July 2024 - Linux-stable-mirror

[PATCH 6.6] sched: Move psi_account_irqtime() out of update_rq_clock_task() hotpath

by John Stultz

commit ddae0ca2a8fe12d0e24ab10ba759c3fbd755ada8 upstream. It was reported that in moving to 6.1, a larger then 10% regression was seen in the performance of clock_gettime(CLOCK_THREAD_CPUTIME_ID,...). Using a simple reproducer, I found: 5.10: 100000000 calls in 24345994193 ns => 243.460 ns per call 100000000 calls in 24288172050 ns => 242.882 ns per call 100000000 calls in 24289135225 ns => 242.891 ns per call 6.1: 100000000 calls in 28248646742 ns => 282.486 ns per call 100000000 calls in 28227055067 ns => 282.271 ns per call 100000000 calls in 28177471287 ns => 281.775 ns per call The cause of this was finally narrowed down to the addition of psi_account_irqtime() in update_rq_clock_task(), in commit 52b1364ba0b1 ("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure"). In my initial attempt to resolve this, I leaned towards moving all accounting work out of the clock_gettime() call path, but it wasn't very pretty, so it will have to wait for a later deeper rework. Instead, Peter shared this approach: Rework psi_account_irqtime() to use its own psi_irq_time base for accounting, and move it out of the hotpath, calling it instead from sched_tick() and __schedule(). In testing this, we found the importance of ensuring psi_account_irqtime() is run under the rq_lock, which Johannes Weiner helpfully explained, so also add some lockdep annotations to make that requirement clear. With this change the performance is back in-line with 5.10: 6.1+fix: 100000000 calls in 24297324597 ns => 242.973 ns per call 100000000 calls in 24318869234 ns => 243.189 ns per call 100000000 calls in 24291564588 ns => 242.916 ns per call Reported-by: Jimmy Shiu <jimmyshiu(a)google.com> Originally-by: Peter Zijlstra <peterz(a)infradead.org> Signed-off-by: John Stultz <jstultz(a)google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: Chengming Zhou <chengming.zhou(a)linux.dev> Reviewed-by: Qais Yousef <qyousef(a)layalina.io> Link: https://lore.kernel.org/r/20240618215909.4099720-1-jstultz@google.com Fixes: 52b1364ba0b1 ("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure") [jstultz: Fixed up minor collisions w/ 6.6-stable] Signed-off-by: John Stultz <jstultz(a)google.com> --- kernel/sched/core.c | 7 +++++-- kernel/sched/psi.c | 21 ++++++++++++++++----- kernel/sched/sched.h | 1 + kernel/sched/stats.h | 11 ++++++++--- 4 files changed, 30 insertions(+), 10 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index dcb30e304871..820880960513 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -722,7 +722,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; - psi_account_irqtime(rq->curr, irq_delta); delayacct_irq(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING @@ -5641,7 +5640,7 @@ void scheduler_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); - struct task_struct *curr = rq->curr; + struct task_struct *curr; struct rq_flags rf; unsigned long thermal_pressure; u64 resched_latency; @@ -5653,6 +5652,9 @@ void scheduler_tick(void) rq_lock(rq, &rf); + curr = rq->curr; + psi_account_irqtime(rq, curr, NULL); + update_rq_clock(rq); thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure); @@ -6690,6 +6692,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) ++*switch_count; migrate_disable_switch(rq, prev); + psi_account_irqtime(rq, prev, next); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 1d0f634725a6..431971acc763 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -784,6 +784,7 @@ static void psi_group_change(struct psi_group *group, int cpu, enum psi_states s; u32 state_mask; + lockdep_assert_rq_held(cpu_rq(cpu)); groupc = per_cpu_ptr(group->pcpu, cpu); /* @@ -1002,19 +1003,29 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, } #ifdef CONFIG_IRQ_TIME_ACCOUNTING -void psi_account_irqtime(struct task_struct *task, u32 delta) +void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev) { - int cpu = task_cpu(task); + int cpu = task_cpu(curr); struct psi_group *group; struct psi_group_cpu *groupc; - u64 now; + u64 now, irq; + s64 delta; - if (!task->pid) + if (!curr->pid) + return; + + lockdep_assert_rq_held(rq); + group = task_psi_group(curr); + if (prev && task_psi_group(prev) == group) return; now = cpu_clock(cpu); + irq = irq_time_read(cpu); + delta = (s64)(irq - rq->psi_irq_time); + if (delta < 0) + return; + rq->psi_irq_time = irq; - group = task_psi_group(task); do { if (!group->enabled) continue; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 35c38daa2d3e..2e8f26a919ed 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1094,6 +1094,7 @@ struct rq { #ifdef CONFIG_IRQ_TIME_ACCOUNTING u64 prev_irq_time; + u64 psi_irq_time; #endif #ifdef CONFIG_PARAVIRT u64 prev_steal_time; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 38f3698f5e5b..b02dfc322951 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -110,8 +110,12 @@ __schedstats_from_se(struct sched_entity *se) void psi_task_change(struct task_struct *task, int clear, int set); void psi_task_switch(struct task_struct *prev, struct task_struct *next, bool sleep); -void psi_account_irqtime(struct task_struct *task, u32 delta); - +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev); +#else +static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr, + struct task_struct *prev) {} +#endif /*CONFIG_IRQ_TIME_ACCOUNTING */ /* * PSI tracks state that persists across sleeps, such as iowaits and * memory stalls. As a result, it has to distinguish between sleeps, @@ -192,7 +196,8 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) {} static inline void psi_sched_switch(struct task_struct *prev, struct task_struct *next, bool sleep) {} -static inline void psi_account_irqtime(struct task_struct *task, u32 delta) {} +static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr, + struct task_struct *prev) {} #endif /* CONFIG_PSI */ #ifdef CONFIG_SCHED_INFO -- 2.45.2.993.g49e7a77208-goog

7 months, 3 weeks

1
0
0 0

+ mm-mglru-fix-ineffective-protection-calculation.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm/mglru: fix ineffective protection calculation has been added to the -mm mm-unstable branch. Its filename is mm-mglru-fix-ineffective-protection-calculation.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-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: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: fix ineffective protection calculation Date: Fri, 12 Jul 2024 17:29:56 -0600 mem_cgroup_calculate_protection() is not stateless and should only be used as part of a top-down tree traversal. shrink_one() traverses the per-node memcg LRU instead of the root_mem_cgroup tree, and therefore it should not call mem_cgroup_calculate_protection(). The existing misuse in shrink_one() can cause ineffective protection of sub-trees that are grandchildren of root_mem_cgroup. Fix it by reusing lru_gen_age_node(), which already traverses the root_mem_cgroup tree, to calculate the protection. Previously lru_gen_age_node() opportunistically skips the first pass, i.e., when scan_control->priority is DEF_PRIORITY. On the second pass, lruvec_is_sizable() uses appropriate scan_control->priority, set by set_initial_priority() from lru_gen_shrink_node(), to decide whether a memcg is too small to reclaim from. Now lru_gen_age_node() unconditionally traverses the root_mem_cgroup tree. So it should call set_initial_priority() upfront, to make sure lruvec_is_sizable() uses appropriate scan_control->priority on the first pass. Otherwise, lruvec_is_reclaimable() can return false negatives and result in premature OOM kills when min_ttl_ms is used. Link: https://lkml.kernel.org/r/20240712232956.1427127-1-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reported-by: T.J. Mercier <tjmercier(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 82 +++++++++++++++++++++++--------------------------- 1 file changed, 38 insertions(+), 44 deletions(-) --- a/mm/vmscan.c~mm-mglru-fix-ineffective-protection-calculation +++ a/mm/vmscan.c @@ -3915,6 +3915,32 @@ done: * working set protection ******************************************************************************/ +static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) +{ + int priority; + unsigned long reclaimable; + + if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) + return; + /* + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. + */ + reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) + reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); + + /* round down reclaimable and round up sc->nr_to_reclaim */ + priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); + + /* + * The estimation is based on LRU pages only, so cap it to prevent + * overshoots of shrinker objects by large margins. + */ + sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); +} + static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc) { int gen, type, zone; @@ -3948,19 +3974,17 @@ static bool lruvec_is_reclaimable(struct struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); - /* see the comment on lru_gen_folio */ - gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); - birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); - - if (time_is_after_jiffies(birth + min_ttl)) + if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; - mem_cgroup_calculate_protection(NULL, memcg); + /* see the comment on lru_gen_folio */ + gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); + birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); - return !mem_cgroup_below_min(NULL, memcg); + return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ @@ -3970,23 +3994,20 @@ static void lru_gen_age_node(struct pgli { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); + bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); - /* check the order to exclude compaction-induced reclaim */ - if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY) - return; + set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) { - mem_cgroup_iter_break(NULL, memcg); - return; - } + mem_cgroup_calculate_protection(NULL, memcg); - cond_resched(); + if (!reclaimable) + reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* @@ -3994,7 +4015,7 @@ static void lru_gen_age_node(struct pgli * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ - if (mutex_trylock(&oom_lock)) { + if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; @@ -4786,8 +4807,7 @@ static int shrink_one(struct lruvec *lru struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - mem_cgroup_calculate_protection(NULL, memcg); - + /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; @@ -4911,32 +4931,6 @@ static void lru_gen_shrink_lruvec(struct blk_finish_plug(&plug); } -static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc) -{ - int priority; - unsigned long reclaimable; - - if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) - return; - /* - * Determine the initial priority based on - * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, - * where reclaimed_to_scanned_ratio = inactive / total. - */ - reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); - if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc)) - reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - - /* round down reclaimable and round up sc->nr_to_reclaim */ - priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); - - /* - * The estimation is based on LRU pages only, so cap it to prevent - * overshoots of shrinker objects by large margins. - */ - sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY); -} - static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc) { struct blk_plug plug; _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-mglru-fix-ineffective-protection-calculation.patch

7 months, 3 weeks

1
0
0 0

+ mm-mglru-fix-ineffective-protection-calculation.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/mglru: fix ineffective protection calculation has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-mglru-fix-ineffective-protection-calculation.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: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: fix ineffective protection calculation Date: Fri, 12 Jul 2024 17:29:56 -0600 mem_cgroup_calculate_protection() is not stateless and should only be used as part of a top-down tree traversal. shrink_one() traverses the per-node memcg LRU instead of the root_mem_cgroup tree, and therefore it should not call mem_cgroup_calculate_protection(). The existing misuse in shrink_one() can cause ineffective protection of sub-trees that are grandchildren of root_mem_cgroup. Fix it by reusing lru_gen_age_node(), which already traverses the root_mem_cgroup tree, to calculate the protection. Previously lru_gen_age_node() opportunistically skips the first pass, i.e., when scan_control->priority is DEF_PRIORITY. On the second pass, lruvec_is_sizable() uses appropriate scan_control->priority, set by set_initial_priority() from lru_gen_shrink_node(), to decide whether a memcg is too small to reclaim from. Now lru_gen_age_node() unconditionally traverses the root_mem_cgroup tree. So it should call set_initial_priority() upfront, to make sure lruvec_is_sizable() uses appropriate scan_control->priority on the first pass. Otherwise, lruvec_is_reclaimable() can return false negatives and result in premature OOM kills when min_ttl_ms is used. Link: https://lkml.kernel.org/r/20240712232956.1427127-1-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reported-by: T.J. Mercier <tjmercier(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 30 ++++++++++++------------------ 1 file changed, 12 insertions(+), 18 deletions(-) --- a/mm/vmscan.c~mm-mglru-fix-ineffective-protection-calculation +++ a/mm/vmscan.c @@ -3933,19 +3933,17 @@ static bool lruvec_is_reclaimable(struct struct mem_cgroup *memcg = lruvec_memcg(lruvec); DEFINE_MIN_SEQ(lruvec); - /* see the comment on lru_gen_folio */ - gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); - birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); - - if (time_is_after_jiffies(birth + min_ttl)) + if (mem_cgroup_below_min(NULL, memcg)) return false; if (!lruvec_is_sizable(lruvec, sc)) return false; - mem_cgroup_calculate_protection(NULL, memcg); + /* see the comment on lru_gen_folio */ + gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]); + birth = READ_ONCE(lruvec->lrugen.timestamps[gen]); - return !mem_cgroup_below_min(NULL, memcg); + return time_is_before_jiffies(birth + min_ttl); } /* to protect the working set of the last N jiffies */ @@ -3955,23 +3953,20 @@ static void lru_gen_age_node(struct pgli { struct mem_cgroup *memcg; unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl); + bool reclaimable = !min_ttl; VM_WARN_ON_ONCE(!current_is_kswapd()); - /* check the order to exclude compaction-induced reclaim */ - if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY) - return; + set_initial_priority(pgdat, sc); memcg = mem_cgroup_iter(NULL, NULL, NULL); do { struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat); - if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) { - mem_cgroup_iter_break(NULL, memcg); - return; - } + mem_cgroup_calculate_protection(NULL, memcg); - cond_resched(); + if (!reclaimable) + reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl); } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL))); /* @@ -3979,7 +3974,7 @@ static void lru_gen_age_node(struct pgli * younger than min_ttl. However, another possibility is all memcgs are * either too small or below min. */ - if (mutex_trylock(&oom_lock)) { + if (!reclaimable && mutex_trylock(&oom_lock)) { struct oom_control oc = { .gfp_mask = sc->gfp_mask, }; @@ -4772,8 +4767,7 @@ static int shrink_one(struct lruvec *lru struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - mem_cgroup_calculate_protection(NULL, memcg); - + /* lru_gen_age_node() called mem_cgroup_calculate_protection() */ if (mem_cgroup_below_min(NULL, memcg)) return MEMCG_LRU_YOUNG; _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-mglru-fix-ineffective-protection-calculation.patch

7 months, 3 weeks

1
0
0 0

+ mm-huge_memory-avoid-pmd-size-page-cache-if-needed.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/huge_memory: avoid PMD-size page cache if needed has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-huge_memory-avoid-pmd-size-page-cache-if-needed.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: Gavin Shan <gshan(a)redhat.com> Subject: mm/huge_memory: avoid PMD-size page cache if needed Date: Mon, 15 Jul 2024 10:04:23 +1000 xarray can't support arbitrary page cache size. the largest and supported page cache size is defined as MAX_PAGECACHE_ORDER by commit 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable to xarray"). However, it's possible to have 512MB page cache in the huge memory's collapsing path on ARM64 system whose base page size is 64KB. 512MB page cache is breaking the limitation and a warning is raised when the xarray entry is split as shown in the following example. [root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize KernelPageSize: 64 kB [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c : int main(int argc, char **argv) { const char *filename = TEST_XFS_FILENAME; int fd = 0; void *buf = (void *)-1, *p; int pgsize = getpagesize(); int ret = 0; if (pgsize != 0x10000) { fprintf(stdout, "System with 64KB base page size is required!\n"); return -EPERM; } system("echo 0 > /sys/devices/virtual/bdi/253:0/read_ahead_kb"); system("echo 1 > /proc/sys/vm/drop_caches"); /* Open the xfs file */ fd = open(filename, O_RDONLY); assert(fd > 0); /* Create VMA */ buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ, MAP_SHARED, fd, 0); assert(buf != (void *)-1); fprintf(stdout, "mapped buffer at 0x%p\n", buf); /* Populate VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_NOHUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_READ); assert(ret == 0); /* Collapse VMA */ ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE); assert(ret == 0); ret = madvise(buf, TEST_MEM_SIZE, MADV_COLLAPSE); if (ret) { fprintf(stdout, "Error %d to madvise(MADV_COLLAPSE)\n", errno); goto out; } /* Split xarray entry. Write permission is needed */ munmap(buf, TEST_MEM_SIZE); buf = (void *)-1; close(fd); fd = open(filename, O_RDWR); assert(fd > 0); fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, TEST_MEM_SIZE - pgsize, pgsize); out: if (buf != (void *)-1) munmap(buf, TEST_MEM_SIZE); if (fd > 0) close(fd); return ret; } [root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test [root@dhcp-10-26-1-207 ~]# /tmp/test ------------[ cut here ]------------ WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128 Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \ nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \ nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \ ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse \ xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 virtio_net \ sha1_ce net_failover virtio_blk virtio_console failover dimlib virtio_mmio CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9 Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024 pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--) pc : xas_split_alloc+0xf8/0x128 lr : split_huge_page_to_list_to_order+0x1c4/0x780 sp : ffff8000ac32f660 x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0 x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000 x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000 x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8 x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40 x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000 Call trace: xas_split_alloc+0xf8/0x128 split_huge_page_to_list_to_order+0x1c4/0x780 truncate_inode_partial_folio+0xdc/0x160 truncate_inode_pages_range+0x1b4/0x4a8 truncate_pagecache_range+0x84/0xa0 xfs_flush_unmap_range+0x70/0x90 [xfs] xfs_file_fallocate+0xfc/0x4d8 [xfs] vfs_fallocate+0x124/0x2f0 ksys_fallocate+0x4c/0xa0 __arm64_sys_fallocate+0x24/0x38 invoke_syscall.constprop.0+0x7c/0xd8 do_el0_svc+0xb4/0xd0 el0_svc+0x44/0x1d8 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Fix it by correcting the supported page cache orders, different sets for DAX and other files. With it corrected, 512MB page cache becomes disallowed on all non-DAX files on ARM64 system where the base page size is 64KB. After this patch is applied, the test program fails with error -EINVAL returned from __thp_vma_allowable_orders() and the madvise() system call to collapse the page caches. Link: https://lkml.kernel.org/r/20240715000423.316491-1-gshan@redhat.com Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache") Signed-off-by: Gavin Shan <gshan(a)redhat.com> Acked-by: David Hildenbrand <david(a)redhat.com> Reviewed-by: Ryan Roberts <ryan.roberts(a)arm.com> Acked-by: Zi Yan <ziy(a)nvidia.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Barry Song <baohua(a)kernel.org> Cc: Don Dutile <ddutile(a)redhat.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Peter Xu <peterx(a)redhat.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: William Kucharski <william.kucharski(a)oracle.com> Cc: <stable(a)vger.kernel.org> [5.17+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/huge_mm.h | 12 +++++++++--- mm/huge_memory.c | 12 ++++++++++-- 2 files changed, 19 insertions(+), 5 deletions(-) --- a/include/linux/huge_mm.h~mm-huge_memory-avoid-pmd-size-page-cache-if-needed +++ a/include/linux/huge_mm.h @@ -72,14 +72,20 @@ extern struct kobj_attribute shmem_enabl #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* - * Mask of all large folio orders supported for file THP. + * Mask of all large folio orders supported for file THP. Folios in a DAX + * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to + * it. */ -#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DAX \ + (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DEFAULT \ + ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ -#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) +#define THP_ORDERS_ALL \ + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT) #define TVA_SMAPS (1 << 0) /* Will be used for procfs */ #define TVA_IN_PF (1 << 1) /* Page fault handler */ --- a/mm/huge_memory.c~mm-huge_memory-avoid-pmd-size-page-cache-if-needed +++ a/mm/huge_memory.c @@ -88,9 +88,17 @@ unsigned long __thp_vma_allowable_orders bool smaps = tva_flags & TVA_SMAPS; bool in_pf = tva_flags & TVA_IN_PF; bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS; + unsigned long supported_orders; + /* Check the intersection of requested and supported orders. */ - orders &= vma_is_anonymous(vma) ? - THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE; + if (vma_is_anonymous(vma)) + supported_orders = THP_ORDERS_ALL_ANON; + else if (vma_is_dax(vma)) + supported_orders = THP_ORDERS_ALL_FILE_DAX; + else + supported_orders = THP_ORDERS_ALL_FILE_DEFAULT; + + orders &= supported_orders; if (!orders) return 0; _ Patches currently in -mm which might be from gshan(a)redhat.com are mm-huge_memory-avoid-pmd-size-page-cache-if-needed.patch

7 months, 3 weeks

1
0
0 0

Request for backporting bpf patches to v6.6

by He Gao

Hi, There are two patches for bpf that I think should be backported to v6.6 kernel to fix a privilege escalation vulnerability in kernelCTF. bpf: Fix too early release of tcx_entry 1cb6f0bae50441f4b4b32a28315853b279c7404e selftests/bpf: Extend tcx tests to cover late tcx_entry release 5f1d18de79180deac2822c93e431bbe547f7d3ce Thanks! Best regards, He

7 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] mm/damon/core: merge regions aggressively when max_nr_regions" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 310d6c15e9104c99d5d9d0ff8e5383a79da7d5e6 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024071546-swerve-grew-de52@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 310d6c15e910 ("mm/damon/core: merge regions aggressively when max_nr_regions is unmet") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 310d6c15e9104c99d5d9d0ff8e5383a79da7d5e6 Mon Sep 17 00:00:00 2001 From: SeongJae Park <sj(a)kernel.org> Date: Mon, 24 Jun 2024 10:58:14 -0700 Subject: [PATCH] mm/damon/core: merge regions aggressively when max_nr_regions is unmet DAMON keeps the number of regions under max_nr_regions by skipping regions split operations when doing so can make the number higher than the limit. It works well for preventing violation of the limit. But, if somehow the violation happens, it cannot recovery well depending on the situation. In detail, if the real number of regions having different access pattern is higher than the limit, the mechanism cannot reduce the number below the limit. In such a case, the system could suffer from high monitoring overhead of DAMON. The violation can actually happen. For an example, the user could reduce max_nr_regions while DAMON is running, to be lower than the current number of regions. Fix the problem by repeating the merge operations with increasing aggressiveness in kdamond_merge_regions() for the case, until the limit is met. [sj(a)kernel.org: increase regions merge aggressiveness while respecting min_nr_regions] Link: https://lkml.kernel.org/r/20240626164753.46270-1-sj@kernel.org [sj(a)kernel.org: ensure max threshold attempt for max_nr_regions violation] Link: https://lkml.kernel.org/r/20240627163153.75969-1-sj@kernel.org Link: https://lkml.kernel.org/r/20240624175814.89611-1-sj@kernel.org Fixes: b9a6ac4e4ede ("mm/damon: adaptively adjust regions") Signed-off-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/damon/core.c b/mm/damon/core.c index 6392f1cc97a3..e66823d6b10b 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1358,14 +1358,31 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, * access frequencies are similar. This is for minimizing the monitoring * overhead under the dynamically changeable access pattern. If a merge was * unnecessarily made, later 'kdamond_split_regions()' will revert it. + * + * The total number of regions could be higher than the user-defined limit, + * max_nr_regions for some cases. For example, the user can update + * max_nr_regions to a number that lower than the current number of regions + * while DAMON is running. For such a case, repeat merging until the limit is + * met while increasing @threshold up to possible maximum level. */ static void kdamond_merge_regions(struct damon_ctx *c, unsigned int threshold, unsigned long sz_limit) { struct damon_target *t; + unsigned int nr_regions; + unsigned int max_thres; - damon_for_each_target(t, c) - damon_merge_regions_of(t, threshold, sz_limit); + max_thres = c->attrs.aggr_interval / + (c->attrs.sample_interval ? c->attrs.sample_interval : 1); + do { + nr_regions = 0; + damon_for_each_target(t, c) { + damon_merge_regions_of(t, threshold, sz_limit); + nr_regions += damon_nr_regions(t); + } + threshold = max(1, threshold * 2); + } while (nr_regions > c->attrs.max_nr_regions && + threshold / 2 < max_thres); } /*

7 months, 3 weeks

3
3
0 0

Re: Xinput Controllers No Longer Working

by Robby Knipp

I have created a bz for this issue as well - https://bugzilla.redhat.com/show_bug.cgi?id=2293600 In my digging, it seems that the 6.9+ kernels do not have the xpad kernel module (running # sudo modprobe xpad returns no value) A workaround was to manually install xone or xpad kernel module and self sign the key (keeping secure boot intact) however, this is somewhat tedious since it did work before.

7 months, 3 weeks

1
0
0 0

[PATCH] usb: gadget: u_serial: Add null pointer checks after RX/TX submission

by Kuen-Han Tsai

Commit ffd603f21423 ("usb: gadget: u_serial: Add null pointer check in gs_start_io") adds null pointer checks to gs_start_io(), but it doesn't fully fix the potential null pointer dereference issue. While gserial_connect() calls gs_start_io() with port_lock held, gs_start_rx() and gs_start_tx() release the lock during endpoint request submission. This creates a window where gs_close() could set port->port_tty to NULL, leading to a dereference when the lock is reacquired. This patch adds a null pointer check for port->port_tty after RX/TX submission, and removes the initial null pointer check in gs_start_io() since the caller must hold port_lock and guarantee non-null values for port_usb and port_tty. Fixes: ffd603f21423 ("usb: gadget: u_serial: Add null pointer check in gs_start_io") Cc: stable(a)vger.kernel.org Signed-off-by: Kuen-Han Tsai <khtsai(a)google.com> --- Explanation: CPU1: CPU2: gserial_connect() // lock gs_close() // await lock gs_start_rx() // unlock usb_ep_queue() gs_close() // lock, reset port_tty and unlock gs_start_rx() // lock tty_wakeup() // dereference Stack traces: [ 51.494375][ T278] ttyGS1: shutdown [ 51.494817][ T269] android_work: sent uevent USB_STATE=DISCONNECTED [ 52.115792][ T1508] usb: [dm_bind] generic ttyGS1: super speed IN/ep1in OUT/ep1out [ 52.516288][ T1026] android_work: sent uevent USB_STATE=CONNECTED [ 52.551667][ T1533] gserial_connect: start ttyGS1 [ 52.565634][ T1533] [khtsai] enter gs_start_io, ttyGS1, port->port.tty=0000000046bd4060 [ 52.565671][ T1533] [khtsai] gs_start_rx, unlock port ttyGS1 [ 52.591552][ T1533] [khtsai] gs_start_rx, lock port ttyGS1 [ 52.619901][ T1533] [khtsai] gs_start_rx, unlock port ttyGS1 [ 52.638659][ T1325] [khtsai] gs_close, lock port ttyGS1 [ 52.656842][ T1325] gs_close: ttyGS1 (0000000046bd4060,00000000be9750a5) ... [ 52.683005][ T1325] [khtsai] gs_close, clear ttyGS1 [ 52.683007][ T1325] gs_close: ttyGS1 (0000000046bd4060,00000000be9750a5) done! [ 52.708643][ T1325] [khtsai] gs_close, unlock port ttyGS1 [ 52.747592][ T1533] [khtsai] gs_start_rx, lock port ttyGS1 [ 52.747616][ T1533] [khtsai] gs_start_io, ttyGS1, going to call tty_wakeup(), port->port.tty=0000000000000000 [ 52.747629][ T1533] Unable to handle kernel NULL pointer dereference at virtual address 00000000000001f8 --- drivers/usb/gadget/function/u_serial.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index a92eb6d90976..2f1890c8f473 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -539,20 +539,16 @@ static int gs_alloc_requests(struct usb_ep *ep, struct list_head *head, static int gs_start_io(struct gs_port *port) { struct list_head *head = &port->read_pool; - struct usb_ep *ep; + struct usb_ep *ep = port->port_usb->out; int status; unsigned started; - if (!port->port_usb || !port->port.tty) - return -EIO; - /* Allocate RX and TX I/O buffers. We can't easily do this much * earlier (with GFP_KERNEL) because the requests are coupled to * endpoints, as are the packet sizes we'll be using. Different * configurations may use different endpoints with a given port; * and high speed vs full speed changes packet sizes too. */ - ep = port->port_usb->out; status = gs_alloc_requests(ep, head, gs_read_complete, &port->read_allocated); if (status) @@ -569,12 +565,22 @@ static int gs_start_io(struct gs_port *port) port->n_read = 0; started = gs_start_rx(port); + /* + * The TTY may be set to NULL by gs_close() after gs_start_rx() or + * gs_start_tx() release locks for endpoint request submission. + */ + if (!port->port.tty) + goto out; + if (started) { gs_start_tx(port); /* Unblock any pending writes into our circular buffer, in case * we didn't in gs_start_tx() */ + if (!port->port.tty) + goto out; tty_wakeup(port->port.tty); } else { +out: gs_free_requests(ep, head, &port->read_allocated); gs_free_requests(port->port_usb->in, &port->write_pool, &port->write_allocated); -- 2.43.0.275.g3460e3d667-goog

7 months, 3 weeks

3
7
0 0

[PATCH v3 1/2] f2fs: use meta inode for GC of atomic file

by Sunmin Jeong

The page cache of the atomic file keeps new data pages which will be stored in the COW file. It can also keep old data pages when GCing the atomic file. In this case, new data can be overwritten by old data if a GC thread sets the old data page as dirty after new data page was evicted. Also, since all writes to the atomic file are redirected to COW inodes, GC for the atomic file is not working well as below. f2fs_gc(gc_type=FG_GC) - select A as a victim segment do_garbage_collect - iget atomic file's inode for block B move_data_page f2fs_do_write_data_page - use dn of cow inode - set fio->old_blkaddr from cow inode - seg_freed is 0 since block B is still valid - goto gc_more and A is selected as victim again To solve the problem, let's separate GC writes and updates in the atomic file by using the meta inode for GC writes. 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> --- v2: - replace post_read to meta_gc fs/f2fs/data.c | 4 ++-- fs/f2fs/f2fs.h | 7 ++++++- fs/f2fs/gc.c | 6 +++--- fs/f2fs/segment.c | 6 +++--- 4 files changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index b6dcb3bcaef7..9a213d03005d 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2693,7 +2693,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) } /* wait for GCed page writeback via META_MAPPING */ - if (fio->post_read) + if (fio->meta_gc) f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); /* @@ -2788,7 +2788,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .submitted = 0, .compr_blocks = compr_blocks, .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, - .post_read = f2fs_post_read_required(inode) ? 1 : 0, + .meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, .bio = bio, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f7ee6c5e371e..796ae11c0fa3 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1211,7 +1211,7 @@ struct f2fs_io_info { unsigned int in_list:1; /* indicate fio is in io_list */ unsigned int is_por:1; /* indicate IO is from recovery or not */ unsigned int encrypted:1; /* indicate file is encrypted */ - unsigned int post_read:1; /* require post read */ + unsigned int meta_gc:1; /* require meta inode GC */ enum iostat_type io_type; /* io type */ struct writeback_control *io_wbc; /* writeback control */ struct bio **bio; /* bio for ipu */ @@ -4263,6 +4263,11 @@ static inline bool f2fs_post_read_required(struct inode *inode) f2fs_compressed_file(inode); } +static inline bool f2fs_meta_inode_gc_required(struct inode *inode) +{ + return f2fs_post_read_required(inode) || f2fs_is_atomic_file(inode); +} + /* * compress.c */ diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ef667fec9a12..cb3006551ab5 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1589,7 +1589,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_post_read_required(inode)) { + if (f2fs_meta_inode_gc_required(inode)) { int err = ra_data_block(inode, start_bidx); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -1640,7 +1640,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_post_read_required(inode)) + if (f2fs_meta_inode_gc_required(inode)) err = move_data_block(inode, start_bidx, gc_type, segno, off); else @@ -1648,7 +1648,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, segno, off); if (!err && (gc_type == FG_GC || - f2fs_post_read_required(inode))) + f2fs_meta_inode_gc_required(inode))) submitted++; if (locked) { diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 4db1add43e36..77ef46b384b4 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3851,7 +3851,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) goto drop_bio; } - if (fio->post_read) + if (fio->meta_gc) f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1); stat_inc_inplace_blocks(fio->sbi); @@ -4021,7 +4021,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; - if (!f2fs_post_read_required(inode)) + if (!f2fs_meta_inode_gc_required(inode)) return; if (!__is_valid_data_blkaddr(blkaddr)) @@ -4040,7 +4040,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); block_t i; - if (!f2fs_post_read_required(inode)) + if (!f2fs_meta_inode_gc_required(inode)) return; for (i = 0; i < len; i++) -- 2.25.1

7 months, 3 weeks

2
1
0 0

[PATCH nf] netfilter: restore default behavior for nf_conntrack_events

by Nicolas Dichtel

Since the below commit, there are regressions for legacy setups: 1/ conntracks are created while there are no listener 2/ a listener starts and dumps all conntracks to get the current state 3/ conntracks deleted before the listener has started are not advertised This is problematic in containers, where conntracks could be created early. This sysctl is part of unsafe sysctl and could not be changed easily in some environments. Let's switch back to the legacy behavior. CC: stable(a)vger.kernel.org Fixes: 90d1daa45849 ("netfilter: conntrack: add nf_conntrack_events autodetect mode") Signed-off-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com> --- Documentation/networking/nf_conntrack-sysctl.rst | 10 ++++++---- net/netfilter/nf_conntrack_ecache.c | 2 +- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index c383a394c665..edc04f99e1aa 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -34,13 +34,15 @@ nf_conntrack_count - INTEGER (read-only) nf_conntrack_events - BOOLEAN - 0 - disabled - - 1 - enabled - - 2 - auto (default) + - 1 - enabled (default) + - 2 - auto If this option is enabled, the connection tracking code will provide userspace with connection tracking events via ctnetlink. - The default allocates the extension if a userspace program is - listening to ctnetlink events. + The 'auto' allocates the extension if a userspace program is + listening to ctnetlink events. Note that conntracks created + before the first listener has started won't trigger any netlink + event. nf_conntrack_expect_max - INTEGER Maximum size of expectation table. Default value is diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 69948e1d6974..4c8559529e18 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -334,7 +334,7 @@ bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp } EXPORT_SYMBOL_GPL(nf_ct_ecache_ext_add); -#define NF_CT_EVENTS_DEFAULT 2 +#define NF_CT_EVENTS_DEFAULT 1 static int nf_ct_events __read_mostly = NF_CT_EVENTS_DEFAULT; void nf_conntrack_ecache_pernet_init(struct net *net) -- 2.43.1

7 months, 3 weeks

3
9
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2024