Linux-stable-mirror September 2025

linux-stable-mirror@lists.linaro.org

590 participants
1185 discussions

[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

1 month

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

by yangshiguang1011＠163.com

1 month

[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

1 month

[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

1 month

[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

1 month

Jump to page:

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2025