mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-30 08:02:30 +00:00
mm: track mmu notifiers in fs_reclaim_acquire/release
fs_reclaim_acquire/release nicely catch recursion issues when allocating GFP_KERNEL memory against shrinkers (which gpu drivers tend to use to keep the excessive caches in check). For mmu notifier recursions we do have lockdep annotations since23b68395c7
("mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end"). But these only fire if a path actually results in some pte invalidation - for most small allocations that's very rarely the case. The other trouble is that pte invalidation can happen any time when __GFP_RECLAIM is set. Which means only really GFP_ATOMIC is a safe choice, GFP_NOIO isn't good enough to avoid potential mmu notifier recursion. I was pondering whether we should just do the general annotation, but there's always the risk for false positives. Plus I'm assuming that the core fs and io code is a lot better reviewed and tested than random mmu notifier code in drivers. Hence why I decide to only annotate for that specific case. Furthermore even if we'd create a lockdep map for direct reclaim, we'd still need to explicit pull in the mmu notifier map - there's a lot more places that do pte invalidation than just direct reclaim, these two contexts arent the same. Note that the mmu notifiers needing their own independent lockdep map is also the reason we can't hold them from fs_reclaim_acquire to fs_reclaim_release - it would nest with the acquistion in the pte invalidation code, causing a lockdep splat. And we can't remove the annotations from pte invalidation and all the other places since they're called from many other places than page reclaim. Hence we can only do the equivalent of might_lock, but on the raw lockdep map. With this we can also remove the lockdep priming added in66204f1d2d
("mm/mmu_notifiers: prime lockdep") since the new annotations are strictly more powerful. Link: https://lkml.kernel.org/r/20201125162532.1299794-2-daniel.vetter@ffwll.ch Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Qian Cai <cai@lca.pw> Cc: Thomas Hellström (Intel) <thomas_os@shipmail.org> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: David Rientjes <rientjes@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Michel Lespinasse <walken@google.com> Cc: Paul E. McKenney <paulmck@kernel.org> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Waiman Long <longman@redhat.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
871402e05b
commit
f920e413ff
2 changed files with 20 additions and 18 deletions
|
@ -612,13 +612,6 @@ int __mmu_notifier_register(struct mmu_notifier *subscription,
|
||||||
mmap_assert_write_locked(mm);
|
mmap_assert_write_locked(mm);
|
||||||
BUG_ON(atomic_read(&mm->mm_users) <= 0);
|
BUG_ON(atomic_read(&mm->mm_users) <= 0);
|
||||||
|
|
||||||
if (IS_ENABLED(CONFIG_LOCKDEP)) {
|
|
||||||
fs_reclaim_acquire(GFP_KERNEL);
|
|
||||||
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
|
|
||||||
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
|
|
||||||
fs_reclaim_release(GFP_KERNEL);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!mm->notifier_subscriptions) {
|
if (!mm->notifier_subscriptions) {
|
||||||
/*
|
/*
|
||||||
* kmalloc cannot be called under mm_take_all_locks(), but we
|
* kmalloc cannot be called under mm_take_all_locks(), but we
|
||||||
|
|
|
@ -57,6 +57,7 @@
|
||||||
#include <trace/events/oom.h>
|
#include <trace/events/oom.h>
|
||||||
#include <linux/prefetch.h>
|
#include <linux/prefetch.h>
|
||||||
#include <linux/mm_inline.h>
|
#include <linux/mm_inline.h>
|
||||||
|
#include <linux/mmu_notifier.h>
|
||||||
#include <linux/migrate.h>
|
#include <linux/migrate.h>
|
||||||
#include <linux/hugetlb.h>
|
#include <linux/hugetlb.h>
|
||||||
#include <linux/sched/rt.h>
|
#include <linux/sched/rt.h>
|
||||||
|
@ -4264,10 +4265,8 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
|
||||||
static struct lockdep_map __fs_reclaim_map =
|
static struct lockdep_map __fs_reclaim_map =
|
||||||
STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
|
STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
|
||||||
|
|
||||||
static bool __need_fs_reclaim(gfp_t gfp_mask)
|
static bool __need_reclaim(gfp_t gfp_mask)
|
||||||
{
|
{
|
||||||
gfp_mask = current_gfp_context(gfp_mask);
|
|
||||||
|
|
||||||
/* no reclaim without waiting on it */
|
/* no reclaim without waiting on it */
|
||||||
if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
|
if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
|
||||||
return false;
|
return false;
|
||||||
|
@ -4276,10 +4275,6 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
|
||||||
if (current->flags & PF_MEMALLOC)
|
if (current->flags & PF_MEMALLOC)
|
||||||
return false;
|
return false;
|
||||||
|
|
||||||
/* We're only interested __GFP_FS allocations for now */
|
|
||||||
if (!(gfp_mask & __GFP_FS))
|
|
||||||
return false;
|
|
||||||
|
|
||||||
if (gfp_mask & __GFP_NOLOCKDEP)
|
if (gfp_mask & __GFP_NOLOCKDEP)
|
||||||
return false;
|
return false;
|
||||||
|
|
||||||
|
@ -4298,15 +4293,29 @@ void __fs_reclaim_release(void)
|
||||||
|
|
||||||
void fs_reclaim_acquire(gfp_t gfp_mask)
|
void fs_reclaim_acquire(gfp_t gfp_mask)
|
||||||
{
|
{
|
||||||
if (__need_fs_reclaim(gfp_mask))
|
gfp_mask = current_gfp_context(gfp_mask);
|
||||||
__fs_reclaim_acquire();
|
|
||||||
|
if (__need_reclaim(gfp_mask)) {
|
||||||
|
if (gfp_mask & __GFP_FS)
|
||||||
|
__fs_reclaim_acquire();
|
||||||
|
|
||||||
|
#ifdef CONFIG_MMU_NOTIFIER
|
||||||
|
lock_map_acquire(&__mmu_notifier_invalidate_range_start_map);
|
||||||
|
lock_map_release(&__mmu_notifier_invalidate_range_start_map);
|
||||||
|
#endif
|
||||||
|
|
||||||
|
}
|
||||||
}
|
}
|
||||||
EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
|
EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
|
||||||
|
|
||||||
void fs_reclaim_release(gfp_t gfp_mask)
|
void fs_reclaim_release(gfp_t gfp_mask)
|
||||||
{
|
{
|
||||||
if (__need_fs_reclaim(gfp_mask))
|
gfp_mask = current_gfp_context(gfp_mask);
|
||||||
__fs_reclaim_release();
|
|
||||||
|
if (__need_reclaim(gfp_mask)) {
|
||||||
|
if (gfp_mask & __GFP_FS)
|
||||||
|
__fs_reclaim_release();
|
||||||
|
}
|
||||||
}
|
}
|
||||||
EXPORT_SYMBOL_GPL(fs_reclaim_release);
|
EXPORT_SYMBOL_GPL(fs_reclaim_release);
|
||||||
#endif
|
#endif
|
||||||
|
|
Loading…
Reference in a new issue