[PATCH] mm/percpu, memcontrol: Per-memcg-lruvec percpu accounting

[PATCH] mm/percpu, memcontrol: Per-memcg-lruvec percpu accounting

[Joshua Hahn]

Convert MEMCG_PERCPU_B from a memcg_stat_item to a memcg_node_stat_item
to give visibility into per-node breakdowns for percpu allocations and
turn it into NR_PERCPU_B.

Because percpu memory is accounted at a sub-PAGE_SIZE level, we must
account node level statistics (accounted in PAGE_SIZE units) and
memcg-lruvec statistics separately. Account node statistics when the pcpu
pages are allocated, and account memcg-lruvec statistics when pcpu
objects are handed out.

To do account these separately, expose mod_memcg_lruvec_state to be
used outside of memcontrol.

One functional change is that we do not account the 8 byte objcg
pointer per-memcg-lruvec. Since the objcg membership is tracked
per-memcg and not percpu, there is no appropriate lruvec to charge this
memory to (see pcpu_obj_full_size). Instead of adding additional
mechanisms to detect which lruvec the 8 byte pointer belongs to, let's
just simplify and account the pcpu objects' size.

Limit-checking is still done with the additional 8 bytes.

Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
---
 include/linux/memcontrol.h |  4 +++-
 include/linux/mmzone.h     |  4 +++-
 mm/memcontrol.c            | 12 ++++++------
 mm/percpu-vm.c             | 14 ++++++++++++--
 mm/percpu.c                | 24 ++++++++++++++++++++----
 mm/vmstat.c                |  1 +
 6 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 086158969529..96dae769c60d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -34,7 +34,6 @@ struct kmem_cache;
 enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
-	MEMCG_PERCPU_B,
 	MEMCG_KMEM,
 	MEMCG_ZSWAP_B,
 	MEMCG_ZSWAPPED,
@@ -909,6 +908,9 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 					    struct mem_cgroup *oom_domain);
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
+void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			    int val);
+
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 void mod_memcg_state(struct mem_cgroup *memcg,
 		     enum memcg_stat_item idx, int val);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 7bd0134c241c..e38d8fe8552b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -328,6 +328,7 @@ enum node_stat_item {
 #endif
 	NR_BALLOON_PAGES,
 	NR_KERNEL_FILE_PAGES,
+	NR_PERCPU_B,
 	NR_VM_NODE_STAT_ITEMS
 };
 
@@ -365,7 +366,8 @@ static __always_inline bool vmstat_item_in_bytes(int idx)
 	 * byte-precise.
 	 */
 	return (idx == NR_SLAB_RECLAIMABLE_B ||
-		idx == NR_SLAB_UNRECLAIMABLE_B);
+		idx == NR_SLAB_UNRECLAIMABLE_B ||
+		idx == NR_PERCPU_B);
 }
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a47fb68dd65f..b320b6a42696 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -377,6 +377,7 @@ static const unsigned int memcg_node_stat_items[] = {
 	NR_UNEVICTABLE,
 	NR_SLAB_RECLAIMABLE_B,
 	NR_SLAB_UNRECLAIMABLE_B,
+	NR_PERCPU_B,
 	WORKINGSET_REFAULT_ANON,
 	WORKINGSET_REFAULT_FILE,
 	WORKINGSET_ACTIVATE_ANON,
@@ -428,7 +429,6 @@ static const unsigned int memcg_node_stat_items[] = {
 static const unsigned int memcg_stat_items[] = {
 	MEMCG_SWAP,
 	MEMCG_SOCK,
-	MEMCG_PERCPU_B,
 	MEMCG_KMEM,
 	MEMCG_ZSWAP_B,
 	MEMCG_ZSWAPPED,
@@ -920,9 +920,8 @@ static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
 	put_cpu();
 }
 
-static void mod_memcg_lruvec_state(struct lruvec *lruvec,
-				     enum node_stat_item idx,
-				     int val)
+void mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
+			    int val)
 {
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup_per_node *pn;
@@ -936,6 +935,7 @@ static void mod_memcg_lruvec_state(struct lruvec *lruvec,
 
 	get_non_dying_memcg_end();
 }
+EXPORT_SYMBOL(mod_memcg_lruvec_state);
 
 /**
  * mod_lruvec_state - update lruvec memory statistics
@@ -1535,7 +1535,7 @@ static const struct memory_stat memory_stats[] = {
 	{ "kernel_stack",		NR_KERNEL_STACK_KB		},
 	{ "pagetables",			NR_PAGETABLE			},
 	{ "sec_pagetables",		NR_SECONDARY_PAGETABLE		},
-	{ "percpu",			MEMCG_PERCPU_B			},
+	{ "percpu",			NR_PERCPU_B			},
 	{ "sock",			MEMCG_SOCK			},
 	{ "vmalloc",			NR_VMALLOC			},
 	{ "shmem",			NR_SHMEM			},
@@ -1597,7 +1597,7 @@ static const struct memory_stat memory_stats[] = {
 static int memcg_page_state_unit(int item)
 {
 	switch (item) {
-	case MEMCG_PERCPU_B:
+	case NR_PERCPU_B:
 	case MEMCG_ZSWAP_B:
 	case NR_SLAB_RECLAIMABLE_B:
 	case NR_SLAB_UNRECLAIMABLE_B:
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 4f5937090590..e36b639f521d 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -55,7 +55,8 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
 			    struct page **pages, int page_start, int page_end)
 {
 	unsigned int cpu;
-	int i;
+	int nr_pages = page_end - page_start;
+	int i, nid;
 
 	for_each_possible_cpu(cpu) {
 		for (i = page_start; i < page_end; i++) {
@@ -65,6 +66,10 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
 				__free_page(page);
 		}
 	}
+
+	for_each_node(nid)
+		mod_node_page_state(NODE_DATA(nid), NR_PERCPU_B,
+				-1L * nr_pages * nr_cpus_node(nid) * PAGE_SIZE);
 }
 
 /**
@@ -84,7 +89,8 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 			    gfp_t gfp)
 {
 	unsigned int cpu, tcpu;
-	int i;
+	int nr_pages = page_end - page_start;
+	int i, nid;
 
 	gfp |= __GFP_HIGHMEM;
 
@@ -97,6 +103,10 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
 				goto err;
 		}
 	}
+
+	for_each_node(nid)
+		mod_node_page_state(NODE_DATA(nid), NR_PERCPU_B,
+				    nr_pages * nr_cpus_node(nid) * PAGE_SIZE);
 	return 0;
 
 err:
diff --git a/mm/percpu.c b/mm/percpu.c
index b0676b8054ed..4ad3b9739eb9 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1632,6 +1632,24 @@ static bool pcpu_memcg_pre_alloc_hook(size_t size, gfp_t gfp,
 	return true;
 }
 
+static void pcpu_mod_memcg_lruvec(struct obj_cgroup *objcg, int charge)
+{
+	struct mem_cgroup *memcg;
+	int nid;
+
+	memcg = obj_cgroup_memcg(objcg);
+	for_each_node(nid) {
+		struct lruvec *lruvec;
+		unsigned int nr_cpus = nr_cpus_node(nid);
+
+		if (!nr_cpus)
+			continue;
+
+		lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+		mod_memcg_lruvec_state(lruvec, NR_PERCPU_B, nr_cpus * charge);
+	}
+}
+
 static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 				       struct pcpu_chunk *chunk, int off,
 				       size_t size)
@@ -1644,8 +1662,7 @@ static void pcpu_memcg_post_alloc_hook(struct obj_cgroup *objcg,
 		chunk->obj_exts[off >> PCPU_MIN_ALLOC_SHIFT].cgroup = objcg;
 
 		rcu_read_lock();
-		mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
-				pcpu_obj_full_size(size));
+		pcpu_mod_memcg_lruvec(objcg, size);
 		rcu_read_unlock();
 	} else {
 		obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
@@ -1667,8 +1684,7 @@ static void pcpu_memcg_free_hook(struct pcpu_chunk *chunk, int off, size_t size)
 	obj_cgroup_uncharge(objcg, pcpu_obj_full_size(size));
 
 	rcu_read_lock();
-	mod_memcg_state(obj_cgroup_memcg(objcg), MEMCG_PERCPU_B,
-			-pcpu_obj_full_size(size));
+	pcpu_mod_memcg_lruvec(objcg, -size);
 	rcu_read_unlock();
 
 	obj_cgroup_put(objcg);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index b33097ab9bc8..d73c3355be71 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1296,6 +1296,7 @@ const char * const vmstat_text[] = {
 #endif
 	[I(NR_BALLOON_PAGES)]			= "nr_balloon_pages",
 	[I(NR_KERNEL_FILE_PAGES)]		= "nr_kernel_file_pages",
+	[I(NR_PERCPU_B)]			= "nr_percpu",
 #undef I
 
 	/* system-wide enum vm_stat_item counters */
-- 
2.52.0

Re: [PATCH] mm/percpu, memcontrol: Per-memcg-lruvec percpu accounting

[Michal Hocko]

On Fri 27-03-26 12:19:35, Joshua Hahn wrote:
> Convert MEMCG_PERCPU_B from a memcg_stat_item to a memcg_node_stat_item
> to give visibility into per-node breakdowns for percpu allocations and
> turn it into NR_PERCPU_B.

Why do we need/want this?
-- 
Michal Hocko
SUSE Labs