From: Shakeel Butt <shakeel.butt@linux.dev>
To: Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Michal Hocko <mhocko@kernel.org>,
Roman Gushchin <roman.gushchin@linux.dev>,
Muchun Song <muchun.song@linux.dev>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 2/7] memcg: dynamically allocate lruvec_stats
Date: Fri, 26 Apr 2024 17:37:28 -0700 [thread overview]
Message-ID: <20240427003733.3898961-3-shakeel.butt@linux.dev> (raw)
In-Reply-To: <20240427003733.3898961-1-shakeel.butt@linux.dev>
To decouple the dependency of lruvec_stats on NR_VM_NODE_STAT_ITEMS, we
need to dynamically allocate lruvec_stats in the mem_cgroup_per_node
structure. Also move the definition of lruvec_stats_percpu and
lruvec_stats and related functions to the memcontrol.c to facilitate
later patches. No functional changes in the patch.
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
---
include/linux/memcontrol.h | 62 +++------------------------
mm/memcontrol.c | 87 ++++++++++++++++++++++++++++++++------
2 files changed, 81 insertions(+), 68 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9aba0d0462ca..ab8a6e884375 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -83,6 +83,8 @@ enum mem_cgroup_events_target {
struct memcg_vmstats_percpu;
struct memcg_vmstats;
+struct lruvec_stats_percpu;
+struct lruvec_stats;
struct mem_cgroup_reclaim_iter {
struct mem_cgroup *position;
@@ -90,25 +92,6 @@ struct mem_cgroup_reclaim_iter {
unsigned int generation;
};
-struct lruvec_stats_percpu {
- /* Local (CPU and cgroup) state */
- long state[NR_VM_NODE_STAT_ITEMS];
-
- /* Delta calculation for lockless upward propagation */
- long state_prev[NR_VM_NODE_STAT_ITEMS];
-};
-
-struct lruvec_stats {
- /* Aggregated (CPU and subtree) state */
- long state[NR_VM_NODE_STAT_ITEMS];
-
- /* Non-hierarchical (CPU aggregated) state */
- long state_local[NR_VM_NODE_STAT_ITEMS];
-
- /* Pending child counts during tree propagation */
- long state_pending[NR_VM_NODE_STAT_ITEMS];
-};
-
/*
* per-node information in memory controller.
*/
@@ -116,7 +99,7 @@ struct mem_cgroup_per_node {
struct lruvec lruvec;
struct lruvec_stats_percpu __percpu *lruvec_stats_percpu;
- struct lruvec_stats lruvec_stats;
+ struct lruvec_stats *lruvec_stats;
unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
@@ -1037,42 +1020,9 @@ static inline void mod_memcg_page_state(struct page *page,
}
unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
-
-static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
- enum node_stat_item idx)
-{
- struct mem_cgroup_per_node *pn;
- long x;
-
- if (mem_cgroup_disabled())
- return node_page_state(lruvec_pgdat(lruvec), idx);
-
- pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- x = READ_ONCE(pn->lruvec_stats.state[idx]);
-#ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
-#endif
- return x;
-}
-
-static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
- enum node_stat_item idx)
-{
- struct mem_cgroup_per_node *pn;
- long x = 0;
-
- if (mem_cgroup_disabled())
- return node_page_state(lruvec_pgdat(lruvec), idx);
-
- pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
-#ifdef CONFIG_SMP
- if (x < 0)
- x = 0;
-#endif
- return x;
-}
+unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
+unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+ enum node_stat_item idx);
void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53769d06053f..5e337ed6c6bf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -576,6 +576,60 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
return mz;
}
+struct lruvec_stats_percpu {
+ /* Local (CPU and cgroup) state */
+ long state[NR_VM_NODE_STAT_ITEMS];
+
+ /* Delta calculation for lockless upward propagation */
+ long state_prev[NR_VM_NODE_STAT_ITEMS];
+};
+
+struct lruvec_stats {
+ /* Aggregated (CPU and subtree) state */
+ long state[NR_VM_NODE_STAT_ITEMS];
+
+ /* Non-hierarchical (CPU aggregated) state */
+ long state_local[NR_VM_NODE_STAT_ITEMS];
+
+ /* Pending child counts during tree propagation */
+ long state_pending[NR_VM_NODE_STAT_ITEMS];
+};
+
+unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx)
+{
+ struct mem_cgroup_per_node *pn;
+ long x;
+
+ if (mem_cgroup_disabled())
+ return node_page_state(lruvec_pgdat(lruvec), idx);
+
+ pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+ x = READ_ONCE(pn->lruvec_stats->state[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
+unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+ enum node_stat_item idx)
+{
+ struct mem_cgroup_per_node *pn;
+ long x = 0;
+
+ if (mem_cgroup_disabled())
+ return node_page_state(lruvec_pgdat(lruvec), idx);
+
+ pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+ x = READ_ONCE(pn->lruvec_stats->state_local[idx]);
+#ifdef CONFIG_SMP
+ if (x < 0)
+ x = 0;
+#endif
+ return x;
+}
+
/* Subset of vm_event_item to report for memcg event stats */
static const unsigned int memcg_vm_event_stat[] = {
PGPGIN,
@@ -5492,18 +5546,25 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
if (!pn)
return 1;
+ pn->lruvec_stats = kzalloc_node(sizeof(struct lruvec_stats), GFP_KERNEL,
+ node);
+ if (!pn->lruvec_stats)
+ goto fail;
+
pn->lruvec_stats_percpu = alloc_percpu_gfp(struct lruvec_stats_percpu,
GFP_KERNEL_ACCOUNT);
- if (!pn->lruvec_stats_percpu) {
- kfree(pn);
- return 1;
- }
+ if (!pn->lruvec_stats_percpu)
+ goto fail;
lruvec_init(&pn->lruvec);
pn->memcg = memcg;
memcg->nodeinfo[node] = pn;
return 0;
+fail:
+ kfree(pn->lruvec_stats);
+ kfree(pn);
+ return 1;
}
static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
@@ -5514,6 +5575,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
return;
free_percpu(pn->lruvec_stats_percpu);
+ kfree(pn->lruvec_stats);
kfree(pn);
}
@@ -5866,18 +5928,19 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
for_each_node_state(nid, N_MEMORY) {
struct mem_cgroup_per_node *pn = memcg->nodeinfo[nid];
- struct mem_cgroup_per_node *ppn = NULL;
+ struct lruvec_stats *lstats = pn->lruvec_stats;
+ struct lruvec_stats *plstats = NULL;
struct lruvec_stats_percpu *lstatc;
if (parent)
- ppn = parent->nodeinfo[nid];
+ plstats = parent->nodeinfo[nid]->lruvec_stats;
lstatc = per_cpu_ptr(pn->lruvec_stats_percpu, cpu);
for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
- delta = pn->lruvec_stats.state_pending[i];
+ delta = lstats->state_pending[i];
if (delta)
- pn->lruvec_stats.state_pending[i] = 0;
+ lstats->state_pending[i] = 0;
delta_cpu = 0;
v = READ_ONCE(lstatc->state[i]);
@@ -5888,12 +5951,12 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
}
if (delta_cpu)
- pn->lruvec_stats.state_local[i] += delta_cpu;
+ lstats->state_local[i] += delta_cpu;
if (delta) {
- pn->lruvec_stats.state[i] += delta;
- if (ppn)
- ppn->lruvec_stats.state_pending[i] += delta;
+ lstats->state[i] += delta;
+ if (plstats)
+ plstats->state_pending[i] += delta;
}
}
}
--
2.43.0
next prev parent reply other threads:[~2024-04-27 0:37 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-27 0:37 [PATCH v2 0/7] memcg: reduce memory consumption by memcg stats Shakeel Butt
2024-04-27 0:37 ` [PATCH v2 1/7] memcg: reduce memory size of mem_cgroup_events_index Shakeel Butt
2024-04-27 0:42 ` Yosry Ahmed
2024-04-27 1:15 ` Shakeel Butt
2024-04-29 15:36 ` Roman Gushchin
2024-04-27 0:37 ` Shakeel Butt [this message]
2024-04-27 1:23 ` [PATCH v2 2/7] memcg: dynamically allocate lruvec_stats Yosry Ahmed
2024-04-29 15:50 ` Roman Gushchin
2024-04-29 19:46 ` Shakeel Butt
2024-04-29 21:02 ` Roman Gushchin
2024-04-29 21:59 ` Shakeel Butt
2024-04-27 0:37 ` [PATCH v2 3/7] memcg: reduce memory for the lruvec and memcg stats Shakeel Butt
2024-04-27 0:51 ` Yosry Ahmed
2024-04-27 1:16 ` Shakeel Butt
2024-04-27 1:18 ` Yosry Ahmed
2024-04-29 16:00 ` Roman Gushchin
2024-04-29 20:00 ` Shakeel Butt
2024-04-29 17:35 ` T.J. Mercier
2024-04-29 20:13 ` Shakeel Butt
2024-04-29 22:23 ` T.J. Mercier
2024-04-27 0:37 ` [PATCH v2 4/7] memcg: cleanup __mod_memcg_lruvec_state Shakeel Butt
2024-04-27 0:53 ` Yosry Ahmed
2024-04-29 15:45 ` Roman Gushchin
2024-04-27 0:37 ` [PATCH v2 5/7] memcg: pr_warn_once for unexpected events and stats Shakeel Butt
2024-04-27 0:58 ` Yosry Ahmed
2024-04-27 1:18 ` Shakeel Butt
2024-04-27 14:22 ` Johannes Weiner
2024-04-29 19:54 ` Shakeel Butt
2024-04-29 16:06 ` Roman Gushchin
2024-04-29 19:56 ` Shakeel Butt
2024-04-27 0:37 ` [PATCH v2 6/7] memcg: use proper type for mod_memcg_state Shakeel Butt
2024-04-27 0:37 ` [PATCH v2 7/7] mm: cleanup WORKINGSET_NODES in workingset Shakeel Butt
2024-04-29 16:07 ` Roman Gushchin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240427003733.3898961-3-shakeel.butt@linux.dev \
--to=shakeel.butt@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=roman.gushchin@linux.dev \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.