memcg: add per-memcg total kernel memory stat

Currently memcg stats show several types of kernel memory: kernel stack,
page tables, sock, vmalloc, and slab.  However, there are other
allocations with __GFP_ACCOUNT (or supersets such as GFP_KERNEL_ACCOUNT)
that are not accounted in any of those stats, a few examples are:

 - various kvm allocations (e.g. allocated pages to create vcpus)
 - io_uring
 - tmp_page in pipes during pipe_write()
 - bpf ringbuffers
 - unix sockets

Keeping track of the total kernel memory is essential for the ease of
migration from cgroup v1 to v2 as there are large discrepancies between
v1's kmem.usage_in_bytes and the sum of the available kernel memory
stats in v2.  Adding separate memcg stats for all __GFP_ACCOUNT kernel
allocations is an impractical maintenance burden as there a lot of those
all over the kernel code, with more use cases likely to show up in the
future.

Therefore, add a "kernel" memcg stat that is analogous to kmem page
counter, with added benefits such as using rstat infrastructure which
aggregates stats more efficiently.  Additionally, this provides a
lighter alternative in case the legacy kmem is deprecated in the future

[yosryahmed@google.com: v2]
  Link: https://lkml.kernel.org/r/20220203193856.972500-1-yosryahmed@google.com

Link: https://lkml.kernel.org/r/20220201200823.3283171-1-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 27 insertions, 6 deletions

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 5aa368d165da..69d7a6983f78 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1301,6 +1301,11 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used to cache filesystem data,
 		including tmpfs and shared memory.
 
+	  kernel (npn)
+		Amount of total kernel memory, including
+		(kernel_stack, pagetables, percpu, vmalloc, slab) in
+		addition to other kernel memory use cases.
+
 	  kernel_stack
 		Amount of memory allocated to kernel stacks.
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 0abbd685703b..8612d7dd0859 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -34,6 +34,7 @@ enum memcg_stat_item {
 	MEMCG_SOCK,
 	MEMCG_PERCPU_B,
 	MEMCG_VMALLOC,
+	MEMCG_KMEM,
 	MEMCG_NR_STAT,
 };
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 209e66893da6..e64a276837b0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1371,6 +1371,7 @@ struct memory_stat {
 static const struct memory_stat memory_stats[] = {
 	{ "anon",			NR_ANON_MAPPED			},
 	{ "file",			NR_FILE_PAGES			},
+	{ "kernel",			MEMCG_KMEM			},
 	{ "kernel_stack",		NR_KERNEL_STACK_KB		},
 	{ "pagetables",			NR_PAGETABLE			},
 	{ "percpu",			MEMCG_PERCPU_B			},
@@ -2114,6 +2115,7 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static void drain_obj_stock(struct obj_stock *stock);
 static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 				     struct mem_cgroup *root_memcg);
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages);
 
 #else
 static inline void drain_obj_stock(struct obj_stock *stock)
@@ -2124,6 +2126,9 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
 {
 	return false;
 }
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
+{
+}
 #endif
 
 /**
@@ -2979,6 +2984,18 @@ static void memcg_free_cache_id(int id)
 	ida_simple_remove(&memcg_cache_ida, id);
 }
 
+static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages)
+{
+	mod_memcg_state(memcg, MEMCG_KMEM, nr_pages);
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
+		if (nr_pages > 0)
+			page_counter_charge(&memcg->kmem, nr_pages);
+		else
+			page_counter_uncharge(&memcg->kmem, -nr_pages);
+	}
+}
+
+
 /*
  * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg
  * @objcg: object cgroup to uncharge
@@ -2991,8 +3008,7 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
 
 	memcg = get_mem_cgroup_from_objcg(objcg);
 
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		page_counter_uncharge(&memcg->kmem, nr_pages);
+	memcg_account_kmem(memcg, -nr_pages);
 	refill_stock(memcg, nr_pages);
 
 	css_put(&memcg->css);
@@ -3018,8 +3034,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
 	if (ret)
 		goto out;
 
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		page_counter_charge(&memcg->kmem, nr_pages);
+	memcg_account_kmem(memcg, nr_pages);
 out:
 	css_put(&memcg->css);
 
@@ -6801,8 +6816,8 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 		page_counter_uncharge(&ug->memcg->memory, ug->nr_memory);
 		if (do_memsw_account())
 			page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory);
-		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem)
-			page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem);
+		if (ug->nr_kmem)
+			memcg_account_kmem(ug->memcg, -ug->nr_kmem);
 		memcg_oom_recover(ug->memcg);
 	}