memcg: add per-memcg vmalloc stat

The kvmalloc* allocation functions can fallback to vmalloc allocations
and more often on long running machines.  In addition the kernel does
have __GFP_ACCOUNT kvmalloc* calls.  So, often on long running machines,
the memory.stat does not tell the complete picture which type of memory
is charged to the memcg.  So add a per-memcg vmalloc stat.

[shakeelb@google.com: page_memcg() within rcu lock, per Muchun]
  Link: https://lkml.kernel.org/r/20211222052457.1960701-1-shakeelb@google.com
[akpm@linux-foundation.org: remove cast, per Muchun]
[shakeelb@google.com: remove area->page[0] checks and move to page by page accounting per Michal]
  Link: https://lkml.kernel.org/r/20220104222341.3972772-1-shakeelb@google.com

Link: https://lkml.kernel.org/r/20211221215336.1922823-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/admin-guide/cgroup-v2.rst

@@ -1314,6 +1314,9 @@ PAGE_SIZE multiple when read back.
 	  sock (npn)
 		Amount of memory used in network transmission buffers
 
+	  vmalloc (npn)
+		Amount of memory used for vmap backed memory.
+
 	  shmem
 		Amount of cached filesystem data that is swap-backed,
 		such as tmpfs, shm segments, shared anonymous mmap()s

include/linux/memcontrol.h

@@ -33,6 +33,7 @@ enum memcg_stat_item {
 	MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS,
 	MEMCG_SOCK,
 	MEMCG_PERCPU_B,
+	MEMCG_VMALLOC,
 	MEMCG_NR_STAT,
 };
 
@@ -992,6 +993,21 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 	local_irq_restore(flags);
 }
 
+static inline void mod_memcg_page_state(struct page *page,
+					int idx, int val)
+{
+	struct mem_cgroup *memcg;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = page_memcg(page);
+	if (memcg)
+		mod_memcg_state(memcg, idx, val);
+	rcu_read_unlock();
+}
+
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
 	return READ_ONCE(memcg->vmstats.state[idx]);
@@ -1447,6 +1463,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg,
 {
 }
 
+static inline void mod_memcg_page_state(struct page *page,
+					int idx, int val)
+{
+}
+
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 {
 	return 0;

mm/memcontrol.c

@@ -1375,6 +1375,7 @@ static const struct memory_stat memory_stats[] = {
 	{ "pagetables",			NR_PAGETABLE			},
 	{ "percpu",			MEMCG_PERCPU_B			},
 	{ "sock",			MEMCG_SOCK			},
+	{ "vmalloc",			MEMCG_VMALLOC			},
 	{ "shmem",			NR_SHMEM			},
 	{ "file_mapped",		NR_FILE_MAPPED			},
 	{ "file_dirty",			NR_FILE_DIRTY			},

mm/vmalloc.c

@@ -31,6 +31,7 @@
 #include <linux/kmemleak.h>
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <linux/memcontrol.h>
 #include <linux/llist.h>
 #include <linux/bitops.h>
 #include <linux/rbtree_augmented.h>
@@ -2623,12 +2624,13 @@ static void __vunmap(const void *addr, int deallocate_pages)
 
 	if (deallocate_pages) {
 		unsigned int page_order = vm_area_page_order(area);
-		int i;
+		int i, step = 1U << page_order;
 
-		for (i = 0; i < area->nr_pages; i += 1U << page_order) {
+		for (i = 0; i < area->nr_pages; i += step) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
+			mod_memcg_page_state(page, MEMCG_VMALLOC, -step);
 			__free_pages(page, page_order);
 			cond_resched();
 		}
@@ -2955,6 +2957,13 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		page_order, nr_small_pages, area->pages);
 
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
+	if (gfp_mask & __GFP_ACCOUNT) {
+		int i, step = 1U << page_order;
+
+		for (i = 0; i < area->nr_pages; i += step)
+			mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC,
+					     step);
+	}
 
 	/*
 	 * If not enough pages were obtained to accomplish an