In order to prepare for per-object slab memory accounting,
convert NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE vmstat
items to bytes.
To make sure that these vmstats are in bytes, rename them
to NR_SLAB_RECLAIMABLE_B and NR_SLAB_UNRECLAIMABLE_B (similar to
NR_KERNEL_STACK_KB).
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 | 14 +++++++++-----
fs/proc/meminfo.c | 4 ++--
include/linux/mmzone.h | 10 ++++++++--
include/linux/vmstat.h | 8 ++++++++
kernel/power/snapshot.c | 2 +-
mm/memcontrol.c | 25 ++++++++++++++-----------
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/vmstat.c | 21 +++++++++++++++++++--
mm/workingset.c | 6 ++++--
15 files changed, 92 insertions(+), 50 deletions(-)
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 98a31bafc8a2..fa07c5806dcd 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"
@@ -505,9 +505,13 @@ static ssize_t node_read_vmstat(struct device *dev,
sum_zone_numa_state(nid, i));
#endif
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
- n += sprintf(buf+n, "%s %lu\n", node_stat_name(i),
- node_page_state(pgdat, i));
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ unsigned long x = node_page_state(pgdat, i);
+
+ if (vmstat_item_in_bytes(i))
+ x >>= PAGE_SHIFT;
+ n += sprintf(buf+n, "%s %lu\n", node_stat_name(i), x);
+ }
return 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 1c5eafd925e7..9935445786b5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -215,8 +215,8 @@ 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,
@@ -246,6 +246,12 @@ enum node_stat_item {
NR_VM_NODE_STAT_ITEMS
};
+static __always_inline bool vmstat_item_in_bytes(enum node_stat_item item)
+{
+ return (item == NR_SLAB_RECLAIMABLE_B ||
+ item == NR_SLAB_UNRECLAIMABLE_B);
+}
+
/*
* We do arithmetic on the LRU lists in various places in the code,
* so it is important to keep the active lists LRU_ACTIVE higher in
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 292485f3d24d..5b0f61b3ca75 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -200,6 +200,12 @@ static inline unsigned long global_node_page_state(enum node_stat_item item)
return x;
}
+static inline
+unsigned long global_node_page_state_pages(enum node_stat_item item)
+{
+ return global_node_page_state(item) >> PAGE_SHIFT;
+}
+
static inline unsigned long zone_page_state(struct zone *zone,
enum zone_stat_item item)
{
@@ -240,6 +246,8 @@ extern unsigned long sum_zone_node_page_state(int node,
extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
extern unsigned long node_page_state(struct pglist_data *pgdat,
enum node_stat_item item);
+extern unsigned long node_page_state_pages(struct pglist_data *pgdat,
+ enum node_stat_item item);
#else
#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
#define node_page_state(node, item) global_node_page_state(item)
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ddade80ad276..84cdeb12ac5c 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 730f230cee6a..bf846fb60d9f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -679,13 +679,16 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
*/
void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
{
- long x;
+ long x, threshold = MEMCG_CHARGE_BATCH;
if (mem_cgroup_disabled())
return;
+ if (vmstat_item_in_bytes(idx))
+ threshold <<= PAGE_SHIFT;
+
x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
- if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+ if (unlikely(abs(x) > threshold)) {
struct mem_cgroup *mi;
/*
@@ -727,7 +730,7 @@ void __mod_lruvec_memcg_state(struct lruvec *lruvec, enum node_stat_item idx,
pg_data_t *pgdat = lruvec_pgdat(lruvec);
struct mem_cgroup_per_node *pn;
struct mem_cgroup *memcg;
- long x;
+ long x, threshold = MEMCG_CHARGE_BATCH;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
memcg = pn->memcg;
@@ -738,8 +741,11 @@ void __mod_lruvec_memcg_state(struct lruvec *lruvec, enum node_stat_item idx,
/* Update lruvec */
__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+ if (vmstat_item_in_bytes(idx))
+ threshold <<= PAGE_SHIFT;
+
x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
- if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+ if (unlikely(abs(x) > threshold)) {
struct mem_cgroup_per_node *pi;
for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
@@ -1409,9 +1415,8 @@ 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 +1450,9 @@ 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 d7cc37e3f91d..93d92575245c 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 f842ebcb4600..e1b54125279a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5108,8 +5108,8 @@ 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)
@@ -5253,8 +5253,8 @@ 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 d943264f0f09..517f1f1359e5 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, 1 << order);
@@ -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 1907cb2903c7..a2afa4ff5d7b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1324,8 +1324,8 @@ 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 fa53e9f73893..8b7b56235438 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);
}
@@ -550,8 +550,8 @@ 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 f2fe3a8e420a..ed6aea234400 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3837,8 +3837,8 @@ 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);
@@ -3969,8 +3969,8 @@ 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 b1863de475fb..ec6d89cdcb73 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4251,7 +4251,8 @@ 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/vmstat.c b/mm/vmstat.c
index 6242129939dd..57dca4a5f0ea 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -344,6 +344,8 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
x = delta + __this_cpu_read(*p);
t = __this_cpu_read(pcp->stat_threshold);
+ if (vmstat_item_in_bytes(item))
+ t <<= PAGE_SHIFT;
if (unlikely(x > t || x < -t)) {
node_page_state_add(x, pgdat, item);
@@ -555,6 +557,8 @@ static inline void mod_node_state(struct pglist_data *pgdat,
* for all cpus in a node.
*/
t = this_cpu_read(pcp->stat_threshold);
+ if (vmstat_item_in_bytes(item))
+ t <<= PAGE_SHIFT;
o = this_cpu_read(*p);
n = delta + o;
@@ -999,6 +1003,12 @@ unsigned long node_page_state(struct pglist_data *pgdat,
#endif
return x;
}
+
+unsigned long node_page_state_pages(struct pglist_data *pgdat,
+ enum node_stat_item item)
+{
+ return node_page_state(pgdat, item) >> PAGE_SHIFT;
+}
#endif
#ifdef CONFIG_COMPACTION
@@ -1565,8 +1575,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
if (is_zone_first_populated(pgdat, zone)) {
seq_printf(m, "\n per-node stats");
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
+ unsigned long x = node_page_state(pgdat, i);
+
+ if (vmstat_item_in_bytes(i))
+ x >>= PAGE_SHIFT;
seq_printf(m, "\n %-12s %lu", node_stat_name(i),
- node_page_state(pgdat, i));
+ x);
}
}
seq_printf(m,
@@ -1686,8 +1700,11 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
v += NR_VM_NUMA_STAT_ITEMS;
#endif
- for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+ for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
v[i] = global_node_page_state(i);
+ if (vmstat_item_in_bytes(i))
+ v[i] >>= PAGE_SHIFT;
+ }
v += NR_VM_NODE_STAT_ITEMS;
global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
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);
--
2.24.1
