- Linux-stable-mirror - lists.linaro.org

[PATCH v2 3/3] drm/xe: Block exec and rebind worker while evicting for suspend / hibernate

by Thomas Hellström

When the xe pm_notifier evicts for suspend / hibernate, there might be racing tasks trying to re-validate again. This can lead to suspend taking excessive time or get stuck in a live-lock. This behaviour becomes much worse with the fix that actually makes re-validation bring back bos to VRAM rather than letting them remain in TT. Prevent that by having exec and the rebind worker waiting for a completion that is set to block by the pm_notifier before suspend and is signaled by the pm_notifier after resume / wakeup. It's probably still possible to craft malicious applications that block suspending. More work is pending to fix that. Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4288 Fixes: c6a4d46ec1d7 ("drm/xe: evict user memory in PM notifier") Cc: Matthew Auld <matthew.auld(a)intel.com> Cc: Rodrigo Vivi <rodrigo.vivi(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.16+ Signed-off-by: Thomas Hellström <thomas.hellstrom(a)linux.intel.com> --- drivers/gpu/drm/xe/xe_device_types.h | 2 ++ drivers/gpu/drm/xe/xe_exec.c | 9 +++++++++ drivers/gpu/drm/xe/xe_pm.c | 4 ++++ drivers/gpu/drm/xe/xe_vm.c | 14 ++++++++++++++ 4 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 092004d14db2..6602bd678cbc 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -507,6 +507,8 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; /** @pmt: Support the PMT driver callback interface */ struct { diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..374c831e691b 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -237,6 +237,15 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto err_unlock_list; } + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index bee9aacd82e7..f4c7a84270ea 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -306,6 +306,7 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); if (err) @@ -322,6 +323,7 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; @@ -348,6 +350,8 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 3ff3c67aa79d..edcdb0528f2a 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -394,6 +394,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); if (ret) return ret; @@ -494,6 +497,12 @@ static void preempt_rebind_work_func(struct work_struct *w) xe_assert(vm->xe, xe_vm_in_preempt_fence_mode(vm)); trace_xe_vm_rebind_worker_enter(vm); + /* + * This blocks the wq during suspend / hibernate. + * Don't hold any locks. + */ +retry_pm: + wait_for_completion(&vm->xe->pm_block); down_write(&vm->lock); if (xe_vm_is_closed_or_banned(vm)) { @@ -503,6 +512,11 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block)) { + up_write(&vm->lock); + goto retry_pm; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) -- 2.50.1

3 months, 3 weeks

1
0
0 0

[PATCH v5] mm: slub: avoid wake up kswapd in set_track_prepare

by yangshiguang1011＠163.com

From: yangshiguang <yangshiguang(a)xiaomi.com> From: yangshiguang <yangshiguang(a)xiaomi.com> set_track_prepare() can incur lock recursion. The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock. Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags. And the slab caller context has preemption disabled, so __GFP_DIRECT_RECLAIM must not appear in gfp_flags. The oops looks something like: BUG: spinlock recursion on CPU#3, swapper/3/0 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3 Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT) Call trace: spin_bug+0x0 _raw_spin_lock_irqsave+0x80 hrtimer_try_to_cancel+0x94 task_contending+0x10c enqueue_dl_entity+0x2a4 dl_server_start+0x74 enqueue_task_fair+0x568 enqueue_task+0xac do_activate_task+0x14c ttwu_do_activate+0xcc try_to_wake_up+0x6c8 default_wake_function+0x20 autoremove_wake_function+0x1c __wake_up+0xac wakeup_kswapd+0x19c wake_all_kswapds+0x78 __alloc_pages_slowpath+0x1ac __alloc_pages_noprof+0x298 stack_depot_save_flags+0x6b0 stack_depot_save+0x14 set_track_prepare+0x5c ___slab_alloc+0xccc __kmalloc_cache_noprof+0x470 __set_page_owner+0x2bc post_alloc_hook[jt]+0x1b8 prep_new_page+0x28 get_page_from_freelist+0x1edc __alloc_pages_noprof+0x13c alloc_slab_page+0x244 allocate_slab+0x7c ___slab_alloc+0x8e8 kmem_cache_alloc_noprof+0x450 debug_objects_fill_pool+0x22c debug_object_activate+0x40 enqueue_hrtimer[jt]+0xdc hrtimer_start_range_ns+0x5f8 ... Signed-off-by: yangshiguang <yangshiguang(a)xiaomi.com> Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects") Cc: stable(a)vger.kernel.org --- v1 -> v2: propagate gfp flags to set_track_prepare() v2 -> v3: Remove the gfp restriction in set_track_prepare() v3 -> v4: Re-describe the comments in set_track_prepare. v4 -> v5: Modify the patch commit. [1]https://lore.kernel.org/all/20250801065121.876793-1-yangshiguang1011@163.… [2]https://lore.kernel.org/all/20250814111641.380629-2-yangshiguang1011@163.… [3]https://lore.kernel.org/all/20250825121737.2535732-1-yangshiguang1011@163… [4]https://lore.kernel.org/all/20250830020946.1767573-1-yangshiguang1011@163… --- mm/slub.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 30003763d224..b0af51a5321b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -962,19 +962,25 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; + /* + * Preemption is disabled in ___slab_alloc() so we need to disallow + * blocking. The flags are further adjusted by gfp_nested_mask() in + * stack_depot itself. + */ + gfp_flags &= ~(__GFP_DIRECT_RECLAIM); nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -996,9 +1002,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1921,9 +1927,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3878,7 +3884,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * tracking info and return the object. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -3910,7 +3916,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -4422,7 +4428,7 @@ static noinline void free_to_partial_list( depot_stack_handle_t handle = 0; if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); -- 2.43.0

3 months, 3 weeks

1
0
0 0

[PATCH v5] mm: slub: avoid wake up kswapd in set_track_prepare

by yangshiguang1011＠163.com

From: yangshiguang <yangshiguang(a)xiaomi.com> From: yangshiguang <yangshiguang(a)xiaomi.com> set_track_prepare() can incur lock recursion. The issue is that it is called from hrtimer_start_range_ns holding the per_cpu(hrtimer_bases)[n].lock, but when enabled CONFIG_DEBUG_OBJECTS_TIMERS, may wake up kswapd in set_track_prepare, and try to hold the per_cpu(hrtimer_bases)[n].lock. Avoid deadlock caused by implicitly waking up kswapd by passing in allocation flags. And the slab caller context has preemption disabled, so __GFP_DIRECT_RECLAIM must not appear in gfp_flags. The oops looks something like: BUG: spinlock recursion on CPU#3, swapper/3/0 lock: 0xffffff8a4bf29c80, .magic: dead4ead, .owner: swapper/3/0, .owner_cpu: 3 Hardware name: Qualcomm Technologies, Inc. Popsicle based on SM8850 (DT) Call trace: spin_bug+0x0 _raw_spin_lock_irqsave+0x80 hrtimer_try_to_cancel+0x94 task_contending+0x10c enqueue_dl_entity+0x2a4 dl_server_start+0x74 enqueue_task_fair+0x568 enqueue_task+0xac do_activate_task+0x14c ttwu_do_activate+0xcc try_to_wake_up+0x6c8 default_wake_function+0x20 autoremove_wake_function+0x1c __wake_up+0xac wakeup_kswapd+0x19c wake_all_kswapds+0x78 __alloc_pages_slowpath+0x1ac __alloc_pages_noprof+0x298 stack_depot_save_flags+0x6b0 stack_depot_save+0x14 set_track_prepare+0x5c ___slab_alloc+0xccc __kmalloc_cache_noprof+0x470 __set_page_owner+0x2bc post_alloc_hook[jt]+0x1b8 prep_new_page+0x28 get_page_from_freelist+0x1edc __alloc_pages_noprof+0x13c alloc_slab_page+0x244 allocate_slab+0x7c ___slab_alloc+0x8e8 kmem_cache_alloc_noprof+0x450 debug_objects_fill_pool+0x22c debug_object_activate+0x40 enqueue_hrtimer[jt]+0xdc hrtimer_start_range_ns+0x5f8 ... Signed-off-by: yangshiguang <yangshiguang(a)xiaomi.com> Fixes: 5cf909c553e9 ("mm/slub: use stackdepot to save stack trace in objects") Cc: stable(a)vger.kernel.org --- v1 -> v2: propagate gfp flags to set_track_prepare() v2 -> v3: Remove the gfp restriction in set_track_prepare() v3 -> v4: Re-describe the comments in set_track_prepare. v4 -> v5: Modify the patch commit. [1]https://lore.kernel.org/all/20250801065121.876793-1-yangshiguang1011@163.… [2]https://lore.kernel.org/all/20250814111641.380629-2-yangshiguang1011@163.… [3]https://lore.kernel.org/all/20250825121737.2535732-1-yangshiguang1011@163… [4]https://lore.kernel.org/all/20250830020946.1767573-1-yangshiguang1011@163… --- mm/slub.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 30003763d224..b0af51a5321b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -962,19 +962,25 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; + /* + * Preemption is disabled in ___slab_alloc() so we need to disallow + * blocking. The flags are further adjusted by gfp_nested_mask() in + * stack_depot itself. + */ + gfp_flags &= ~(__GFP_DIRECT_RECLAIM); nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -996,9 +1002,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1921,9 +1927,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3878,7 +3884,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, * tracking info and return the object. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -3910,7 +3916,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, gfpflags); return freelist; } @@ -4422,7 +4428,7 @@ static noinline void free_to_partial_list( depot_stack_handle_t handle = 0; if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); -- 2.43.0

3 months, 3 weeks

1
0
0 0

[PATCH v2] mm: memory-tiering: fix PGPROMOTE_CANDIDATE counting

by Ruan Shiyang

Goto-san reported confusing pgpromote statistics where the pgpromote_success count significantly exceeded pgpromote_candidate. On a system with three nodes (nodes 0-1: DRAM 4GB, node 2: NVDIMM 4GB): # Enable demotion only echo 1 > /sys/kernel/mm/numa/demotion_enabled numactl -m 0-1 memhog -r200 3500M >/dev/null & pid=$! sleep 2 numactl memhog -r100 2500M >/dev/null & sleep 10 kill -9 $pid # terminate the 1st memhog # Enable promotion echo 2 > /proc/sys/kernel/numa_balancing After a few seconds, we observeed `pgpromote_candidate < pgpromote_success` $ grep -e pgpromote /proc/vmstat pgpromote_success 2579 pgpromote_candidate 0 In this scenario, after terminating the first memhog, the conditions for pgdat_free_space_enough() are quickly met, and triggers promotion. However, these migrated pages are only counted for in PGPROMOTE_SUCCESS, not in PGPROMOTE_CANDIDATE. To solve these confusing statistics, introduce PGPROMOTE_CANDIDATE_NRL to count the missed promotion pages. And also, not counting these pages into PGPROMOTE_CANDIDATE is to avoid changing the existing algorithm or performance of the promotion rate limit. Link: https://lkml.kernel.org/r/20250729035101.1601407-1-ruansy.fnst@fujitsu.com Co-developed-by: Li Zhijian <lizhijian(a)fujitsu.com> Signed-off-by: Ruan Shiyang <ruansy.fnst(a)fujitsu.com> Reported-by: Yasunori Gotou (Fujitsu) <y-goto(a)fujitsu.com> Suggested-by: Huang Ying <ying.huang(a)linux.alibaba.com> Acked-by: Vlastimil Babka <vbabka(a)suse.cz> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Juri Lelli <juri.lelli(a)redhat.com> Cc: Vincent Guittot <vincent.guittot(a)linaro.org> Cc: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Cc: Steven Rostedt <rostedt(a)goodmis.org> Cc: Ben Segall <bsegall(a)google.com> Cc: Mel Gorman <mgorman(a)suse.de> Cc: Valentin Schneider <vschneid(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- Changes since v1: 1. change Li Zhijian from 'Signed-off-by' to 'Co-developed-by' per Vlastimil. 2. add Acked-by: Vlastimil Babka <vbabka(a)suse.cz> --- include/linux/mmzone.h | 16 +++++++++++++++- kernel/sched/fair.c | 5 +++-- mm/vmstat.c | 1 + 3 files changed, 19 insertions(+), 3 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0c5da9141983..9d3ea9085556 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -234,7 +234,21 @@ enum node_stat_item { #endif #ifdef CONFIG_NUMA_BALANCING PGPROMOTE_SUCCESS, /* promote successfully */ - PGPROMOTE_CANDIDATE, /* candidate pages to promote */ + /** + * Candidate pages for promotion based on hint fault latency. This + * counter is used to control the promotion rate and adjust the hot + * threshold. + */ + PGPROMOTE_CANDIDATE, + /** + * Not rate-limited (NRL) candidate pages for those can be promoted + * without considering hot threshold because of enough free pages in + * fast-tier node. These promotions bypass the regular hotness checks + * and do NOT influence the promotion rate-limiter or + * threshold-adjustment logic. + * This is for statistics/monitoring purposes. + */ + PGPROMOTE_CANDIDATE_NRL, #endif /* PGDEMOTE_*: pages demoted */ PGDEMOTE_KSWAPD, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b173a059315c..82c8d804c54c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1923,11 +1923,13 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, struct pglist_data *pgdat; unsigned long rate_limit; unsigned int latency, th, def_th; + long nr = folio_nr_pages(folio); pgdat = NODE_DATA(dst_nid); if (pgdat_free_space_enough(pgdat)) { /* workload changed, reset hot threshold */ pgdat->nbp_threshold = 0; + mod_node_page_state(pgdat, PGPROMOTE_CANDIDATE_NRL, nr); return true; } @@ -1941,8 +1943,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, if (latency >= th) return false; - return !numa_promotion_rate_limit(pgdat, rate_limit, - folio_nr_pages(folio)); + return !numa_promotion_rate_limit(pgdat, rate_limit, nr); } this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); diff --git a/mm/vmstat.c b/mm/vmstat.c index 71cd1ceba191..e74f0b2a1021 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1280,6 +1280,7 @@ const char * const vmstat_text[] = { #ifdef CONFIG_NUMA_BALANCING [I(PGPROMOTE_SUCCESS)] = "pgpromote_success", [I(PGPROMOTE_CANDIDATE)] = "pgpromote_candidate", + [I(PGPROMOTE_CANDIDATE_NRL)] = "pgpromote_candidate_nrl", #endif [I(PGDEMOTE_KSWAPD)] = "pgdemote_kswapd", [I(PGDEMOTE_DIRECT)] = "pgdemote_direct", -- 2.43.0

3 months, 3 weeks

2
1
0 0

[PATCH] iommu/intel: Fix __domain_mapping()'s usage of switch_to_super_page()

by Eugene Koira

switch_to_super_page() assumes the memory range it's working on is aligned to the target large page level. Unfortunately, __domain_mapping() doesn't take this into account when using it, and will pass unaligned ranges ultimately freeing a PTE range larger than expected. Take for example a mapping with the following iov_pfn range [0x3fe400, 0x4c0600], which should be backed by the following mappings: iov_pfn [0x3fe400, 0x3fffff] covered by 2MiB pages iov_pfn [0x400000, 0x4bffff] covered by 1GiB pages iov_pfn [0x4c0000, 0x4c05ff] covered by 2MiB pages Under this circumstance, __domain_mapping() will pass [0x400000, 0x4c05ff] to switch_to_super_page() at a 1 GiB granularity, which will in turn free PTEs all the way to iov_pfn 0x4fffff. Mitigate this by rounding down the iov_pfn range passed to switch_to_super_page() in __domain_mapping() to the target large page level. Additionally add range alignment checks to switch_to_super_page. Fixes: 9906b9352a35 ("iommu/vt-d: Avoid duplicate removing in __domain_mapping()") Signed-off-by: Eugene Koira <eugkoira(a)amazon.com> Cc: stable(a)vger.kernel.org --- drivers/iommu/intel/iommu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9c3ab9d9f69a..dff2d895b8ab 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1575,6 +1575,10 @@ static void switch_to_super_page(struct dmar_domain *domain, unsigned long lvl_pages = lvl_to_nr_pages(level); struct dma_pte *pte = NULL; + if (WARN_ON(!IS_ALIGNED(start_pfn, lvl_pages) || + !IS_ALIGNED(end_pfn + 1, lvl_pages))) + return; + while (start_pfn <= end_pfn) { if (!pte) pte = pfn_to_dma_pte(domain, start_pfn, &level, @@ -1650,7 +1654,8 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, unsigned long pages_to_remove; pteval |= DMA_PTE_LARGE_PAGE; - pages_to_remove = min_t(unsigned long, nr_pages, + pages_to_remove = min_t(unsigned long, + round_down(nr_pages, lvl_pages), nr_pte_to_next_page(pte) * lvl_pages); end_pfn = iov_pfn + pages_to_remove - 1; switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl); -- 2.47.3 Amazon Development Center (Netherlands) B.V., Johanna Westerdijkplein 1, NL-2521 EN The Hague, Registration No. Chamber of Commerce 56869649, VAT: NL 852339859B01

3 months, 3 weeks

4
5
0 0

[PATCH] coresight: trbe: Fix incorrect error check for devm_kzalloc

by Miaoqian Lin

Fix incorrect use of IS_ERR() to check devm_kzalloc() return value. devm_kzalloc() returns NULL on failure, not an error pointer. This issue was introduced by commit 4277f035d227 ("coresight: trbe: Add a representative coresight_platform_data for TRBE") which replaced the original function but didn't update the error check. Fixes: 4277f035d227 ("coresight: trbe: Add a representative coresight_platform_data for TRBE") Cc: stable(a)vger.kernel.org Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> --- drivers/hwtracing/coresight/coresight-trbe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c index 8267dd1a2130..caf873adfc3a 100644 --- a/drivers/hwtracing/coresight/coresight-trbe.c +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -1279,7 +1279,7 @@ static void arm_trbe_register_coresight_cpu(struct trbe_drvdata *drvdata, int cp * into the device for that purpose. */ desc.pdata = devm_kzalloc(dev, sizeof(*desc.pdata), GFP_KERNEL); - if (IS_ERR(desc.pdata)) + if (!desc.pdata) goto cpu_clear; desc.type = CORESIGHT_DEV_TYPE_SINK; -- 2.35.1

3 months, 3 weeks

2
1
0 0

+ mm-fix-folio_expected_ref_count-when-pg_private_2.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm: fix folio_expected_ref_count() when PG_private_2 has been added to the -mm mm-new branch. Its filename is mm-fix-folio_expected_ref_count-when-pg_private_2.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-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. 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: Hugh Dickins <hughd(a)google.com> Subject: mm: fix folio_expected_ref_count() when PG_private_2 Date: Sun, 31 Aug 2025 02:01:16 -0700 (PDT) 6.16's folio_expected_ref_count() is forgetting the PG_private_2 flag, which (like PG_private, but not in addition to PG_private) counts for 1 more reference: it needs to be using folio_has_private() in place of folio_test_private(). But this went wrong earlier: folio_expected_ref_count() was based on (and replaced) mm/migrate.c's folio_expected_refs(), which has been using folio_test_private() since 6.0 converted to folios(): before that, expected_page_refs() was correctly using page_has_private(). Just a few filesystems are still using PG_private_2 a.k.a. PG_fscache. Potentially, this fix re-enables page migration on their folios; but it would not be surprising to learn that in practice those folios are not migratable for other reasons. Link: https://lkml.kernel.org/r/f91ee36e-a8cb-e3a4-c23b-524ff3848da7@google.com Fixes: 86ebd50224c0 ("mm: add folio_expected_ref_count() for reference count calculation") Fixes: 108ca8358139 ("mm/migrate: Convert expected_page_refs() to folio_expected_refs()") Signed-off-by: Hugh Dickins <hughd(a)google.com> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/include/linux/mm.h~mm-fix-folio_expected_ref_count-when-pg_private_2 +++ a/include/linux/mm.h @@ -2234,8 +2234,8 @@ static inline int folio_expected_ref_cou } else { /* One reference per page from the pagecache. */ ref_count += !!folio->mapping << order; - /* One reference from PG_private. */ - ref_count += folio_test_private(folio); + /* One reference from PG_private or PG_private_2. */ + ref_count += folio_has_private(folio); } /* One reference per page table mapping. */ _ Patches currently in -mm which might be from hughd(a)google.com are mm-fix-folio_expected_ref_count-when-pg_private_2.patch mm-gup-check-ref_count-instead-of-lru-before-migration.patch mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all.patch mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch.patch mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test.patch mm-folio_may_be_cached-unless-folio_test_large.patch mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

3 months, 3 weeks

2
1
0 0

PCI: dwc: Ensure that dw_pcie_wait_for_link() waits 100 ms after link up

by Marek Vasut

Please backport the following commit into Linux v5.4 and newer stable releases: 80dc18a0cba8dea42614f021b20a04354b213d86 The backport will likely depend on macro rename commit: 817f989700fddefa56e5e443e7d138018ca6709d This part of commit description clarifies why this is a fix: " As per PCIe r6.0, sec 6.6.1, a Downstream Port that supports Link speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms after Link training completes before sending a Configuration Request. " In practice, this makes detection of PCIe Gen3 and Gen4 SSDs reliable on Renesas R-Car V4H SoC. Without this commit, the SSDs sporadically do not get detected, or sometimes they link up in Gen1 mode. This fixes commit 886bc5ceb5cc ("PCI: designware: Add generic dw_pcie_wait_for_link()") which is in v4.5-rc1-4-g886bc5ceb5cc3 , so I think this fix should be backported to all currently maintained stable releases, i.e. v5.4+ . Thank you -- Best regards, Marek Vasut

3 months, 3 weeks

2
2
0 0

+ mm-folio_may_be_cached-unless-folio_test_large.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm: folio_may_be_cached() unless folio_test_large() has been added to the -mm mm-new branch. Its filename is mm-folio_may_be_cached-unless-folio_test_large.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-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. 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: Hugh Dickins <hughd(a)google.com> Subject: mm: folio_may_be_cached() unless folio_test_large() Date: Sun, 31 Aug 2025 02:16:25 -0700 (PDT) mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a large folio is added: so collect_longterm_unpinnable_folios() just wastes effort when calling lru_add_drain_all() on a large folio. But although there is good reason not to batch up PMD-sized folios, we might well benefit from batching a small number of low-order mTHPs (though unclear how that "small number" limitation will be implemented). So ask if folio_may_be_cached() rather than !folio_test_large(), to insulate those particular checks from future change. Name preferred to "folio_is_batchable" because large folios can well be put on a batch: it's just the per-CPU LRU caches, drained much later, which need care. Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Link: https://lkml.kernel.org/r/861c061c-51cd-b940-49df-9f55e1fee2c8@google.com Signed-off-by: Hugh Dickins <hughd(a)google.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Cc: <stable(a)vger.kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/swap.h | 10 ++++++++++ mm/gup.c | 5 +++-- mm/mlock.c | 6 +++--- mm/swap.c | 2 +- 4 files changed, 17 insertions(+), 6 deletions(-) --- a/include/linux/swap.h~mm-folio_may_be_cached-unless-folio_test_large +++ a/include/linux/swap.h @@ -381,6 +381,16 @@ void folio_add_lru_vma(struct folio *, s void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) --- a/mm/gup.c~mm-folio_may_be_cached-unless-folio_test_large +++ a/mm/gup.c @@ -2309,8 +2309,9 @@ static unsigned long collect_longterm_un continue; } - if (drain_allow && folio_ref_count(folio) != - folio_expected_ref_count(folio) + 1) { + if (drain_allow && folio_may_be_cached(folio) && + folio_ref_count(folio) != + folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); drain_allow = false; } --- a/mm/mlock.c~mm-folio_may_be_cached-unless-folio_test_large +++ a/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } --- a/mm/swap.c~mm-folio_may_be_cached-unless-folio_test_large +++ a/mm/swap.c @@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(s local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) _ Patches currently in -mm which might be from hughd(a)google.com are mm-fix-folio_expected_ref_count-when-pg_private_2.patch mm-gup-check-ref_count-instead-of-lru-before-migration.patch mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all.patch mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch.patch mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test.patch mm-folio_may_be_cached-unless-folio_test_large.patch mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

3 months, 3 weeks

1
0
0 0

+ mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm: Revert "mm: vmscan.c: fix OOM on swap stress test" has been added to the -mm mm-new branch. Its filename is mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test.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-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. 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: Hugh Dickins <hughd(a)google.com> Subject: mm: Revert "mm: vmscan.c: fix OOM on swap stress test" Date: Sun, 31 Aug 2025 02:13:55 -0700 (PDT) This reverts commit 0885ef4705607936fc36a38fd74356e1c465b023: that was a fix to the reverted 33dfe9204f29b415bbc0abb1a50642d1ba94f5e9. Link: https://lkml.kernel.org/r/bd440614-3d2c-31d6-1b8f-9635c69cef7c@google.com Fixes: 0885ef470560 ("mm: vmscan.c: fix OOM on swap stress test") Signed-off-by: Hugh Dickins <hughd(a)google.com> Cc: <stable(a)vger.kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Jason Gunthorpe <jgg(a)ziepe.ca> Cc: Johannes Weiner <hannes(a)cmpxchg.org> Cc: John Hubbard <jhubbard(a)nvidia.com> Cc: Keir Fraser <keirf(a)google.com> Cc: Konstantin Khlebnikov <koct9i(a)gmail.com> Cc: Li Zhe <lizhe.67(a)bytedance.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Shivank Garg <shivankg(a)amd.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Wei Xu <weixugc(a)google.com> Cc: Will Deacon <will(a)kernel.org> Cc: yangge <yangge1116(a)126.com> Cc: Yuanchu Xie <yuanchu(a)google.com> Cc: Yu Zhao <yuzhao(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/vmscan.c~mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test +++ a/mm/vmscan.c @@ -4500,7 +4500,7 @@ static bool sort_folio(struct lruvec *lr } /* ineligible */ - if (!folio_test_lru(folio) || zone > sc->reclaim_idx) { + if (zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; _ Patches currently in -mm which might be from hughd(a)google.com are mm-fix-folio_expected_ref_count-when-pg_private_2.patch mm-gup-check-ref_count-instead-of-lru-before-migration.patch mm-gup-local-lru_add_drain-to-avoid-lru_add_drain_all.patch mm-revert-mm-gup-clear-the-lru-flag-of-a-page-before-adding-to-lru-batch.patch mm-revert-mm-vmscanc-fix-oom-on-swap-stress-test.patch mm-folio_may_be_cached-unless-folio_test_large.patch mm-lru_add_drain_all-do-local-lru_add_drain-first.patch

3 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror