efa869b68b
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@fb.com/
[2] https://lore.kernel.org/linux-mm/20210401185158.3275.409509F4@e16-tech.com/
[3] https://lore.kernel.org/linux-mm/CAL3q7H5RNBjCi708GH7jnczAOe0BLnacT9C+OBgA-Dx9jhB6SQ@mail.gmail.com/
Fixes: 3c7be18ac9
("mm: memcg/percpu: account percpu memory to memory cgroups")
Cc: stable@vger.kernel.org # 5.9+
Signed-off-by: Roman Gushchin <guro@fb.com>
Tested-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
250 lines
6.2 KiB
C
250 lines
6.2 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* mm/percpu-debug.c
|
|
*
|
|
* Copyright (C) 2017 Facebook Inc.
|
|
* Copyright (C) 2017 Dennis Zhou <dennis@kernel.org>
|
|
*
|
|
* Prints statistics about the percpu allocator and backing chunks.
|
|
*/
|
|
#include <linux/debugfs.h>
|
|
#include <linux/list.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/seq_file.h>
|
|
#include <linux/sort.h>
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include "percpu-internal.h"
|
|
|
|
#define P(X, Y) \
|
|
seq_printf(m, " %-20s: %12lld\n", X, (long long int)Y)
|
|
|
|
struct percpu_stats pcpu_stats;
|
|
struct pcpu_alloc_info pcpu_stats_ai;
|
|
|
|
static int cmpint(const void *a, const void *b)
|
|
{
|
|
return *(int *)a - *(int *)b;
|
|
}
|
|
|
|
/*
|
|
* Iterates over all chunks to find the max nr_alloc entries.
|
|
*/
|
|
static int find_max_nr_alloc(void)
|
|
{
|
|
struct pcpu_chunk *chunk;
|
|
int slot, max_nr_alloc;
|
|
enum pcpu_chunk_type type;
|
|
|
|
max_nr_alloc = 0;
|
|
for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
|
|
for (slot = 0; slot < pcpu_nr_slots; slot++)
|
|
list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
|
|
list)
|
|
max_nr_alloc = max(max_nr_alloc,
|
|
chunk->nr_alloc);
|
|
|
|
return max_nr_alloc;
|
|
}
|
|
|
|
/*
|
|
* Prints out chunk state. Fragmentation is considered between
|
|
* the beginning of the chunk to the last allocation.
|
|
*
|
|
* All statistics are in bytes unless stated otherwise.
|
|
*/
|
|
static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
|
|
int *buffer)
|
|
{
|
|
struct pcpu_block_md *chunk_md = &chunk->chunk_md;
|
|
int i, last_alloc, as_len, start, end;
|
|
int *alloc_sizes, *p;
|
|
/* statistics */
|
|
int sum_frag = 0, max_frag = 0;
|
|
int cur_min_alloc = 0, cur_med_alloc = 0, cur_max_alloc = 0;
|
|
|
|
alloc_sizes = buffer;
|
|
|
|
/*
|
|
* find_last_bit returns the start value if nothing found.
|
|
* Therefore, we must determine if it is a failure of find_last_bit
|
|
* and set the appropriate value.
|
|
*/
|
|
last_alloc = find_last_bit(chunk->alloc_map,
|
|
pcpu_chunk_map_bits(chunk) -
|
|
chunk->end_offset / PCPU_MIN_ALLOC_SIZE - 1);
|
|
last_alloc = test_bit(last_alloc, chunk->alloc_map) ?
|
|
last_alloc + 1 : 0;
|
|
|
|
as_len = 0;
|
|
start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
|
|
|
|
/*
|
|
* If a bit is set in the allocation map, the bound_map identifies
|
|
* where the allocation ends. If the allocation is not set, the
|
|
* bound_map does not identify free areas as it is only kept accurate
|
|
* on allocation, not free.
|
|
*
|
|
* Positive values are allocations and negative values are free
|
|
* fragments.
|
|
*/
|
|
while (start < last_alloc) {
|
|
if (test_bit(start, chunk->alloc_map)) {
|
|
end = find_next_bit(chunk->bound_map, last_alloc,
|
|
start + 1);
|
|
alloc_sizes[as_len] = 1;
|
|
} else {
|
|
end = find_next_bit(chunk->alloc_map, last_alloc,
|
|
start + 1);
|
|
alloc_sizes[as_len] = -1;
|
|
}
|
|
|
|
alloc_sizes[as_len++] *= (end - start) * PCPU_MIN_ALLOC_SIZE;
|
|
|
|
start = end;
|
|
}
|
|
|
|
/*
|
|
* The negative values are free fragments and thus sorting gives the
|
|
* free fragments at the beginning in largest first order.
|
|
*/
|
|
if (as_len > 0) {
|
|
sort(alloc_sizes, as_len, sizeof(int), cmpint, NULL);
|
|
|
|
/* iterate through the unallocated fragments */
|
|
for (i = 0, p = alloc_sizes; *p < 0 && i < as_len; i++, p++) {
|
|
sum_frag -= *p;
|
|
max_frag = max(max_frag, -1 * (*p));
|
|
}
|
|
|
|
cur_min_alloc = alloc_sizes[i];
|
|
cur_med_alloc = alloc_sizes[(i + as_len - 1) / 2];
|
|
cur_max_alloc = alloc_sizes[as_len - 1];
|
|
}
|
|
|
|
P("nr_alloc", chunk->nr_alloc);
|
|
P("max_alloc_size", chunk->max_alloc_size);
|
|
P("empty_pop_pages", chunk->nr_empty_pop_pages);
|
|
P("first_bit", chunk_md->first_free);
|
|
P("free_bytes", chunk->free_bytes);
|
|
P("contig_bytes", chunk_md->contig_hint * PCPU_MIN_ALLOC_SIZE);
|
|
P("sum_frag", sum_frag);
|
|
P("max_frag", max_frag);
|
|
P("cur_min_alloc", cur_min_alloc);
|
|
P("cur_med_alloc", cur_med_alloc);
|
|
P("cur_max_alloc", cur_max_alloc);
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
P("memcg_aware", pcpu_is_memcg_chunk(pcpu_chunk_type(chunk)));
|
|
#endif
|
|
seq_putc(m, '\n');
|
|
}
|
|
|
|
static int percpu_stats_show(struct seq_file *m, void *v)
|
|
{
|
|
struct pcpu_chunk *chunk;
|
|
int slot, max_nr_alloc;
|
|
int *buffer;
|
|
enum pcpu_chunk_type type;
|
|
int nr_empty_pop_pages;
|
|
|
|
alloc_buffer:
|
|
spin_lock_irq(&pcpu_lock);
|
|
max_nr_alloc = find_max_nr_alloc();
|
|
spin_unlock_irq(&pcpu_lock);
|
|
|
|
/* there can be at most this many free and allocated fragments */
|
|
buffer = vmalloc(array_size(sizeof(int), (2 * max_nr_alloc + 1)));
|
|
if (!buffer)
|
|
return -ENOMEM;
|
|
|
|
spin_lock_irq(&pcpu_lock);
|
|
|
|
/* if the buffer allocated earlier is too small */
|
|
if (max_nr_alloc < find_max_nr_alloc()) {
|
|
spin_unlock_irq(&pcpu_lock);
|
|
vfree(buffer);
|
|
goto alloc_buffer;
|
|
}
|
|
|
|
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,
|
|
"Percpu Memory Statistics\n"
|
|
"Allocation Info:\n"
|
|
"----------------------------------------\n");
|
|
PL(unit_size);
|
|
PL(static_size);
|
|
PL(reserved_size);
|
|
PL(dyn_size);
|
|
PL(atom_size);
|
|
PL(alloc_size);
|
|
seq_putc(m, '\n');
|
|
|
|
#undef PL
|
|
|
|
#define PU(X) \
|
|
seq_printf(m, " %-20s: %12llu\n", #X, (unsigned long long)pcpu_stats.X)
|
|
|
|
seq_printf(m,
|
|
"Global Stats:\n"
|
|
"----------------------------------------\n");
|
|
PU(nr_alloc);
|
|
PU(nr_dealloc);
|
|
PU(nr_cur_alloc);
|
|
PU(nr_max_alloc);
|
|
PU(nr_chunks);
|
|
PU(nr_max_chunks);
|
|
PU(min_alloc_size);
|
|
PU(max_alloc_size);
|
|
P("empty_pop_pages", nr_empty_pop_pages);
|
|
seq_putc(m, '\n');
|
|
|
|
#undef PU
|
|
|
|
seq_printf(m,
|
|
"Per Chunk Stats:\n"
|
|
"----------------------------------------\n");
|
|
|
|
if (pcpu_reserved_chunk) {
|
|
seq_puts(m, "Chunk: <- Reserved Chunk\n");
|
|
chunk_map_stats(m, pcpu_reserved_chunk, buffer);
|
|
}
|
|
|
|
for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) {
|
|
for (slot = 0; slot < pcpu_nr_slots; slot++) {
|
|
list_for_each_entry(chunk, &pcpu_chunk_list(type)[slot],
|
|
list) {
|
|
if (chunk == pcpu_first_chunk) {
|
|
seq_puts(m, "Chunk: <- First Chunk\n");
|
|
chunk_map_stats(m, chunk, buffer);
|
|
} else {
|
|
seq_puts(m, "Chunk:\n");
|
|
chunk_map_stats(m, chunk, buffer);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
spin_unlock_irq(&pcpu_lock);
|
|
|
|
vfree(buffer);
|
|
|
|
return 0;
|
|
}
|
|
DEFINE_SHOW_ATTRIBUTE(percpu_stats);
|
|
|
|
static int __init init_percpu_stats_debugfs(void)
|
|
{
|
|
debugfs_create_file("percpu_stats", 0444, NULL, NULL,
|
|
&percpu_stats_fops);
|
|
|
|
return 0;
|
|
}
|
|
|
|
late_initcall(init_percpu_stats_debugfs);
|