mm: get rid of __GFP_KMEMCG
Currently to allocate a page that should be charged to kmemcg (e.g.
threadinfo), we pass __GFP_KMEMCG flag to the page allocator. The page
allocated is then to be freed by free_memcg_kmem_pages. Apart from
looking asymmetrical, this also requires intrusion to the general
allocation path. So let's introduce separate functions that will
alloc/free pages charged to kmemcg.
The new functions are called alloc_kmem_pages and free_kmem_pages. They
should be used when the caller actually would like to use kmalloc, but
has to fall back to the page allocator for the allocation is large.
They only differ from alloc_pages and free_pages in that besides
allocating or freeing pages they also charge them to the kmem resource
counter of the current memory cgroup.
[sfr@canb.auug.org.au: export kmalloc_order() to modules]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Glauber Costa <glommer@gmail.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 39b81dc..d382db7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -31,7 +31,6 @@
#define ___GFP_HARDWALL 0x20000u
#define ___GFP_THISNODE 0x40000u
#define ___GFP_RECLAIMABLE 0x80000u
-#define ___GFP_KMEMCG 0x100000u
#define ___GFP_NOTRACK 0x200000u
#define ___GFP_NO_KSWAPD 0x400000u
#define ___GFP_OTHER_NODE 0x800000u
@@ -91,7 +90,6 @@
#define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
-#define __GFP_KMEMCG ((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */
#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) /* Allocator intends to dirty page */
/*
@@ -353,6 +351,10 @@
#define alloc_page_vma_node(gfp_mask, vma, addr, node) \
alloc_pages_vma(gfp_mask, 0, vma, addr, node)
+extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order);
+extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask,
+ unsigned int order);
+
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
@@ -372,8 +374,8 @@
extern void free_hot_cold_page(struct page *page, int cold);
extern void free_hot_cold_page_list(struct list_head *list, int cold);
-extern void __free_memcg_kmem_pages(struct page *page, unsigned int order);
-extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order);
+extern void __free_kmem_pages(struct page *page, unsigned int order);
+extern void free_kmem_pages(unsigned long addr, unsigned int order);
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 96e5d25..5155d09 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -537,7 +537,7 @@
* res_counter_charge_nofail, but we hope those allocations are rare,
* and won't be worth the trouble.
*/
- if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL))
+ if (gfp & __GFP_NOFAIL)
return true;
if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
return true;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 307bfbe..a6aab2c 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -369,16 +369,7 @@
#include <linux/slub_def.h>
#endif
-static __always_inline void *
-kmalloc_order(size_t size, gfp_t flags, unsigned int order)
-{
- void *ret;
-
- flags |= (__GFP_COMP | __GFP_KMEMCG);
- ret = (void *) __get_free_pages(flags, order);
- kmemleak_alloc(ret, size, 1, flags);
- return ret;
-}
+extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order);
#ifdef CONFIG_TRACING
extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order);
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index cb0cec9..ff307b5 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -61,8 +61,6 @@
# define THREADINFO_GFP (GFP_KERNEL | __GFP_NOTRACK)
#endif
-#define THREADINFO_GFP_ACCOUNTED (THREADINFO_GFP | __GFP_KMEMCG)
-
/*
* flag set/clear/test wrappers
* - pass TIF_xxxx constants to these functions
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index 1eddbf1..d6fd8e5 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -34,7 +34,6 @@
{(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \
{(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \
{(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \
- {(unsigned long)__GFP_KMEMCG, "GFP_KMEMCG"}, \
{(unsigned long)__GFP_MOVABLE, "GFP_MOVABLE"}, \
{(unsigned long)__GFP_NOTRACK, "GFP_NOTRACK"}, \
{(unsigned long)__GFP_NO_KSWAPD, "GFP_NO_KSWAPD"}, \