Merge branch 'for-5.12-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu
Pull percpu fix from Dennis Zhou:
"This contains a fix for sporadically failing atomic percpu
allocations.
I only caught it recently while I was reviewing a new series [1] and
simultaneously saw reports by btrfs in xfstests [2] and [3].
In v5.9, memcg accounting was extended to percpu done by adding a
second type of chunk. I missed an interaction with the free page float
count used to ensure we can support atomic allocations. If one type of
chunk has no free pages, but the other has enough to satisfy the free
page float requirement, we will not repopulate the free pages for the
former type of chunk. This led to the sporadically failing atomic
allocations"
Link: https://lore.kernel.org/linux-mm/20210324190626.564297-1-guro@fb.com/ [1]
Link: https://lore.kernel.org/linux-mm/20210401185158.3275.409509F4@e16-tech.com/ [2]
Link: https://lore.kernel.org/linux-mm/CAL3q7H5RNBjCi708GH7jnczAOe0BLnacT9C+OBgA-Dx9jhB6SQ@mail.gmail.com/ [3]
* 'for-5.12-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu:
percpu: make pcpu_nr_empty_pop_pages per chunk type
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index 18b768a..095d7ea 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -87,7 +87,7 @@
extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
-extern int pcpu_nr_empty_pop_pages;
+extern int pcpu_nr_empty_pop_pages[];
extern struct pcpu_chunk *pcpu_first_chunk;
extern struct pcpu_chunk *pcpu_reserved_chunk;
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index c8400a2..f6026db 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -145,6 +145,7 @@
int slot, max_nr_alloc;
int *buffer;
enum pcpu_chunk_type type;
+ int nr_empty_pop_pages;
alloc_buffer:
spin_lock_irq(&pcpu_lock);
@@ -165,7 +166,11 @@
goto alloc_buffer;
}
-#define PL(X) \
+ nr_empty_pop_pages = 0;
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type];
+
+#define PL(X) \
seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X)
seq_printf(m,
@@ -196,7 +201,7 @@
PU(nr_max_chunks);
PU(min_alloc_size);
PU(max_alloc_size);
- P("empty_pop_pages", pcpu_nr_empty_pop_pages);
+ P("empty_pop_pages", nr_empty_pop_pages);
seq_putc(m, '\n');
#undef PU
diff --git a/mm/percpu.c b/mm/percpu.c
index 6596a0a..2330811 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -173,10 +173,10 @@
static LIST_HEAD(pcpu_map_extend_chunks);
/*
- * The number of empty populated pages, protected by pcpu_lock. The
- * reserved chunk doesn't contribute to the count.
+ * The number of empty populated pages by chunk type, protected by pcpu_lock.
+ * The reserved chunk doesn't contribute to the count.
*/
-int pcpu_nr_empty_pop_pages;
+int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES];
/*
* The number of populated pages in use by the allocator, protected by
@@ -556,7 +556,7 @@
{
chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk)
- pcpu_nr_empty_pop_pages += nr;
+ pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr;
}
/*
@@ -1832,7 +1832,7 @@
mutex_unlock(&pcpu_alloc_mutex);
}
- if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+ if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
/* clear the areas and return address relative to base address */
@@ -2000,7 +2000,7 @@
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
- pcpu_nr_empty_pop_pages,
+ pcpu_nr_empty_pop_pages[type],
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
@@ -2580,7 +2580,7 @@
/* link the first chunk in */
pcpu_first_chunk = chunk;
- pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
+ pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* include all regions of the first chunk */
