The patch titled
Subject: mm/ksm: fix KSM COW breaking with userfaultfd-wp via FAULT_FLAG_UNSHARE
has been added to the -mm mm-unstable branch. Its filename is
mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: David Hildenbrand <david@xxxxxxxxxx>
Subject: mm/ksm: fix KSM COW breaking with userfaultfd-wp via FAULT_FLAG_UNSHARE
Date: Fri, 30 Sep 2022 16:19:28 +0200
Let's stop breaking COW via a fake write fault and let's use
FAULT_FLAG_UNSHARE instead. This avoids any wrong side effects of the
fake write fault, such as mapping the PTE writable and marking the pte
dirty/softdirty.
Also, this fixes KSM interaction with userfaultfd-wp: when we have a KSM
page that's write-protected by userfaultfd, break_ksm()->handle_mm_fault()
will fail with VM_FAULT_SIGBUS and will simpy return in break_ksm() with
0. The warning in dmesg indicates this wrong handling:
[ 230.096368] FAULT_FLAG_ALLOW_RETRY missing 881
[ 230.100822] CPU: 1 PID: 1643 Comm: ksm-uffd-wp [...]
[ 230.110124] Hardware name: [...]
[ 230.117775] Call Trace:
[ 230.120227] <TASK>
[ 230.122334] dump_stack_lvl+0x44/0x5c
[ 230.126010] handle_userfault.cold+0x14/0x19
[ 230.130281] ? tlb_finish_mmu+0x65/0x170
[ 230.134207] ? uffd_wp_range+0x65/0xa0
[ 230.137959] ? _raw_spin_unlock+0x15/0x30
[ 230.141972] ? do_wp_page+0x50/0x590
[ 230.145551] __handle_mm_fault+0x9f5/0xf50
[ 230.149652] ? mmput+0x1f/0x40
[ 230.152712] handle_mm_fault+0xb9/0x2a0
[ 230.156550] break_ksm+0x141/0x180
[ 230.159964] unmerge_ksm_pages+0x60/0x90
[ 230.163890] ksm_madvise+0x3c/0xb0
[ 230.167295] do_madvise.part.0+0x10c/0xeb0
[ 230.171396] ? do_syscall_64+0x67/0x80
[ 230.175157] __x64_sys_madvise+0x5a/0x70
[ 230.179082] do_syscall_64+0x58/0x80
[ 230.182661] ? do_syscall_64+0x67/0x80
[ 230.186413] entry_SYSCALL_64_after_hwframe+0x63/0xcd
--------------------------------------------------------------------------
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <fcntl.h>
#include <unistd.h>
#include <errno.h>
#include <sys/mman.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <linux/userfaultfd.h>
#define MMAP_SIZE (2 * 1024 * 1024u)
static char *map;
int uffd;
static int setup_uffd(void)
{
struct uffdio_api uffdio_api;
struct uffdio_register uffdio_register;
struct uffdio_writeprotect uffd_writeprotect;
struct uffdio_range uffd_range;
uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
if (uffd < 0) {
fprintf(stderr, "syscall() failed: %d\n", errno);
return -errno;
}
uffdio_api.api = UFFD_API;
uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP;
if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) {
fprintf(stderr, "UFFDIO_API failed: %d\n", errno);
return -errno;
}
if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) {
fprintf(stderr, "UFFD_FEATURE_WRITEPROTECT missing\n");
return -ENOSYS;
}
/* Register UFFD-WP */
uffdio_register.range.start = (unsigned long) map;
uffdio_register.range.len = MMAP_SIZE;
uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) {
fprintf(stderr, "UFFDIO_REGISTER failed: %d\n", errno);
return -errno;
}
/* Writeprotect the range. */
uffd_writeprotect.range.start = (unsigned long) map;
uffd_writeprotect.range.len = MMAP_SIZE;
uffd_writeprotect.mode = UFFDIO_WRITEPROTECT_MODE_WP;
if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect)) {
fprintf(stderr, "UFFDIO_WRITEPROTECT failed: %d\n", errno);
return -errno;
}
return 0;
}
int main(int argc, char **argv)
{
int ksm_fd, ret;
ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR);
if (ksm_fd < 0) {
fprintf(stderr, "KSM not available\n");
return -errno;
}
map = mmap(NULL, MMAP_SIZE, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_ANON, -1, 0);
if (map == MAP_FAILED) {
fprintf(stderr, "mmap() failed\n");
return -errno;
}
ret = madvise(map, MMAP_SIZE, MADV_NOHUGEPAGE);
if (ret) {
fprintf(stderr, "MADV_NOHUGEPAGE failed\n");
return -errno;
}
/* Fill with same value and trigger merging. */
memset(map, 0xff, MMAP_SIZE);
ret = madvise(map, MMAP_SIZE, MADV_MERGEABLE);
if (ret) {
fprintf(stderr, "MADV_MERGEABLE failed\n");
return -errno;
}
/*
* Run KSM to trigger merging and wait a bit until merging should be
* done.
*/
if (write(ksm_fd, "1", 1) != 1) {
fprintf(stderr, "Running KSM failed\n");
}
sleep(10);
/* Write-protect the range with UFFD. */
if (setup_uffd())
return 1;
/* Trigger unsharing. */
ret = madvise(map, MMAP_SIZE, MADV_UNMERGEABLE);
if (ret) {
fprintf(stderr, "MADV_UNMERGEABLE failed\n");
return -errno;
}
return 0;
}
--------------------------------------------------------------------------
Consequently, we will no longer trigger a fake write fault and break COW
without any such side-effects.
This is primarily a fix for KSM+userfaultfd-wp, however, the fake write
fault was always questionable. As this fix is not easy to backport and
it's not very critical, let's not cc stable.
Link: https://lkml.kernel.org/r/20220930141931.174362-5-david@xxxxxxxxxx
Fixes: 529b930b87d9 ("userfaultfd: wp: hook userfault handler to write protection fault")
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
Acked-by: Peter Xu <peterx@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/ksm.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
--- a/mm/ksm.c~mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare
+++ a/mm/ksm.c
@@ -420,17 +420,15 @@ static inline bool ksm_test_exit(struct
}
/*
- * We use break_ksm to break COW on a ksm page: it's a stripped down
+ * We use break_ksm to break COW on a ksm page by triggering unsharing,
+ * such that the ksm page will get replaced by an exclusive anonymous page.
*
- * if (get_user_pages(addr, 1, FOLL_WRITE, &page, NULL) == 1)
- * put_page(page);
- *
- * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma,
+ * We take great care only to touch a ksm page, in a VM_MERGEABLE vma,
* in case the application has unmapped and remapped mm,addr meanwhile.
* Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP
* mmap of /dev/mem, where we would not want to touch it.
*
- * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context
+ * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context
* of the process that owns 'vma'. We also do not want to enforce
* protection keys here anyway.
*/
@@ -454,7 +452,7 @@ static int break_ksm(struct vm_area_stru
if (!ksm_page)
return 0;
ret = handle_mm_fault(vma, addr,
- FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE,
+ FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE,
NULL);
} while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM)));
/*
_
Patches currently in -mm which might be from david@xxxxxxxxxx are
selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch
mm-ksm-simplify-break_ksm-to-not-rely-on-vm_fault_write.patch
mm-remove-vm_fault_write.patch
mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
mm-pagewalk-add-walk_page_range_vma.patch
mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch
mm-gup-remove-foll_migration.patch
