On Wed, Feb 19, 2025 at 3:25 AM Barry Song <21cnbao@xxxxxxxxx> wrote:
>
> From: Barry Song <v-songbaohua@xxxxxxxx>
>
> userfaultfd_move() checks whether the PTE entry is present or a
> swap entry.
>
> - If the PTE entry is present, move_present_pte() handles folio
> migration by setting:
>
> src_folio->index = linear_page_index(dst_vma, dst_addr);
>
> - If the PTE entry is a swap entry, move_swap_pte() simply copies
> the PTE to the new dst_addr.
>
> This approach is incorrect because even if the PTE is a swap
> entry, it can still reference a folio that remains in the swap
> cache.
>
> If do_swap_page() is triggered, it may locate the folio in the
> swap cache. However, during add_rmap operations, a kernel panic
> can occur due to:
> page_pgoff(folio, page) != linear_page_index(vma, address)
>
> $./a.out > /dev/null
> [ 13.336953] page: refcount:6 mapcount:1 mapping:00000000f43db19c index:0xffffaf150 pfn:0x4667c
> [ 13.337520] head: order:2 mapcount:1 entire_mapcount:0 nr_pages_mapped:1 pincount:0
> [ 13.337716] memcg:ffff00000405f000
> [ 13.337849] anon flags: 0x3fffc0000020459(locked|uptodate|dirty|owner_priv_1|head|swapbacked|node=0|zone=0|lastcpupid=0xffff)
> [ 13.338630] raw: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
> [ 13.338831] raw: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
> [ 13.339031] head: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
> [ 13.339204] head: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
> [ 13.339375] head: 03fffc0000000202 fffffdffc0199f01 ffffffff00000000 0000000000000001
> [ 13.339546] head: 0000000000000004 0000000000000000 00000000ffffffff 0000000000000000
> [ 13.339736] page dumped because: VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address))
> [ 13.340190] ------------[ cut here ]------------
> [ 13.340316] kernel BUG at mm/rmap.c:1380!
> [ 13.340683] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
> [ 13.340969] Modules linked in:
> [ 13.341257] CPU: 1 UID: 0 PID: 107 Comm: a.out Not tainted 6.14.0-rc3-gcf42737e247a-dirty #299
> [ 13.341470] Hardware name: linux,dummy-virt (DT)
> [ 13.341671] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
> [ 13.341815] pc : __page_check_anon_rmap+0xa0/0xb0
> [ 13.341920] lr : __page_check_anon_rmap+0xa0/0xb0
> [ 13.342018] sp : ffff80008752bb20
> [ 13.342093] x29: ffff80008752bb20 x28: fffffdffc0199f00 x27: 0000000000000001
> [ 13.342404] x26: 0000000000000000 x25: 0000000000000001 x24: 0000000000000001
> [ 13.342575] x23: 0000ffffaf0d0000 x22: 0000ffffaf0d0000 x21: fffffdffc0199f00
> [ 13.342731] x20: fffffdffc0199f00 x19: ffff000006210700 x18: 00000000ffffffff
> [ 13.342881] x17: 6c203d2120296567 x16: 6170202c6f696c6f x15: 662866666f67705f
> [ 13.343033] x14: 6567617028454741 x13: 2929737365726464 x12: ffff800083728ab0
> [ 13.343183] x11: ffff800082996bf8 x10: 0000000000000fd7 x9 : ffff80008011bc40
> [ 13.343351] x8 : 0000000000017fe8 x7 : 00000000fffff000 x6 : ffff8000829eebf8
> [ 13.343498] x5 : c0000000fffff000 x4 : 0000000000000000 x3 : 0000000000000000
> [ 13.343645] x2 : 0000000000000000 x1 : ffff0000062db980 x0 : 000000000000005f
> [ 13.343876] Call trace:
> [ 13.344045] __page_check_anon_rmap+0xa0/0xb0 (P)
> [ 13.344234] folio_add_anon_rmap_ptes+0x22c/0x320
> [ 13.344333] do_swap_page+0x1060/0x1400
> [ 13.344417] __handle_mm_fault+0x61c/0xbc8
> [ 13.344504] handle_mm_fault+0xd8/0x2e8
> [ 13.344586] do_page_fault+0x20c/0x770
> [ 13.344673] do_translation_fault+0xb4/0xf0
> [ 13.344759] do_mem_abort+0x48/0xa0
> [ 13.344842] el0_da+0x58/0x130
> [ 13.344914] el0t_64_sync_handler+0xc4/0x138
> [ 13.345002] el0t_64_sync+0x1ac/0x1b0
> [ 13.345208] Code: aa1503e0 f000f801 910f6021 97ff5779 (d4210000)
> [ 13.345504] ---[ end trace 0000000000000000 ]---
> [ 13.345715] note: a.out[107] exited with irqs disabled
> [ 13.345954] note: a.out[107] exited with preempt_count 2
>
> Fully fixing it would be quite complex, requiring similar handling
> of folios as done in move_present_pte. For now, a quick solution
> is to return -EBUSY.
> I'd like to see others' opinions on whether a full fix is worth
> pursuing.
>
Thanks a lot for finding this.
As a user of MOVE ioctl (in Android GC) I strongly urge you to fix
this properly. Because this is not going to be a rare occurrence in
the case of Android. And when -EBUSY is returned, all that userspace
can do is touch the page, which also does not guarantee that a
subsequent retry of the ioctl will succeed.
> For anyone interested in reproducing it, the a.out test program is
> as below,
>
> #define _GNU_SOURCE
> #include <stdio.h>
> #include <stdlib.h>
> #include <string.h>
> #include <sys/mman.h>
> #include <sys/ioctl.h>
> #include <sys/syscall.h>
> #include <linux/userfaultfd.h>
> #include <fcntl.h>
> #include <pthread.h>
> #include <unistd.h>
> #include <poll.h>
> #include <errno.h>
>
> #define PAGE_SIZE 4096
> #define REGION_SIZE (512 * 1024)
>
> #ifndef UFFDIO_MOVE
> struct uffdio_move {
> __u64 dst;
> __u64 src;
> __u64 len;
> #define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0)
> #define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1)
> __u64 mode;
> __s64 move;
> };
> #define _UFFDIO_MOVE (0x05)
> #define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, struct uffdio_move)
> #endif
>
> void *src, *dst;
> int uffd;
>
> void *madvise_thread(void *arg) {
> if (madvise(src, REGION_SIZE, MADV_PAGEOUT) == -1) {
> perror("madvise MADV_PAGEOUT");
> }
> return NULL;
> }
>
> void *fault_handler_thread(void *arg) {
> struct uffd_msg msg;
> struct uffdio_move move;
> struct pollfd pollfd = { .fd = uffd, .events = POLLIN };
>
> pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL);
> pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL);
>
> while (1) {
> if (poll(&pollfd, 1, -1) == -1) {
> perror("poll");
> exit(EXIT_FAILURE);
> }
>
> if (read(uffd, &msg, sizeof(msg)) <= 0) {
> perror("read");
> exit(EXIT_FAILURE);
> }
>
> if (msg.event != UFFD_EVENT_PAGEFAULT) {
> fprintf(stderr, "Unexpected event\n");
> exit(EXIT_FAILURE);
> }
>
> move.src = (unsigned long)src + (msg.arg.pagefault.address - (unsigned long)dst);
> move.dst = msg.arg.pagefault.address & ~(PAGE_SIZE - 1);
> move.len = PAGE_SIZE;
> move.mode = 0;
>
> if (ioctl(uffd, UFFDIO_MOVE, &move) == -1) {
> perror("UFFDIO_MOVE");
> exit(EXIT_FAILURE);
> }
> }
> return NULL;
> }
>
> int main() {
> again:
> pthread_t thr, madv_thr;
> struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 };
> struct uffdio_register uffdio_register;
>
> src = mmap(NULL, REGION_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
> if (src == MAP_FAILED) {
> perror("mmap src");
> exit(EXIT_FAILURE);
> }
> memset(src, 1, REGION_SIZE);
>
> dst = mmap(NULL, REGION_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
> if (dst == MAP_FAILED) {
> perror("mmap dst");
> exit(EXIT_FAILURE);
> }
>
> uffd = syscall(SYS_userfaultfd, O_CLOEXEC | O_NONBLOCK);
> if (uffd == -1) {
> perror("userfaultfd");
> exit(EXIT_FAILURE);
> }
>
> if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
> perror("UFFDIO_API");
> exit(EXIT_FAILURE);
> }
>
> uffdio_register.range.start = (unsigned long)dst;
> uffdio_register.range.len = REGION_SIZE;
> uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
>
> if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
> perror("UFFDIO_REGISTER");
> exit(EXIT_FAILURE);
> }
>
> if (pthread_create(&madv_thr, NULL, madvise_thread, NULL) != 0) {
> perror("pthread_create madvise_thread");
> exit(EXIT_FAILURE);
> }
>
> if (pthread_create(&thr, NULL, fault_handler_thread, NULL) != 0) {
> perror("pthread_create fault_handler_thread");
> exit(EXIT_FAILURE);
> }
>
> for (size_t i = 0; i < REGION_SIZE; i += PAGE_SIZE) {
> char val = ((char *)dst)[i];
> printf("Accessing dst at offset %zu, value: %d\n", i, val);
> }
>
> pthread_join(madv_thr, NULL);
> pthread_cancel(thr);
> pthread_join(thr, NULL);
>
> munmap(src, REGION_SIZE);
> munmap(dst, REGION_SIZE);
> close(uffd);
> goto again;
> return 0;
> }
>
> As long as you enable mTHP (which likely increases the residency
> time of swapcache), you can reproduce the issue within a few
> seconds. But I guess the same race condition also exists with
> small folios.
>
> Fixes: adef440691bab ("userfaultfd: UFFDIO_MOVE uABI")
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Cc: Suren Baghdasaryan <surenb@xxxxxxxxxx>
> Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
> Cc: Axel Rasmussen <axelrasmussen@xxxxxxxxxx>
> Cc: Brian Geffon <bgeffon@xxxxxxxxxx>
> Cc: Christian Brauner <brauner@xxxxxxxxxx>
> Cc: David Hildenbrand <david@xxxxxxxxxx>
> Cc: Hugh Dickins <hughd@xxxxxxxxxx>
> Cc: Jann Horn <jannh@xxxxxxxxxx>
> Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
> Cc: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
> Cc: Lokesh Gidra <lokeshgidra@xxxxxxxxxx>
> Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
> Cc: Michal Hocko <mhocko@xxxxxxxx>
> Cc: Mike Rapoport (IBM) <rppt@xxxxxxxxxx>
> Cc: Nicolas Geoffray <ngeoffray@xxxxxxxxxx>
> Cc: Peter Xu <peterx@xxxxxxxxxx>
> Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
> Cc: Shuah Khan <shuah@xxxxxxxxxx>
> Cc: ZhangPeng <zhangpeng362@xxxxxxxxxx>
> Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
> ---
> mm/userfaultfd.c | 11 +++++++++++
> 1 file changed, 11 insertions(+)
>
> diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
> index 867898c4e30b..34cf1c8c725d 100644
> --- a/mm/userfaultfd.c
> +++ b/mm/userfaultfd.c
> @@ -18,6 +18,7 @@
> #include <asm/tlbflush.h>
> #include <asm/tlb.h>
> #include "internal.h"
> +#include "swap.h"
>
> static __always_inline
> bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
> @@ -1079,9 +1080,19 @@ static int move_swap_pte(struct mm_struct *mm,
> pmd_t *dst_pmd, pmd_t dst_pmdval,
> spinlock_t *dst_ptl, spinlock_t *src_ptl)
> {
> + struct folio *folio;
> + swp_entry_t entry;
> +
> if (!pte_swp_exclusive(orig_src_pte))
> return -EBUSY;
>
> + entry = pte_to_swp_entry(orig_src_pte);
> + folio = filemap_get_folio(swap_address_space(entry), swap_cache_index(entry));
> + if (!IS_ERR(folio)) {
> + folio_put(folio);
> + return -EBUSY;
> + }
> +
> double_pt_lock(dst_ptl, src_ptl);
>
> if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
> --
> 2.39.3 (Apple Git-146)
>
