aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>2015-02-11 15:25:19 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2015-03-06 14:43:27 -0800
commit9a3a249a942ded8bb8a7faedeeee310186139f8a (patch)
tree9b360dc3352bfddf5127f3a56d376fccdeab8dd0
parent509e937b2e439947c51f04347b7e4bd4ef72b161 (diff)
downloadlinux-yocto-9a3a249a942ded8bb8a7faedeeee310186139f8a.tar.gz
linux-yocto-9a3a249a942ded8bb8a7faedeeee310186139f8a.tar.bz2
linux-yocto-9a3a249a942ded8bb8a7faedeeee310186139f8a.zip
mm/hugetlb: pmd_huge() returns true for non-present hugepage
commit cbef8478bee55775ac312a574aad48af7bb9cf9f upstream. Migrating hugepages and hwpoisoned hugepages are considered as non-present hugepages, and they are referenced via migration entries and hwpoison entries in their page table slots. This behavior causes race condition because pmd_huge() doesn't tell non-huge pages from migrating/hwpoisoned hugepages. follow_page_mask() is one example where the kernel would call follow_page_pte() for such hugepage while this function is supposed to handle only normal pages. To avoid this, this patch makes pmd_huge() return true when pmd_none() is true *and* pmd_present() is false. We don't have to worry about mixing up non-present pmd entry with normal pmd (pointing to leaf level pte entry) because pmd_present() is true in normal pmd. The same race condition could happen in (x86-specific) gup_pmd_range(), where this patch simply adds pmd_present() check instead of pmd_huge(). This is because gup_pmd_range() is fast path. If we have non-present hugepage in this function, we will go into gup_huge_pmd(), then return 0 at flag mask check, and finally fall back to the slow path. Fixes: 290408d4a2 ("hugetlb: hugepage migration core") Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Hugh Dickins <hughd@google.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Nishanth Aravamudan <nacc@linux.vnet.ibm.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Steve Capper <steve.capper@linaro.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--arch/x86/mm/gup.c2
-rw-r--r--arch/x86/mm/hugetlbpage.c8
-rw-r--r--mm/hugetlb.c2
3 files changed, 10 insertions, 2 deletions
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 207d9aef662d..448ee8912d9b 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
*/
if (pmd_none(pmd) || pmd_trans_splitting(pmd))
return 0;
- if (unlikely(pmd_large(pmd))) {
+ if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) {
/*
* NUMA hinting faults need to be handled in the GUP
* slowpath for accounting purposes and so that they
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 8b977ebf9388..006cc914994b 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
return ERR_PTR(-EINVAL);
}
+/*
+ * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal
+ * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry.
+ * Otherwise, returns 0.
+ */
int pmd_huge(pmd_t pmd)
{
- return !!(pmd_val(pmd) & _PAGE_PSE);
+ return !pmd_none(pmd) &&
+ (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT;
}
int pud_huge(pud_t pud)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67d0c175efcf..472259b00618 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3456,6 +3456,8 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
{
struct page *page;
+ if (!pmd_present(*pmd))
+ return NULL;
page = pte_page(*(pte_t *)pmd);
if (page)
page += ((address & ~PMD_MASK) >> PAGE_SHIFT);