From 9d3c3354bb85bab4d865fe95039443f09a4c8394 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Thu, 22 Mar 2018 16:17:45 -0700
Subject: [PATCH] mm, thp: do not cause memcg oom for thp
Git-commit: 9d3c3354bb85bab4d865fe95039443f09a4c8394
Patch-mainline: v4.16-rc7
References: bnc#1089663

Commit 2516035499b9 ("mm, thp: remove __GFP_NORETRY from khugepaged and
madvised allocations") changed the page allocator to no longer detect
thp allocations based on __GFP_NORETRY.

It did not, however, modify the mem cgroup try_charge() path to avoid
oom kill for either khugepaged collapsing or thp faulting.  It is never
expected to oom kill a process to allocate a hugepage for thp; reclaim
is governed by the thp defrag mode and MADV_HUGEPAGE, but allocations
(and charging) should fallback instead of oom killing processes.

Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1803191409420.124411@chino.kir.corp.google.com
Fixes: 2516035499b9 ("mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocations")
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Michal Hocko <mhocko@suse.com>

---
 mm/huge_memory.c | 5 +++--
 mm/khugepaged.c  | 8 ++++++--
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 529cf36b7edb..5a68730eebd6 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -555,7 +555,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg,
+				  true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1316,7 +1317,7 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
 	}
 
 	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
-					huge_gfp, &memcg, true))) {
+				huge_gfp | __GFP_NORETRY, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		if (page)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index c15da1ea7e63..e42568284e06 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -965,7 +965,9 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out_nolock;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out_nolock;
 	}
@@ -1324,7 +1326,9 @@ static void collapse_shmem(struct mm_struct *mm,
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) {
+	/* Do not oom kill for khugepaged charges */
+	if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY,
+					   &memcg, true))) {
 		result = SCAN_CGROUP_CHARGE_FAIL;
 		goto out;
 	}
-- 
1.8.5.6