The patch titled
Subject: khugepaged: skip collapse if uffd-wp detected
has been added to the -mm tree. Its filename is
khugepaged-skip-collapse-if-uffd-wp-detected.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/khugepaged-skip-collapse-if-uffd-wp-detected.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/khugepaged-skip-collapse-if-uffd-wp-detected.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Peter Xu <peterx@xxxxxxxxxx>
Subject: khugepaged: skip collapse if uffd-wp detected
Don't collapse the huge PMD if there is any userfault write protected
small PTEs. The problem is that the write protection is in small page
granularity and there's no way to keep all these write protection
information if the small pages are going to be merged into a huge PMD.
The same thing needs to be considered for swap entries and migration
entries. So do the check as well disregarding khugepaged_max_ptes_swap.
Link: http://lkml.kernel.org/r/20200220163112.11409-12-peterx@xxxxxxxxxx
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Reviewed-by: Jerome Glisse <jglisse@xxxxxxxxxx>
Reviewed-by: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Bobby Powers <bobbypowers@xxxxxxxxx>
Cc: Brian Geffon <bgeffon@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Denis Plotnikov <dplotnikov@xxxxxxxxxxxxx>
Cc: "Dr . David Alan Gilbert" <dgilbert@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: "Kirill A . Shutemov" <kirill@xxxxxxxxxxxxx>
Cc: Martin Cracauer <cracauer@xxxxxxxx>
Cc: Marty McFadden <mcfadden8@xxxxxxxx>
Cc: Maya Gokhale <gokhale2@xxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/trace/events/huge_memory.h | 1 +
mm/khugepaged.c | 23 +++++++++++++++++++++++
2 files changed, 24 insertions(+)
--- a/include/trace/events/huge_memory.h~khugepaged-skip-collapse-if-uffd-wp-detected
+++ a/include/trace/events/huge_memory.h
@@ -13,6 +13,7 @@
EM( SCAN_PMD_NULL, "pmd_null") \
EM( SCAN_EXCEED_NONE_PTE, "exceed_none_pte") \
EM( SCAN_PTE_NON_PRESENT, "pte_non_present") \
+ EM( SCAN_PTE_UFFD_WP, "pte_uffd_wp") \
EM( SCAN_PAGE_RO, "no_writable_page") \
EM( SCAN_LACK_REFERENCED_PAGE, "lack_referenced_page") \
EM( SCAN_PAGE_NULL, "page_null") \
--- a/mm/khugepaged.c~khugepaged-skip-collapse-if-uffd-wp-detected
+++ a/mm/khugepaged.c
@@ -29,6 +29,7 @@ enum scan_result {
SCAN_PMD_NULL,
SCAN_EXCEED_NONE_PTE,
SCAN_PTE_NON_PRESENT,
+ SCAN_PTE_UFFD_WP,
SCAN_PAGE_RO,
SCAN_LACK_REFERENCED_PAGE,
SCAN_PAGE_NULL,
@@ -1139,6 +1140,15 @@ static int khugepaged_scan_pmd(struct mm
pte_t pteval = *_pte;
if (is_swap_pte(pteval)) {
if (++unmapped <= khugepaged_max_ptes_swap) {
+ /*
+ * Always be strict with uffd-wp
+ * enabled swap entries. Please see
+ * comment below for pte_uffd_wp().
+ */
+ if (pte_swp_uffd_wp(pteval)) {
+ result = SCAN_PTE_UFFD_WP;
+ goto out_unmap;
+ }
continue;
} else {
result = SCAN_EXCEED_SWAP_PTE;
@@ -1158,6 +1168,19 @@ static int khugepaged_scan_pmd(struct mm
result = SCAN_PTE_NON_PRESENT;
goto out_unmap;
}
+ if (pte_uffd_wp(pteval)) {
+ /*
+ * Don't collapse the page if any of the small
+ * PTEs are armed with uffd write protection.
+ * Here we can also mark the new huge pmd as
+ * write protected if any of the small ones is
+ * marked but that could bring uknown
+ * userfault messages that falls outside of
+ * the registered range. So, just be simple.
+ */
+ result = SCAN_PTE_UFFD_WP;
+ goto out_unmap;
+ }
if (pte_write(pteval))
writable = true;
_
Patches currently in -mm which might be from peterx@xxxxxxxxxx are
mm-gup-rename-nonblocking-to-locked-where-proper.patch
mm-gup-fix-__get_user_pages-on-fault-retry-of-hugetlb.patch
mm-introduce-fault_signal_pending.patch
x86-mm-use-helper-fault_signal_pending.patch
arc-mm-use-helper-fault_signal_pending.patch
arm64-mm-use-helper-fault_signal_pending.patch
powerpc-mm-use-helper-fault_signal_pending.patch
sh-mm-use-helper-fault_signal_pending.patch
mm-return-faster-for-non-fatal-signals-in-user-mode-faults.patch
userfaultfd-dont-retake-mmap_sem-to-emulate-nopage.patch
mm-introduce-fault_flag_default.patch
mm-introduce-fault_flag_interruptible.patch
mm-allow-vm_fault_retry-for-multiple-times.patch
mm-gup-allow-vm_fault_retry-for-multiple-times.patch
mm-gup-allow-to-react-to-fatal-signals.patch
mm-userfaultfd-honor-fault_flag_killable-in-fault-path.patch
mm-merge-parameters-for-change_protection.patch
userfaultfd-wp-apply-_page_uffd_wp-bit.patch
userfaultfd-wp-drop-_page_uffd_wp-properly-when-fork.patch
userfaultfd-wp-add-pmd_swp_uffd_wp-helpers.patch
userfaultfd-wp-support-swap-and-page-migration.patch
khugepaged-skip-collapse-if-uffd-wp-detected.patch
userfaultfd-wp-dont-wake-up-when-doing-write-protect.patch
userfaultfd-wp-declare-_uffdio_writeprotect-conditionally.patch
userfaultfd-selftests-refactor-statistics.patch
userfaultfd-selftests-add-write-protect-test.patch
