The patch titled
Subject: mm: allocate kernel pages to the right memcg
has been added to the -mm tree. Its filename is
mm-allocate-kernel-pages-to-the-right-memcg.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Glauber Costa <glommer@xxxxxxxxxxxxx>
Subject: mm: allocate kernel pages to the right memcg
When a process tries to allocate a page with the __GFP_KMEMCG flag, the
page allocator will call the corresponding memcg functions to validate the
allocation. Tasks in the root memcg can always proceed.
To avoid adding markers to the page - and a kmem flag that would
necessarily follow, as much as doing page_cgroup lookups for no reason,
whoever is marking its allocations with __GFP_KMEMCG flag is responsible
for telling the page allocator that this is such an allocation at
free_pages() time. This is done by the invocation of
__free_accounted_pages() and free_accounted_pages().
Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxxx>
Cc: Greg Thelen <gthelen@xxxxxxxxxx>
Cc: JoonSoo Kim <js1304@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/gfp.h | 3 +++
mm/page_alloc.c | 35 +++++++++++++++++++++++++++++++++++
2 files changed, 38 insertions(+)
diff -puN include/linux/gfp.h~mm-allocate-kernel-pages-to-the-right-memcg include/linux/gfp.h
--- a/include/linux/gfp.h~mm-allocate-kernel-pages-to-the-right-memcg
+++ a/include/linux/gfp.h
@@ -362,6 +362,9 @@ extern void free_pages(unsigned long add
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);
+
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)
diff -puN mm/page_alloc.c~mm-allocate-kernel-pages-to-the-right-memcg mm/page_alloc.c
--- a/mm/page_alloc.c~mm-allocate-kernel-pages-to-the-right-memcg
+++ a/mm/page_alloc.c
@@ -2598,6 +2598,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u
int migratetype = allocflags_to_migratetype(gfp_mask);
unsigned int cpuset_mems_cookie;
int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+ struct mem_cgroup *memcg = NULL;
gfp_mask &= gfp_allowed_mask;
@@ -2616,6 +2617,13 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
+ /*
+ * Will only have any effect when __GFP_KMEMCG is set. This is
+ * verified in the (always inline) callee
+ */
+ if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+ return NULL;
+
retry_cpuset:
cpuset_mems_cookie = get_mems_allowed();
@@ -2651,6 +2659,8 @@ out:
if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
goto retry_cpuset;
+ memcg_kmem_commit_charge(page, memcg, order);
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2703,6 +2713,31 @@ void free_pages(unsigned long addr, unsi
EXPORT_SYMBOL(free_pages);
+/*
+ * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
+ * pages allocated with __GFP_KMEMCG.
+ *
+ * Those pages are accounted to a particular memcg, embedded in the
+ * corresponding page_cgroup. To avoid adding a hit in the allocator to search
+ * for that information only to find out that it is NULL for users who have no
+ * interest in that whatsoever, we provide these functions.
+ *
+ * The caller knows better which flags it relies on.
+ */
+void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+{
+ memcg_kmem_uncharge_pages(page, order);
+ __free_pages(page, order);
+}
+
+void free_memcg_kmem_pages(unsigned long addr, unsigned int order)
+{
+ if (addr != 0) {
+ VM_BUG_ON(!virt_addr_valid((void *)addr));
+ __free_memcg_kmem_pages(virt_to_page((void *)addr), order);
+ }
+}
+
static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
{
if (addr) {
_
Patches currently in -mm which might be from glommer@xxxxxxxxxxxxx are
linux-next.patch
memcg-make-it-possible-to-use-the-stock-for-more-than-one-page.patch
memcg-reclaim-when-more-than-one-page-needed.patch
memcg-change-defines-to-an-enum.patch
memcg-kmem-accounting-basic-infrastructure.patch
mm-add-a-__gfp_kmemcg-flag.patch
memcg-kmem-controller-infrastructure.patch
mm-allocate-kernel-pages-to-the-right-memcg.patch
res_counter-return-amount-of-charges-after-res_counter_uncharge.patch
memcg-kmem-accounting-lifecycle-management.patch
memcg-use-static-branches-when-code-not-in-use.patch
memcg-allow-a-memcg-with-kmem-charges-to-be-destructed.patch
memcg-execute-the-whole-memcg-freeing-in-free_worker.patch
fork-protect-architectures-where-thread_size-=-page_size-against-fork-bombs.patch
memcg-add-documentation-about-the-kmem-controller.patch
slab-slub-struct-memcg_params.patch
slab-annotate-on-slab-caches-nodelist-locks.patch
slab-slub-consider-a-memcg-parameter-in-kmem_create_cache.patch
memcg-allocate-memory-for-memcg-caches-whenever-a-new-memcg-appears.patch
memcg-infrastructure-to-match-an-allocation-to-the-right-cache.patch
memcg-skip-memcg-kmem-allocations-in-specified-code-regions.patch
slb-always-get-the-cache-from-its-page-in-kmem_cache_free.patch
slb-allocate-objects-from-memcg-cache.patch
memcg-destroy-memcg-caches.patch
memcg-slb-track-all-the-memcg-children-of-a-kmem_cache.patch
memcg-slb-shrink-dead-caches.patch
memcg-aggregate-memcg-cache-values-in-slabinfo.patch
slab-propagate-tunable-values.patch
slub-slub-specific-propagation-changes.patch
kmem-add-slab-specific-documentation-about-the-kmem-controller.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
