Commit 1f1d06c3 authored by David Rientjes's avatar David Rientjes Committed by Linus Torvalds
Browse files

thp, memcg: split hugepage for memcg oom on cow 



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: default avatarDavid Rientjes <rientjes@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Acked-by: default avatarKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent bde8bd8a

mm/huge_memory.c

+3 −0
Original line number Diff line number Diff line
@@ -952,6 +952,8 @@ 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;

	}
@@ -959,6 +961,7 @@ 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;

mm/memory.c

+15 −3
Original line number Diff line number Diff line
@@ -3486,6 +3486,7 @@ 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)
@@ -3499,13 +3500,24 @@ 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;

		}

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE