linux_dsm_epyc7002/fs
Chris Mason 56244ef151 Btrfs: fix handling of faults from btrfs_copy_from_user
When btrfs_copy_from_user isn't able to copy all of the pages, we need
to adjust our accounting to reflect the work that was actually done.

Commit 2e78c927d7 changed around the decisions a little and we ended up
skipping the accounting adjustments some of the time.  This commit makes
sure that when we don't copy anything at all, we still hop into
the adjustments, and switches to release_bytes instead of write_bytes,
since write_bytes isn't aligned.

The accounting errors led to warnings during btrfs_destroy_inode:

[   70.847532] WARNING: CPU: 10 PID: 514 at fs/btrfs/inode.c:9350 btrfs_destroy_inode+0x2b3/0x2c0
[   70.847536] Modules linked in: i2c_piix4 virtio_net i2c_core input_leds button led_class serio_raw acpi_cpufreq sch_fq_codel autofs4 virtio_blk
[   70.847538] CPU: 10 PID: 514 Comm: umount Tainted: G        W 4.6.0-rc6_00062_g2997da1-dirty #23
[   70.847539] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.9.0-1.fc24 04/01/2014
[   70.847542]  0000000000000000 ffff880ff5cafab8 ffffffff8149d5e9 0000000000000202
[   70.847543]  0000000000000000 0000000000000000 0000000000000000 ffff880ff5cafb08
[   70.847547]  ffffffff8107bdfd ffff880ff5cafaf8 000024868120013d ffff880ff5cafb28
[   70.847547] Call Trace:
[   70.847550]  [<ffffffff8149d5e9>] dump_stack+0x51/0x78
[   70.847551]  [<ffffffff8107bdfd>] __warn+0xfd/0x120
[   70.847553]  [<ffffffff8107be3d>] warn_slowpath_null+0x1d/0x20
[   70.847555]  [<ffffffff8139c9e3>] btrfs_destroy_inode+0x2b3/0x2c0
[   70.847556]  [<ffffffff812003a1>] ? __destroy_inode+0x71/0x140
[   70.847558]  [<ffffffff812004b3>] destroy_inode+0x43/0x70
[   70.847559]  [<ffffffff810b7b5f>] ? wake_up_bit+0x2f/0x40
[   70.847560]  [<ffffffff81200c68>] evict+0x148/0x1d0
[   70.847562]  [<ffffffff81398ade>] ? start_transaction+0x3de/0x460
[   70.847564]  [<ffffffff81200d49>] dispose_list+0x59/0x80
[   70.847565]  [<ffffffff81201ba0>] evict_inodes+0x180/0x190
[   70.847566]  [<ffffffff812191ff>] ? __sync_filesystem+0x3f/0x50
[   70.847568]  [<ffffffff811e95f8>] generic_shutdown_super+0x48/0x100
[   70.847569]  [<ffffffff810b75c0>] ? woken_wake_function+0x20/0x20
[   70.847571]  [<ffffffff811e9796>] kill_anon_super+0x16/0x30
[   70.847573]  [<ffffffff81365cde>] btrfs_kill_super+0x1e/0x130
[   70.847574]  [<ffffffff811e99be>] deactivate_locked_super+0x4e/0x90
[   70.847576]  [<ffffffff811e9e61>] deactivate_super+0x51/0x70
[   70.847577]  [<ffffffff8120536f>] cleanup_mnt+0x3f/0x80
[   70.847579]  [<ffffffff81205402>] __cleanup_mnt+0x12/0x20
[   70.847581]  [<ffffffff81098358>] task_work_run+0x68/0xa0
[   70.847582]  [<ffffffff810022b6>] exit_to_usermode_loop+0xd6/0xe0
[   70.847583]  [<ffffffff81002e1d>] do_syscall_64+0xbd/0x170
[   70.847586]  [<ffffffff817d4dbc>] entry_SYSCALL64_slow_path+0x25/0x25

This is the test program I used to force short returns from
btrfs_copy_from_user

void *dontneed(void *arg)
{
	char *p = arg;
	int ret;

	while(1) {
		ret = madvise(p, BUFSIZE/4, MADV_DONTNEED);
		if (ret) {
			perror("madvise");
			exit(1);
		}
	}
}

int main(int ac, char **av) {
	int ret;
	int fd;
	char *filename;
	unsigned long offset;
	char *buf;
	int i;
	pthread_t tid;

	if (ac != 2) {
		fprintf(stderr, "usage: dammitdave filename\n");
		exit(1);
	}

	buf = mmap(NULL, BUFSIZE, PROT_READ|PROT_WRITE,
		   MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
	if (buf == MAP_FAILED) {
		perror("mmap");
		exit(1);
	}
	memset(buf, 'a', BUFSIZE);
	filename = av[1];

	ret = pthread_create(&tid, NULL, dontneed, buf);
	if (ret) {
		fprintf(stderr, "error %d from pthread_create\n", ret);
		exit(1);
	}

	ret = pthread_detach(tid);
	if (ret) {
		fprintf(stderr, "pthread detach failed %d\n", ret);
		exit(1);
	}

	while (1) {
		fd = open(filename, O_RDWR | O_CREAT, 0600);
		if (fd < 0) {
			perror("open");
			exit(1);
		}

		for (i = 0; i < ROUNDS; i++) {
			int this_write = BUFSIZE;

			offset = rand() % MAXSIZE;
			ret = pwrite(fd, buf, this_write, offset);
			if (ret < 0) {
				perror("pwrite");
				exit(1);
			} else if (ret != this_write) {
				fprintf(stderr, "short write to %s offset %lu ret %d\n",
					filename, offset, ret);
				exit(1);
			}
			if (i == ROUNDS - 1) {
				ret = sync_file_range(fd, offset, 4096,
				    SYNC_FILE_RANGE_WRITE);
				if (ret < 0) {
					perror("sync_file_range");
					exit(1);
				}
			}
		}
		ret = ftruncate(fd, 0);
		if (ret < 0) {
			perror("ftruncate");
			exit(1);
		}
		ret = close(fd);
		if (ret) {
			perror("close");
			exit(1);
		}
		ret = unlink(filename);
		if (ret) {
			perror("unlink");
			exit(1);
		}

	}
	return 0;
}

Signed-off-by: Chris Mason <clm@fb.com>
Reported-by: Dave Jones <dsj@fb.com>
Fixes: 2e78c927d7
cc: stable@vger.kernel.org # v4.6
Signed-off-by: Chris Mason <clm@fb.com>
2016-05-26 13:23:59 -07:00
..
9p mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
adfs fs/adfs/adfs.h: tidy up comments 2016-01-20 17:09:18 -08:00
affs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
afs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
autofs4 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2016-03-19 18:52:29 -07:00
befs kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
bfs kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
btrfs Btrfs: fix handling of faults from btrfs_copy_from_user 2016-05-26 13:23:59 -07:00
cachefiles mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
ceph libceph: make authorizer destruction independent of ceph_auth_client 2016-04-25 20:54:13 +02:00
cifs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
coda Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2016-01-23 12:24:56 -08:00
configfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
cramfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
crypto ext4/fscrypto: avoid RCU lookup in d_revalidate 2016-04-12 20:01:35 -07:00
debugfs debugfs: Make automount point inodes permanently empty 2016-04-12 15:01:53 -07:00
devpts devpts: more pty driver interface cleanups 2016-04-26 15:47:32 -07:00
dlm mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
ecryptfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
efivarfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
efs kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
exofs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
exportfs wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
ext2 mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
ext4 ext4/fscrypto: avoid RCU lookup in d_revalidate 2016-04-12 20:01:35 -07:00
f2fs fscrypto: don't let data integrity writebacks fail with ENOMEM 2016-04-12 10:25:30 -07:00
fat fat: add config option to set UTF-8 mount option by default 2016-03-22 15:36:02 -07:00
freevxfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
fscache mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
fuse fuse: Fix return value from fuse_get_user_pages() 2016-04-25 13:01:04 +02:00
gfs2 mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
hfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
hfsplus mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
hostfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
hpfs hpfs: don't truncate the file when delete fails 2016-02-27 19:15:51 -05:00
hugetlbfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
isofs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
jbd2 mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
jffs2 mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
jfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
kernfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
lockd lockd: constify nlmsvc_binding structure 2016-01-07 10:10:50 -05:00
logfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
minix mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
ncpfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
nfs These changes contains a fix for overlayfs interacting with some 2016-04-07 17:22:20 -07:00
nfs_common
nfsd Various bugfixes, a RDMA update from Chuck Lever, and support for a new 2016-03-24 19:50:32 -07:00
nilfs2 mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
nls
notify fsnotify: turn fsnotify reaper thread into a workqueue job 2016-02-18 16:23:24 -08:00
ntfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
ocfs2 ocfs2/dlm: return zero if deref_done message is successfully handled 2016-04-28 19:34:04 -07:00
omfs
openpromfs kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
orangefs Orangefs: cleanups and a strncpy vulnerability fix. 2016-04-09 10:33:58 -07:00
overlayfs fs: add file_dentry() 2016-03-26 16:14:37 -04:00
proc proc: prevent accessing /proc/<PID>/environ until it's ready 2016-05-05 17:38:53 -07:00
pstore mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
qnx4 kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
qnx6 mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
quota quota: Handle Q_GETNEXTQUOTA when quota is disabled 2016-03-29 17:20:10 +02:00
ramfs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
reiserfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
romfs kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
squashfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
sysfs
sysv mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
tracefs wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
ubifs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
udf udf: Fix conversion of 'dstring' fields to UTF8 2016-04-25 15:18:50 +02:00
ufs mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
xfs mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
aio.c
anon_inodes.c
attr.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
bad_inode.c fs/bad_inode.c: is_bad_inode can be boolean 2015-12-06 21:17:14 -05:00
binfmt_aout.c
binfmt_elf_fdpic.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
binfmt_elf.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
binfmt_em86.c
binfmt_flat.c
binfmt_misc.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
binfmt_script.c
block_dev.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
buffer.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
char_dev.c
compat_binfmt_elf.c
compat_ioctl.c Merge 4.5-rc4 into char-misc-next 2016-02-14 14:25:59 -08:00
compat.c saner calling conventions for copy_mount_options() 2016-01-04 10:28:32 -05:00
coredump.c fs/coredump: prevent fsuid=0 dumps into user-controlled directories 2016-03-22 15:36:02 -07:00
dax.c mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
dcache.c fs: add file_dentry() 2016-03-26 16:14:37 -04:00
dcookies.c
direct-io.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
drop_caches.c
eventfd.c eventfd: document lockless access in eventfd_poll 2016-03-22 15:36:02 -07:00
eventpoll.c timer: convert timer_slack_ns from unsigned long to u64 2016-03-17 15:09:34 -07:00
exec.c Merge branch 'mm-pkeys-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2016-03-20 19:08:56 -07:00
fcntl.c fcntl: allow to set O_DIRECT flag on pipe 2016-01-09 02:55:37 -05:00
fhandle.c fs/coredump: prevent fsuid=0 dumps into user-controlled directories 2016-03-22 15:36:02 -07:00
file_table.c
file.c kmemcg: account certain kmem allocations to memcg 2016-01-14 16:00:49 -08:00
filesystems.c find_filesystem(): simplify comparison 2016-01-19 12:02:23 -05:00
fs_pin.c
fs_struct.c
fs-writeback.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
inode.c writeback: initialize inode members that track writeback history 2016-02-16 14:57:21 -07:00
internal.h Merge branch 'for-linus' into work.misc 2016-01-08 21:20:11 -05:00
ioctl.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
Kconfig Merge tag 'ofs-pull-tag-1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux 2016-03-26 12:59:04 -07:00
Kconfig.binfmt
libfs.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
locks.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
Makefile Merge tag 'ofs-pull-tag-1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux 2016-03-26 12:59:04 -07:00
mbcache.c mbcache: add reusable flag to cache entries 2016-02-22 22:44:04 -05:00
mount.h
mpage.c mm, fs: remove remaining PAGE_CACHE_* and page_cache_{get,release} usage 2016-04-04 10:41:08 -07:00
namei.c fix the braino in "namei: massage lookup_slow() to be usable by lookup_one_len_unlocked()" 2016-03-31 00:23:05 -04:00
namespace.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
no-block.c
nsfs.c
open.c fs/coredump: prevent fsuid=0 dumps into user-controlled directories 2016-03-22 15:36:02 -07:00
pipe.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
pnode.c propogate_mnt: Handle the first propogated copy being a slave 2016-05-05 09:54:45 -05:00
pnode.h
posix_acl.c xattr handlers: Simplify list operation 2015-12-13 19:46:12 -05:00
proc_namespace.c vfs: show_vfsstat: do not ignore errors from show_devname method 2016-03-16 13:09:08 -04:00
read_write.c Merge branches 'work.lookups', 'work.misc' and 'work.preadv2' into for-next 2016-03-18 16:07:38 -04:00
readdir.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
select.c timer: convert timer_slack_ns from unsigned long to u64 2016-03-17 15:09:34 -07:00
seq_file.c Make file credentials available to the seqfile interfaces 2016-04-14 12:56:09 -07:00
signalfd.c
splice.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
stack.c
stat.c fs/stat.c: drop the last new_valid_dev check 2016-01-16 11:17:23 -08:00
statfs.c
super.c writeback: flush inode cgroup wb switches instead of pinning super_block 2016-03-03 14:42:50 -07:00
sync.c mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros 2016-04-04 10:41:08 -07:00
timerfd.c timerfd: Handle relative timers with CONFIG_TIME_LOW_RES proper 2016-01-17 11:13:55 +01:00
userfaultfd.c userfaultfd: don't block on the last VM updates at exit time 2016-03-02 09:03:18 -08:00
utimes.c wrappers for ->i_mutex access 2016-01-22 18:04:28 -05:00
xattr.c xattr handlers: plug a lock leak in simple_xattr_list 2016-02-20 00:15:51 -05:00