From 0764db9b49c932b89ee4d9e3236dff4bb07b4a66 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 11 Feb 2022 16:32:32 -0800 Subject: mm: memcg: synchronize objcg lists with a dedicated spinlock Alexander reported a circular lock dependency revealed by the mmap1 ltp test: LOCKDEP_CIRCULAR (suite: ltp, case: mtest06 (mmap1)) WARNING: possible circular locking dependency detected 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Not tainted ------------------------------------------------------ mmap1/202299 is trying to acquire lock: 00000001892c0188 (css_set_lock){..-.}-{2:2}, at: obj_cgroup_release+0x4a/0xe0 but task is already holding lock: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sighand->siglock){-.-.}-{2:2}: __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 __lock_task_sighand+0x90/0x190 cgroup_freeze_task+0x2e/0x90 cgroup_migrate_execute+0x11c/0x608 cgroup_update_dfl_csses+0x246/0x270 cgroup_subtree_control_write+0x238/0x518 kernfs_fop_write_iter+0x13e/0x1e0 new_sync_write+0x100/0x190 vfs_write+0x22c/0x2d8 ksys_write+0x6c/0xf8 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #0 (css_set_lock){..-.}-{2:2}: check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sighand->siglock); lock(css_set_lock); lock(&sighand->siglock); lock(css_set_lock); *** DEADLOCK *** 2 locks held by mmap1/202299: #0: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 #1: 00000001892ad560 (rcu_read_lock){....}-{1:2}, at: percpu_ref_put_many.constprop.0+0x0/0x168 stack backtrace: CPU: 15 PID: 202299 Comm: mmap1 Not tainted 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Hardware name: IBM 3906 M04 704 (LPAR) Call Trace: dump_stack_lvl+0x76/0x98 check_noncircular+0x136/0x158 check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 INFO: lockdep is turned off. In this example a slab allocation from __send_signal() caused a refilling and draining of a percpu objcg stock, resulted in a releasing of another non-related objcg. Objcg release path requires taking the css_set_lock, which is used to synchronize objcg lists. This can create a circular dependency with the sighandler lock, which is taken with the locked css_set_lock by the freezer code (to freeze a task). In general it seems that using css_set_lock to synchronize objcg lists makes any slab allocations and deallocation with the locked css_set_lock and any intervened locks risky. To fix the problem and make the code more robust let's stop using css_set_lock to synchronize objcg lists and use a new dedicated spinlock instead. Link: https://lkml.kernel.org/r/Yfm1IHmoGdyUR81T@carbon.dhcp.thefacebook.com Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Roman Gushchin Reported-by: Alexander Egorenkov Tested-by: Alexander Egorenkov Reviewed-by: Waiman Long Acked-by: Tejun Heo Reviewed-by: Shakeel Butt Reviewed-by: Jeremy Linton Tested-by: Jeremy Linton Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b72d75141e12..0abbd685703b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -219,7 +219,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -315,7 +315,8 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); -- cgit v1.2.3 From 8913c61001482378d4ed8cc577b17c1ba3e847e4 Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Fri, 11 Feb 2022 16:32:35 -0800 Subject: kfence: make test case compatible with run time set sample interval The parameter kfence_sample_interval can be set via boot parameter and late shell command, which is convenient for automated tests and KFENCE parameter optimization. However, KFENCE test case just uses compile-time CONFIG_KFENCE_SAMPLE_INTERVAL, which will make KFENCE test case not run as users desired. Export kfence_sample_interval, so that KFENCE test case can use run-time-set sample interval. Link: https://lkml.kernel.org/r/20220207034432.185532-1-liupeng256@huawei.com Signed-off-by: Peng Liu Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Sumit Semwal Cc: Christian Knig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 2 ++ mm/kfence/core.c | 3 ++- mm/kfence/kfence_test.c | 8 ++++---- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 4b5e3679a72c..f49e64222628 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -17,6 +17,8 @@ #include #include +extern unsigned long kfence_sample_interval; + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 5ad40e3add45..13128fa13062 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -47,7 +47,8 @@ static bool kfence_enabled __read_mostly; -static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +EXPORT_SYMBOL_GPL(kfence_sample_interval); /* Export for test modules. */ #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index a22b1af85577..50dbb815a2a8 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -268,13 +268,13 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); /* * Especially for non-preemption kernels, ensure the allocation-gate * timer can catch up: after @resched_after, every failed allocation * attempt yields, to ensure the allocation-gate timer is scheduled. */ - resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL); + resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval); do { if (test_cache) alloc = kmem_cache_alloc(test_cache, gfp); @@ -608,7 +608,7 @@ static void test_gfpzero(struct kunit *test) int i; /* Skip if we think it'd take too long. */ - KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100); + KFENCE_TEST_REQUIRES(test, kfence_sample_interval <= 100); setup_test_cache(test, size, 0, NULL); buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); @@ -739,7 +739,7 @@ static void test_memcache_alloc_bulk(struct kunit *test) * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); do { void *objects[100]; int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects), -- cgit v1.2.3