mm: memcontrol: account kernel stack per node

Currently the kernel stack is being accounted per-zone.  There is no need
to do that.  In addition due to being per-zone, memcg has to keep a
separate MEMCG_KERNEL_STACK_KB.  Make the stat per-node and deprecate
MEMCG_KERNEL_STACK_KB as memcg_stat_item is an extension of
node_stat_item.  In addition localize the kernel stack stats updates to
account_kernel_stack().

Signed-off-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Link: http://lkml.kernel.org/r/20200630161539.1759185-1-shakeelb@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 15 insertions, 38 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 76d3f3387554..c7b4ce9d2647 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -276,13 +276,8 @@ static inline void free_thread_stack(struct task_struct *tsk)
 	if (vm) {
 		int i;
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     -(int)(PAGE_SIZE / 1024));
-
+		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
 			memcg_kmem_uncharge_page(vm->pages[i], 0);
-		}
 
 		for (i = 0; i < NR_CACHED_STACKS; i++) {
 			if (this_cpu_cmpxchg(cached_stacks[i],
@@ -382,31 +377,14 @@ static void account_kernel_stack(struct task_struct *tsk, int account)
 	void *stack = task_stack_page(tsk);
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
-
-	if (vm) {
-		int i;
-
-		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
 
-		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
-			mod_zone_page_state(page_zone(vm->pages[i]),
-					    NR_KERNEL_STACK_KB,
-					    PAGE_SIZE / 1024 * account);
-		}
-	} else {
-		/*
-		 * All stack pages are in the same zone and belong to the
-		 * same memcg.
-		 */
-		struct page *first_page = virt_to_page(stack);
-
-		mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
-				    THREAD_SIZE / 1024 * account);
-
-		mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
-				    account * (THREAD_SIZE / 1024));
-	}
+	/* All stack pages are in the same node. */
+	if (vm)
+		mod_lruvec_page_state(vm->pages[0], NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
+	else
+		mod_lruvec_slab_state(stack, NR_KERNEL_STACK_KB,
+				      account * (THREAD_SIZE / 1024));
 }
 
 static int memcg_charge_kernel_stack(struct task_struct *tsk)
@@ -415,24 +393,23 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk)
 	struct vm_struct *vm = task_stack_vm_area(tsk);
 	int ret;
 
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
+
 	if (vm) {
 		int i;
 
+		BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+
 		for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 			/*
 			 * If memcg_kmem_charge_page() fails, page->mem_cgroup
-			 * pointer is NULL, and both memcg_kmem_uncharge_page()
-			 * and mod_memcg_page_state() in free_thread_stack()
-			 * will ignore this page. So it's safe.
+			 * pointer is NULL, and memcg_kmem_uncharge_page() in
+			 * free_thread_stack() will ignore this page.
 			 */
 			ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL,
 						     0);
 			if (ret)
 				return ret;
-
-			mod_memcg_page_state(vm->pages[i],
-					     MEMCG_KERNEL_STACK_KB,
-					     PAGE_SIZE / 1024);
 		}
 	}
 #endif
diff --git a/kernel/scs.c b/kernel/scs.c
index 5d4d9bbdec36..4ff4a7ba0094 100644
--- a/kernel/scs.c
+++ b/kernel/scs.c
@@ -17,7 +17,7 @@ static void __scs_account(void *s, int account)
 {
 	struct page *scs_page = virt_to_page(s);
 
-	mod_zone_page_state(page_zone(scs_page), NR_KERNEL_SCS_KB,
+	mod_node_page_state(page_pgdat(scs_page), NR_KERNEL_SCS_KB,
 			    account * (SCS_SIZE / SZ_1K));
 }