On Wed, Mar 20, 2024 at 10:36:42AM -0400, Josef Bacik wrote:
> Btrfs had a deadlock that you could trigger by mmap'ing a large file and
> using that as the buffer for fiemap. This test adds a c program to do
> this, and the fstest creates a large enough file and then runs the
> reproducer on the file. Without the fix btrfs deadlocks, with the fix
> we pass fine.
>
> Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
> ---
> v2->v3:
> - Add fiemap-fault to .gitignore
> - Added a _cleanup() helper
> - Just let the output of fiemap-fault go instead of using || _fail
> - Added the munmap
> - Moved $dst to $TEST_DIR/$seq
>
> .gitignore | 1 +
> src/Makefile | 2 +-
> src/fiemap-fault.c | 74 +++++++++++++++++++++++++++++++++++++++++++
> tests/generic/808 | 48 ++++++++++++++++++++++++++++
> tests/generic/808.out | 2 ++
> 5 files changed, 126 insertions(+), 1 deletion(-)
> create mode 100644 src/fiemap-fault.c
> create mode 100755 tests/generic/808
> create mode 100644 tests/generic/808.out
>
> diff --git a/.gitignore b/.gitignore
> index 3b160209..f0fb72bd 100644
> --- a/.gitignore
> +++ b/.gitignore
> @@ -205,6 +205,7 @@ tags
> /src/vfs/mount-idmapped
> /src/log-writes/replay-log
> /src/perf/*.pyc
> +/src/filemap-fault
>
> # Symlinked files
> /tests/generic/035.out
> diff --git a/src/Makefile b/src/Makefile
> index e7442487..ab98a06f 100644
> --- a/src/Makefile
> +++ b/src/Makefile
> @@ -34,7 +34,7 @@ LINUX_TARGETS = xfsctl bstat t_mtab getdevicesize preallo_rw_pattern_reader \
> attr_replace_test swapon mkswap t_attr_corruption t_open_tmpfiles \
> fscrypt-crypt-util bulkstat_null_ocount splice-test chprojid_fail \
> detached_mounts_propagation ext4_resize t_readdir_3 splice2pipe \
> - uuid_ioctl t_snapshot_deleted_subvolume
> + uuid_ioctl t_snapshot_deleted_subvolume fiemap-fault
>
> EXTRA_EXECS = dmerror fill2attr fill2fs fill2fs_check scaleread.sh \
> btrfs_crc32c_forged_name.py popdir.pl popattr.py \
> diff --git a/src/fiemap-fault.c b/src/fiemap-fault.c
> new file mode 100644
> index 00000000..73260068
> --- /dev/null
> +++ b/src/fiemap-fault.c
> @@ -0,0 +1,74 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2024 Meta Platforms, Inc. All Rights Reserved.
> + */
> +
> +#include <sys/ioctl.h>
> +#include <sys/mman.h>
> +#include <sys/types.h>
> +#include <sys/stat.h>
> +#include <linux/fs.h>
> +#include <linux/types.h>
> +#include <linux/fiemap.h>
> +#include <err.h>
> +#include <errno.h>
> +#include <fcntl.h>
> +#include <stdio.h>
> +#include <string.h>
> +#include <unistd.h>
> +
> +int prep_mmap_buffer(int fd, void **addr)
> +{
> + struct stat st;
> + int ret;
> +
> + ret = fstat(fd, &st);
> + if (ret)
> + err(1, "failed to stat %d", fd);
> +
> + *addr = mmap(NULL, st.st_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
> + if (*addr == MAP_FAILED)
> + err(1, "failed to mmap %d", fd);
> +
> + return st.st_size;
> +}
> +
> +int main(int argc, char *argv[])
> +{
> + struct fiemap *fiemap;
> + size_t sz, last = 0;
> + void *buf = NULL;
> + int ret, fd;
> +
> + if (argc != 2)
> + errx(1, "no in and out file name arguments given");
> +
> + fd = open(argv[1], O_RDWR, 0666);
> + if (fd == -1)
> + err(1, "failed to open %s", argv[1]);
> +
> + sz = prep_mmap_buffer(fd, &buf);
> +
> + fiemap = (struct fiemap *)buf;
> + fiemap->fm_flags = 0;
> + fiemap->fm_extent_count = (sz - sizeof(struct fiemap)) /
> + sizeof(struct fiemap_extent);
> +
> + while (last < sz) {
> + int i;
> +
> + fiemap->fm_start = last;
> + fiemap->fm_length = sz - last;
> +
> + ret = ioctl(fd, FS_IOC_FIEMAP, (unsigned long)fiemap);
> + if (ret < 0)
> + err(1, "fiemap failed %d", errno);
> + for (i = 0; i < fiemap->fm_mapped_extents; i++)
> + last = fiemap->fm_extents[i].fe_logical +
> + fiemap->fm_extents[i].fe_length;
> + }
> +
> + munmap(buf, sz);
> + close(fd);
> + return 0;
> +}
> diff --git a/tests/generic/808 b/tests/generic/808
> new file mode 100755
> index 00000000..36015f35
> --- /dev/null
> +++ b/tests/generic/808
> @@ -0,0 +1,48 @@
> +#! /bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +# Copyright (c) 2024 Meta Platforms, Inc. All Rights Reserved.
> +#
> +# FS QA Test 808
> +#
> +# Test fiemap into an mmaped buffer of the same file
> +#
> +# Create a reasonably large file, then run a program which mmaps it and uses
> +# that as a buffer for an fiemap call. This is a regression test for btrfs
> +# where we used to hold a lock for the duration of the fiemap call which would
> +# result in a deadlock if we page faulted.
> +#
> +. ./common/preamble
> +_begin_fstest quick auto fiemap
> +[ $FSTYP == "btrfs" ] && \
> + _fixed_by_kernel_commit b0ad381fa769 \
> + "btrfs: fix deadlock with fiemap and extent locking"
> +
> +_cleanup()
> +{
> + rm -f $dst
> + cd /
> + rm -r -f $tmp.*
> +}
> +
> +# real QA test starts here
> +_supported_fs generic
> +_require_test
> +_require_odirect
> +_require_test_program fiemap-fault
> +dst=$TEST_DIR/$seq/fiemap-fault
> +
> +mkdir -p $TEST_DIR/$seq
> +
> +echo "Silence is golden"
> +
> +for i in $(seq 0 2 1000)
> +do
> + $XFS_IO_PROG -d -f -c "pwrite -q $((i * 4096)) 4096" $dst
> +done
I don't know if there's a specific reason that this does directio writes
at alternating offsets other than forcing allocations, but usually we do:
$XFS_IO_PROG -f -c "pwrite -q 0 409600" $dst
$src/punch-alternating $dst
to generate a file with a bunch of extent records. Also, since this is
a generic test that wants to create a file with sparse holes, it really
ought to be querying the file's allocation unit size:
blksz=$(_get_file_block_size $TEST_DIR)
$XFS_IO_PROG -f -c "pwrite -q 0 $((blksz * 100))" $dst
--D
> +
> +$here/src/fiemap-fault $dst
> +
> +# success, all done
> +status=$?
> +exit
> +
> diff --git a/tests/generic/808.out b/tests/generic/808.out
> new file mode 100644
> index 00000000..88253428
> --- /dev/null
> +++ b/tests/generic/808.out
> @@ -0,0 +1,2 @@
> +QA output created by 808
> +Silence is golden
> --
> 2.43.0
>
>
