[tip:numa/core] sched, numa, mm: Add memcg support to do_huge_pmd_numa_page()

[tip-bot for Johannes Weiner <hannes@cmpxchg.org>]

Commit-ID:  3eaf14577ceb5c540e33a4eab967160d374b93b1
Gitweb:     http://git.kernel.org/tip/3eaf14577ceb5c540e33a4eab967160d374b93b1
Author:     Johannes Weiner <hannes@cmpxchg.org>
AuthorDate: Thu, 25 Oct 2012 12:49:51 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 29 Oct 2012 12:15:15 +0100

sched, numa, mm: Add memcg support to do_huge_pmd_numa_page()

Add memory control group support to hugepage migration.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Zhouping Liu <zliu@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-rDk9mgpoyhZlwh2xhlykvgnp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 mm/huge_memory.c |   15 +++++++++++++++
 mm/memcontrol.c  |    7 +++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7361fd9..1fc805e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -742,6 +742,7 @@ void do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			   unsigned int flags, pmd_t entry)
 {
 	unsigned long haddr = address & HPAGE_PMD_MASK;
+	struct mem_cgroup *memcg = NULL;
 	struct page *new_page = NULL;
 	struct page *page = NULL;
 	int node, lru;
@@ -832,6 +833,14 @@ migrate:
 
 		return;
 	}
+	/*
+	 * Traditional migration needs to prepare the memcg charge
+	 * transaction early to prevent the old page from being
+	 * uncharged when installing migration entries.  Here we can
+	 * save the potential rollback and start the charge transfer
+	 * only when migration is already known to end successfully.
+	 */
+	mem_cgroup_prepare_migration(page, new_page, &memcg);
 
 	entry = mk_pmd(new_page, vma->vm_page_prot);
 	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -842,6 +851,12 @@ migrate:
 	set_pmd_at(mm, haddr, pmd, entry);
 	update_mmu_cache_pmd(vma, address, entry);
 	page_remove_rmap(page);
+	/*
+	 * Finish the charge transaction under the page table lock to
+	 * prevent split_huge_page() from dividing up the charge
+	 * before it's fully transferred to the new page.
+	 */
+	mem_cgroup_end_migration(memcg, page, new_page, true);
 	spin_unlock(&mm->page_table_lock);
 
 	put_page(page);			/* Drop the rmap reference */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7acf43b..011e510 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3255,15 +3255,18 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 				  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
 	enum charge_type ctype;
 
 	*memcgp = NULL;
 
-	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
 		return;
 
+	if (PageTransHuge(page))
+		nr_pages <<= compound_order(page);
+
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
@@ -3325,7 +3328,7 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 	 * charged to the res_counter since we plan on replacing the
 	 * old one and only one page is going to be left afterwards.
 	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
+	__mem_cgroup_commit_charge(memcg, newpage, nr_pages, ctype, false);
 }
 
 /* remove redundant charge if migration failed*/