Hello,
On Wed, Apr 07, 2021 at 08:57:33PM -0700, Roman Gushchin wrote:
> 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.
>
> Signed-off-by: Roman Gushchin <guro@xxxxxx>
> ---
> mm/percpu-internal.h | 2 +-
> mm/percpu-stats.c | 9 +++++++--
> mm/percpu.c | 14 +++++++-------
> 3 files changed, 15 insertions(+), 10 deletions(-)
>
> diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
> index 18b768ac7dca..095d7eaa0db4 100644
> --- 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;
> diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
> index c8400a2adbc2..f6026dbcdf6b 100644
> --- a/mm/percpu-stats.c
> +++ b/mm/percpu-stats.c
> @@ -145,6 +145,7 @@ static int percpu_stats_show(struct seq_file *m, void *v)
> 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 @@ static int percpu_stats_show(struct seq_file *m, void *v)
> 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 @@ static int percpu_stats_show(struct seq_file *m, void *v)
> 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 7e31e1b8725f..61339b3d9337 100644
> --- a/mm/percpu.c
> +++ b/mm/percpu.c
> @@ -176,10 +176,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */
> 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
> @@ -559,7 +559,7 @@ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr)
> {
> 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;
> }
>
> /*
> @@ -1835,7 +1835,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
> 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 */
> @@ -2013,7 +2013,7 @@ static void pcpu_balance_populated(enum pcpu_chunk_type type)
> 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);
> }
>
> @@ -2595,7 +2595,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
>
> /* 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 */
> --
> 2.30.2
>
This turns out to have been a more pressing issue. Thanks for fixing
this. I ran this to Linus for v5.12-rc7 [1].
https://lore.kernel.org/lkml/YHHs618ESvKhYeeM@xxxxxxxxxx/
Thanks,
Dennis
