Dzień dobry,
zapoznałem się z Państwa ofertą i z przyjemnością przyznaję, że przyciąga uwagę i zachęca do dalszych rozmów.
Pomyślałem, że może mógłbym mieć swój wkład w Państwa rozwój i pomóc dotrzeć z tą ofertą do większego grona odbiorców. Pozycjonuję strony www, dzięki czemu generują świetny ruch w sieci.
Możemy porozmawiać w najbliższym czasie?
Pozdrawiam serdecznie
Adam Charachuta
The test mm `hugetlb_fault_after_madv` selftest needs one and only one
huge page to run, thus it sets `/proc/sys/vm/nr_hugepages` to 1.
The problem is that further tests require the previous number of
hugepages allocated in order to succeed.
Save the number of huge pages before changing it, and restore it once the
test finishes, so, further tests could run successfully.
Fixes: 116d57303a05 ("selftests/mm: add a new test for madv and hugetlb")
Reported-by: Ryan Roberts <ryan.roberts(a)arm.com>
Closes: https://lore.kernel.org/all/662df57e-47f1-4c15-9b84-f2f2d587fc5c@arm.com/
Signed-off-by: Breno Leitao <leitao(a)debian.org>
---
tools/testing/selftests/mm/run_vmtests.sh | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index cc16f6ca8533..00757445278e 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -223,9 +223,12 @@ CATEGORY="hugetlb" run_test ./hugepage-mremap
CATEGORY="hugetlb" run_test ./hugepage-vmemmap
CATEGORY="hugetlb" run_test ./hugetlb-madvise
+nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages)
# For this test, we need one and just one huge page
echo 1 > /proc/sys/vm/nr_hugepages
CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
+# Restore the previous number of huge pages, since further tests rely on it
+echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages
if test_selected "hugetlb"; then
echo "NOTE: These hugetlb tests provide minimal coverage. Use"
--
2.34.1
Create a selftest that exercises the race between page faults and
madvise(MADV_DONTNEED) in the same huge page. Do it by running two
threads that touches the huge page and madvise(MADV_DONTNEED) at the same
time.
In case of a SIGBUS coming at pagefault, the test should fail, since we
hit the bug.
The test doesn't have a signal handler, and if it fails, it fails like
the following
----------------------------------
running ./hugetlb_fault_after_madv
----------------------------------
./run_vmtests.sh: line 186: 595563 Bus error (core dumped) "$@"
[FAIL]
This selftest goes together with the fix of the bug[1] itself.
[1] https://lore.kernel.org/all/20231001005659.2185316-1-riel@surriel.com/#r
Signed-off-by: Breno Leitao <leitao(a)debian.org>
---
tools/testing/selftests/mm/Makefile | 1 +
.../selftests/mm/hugetlb_fault_after_madv.c | 73 +++++++++++++++++++
tools/testing/selftests/mm/run_vmtests.sh | 4 +
3 files changed, 78 insertions(+)
create mode 100644 tools/testing/selftests/mm/hugetlb_fault_after_madv.c
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 6a9fc5693145..e71ec9910c62 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -68,6 +68,7 @@ TEST_GEN_FILES += split_huge_page_test
TEST_GEN_FILES += ksm_tests
TEST_GEN_FILES += ksm_functional_tests
TEST_GEN_FILES += mdwe_test
+TEST_GEN_FILES += hugetlb_fault_after_madv
ifneq ($(ARCH),arm64)
TEST_GEN_PROGS += soft-dirty
diff --git a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c
new file mode 100644
index 000000000000..73b81c632366
--- /dev/null
+++ b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "vm_util.h"
+#include "../kselftest.h"
+
+#define MMAP_SIZE (1 << 21)
+#define INLOOP_ITER 100
+
+char *huge_ptr;
+
+/* Touch the memory while it is being madvised() */
+void *touch(void *unused)
+{
+ char *ptr = (char *)huge_ptr;
+
+ for (int i = 0; i < INLOOP_ITER; i++)
+ ptr[0] = '.';
+
+ return NULL;
+}
+
+void *madv(void *unused)
+{
+ usleep(rand() % 10);
+
+ for (int i = 0; i < INLOOP_ITER; i++)
+ madvise(huge_ptr, MMAP_SIZE, MADV_DONTNEED);
+
+ return NULL;
+}
+
+int main(void)
+{
+ unsigned long free_hugepages;
+ pthread_t thread1, thread2;
+ /*
+ * On kernel 6.4, we are able to reproduce the problem with ~1000
+ * interactions
+ */
+ int max = 10000;
+
+ srand(getpid());
+
+ free_hugepages = get_free_hugepages();
+ if (free_hugepages != 1) {
+ ksft_exit_skip("This test needs one and only one page to execute. Got %lu\n",
+ free_hugepages);
+ }
+
+ while (max--) {
+ huge_ptr = mmap(NULL, MMAP_SIZE, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+ -1, 0);
+
+ if ((unsigned long)huge_ptr == -1)
+ ksft_exit_skip("Failed to allocated huge page\n");
+
+ pthread_create(&thread1, NULL, madv, NULL);
+ pthread_create(&thread2, NULL, touch, NULL);
+
+ pthread_join(thread1, NULL);
+ pthread_join(thread2, NULL);
+ munmap(huge_ptr, MMAP_SIZE);
+ }
+
+ return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 3e2bc818d566..9f53f7318a38 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -221,6 +221,10 @@ CATEGORY="hugetlb" run_test ./hugepage-mremap
CATEGORY="hugetlb" run_test ./hugepage-vmemmap
CATEGORY="hugetlb" run_test ./hugetlb-madvise
+# For this test, we need one and just one huge page
+echo 1 > /proc/sys/vm/nr_hugepages
+CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv
+
if test_selected "hugetlb"; then
echo "NOTE: These hugetlb tests provide minimal coverage. Use"
echo " https://github.com/libhugetlbfs/libhugetlbfs.git for"
--
2.34.1
In the PMTU test, when all previous tests are skipped and the new test
passes, the exit code is set to 0. However, the current check mistakenly
treats this as an assignment, causing the check to pass every time.
Consequently, regardless of how many tests have failed, if the latest test
passes, the PMTU test will report a pass.
Fixes: 2a9d3716b810 ("selftests: pmtu.sh: improve the test result processing")
Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com>
---
v2: use "-eq" instead of "=" to make less error-prone
---
tools/testing/selftests/net/pmtu.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index f838dd370f6a..b3b2dc5a630c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -2048,7 +2048,7 @@ run_test() {
case $ret in
0)
all_skipped=false
- [ $exitcode=$ksft_skip ] && exitcode=0
+ [ $exitcode -eq $ksft_skip ] && exitcode=0
;;
$ksft_skip)
[ $all_skipped = true ] && exitcode=$ksft_skip
--
2.41.0
This patch series introduces UFFDIO_MOVE feature to userfaultfd, which
has long been implemented and maintained by Andrea in his local tree [1],
but was not upstreamed due to lack of use cases where this approach would
be better than allocating a new page and copying the contents. Previous
upstraming attempts could be found at [6] and [7].
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [2]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [3].
We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread’s completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [3].
Furthermore, UFFDIO_MOVE enables moving swapped-out pages without
touching them within the same vma. Today, it can only be done by mremap,
however it forces splitting the vma.
TODOs for follow-up improvements:
- cross-mm support. Known differences from single-mm and missing pieces:
- memcg recharging (might need to isolate pages in the process)
- mm counters
- cross-mm deposit table moves
- cross-mm test
- document the address space where src and dest reside in struct
uffdio_move
- TLB flush batching. Will require extensive changes to PTL locking in
move_pages_pte(). OTOH that might let us reuse parts of mremap code.
Changes since v3 [8]:
- changed retry path in folio_lock_anon_vma_read() to unlock and then
relock RCU, per Peter Xu
- removed cross-mm support from initial patchset, per David Hildenbrand
- replaced BUG_ONs with VM_WARN_ON or WARN_ON_ONCE, per David Hildenbrand
- added missing cache flushing, per Lokesh Gidra and Peter Xu
- updated manpage text in the patch description, per Peter Xu
- renamed internal functions from "remap" to "move", per Peter Xu
- added mmap_changing check after taking mmap_lock, per Peter Xu
- changed uffd context check to ensure dst_mm is registered onto uffd we
are operating on, Peter Xu and David Hildenbrand
- changed to non-maybe variants of maybe*_mkwrite(), per David Hildenbrand
- fixed warning for CONFIG_TRANSPARENT_HUGEPAGE=n, per kernel test robot
- comments cleanup, per David Hildenbrand and Peter Xu
- checks for VM_IO,VM_PFNMAP,VM_HUGETLB,..., per David Hildenbrand
- prevent moving pinned pages, per Peter Xu
- changed uffd tests to call move uffd_test_ctx_clear() at the end of the
test run instead of in the beginning of the next run
- added support for testcase-specific ops
- added test for moving PMD-aligned blocks
Changes since v2 [5]:
- renamed UFFDIO_REMAP to UFFDIO_MOVE, per David Hildenbrand
- rebase over mm-unstable to use folio_move_anon_rmap(),
per David Hildenbrand
- added text for manpage explaining DONTFORK and KSM requirements for this
feature, per David Hildenbrand
- check for anon_vma changes in the fast path of folio_lock_anon_vma_read,
per Peter Xu
- updated the title and description of the first patch,
per David Hildenbrand
- updating comments in folio_lock_anon_vma_read() explaining the need for
anon_vma checks, per David Hildenbrand
- changed all mapcount checks to PageAnonExclusive, per Jann Horn and
David Hildenbrand
- changed counters in remap_swap_pte() from MM_ANONPAGES to MM_SWAPENTS,
per Jann Horn
- added a check for PTE change after folio is locked in remap_pages_pte(),
per Jann Horn
- added handling of PMD migration entries and bailout when pmd_devmap(),
per Jann Horn
- added checks to ensure both src and dst VMAs are writable, per Peter Xu
- added UFFD_FEATURE_MOVE, per Peter Xu
- removed obsolete comments, per Peter Xu
- renamed remap_anon_pte to remap_present_pte, per Peter Xu
- added a comment for folio_get_anon_vma() explaining the need for
anon_vma checks, per Peter Xu
- changed error handling in remap_pages() to make it more clear,
per Peter Xu
- changed EFAULT to EAGAIN to retry when a hugepage appears or disappears
from under us, per Peter Xu
- added links to previous upstreaming attempts, per David Hildenbrand
Changes since v1 [4]:
- add mmget_not_zero in userfaultfd_remap, per Jann Horn
- removed extern from function definitions, per Matthew Wilcox
- converted to folios in remap_pages_huge_pmd, per Matthew Wilcox
- use PageAnonExclusive in remap_pages_huge_pmd, per David Hildenbrand
- handle pgtable transfers between MMs, per Jann Horn
- ignore concurrent A/D pte bit changes, per Jann Horn
- split functions into smaller units, per David Hildenbrand
- test for folio_test_large in remap_anon_pte, per Matthew Wilcox
- use pte_swp_exclusive for swapcount check, per David Hildenbrand
- eliminated use of mmu_notifier_invalidate_range_start_nonblock,
per Jann Horn
- simplified THP alignment checks, per Jann Horn
- refactored the loop inside remap_pages, per Jann Horn
- additional clarifying comments, per Jann Horn
Main changes since Andrea's last version [1]:
- Trivial translations from page to folio, mmap_sem to mmap_lock
- Replace pmd_trans_unstable() with pte_offset_map_nolock() and handle its
possible failure
- Move pte mapping into remap_pages_pte to allow for retries when source
page or anon_vma is contended. Since pte_offset_map_nolock() start RCU
read section, we can't block anymore after mapping a pte, so have to unmap
the ptesm do the locking and retry.
- Add and use anon_vma_trylock_write() to avoid blocking while in RCU
read section.
- Accommodate changes in mmu_notifier_range_init() API, switch to
mmu_notifier_invalidate_range_start_nonblock() to avoid blocking while in
RCU read section.
- Open-code now removed __swp_swapcount()
- Replace pmd_read_atomic() with pmdp_get_lockless()
- Add new selftest for UFFDIO_MOVE
[1] https://gitlab.com/aarcange/aa/-/commit/2aec7aea56b10438a3881a20a411aa4b1fc…
[2] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redha…
[3] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyj…
[4] https://lore.kernel.org/all/20230914152620.2743033-1-surenb@google.com/
[5] https://lore.kernel.org/all/20230923013148.1390521-1-surenb@google.com/
[6] https://lore.kernel.org/all/1425575884-2574-21-git-send-email-aarcange@redh…
[7] https://lore.kernel.org/all/cover.1547251023.git.blake.caldwell@colorado.ed…
[8] https://lore.kernel.org/all/20231009064230.2952396-1-surenb@google.com/
The patchset applies over mm-unstable.
Andrea Arcangeli (2):
mm/rmap: support move to different root anon_vma in
folio_move_anon_rmap()
userfaultfd: UFFDIO_MOVE uABI
Suren Baghdasaryan (3):
selftests/mm: call uffd_test_ctx_clear at the end of the test
selftests/mm: add uffd_test_case_ops to allow test case-specific
operations
selftests/mm: add UFFDIO_MOVE ioctl test
Documentation/admin-guide/mm/userfaultfd.rst | 3 +
fs/userfaultfd.c | 72 +++
include/linux/rmap.h | 5 +
include/linux/userfaultfd_k.h | 11 +
include/uapi/linux/userfaultfd.h | 29 +-
mm/huge_memory.c | 122 ++++
mm/khugepaged.c | 3 +
mm/rmap.c | 30 +
mm/userfaultfd.c | 596 +++++++++++++++++++
tools/testing/selftests/mm/uffd-common.c | 51 +-
tools/testing/selftests/mm/uffd-common.h | 11 +
tools/testing/selftests/mm/uffd-stress.c | 5 +-
tools/testing/selftests/mm/uffd-unit-tests.c | 144 +++++
13 files changed, 1078 insertions(+), 4 deletions(-)
--
2.42.0.820.g83a721a137-goog
Üdvözlöm, van egy vállalkozásom, amelyre úgy hivatkoztam rád, mint
neked ugyanaz a vezetéknév, mint a néhai ügyfelem, de a részletek az
alábbiak lesznek értesítjük Önt, amikor megerősíti ennek az e-mailnek
a kézhezvételét. Üdvözlettel
