On 14 Jul 2024, at 20:04, Gavin Shan wrote:
> xarray can't support arbitrary page cache size. the largest and
> supported page cache size is defined as MAX_PAGECACHE_ORDER by
> commit 099d90642a71 ("mm/filemap: make MAX_PAGECACHE_ORDER acceptable
> to xarray"). However, it's possible to have 512MB page cache in
> the huge memory's collapsing path on ARM64 system whose base page
> size is 64KB. 512MB page cache is breaking the limitation and a
> warning is raised when the xarray entry is split as shown in the
> following example.
>
> [root@dhcp-10-26-1-207 ~]# cat /proc/1/smaps | grep KernelPageSize
> KernelPageSize: 64 kB
> [root@dhcp-10-26-1-207 ~]# cat /tmp/test.c
> :
> int main(int argc, char **argv)
> {
> const char *filename = TEST_XFS_FILENAME;
> int fd = 0;
> void *buf = (void *)-1, *p;
> int pgsize = getpagesize();
> int ret = 0;
>
> if (pgsize != 0x10000) {
> fprintf(stdout, "System with 64KB base page size is required!\n");
> return -EPERM;
> }
>
> system("echo 0 > /sys/devices/virtual/bdi/253:0/read_ahead_kb");
> system("echo 1 > /proc/sys/vm/drop_caches");
>
> /* Open the xfs file */
> fd = open(filename, O_RDONLY);
> assert(fd > 0);
>
> /* Create VMA */
> buf = mmap(NULL, TEST_MEM_SIZE, PROT_READ, MAP_SHARED, fd, 0);
> assert(buf != (void *)-1);
> fprintf(stdout, "mapped buffer at 0x%p\n", buf);
>
> /* Populate VMA */
> ret = madvise(buf, TEST_MEM_SIZE, MADV_NOHUGEPAGE);
> assert(ret == 0);
> ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_READ);
> assert(ret == 0);
>
> /* Collapse VMA */
> ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE);
> assert(ret == 0);
> ret = madvise(buf, TEST_MEM_SIZE, MADV_COLLAPSE);
> if (ret) {
> fprintf(stdout, "Error %d to madvise(MADV_COLLAPSE)\n", errno);
> goto out;
> }
>
> /* Split xarray entry. Write permission is needed */
> munmap(buf, TEST_MEM_SIZE);
> buf = (void *)-1;
> close(fd);
> fd = open(filename, O_RDWR);
> assert(fd > 0);
> fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
> TEST_MEM_SIZE - pgsize, pgsize);
> out:
> if (buf != (void *)-1)
> munmap(buf, TEST_MEM_SIZE);
> if (fd > 0)
> close(fd);
>
> return ret;
> }
>
> [root@dhcp-10-26-1-207 ~]# gcc /tmp/test.c -o /tmp/test
> [root@dhcp-10-26-1-207 ~]# /tmp/test
> ------------[ cut here ]------------
> WARNING: CPU: 25 PID: 7560 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128
> Modules linked in: nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib \
> nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct \
> nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 \
> ip_set rfkill nf_tables nfnetlink vfat fat virtio_balloon drm fuse \
> xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 virtio_net \
> sha1_ce net_failover virtio_blk virtio_console failover dimlib virtio_mmio
> CPU: 25 PID: 7560 Comm: test Kdump: loaded Not tainted 6.10.0-rc7-gavin+ #9
> Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20240524-1.el9 05/24/2024
> pstate: 83400005 (Nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
> pc : xas_split_alloc+0xf8/0x128
> lr : split_huge_page_to_list_to_order+0x1c4/0x780
> sp : ffff8000ac32f660
> x29: ffff8000ac32f660 x28: ffff0000e0969eb0 x27: ffff8000ac32f6c0
> x26: 0000000000000c40 x25: ffff0000e0969eb0 x24: 000000000000000d
> x23: ffff8000ac32f6c0 x22: ffffffdfc0700000 x21: 0000000000000000
> x20: 0000000000000000 x19: ffffffdfc0700000 x18: 0000000000000000
> x17: 0000000000000000 x16: ffffd5f3708ffc70 x15: 0000000000000000
> x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
> x11: ffffffffffffffc0 x10: 0000000000000040 x9 : ffffd5f3708e692c
> x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff0000e0969eb8
> x5 : ffffd5f37289e378 x4 : 0000000000000000 x3 : 0000000000000c40
> x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000
> Call trace:
> xas_split_alloc+0xf8/0x128
> split_huge_page_to_list_to_order+0x1c4/0x780
> truncate_inode_partial_folio+0xdc/0x160
> truncate_inode_pages_range+0x1b4/0x4a8
> truncate_pagecache_range+0x84/0xa0
> xfs_flush_unmap_range+0x70/0x90 [xfs]
> xfs_file_fallocate+0xfc/0x4d8 [xfs]
> vfs_fallocate+0x124/0x2f0
> ksys_fallocate+0x4c/0xa0
> __arm64_sys_fallocate+0x24/0x38
> invoke_syscall.constprop.0+0x7c/0xd8
> do_el0_svc+0xb4/0xd0
> el0_svc+0x44/0x1d8
> el0t_64_sync_handler+0x134/0x150
> el0t_64_sync+0x17c/0x180
>
> Fix it by correcting the supported page cache orders, different sets
> for DAX and other files. With it corrected, 512MB page cache becomes
> disallowed on all non-DAX files on ARM64 system where the base page
> size is 64KB. After this patch is applied, the test program fails
> with error -EINVAL returned from __thp_vma_allowable_orders() and
> the madvise() system call to collapse the page caches.
>
> Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache")
> Cc: <stable@xxxxxxxxxxxxxxx> # v5.17+
> Signed-off-by: Gavin Shan <gshan@xxxxxxxxxx>
> ---
> v2: Corrected supported orders for DAX and other files as suggested
> by David/Matthew/Baolin
> ---
> include/linux/huge_mm.h | 12 +++++++++---
> mm/huge_memory.c | 12 ++++++++++--
> 2 files changed, 19 insertions(+), 5 deletions(-)
LGTM. Thanks. Acked-by: Zi Yan <ziy@xxxxxxxxxx>
--
Best Regards,
Yan, Zi
Attachment:
signature.asc
Description: OpenPGP digital signature
