summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorBaolin Wang <baolin.wang@linux.alibaba.com>2022-09-01 18:41:31 +0800
committerAndrew Morton <akpm@linux-foundation.org>2022-10-11 19:05:44 -0700
commitfac35ba763ed07ba93154c95ffc0c4a55023707f (patch)
tree1481c3ae84db3e9eeb1fa5d11e9fcffe489f3f81 /mm
parent1c8e2349f2d033f634d046063b704b2ca6c46972 (diff)
mm/hugetlb: fix races when looking up a CONT-PTE/PMD size hugetlb page
On some architectures (like ARM64), it can support CONT-PTE/PMD size hugetlb, which means it can support not only PMD/PUD size hugetlb (2M and 1G), but also CONT-PTE/PMD size(64K and 32M) if a 4K page size specified. So when looking up a CONT-PTE size hugetlb page by follow_page(), it will use pte_offset_map_lock() to get the pte entry lock for the CONT-PTE size hugetlb in follow_page_pte(). However this pte entry lock is incorrect for the CONT-PTE size hugetlb, since we should use huge_pte_lock() to get the correct lock, which is mm->page_table_lock. That means the pte entry of the CONT-PTE size hugetlb under current pte lock is unstable in follow_page_pte(), we can continue to migrate or poison the pte entry of the CONT-PTE size hugetlb, which can cause some potential race issues, even though they are under the 'pte lock'. For example, suppose thread A is trying to look up a CONT-PTE size hugetlb page by move_pages() syscall under the lock, however antoher thread B can migrate the CONT-PTE hugetlb page at the same time, which will cause thread A to get an incorrect page, if thread A also wants to do page migration, then data inconsistency error occurs. Moreover we have the same issue for CONT-PMD size hugetlb in follow_huge_pmd(). To fix above issues, rename the follow_huge_pmd() as follow_huge_pmd_pte() to handle PMD and PTE level size hugetlb, which uses huge_pte_lock() to get the correct pte entry lock to make the pte entry stable. Mike said: Support for CONT_PMD/_PTE was added with bb9dd3df8ee9 ("arm64: hugetlb: refactor find_num_contig()"). Patch series "Support for contiguous pte hugepages", v4. However, I do not believe these code paths were executed until migration support was added with 5480280d3f2d ("arm64/mm: enable HugeTLB migration for contiguous bit HugeTLB pages") I would go with 5480280d3f2d for the Fixes: targe. Link: https://lkml.kernel.org/r/635f43bdd85ac2615a58405da82b4d33c6e5eb05.1662017562.git.baolin.wang@linux.alibaba.com Fixes: 5480280d3f2d ("arm64/mm: enable HugeTLB migration for contiguous bit HugeTLB pages") Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> Suggested-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: David Hildenbrand <david@redhat.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/gup.c14
-rw-r--r--mm/hugetlb.c27
2 files changed, 26 insertions, 15 deletions
diff --git a/mm/gup.c b/mm/gup.c
index 00926abb4426..251cb6a10bc0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -530,6 +530,18 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
(FOLL_PIN | FOLL_GET)))
return ERR_PTR(-EINVAL);
+
+ /*
+ * Considering PTE level hugetlb, like continuous-PTE hugetlb on
+ * ARM64 architecture.
+ */
+ if (is_vm_hugetlb_page(vma)) {
+ page = follow_huge_pmd_pte(vma, address, flags);
+ if (page)
+ return page;
+ return no_page_table(vma, flags);
+ }
+
retry:
if (unlikely(pmd_bad(*pmd)))
return no_page_table(vma, flags);
@@ -662,7 +674,7 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
if (pmd_none(pmdval))
return no_page_table(vma, flags);
if (pmd_huge(pmdval) && is_vm_hugetlb_page(vma)) {
- page = follow_huge_pmd(mm, address, pmd, flags);
+ page = follow_huge_pmd_pte(vma, address, flags);
if (page)
return page;
return no_page_table(vma, flags);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0bdfc7e1c933..9564bf817e6a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6946,12 +6946,13 @@ follow_huge_pd(struct vm_area_struct *vma,
}
struct page * __weak
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
- pmd_t *pmd, int flags)
+follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags)
{
+ struct hstate *h = hstate_vma(vma);
+ struct mm_struct *mm = vma->vm_mm;
struct page *page = NULL;
spinlock_t *ptl;
- pte_t pte;
+ pte_t *ptep, pte;
/*
* FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via
@@ -6961,17 +6962,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
return NULL;
retry:
- ptl = pmd_lockptr(mm, pmd);
- spin_lock(ptl);
- /*
- * make sure that the address range covered by this pmd is not
- * unmapped from other threads.
- */
- if (!pmd_huge(*pmd))
- goto out;
- pte = huge_ptep_get((pte_t *)pmd);
+ ptep = huge_pte_offset(mm, address, huge_page_size(h));
+ if (!ptep)
+ return NULL;
+
+ ptl = huge_pte_lock(h, mm, ptep);
+ pte = huge_ptep_get(ptep);
if (pte_present(pte)) {
- page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
+ page = pte_page(pte) +
+ ((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
/*
* try_grab_page() should always succeed here, because: a) we
* hold the pmd (ptl) lock, and b) we've just checked that the
@@ -6987,7 +6986,7 @@ retry:
} else {
if (is_hugetlb_entry_migration(pte)) {
spin_unlock(ptl);
- __migration_entry_wait_huge((pte_t *)pmd, ptl);
+ __migration_entry_wait_huge(ptep, ptl);
goto retry;
}
/*