Sven reports an infinite loop in __alloc_pages_slowpath() for costly order
__GFP_RETRY_MAYFAIL allocations that are also GFP_NOIO. Such combination
can happen in a suspend/resume context where a GFP_KERNEL allocation can
have __GFP_IO masked out via gfp_allowed_mask.
Quoting Sven:
1. try to do a "costly" allocation (order > PAGE_ALLOC_COSTLY_ORDER)
with __GFP_RETRY_MAYFAIL set.
2. page alloc's __alloc_pages_slowpath tries to get a page from the
freelist. This fails because there is nothing free of that costly
order.
3. page alloc tries to reclaim by calling __alloc_pages_direct_reclaim,
which bails out because a zone is ready to be compacted; it pretends
to have made a single page of progress.
4. page alloc tries to compact, but this always bails out early because
__GFP_IO is not set (it's not passed by the snd allocator, and even
if it were, we are suspending so the __GFP_IO flag would be cleared
anyway).
5. page alloc believes reclaim progress was made (because of the
pretense in item 3) and so it checks whether it should retry
compaction. The compaction retry logic thinks it should try again,
because:
a) reclaim is needed because of the early bail-out in item 4
b) a zonelist is suitable for compaction
6. goto 2. indefinite stall.
(end quote)
The immediate root cause is confusing the COMPACT_SKIPPED returned from
__alloc_pages_direct_compact() (step 4) due to lack of __GFP_IO to be
indicating a lack of order-0 pages, and in step 5 evaluating that in
should_compact_retry() as a reason to retry, before incrementing and
limiting the number of retries. There are however other places that
wrongly assume that compaction can happen while we lack __GFP_IO.
To fix this, introduce gfp_compaction_allowed() to abstract the __GFP_IO
evaluation and switch the open-coded test in try_to_compact_pages() to use
it.
Also use the new helper in:
- compaction_ready(), which will make reclaim not bail out in step 3, so
there's at least one attempt to actually reclaim, even if chances are
small for a costly order
- in_reclaim_compaction() which will make should_continue_reclaim()
return false and we don't over-reclaim unnecessarily
- in __alloc_pages_slowpath() to set a local variable can_compact,
which is then used to avoid retrying reclaim/compaction for costly
allocations (step 5) if we can't compact and also to skip the early
compaction attempt that we do in some cases
Link: https://lkml.kernel.org/r/20240221114357.13655-2-vbabka@xxxxxxx
Fixes: 3250845d0526 ("Revert "mm, oom: prevent premature OOM killer invocation for high order request"")
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Reported-by: Sven van Ashbrook <svenva@xxxxxxxxxxxx>
Closes: https://lore.kernel.org/all/CAG-rBihs_xMKb3wrMO1%2B-%2Bp4fowP9oy1pa_OTkfxBzPUVOZF%2Bg@xxxxxxxxxxxxxx/
Tested-by: Karthikeyan Ramasubramanian <kramasub@xxxxxxxxxxxx>
Cc: Brian Geffon <bgeffon@xxxxxxxxxx>
Cc: Curtis Malainey <cujomalainey@xxxxxxxxxxxx>
Cc: Jaroslav Kysela <perex@xxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Takashi Iwai <tiwai@xxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
(cherry picked from commit 803de9000f334b771afacb6ff3e78622916668b0)
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
---
include/linux/gfp.h | 9 +++++++++
mm/compaction.c | 7 +------
mm/page_alloc.c | 10 ++++++----
mm/vmscan.c | 5 ++++-
4 files changed, 20 insertions(+), 11 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f78d1e89593f..6f8ace5c73d9 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -608,6 +608,15 @@ static inline bool pm_suspended_storage(void)
}
#endif /* CONFIG_PM_SLEEP */
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+ return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
/* The below functions must be run on a range from a single zone. */
extern int alloc_contig_range(unsigned long start, unsigned long end,
diff --git a/mm/compaction.c b/mm/compaction.c
index 5079ddbec8f9..7dc5a5d684fd 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1751,16 +1751,11 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
enum compact_priority prio)
{
- int may_perform_io = gfp_mask & __GFP_IO;
struct zoneref *z;
struct zone *zone;
enum compact_result rc = COMPACT_SKIPPED;
- /*
- * Check if the GFP flags allow compaction - GFP_NOIO is really
- * tricky context because the migration might require IO
- */
- if (!may_perform_io)
+ if (!gfp_compaction_allowed(gfp_mask))
return COMPACT_SKIPPED;
trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4553cc848abc..147b67d31431 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4099,6 +4099,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+ bool can_compact = gfp_compaction_allowed(gfp_mask);
const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
struct page *page = NULL;
unsigned int alloc_flags;
@@ -4164,7 +4165,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* Don't try this for allocations that are allowed to ignore
* watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
*/
- if (can_direct_reclaim &&
+ if (can_direct_reclaim && can_compact &&
(costly_order ||
(order > 0 && ac->migratetype != MIGRATE_MOVABLE))
&& !gfp_pfmemalloc_allowed(gfp_mask)) {
@@ -4251,9 +4252,10 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
/*
* Do not retry costly high order allocations unless they are
- * __GFP_RETRY_MAYFAIL
+ * __GFP_RETRY_MAYFAIL and we can compact
*/
- if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
+ if (costly_order && (!can_compact ||
+ !(gfp_mask & __GFP_RETRY_MAYFAIL)))
goto nopage;
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
@@ -4266,7 +4268,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* implementation of the compaction depends on the sufficient amount
* of free memory (see __compaction_suitable)
*/
- if (did_some_progress > 0 &&
+ if (did_some_progress > 0 && can_compact &&
should_compact_retry(ac, order, alloc_flags,
compact_result, &compact_priority,
&compaction_retries))
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7d7f6d65bd5..b23016615c54 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2595,7 +2595,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
/* Use reclaim/compaction for costly allocs or under memory pressure */
static bool in_reclaim_compaction(struct scan_control *sc)
{
- if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+ if (gfp_compaction_allowed(sc->gfp_mask) && sc->order &&
(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
sc->priority < DEF_PRIORITY - 2))
return true;
@@ -2869,6 +2869,9 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
unsigned long watermark;
enum compact_result suitable;
+ if (!gfp_compaction_allowed(sc->gfp_mask))
+ return false;
+
suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
if (suitable == COMPACT_SUCCESS)
/* Allocation should succeed already. Don't reclaim. */
--
2.44.0
