mm: Convert page kmemcg type to a page memcg flag

PageKmemcg flag is currently defined as a page type (like buddy, offline,
table and guard).  Semantically it means that the page was accounted as a
kernel memory by the page allocator and has to be uncharged on the
release.

As a side effect of defining the flag as a page type, the accounted page
can't be mapped to userspace (look at page_has_type() and comments above).
In particular, this blocks the accounting of vmalloc-backed memory used
by some bpf maps, because these maps do map the memory to userspace.

One option is to fix it by complicating the access to page->mapcount,
which provides some free bits for page->page_type.

But it's way better to move this flag into page->memcg_data flags.
Indeed, the flag makes no sense without enabled memory cgroups and memory
cgroup pointer set in particular.

This commit replaces PageKmemcg() and __SetPageKmemcg() with
PageMemcgKmem() and an open-coded OR operation setting the memcg pointer
with the MEMCG_DATA_KMEM bit.  __ClearPageKmemcg() can be simple deleted,
as the whole memcg_data is zeroed at once.

As a bonus, on !CONFIG_MEMCG build the PageMemcgKmem() check will be
compiled out.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Link: https://lkml.kernel.org/r/20201027001657.3398190-5-guro@fb.com
Link: https://lore.kernel.org/bpf/20201201215900.3569844-5-guro@fb.com

1 files changed, 33 insertions, 4 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 99a4841d658b..7c9d43476166 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -346,8 +346,10 @@ extern struct mem_cgroup *root_mem_cgroup;
 enum page_memcg_data_flags {
 	/* page->memcg_data is a pointer to an objcgs vector */
 	MEMCG_DATA_OBJCGS = (1UL << 0),
+	/* page has been accounted as a non-slab kernel page */
+	MEMCG_DATA_KMEM = (1UL << 1),
 	/* the next bit after the last actual flag */
-	__NR_MEMCG_DATA_FLAGS  = (1UL << 1),
+	__NR_MEMCG_DATA_FLAGS  = (1UL << 2),
 };
 
 #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
@@ -369,8 +371,12 @@ enum page_memcg_data_flags {
  */
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
+	unsigned long memcg_data = page->memcg_data;
+
 	VM_BUG_ON_PAGE(PageSlab(page), page);
-	return (struct mem_cgroup *)page->memcg_data;
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
+
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -387,7 +393,8 @@ static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
 	VM_BUG_ON_PAGE(PageSlab(page), page);
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	return (struct mem_cgroup *)READ_ONCE(page->memcg_data);
+	return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) &
+				     ~MEMCG_DATA_FLAGS_MASK);
 }
 
 /*
@@ -416,7 +423,21 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	if (memcg_data & MEMCG_DATA_OBJCGS)
 		return NULL;
 
-	return (struct mem_cgroup *)memcg_data;
+	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+/*
+ * PageMemcgKmem - check if the page has MemcgKmem flag set
+ * @page: a pointer to the page struct
+ *
+ * Checks if the page has MemcgKmem flag set. The caller must ensure that
+ * the page has an associated memory cgroup. It's not safe to call this function
+ * against some types of pages, e.g. slab pages.
+ */
+static inline bool PageMemcgKmem(struct page *page)
+{
+	VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
+	return page->memcg_data & MEMCG_DATA_KMEM;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -435,6 +456,7 @@ static inline struct obj_cgroup **page_objcgs(struct page *page)
 	unsigned long memcg_data = READ_ONCE(page->memcg_data);
 
 	VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
 
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
@@ -454,6 +476,8 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
 	if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
 		return NULL;
 
+	VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+
 	return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
 }
 
@@ -1109,6 +1133,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
 	return NULL;
 }
 
+static inline bool PageMemcgKmem(struct page *page)
+{
+	return false;
+}
+
 static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 {
 	return true;