[PATCH v3 03/19] mm: memcg: convert vmstat slab counters to bytes

From: Roman Gushchin
Date: Wed Apr 22 2020 - 16:48:26 EST


In order to prepare for per-object slab memory accounting, convert
NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE vmstat items to bytes.

To make it obvious, rename them to NR_SLAB_RECLAIMABLE_B and
NR_SLAB_UNRECLAIMABLE_B (similar to NR_KERNEL_STACK_KB).

Internally global and per-node counters are stored in pages,
however memcg and lruvec counters are stored in bytes.
This scheme may look weird, but only for now. As soon as slab
pages will be shared between multiple cgroups, global and
node counters will reflect the total number of slab pages.
However memcg and lruvec counters will be used for per-memcg
slab memory tracking, which will take separate kernel objects
in the account. Keeping global and node counters in pages helps
to avoid additional overhead.

The size of slab memory shouldn't exceed 4Gb on 32-bit machines,
so it will fit into atomic_long_t we use for vmstats.

Signed-off-by: Roman Gushchin <guro@xxxxxx>
---
drivers/base/node.c | 4 ++--
fs/proc/meminfo.c | 4 ++--
include/linux/mmzone.h | 16 +++++++++++++---
kernel/power/snapshot.c | 2 +-
mm/memcontrol.c | 11 ++++-------
mm/oom_kill.c | 2 +-
mm/page_alloc.c | 8 ++++----
mm/slab.h | 15 ++++++++-------
mm/slab_common.c | 4 ++--
mm/slob.c | 12 ++++++------
mm/slub.c | 8 ++++----
mm/vmscan.c | 3 ++-
mm/workingset.c | 6 ++++--
13 files changed, 53 insertions(+), 42 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 9d6afb7d2ccd..b3d13fa715ad 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -368,8 +368,8 @@ static ssize_t node_read_meminfo(struct device *dev,
unsigned long sreclaimable, sunreclaimable;

si_meminfo_node(&i, nid);
- sreclaimable = node_page_state(pgdat, NR_SLAB_RECLAIMABLE);
- sunreclaimable = node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE);
+ sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
+ sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B);
n = sprintf(buf,
"Node %d MemTotal: %8lu kB\n"
"Node %d MemFree: %8lu kB\n"
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 8c1f1bb1a5ce..0811e4100084 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -53,8 +53,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
pages[lru] = global_node_page_state(NR_LRU_BASE + lru);

available = si_mem_available();
- sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
- sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
+ sreclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B);
+ sunreclaim = global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B);

show_val_kb(m, "MemTotal: ", i.totalram);
show_val_kb(m, "MemFree: ", i.freeram);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 22fe65edf425..1c68c482df6f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -171,8 +171,8 @@ enum node_stat_item {
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
- NR_SLAB_RECLAIMABLE,
- NR_SLAB_UNRECLAIMABLE,
+ NR_SLAB_RECLAIMABLE_B,
+ NR_SLAB_UNRECLAIMABLE_B,
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
WORKINGSET_NODES,
@@ -206,7 +206,17 @@ enum node_stat_item {

static __always_inline bool vmstat_item_in_bytes(enum node_stat_item item)
{
- return false;
+ /*
+ * Global and per-node slab counters track slab pages.
+ * It's expected that changes are multiples of PAGE_SIZE.
+ * Internally values are stored in pages.
+ *
+ * Per-memcg and per-lruvec counters track memory, consumed
+ * by individual slab objects. These counters are actually
+ * byte-precise.
+ */
+ return (item == NR_SLAB_RECLAIMABLE_B ||
+ item == NR_SLAB_UNRECLAIMABLE_B);
}

/*
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 659800157b17..22da1728b9cb 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1664,7 +1664,7 @@ static unsigned long minimum_image_size(unsigned long saveable)
{
unsigned long size;

- size = global_node_page_state(NR_SLAB_RECLAIMABLE)
+ size = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B)
+ global_node_page_state(NR_ACTIVE_ANON)
+ global_node_page_state(NR_INACTIVE_ANON)
+ global_node_page_state(NR_ACTIVE_FILE)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5f700fa8b78c..6cbc1f4829fc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1409,9 +1409,8 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
(u64)memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) *
1024);
seq_buf_printf(&s, "slab %llu\n",
- (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) +
- memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE)) *
- PAGE_SIZE);
+ (u64)(memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B) +
+ memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B)));
seq_buf_printf(&s, "sock %llu\n",
(u64)memcg_page_state(memcg, MEMCG_SOCK) *
PAGE_SIZE);
@@ -1445,11 +1444,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
PAGE_SIZE);

seq_buf_printf(&s, "slab_reclaimable %llu\n",
- (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE) *
- PAGE_SIZE);
+ (u64)memcg_page_state(memcg, NR_SLAB_RECLAIMABLE_B));
seq_buf_printf(&s, "slab_unreclaimable %llu\n",
- (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE) *
- PAGE_SIZE);
+ (u64)memcg_page_state(memcg, NR_SLAB_UNRECLAIMABLE_B));

/* Accumulated memory events */

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 463b3d74a64a..eb0ccb8666b0 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -184,7 +184,7 @@ static bool is_dump_unreclaim_slabs(void)
global_node_page_state(NR_ISOLATED_FILE) +
global_node_page_state(NR_UNEVICTABLE);

- return (global_node_page_state(NR_SLAB_UNRECLAIMABLE) > nr_lru);
+ return (global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B) > nr_lru);
}

/**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b48336e20bdc..a4daae53b273 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5175,8 +5175,8 @@ long si_mem_available(void)
* items that are in use, and cannot be freed. Cap this estimate at the
* low watermark.
*/
- reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) +
- global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) +
+ global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
available += reclaimable - min(reclaimable / 2, wmark_low);

if (available < 0)
@@ -5320,8 +5320,8 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
global_node_page_state(NR_FILE_DIRTY),
global_node_page_state(NR_WRITEBACK),
global_node_page_state(NR_UNSTABLE_NFS),
- global_node_page_state(NR_SLAB_RECLAIMABLE),
- global_node_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B),
+ global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
global_node_page_state(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_zone_page_state(NR_PAGETABLE),
diff --git a/mm/slab.h b/mm/slab.h
index 815e4e9a94cd..633eedb6bad1 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -272,7 +272,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
static inline int cache_vmstat_idx(struct kmem_cache *s)
{
return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
- NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE;
+ NR_SLAB_RECLAIMABLE_B : NR_SLAB_UNRECLAIMABLE_B;
}

#ifdef CONFIG_MEMCG_KMEM
@@ -361,7 +361,7 @@ static __always_inline int memcg_charge_slab(struct page *page,

if (unlikely(!memcg || mem_cgroup_is_root(memcg))) {
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
- nr_pages);
+ nr_pages << PAGE_SHIFT);
percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
return 0;
}
@@ -371,7 +371,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
goto out;

lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
- mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages);
+ mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages << PAGE_SHIFT);

/* transer try_charge() page references to kmem_cache */
percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
@@ -396,11 +396,12 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
memcg = READ_ONCE(s->memcg_params.memcg);
if (likely(!mem_cgroup_is_root(memcg))) {
lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
- mod_lruvec_state(lruvec, cache_vmstat_idx(s), -nr_pages);
+ mod_lruvec_state(lruvec, cache_vmstat_idx(s),
+ -(nr_pages << PAGE_SHIFT));
memcg_kmem_uncharge(memcg, nr_pages);
} else {
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
- -nr_pages);
+ -(nr_pages << PAGE_SHIFT));
}
rcu_read_unlock();

@@ -484,7 +485,7 @@ static __always_inline int charge_slab_page(struct page *page,
{
if (is_root_cache(s)) {
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
- 1 << order);
+ PAGE_SIZE << order);
return 0;
}

@@ -496,7 +497,7 @@ static __always_inline void uncharge_slab_page(struct page *page, int order,
{
if (is_root_cache(s)) {
mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
- -(1 << order));
+ -(PAGE_SIZE << order));
return;
}

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 9e72ba224175..b578ae29c743 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1325,8 +1325,8 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
page = alloc_pages(flags, order);
if (likely(page)) {
ret = page_address(page);
- mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
- 1 << order);
+ mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+ PAGE_SIZE << order);
}
ret = kasan_kmalloc_large(ret, size, flags);
/* As ret might get tagged, call kmemleak hook after KASAN. */
diff --git a/mm/slob.c b/mm/slob.c
index ac2aecfbc7a8..7cc9805c8091 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -202,8 +202,8 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
if (!page)
return NULL;

- mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
- 1 << order);
+ mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+ PAGE_SIZE << order);
return page_address(page);
}

@@ -214,8 +214,8 @@ static void slob_free_pages(void *b, int order)
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += 1 << order;

- mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
- -(1 << order));
+ mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+ -(PAGE_SIZE << order));
__free_pages(sp, order);
}

@@ -552,8 +552,8 @@ void kfree(const void *block)
slob_free(m, *m + align);
} else {
unsigned int order = compound_order(sp);
- mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
- -(1 << order));
+ mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+ -(PAGE_SIZE << order));
__free_pages(sp, order);

}
diff --git a/mm/slub.c b/mm/slub.c
index 914b7261e6b6..03071ae5ff07 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3898,8 +3898,8 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
page = alloc_pages_node(node, flags, order);
if (page) {
ptr = page_address(page);
- mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
- 1 << order);
+ mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+ PAGE_SIZE << order);
}

return kmalloc_large_node_hook(ptr, size, flags);
@@ -4030,8 +4030,8 @@ void kfree(const void *x)

BUG_ON(!PageCompound(page));
kfree_hook(object);
- mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
- -(1 << order));
+ mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE_B,
+ -(PAGE_SIZE << order));
__free_pages(page, order);
return;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4c3a760c0522..88aa6656aaca 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4226,7 +4226,8 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
* unmapped file backed pages.
*/
if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
- node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+ node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
+ pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;

/*
diff --git a/mm/workingset.c b/mm/workingset.c
index 474186b76ced..9358c1ee5bb6 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -467,8 +467,10 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
pages += lruvec_page_state_local(lruvec,
NR_LRU_BASE + i);
- pages += lruvec_page_state_local(lruvec, NR_SLAB_RECLAIMABLE);
- pages += lruvec_page_state_local(lruvec, NR_SLAB_UNRECLAIMABLE);
+ pages += lruvec_page_state_local(
+ lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
+ pages += lruvec_page_state_local(
+ lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
} else
#endif
pages = node_present_pages(sc->nid);
--
2.25.3