From: Roman Gushchin <guro@xxxxxx> commit 0760fa3d8f7fceeea508b98899f1c826e10ffe78 upstream. nr_empty_pop_pages is used to guarantee that there are some free populated pages to satisfy atomic allocations. Accounted and non-accounted allocations are using separate sets of chunks, so both need to have a surplus of empty pages. This commit makes pcpu_nr_empty_pop_pages and the corresponding logic per chunk type. [Dennis] This issue came up as I was reviewing [1] and realized I missed this. Simultaneously, it was reported btrfs was seeing failed atomic allocations in fsstress tests [2] and [3]. [1] https://lore.kernel.org/linux-mm/20210324190626.564297-1-guro@xxxxxx/ [2] https://lore.kernel.org/linux-mm/20210401185158.3275.409509F4@xxxxxxxxxxxx/ [3] https://lore.kernel.org/linux-mm/CAL3q7H5RNBjCi708GH7jnczAOe0BLnacT9C+OBgA-Dx9jhB6SQ@xxxxxxxxxxxxxx/ Fixes: 3c7be18ac9a0 ("mm: memcg/percpu: account percpu memory to memory cgroups") Cc: stable@xxxxxxxxxxxxxxx # 5.9+ Signed-off-by: Roman Gushchin <guro@xxxxxx> Tested-by: Filipe Manana <fdmanana@xxxxxxxx> Signed-off-by: Dennis Zhou <dennis@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- mm/percpu-internal.h | 2 +- mm/percpu-stats.c | 9 +++++++-- mm/percpu.c | 14 +++++++------- 3 files changed, 15 insertions(+), 10 deletions(-) --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -87,7 +87,7 @@ extern spinlock_t pcpu_lock; 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; --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -145,6 +145,7 @@ static int percpu_stats_show(struct seq_ 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 @@ alloc_buffer: 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 @@ alloc_buffer: 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 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -172,10 +172,10 @@ struct list_head *pcpu_chunk_lists __ro_ 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 @@ -555,7 +555,7 @@ static inline void pcpu_update_empty_pag { 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; } /* @@ -1831,7 +1831,7 @@ area_found: 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 */ @@ -1999,7 +1999,7 @@ retry_pop: 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); } @@ -2579,7 +2579,7 @@ void __init pcpu_setup_first_chunk(const /* 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 */
