summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPeter Xu <peterx@redhat.com>2022-12-14 15:04:53 -0500
committerAndrew Morton <akpm@linux-foundation.org>2023-01-18 17:02:19 -0800
commit7e3ce3f8d2d235f916baad1582f6cf12e0319013 (patch)
tree41ec8de4623912faca81480a077ebd28b0c7d456
parent49d6d7fb631345b0f2957a7c4be24ad63903150f (diff)
mm: fix a few rare cases of using swapin error pte marker
This patch should harden commit 15520a3f0469 ("mm: use pte markers for swap errors") on using pte markers for swapin errors on a few corner cases. 1. Propagate swapin errors across fork()s: if there're swapin errors in the parent mm, after fork()s the child should sigbus too when an error page is accessed. 2. Fix a rare condition race in pte_marker_clear() where a uffd-wp pte marker can be quickly switched to a swapin error. 3. Explicitly ignore swapin error pte markers in change_protection(). I mostly don't worry on (2) or (3) at all, but we should still have them. Case (1) is special because it can potentially cause silent data corrupt on child when parent has swapin error triggered with swapoff, but since swapin error is rare itself already it's probably not easy to trigger either. Currently there is a priority difference between the uffd-wp bit and the swapin error entry, in which the swapin error always has higher priority (e.g. we don't need to wr-protect a swapin error pte marker). If there will be a 3rd bit introduced, we'll probably need to consider a more involved approach so we may need to start operate on the bits. Let's leave that for later. This patch is tested with case (1) explicitly where we'll get corrupted data before in the child if there's existing swapin error pte markers, and after patch applied the child can be rightfully killed. We don't need to copy stable for this one since 15520a3f0469 just landed as part of v6.2-rc1, only "Fixes" applied. Link: https://lkml.kernel.org/r/20221214200453.1772655-3-peterx@redhat.com Fixes: 15520a3f0469 ("mm: use pte markers for swap errors") Signed-off-by: Peter Xu <peterx@redhat.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Miaohe Lin <linmiaohe@huawei.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: Pengfei Xu <pengfei.xu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r--mm/hugetlb.c3
-rw-r--r--mm/memory.c8
-rw-r--r--mm/mprotect.c8
3 files changed, 16 insertions, 3 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7fcdb98c9e68..bdbfeb6fb393 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5051,6 +5051,9 @@ again:
entry = huge_pte_clear_uffd_wp(entry);
set_huge_pte_at(dst, addr, dst_pte, entry);
} else if (unlikely(is_pte_marker(entry))) {
+ /* No swap on hugetlb */
+ WARN_ON_ONCE(
+ is_swapin_error_entry(pte_to_swp_entry(entry)));
/*
* We copy the pte marker only if the dst vma has
* uffd-wp enabled.
diff --git a/mm/memory.c b/mm/memory.c
index 032ef700c3e8..3e836fecd035 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -828,7 +828,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
return -EBUSY;
return -ENOENT;
} else if (is_pte_marker_entry(entry)) {
- if (userfaultfd_wp(dst_vma))
+ if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma))
set_pte_at(dst_mm, addr, dst_pte, pte);
return 0;
}
@@ -3625,8 +3625,12 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf)
/*
* Be careful so that we will only recover a special uffd-wp pte into a
* none pte. Otherwise it means the pte could have changed, so retry.
+ *
+ * This should also cover the case where e.g. the pte changed
+ * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR.
+ * So is_pte_marker() check is not enough to safely drop the pte.
*/
- if (is_pte_marker(*vmf->pte))
+ if (pte_same(vmf->orig_pte, *vmf->pte))
pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte);
pte_unmap_unlock(vmf->pte, vmf->ptl);
return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 908df12caa26..61cf60015a8b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -245,7 +245,13 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
newpte = pte_swp_mksoft_dirty(newpte);
if (pte_swp_uffd_wp(oldpte))
newpte = pte_swp_mkuffd_wp(newpte);
- } else if (pte_marker_entry_uffd_wp(entry)) {
+ } else if (is_pte_marker_entry(entry)) {
+ /*
+ * Ignore swapin errors unconditionally,
+ * because any access should sigbus anyway.
+ */
+ if (is_swapin_error_entry(entry))
+ continue;
/*
* If this is uffd-wp pte marker and we'd like
* to unprotect it, drop it; the next page