* + memcg-dynamically-allocate-lruvec_stats.patch added to mm-unstable branch
@ 2024-04-29 17:19 Andrew Morton
0 siblings, 0 replies; 2+ messages in thread
From: Andrew Morton @ 2024-04-29 17:19 UTC (permalink / raw)
To: mm-commits, yosryahmed, roman.gushchin, muchun.song, mhocko,
hannes, shakeel.butt, akpm
The patch titled
Subject: memcg: dynamically allocate lruvec_stats
has been added to the -mm mm-unstable branch. Its filename is
memcg-dynamically-allocate-lruvec_stats.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/memcg-dynamically-allocate-lruvec_stats.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Shakeel Butt <shakeel.butt@linux.dev>
Subject: memcg: dynamically allocate lruvec_stats
Date: Fri, 26 Apr 2024 17:37:28 -0700
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.
Link: https://lkml.kernel.org/r/20240427003733.3898961-3-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memcontrol.h | 62 ++----------------------
mm/memcontrol.c | 87 ++++++++++++++++++++++++++++++-----
2 files changed, 81 insertions(+), 68 deletions(-)
--- a/include/linux/memcontrol.h~memcg-dynamically-allocate-lruvec_stats
+++ a/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(
}
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);
--- a/mm/memcontrol.c~memcg-dynamically-allocate-lruvec_stats
+++ a/mm/memcontrol.c
@@ -575,6 +575,60 @@ mem_cgroup_largest_soft_limit_node(struc
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,
@@ -5487,18 +5541,25 @@ static int alloc_mem_cgroup_per_node_inf
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)
@@ -5509,6 +5570,7 @@ static void free_mem_cgroup_per_node_inf
return;
free_percpu(pn->lruvec_stats_percpu);
+ kfree(pn->lruvec_stats);
kfree(pn);
}
@@ -5861,18 +5923,19 @@ static void mem_cgroup_css_rstat_flush(s
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]);
@@ -5883,12 +5946,12 @@ static void mem_cgroup_css_rstat_flush(s
}
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;
}
}
}
_
Patches currently in -mm which might be from shakeel.butt@linux.dev are
memcg-simple-cleanup-of-stats-update-functions.patch
memcg-reduce-memory-size-of-mem_cgroup_events_index.patch
memcg-dynamically-allocate-lruvec_stats.patch
memcg-reduce-memory-for-the-lruvec-and-memcg-stats.patch
memcg-cleanup-__mod_memcg_lruvec_state.patch
memcg-pr_warn_once-for-unexpected-events-and-stats.patch
memcg-use-proper-type-for-mod_memcg_state.patch
mm-cleanup-workingset_nodes-in-workingset.patch
^ permalink raw reply [flat|nested] 2+ messages in thread* + memcg-dynamically-allocate-lruvec_stats.patch added to mm-unstable branch
@ 2024-05-02 15:35 Andrew Morton
0 siblings, 0 replies; 2+ messages in thread
From: Andrew Morton @ 2024-05-02 15:35 UTC (permalink / raw)
To: mm-commits, yosryahmed, tjmercier, roman.gushchin, muchun.song,
mhocko, hannes, shakeel.butt, akpm
The patch titled
Subject: memcg: dynamically allocate lruvec_stats
has been added to the -mm mm-unstable branch. Its filename is
memcg-dynamically-allocate-lruvec_stats.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/memcg-dynamically-allocate-lruvec_stats.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Shakeel Butt <shakeel.butt@linux.dev>
Subject: memcg: dynamically allocate lruvec_stats
Date: Wed, 1 May 2024 10:26:11 -0700
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.
Link: https://lkml.kernel.org/r/20240501172617.678560-3-shakeel.butt@linux.dev
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: T.J. Mercier <tjmercier@google.com>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
include/linux/memcontrol.h | 62 ++----------------------
mm/memcontrol.c | 87 ++++++++++++++++++++++++++++++-----
2 files changed, 81 insertions(+), 68 deletions(-)
--- a/include/linux/memcontrol.h~memcg-dynamically-allocate-lruvec_stats
+++ a/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(
}
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);
--- a/mm/memcontrol.c~memcg-dynamically-allocate-lruvec_stats
+++ a/mm/memcontrol.c
@@ -575,6 +575,60 @@ mem_cgroup_largest_soft_limit_node(struc
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,
@@ -5486,18 +5540,25 @@ static int alloc_mem_cgroup_per_node_inf
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)
@@ -5508,6 +5569,7 @@ static void free_mem_cgroup_per_node_inf
return;
free_percpu(pn->lruvec_stats_percpu);
+ kfree(pn->lruvec_stats);
kfree(pn);
}
@@ -5860,18 +5922,19 @@ static void mem_cgroup_css_rstat_flush(s
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]);
@@ -5882,12 +5945,12 @@ static void mem_cgroup_css_rstat_flush(s
}
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;
}
}
}
_
Patches currently in -mm which might be from shakeel.butt@linux.dev are
memcg-simple-cleanup-of-stats-update-functions.patch
memcg-reduce-memory-size-of-mem_cgroup_events_index.patch
memcg-dynamically-allocate-lruvec_stats.patch
memcg-reduce-memory-for-the-lruvec-and-memcg-stats.patch
memcg-cleanup-__mod_memcg_lruvec_state.patch
mm-cleanup-workingset_nodes-in-workingset.patch
memcg-warn-for-unexpected-events-and-stats.patch
memcg-use-proper-type-for-mod_memcg_state.patch
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2024-05-02 15:35 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-04-29 17:19 + memcg-dynamically-allocate-lruvec_stats.patch added to mm-unstable branch Andrew Morton
-- strict thread matches above, loose matches on Subject: below --
2024-05-02 15:35 Andrew Morton
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.