On COW, a new hugepage is allocated and charged to the memcg. If the
memcg is oom, however, this charge will fail and will return VM_FAULT_OOM
to the page fault handler 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 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>
---
mm/huge_memory.c | 1 +
mm/memory.c | 18 +++++++++++++++---
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -959,6 +959,7 @@ 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
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3489,6 +3489,7 @@ 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)
@@ -3502,13 +3503,24 @@ 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 memcg, the huge pmd
+ * will already 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;
}
}
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>