The patch titled
Subject: thp, memcg: split hugepage for memcg oom on cow
has been removed from the -mm tree. Its filename was
thp-memcg-split-hugepage-for-memcg-oom-on-cow.patch
This patch was dropped because it was merged into mainline or a subsystem tree
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
From: David Rientjes <rientjes@xxxxxxxxxx>
Subject: 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: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Johannes Weiner <jweiner@xxxxxxxxxx>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 3 +++
mm/memory.c | 18 +++++++++++++++---
2 files changed, 18 insertions(+), 3 deletions(-)
diff -puN mm/huge_memory.c~thp-memcg-split-hugepage-for-memcg-oom-on-cow mm/huge_memory.c
--- a/mm/huge_memory.c~thp-memcg-split-hugepage-for-memcg-oom-on-cow
+++ a/mm/huge_memory.c
@@ -952,6 +952,8 @@ int do_huge_pmd_wp_page(struct mm_struct
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
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 -puN mm/memory.c~thp-memcg-split-hugepage-for-memcg-oom-on-cow mm/memory.c
--- a/mm/memory.c~thp-memcg-split-hugepage-for-memcg-oom-on-cow
+++ a/mm/memory.c
@@ -3486,6 +3486,7 @@ int handle_mm_fault(struct mm_struct *mm
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
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;
}
}
_
Patches currently in -mm which might be from rientjes@xxxxxxxxxx are
origin.patch
linux-next.patch
slab-move-full-state-transition-to-an-initcall.patch
hugetlb-rename-max_hstate-to-hugetlb_max_hstate.patch
hugetlbfs-add-an-inline-helper-for-finding-hstate-index-fix.patch
hugetlb-simplify-migrate_huge_page.patch
hugetlb-simplify-migrate_huge_page-fix.patch
memcg-add-hugetlb-extension-fix.patch
memcg-add-hugetlb-extension-fix-fix.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
