diff options
| author | David Rientjes <rientjes@google.com> | 2012-05-29 15:06:23 -0700 |
|---|---|---|
| committer | Ben Hutchings <ben@decadent.org.uk> | 2013-01-03 03:33:55 +0000 |
| commit | 505bd8dcba128970db6fed2eca126f9e11a44290 (patch) | |
| tree | 76104e162f9ebc2f9cc0428244515de75b82d85f /mm | |
| parent | 40686464a6c29b4d8f5ef1d6c86117022e46ecd1 (diff) | |
| download | lwn-505bd8dcba128970db6fed2eca126f9e11a44290.tar.gz lwn-505bd8dcba128970db6fed2eca126f9e11a44290.zip | |
thp, memcg: split hugepage for memcg oom on cow
commit 1f1d06c34f7675026326cd9f39ff91e4555cf355 upstream.
On COW, a new hugepage is allocated and charged to the memcg. If the
system is oom or the charge to the memcg fails, however, the fault
handler will return VM_FAULT_OOM which results in an oom kill.
Instead, it's possible to fallback to splitting the hugepage so that the
COW results only in an order-0 page being allocated and charged to the
memcg which has a higher liklihood to succeed. This is expensive
because the hugepage must be split in the page fault handler, but it is
much better than unnecessarily oom killing a process.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/huge_memory.c | 3 | ||||
| -rw-r--r-- | mm/memory.c | 18 |
2 files changed, 18 insertions, 3 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8f005e999593..470cbb45410a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -921,6 +921,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); + if (ret & VM_FAULT_OOM) + split_huge_page(page); put_page(page); goto out; } @@ -928,6 +930,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { put_page(new_page); + split_huge_page(page); put_page(page); ret |= VM_FAULT_OOM; goto out; diff --git a/mm/memory.c b/mm/memory.c index 70f5dafabb2a..15e686a42eb5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3469,6 +3469,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); +retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3482,13 +3483,24 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, pmd, flags); } else { pmd_t orig_pmd = *pmd; + int ret; + barrier(); if (pmd_trans_huge(orig_pmd)) { if (flags & FAULT_FLAG_WRITE && !pmd_write(orig_pmd) && - !pmd_trans_splitting(orig_pmd)) - return do_huge_pmd_wp_page(mm, vma, address, - pmd, orig_pmd); + !pmd_trans_splitting(orig_pmd)) { + ret = do_huge_pmd_wp_page(mm, vma, address, pmd, + orig_pmd); + /* + * If COW results in an oom, the huge pmd will + * have been split, so retry the fault on the + * pte for a smaller charge. + */ + if (unlikely(ret & VM_FAULT_OOM)) + goto retry; + return ret; + } return 0; } } |