[PATCH v2 0/4] mm/filemap: Limit page cache size to that supported by xarray

[PATCH v2 0/4] mm/filemap: Limit page cache size to that supported by xarray

[Gavin Shan]

Currently, xarray can't support arbitrary page cache size. More details
can be found from the WARN_ON() statement in xas_split_alloc(). In our
test whose code is attached below, we hit the WARN_ON() on ARM64 system
where the base page size is 64KB and huge page size is 512MB. The issue
was reported long time ago and some discussions on it can be found here
[1].

[1] https://www.spinics.net/lists/linux-xfs/msg75404.html

In order to fix the issue, we need to adjust MAX_PAGECACHE_ORDER to one
supported by xarray and avoid PMD-sized page cache if needed. The code
changes are suggested by David Hildenbrand.

PATCH[1] adjusts MAX_PAGECACHE_ORDER to that supported by xarray
PATCH[2-3] avoids PMD-sized page cache in the synchronous readahead path
PATCH[4] avoids PMD-sized page cache for shmem files if needed

Test program
============
# cat test.c
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include <fcntl.h>
#include <errno.h>
#include <sys/syscall.h>
#include <sys/mman.h>

#define TEST_XFS_FILENAME	"/tmp/data"
#define TEST_SHMEM_FILENAME	"/dev/shm/data"
#define TEST_MEM_SIZE		0x20000000

int main(int argc, char **argv)
{
	const char *filename;
	int fd = 0;
	void *buf = (void *)-1, *p;
	int pgsize = getpagesize();
	int ret;

	if (pgsize != 0x10000) {
		fprintf(stderr, "64KB base page size is required\n");
		return -EPERM;
	}

	system("echo force > /sys/kernel/mm/transparent_hugepage/shmem_enabled");
	system("rm -fr /tmp/data");
	system("rm -fr /dev/shm/data");
	system("echo 1 > /proc/sys/vm/drop_caches");

	/* Open xfs or shmem file */
	filename = TEST_XFS_FILENAME;
	if (argc > 1 && !strcmp(argv[1], "shmem"))
		filename = TEST_SHMEM_FILENAME;

	fd = open(filename, O_CREAT | O_RDWR | O_TRUNC);
	if (fd < 0) {
		fprintf(stderr, "Unable to open <%s>\n", filename);
		return -EIO;
	}

	/* Extend file size */
	ret = ftruncate(fd, TEST_MEM_SIZE);
	if (ret) {
		fprintf(stderr, "Error %d to ftruncate()\n", ret);
		goto cleanup;
	}

	/* Create VMA */
	buf = mmap(NULL, TEST_MEM_SIZE,
		   PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
	if (buf == (void *)-1) {
		fprintf(stderr, "Unable to mmap <%s>\n", filename);
		goto cleanup;
	}

	fprintf(stdout, "mapped buffer at 0x%p\n", buf);
	ret = madvise(buf, TEST_MEM_SIZE, MADV_HUGEPAGE);
        if (ret) {
		fprintf(stderr, "Unable to madvise(MADV_HUGEPAGE)\n");
		goto cleanup;
	}

	/* Populate VMA */
	ret = madvise(buf, TEST_MEM_SIZE, MADV_POPULATE_WRITE);
	if (ret) {
		fprintf(stderr, "Error %d to madvise(MADV_POPULATE_WRITE)\n", ret);
		goto cleanup;
	}

	/* Punch the file to enforce xarray split */
	ret = fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
        		TEST_MEM_SIZE - pgsize, pgsize);
	if (ret)
		fprintf(stderr, "Error %d to fallocate()\n", ret);

cleanup:
	if (buf != (void *)-1)
		munmap(buf, TEST_MEM_SIZE);
	if (fd > 0)
		close(fd);

	return 0;
}

# gcc test.c -o test
# cat /proc/1/smaps | grep KernelPageSize | head -n 1
KernelPageSize:       64 kB
# ./test shmem
   :
------------[ cut here ]------------
WARNING: CPU: 17 PID: 5253 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 nf_tables rfkill nfnetlink vfat fat virtio_balloon          \
drm fuse xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64  \
virtio_net sha1_ce net_failover failover virtio_console virtio_blk \
dimlib virtio_mmio
CPU: 17 PID: 5253 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-gavin+ #12
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+0x1c4/0x720
sp : ffff80008a92f5b0
x29: ffff80008a92f5b0 x28: ffff80008a92f610 x27: ffff80008a92f728
x26: 0000000000000cc0 x25: 000000000000000d x24: ffff0000cf00c858
x23: ffff80008a92f610 x22: ffffffdfc0600000 x21: 0000000000000000
x20: 0000000000000000 x19: ffffffdfc0600000 x18: 0000000000000000
x17: 0000000000000000 x16: 0000018000000000 x15: 3374004000000000
x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020
x11: 3374000000000000 x10: 3374e1c0ffff6000 x9 : ffffb463a84c681c
x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff00011c976ce0
x5 : ffffb463aa47e378 x4 : 0000000000000000 x3 : 0000000000000cc0
x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000
Call trace:
 xas_split_alloc+0xf8/0x128
 split_huge_page_to_list_to_order+0x1c4/0x720
 truncate_inode_partial_folio+0xdc/0x160
 shmem_undo_range+0x2bc/0x6a8
 shmem_fallocate+0x134/0x430
 vfs_fallocate+0x124/0x2e8
 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

Changelog
=========
v2:
  * Address David's comments and pick up ack tags from him
  * Swapped PATCH[v1 2/4] and PATCH[v1 3/4] and corrected fix tags
    based on comments from Andrew, David and Matthew

Gavin Shan (4):
  mm/filemap: Make MAX_PAGECACHE_ORDER acceptable to xarray
  mm/readahead: Limit page cache size in page_cache_ra_order()
  mm/filemap: Skip to create PMD-sized page cache if needed
  mm/shmem: Disable PMD-sized page cache if needed

 include/linux/pagemap.h | 11 +++++++++--
 mm/filemap.c            |  2 +-
 mm/readahead.c          |  8 ++++----
 mm/shmem.c              | 15 +++++++++++++--
 4 files changed, 27 insertions(+), 9 deletions(-)

-- 
2.45.1

[PATCH v2 3/4] mm/filemap: Skip to create PMD-sized page cache if needed

[Gavin Shan]

On ARM64, HPAGE_PMD_ORDER is 13 when the base page size is 64KB. The
PMD-sized page cache can't be supported by xarray as the following
error messages indicate.

------------[ cut here ]------------
WARNING: CPU: 35 PID: 7484 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      \
sha1_ce virtio_net net_failover virtio_console virtio_blk failover \
dimlib virtio_mmio
CPU: 35 PID: 7484 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-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+0x1c4/0x720
sp : ffff800087a4f6c0
x29: ffff800087a4f6c0 x28: ffff800087a4f720 x27: 000000001fffffff
x26: 0000000000000c40 x25: 000000000000000d x24: ffff00010625b858
x23: ffff800087a4f720 x22: ffffffdfc0780000 x21: 0000000000000000
x20: 0000000000000000 x19: ffffffdfc0780000 x18: 000000001ff40000
x17: 00000000ffffffff x16: 0000018000000000 x15: 51ec004000000000
x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020
x11: 51ec000000000000 x10: 51ece1c0ffff8000 x9 : ffffbeb961a44d28
x8 : 0000000000000003 x7 : ffffffdfc0456420 x6 : ffff0000e1aa6eb8
x5 : 20bf08b4fe778fca x4 : ffffffdfc0456420 x3 : 0000000000000c40
x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000
Call trace:
 xas_split_alloc+0xf8/0x128
 split_huge_page_to_list_to_order+0x1c4/0x720
 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+0x124/0x2e8
 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 skipping to allocate PMD-sized page cache when its size
is larger than MAX_PAGECACHE_ORDER. For this specific case, we will
fall to regular path where the readahead window is determined by BDI's
sysfs file (read_ahead_kb).

Fixes: 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings")
Cc: stable@kernel.org # v5.18+
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
---
 mm/filemap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 876cc64aadd7..b306861d9d36 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3124,7 +3124,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
-	if (vm_flags & VM_HUGEPAGE) {
+	if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 		ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
 		ra->size = HPAGE_PMD_NR;
-- 
2.45.1

[PATCH v2 4/4] mm/shmem: Disable PMD-sized page cache if needed

[Gavin Shan]

For shmem files, it's possible that PMD-sized page cache can't be
supported by xarray. For example, 512MB page cache on ARM64 when
the base page size is 64KB can't be supported by xarray. It leads
to errors as the following messages indicate when this sort of
xarray entry is split.

WARNING: CPU: 34 PID: 7578 at lib/xarray.c:1025 xas_split_alloc+0xf8/0x128
Modules linked in: binfmt_misc 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 sha1_ce virtio_net \
net_failover virtio_console virtio_blk failover dimlib virtio_mmio
CPU: 34 PID: 7578 Comm: test Kdump: loaded Tainted: G W 6.10.0-rc5-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+0x1c4/0x720
sp : ffff8000882af5f0
x29: ffff8000882af5f0 x28: ffff8000882af650 x27: ffff8000882af768
x26: 0000000000000cc0 x25: 000000000000000d x24: ffff00010625b858
x23: ffff8000882af650 x22: ffffffdfc0900000 x21: 0000000000000000
x20: 0000000000000000 x19: ffffffdfc0900000 x18: 0000000000000000
x17: 0000000000000000 x16: 0000018000000000 x15: 52f8004000000000
x14: 0000e00000000000 x13: 0000000000002000 x12: 0000000000000020
x11: 52f8000000000000 x10: 52f8e1c0ffff6000 x9 : ffffbeb9619a681c
x8 : 0000000000000003 x7 : 0000000000000000 x6 : ffff00010b02ddb0
x5 : ffffbeb96395e378 x4 : 0000000000000000 x3 : 0000000000000cc0
x2 : 000000000000000d x1 : 000000000000000c x0 : 0000000000000000
Call trace:
 xas_split_alloc+0xf8/0x128
 split_huge_page_to_list_to_order+0x1c4/0x720
 truncate_inode_partial_folio+0xdc/0x160
 shmem_undo_range+0x2bc/0x6a8
 shmem_fallocate+0x134/0x430
 vfs_fallocate+0x124/0x2e8
 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 disabling PMD-sized page cache when HPAGE_PMD_ORDER is
larger than MAX_PAGECACHE_ORDER. As Matthew Wilcox pointed, the page
cache in a shmem file isn't represented by a multi-index entry and
doesn't have this limitation when the xarry entry is split until
commit 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache").

Fixes: 6b24ca4a1a8d ("mm: Use multi-index entries in the page cache")
Cc: stable@kernel.org # v5.17+
Signed-off-by: Gavin Shan <gshan@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
---
 mm/shmem.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index a8b181a63402..c1befe046c7e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -541,8 +541,9 @@ static bool shmem_confirm_swap(struct address_space *mapping,
 
 static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
 
-bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
-		   struct mm_struct *mm, unsigned long vm_flags)
+static bool __shmem_is_huge(struct inode *inode, pgoff_t index,
+			    bool shmem_huge_force, struct mm_struct *mm,
+			    unsigned long vm_flags)
 {
 	loff_t i_size;
 
@@ -573,6 +574,16 @@ bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force,
 	}
 }
 
+bool shmem_is_huge(struct inode *inode, pgoff_t index,
+		   bool shmem_huge_force, struct mm_struct *mm,
+		   unsigned long vm_flags)
+{
+	if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER)
+		return false;
+
+	return __shmem_is_huge(inode, index, shmem_huge_force, mm, vm_flags);
+}
+
 #if defined(CONFIG_SYSFS)
 static int shmem_parse_huge(const char *str)
 {
-- 
2.45.1