[patch v2] mm, page_alloc: reintroduce page allocation stall warning

[David Rientjes <rientjes@google.com>]

Previously, we had warnings when a single page allocation took longer
than reasonably expected.  This was introduced in commit 63f53dea0c98
("mm: warn about allocations which stall for too long").

The warning was subsequently reverted in commit 400e22499dd9 ("mm: don't
warn about allocations which stall for too long") because it was possible
to generate memory pressure that would effectively stall further progress
through printk execution.

Page allocation stalls in excess of 10 seconds are always useful to debug
because they can result in severe userspace unresponsiveness.  Adding
this artifact can be used to correlate with userspace going out to lunch
and to understand the state of memory at the time.

There should be a reasonable expectation that this warning will never
trigger given it is very passive, it will only be emitted when a page
allocation takes longer than 10 seconds.  If it does trigger, this
reveals an issue that should be fixed: a single page allocation should
never loop for more than 10 seconds without oom killing to make memory
available.

Unlike the original implementation, this implementation only reports
stalls once for the system every 10 seconds.  Otherwise, many concurrent
reclaimers could spam the kernel log unnecessarily.  Stalls are only
reported when calling into direct reclaim.

Acked-by: Vlastimil Babka (SUSE) <vbabka@kernel.org>
Signed-off-by: David Rientjes <rientjes@google.com>
---
 v2:
  - commit message update per Michal
  - check_alloc_stall_warn() cleanup per Vlastimil

 mm/page_alloc.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -316,6 +316,14 @@ EXPORT_SYMBOL(nr_node_ids);
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+/*
+ * When page allocations stall for longer than a threshold,
+ * ALLOC_STALL_WARN_MSECS, leave a warning in the kernel log.  Only one warning
+ * will be printed during this duration for the entire system.
+ */
+#define ALLOC_STALL_WARN_MSECS (10 * 1000UL)
+static unsigned long alloc_stall_warn_jiffies;
+
 static bool page_contains_unaccepted(struct page *page, unsigned int order);
 static bool cond_accept_memory(struct zone *zone, unsigned int order,
 			       int alloc_flags);
@@ -4706,6 +4714,40 @@ check_retry_cpuset(int cpuset_mems_cookie, struct alloc_context *ac)
 	return false;
 }
 
+static void check_alloc_stall_warn(gfp_t gfp_mask, nodemask_t *nodemask,
+				unsigned int order, unsigned long alloc_start_time)
+{
+	static DEFINE_SPINLOCK(alloc_stall_lock);
+	unsigned long stall_msecs = jiffies_to_msecs(jiffies - alloc_start_time);
+
+	if (likely(stall_msecs < ALLOC_STALL_WARN_MSECS))
+		return;
+	if (time_before(jiffies, READ_ONCE(alloc_stall_warn_jiffies)))
+		return;
+	if (gfp_mask & __GFP_NOWARN)
+		return;
+
+	if (!spin_trylock(&alloc_stall_lock))
+		return;
+
+	/* Check again, this time under the lock */
+	if (time_before(jiffies, alloc_stall_warn_jiffies)) {
+		spin_unlock(&alloc_stall_lock);
+		return;
+	}
+
+	WRITE_ONCE(alloc_stall_warn_jiffies, jiffies + msecs_to_jiffies(ALLOC_STALL_WARN_MSECS));
+	spin_unlock(&alloc_stall_lock);
+
+	pr_warn("%s: page allocation stall for %lu secs: order:%d, mode:%#x(%pGg) nodemask=%*pbl",
+		current->comm, stall_msecs / MSEC_PER_SEC, order, gfp_mask, &gfp_mask,
+		nodemask_pr_args(nodemask));
+	cpuset_print_current_mems_allowed();
+	pr_cont("\n");
+	dump_stack();
+	warn_alloc_show_mem(gfp_mask, nodemask);
+}
+
 static inline struct page *
 __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 						struct alloc_context *ac)
@@ -4726,6 +4768,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int reserve_flags;
 	bool compact_first = false;
 	bool can_retry_reserves = true;
+	unsigned long alloc_start_time = jiffies;
 
 	if (unlikely(nofail)) {
 		/*
@@ -4841,6 +4884,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	if (current->flags & PF_MEMALLOC)
 		goto nopage;
 
+	/* If allocation has taken excessively long, warn about it */
+	check_alloc_stall_warn(gfp_mask, ac->nodemask, order, alloc_start_time);
+
 	/* Try direct reclaim and then allocating */
 	if (!compact_first) {
 		page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags,