Since we are not allowed to depend on blocking memory allocations when
oom_lock is already held, teach lockdep to consider that blocking memory
allocations might wait for oom_lock at as early location as possible, and
teach lockdep to consider that oom_lock is held by mutex_lock() than by
mutex_trylock().
Also, since the OOM killer is disabled until the OOM reaper or exit_mmap()
sets MMF_OOM_SKIP, teach lockdep to consider that oom_lock is held when
__oom_reap_task_mm() is called.
This patch should not cause lockdep splats unless there is somebody doing
dangerous things (e.g. from OOM notifiers, from the OOM reaper).
Signed-off-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
---
mm/oom_kill.c | 9 ++++++++-
mm/page_alloc.c | 13 +++++++++++++
2 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3a24848..759aa4e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -513,6 +513,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
*/
set_bit(MMF_UNSTABLE, &mm->flags);
+ mutex_acquire(&oom_lock.dep_map, 0, 0, _THIS_IP_);
for (vma = mm->mmap ; vma; vma = vma->vm_next) {
if (!can_madv_dontneed_vma(vma))
continue;
@@ -544,6 +545,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm)
tlb_finish_mmu(&tlb, range.start, range.end);
}
}
+ mutex_release(&oom_lock.dep_map, 1, _THIS_IP_);
return ret;
}
@@ -1120,8 +1122,13 @@ void pagefault_out_of_memory(void)
if (mem_cgroup_oom_synchronize(true))
return;
- if (!mutex_trylock(&oom_lock))
+ if (!mutex_trylock(&oom_lock)) {
+ mutex_acquire(&oom_lock.dep_map, 0, 0, _THIS_IP_);
+ mutex_release(&oom_lock.dep_map, 1, _THIS_IP_);
return;
+ }
+ mutex_release(&oom_lock.dep_map, 1, _THIS_IP_);
+ mutex_acquire(&oom_lock.dep_map, 0, 0, _THIS_IP_);
out_of_memory(&oc);
mutex_unlock(&oom_lock);
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6d0fa5b..25533214 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3793,6 +3793,8 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
schedule_timeout_uninterruptible(1);
return NULL;
}
+ mutex_release(&oom_lock.dep_map, 1, _THIS_IP_);
+ mutex_acquire(&oom_lock.dep_map, 0, 0, _THIS_IP_);
/*
* Go through the zonelist yet one more time, keep very high watermark
@@ -4651,6 +4653,17 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
fs_reclaim_acquire(gfp_mask);
fs_reclaim_release(gfp_mask);
+ /*
+ * Allocation requests which can call __alloc_pages_may_oom() might
+ * fail to bail out due to waiting for oom_lock.
+ */
+ if ((gfp_mask & __GFP_DIRECT_RECLAIM) && !(gfp_mask & __GFP_NORETRY) &&
+ (!(gfp_mask & __GFP_RETRY_MAYFAIL) ||
+ order <= PAGE_ALLOC_COSTLY_ORDER)) {
+ mutex_acquire(&oom_lock.dep_map, 0, 0, _THIS_IP_);
+ mutex_release(&oom_lock.dep_map, 1, _THIS_IP_);
+ }
+
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
--
1.8.3.1
