mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-27 12:57:53 +00:00
9ea9cb00a8
Breno and Josef report a deadlock scenario from cgroup reclaim re-entering the filesystem: [ 361.546690] ====================================================== [ 361.559210] WARNING: possible circular locking dependency detected [ 361.571703] 6.5.0-0_fbk700_debug_rc0_kbuilder_13159_gbf787a128001 #1 Tainted: G S E [ 361.589704] ------------------------------------------------------ [ 361.602277] find/9315 is trying to acquire lock: [ 361.611625] ffff88837ba140c0 (&delayed_node->mutex){+.+.}-{4:4}, at: __btrfs_release_delayed_node+0x68/0x4f0 [ 361.631437] [ 361.631437] but task is already holding lock: [ 361.643243] ffff8881765b8678 (btrfs-tree-01){++++}-{4:4}, at: btrfs_tree_read_lock+0x1e/0x40 [ 362.904457] mutex_lock_nested+0x1c/0x30 [ 362.912414] __btrfs_release_delayed_node+0x68/0x4f0 [ 362.922460] btrfs_evict_inode+0x301/0x770 [ 362.982726] evict+0x17c/0x380 [ 362.988944] prune_icache_sb+0x100/0x1d0 [ 363.005559] super_cache_scan+0x1f8/0x260 [ 363.013695] do_shrink_slab+0x2a2/0x540 [ 363.021489] shrink_slab_memcg+0x237/0x3d0 [ 363.050606] shrink_slab+0xa7/0x240 [ 363.083382] shrink_node_memcgs+0x262/0x3b0 [ 363.091870] shrink_node+0x1a4/0x720 [ 363.099150] shrink_zones+0x1f6/0x5d0 [ 363.148798] do_try_to_free_pages+0x19b/0x5e0 [ 363.157633] try_to_free_mem_cgroup_pages+0x266/0x370 [ 363.190575] reclaim_high+0x16f/0x1f0 [ 363.208409] mem_cgroup_handle_over_high+0x10b/0x270 [ 363.246678] try_charge_memcg+0xaf2/0xc70 [ 363.304151] charge_memcg+0xf0/0x350 [ 363.320070] __mem_cgroup_charge+0x28/0x40 [ 363.328371] __filemap_add_folio+0x870/0xd50 [ 363.371303] filemap_add_folio+0xdd/0x310 [ 363.399696] __filemap_get_folio+0x2fc/0x7d0 [ 363.419086] pagecache_get_page+0xe/0x30 [ 363.427048] alloc_extent_buffer+0x1cd/0x6a0 [ 363.435704] read_tree_block+0x43/0xc0 [ 363.443316] read_block_for_search+0x361/0x510 [ 363.466690] btrfs_search_slot+0xc8c/0x1520 This is caused by the mem_cgroup_handle_over_high() not respecting the gfp_mask of the allocation context. We used to only call this function on resume to userspace, where no locks were held. Butc9afe31ec4("memcg: synchronously enforce memory.high for large overcharges") added a call from the allocation context without considering the gfp. Link: https://lkml.kernel.org/r/20230914152139.100822-1-hannes@cmpxchg.org Fixes:c9afe31ec4("memcg: synchronously enforce memory.high for large overcharges") Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reported-by: Breno Leitao <leitao@debian.org> Reported-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Shakeel Butt <shakeelb@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Muchun Song <songmuchun@bytedance.com> Cc: <stable@vger.kernel.org> [5.17+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
64 lines
1.9 KiB
C
64 lines
1.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
|
|
#ifndef LINUX_RESUME_USER_MODE_H
|
|
#define LINUX_RESUME_USER_MODE_H
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/task_work.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/blk-cgroup.h>
|
|
|
|
/**
|
|
* set_notify_resume - cause resume_user_mode_work() to be called
|
|
* @task: task that will call resume_user_mode_work()
|
|
*
|
|
* Calling this arranges that @task will call resume_user_mode_work()
|
|
* before returning to user mode. If it's already running in user mode,
|
|
* it will enter the kernel and call resume_user_mode_work() soon.
|
|
* If it's blocked, it will not be woken.
|
|
*/
|
|
static inline void set_notify_resume(struct task_struct *task)
|
|
{
|
|
if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME))
|
|
kick_process(task);
|
|
}
|
|
|
|
|
|
/**
|
|
* resume_user_mode_work - Perform work before returning to user mode
|
|
* @regs: user-mode registers of @current task
|
|
*
|
|
* This is called when %TIF_NOTIFY_RESUME has been set. Now we are
|
|
* about to return to user mode, and the user state in @regs can be
|
|
* inspected or adjusted. The caller in arch code has cleared
|
|
* %TIF_NOTIFY_RESUME before the call. If the flag gets set again
|
|
* asynchronously, this will be called again before we return to
|
|
* user mode.
|
|
*
|
|
* Called without locks.
|
|
*/
|
|
static inline void resume_user_mode_work(struct pt_regs *regs)
|
|
{
|
|
clear_thread_flag(TIF_NOTIFY_RESUME);
|
|
/*
|
|
* This barrier pairs with task_work_add()->set_notify_resume() after
|
|
* hlist_add_head(task->task_works);
|
|
*/
|
|
smp_mb__after_atomic();
|
|
if (unlikely(task_work_pending(current)))
|
|
task_work_run();
|
|
|
|
#ifdef CONFIG_KEYS_REQUEST_CACHE
|
|
if (unlikely(current->cached_requested_key)) {
|
|
key_put(current->cached_requested_key);
|
|
current->cached_requested_key = NULL;
|
|
}
|
|
#endif
|
|
|
|
mem_cgroup_handle_over_high(GFP_KERNEL);
|
|
blkcg_maybe_throttle_current();
|
|
|
|
rseq_handle_notify_resume(NULL, regs);
|
|
}
|
|
|
|
#endif /* LINUX_RESUME_USER_MODE_H */
|