On Fri, Jul 26, 2024 at 04:55:46PM +0100, fdmanana@xxxxxxxxxx wrote:
> From: Filipe Manana <fdmanana@xxxxxxxx>
>
> Test that doing a direct IO append write to a file when the input buffer
> was not yet faulted in, does not result in an incorrect file size.
>
> This exercises a bug on btrfs reported by users and which is fixed by
> the following kernel patch:
>
> "btrfs: fix corruption after buffer fault in during direct IO append write"
>
> Signed-off-by: Filipe Manana <fdmanana@xxxxxxxx>
> ---
> .gitignore | 1 +
> src/Makefile | 2 +-
> src/dio-append-buf-fault.c | 131 +++++++++++++++++++++++++++++++++++++
> tests/generic/362 | 28 ++++++++
> tests/generic/362.out | 2 +
> 5 files changed, 163 insertions(+), 1 deletion(-)
> create mode 100644 src/dio-append-buf-fault.c
> create mode 100755 tests/generic/362
> create mode 100644 tests/generic/362.out
>
> diff --git a/.gitignore b/.gitignore
> index b5f15162..97c7e001 100644
> --- a/.gitignore
> +++ b/.gitignore
> @@ -72,6 +72,7 @@ tags
> /src/deduperace
> /src/detached_mounts_propagation
> /src/devzero
> +/src/dio-append-buf-fault
> /src/dio-buf-fault
> /src/dio-interleaved
> /src/dio-invalidate-cache
> diff --git a/src/Makefile b/src/Makefile
> index 99796137..559209be 100644
> --- a/src/Makefile
> +++ b/src/Makefile
> @@ -20,7 +20,7 @@ TARGETS = dirstress fill fill2 getpagesize holes lstat64 \
> t_get_file_time t_create_short_dirs t_create_long_dirs t_enospc \
> t_mmap_writev_overlap checkpoint_journal mmap-rw-fault allocstale \
> t_mmap_cow_memory_failure fake-dump-rootino dio-buf-fault rewinddir-test \
> - readdir-while-renames
> + readdir-while-renames dio-append-buf-fault
>
> LINUX_TARGETS = xfsctl bstat t_mtab getdevicesize preallo_rw_pattern_reader \
> preallo_rw_pattern_writer ftrunc trunc fs_perms testx looptest \
> diff --git a/src/dio-append-buf-fault.c b/src/dio-append-buf-fault.c
> new file mode 100644
> index 00000000..f4be4845
> --- /dev/null
> +++ b/src/dio-append-buf-fault.c
> @@ -0,0 +1,131 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2024 SUSE Linux Products GmbH. All Rights Reserved.
> + */
> +
> +/*
> + * Test a direct IO write in append mode with a buffer that was not faulted in
> + * (or just partially) before the write.
> + */
> +
> +/* Get the O_DIRECT definition. */
> +#ifndef _GNU_SOURCE
> +#define _GNU_SOURCE
> +#endif
> +
> +#include <stdio.h>
> +#include <stdlib.h>
> +#include <unistd.h>
> +#include <stdint.h>
> +#include <fcntl.h>
> +#include <errno.h>
> +#include <string.h>
> +#include <sys/mman.h>
> +#include <sys/stat.h>
> +
> +int main(int argc, char *argv[])
> +{
> + struct stat stbuf;
> + int fd;
> + long pagesize;
> + void *buf;
> + ssize_t ret;
> +
> + if (argc != 2) {
> + fprintf(stderr, "Use: %s <file path>\n", argv[0]);
> + return 1;
> + }
> +
> + /*
> + * First try an append write against an empty file of a buffer with a
> + * size matching the page size. The buffer is not faulted in before
> + * attempting the write.
> + */
> +
> + fd = open(argv[1], O_WRONLY | O_CREAT | O_TRUNC | O_DIRECT | O_APPEND, 0666);
> + if (fd == -1) {
> + perror("Failed to open/create file");
> + return 2;
> + }
> +
> + pagesize = sysconf(_SC_PAGE_SIZE);
> + if (pagesize == -1) {
> + perror("Failed to get page size");
> + return 3;
> + }
> +
> + buf = mmap(NULL, pagesize, PROT_READ | PROT_WRITE,
> + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
> + if (buf == MAP_FAILED) {
> + perror("Failed to allocate first buffer");
> + return 4;
> + }
> +
> + ret = write(fd, buf, pagesize);
> + if (ret < 0) {
> + perror("First write failed");
> + return 5;
> + }
> +
> + ret = fstat(fd, &stbuf);
> + if (ret < 0) {
> + perror("First stat failed");
> + return 6;
> + }
> +
> + if (stbuf.st_size != pagesize) {
> + fprintf(stderr,
> + "Wrong file size after first write, got %jd expected %ld\n",
> + (intmax_t)stbuf.st_size, pagesize);
> + return 7;
> + }
> +
> + munmap(buf, pagesize);
> + close(fd);
> +
> + /*
> + * Now try an append write against an empty file of a buffer with a
> + * size matching twice the page size. Only the first page of the buffer
> + * is faulted in before attempting the write, so that the second page
> + * should be faulted in during the write.
> + */
> + fd = open(argv[1], O_WRONLY | O_CREAT | O_TRUNC | O_DIRECT | O_APPEND, 0666);
> + if (fd == -1) {
> + perror("Failed to open/create file");
> + return 8;
> + }
> +
> + buf = mmap(NULL, pagesize * 2, PROT_READ | PROT_WRITE,
> + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
> + if (buf == MAP_FAILED) {
> + perror("Failed to allocate second buffer");
> + return 9;
> + }
> +
> + /* Fault in first page of the buffer before the write. */
> + memset(buf, 0, 1);
> +
> + ret = write(fd, buf, pagesize * 2);
> + if (ret < 0) {
> + perror("Second write failed");
Hi Filipe,
This patch looks good to me, just a question about this part. Is it possible
to get (0 < ret < pagesize * 2) at here? Is so, should we report fail too?
> + return 10;
> + }
> +
> + ret = fstat(fd, &stbuf);
> + if (ret < 0) {
> + perror("Second stat failed");
> + return 11;
> + }
> +
> + if (stbuf.st_size != pagesize * 2) {
> + fprintf(stderr,
> + "Wrong file size after second write, got %jd expected %ld\n",
> + (intmax_t)stbuf.st_size, pagesize * 2);
Does this try to check the stbuf.st_size isn't equal to the write(2) return
value? Or checks stbuf.st_size != pagesize * 2, when the return value is
good (equal to pagesize * 2) ?
Thanks,
Zorro
> + return 12;
> + }
> +
> + munmap(buf, pagesize * 2);
> + close(fd);
> +
> + return 0;
> +}
[snip]
