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 97/800 reiserfs: Initialize sec->length in reiserfs_security_init().
In reply to Greg Kroah-HartmanFrom: Tetsuo Handa <[email protected]>
[ Upstream commit d031f4e8b493df299123fbb4ec13db870584ed28 ]
syzbot is reporting that sec->length is not initialized.
Since security_inode_init_security() returns 0 when initxattrs is provided but call_int_hook(inode_init_security) returned -EOPNOTSUPP, control will reach to "if (sec->length && ...) {" without initializing sec->length.
--- fs/reiserfs/xattr_security.c | 1 + 1 file changed, 1 insertion(+)
fs/reiserfs/xattr_security.c +1 -0
@@ -67,6 +67,7 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, sec->name =NULL ; sec->value =NULL ; + sec->length =0 ;/* Don't add selinux attributes on xattrs - they'll never get used */ if (IS_PRIVATE (dir))
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 98/800 locking/atomic: arm: fix sync ops
In reply to Greg Kroah-HartmanFrom: Mark Rutland <[email protected]>
[ Upstream commit dda5f312bb09e56e7a1c3e3851f2000eb2e9c879 ]
The sync_*() ops on arch/arm are defined in terms of the regular bitops with no special handling. This is not correct, as UP kernels elide barriers for the fully-ordered operations, and so the required ordering is lost when such UP kernels are run under a hypervsior on an SMP system.
Fix this by defining sync ops with the required barriers.
Note: On 32-bit arm, the sync_*() ops are currently only used by Xen, which requires ARMv7, but the semantics can be implemented for ARMv6+.
--- arch/arm/include/asm/assembler.h | 17 +++++++++++++++++ arch/arm/include/asm/sync_bitops.h | 29 +++++++++++++++++++++++++---- arch/arm/lib/bitops.h | 14 +++++++++++--- arch/arm/lib/testchangebit.S | 4 ++++ arch/arm/lib/testclearbit.S | 4 ++++ arch/arm/lib/testsetbit.S | 4 ++++ 6 files changed, 65 insertions(+), 7 deletions(-)
arch/arm/include/asm/assembler.h +17 -0
@@ -394,6 +394,23 @@ ALT_UP_B(.L0_\@)#endif .endm +/* + * Raw SMP data memory barrier + */ + .macro __smp_dmb mode +#if __LINUX_ARM_ARCH__ >=7 + .ifeqs "\mode","arm" + dmb ish + .else + W(dmb) ish + .endif +#elif __LINUX_ARM_ARCH__ ==6 + mcr p15, 0, r0, c7, c10, 5 @ dmb +#else + .error "Incompatible SMP platform" +#endif + .endm +#if defined(CONFIG_CPU_V7M )/* * setmode is used to assert to be in svc mode during boot. For v7-M
arch/arm/include/asm/sync_bitops.h +25 -4
@@ -14,14 +14,35 @@* ops which are SMP safe even on a UP kernel. */ +/* +* Unordered +*/ +#define sync_set_bit (nr, p) _set_bit(nr, p)#define sync_clear_bit (nr, p) _clear_bit(nr, p)#define sync_change_bit (nr, p) _change_bit(nr, p) -#define sync_test_and_set_bit (nr, p) _test_and_set_bit(nr, p) -#define sync_test_and_clear_bit (nr, p) _test_and_clear_bit(nr, p) -#define sync_test_and_change_bit (nr, p) _test_and_change_bit(nr, p)#define sync_test_bit (nr, addr) test_bit(nr, addr) -#define arch_sync_cmpxchg arch_cmpxchg +/* +* Fully ordered +*/ + +int _sync_test_and_set_bit (int nr,volatile unsigned long * p); +#define sync_test_and_set_bit (nr, p) _sync_test_and_set_bit(nr, p) + +int _sync_test_and_clear_bit (int nr,volatile unsigned long * p); +#define sync_test_and_clear_bit (nr, p) _sync_test_and_clear_bit(nr, p) + +int _sync_test_and_change_bit (int nr,volatile unsigned long * p); +#define sync_test_and_change_bit (nr, p) _sync_test_and_change_bit(nr, p) + +#define arch_sync_cmpxchg (ptr, old, new) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __smp_mb__before_atomic(); \ + __ret = arch_cmpxchg_relaxed((ptr), (old), (new)); \ + __smp_mb__after_atomic(); \ + __ret; \ +})#endif
arch/arm/lib/bitops.h +11 -3
@@ -28,7 +28,7 @@ UNWIND( .fnend ) ENDPROC(\name ) .endm - .macro testop, name, instr, store + .macro __testop, name, instr, store, barrier ENTRY( \name ) UNWIND( .fnstart ) ands ip, r1, #3
@@ -38,7 +38,7 @@ UNWIND( .fnstart ) mov r0, r0, lsr #5 add r1, r1, r0, lsl #2 @ Get word offset mov r3, r2, lsl r3 @ create mask - smp_dmb + \barrier #if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP) .arch_extension mpALT_SMP (W (pldw ) [r1])
@@ -50,13 +50,21 @@ UNWIND( .fnstart ) strex ip, r2, [r1] cmp ip, #0 bne 1b - smp_dmb + \barrier cmp r0, #0 movne r0, #1 2: bx lr UNWIND( .fnend ) ENDPROC(\name ) .endm + + .macro testop, name, instr, store + __testop \name, \instr, \store, smp_dmb + .endm + + .macro sync_testop, name, instr, store + __testop \name, \instr, \store, __smp_dmb + .endm #else .macro bitop, name, instr ENTRY( \name )
arch/arm/lib/testchangebit.S +4 -0
@@ -10,3 +10,7 @@ .text testop _test_and_change_bit, eor, str + +#if __LINUX_ARM_ARCH__ >= 6 +sync_testop _sync_test_and_change_bit, eor, str +#endif
arch/arm/lib/testclearbit.S +4 -0
@@ -10,3 +10,7 @@ .text testop _test_and_clear_bit, bicne, strne + +#if __LINUX_ARM_ARCH__ >= 6 +sync_testop _sync_test_and_clear_bit, bicne, strne +#endif
arch/arm/lib/testsetbit.S +4 -0
@@ -10,3 +10,7 @@ .text testop _test_and_set_bit, orreq, streq + +#if __LINUX_ARM_ARCH__ >= 6 +sync_testop _sync_test_and_set_bit, orreq, streq +#endif
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 99/800 evm: Complete description of evm_inode_setattr()
In reply to Greg Kroah-HartmanFrom: Roberto Sassu <[email protected]>
[ Upstream commit b1de86d4248b273cb12c4cd7d20c08d459519f7d ]
Add the description for missing parameters of evm_inode_setattr() to avoid the warning arising with W=n compile option.
--- security/integrity/evm/evm_main.c | 2 ++ 1 file changed, 2 insertions(+)
security/integrity/evm/evm_main.c +2 -0
@@ -795,7 +795,9 @@ static int evm_attr_change(struct mnt_idmap *idmap,/** * evm_inode_setattr - prevent updating an invalid EVM extended attribute +* @idmap: idmap of the mount * @dentry: pointer to the affected dentry +* @attr: iattr structure containing the new file attributes * * Permit update of file attributes when files have a valid EVM signature, * except in the case of them having an immutable portable signature.
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 100/800 evm: Fix build warnings
In reply to Greg Kroah-HartmanFrom: Roberto Sassu <[email protected]>
[ Upstream commit 996e0a97ebd7b11cb785794e2a83c20c1add9d92 ]
Fix build warnings (function parameters description) for evm_read_protected_xattrs(), evm_set_key() and evm_verifyxattr().
--- security/integrity/evm/evm_crypto.c | 2 +- security/integrity/evm/evm_main.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
security/integrity/evm/evm_crypto.c +1 -1
@@ -40,7 +40,7 @@ static const char evm_hmac[] = "hmac(sha1)";/** * evm_set_key() - set EVM HMAC key from the kernel * @key: pointer to a buffer with the key data -* @size: length of the key data +* @keylen: length of the key data * * This function allows setting the EVM HMAC key from the kernel * without using the "encrypted" key subsystem keys. It can be used
security/integrity/evm/evm_main.c +1 -1
@@ -318,7 +318,6 @@ int evm_protected_xattr_if_enabled(const char *req_xattr_name)/** * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values * @dentry: dentry of the read xattrs -* @inode: inode of the read xattrs * @buffer: buffer xattr names, lengths or values are copied to * @buffer_size: size of buffer * @type: n: names, l: lengths, v: values
@@ -390,6 +389,7 @@ int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer,* @xattr_name: requested xattr * @xattr_value: requested xattr value * @xattr_value_len: requested xattr value length +* @iint: inode integrity metadata * * Calculate the HMAC for the given dentry and verify it against the stored * security.evm xattr. For performance, use the xattr value and length
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 101/800 ima: Fix build warnings
In reply to Greg Kroah-HartmanFrom: Roberto Sassu <[email protected]>
[ Upstream commit 95526d13038c2bbddd567a4d8e39fac42484e182 ]
Fix build warnings (function parameters description) for ima_collect_modsig(), ima_match_policy() and ima_parse_add_rule().
--- security/integrity/ima/ima_modsig.c | 3 +++ security/integrity/ima/ima_policy.c | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-)
security/integrity/ima/ima_modsig.c +3 -0
@@ -89,6 +89,9 @@ int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len,/** * ima_collect_modsig - Calculate the file hash without the appended signature. +* @modsig: parsed module signature +* @buf: data to verify the signature on +* @size: data size * * Since the modsig is part of the file contents, the hash used in its signature * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code
security/integrity/ima/ima_policy.c +2 -1
@@ -721,6 +721,7 @@ static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func)* @secid: LSM secid of the task to be validated * @func: IMA hook identifier * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC) +* @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE) * @pcr: set the pcr to extend * @template_desc: the template that should be used for this rule * @func_data: func specific data, may be NULL
@@ -1915,7 +1916,7 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)/** * ima_parse_add_rule - add a rule to ima_policy_rules -* @rule - ima measurement policy rule +* @rule: ima measurement policy rule * * Avoid locking by allowing just one writer at a time in ima_write_policy() * Returns the length of the rule parsed, an error code on failure
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 84/800 rcutorture: Correct name of use_softirq module parameter
In reply to Greg Kroah-HartmanFrom: Paul E. McKenney <[email protected]>
[ Upstream commit b409afe0268faeb77267f028ea85f2d93438fced ]
The BUSTED-BOOST and TREE03 scenarios specify a mythical tree.use_softirq module parameter, which means a failure to get full test coverage. This commit therefore corrects the name to rcutree.use_softirq.
--- .../testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot | 2 +- tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/rcutorture/configs/rcu/BUSTED-BOOST.boot +1 -1
@@ -5,4 +5,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0
tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot +1 -1
@@ -4,4 +4,4 @@ rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 rcutree.kthread_prio=2 threadirqs -tree.use_softirq=0 +rcutree.use_softirq=0
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 102/800 pstore/ram: Add check for kstrdup
In reply to Greg Kroah-HartmanFrom: Jiasheng Jiang <[email protected]>
[ Upstream commit d97038d5ec2062733c1e016caf9baaf68cf64ea1 ]
Add check for the return value of kstrdup() and return the error if it fails in order to avoid NULL pointer dereference.
--- fs/pstore/ram_core.c | 2 ++ 1 file changed, 2 insertions(+)
fs/pstore/ram_core.c +2 -0
@@ -599,6 +599,8 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,raw_spin_lock_init (&prz->buffer_lock); prz->flags = flags; prz->label =kstrdup (label,GFP_KERNEL ); +if (!prz->label) + goto err; ret =persistent_ram_buffer_map (start, size, prz, memtype);if (ret)
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 103/800 sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
In reply to Greg Kroah-HartmanFrom: Hao Jia <[email protected]>
[ Upstream commit ebb83d84e49b54369b0db67136a5fe1087124dcc ]
After commit 8ad075c2eb1f ("sched: Async unthrottling for cfs bandwidth"), we may update the rq clock multiple times in the loop of __cfsb_csd_unthrottle().
A prior (although less common) instance of this problem exists in unthrottle_offline_cfs_rqs().
Cure both by ensuring update_rq_clock() is called before the loop and setting RQCF_ACT_SKIP during the loop, to supress further updates. The alternative would be pulling update_rq_clock() out of unthrottle_cfs_rq(), but that gives an even bigger mess.
--- kernel/sched/fair.c | 18 ++++++++++++++++++ kernel/sched/sched.h | 22 ++++++++++++++++++++++ 2 files changed, 40 insertions(+)
kernel/sched/fair.c +18 -0
@@ -5576,6 +5576,14 @@ static void __cfsb_csd_unthrottle(void *arg)rq_lock (rq, &rf); +/* +* Iterating over the list can trigger several call to +* update_rq_clock() in unthrottle_cfs_rq(). +* Do it once and skip the potential next ones. +*/ +update_rq_clock (rq); +rq_clock_start_loop_update (rq); +/* * Since we hold rq lock we're safe from concurrent manipulation of * the CSD list. However, this RCU critical section annotates the
@@ -5595,6 +5603,7 @@ static void __cfsb_csd_unthrottle(void *arg)rcu_read_unlock (); +rq_clock_stop_loop_update (rq);rq_unlock (rq, &rf); }
@@ -6115,6 +6124,13 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)lockdep_assert_rq_held (rq); +/* +* The rq clock has already been updated in the +* set_rq_offline(), so we should skip updating +* the rq clock again in unthrottle_cfs_rq(). +*/ +rq_clock_start_loop_update (rq); +rcu_read_lock ();list_for_each_entry_rcu (tg, &task_groups, list) {struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of (rq)];
@@ -6137,6 +6153,8 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) unthrottle_cfs_rq(cfs_rq); }rcu_read_unlock (); + +rq_clock_stop_loop_update (rq); }#else /* CONFIG_CFS_BANDWIDTH */
kernel/sched/sched.h +22 -0
@@ -1546,6 +1546,28 @@ static inline void rq_clock_cancel_skipupdate(struct rq *rq) rq->clock_update_flags &= ~RQCF_REQ_SKIP ; } +/* +* During cpu offlining and rq wide unthrottling, we can trigger +* an update_rq_clock() for several cfs and rt runqueues (Typically +* when using list_for_each_entry_*) +* rq_clock_start_loop_update() can be called after updating the clock +* once and before iterating over the list to prevent multiple update. +* After the iterative traversal, we need to call rq_clock_stop_loop_update() +* to clear RQCF_ACT_SKIP of rq->clock_update_flags. +*/ +static inline void rq_clock_start_loop_update (struct rq *rq) +{ +lockdep_assert_rq_held (rq); +SCHED_WARN_ON (rq->clock_update_flags &RQCF_ACT_SKIP ); + rq->clock_update_flags |=RQCF_ACT_SKIP ; +} + +static inline void rq_clock_stop_loop_update (struct rq *rq) +{ +lockdep_assert_rq_held (rq); + rq->clock_update_flags &= ~RQCF_ACT_SKIP ; +} +struct rq_flags {unsigned long flags;struct pin_cookie cookie;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 104/800 igc: Enable and fix RX hash usage by netstack
In reply to Greg Kroah-HartmanFrom: Jesper Dangaard Brouer <[email protected]>
[ Upstream commit 84214ab4689f962b4bfc47fc9a5838d25ac4274d ]
When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372 ("igc: Add transmit and receive fastpath and interrupt handlers"), the hardware wasn't configured to provide RSS hash, thus it made sense to not enable net_device NETIF_F_RXHASH feature bit.
The NIC hardware was configured to enable RSS hash info in v5.2 via commit 2121c2712f82 ("igc: Add multiple receive queues control supporting"), but forgot to set the NETIF_F_RXHASH feature bit.
The original implementation of igc_rx_hash() didn't extract the associated pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of this patch are about extracting the RSS Type from the hardware and mapping this to enum pkt_hash_types. This was based on Foxville i225 software user manual rev-1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03).
For UDP it's worth noting that RSS (type) hashing have been disabled both for IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP + IGC_MRQC_RSS_FIELD_IPV6_UDP) because hardware RSS doesn't handle fragmented pkts well when enabled (can cause out-of-order). This results in PKT_HASH_TYPE_L3 for UDP packets, and hash value doesn't include UDP port numbers. Not being PKT_HASH_TYPE_L4, have the effect that netstack will do a software based hash calc calling into flow_dissect, but only when code calls skb_get_hash(), which doesn't necessary happen for local delivery.
For QA verification testing I wrote a small bpftrace prog:
[0] https://github.com/xdp-project/xdp-project/blob/master/areas/hints/monitor_skb_hash_on_dev.bt
--- drivers/net/ethernet/intel/igc/igc.h | 28 ++++++++++++++++++++ drivers/net/ethernet/intel/igc/igc_main.c | 31 ++++++++++++++++++++--- 2 files changed, 55 insertions(+), 4 deletions(-)
drivers/net/ethernet/intel/igc/igc.h +28 -0
@@ -13,6 +13,7 @@#include <linux/ptp_clock_kernel.h> #include <linux/timecounter.h> #include <linux/net_tstamp.h> +#include <linux/bitfield.h> #include "igc_hw.h"
@@ -311,6 +312,33 @@ extern char igc_driver_name[];#define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000#define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +/* RX-desc Write-Back format RSS Type's */ +enum igc_rss_type_num { +IGC_RSS_TYPE_NO_HASH =0 , +IGC_RSS_TYPE_HASH_TCP_IPV4 =1 , +IGC_RSS_TYPE_HASH_IPV4 =2 , +IGC_RSS_TYPE_HASH_TCP_IPV6 =3 , +IGC_RSS_TYPE_HASH_IPV6_EX =4 , +IGC_RSS_TYPE_HASH_IPV6 =5 , +IGC_RSS_TYPE_HASH_TCP_IPV6_EX =6 , +IGC_RSS_TYPE_HASH_UDP_IPV4 =7 , +IGC_RSS_TYPE_HASH_UDP_IPV6 =8 , +IGC_RSS_TYPE_HASH_UDP_IPV6_EX =9 , +IGC_RSS_TYPE_MAX =10 , +}; +#define IGC_RSS_TYPE_MAX_TABLE 16 +#define IGC_RSS_TYPE_MASK GENMASK(3,0)/* 4-bits (3:0) = mask 0x0F */ + +/* igc_rss_type - Rx descriptor RSS type field */ +static inline u32 igc_rss_type (const union igc_adv_rx_desc *rx_desc) +{ +/* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved) +* Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info) +* is slightly slower than via u32 (wb.lower.lo_dword.data) +*/ +return le32_get_bits (rx_desc->wb.lower.lo_dword.data,IGC_RSS_TYPE_MASK ); +} +/* Interrupt defines */ #define IGC_START_ITR 648/* ~6000 ints/sec */ #define IGC_4K_ITR 980
drivers/net/ethernet/intel/igc/igc_main.c +27 -4
@@ -1697,14 +1697,36 @@ static void igc_rx_checksum(struct igc_ring *ring, le32_to_cpu(rx_desc->wb.upper.status_error)); } +/* Mapping HW RSS Type to enum pkt_hash_types */ +static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE ] = { + [IGC_RSS_TYPE_NO_HASH ] =PKT_HASH_TYPE_L2 , + [IGC_RSS_TYPE_HASH_TCP_IPV4 ] =PKT_HASH_TYPE_L4 , + [IGC_RSS_TYPE_HASH_IPV4 ] =PKT_HASH_TYPE_L3 , + [IGC_RSS_TYPE_HASH_TCP_IPV6 ] =PKT_HASH_TYPE_L4 , + [IGC_RSS_TYPE_HASH_IPV6_EX ] =PKT_HASH_TYPE_L3 , + [IGC_RSS_TYPE_HASH_IPV6 ] =PKT_HASH_TYPE_L3 , + [IGC_RSS_TYPE_HASH_TCP_IPV6_EX ] =PKT_HASH_TYPE_L4 , + [IGC_RSS_TYPE_HASH_UDP_IPV4 ] =PKT_HASH_TYPE_L4 , + [IGC_RSS_TYPE_HASH_UDP_IPV6 ] =PKT_HASH_TYPE_L4 , + [IGC_RSS_TYPE_HASH_UDP_IPV6_EX ] =PKT_HASH_TYPE_L4 , + [10 ] =PKT_HASH_TYPE_NONE ,/* RSS Type above 9 "Reserved" by HW */ + [11 ] =PKT_HASH_TYPE_NONE ,/* keep array sized for SW bit-mask */ + [12 ] =PKT_HASH_TYPE_NONE ,/* to handle future HW revisons */ + [13 ] =PKT_HASH_TYPE_NONE , + [14 ] =PKT_HASH_TYPE_NONE , + [15 ] =PKT_HASH_TYPE_NONE , +}; +static inline void igc_rx_hash (struct igc_ring *ring,union igc_adv_rx_desc *rx_desc,struct sk_buff *skb) { -if (ring->netdev->features &NETIF_F_RXHASH ) -skb_set_hash (skb, -le32_to_cpu (rx_desc->wb.lower.hi_dword.rss), -PKT_HASH_TYPE_L3 ); +if (ring->netdev->features &NETIF_F_RXHASH ) { +u32 rss_hash =le32_to_cpu (rx_desc->wb.lower.hi_dword.rss); +u32 rss_type =igc_rss_type (rx_desc); + +skb_set_hash (skb, rss_hash, igc_rss_type_table[rss_type]); + } } static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -6561,6 +6583,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->features |=NETIF_F_TSO ; netdev->features |=NETIF_F_TSO6 ; netdev->features |=NETIF_F_TSO_ECN ; + netdev->features |=NETIF_F_RXHASH ; netdev->features |=NETIF_F_RXCSUM ; netdev->features |=NETIF_F_HW_CSUM ; netdev->features |=NETIF_F_SCTP_CRC ;
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 105/800 wifi: ath9k: fix AR9003 mac hardware hang check register offset calculation
In reply to Greg Kroah-HartmanFrom: Peter Seiderer <[email protected]>
[ Upstream commit 3e56c80931c7615250fe4bf83f93b57881969266 ]
Fix ath9k_hw_verify_hang()/ar9003_hw_detect_mac_hang() register offset calculation (do not overflow the shift for the second register/queues above five, use the register layout described in the comments above ath9k_hw_verify_hang() instead).
--- drivers/net/wireless/ath/ath9k/ar9003_hw.c | 27 ++++++++++++++-------- 1 file changed, 18 insertions(+), 9 deletions(-)
drivers/net/wireless/ath/ath9k/ar9003_hw.c +18 -9
@@ -1099,17 +1099,22 @@ static bool ath9k_hw_verify_hang(struct ath_hw *ah, unsigned int queue) {u32 dma_dbg_chain, dma_dbg_complete;u8 dcu_chain_state, dcu_complete_state; +unsigned int dbg_reg, reg_offset;int i; -for (i =0 ; i <NUM_STATUS_READS ; i++) { -if (queue <6 ) - dma_dbg_chain =REG_READ (ah,AR_DMADBG_4 ); -else - dma_dbg_chain =REG_READ (ah,AR_DMADBG_5 ); +if (queue <6 ) { + dbg_reg =AR_DMADBG_4 ; + reg_offset = queue *5 ; + }else { + dbg_reg =AR_DMADBG_5 ; + reg_offset = (queue -6 ) *5 ; + } +for (i =0 ; i <NUM_STATUS_READS ; i++) { + dma_dbg_chain =REG_READ (ah, dbg_reg); dma_dbg_complete =REG_READ (ah,AR_DMADBG_6 ); - dcu_chain_state = (dma_dbg_chain >> (5 * queue)) &0x1f ; + dcu_chain_state = (dma_dbg_chain >> reg_offset) &0x1f ; dcu_complete_state = dma_dbg_complete &0x3 ;if ((dcu_chain_state !=0x6 ) || (dcu_complete_state !=0x1 ))
@@ -1128,6 +1133,7 @@ static bool ar9003_hw_detect_mac_hang(struct ath_hw *ah)u8 dcu_chain_state, dcu_complete_state;bool dcu_wait_frdone = false;unsigned long chk_dcu =0 ; +unsigned int reg_offset;unsigned int i =0 ; dma_dbg_4 =REG_READ (ah,AR_DMADBG_4 );
@@ -1139,12 +1145,15 @@ static bool ar9003_hw_detect_mac_hang(struct ath_hw *ah) goto exit;for (i =0 ; i <ATH9K_NUM_TX_QUEUES ; i++) { -if (i <6 ) +if (i <6 ) { chk_dbg = dma_dbg_4; -else + reg_offset = i *5 ; + }else { chk_dbg = dma_dbg_5; + reg_offset = (i -6 ) *5 ; + } - dcu_chain_state = (chk_dbg >> (5 * i)) &0x1f ; + dcu_chain_state = (chk_dbg >> reg_offset) &0x1f ;if (dcu_chain_state ==0x6 ) { dcu_wait_frdone = true; chk_dcu |=BIT (i);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 106/800 wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx
In reply to Greg Kroah-HartmanFrom: Fedor Pchelkin <[email protected]>
[ Upstream commit f24292e827088bba8de7158501ac25a59b064953 ]
For the reasons also described in commit b383e8abed41 ("wifi: ath9k: avoid uninit memory read in ath9k_htc_rx_msg()"), ath9k_htc_rx_msg() should validate pkt_len before accessing the SKB.
For example, the obtained SKB may have been badly constructed with pkt_len = 8. In this case, the SKB can only contain a valid htc_frame_hdr but after being processed in ath9k_htc_rx_msg() and passed to ath9k_wmi_ctrl_rx() endpoint RX handler, it is expected to have a WMI command header which should be located inside its data payload.
Implement sanity checking inside ath9k_wmi_ctrl_rx(). Otherwise, uninit memory can be referenced.
Tested on Qualcomm Atheros Communications AR9271 802.11n .
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
--- drivers/net/wireless/ath/ath9k/wmi.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/net/wireless/ath/ath9k/wmi.c +4 -0
@@ -221,6 +221,10 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,if (unlikely (wmi->stopped)) goto free_skb; +/* Validate the obtained SKB. */ +if (unlikely (skb->len <sizeof (struct wmi_cmd_hdr ))) + goto free_skb; + hdr = (struct wmi_cmd_hdr *) skb->data; cmd_id =be16_to_cpu (hdr->command_id);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 107/800 libbpf: btf_dump_type_data_check_overflow needs to consider BTF_MEMBER_BITFIELD_SIZE
In reply to Greg Kroah-HartmanFrom: Martin KaFai Lau <[email protected]>
[ Upstream commit c39028b333f3a3a765c5c0b9726b8e38aedf0ba1 ]
The btf_dump/struct_data selftest is failing with:
[...]
test_btf_dump_struct_data:FAIL:unexpected return value dumping fs_context unexpected unexpected return value dumping fs_context: actual -7 != expected 264 [...]
The reason is in btf_dump_type_data_check_overflow(). It does not use BTF_MEMBER_BITFIELD_SIZE from the struct's member (btf_member). Instead, it is using the enum size which is 4. It had been working till the recent commit 4e04143c869c ("fs_context: drop the unused lsm_flags member") removed an integer member which also removed the 4 bytes padding at the end of the fs_context. Missing this 4 bytes padding exposed this bug. In particular, when btf_dump_type_data_check_overflow() reaches the member 'phase', -E2BIG is returned.
The fix is to pass bit_sz to btf_dump_type_data_check_overflow(). In btf_dump_type_data_check_overflow(), it does a different size check when bit_sz is not zero.
The current fs_context:
[3600] ENUM 'fs_context_purpose' encoding=UNSIGNED size=4 vlen=3
'FS_CONTEXT_FOR_MOUNT' val=0 'FS_CONTEXT_FOR_SUBMOUNT' val=1 'FS_CONTEXT_FOR_RECONFIGURE' val=2
[3601] ENUM 'fs_context_phase' encoding=UNSIGNED size=4 vlen=7
'FS_CONTEXT_CREATE_PARAMS' val=0 'FS_CONTEXT_CREATING' val=1 'FS_CONTEXT_AWAITING_MOUNT' val=2 'FS_CONTEXT_AWAITING_RECONF' val=3 'FS_CONTEXT_RECONF_PARAMS' val=4 'FS_CONTEXT_RECONFIGURING' val=5 'FS_CONTEXT_FAILED' val=6
[3602] STRUCT 'fs_context' size=264 vlen=21
'ops' type_id=3603 bits_offset=0 'uapi_mutex' type_id=235 bits_offset=64 'fs_type' type_id=872 bits_offset=1216 'fs_private' type_id=21 bits_offset=1280 'sget_key' type_id=21 bits_offset=1344 'root' type_id=781 bits_offset=1408 'user_ns' type_id=251 bits_offset=1472 'net_ns' type_id=984 bits_offset=1536 'cred' type_id=1785 bits_offset=1600 'log' type_id=3621 bits_offset=1664 'source' type_id=42 bits_offset=1792 'security' type_id=21 bits_offset=1856 's_fs_info' type_id=21 bits_offset=1920 'sb_flags' type_id=20 bits_offset=1984 'sb_flags_mask' type_id=20 bits_offset=2016 's_iflags' type_id=20 bits_offset=2048 'purpose' type_id=3600 bits_offset=2080 bitfield_size=8 'phase' type_id=3601 bits_offset=2088 bitfield_size=8 'need_free' type_id=67 bits_offset=2096 bitfield_size=1 'global' type_id=67 bits_offset=2097 bitfield_size=1 'oldapi' type_id=67 bits_offset=2098 bitfield_size=1
--- tools/lib/bpf/btf_dump.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
tools/lib/bpf/btf_dump.c +19 -3
@@ -2250,9 +2250,25 @@ static int btf_dump_type_data_check_overflow(struct btf_dump *d,const struct btf_type *t, __u32 id, const void *data, - __u8 bits_offset) + __u8 bits_offset, + __u8 bit_sz) { - __s64 size = btf__resolve_size(d->btf, id); + __s64 size; + +if (bit_sz) { +/* bits_offset is at most 7. bit_sz is at most 128. */ +__u8 nr_bytes = (bits_offset + bit_sz +7 ) /8 ; + +/* When bit_sz is non zero, it is called from +* btf_dump_struct_data() where it only cares about +* negative error value. +* Return nr_bytes in success case to make it +* consistent as the regular integer case below. +*/ +return data + nr_bytes > d->typed_dump->data_end ? -E2BIG : nr_bytes; + } + + size =btf__resolve_size (d->btf, id);if (size <0 || size >=INT_MAX ) { pr_warn("unexpected size [%zu] for id [%u]\n",
@@ -2407,7 +2423,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, {int size, err =0 ; - size =btf_dump_type_data_check_overflow (d, t, id, data, bits_offset); + size =btf_dump_type_data_check_overflow (d, t, id, data, bits_offset, bit_sz);if (size <0 )return size; err =btf_dump_type_data_check_zero (d, t, id, data, bits_offset, bit_sz);
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 108/800 bpf: encapsulate precision backtracking bookkeeping
In reply to Greg Kroah-HartmanFrom: Andrii Nakryiko <[email protected]>
[ Upstream commit 407958a0e980b9e1842ab87b5a1040521e1e24e9 ]
Add struct backtrack_state and straightforward API around it to keep track of register and stack masks used and maintained during precision backtracking process. Having this logic separately allow to keep high-level backtracking algorithm cleaner, but also it sets us up to cleanly keep track of register and stack masks per frame, allowing (with some further logic adjustments) to perform precision backpropagation across multiple frames (i.e., subprog calls).
Stable-dep-of: f655badf2a8f ("bpf: fix propagate_precision() logic for inner frames")
--- include/linux/bpf_verifier.h | 14 ++ kernel/bpf/verifier.c | 249 +++++++++++++++++++++++++---------- 2 files changed, 196 insertions(+), 67 deletions(-)
include/linux/bpf_verifier.h +14 -0
@@ -238,6 +238,10 @@ enum bpf_stack_slot_type {#define BPF_REG_SIZE 8/* size of eBPF register in bytes */ +#define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \ + (1 << BPF_REG_3) | (1 << BPF_REG_4) | \ + (1 << BPF_REG_5)) +#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern)#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE)
@@ -541,6 +545,15 @@ struct bpf_subprog_info {bool is_async_cb; }; +struct bpf_verifier_env ; + +struct backtrack_state { +struct bpf_verifier_env *env; +u32 frame; +u32 reg_masks[MAX_CALL_FRAMES ]; +u64 stack_masks[MAX_CALL_FRAMES ]; +}; +/* single container for all structs * one verifier_env per bpf_check() call */
@@ -578,6 +591,7 @@ struct bpf_verifier_env {int *insn_stack;int cur_stack; } cfg; +struct backtrack_state bt;u32 pass_cnt;/* number of times do_check() was called */ u32 subprog_cnt;/* number of instructions analyzed by the verifier */
kernel/bpf/verifier.c +182 -67
445 lines not on this page · raw message
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 109/800 bpf: improve precision backtrack logging
In reply to Greg Kroah-HartmanFrom: Andrii Nakryiko <[email protected]>
[ Upstream commit d9439c21a9e4769bfd83a03ab39056164d44ac31 ]
Add helper to format register and stack masks in more human-readable format. Adjust logging a bit during backtrack propagation and especially during forcing precision fallback logic to make it clearer what's going on (with log_level=2, of course), and also start reporting affected frame depth. This is in preparation for having more than one active frame later when precision propagation between subprog calls is added.
Stable-dep-of: f655badf2a8f ("bpf: fix propagate_precision() logic for inner frames")
--- include/linux/bpf_verifier.h | 13 ++- kernel/bpf/verifier.c | 72 ++++++++++-- .../testing/selftests/bpf/verifier/precise.c | 106 +++++++++--------- 3 files changed, 128 insertions(+), 63 deletions(-)
include/linux/bpf_verifier.h +9 -4
@@ -18,8 +18,11 @@* that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) -/* size of type_str_buf in bpf_verifier. */ -#define TYPE_STR_BUF_LEN 128 +/* size of tmp_str_buf in bpf_verifier. +* we need at least 306 bytes to fit full stack mask representation +* (in the "-8,-16,...,-512" form) +*/ +#define TMP_STR_BUF_LEN 320/* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that
@@ -620,8 +623,10 @@ struct bpf_verifier_env {/* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots;u64 prev_log_pos, prev_insn_print_pos; -/* buffer used in reg_type_str() to generate reg_type string */ -char type_str_buf[TYPE_STR_BUF_LEN ]; +/* buffer used to generate temporary string representations, +* e.g., in reg_type_str() to generate reg_type string +*/ +char tmp_str_buf[TMP_STR_BUF_LEN ]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
kernel/bpf/verifier.c +65 -7
118 lines not on this page · raw message
tools/testing/selftests/bpf/verifier/precise.c +54 -52
130 lines not on this page · raw message
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 110/800 bpf: maintain bitmasks across all active frames in __mark_chain_precision
In reply to Greg Kroah-HartmanFrom: Andrii Nakryiko <[email protected]>
[ Upstream commit 1ef22b6865a73a8aed36d43375fe8c7b30869326 ]
Teach __mark_chain_precision logic to maintain register/stack masks across all active frames when going from child state to parent state. Currently this should be mostly no-op, as precision backtracking usually bails out when encountering subprog entry/exit.
It's not very apparent from the diff due to increased indentation, but the logic remains the same, except everything is done on specific fr frame index. Calls to bt_clear_reg() and bt_clear_slot() are replaced with frame-specific bt_clear_frame_reg() and bt_clear_frame_slot(), where frame index is passed explicitly, instead of using current frame number.
We also adjust logging to emit affected frame number. And we also add better logging of human-readable register and stack slot masks, similar to previous patch.
Stable-dep-of: f655badf2a8f ("bpf: fix propagate_precision() logic for inner frames")
--- kernel/bpf/verifier.c | 100 ++++++++++-------- .../testing/selftests/bpf/verifier/precise.c | 18 ++-- 2 files changed, 62 insertions(+), 56 deletions(-)
kernel/bpf/verifier.c +53 -47
@@ -3694,7 +3694,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int rstruct bpf_func_state *func;struct bpf_reg_state *reg;bool skip_first = true; -int i, err; +int i, fr, err;if (!env->bpf_capable)return 0 ;
@@ -3803,56 +3803,62 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int rif (!st)break ; - func = st->frame[frame]; -bitmap_from_u64 (mask,bt_reg_mask (bt)); -for_each_set_bit (i, mask,32 ) { - reg = &func->regs[i]; -if (reg->type !=SCALAR_VALUE ) { -bt_clear_reg (bt, i); -continue ; +for (fr = bt->frame; fr >=0 ; fr--) { + func = st->frame[fr]; +bitmap_from_u64 (mask,bt_frame_reg_mask (bt, fr)); +for_each_set_bit (i, mask,32 ) { + reg = &func->regs[i]; +if (reg->type !=SCALAR_VALUE ) { +bt_clear_frame_reg (bt, fr, i); +continue ; + } +if (reg->precise) +bt_clear_frame_reg (bt, fr, i); +else + reg->precise = true; } -if (reg->precise) -bt_clear_reg (bt, i); -else - reg->precise = true; - } -bitmap_from_u64 (mask,bt_stack_mask (bt)); -for_each_set_bit (i, mask,64 ) { -if (i >= func->allocated_stack /BPF_REG_SIZE ) { -/* the sequence of instructions: -* 2: (bf) r3 = r10 -* 3: (7b) *(u64 *)(r3 -8) = r0 -* 4: (79) r4 = *(u64 *)(r10 -8) -* doesn't contain jmps. It's backtracked -* as a single block. -* During backtracking insn 3 is not recognized as -* stack access, so at the end of backtracking -* stack slot fp-8 is still marked in stack_mask. -* However the parent state may not have accessed -* fp-8 and it's "unallocated" stack space. -* In such case fallback to conservative. -*/ -mark_all_scalars_precise (env, st); -bt_reset (bt); -return 0 ; - } +bitmap_from_u64 (mask,bt_frame_stack_mask (bt, fr)); +for_each_set_bit (i, mask,64 ) { +if (i >= func->allocated_stack /BPF_REG_SIZE ) { +/* the sequence of instructions: +* 2: (bf) r3 = r10 +* 3: (7b) *(u64 *)(r3 -8) = r0 +* 4: (79) r4 = *(u64 *)(r10 -8) +* doesn't contain jmps. It's backtracked +* as a single block. +* During backtracking insn 3 is not recognized as +* stack access, so at the end of backtracking +* stack slot fp-8 is still marked in stack_mask. +* However the parent state may not have accessed +* fp-8 and it's "unallocated" stack space. +* In such case fallback to conservative. +*/ +mark_all_scalars_precise (env, st); +bt_reset (bt); +return 0 ; + } -if (!is_spilled_scalar_reg (&func->stack[i])) { -bt_clear_slot (bt, i); -continue ; +if (!is_spilled_scalar_reg (&func->stack[i])) { +bt_clear_frame_slot (bt, fr, i); +continue ; + } + reg = &func->stack[i].spilled_ptr; +if (reg->precise) +bt_clear_frame_slot (bt, fr, i); +else + reg->precise = true; + } +if (env->log.level &BPF_LOG_LEVEL2 ) { +fmt_reg_mask (env->tmp_str_buf,TMP_STR_BUF_LEN , +bt_frame_reg_mask (bt, fr)); +verbose (env,"mark_precise: frame%d: parent state regs=%s " , + fr, env->tmp_str_buf); +fmt_stack_mask (env->tmp_str_buf,TMP_STR_BUF_LEN , +bt_frame_stack_mask (bt, fr)); +verbose (env,"stack=%s: " , env->tmp_str_buf); +print_verifier_state (env, func, true); } - reg = &func->stack[i].spilled_ptr; -if (reg->precise) -bt_clear_slot (bt, i); -else - reg->precise = true; - } -if (env->log.level &BPF_LOG_LEVEL2 ) { -verbose (env,"parent %s regs=%x stack=%llx marks:" , - !bt_empty (bt) ?"didn't have" :"already had" , -bt_reg_mask (bt),bt_stack_mask (bt)); -print_verifier_state (env, func, true); }if (bt_empty (bt))
tools/testing/selftests/bpf/verifier/precise.c +9 -9
@@ -44,7 +44,7 @@ mark_precise: frame0: regs=r2 stack= before 23\ mark_precise: frame0: regs=r2 stack= before 22\ mark_precise: frame0: regs=r2 stack= before 20\ - parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 10\ mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\
@@ -55,7 +55,7 @@ mark_precise: frame0: regs=r9 stack= before 12\ mark_precise: frame0: regs=r9 stack= before 11\ mark_precise: frame0: regs=r9 stack= before 10\ - parent already had regs=0 stack=0 marks:", + mark_precise: frame0: parent state regs= stack=:", }, { "precise: test 2",
@@ -104,15 +104,15 @@ mark_precise: frame0: regs=r2 stack= before 24\ mark_precise: frame0: regs=r2 stack= before 23\ mark_precise: frame0: regs=r2 stack= before 22\ - parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 20 first_idx 20\ mark_precise: frame0: regs=r2 stack= before 20\ - parent didn't have regs=4 stack=0 marks:\ + mark_precise: frame0: parent state regs=r2 stack=:\ mark_precise: frame0: last_idx 19 first_idx 17\ mark_precise: frame0: regs=r2 stack= before 19\ mark_precise: frame0: regs=r9 stack= before 18\ mark_precise: frame0: regs=r8,r9 stack= before 17\ - parent already had regs=0 stack=0 marks:", + mark_precise: frame0: parent state regs= stack=:", }, { "precise: cross frame pruning",
@@ -153,14 +153,14 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, .errstr ="mark_precise: frame0: last_idx 5 first_idx 5\ -parent didn't have regs=10 stack=0 marks:\ +mark_precise: frame0: parent state regs=r4 stack=:\ mark_precise: frame0: last_idx 4 first_idx 2\ mark_precise: frame0: regs=r4 stack= before 4\ mark_precise: frame0: regs=r4 stack= before 3\ mark_precise: frame0: regs= stack=-8 before 2\ mark_precise: frame0: falling back to forcing all scalars precise\ mark_precise: frame0: last_idx 5 first_idx 5\ - parent didn't have regs=1 stack=0 marks:", + mark_precise: frame0: parent state regs=r0 stack=:", .result = VERBOSE_ACCEPT, .retval = -1, },
@@ -179,7 +179,7 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = BPF_F_TEST_STATE_FREQ, .errstr ="mark_precise: frame0: last_idx 6 first_idx 6\ -parent didn't have regs=10 stack=0 marks:\ +mark_precise: frame0: parent state regs=r4 stack=:\ mark_precise: frame0: last_idx 5 first_idx 3\ mark_precise: frame0: regs=r4 stack= before 5\ mark_precise: frame0: regs=r4 stack= before 4\
@@ -188,7 +188,7 @@ force_precise: frame0: forcing r0 to be precise\ force_precise: frame0: forcing r0 to be precise\ mark_precise: frame0: last_idx 6 first_idx 6\ - parent didn't have regs=1 stack=0 marks:\ + mark_precise: frame0: parent state regs=r0 stack=:\ mark_precise: frame0: last_idx 5 first_idx 3\ mark_precise: frame0: regs=r0 stack= before 5", .result = VERBOSE_ACCEPT,
Signature · 1 line
2.39.2
Greg Kroah-Hartman
maintainerPATCH 111/800 bpf: fix propagate_precision() logic for inner frames
In reply to Greg Kroah-HartmanFrom: Andrii Nakryiko <[email protected]>
[ Upstream commit f655badf2a8fc028433d9583bf86a6b473721f09 ]
Fix propagate_precision() logic to perform propagation of all necessary registers and stack slots across all active frames *in one batch step*.
Doing this for each register/slot in each individual frame is wasteful, but the main problem is that backtracking of instruction in any frame except the deepest one just doesn't work. This is due to backtracking logic relying on jump history, and available jump history always starts (or ends, depending how you view it) in current frame. So, if prog A (frame #0) called subprog B (frame #1) and we need to propagate precision of, say, register R6 (callee-saved) within frame #0, we actually don't even know where jump history that corresponds to prog A even starts. We'd need to skip subprog part of jump history first to be able to do this.
Luckily, with struct backtrack_state and __mark_chain_precision() handling bitmasks tracking/propagation across all active frames at the same time (added in previous patch), propagate_precision() can be both fixed and sped up by setting all the necessary bits across all frames and then performing one __mark_chain_precision() pass. This makes it unnecessary to skip subprog parts of jump history.
We also improve logging along the way, to clearly specify which registers' and slots' precision markings are propagated within which frame. Each frame will have dedicated line and all registers and stack slots from that frame will be reported in format similar to precision backtrack regs/stack logging. E.g.:
frame 1: propagating r1,r2,r3,fp-8,fp-16
frame 0: propagating r3,r9,fp-120
--- kernel/bpf/verifier.c | 65 +++++++++++++++++++++++-------------------- 1 file changed, 35 insertions(+), 30 deletions(-)
kernel/bpf/verifier.c +35 -30
@@ -3684,8 +3684,7 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_* mark_all_scalars_imprecise() to hopefully get more permissive and generic * finalized states which help in short circuiting more future states. */ -static int __mark_chain_precision (struct bpf_verifier_env *env,int frame,int regno, -int spi) +static int __mark_chain_precision (struct bpf_verifier_env *env,int regno) {struct backtrack_state *bt = &env->bt;struct bpf_verifier_state *st = env->cur_state;
@@ -3700,13 +3699,13 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int rreturn 0 ;/* set frame number from which we are starting to backtrack */ -bt_init (bt, frame); +bt_init (bt, env->cur_state->curframe);/* Do sanity checks against current state of register and/or stack * slot, but don't set precise flag in current state, as precision * tracking in the current state is unnecessary. */ - func = st->frame[frame]; + func = st->frame[bt->frame];if (regno >=0 ) { reg = &func->regs[regno];if (reg->type !=SCALAR_VALUE ) {
@@ -3716,13 +3715,6 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int rbt_set_reg (bt, regno); } -while (spi >=0 ) { -if (!is_spilled_scalar_reg (&func->stack[spi])) -break ; -bt_set_slot (bt, spi); -break ; - } -if (bt_empty (bt))return 0 ;
@@ -3872,17 +3864,15 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int rint mark_chain_precision (struct bpf_verifier_env *env,int regno) { -return __mark_chain_precision (env, env->cur_state->curframe, regno,-1 ); -} - -static int mark_chain_precision_frame (struct bpf_verifier_env *env,int frame,int regno) -{ -return __mark_chain_precision (env, frame, regno,-1 ); +return __mark_chain_precision (env, regno); } -static int mark_chain_precision_stack_frame (struct bpf_verifier_env *env,int frame,int spi) +/* mark_chain_precision_batch() assumes that env->bt is set in the caller to +* desired reg and stack masks across all relevant frames +*/ +static int mark_chain_precision_batch (struct bpf_verifier_env *env) { -return __mark_chain_precision (env, frame,-1 , spi); +return __mark_chain_precision (env,-1 ); }static bool is_spillable_regtype (enum bpf_reg_type type)
@@ -15298,20 +15288,25 @@ static int propagate_precision(struct bpf_verifier_env *env,struct bpf_reg_state *state_reg;struct bpf_func_state *state;int i, err =0 , fr; +bool first;for (fr = old->curframe; fr >=0 ; fr--) { state = old->frame[fr]; state_reg = state->regs; + first = true;for (i =0 ; i <BPF_REG_FP ; i++, state_reg++) {if (state_reg->type !=SCALAR_VALUE || !state_reg->precise || !(state_reg->live ®_LIVE_READ ))continue ; -if (env->log.level &BPF_LOG_LEVEL2 ) -verbose (env,"frame %d: propagating r%d\n" , fr, i); - err =mark_chain_precision_frame (env, fr, i); -if (err <0 ) -return err; +if (env->log.level &BPF_LOG_LEVEL2 ) { +if (first) +verbose (env,"frame %d: propagating r%d" , fr, i); +else +verbose (env,",r%d" , i); + } +bt_set_frame_reg (&env->bt, fr, i); + first = false; }for (i =0 ; i < state->allocated_stack /BPF_REG_SIZE ; i++) {
@@ -15322,14 +15317,24 @@ static int propagate_precision(struct bpf_verifier_env *env, !state_reg->precise || !(state_reg->live & REG_LIVE_READ)) continue; -if (env->log.level &BPF_LOG_LEVEL2 ) -verbose (env,"frame %d: propagating fp%d\n" , - fr, (-i -1 ) *BPF_REG_SIZE ); - err =mark_chain_precision_stack_frame (env, fr, i); -if (err <0 ) -return err; +if (env->log.level &BPF_LOG_LEVEL2 ) { +if (first) +verbose (env,"frame %d: propagating fp%d" , + fr, (-i -1 ) *BPF_REG_SIZE ); +else +verbose (env,",fp%d" , (-i -1 ) *BPF_REG_SIZE ); + } +bt_set_frame_slot (&env->bt, fr, i); + first = false; } +if (!first) +verbose (env,"\n" ); } + + err =mark_chain_precision_batch (env); +if (err <0 ) +return err; +return 0 ; }
Signature · 1 line
2.39.2