July 2024 - Linux-stable-mirror

[PATCH 02/12] drm/v3d: Fix potential memory leak in the timestamp extension

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> If fetching of userspace memory fails during the main loop, all drm sync objs looked up until that point will be leaked because of the missing drm_syncobj_put. Fix it by exporting and using a common cleanup helper. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: 9ba0ff3e083f ("drm/v3d: Create a CPU job extension for the timestamp query job") Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/v3d/v3d_drv.h | 2 ++ drivers/gpu/drm/v3d/v3d_sched.c | 22 +++++++++++++------ drivers/gpu/drm/v3d/v3d_submit.c | 36 ++++++++++++++++++++++---------- 3 files changed, 43 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 099b962bdfde..95651c3c926f 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -563,6 +563,8 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo); void v3d_mmu_remove_ptes(struct v3d_bo *bo); /* v3d_sched.c */ +void __v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *qinfo, + unsigned int count); void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue); int v3d_sched_init(struct v3d_dev *v3d); void v3d_sched_fini(struct v3d_dev *v3d); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 03df37a3acf5..e45d3ddc6f82 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -73,18 +73,28 @@ v3d_sched_job_free(struct drm_sched_job *sched_job) v3d_job_cleanup(job); } +void +__v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *qinfo, + unsigned int count) +{ + if (qinfo->queries) { + unsigned int i; + + for (i = 0; i < count; i++) + drm_syncobj_put(qinfo->queries[i].syncobj); + + kvfree(qinfo->queries); + } +} + static void v3d_cpu_job_free(struct drm_sched_job *sched_job) { struct v3d_cpu_job *job = to_cpu_job(sched_job); - struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query; struct v3d_performance_query_info *performance_query = &job->performance_query; - if (timestamp_query->queries) { - for (int i = 0; i < timestamp_query->count; i++) - drm_syncobj_put(timestamp_query->queries[i].syncobj); - kvfree(timestamp_query->queries); - } + __v3d_timestamp_query_info_free(&job->timestamp_query, + job->timestamp_query.count); if (performance_query->queries) { for (int i = 0; i < performance_query->count; i++) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 263fefc1d04f..2818afdd4807 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -452,6 +452,7 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, { u32 __user *offsets, *syncs; struct drm_v3d_timestamp_query timestamp; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -484,15 +485,15 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, u32 offset, sync; if (copy_from_user(&offset, offsets++, sizeof(offset))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].offset = offset; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -500,6 +501,10 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, job->timestamp_query.count = timestamp.count; return 0; + +error: + __v3d_timestamp_query_info_free(qinfo, i); + return err; } static int @@ -509,6 +514,7 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, { u32 __user *syncs; struct drm_v3d_reset_timestamp_query reset; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -539,8 +545,8 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, job->timestamp_query.queries[i].offset = reset.offset + 8 * i; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -548,6 +554,10 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, job->timestamp_query.count = reset.count; return 0; + +error: + __v3d_timestamp_query_info_free(qinfo, i); + return err; } /* Get data for the copy timestamp query results job submission. */ @@ -558,7 +568,7 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, { u32 __user *offsets, *syncs; struct drm_v3d_copy_timestamp_query copy; - int i; + int i, err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -591,15 +601,15 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, u32 offset, sync; if (copy_from_user(&offset, offsets++, sizeof(offset))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].offset = offset; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -613,6 +623,10 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, job->copy.stride = copy.stride; return 0; + +error: + __v3d_timestamp_query_info_free(qinfo, i); + return err; } static int -- 2.44.0

9 months, 4 weeks

2
1
0 0

+ mm-fix-old-young-bit-handling-in-the-faulting-path.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: fix old/young bit handling in the faulting path has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-fix-old-young-bit-handling-in-the-faulting-path.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ram Tummala <rtummala(a)nvidia.com> Subject: mm: fix old/young bit handling in the faulting path Date: Tue, 9 Jul 2024 18:45:39 -0700 Commit 3bd786f76de2 ("mm: convert do_set_pte() to set_pte_range()") replaced do_set_pte() with set_pte_range() and that introduced a regression in the following faulting path of non-anonymous vmas which caused the PTE for the faulting address to be marked as old instead of young. handle_pte_fault() do_pte_missing() do_fault() do_read_fault() || do_cow_fault() || do_shared_fault() finish_fault() set_pte_range() The polarity of prefault calculation is incorrect. This leads to prefault being incorrectly set for the faulting address. The following check will incorrectly mark the PTE old rather than young. On some architectures this will cause a double fault to mark it young when the access is retried. if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); On a subsequent fault on the same address, the faulting path will see a non NULL vmf->pte and instead of reaching the do_pte_missing() path, PTE will then be correctly marked young in handle_pte_fault() itself. Due to this bug, performance degradation in the fault handling path will be observed due to unnecessary double faulting. Link: https://lkml.kernel.org/r/20240710014539.746200-1-rtummala@nvidia.com Fixes: 3bd786f76de2 ("mm: convert do_set_pte() to set_pte_range()") Signed-off-by: Ram Tummala <rtummala(a)nvidia.com> Reviewed-by: Yin Fengwei <fengwei.yin(a)intel.com> Cc: Alistair Popple <apopple(a)nvidia.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Yin Fengwei <fengwei.yin(a)intel.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/memory.c~mm-fix-old-young-bit-handling-in-the-faulting-path +++ a/mm/memory.c @@ -4681,7 +4681,7 @@ void set_pte_range(struct vm_fault *vmf, { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; - bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE); + bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; flush_icache_pages(vma, page, nr); _ Patches currently in -mm which might be from rtummala(a)nvidia.com are mm-fix-old-young-bit-handling-in-the-faulting-path.patch

9 months, 4 weeks

1
0
0 0

[PATCH 01/12] drm/v3d: Prevent out of bounds access in performance query extensions

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Check that the number of perfmons userspace is passing in the copy and reset extensions is not greater than the internal kernel storage where the ids will be copied into. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: bae7cb5d6800 ("drm/v3d: Create a CPU job extension for the reset performance query job" Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/v3d/v3d_submit.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 88f63d526b22..263fefc1d04f 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -637,6 +637,9 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, if (copy_from_user(&reset, ext, sizeof(reset))) return -EFAULT; + if (reset.nperfmons > V3D_MAX_PERFMONS) + return -EINVAL; + job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY; job->performance_query.queries = kvmalloc_array(reset.count, @@ -708,6 +711,9 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, if (copy.pad) return -EINVAL; + if (copy.nperfmons > V3D_MAX_PERFMONS) + return -EINVAL; + job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY; job->performance_query.queries = kvmalloc_array(copy.count, -- 2.44.0

9 months, 4 weeks

3
2
0 0

[PATCH] drm/i915/gt: Do not consider preemption during execlists_dequeue for gen8

by Nitin Gote

We're seeing a GPU HANG issue on a CHV platform, which was caused by bac24f59f454 ("drm/i915/execlists: Enable coarse preemption boundaries for gen8"). Gen8 platform has only timeslice and doesn't support a preemption mechanism as engines do not have a preemption timer and doesn't send an irq if the preemption timeout expires. So, add a fix to not consider preemption during dequeuing for gen8 platforms. Also move can_preemt() above need_preempt() function to resolve implicit declaration of function ‘can_preempt' error and make can_preempt() function param as const to resolve error: passing argument 1 of ‘can_preempt’ discards ‘const’ qualifier from the pointer target type. Fixes: bac24f59f454 ("drm/i915/execlists: Enable coarse preemption boundaries for gen8") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/11396 Suggested-by: Andi Shyti <andi.shyti(a)intel.com> Signed-off-by: Nitin Gote <nitin.r.gote(a)intel.com> Cc: Chris Wilson <chris.p.wilson(a)linux.intel.com> CC: <stable(a)vger.kernel.org> # v5.2+ --- .../drm/i915/gt/intel_execlists_submission.c | 24 ++++++++++++------- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 21829439e686..30631cc690f2 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -294,11 +294,26 @@ static int virtual_prio(const struct intel_engine_execlists *el) return rb ? rb_entry(rb, struct ve_node, rb)->prio : INT_MIN; } +static bool can_preempt(const struct intel_engine_cs *engine) +{ + if (GRAPHICS_VER(engine->i915) > 8) + return true; + + if (IS_CHERRYVIEW(engine->i915) || IS_BROADWELL(engine->i915)) + return false; + + /* GPGPU on bdw requires extra w/a; not implemented */ + return engine->class != RENDER_CLASS; +} + static bool need_preempt(const struct intel_engine_cs *engine, const struct i915_request *rq) { int last_prio; + if ((GRAPHICS_VER(engine->i915) <= 8) && can_preempt(engine)) + return false; + if (!intel_engine_has_semaphores(engine)) return false; @@ -3313,15 +3328,6 @@ static void remove_from_engine(struct i915_request *rq) i915_request_notify_execute_cb_imm(rq); } -static bool can_preempt(struct intel_engine_cs *engine) -{ - if (GRAPHICS_VER(engine->i915) > 8) - return true; - - /* GPGPU on bdw requires extra w/a; not implemented */ - return engine->class != RENDER_CLASS; -} - static void kick_execlists(const struct i915_request *rq, int prio) { struct intel_engine_cs *engine = rq->engine; -- 2.25.1

9 months, 4 weeks

3
3
0 0

[PATCH v2] cxl: Fix possible null pointer dereference in read_handle()

by Ma Ke

In read_handle(), of_get_address() may return NULL which is later dereferenced. Fix this by adding NULL check. Cc: stable(a)vger.kernel.org Fixes: 14baf4d9c739 ("cxl: Add guest-specific code") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- Changes in v2: - The potential vulnerability was discovered as follows: based on our customized static analysis tool, extract vulnerability features[1], and then match similar vulnerability features in this function. - Reference link: [1] https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --- drivers/misc/cxl/of.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/cxl/of.c b/drivers/misc/cxl/of.c index bcc005dff1c0..d8dbb3723951 100644 --- a/drivers/misc/cxl/of.c +++ b/drivers/misc/cxl/of.c @@ -58,7 +58,7 @@ static int read_handle(struct device_node *np, u64 *handle) /* Get address and size of the node */ prop = of_get_address(np, 0, &size, NULL); - if (size) + if (!prop || size) return -EINVAL; /* Helper to read a big number; size is in cells (not bytes) */ -- 2.25.1

9 months, 4 weeks

3
2
0 0

+ mm-fix-pte_af-handling-in-fault-path-on-architectures-with-hw-af-support.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: fix PTE_AF handling in fault path on architectures with HW AF support has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-fix-pte_af-handling-in-fault-path-on-architectures-with-hw-af-support.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ram Tummala <rtummala(a)nvidia.com> Subject: mm: fix PTE_AF handling in fault path on architectures with HW AF support Date: Tue, 9 Jul 2024 17:09:42 -0700 Commit 3bd786f76de2 ("mm: convert do_set_pte() to set_pte_range()") replaced do_set_pte() with set_pte_range() and that introduced a regression in the following faulting path of non-anonymous vmas on CPUs with HW AF (Access Flag) support. handle_pte_fault() do_pte_missing() do_fault() do_read_fault() || do_cow_fault() || do_shared_fault() finish_fault() set_pte_range() The polarity of prefault calculation is incorrect. This leads to prefault being incorrectly set for the faulting address. The following if check will incorrectly clear the PTE_AF bit instead of setting it and the access will fault again on the same address due to the missing PTE_AF bit. if (prefault && arch_wants_old_prefaulted_pte()) entry = pte_mkold(entry); On a subsequent fault on the same address, the faulting path will see a non NULL vmf->pte and instead of reaching the do_pte_missing() path, PTE_AF will be correctly set in handle_pte_fault() itself. Due to this bug, performance degradation in the fault handling path will be observed due to unnecessary double faulting. Link: https://lkml.kernel.org/r/20240710000942.623704-1-rtummala@nvidia.com Fixes: 3bd786f76de2 ("mm: convert do_set_pte() to set_pte_range()") Signed-off-by: Ram Tummala <rtummala(a)nvidia.com> Reviewed-by: Yin Fengwei <fengwei.yin(a)intel.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Alistair Popple <apopple(a)nvidia.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/memory.c~mm-fix-pte_af-handling-in-fault-path-on-architectures-with-hw-af-support +++ a/mm/memory.c @@ -4681,7 +4681,7 @@ void set_pte_range(struct vm_fault *vmf, { struct vm_area_struct *vma = vmf->vma; bool write = vmf->flags & FAULT_FLAG_WRITE; - bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE); + bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE); pte_t entry; flush_icache_pages(vma, page, nr); _ Patches currently in -mm which might be from rtummala(a)nvidia.com are mm-fix-pte_af-handling-in-fault-path-on-architectures-with-hw-af-support.patch

9 months, 4 weeks

2
1
0 0

[PATCH AUTOSEL 4.19] wifi: cfg80211: wext: add extra SIOCSIWSCAN data check

by Sasha Levin

From: Dmitry Antipov <dmantipov(a)yandex.ru> [ Upstream commit 6ef09cdc5ba0f93826c09d810c141a8d103a80fc ] In 'cfg80211_wext_siwscan()', add extra check whether number of channels passed via 'ioctl(sock, SIOCSIWSCAN, ...)' doesn't exceed IW_MAX_FREQUENCIES and reject invalid request with -EINVAL otherwise. Reported-by: syzbot+253cd2d2491df77c93ac(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=253cd2d2491df77c93ac Signed-off-by: Dmitry Antipov <dmantipov(a)yandex.ru> Link: https://msgid.link/20240531032010.451295-1-dmantipov@yandex.ru Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- net/wireless/scan.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index dacb9ceee3efd..0dc27703443c8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1405,10 +1405,14 @@ int cfg80211_wext_siwscan(struct net_device *dev, wiphy = &rdev->wiphy; /* Determine number of channels, needed to allocate creq */ - if (wreq && wreq->num_channels) + if (wreq && wreq->num_channels) { + /* Passed from userspace so should be checked */ + if (unlikely(wreq->num_channels > IW_MAX_FREQUENCIES)) + return -EINVAL; n_channels = wreq->num_channels; - else + } else { n_channels = ieee80211_get_num_supported_channels(wiphy); + } creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), -- 2.43.0

9 months, 4 weeks

3
3
0 0

[PATCH AUTOSEL 6.1 01/29] scsi: core: alua: I/O errors for ALUA state transitions

by Sasha Levin

From: Martin Wilck <martin.wilck(a)suse.com> [ Upstream commit 10157b1fc1a762293381e9145041253420dfc6ad ] When a host is configured with a few LUNs and I/O is running, injecting FC faults repeatedly leads to path recovery problems. The LUNs have 4 paths each and 3 of them come back active after say an FC fault which makes 2 of the paths go down, instead of all 4. This happens after several iterations of continuous FC faults. Reason here is that we're returning an I/O error whenever we're encountering sense code 06/04/0a (LOGICAL UNIT NOT ACCESSIBLE, ASYMMETRIC ACCESS STATE TRANSITION) instead of retrying. [mwilck: The original patch was developed by Rajashekhar M A and Hannes Reinecke. I moved the code to alua_check_sense() as suggested by Mike Christie [1]. Evan Milne had raised the question whether pg->state should be set to transitioning in the UA case [2]. I believe that doing this is correct. SCSI_ACCESS_STATE_TRANSITIONING by itself doesn't cause I/O errors. Our handler schedules an RTPG, which will only result in an I/O error condition if the transitioning timeout expires.] [1] https://lore.kernel.org/all/0bc96e82-fdda-4187-148d-5b34f81d4942@oracle.com/ [2] https://lore.kernel.org/all/CAGtn9r=kicnTDE2o7Gt5Y=yoidHYD7tG8XdMHEBJTBraVE… Co-developed-by: Rajashekhar M A <rajs(a)netapp.com> Co-developed-by: Hannes Reinecke <hare(a)suse.de> Signed-off-by: Hannes Reinecke <hare(a)suse.de> Signed-off-by: Martin Wilck <martin.wilck(a)suse.com> Link: https://lore.kernel.org/r/20240514140344.19538-1-mwilck@suse.com Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Reviewed-by: Mike Christie <michael.christie(a)oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/scsi/device_handler/scsi_dh_alua.c | 31 +++++++++++++++------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 0781f991e7845..f5fc8631883d5 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -406,28 +406,40 @@ static char print_alua_state(unsigned char state) } } -static enum scsi_disposition alua_check_sense(struct scsi_device *sdev, - struct scsi_sense_hdr *sense_hdr) +static void alua_handle_state_transition(struct scsi_device *sdev) { struct alua_dh_data *h = sdev->handler_data; struct alua_port_group *pg; + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (pg) + pg->state = SCSI_ACCESS_STATE_TRANSITIONING; + rcu_read_unlock(); + alua_check(sdev, false); +} + +static enum scsi_disposition alua_check_sense(struct scsi_device *sdev, + struct scsi_sense_hdr *sense_hdr) +{ switch (sense_hdr->sense_key) { case NOT_READY: if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) { /* * LUN Not Accessible - ALUA state transition */ - rcu_read_lock(); - pg = rcu_dereference(h->pg); - if (pg) - pg->state = SCSI_ACCESS_STATE_TRANSITIONING; - rcu_read_unlock(); - alua_check(sdev, false); + alua_handle_state_transition(sdev); return NEEDS_RETRY; } break; case UNIT_ATTENTION: + if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x0a) { + /* + * LUN Not Accessible - ALUA state transition + */ + alua_handle_state_transition(sdev); + return NEEDS_RETRY; + } if (sense_hdr->asc == 0x29 && sense_hdr->ascq == 0x00) { /* * Power On, Reset, or Bus Device Reset. @@ -494,7 +506,8 @@ static int alua_tur(struct scsi_device *sdev) retval = scsi_test_unit_ready(sdev, ALUA_FAILOVER_TIMEOUT * HZ, ALUA_FAILOVER_RETRIES, &sense_hdr); - if (sense_hdr.sense_key == NOT_READY && + if ((sense_hdr.sense_key == NOT_READY || + sense_hdr.sense_key == UNIT_ATTENTION) && sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) return SCSI_DH_RETRY; else if (retval) -- 2.43.0

9 months, 4 weeks

4
32
0 0

[PATCH v3 2/2] f2fs: use meta inode for GC of COW file

by Sunmin Jeong

In case of the COW file, new updates and GC writes are already separated to page caches of the atomic file and COW file. As some cases that use the meta inode for GC, there are some race issues between a foreground thread and GC thread. To handle them, we need to take care when to invalidate and wait writeback of GC pages in COW files as the case of using the meta inode. Also, a pointer from the COW inode to the original inode is required to check the state of original pages. For the former, we can solve the problem by using the meta inode for GC of COW files. Then let's get a page from the original inode in move_data_block when GCing the COW file to avoid race condition. Fixes: 3db1de0e582c ("f2fs: change the current atomic write way") Cc: stable(a)vger.kernel.org #v5.19+ Reviewed-by: Sungjong Seo <sj1557.seo(a)samsung.com> Reviewed-by: Yeongjin Gil <youngjin.gil(a)samsung.com> Signed-off-by: Sunmin Jeong <s_min.jeong(a)samsung.com> Reviewed-by: Chao Yu <chao(a)kernel.org> --- v3: - make the mapping variable to select a proper inode v2: - use union for cow inode to point to atomic inode fs/f2fs/data.c | 2 +- fs/f2fs/f2fs.h | 13 +++++++++++-- fs/f2fs/file.c | 3 +++ fs/f2fs/gc.c | 7 +++++-- fs/f2fs/inline.c | 2 +- fs/f2fs/inode.c | 3 ++- 6 files changed, 23 insertions(+), 7 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9a213d03005d..f6b1782f965a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2606,7 +2606,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_NOQUOTA(inode)) return true; - if (f2fs_is_atomic_file(inode)) + if (f2fs_used_in_atomic_write(inode)) return true; /* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */ if (f2fs_compressed_file(inode) && diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 796ae11c0fa3..4a8621e4a33a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -843,7 +843,11 @@ struct f2fs_inode_info { struct task_struct *atomic_write_task; /* store atomic write task */ struct extent_tree *extent_tree[NR_EXTENT_CACHES]; /* cached extent_tree entry */ - struct inode *cow_inode; /* copy-on-write inode for atomic write */ + union { + struct inode *cow_inode; /* copy-on-write inode for atomic write */ + struct inode *atomic_inode; + /* point to atomic_inode, available only for cow_inode */ + }; /* avoid racing between foreground op and gc */ struct f2fs_rwsem i_gc_rwsem[2]; @@ -4263,9 +4267,14 @@ static inline bool f2fs_post_read_required(struct inode *inode) f2fs_compressed_file(inode); } +static inline bool f2fs_used_in_atomic_write(struct inode *inode) +{ + return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode); +} + static inline bool f2fs_meta_inode_gc_required(struct inode *inode) { - return f2fs_post_read_required(inode) || f2fs_is_atomic_file(inode); + return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode); } /* diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index e4a7cff00796..547e7ec32b1f 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2183,6 +2183,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) set_inode_flag(fi->cow_inode, FI_COW_FILE); clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); + + /* Set the COW inode's atomic_inode to the atomic inode */ + F2FS_I(fi->cow_inode)->atomic_inode = inode; } else { /* Reuse the already created COW inode */ ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index cb3006551ab5..724bbcb447d3 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1171,7 +1171,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, static int ra_data_block(struct inode *inode, pgoff_t index) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct address_space *mapping = inode->i_mapping; + struct address_space *mapping = f2fs_is_cow_file(inode) ? + F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct dnode_of_data dn; struct page *page; struct f2fs_io_info fio = { @@ -1260,6 +1261,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index) static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { + struct address_space *mapping = f2fs_is_cow_file(inode) ? + F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, @@ -1282,7 +1285,7 @@ static int move_data_block(struct inode *inode, block_t bidx, CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA; /* do not read out */ - page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); + page = f2fs_grab_cache_page(mapping, bidx, false); if (!page) return -ENOMEM; diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 1fba5728be70..cca7d448e55c 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -16,7 +16,7 @@ static bool support_inline_data(struct inode *inode) { - if (f2fs_is_atomic_file(inode)) + if (f2fs_used_in_atomic_write(inode)) return false; if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 7a3e2458b2d9..18dea43e694b 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -804,8 +804,9 @@ void f2fs_evict_inode(struct inode *inode) f2fs_abort_atomic_write(inode, true); - if (fi->cow_inode) { + if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) { clear_inode_flag(fi->cow_inode, FI_COW_FILE); + F2FS_I(fi->cow_inode)->atomic_inode = NULL; iput(fi->cow_inode); fi->cow_inode = NULL; } -- 2.25.1

9 months, 4 weeks

1
0
0 0

[PATCH v2 0/5] ACPI: sysfs: manage sysfs attributes through device core

by Thomas Weißschuh

Simplify the lifecycle of the sysfs attributes by letting the device core manage them. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Changes in v2: - Add fix to validate buffer type validation (patch 1) - Drop usage of devm-APIs as these are unusable for unbound devices - Evaluate _STR on each sysfs access - Link to v1: https://lore.kernel.org/r/20240613-acpi-sysfs-groups-v1-0-665e0deb052a@weis… --- Thomas Weißschuh (5): ACPI: sysfs: validate return type of _STR method ACPI: sysfs: evaluate _STR on each sysfs access ACPI: sysfs: manage attributes as attribute_group ACPI: sysfs: manage sysfs attributes through device core ACPI: sysfs: remove return value of acpi_device_setup_files() drivers/acpi/device_sysfs.c | 196 +++++++++++++++++++------------------------- drivers/acpi/internal.h | 3 +- drivers/acpi/scan.c | 6 +- include/acpi/acpi_bus.h | 1 - 4 files changed, 89 insertions(+), 117 deletions(-) --- base-commit: 34afb82a3c67f869267a26f593b6f8fc6bf35905 change-id: 20240609-acpi-sysfs-groups-cfa756d16752 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

9 months, 4 weeks

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2024