linux/fs/btrfs/xattr.c

493 lines
13 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2007 Red Hat. All rights reserved.
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/rwsem.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/posix_acl_xattr.h>
#include <linux/iversion.h>
#include <linux/sched/mm.h>
#include "ctree.h"
#include "btrfs_inode.h"
#include "transaction.h"
#include "xattr.h"
#include "disk-io.h"
Btrfs: add support for inode properties This change adds infrastructure to allow for generic properties for inodes. Properties are name/value pairs that can be associated with inodes for different purposes. They are stored as xattrs with the prefix "btrfs." Properties can be inherited - this means when a directory inode has inheritable properties set, these are added to new inodes created under that directory. Further, subvolumes can also have properties associated with them, and they can be inherited from their parent subvolume. Naturally, directory properties have priority over subvolume properties (in practice a subvolume property is just a regular property associated with the root inode, objectid 256, of the subvolume's fs tree). This change also adds one specific property implementation, named "compression", whose values can be "lzo" or "zlib" and it's an inheritable property. The corresponding changes to btrfs-progs were also implemented. A patch with xfstests for this feature will follow once there's agreement on this change/feature. Further, the script at the bottom of this commit message was used to do some benchmarks to measure any performance penalties of this feature. Basically the tests correspond to: Test 1 - create a filesystem and mount it with compress-force=lzo, then sequentially create N files of 64Kb each, measure how long it took to create the files, unmount the filesystem, mount the filesystem and perform an 'ls -lha' against the test directory holding the N files, and report the time the command took. Test 2 - create a filesystem and don't use any compression option when mounting it - instead set the compression property of the subvolume's root to 'lzo'. Then create N files of 64Kb, and report the time it took. The unmount the filesystem, mount it again and perform an 'ls -lha' like in the former test. This means every single file ends up with a property (xattr) associated to it. Test 3 - same as test 2, but uses 4 properties - 3 are duplicates of the compression property, have no real effect other than adding more work when inheriting properties and taking more btree leaf space. Test 4 - same as test 3 but with 10 properties per file. Results (in seconds, and averages of 5 runs each), for different N numbers of files follow. * Without properties (test 1) file creation time ls -lha time 10 000 files 3.49 0.76 100 000 files 47.19 8.37 1 000 000 files 518.51 107.06 * With 1 property (compression property set to lzo - test 2) file creation time ls -lha time 10 000 files 3.63 0.93 100 000 files 48.56 9.74 1 000 000 files 537.72 125.11 * With 4 properties (test 3) file creation time ls -lha time 10 000 files 3.94 1.20 100 000 files 52.14 11.48 1 000 000 files 572.70 142.13 * With 10 properties (test 4) file creation time ls -lha time 10 000 files 4.61 1.35 100 000 files 58.86 13.83 1 000 000 files 656.01 177.61 The increased latencies with properties are essencialy because of: *) When creating an inode, we now synchronously write 1 more item (an xattr item) for each property inherited from the parent dir (or subvolume). This could be done in an asynchronous way such as we do for dir intex items (delayed-inode.c), which could help reduce the file creation latency; *) With properties, we now have larger fs trees. For this particular test each xattr item uses 75 bytes of leaf space in the fs tree. This could be less by using a new item for xattr items, instead of the current btrfs_dir_item, since we could cut the 'location' and 'type' fields (saving 18 bytes) and maybe 'transid' too (saving a total of 26 bytes per xattr item) from the btrfs_dir_item type. Also tried batching the xattr insertions (ignoring proper hash collision handling, since it didn't exist) when creating files that inherit properties from their parent inode/subvolume, but the end results were (surprisingly) essentially the same. Test script: $ cat test.pl #!/usr/bin/perl -w use strict; use Time::HiRes qw(time); use constant NUM_FILES => 10_000; use constant FILE_SIZES => (64 * 1024); use constant DEV => '/dev/sdb4'; use constant MNT_POINT => '/home/fdmanana/btrfs-tests/dev'; use constant TEST_DIR => (MNT_POINT . '/testdir'); system("mkfs.btrfs", "-l", "16384", "-f", DEV) == 0 or die "mkfs.btrfs failed!"; # following line for testing without properties #system("mount", "-o", "compress-force=lzo", DEV, MNT_POINT) == 0 or die "mount failed!"; # following 2 lines for testing with properties system("mount", DEV, MNT_POINT) == 0 or die "mount failed!"; system("btrfs", "prop", "set", MNT_POINT, "compression", "lzo") == 0 or die "set prop failed!"; system("mkdir", TEST_DIR) == 0 or die "mkdir failed!"; my ($t1, $t2); $t1 = time(); for (my $i = 1; $i <= NUM_FILES; $i++) { my $p = TEST_DIR . '/file_' . $i; open(my $f, '>', $p) or die "Error opening file!"; $f->autoflush(1); for (my $j = 0; $j < FILE_SIZES; $j += 4096) { print $f ('A' x 4096) or die "Error writing to file!"; } close($f); } $t2 = time(); print "Time to create " . NUM_FILES . ": " . ($t2 - $t1) . " seconds.\n"; system("umount", DEV) == 0 or die "umount failed!"; system("mount", DEV, MNT_POINT) == 0 or die "mount failed!"; $t1 = time(); system("bash -c 'ls -lha " . TEST_DIR . " > /dev/null'") == 0 or die "ls failed!"; $t2 = time(); print "Time to ls -lha all files: " . ($t2 - $t1) . " seconds.\n"; system("umount", DEV) == 0 or die "umount failed!"; Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com> Signed-off-by: Josef Bacik <jbacik@fb.com> Signed-off-by: Chris Mason <clm@fb.com>
2014-01-07 11:47:46 +00:00
#include "props.h"
#include "locking.h"
int btrfs_getxattr(struct inode *inode, const char *name,
void *buffer, size_t size)
{
struct btrfs_dir_item *di;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
struct extent_buffer *leaf;
int ret = 0;
unsigned long data_ptr;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
/* lookup the xattr by name */
di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(BTRFS_I(inode)),
name, strlen(name), 0);
if (!di) {
ret = -ENODATA;
goto out;
} else if (IS_ERR(di)) {
ret = PTR_ERR(di);
goto out;
}
leaf = path->nodes[0];
/* if size is 0, that means we want the size of the attr */
if (!size) {
ret = btrfs_dir_data_len(leaf, di);
goto out;
}
/* now get the data out of our dir_item */
if (btrfs_dir_data_len(leaf, di) > size) {
ret = -ERANGE;
goto out;
}
/*
* The way things are packed into the leaf is like this
* |struct btrfs_dir_item|name|data|
* where name is the xattr name, so security.foo, and data is the
* content of the xattr. data_ptr points to the location in memory
* where the data starts in the in memory leaf
*/
data_ptr = (unsigned long)((char *)(di + 1) +
btrfs_dir_name_len(leaf, di));
read_extent_buffer(leaf, buffer, data_ptr,
btrfs_dir_data_len(leaf, di));
ret = btrfs_dir_data_len(leaf, di);
out:
btrfs_free_path(path);
return ret;
}
int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode,
const char *name, const void *value, size_t size, int flags)
{
struct btrfs_dir_item *di = NULL;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_path *path;
size_t name_len = strlen(name);
int ret = 0;
ASSERT(trans);
if (name_len + size > BTRFS_MAX_XATTR_SIZE(root->fs_info))
return -ENOSPC;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->skip_release_on_error = 1;
if (!value) {
di = btrfs_lookup_xattr(trans, root, path,
btrfs_ino(BTRFS_I(inode)), name, name_len, -1);
if (!di && (flags & XATTR_REPLACE))
ret = -ENODATA;
else if (IS_ERR(di))
ret = PTR_ERR(di);
else if (di)
ret = btrfs_delete_one_dir_name(trans, root, path, di);
goto out;
}
/*
* For a replace we can't just do the insert blindly.
* Do a lookup first (read-only btrfs_search_slot), and return if xattr
* doesn't exist. If it exists, fall down below to the insert/replace
* path - we can't race with a concurrent xattr delete, because the VFS
* locks the inode's i_mutex before calling setxattr or removexattr.
*/
if (flags & XATTR_REPLACE) {
ASSERT(inode_is_locked(inode));
di = btrfs_lookup_xattr(NULL, root, path,
btrfs_ino(BTRFS_I(inode)), name, name_len, 0);
if (!di)
ret = -ENODATA;
else if (IS_ERR(di))
ret = PTR_ERR(di);
if (ret)
goto out;
btrfs_release_path(path);
di = NULL;
}
ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(BTRFS_I(inode)),
name, name_len, value, size);
if (ret == -EOVERFLOW) {
/*
* We have an existing item in a leaf, split_leaf couldn't
* expand it. That item might have or not a dir_item that
* matches our target xattr, so lets check.
*/
ret = 0;
btrfs_assert_tree_write_locked(path->nodes[0]);
di = btrfs_match_dir_item_name(fs_info, path, name, name_len);
if (!di && !(flags & XATTR_REPLACE)) {
ret = -ENOSPC;
goto out;
}
} else if (ret == -EEXIST) {
ret = 0;
di = btrfs_match_dir_item_name(fs_info, path, name, name_len);
ASSERT(di); /* logic error */
} else if (ret) {
goto out;
}
if (di && (flags & XATTR_CREATE)) {
ret = -EEXIST;
goto out;
}
if (di) {
/*
* We're doing a replace, and it must be atomic, that is, at
* any point in time we have either the old or the new xattr
* value in the tree. We don't want readers (getxattr and
* listxattrs) to miss a value, this is specially important
* for ACLs.
*/
const int slot = path->slots[0];
struct extent_buffer *leaf = path->nodes[0];
const u16 old_data_len = btrfs_dir_data_len(leaf, di);
const u32 item_size = btrfs_item_size(leaf, slot);
const u32 data_size = sizeof(*di) + name_len + size;
unsigned long data_ptr;
char *ptr;
if (size > old_data_len) {
if (btrfs_leaf_free_space(leaf) <
(size - old_data_len)) {
ret = -ENOSPC;
goto out;
}
}
if (old_data_len + name_len + sizeof(*di) == item_size) {
/* No other xattrs packed in the same leaf item. */
if (size > old_data_len)
btrfs_extend_item(path, size - old_data_len);
else if (size < old_data_len)
btrfs_truncate_item(path, data_size, 1);
} else {
/* There are other xattrs packed in the same item. */
ret = btrfs_delete_one_dir_name(trans, root, path, di);
if (ret)
goto out;
btrfs_extend_item(path, data_size);
}
ptr = btrfs_item_ptr(leaf, slot, char);
ptr += btrfs_item_size(leaf, slot) - data_size;
di = (struct btrfs_dir_item *)ptr;
btrfs_set_dir_data_len(leaf, di, size);
data_ptr = ((unsigned long)(di + 1)) + name_len;
write_extent_buffer(leaf, value, data_ptr, size);
btrfs_mark_buffer_dirty(leaf);
} else {
/*
* Insert, and we had space for the xattr, so path->slots[0] is
* where our xattr dir_item is and btrfs_insert_xattr_item()
* filled it.
*/
}
out:
btrfs_free_path(path);
btrfs: skip unnecessary searches for xattrs when logging an inode Every time we log an inode we lookup in the fs/subvol tree for xattrs and if we have any, log them into the log tree. However it is very common to have inodes without any xattrs, so doing the search wastes times, but more importantly it adds contention on the fs/subvol tree locks, either making the logging code block and wait for tree locks or making the logging code making other concurrent operations block and wait. The most typical use cases where xattrs are used are when capabilities or ACLs are defined for an inode, or when SELinux is enabled. This change makes the logging code detect when an inode does not have xattrs and skip the xattrs search the next time the inode is logged, unless the inode is evicted and loaded again or a xattr is added to the inode. Therefore skipping the search for xattrs on inodes that don't ever have xattrs and are fsynced with some frequency. The following script that calls dbench was used to measure the impact of this change on a VM with 8 CPUs, 16Gb of ram, using a raw NVMe device directly (no intermediary filesystem on the host) and using a non-debug kernel (default configuration on Debian distributions): $ cat test.sh #!/bin/bash DEV=/dev/sdk MNT=/mnt/sdk MOUNT_OPTIONS="-o ssd" mkfs.btrfs -f -m single -d single $DEV mount $MOUNT_OPTIONS $DEV $MNT dbench -D $MNT -t 200 40 umount $MNT The results before this change: Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 5761605 0.172 312.057 Close 4232452 0.002 10.927 Rename 243937 1.406 277.344 Unlink 1163456 0.631 298.402 Deltree 160 11.581 221.107 Mkdir 80 0.003 0.005 Qpathinfo 5221410 0.065 122.309 Qfileinfo 915432 0.001 3.333 Qfsinfo 957555 0.003 3.992 Sfileinfo 469244 0.023 20.494 Find 2018865 0.448 123.659 WriteX 2874851 0.049 118.529 ReadX 9030579 0.004 21.654 LockX 18754 0.003 4.423 UnlockX 18754 0.002 0.331 Flush 403792 10.944 359.494 Throughput 908.444 MB/sec 40 clients 40 procs max_latency=359.500 ms The results after this change: Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 6442521 0.159 230.693 Close 4732357 0.002 10.972 Rename 272809 1.293 227.398 Unlink 1301059 0.563 218.500 Deltree 160 7.796 54.887 Mkdir 80 0.008 0.478 Qpathinfo 5839452 0.047 124.330 Qfileinfo 1023199 0.001 4.996 Qfsinfo 1070760 0.003 5.709 Sfileinfo 524790 0.033 21.765 Find 2257658 0.314 125.611 WriteX 3211520 0.040 232.135 ReadX 10098969 0.004 25.340 LockX 20974 0.003 1.569 UnlockX 20974 0.002 3.475 Flush 451553 10.287 331.037 Throughput 1011.77 MB/sec 40 clients 40 procs max_latency=331.045 ms +10.8% throughput, -8.2% max latency Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 11:21:49 +00:00
if (!ret) {
Btrfs: fix failure to persist compression property xattr deletion on fsync After the recent series of cleanups in the properties and xattrs modules that landed in the 5.2 merge window, we ended up with a regression where after deleting the compression xattr property through the setflags ioctl, we don't set the BTRFS_INODE_COPY_EVERYTHING flag in the inode anymore. As a consequence, if the inode was fsync'ed when it had the compression property set, after deleting the compression property through the setflags ioctl and fsync'ing again the inode, the log will still contain the compression xattr, because the inode did not had that bit set, which made the fsync not delete all xattrs from the log and copy all xattrs from the subvolume tree to the log tree. This regression happens due to the fact that that series of cleanups made btrfs_set_prop() call the old function do_setxattr() (which is now named btrfs_setxattr()), and not the old version of btrfs_setxattr(), which is now called btrfs_setxattr_trans(). Fix this by setting the BTRFS_INODE_COPY_EVERYTHING bit in the current btrfs_setxattr() function and remove it from everywhere else, including its setup at btrfs_ioctl_setflags(). This is cleaner, avoids similar regressions in the future, and centralizes the setup of the bit. After all, the need to setup this bit should only be in the xattrs module, since it is an implementation of xattrs. Fixes: 04e6863b19c722 ("btrfs: split btrfs_setxattr calls regarding transaction") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2019-06-12 14:14:11 +00:00
set_bit(BTRFS_INODE_COPY_EVERYTHING,
&BTRFS_I(inode)->runtime_flags);
btrfs: skip unnecessary searches for xattrs when logging an inode Every time we log an inode we lookup in the fs/subvol tree for xattrs and if we have any, log them into the log tree. However it is very common to have inodes without any xattrs, so doing the search wastes times, but more importantly it adds contention on the fs/subvol tree locks, either making the logging code block and wait for tree locks or making the logging code making other concurrent operations block and wait. The most typical use cases where xattrs are used are when capabilities or ACLs are defined for an inode, or when SELinux is enabled. This change makes the logging code detect when an inode does not have xattrs and skip the xattrs search the next time the inode is logged, unless the inode is evicted and loaded again or a xattr is added to the inode. Therefore skipping the search for xattrs on inodes that don't ever have xattrs and are fsynced with some frequency. The following script that calls dbench was used to measure the impact of this change on a VM with 8 CPUs, 16Gb of ram, using a raw NVMe device directly (no intermediary filesystem on the host) and using a non-debug kernel (default configuration on Debian distributions): $ cat test.sh #!/bin/bash DEV=/dev/sdk MNT=/mnt/sdk MOUNT_OPTIONS="-o ssd" mkfs.btrfs -f -m single -d single $DEV mount $MOUNT_OPTIONS $DEV $MNT dbench -D $MNT -t 200 40 umount $MNT The results before this change: Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 5761605 0.172 312.057 Close 4232452 0.002 10.927 Rename 243937 1.406 277.344 Unlink 1163456 0.631 298.402 Deltree 160 11.581 221.107 Mkdir 80 0.003 0.005 Qpathinfo 5221410 0.065 122.309 Qfileinfo 915432 0.001 3.333 Qfsinfo 957555 0.003 3.992 Sfileinfo 469244 0.023 20.494 Find 2018865 0.448 123.659 WriteX 2874851 0.049 118.529 ReadX 9030579 0.004 21.654 LockX 18754 0.003 4.423 UnlockX 18754 0.002 0.331 Flush 403792 10.944 359.494 Throughput 908.444 MB/sec 40 clients 40 procs max_latency=359.500 ms The results after this change: Operation Count AvgLat MaxLat ---------------------------------------- NTCreateX 6442521 0.159 230.693 Close 4732357 0.002 10.972 Rename 272809 1.293 227.398 Unlink 1301059 0.563 218.500 Deltree 160 7.796 54.887 Mkdir 80 0.008 0.478 Qpathinfo 5839452 0.047 124.330 Qfileinfo 1023199 0.001 4.996 Qfsinfo 1070760 0.003 5.709 Sfileinfo 524790 0.033 21.765 Find 2257658 0.314 125.611 WriteX 3211520 0.040 232.135 ReadX 10098969 0.004 25.340 LockX 20974 0.003 1.569 UnlockX 20974 0.002 3.475 Flush 451553 10.287 331.037 Throughput 1011.77 MB/sec 40 clients 40 procs max_latency=331.045 ms +10.8% throughput, -8.2% max latency Reviewed-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana@suse.com> Reviewed-by: David Sterba <dsterba@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2020-11-13 11:21:49 +00:00
clear_bit(BTRFS_INODE_NO_XATTRS, &BTRFS_I(inode)->runtime_flags);
}
return ret;
}
/*
* @value: "" makes the attribute to empty, NULL removes it
*/
int btrfs_setxattr_trans(struct inode *inode, const char *name,
const void *value, size_t size, int flags)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
btrfs: fix warning when creating a directory with smack enabled When we have smack enabled, during the creation of a directory smack may attempt to add a "smack transmute" xattr on the inode, which results in the following warning and trace: WARNING: CPU: 3 PID: 2548 at fs/btrfs/transaction.c:537 start_transaction+0x489/0x4f0 Modules linked in: nft_objref nf_conntrack_netbios_ns (...) CPU: 3 PID: 2548 Comm: mkdir Not tainted 5.9.0-rc2smack+ #81 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 RIP: 0010:start_transaction+0x489/0x4f0 Code: e9 be fc ff ff (...) RSP: 0018:ffffc90001887d10 EFLAGS: 00010202 RAX: ffff88816f1e0000 RBX: 0000000000000201 RCX: 0000000000000003 RDX: 0000000000000201 RSI: 0000000000000002 RDI: ffff888177849000 RBP: ffff888177849000 R08: 0000000000000001 R09: 0000000000000004 R10: ffffffff825e8f7a R11: 0000000000000003 R12: ffffffffffffffe2 R13: 0000000000000000 R14: ffff88803d884270 R15: ffff8881680d8000 FS: 00007f67317b8440(0000) GS:ffff88817bcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f67247a22a8 CR3: 000000004bfbc002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? slab_free_freelist_hook+0xea/0x1b0 ? trace_hardirqs_on+0x1c/0xe0 btrfs_setxattr_trans+0x3c/0xf0 __vfs_setxattr+0x63/0x80 smack_d_instantiate+0x2d3/0x360 security_d_instantiate+0x29/0x40 d_instantiate_new+0x38/0x90 btrfs_mkdir+0x1cf/0x1e0 vfs_mkdir+0x14f/0x200 do_mkdirat+0x6d/0x110 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f673196ae6b Code: 8b 05 11 (...) RSP: 002b:00007ffc3c679b18 EFLAGS: 00000246 ORIG_RAX: 0000000000000053 RAX: ffffffffffffffda RBX: 00000000000001ff RCX: 00007f673196ae6b RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007ffc3c67a30d RBP: 00007ffc3c67a30d R08: 00000000000001ff R09: 0000000000000000 R10: 000055d3e39fe930 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc3c679cd8 R14: 00007ffc3c67a30d R15: 00007ffc3c679ce0 irq event stamp: 11029 hardirqs last enabled at (11037): [<ffffffff81153fe6>] console_unlock+0x486/0x670 hardirqs last disabled at (11044): [<ffffffff81153c01>] console_unlock+0xa1/0x670 softirqs last enabled at (8864): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 softirqs last disabled at (8851): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 This happens because at btrfs_mkdir() we call d_instantiate_new() while holding a transaction handle, which results in the following call chain: btrfs_mkdir() trans = btrfs_start_transaction(root, 5); d_instantiate_new() smack_d_instantiate() __vfs_setxattr() btrfs_setxattr_trans() btrfs_start_transaction() start_transaction() WARN_ON() --> a tansaction start has TRANS_EXTWRITERS set in its type h->orig_rsv = h->block_rsv h->block_rsv = NULL btrfs_end_transaction(trans) Besides the warning triggered at start_transaction, we set the handle's block_rsv to NULL which may cause some surprises later on. So fix this by making btrfs_setxattr_trans() not start a transaction when we already have a handle on one, stored in current->journal_info, and use that handle. We are good to use the handle because at btrfs_mkdir() we did reserve space for the xattr and the inode item. Reported-by: Casey Schaufler <casey@schaufler-ca.com> CC: stable@vger.kernel.org # 5.4+ Acked-by: Casey Schaufler <casey@schaufler-ca.com> Tested-by: Casey Schaufler <casey@schaufler-ca.com> Link: https://lore.kernel.org/linux-btrfs/434d856f-bd7b-4889-a6ec-e81aaebfa735@schaufler-ca.com/ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-26 17:51:44 +00:00
const bool start_trans = (current->journal_info == NULL);
int ret;
btrfs: fix warning when creating a directory with smack enabled When we have smack enabled, during the creation of a directory smack may attempt to add a "smack transmute" xattr on the inode, which results in the following warning and trace: WARNING: CPU: 3 PID: 2548 at fs/btrfs/transaction.c:537 start_transaction+0x489/0x4f0 Modules linked in: nft_objref nf_conntrack_netbios_ns (...) CPU: 3 PID: 2548 Comm: mkdir Not tainted 5.9.0-rc2smack+ #81 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 RIP: 0010:start_transaction+0x489/0x4f0 Code: e9 be fc ff ff (...) RSP: 0018:ffffc90001887d10 EFLAGS: 00010202 RAX: ffff88816f1e0000 RBX: 0000000000000201 RCX: 0000000000000003 RDX: 0000000000000201 RSI: 0000000000000002 RDI: ffff888177849000 RBP: ffff888177849000 R08: 0000000000000001 R09: 0000000000000004 R10: ffffffff825e8f7a R11: 0000000000000003 R12: ffffffffffffffe2 R13: 0000000000000000 R14: ffff88803d884270 R15: ffff8881680d8000 FS: 00007f67317b8440(0000) GS:ffff88817bcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f67247a22a8 CR3: 000000004bfbc002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? slab_free_freelist_hook+0xea/0x1b0 ? trace_hardirqs_on+0x1c/0xe0 btrfs_setxattr_trans+0x3c/0xf0 __vfs_setxattr+0x63/0x80 smack_d_instantiate+0x2d3/0x360 security_d_instantiate+0x29/0x40 d_instantiate_new+0x38/0x90 btrfs_mkdir+0x1cf/0x1e0 vfs_mkdir+0x14f/0x200 do_mkdirat+0x6d/0x110 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f673196ae6b Code: 8b 05 11 (...) RSP: 002b:00007ffc3c679b18 EFLAGS: 00000246 ORIG_RAX: 0000000000000053 RAX: ffffffffffffffda RBX: 00000000000001ff RCX: 00007f673196ae6b RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007ffc3c67a30d RBP: 00007ffc3c67a30d R08: 00000000000001ff R09: 0000000000000000 R10: 000055d3e39fe930 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc3c679cd8 R14: 00007ffc3c67a30d R15: 00007ffc3c679ce0 irq event stamp: 11029 hardirqs last enabled at (11037): [<ffffffff81153fe6>] console_unlock+0x486/0x670 hardirqs last disabled at (11044): [<ffffffff81153c01>] console_unlock+0xa1/0x670 softirqs last enabled at (8864): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 softirqs last disabled at (8851): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 This happens because at btrfs_mkdir() we call d_instantiate_new() while holding a transaction handle, which results in the following call chain: btrfs_mkdir() trans = btrfs_start_transaction(root, 5); d_instantiate_new() smack_d_instantiate() __vfs_setxattr() btrfs_setxattr_trans() btrfs_start_transaction() start_transaction() WARN_ON() --> a tansaction start has TRANS_EXTWRITERS set in its type h->orig_rsv = h->block_rsv h->block_rsv = NULL btrfs_end_transaction(trans) Besides the warning triggered at start_transaction, we set the handle's block_rsv to NULL which may cause some surprises later on. So fix this by making btrfs_setxattr_trans() not start a transaction when we already have a handle on one, stored in current->journal_info, and use that handle. We are good to use the handle because at btrfs_mkdir() we did reserve space for the xattr and the inode item. Reported-by: Casey Schaufler <casey@schaufler-ca.com> CC: stable@vger.kernel.org # 5.4+ Acked-by: Casey Schaufler <casey@schaufler-ca.com> Tested-by: Casey Schaufler <casey@schaufler-ca.com> Link: https://lore.kernel.org/linux-btrfs/434d856f-bd7b-4889-a6ec-e81aaebfa735@schaufler-ca.com/ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-26 17:51:44 +00:00
if (start_trans) {
/*
* 1 unit for inserting/updating/deleting the xattr
* 1 unit for the inode item update
*/
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans))
return PTR_ERR(trans);
} else {
/*
* This can happen when smack is enabled and a directory is being
* created. It happens through d_instantiate_new(), which calls
* smack_d_instantiate(), which in turn calls __vfs_setxattr() to
* set the transmute xattr (XATTR_NAME_SMACKTRANSMUTE) on the
* inode. We have already reserved space for the xattr and inode
* update at btrfs_mkdir(), so just use the transaction handle.
* We don't join or start a transaction, as that will reset the
* block_rsv of the handle and trigger a warning for the start
* case.
*/
ASSERT(strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN) == 0);
trans = current->journal_info;
}
ret = btrfs_setxattr(trans, inode, name, value, size, flags);
if (ret)
goto out;
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
if (ret)
btrfs_abort_transaction(trans, ret);
out:
btrfs: fix warning when creating a directory with smack enabled When we have smack enabled, during the creation of a directory smack may attempt to add a "smack transmute" xattr on the inode, which results in the following warning and trace: WARNING: CPU: 3 PID: 2548 at fs/btrfs/transaction.c:537 start_transaction+0x489/0x4f0 Modules linked in: nft_objref nf_conntrack_netbios_ns (...) CPU: 3 PID: 2548 Comm: mkdir Not tainted 5.9.0-rc2smack+ #81 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-2.fc32 04/01/2014 RIP: 0010:start_transaction+0x489/0x4f0 Code: e9 be fc ff ff (...) RSP: 0018:ffffc90001887d10 EFLAGS: 00010202 RAX: ffff88816f1e0000 RBX: 0000000000000201 RCX: 0000000000000003 RDX: 0000000000000201 RSI: 0000000000000002 RDI: ffff888177849000 RBP: ffff888177849000 R08: 0000000000000001 R09: 0000000000000004 R10: ffffffff825e8f7a R11: 0000000000000003 R12: ffffffffffffffe2 R13: 0000000000000000 R14: ffff88803d884270 R15: ffff8881680d8000 FS: 00007f67317b8440(0000) GS:ffff88817bcc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f67247a22a8 CR3: 000000004bfbc002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? slab_free_freelist_hook+0xea/0x1b0 ? trace_hardirqs_on+0x1c/0xe0 btrfs_setxattr_trans+0x3c/0xf0 __vfs_setxattr+0x63/0x80 smack_d_instantiate+0x2d3/0x360 security_d_instantiate+0x29/0x40 d_instantiate_new+0x38/0x90 btrfs_mkdir+0x1cf/0x1e0 vfs_mkdir+0x14f/0x200 do_mkdirat+0x6d/0x110 do_syscall_64+0x2d/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f673196ae6b Code: 8b 05 11 (...) RSP: 002b:00007ffc3c679b18 EFLAGS: 00000246 ORIG_RAX: 0000000000000053 RAX: ffffffffffffffda RBX: 00000000000001ff RCX: 00007f673196ae6b RDX: 0000000000000000 RSI: 00000000000001ff RDI: 00007ffc3c67a30d RBP: 00007ffc3c67a30d R08: 00000000000001ff R09: 0000000000000000 R10: 000055d3e39fe930 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffc3c679cd8 R14: 00007ffc3c67a30d R15: 00007ffc3c679ce0 irq event stamp: 11029 hardirqs last enabled at (11037): [<ffffffff81153fe6>] console_unlock+0x486/0x670 hardirqs last disabled at (11044): [<ffffffff81153c01>] console_unlock+0xa1/0x670 softirqs last enabled at (8864): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 softirqs last disabled at (8851): [<ffffffff81e0102f>] asm_call_on_stack+0xf/0x20 This happens because at btrfs_mkdir() we call d_instantiate_new() while holding a transaction handle, which results in the following call chain: btrfs_mkdir() trans = btrfs_start_transaction(root, 5); d_instantiate_new() smack_d_instantiate() __vfs_setxattr() btrfs_setxattr_trans() btrfs_start_transaction() start_transaction() WARN_ON() --> a tansaction start has TRANS_EXTWRITERS set in its type h->orig_rsv = h->block_rsv h->block_rsv = NULL btrfs_end_transaction(trans) Besides the warning triggered at start_transaction, we set the handle's block_rsv to NULL which may cause some surprises later on. So fix this by making btrfs_setxattr_trans() not start a transaction when we already have a handle on one, stored in current->journal_info, and use that handle. We are good to use the handle because at btrfs_mkdir() we did reserve space for the xattr and the inode item. Reported-by: Casey Schaufler <casey@schaufler-ca.com> CC: stable@vger.kernel.org # 5.4+ Acked-by: Casey Schaufler <casey@schaufler-ca.com> Tested-by: Casey Schaufler <casey@schaufler-ca.com> Link: https://lore.kernel.org/linux-btrfs/434d856f-bd7b-4889-a6ec-e81aaebfa735@schaufler-ca.com/ Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-26 17:51:44 +00:00
if (start_trans)
btrfs_end_transaction(trans);
return ret;
}
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
struct btrfs_key found_key;
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
struct btrfs_key key;
struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_path *path;
int iter_ret = 0;
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
int ret = 0;
size_t total_size = 0, size_left = size;
/*
* ok we want all objects associated with this id.
* NOTE: we set key.offset = 0; because we want to start with the
* first xattr that we find and walk forward
*/
key.objectid = btrfs_ino(BTRFS_I(inode));
key.type = BTRFS_XATTR_ITEM_KEY;
key.offset = 0;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
path->reada = READA_FORWARD;
/* search for our xattrs */
btrfs_for_each_slot(root, &key, &found_key, path, iter_ret) {
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
struct extent_buffer *leaf;
int slot;
struct btrfs_dir_item *di;
u32 item_size;
u32 cur;
leaf = path->nodes[0];
slot = path->slots[0];
/* check to make sure this item is what we want */
if (found_key.objectid != key.objectid)
break;
Btrfs: fix race when listing an inode's xattrs When listing a inode's xattrs we have a time window where we race against a concurrent operation for adding a new hard link for our inode that makes us not return any xattr to user space. In order for this to happen, the first xattr of our inode needs to be at slot 0 of a leaf and the previous leaf must still have room for an inode ref (or extref) item, and this can happen because an inode's listxattrs callback does not lock the inode's i_mutex (nor does the VFS does it for us), but adding a hard link to an inode makes the VFS lock the inode's i_mutex before calling the inode's link callback. If we have the following leafs: Leaf X (has N items) Leaf Y [ ... (257 INODE_ITEM 0) (257 INODE_REF 256) ] [ (257 XATTR_ITEM 12345), ... ] slot N - 2 slot N - 1 slot 0 The race illustrated by the following sequence diagram is possible: CPU 1 CPU 2 btrfs_listxattr() searches for key (257 XATTR_ITEM 0) gets path with path->nodes[0] == leaf X and path->slots[0] == N because path->slots[0] is >= btrfs_header_nritems(leaf X), it calls btrfs_next_leaf() btrfs_next_leaf() releases the path adds key (257 INODE_REF 666) to the end of leaf X (slot N), and leaf X now has N + 1 items searches for the key (257 INODE_REF 256), with path->keep_locks == 1, because that is the last key it saw in leaf X before releasing the path ends up at leaf X again and it verifies that the key (257 INODE_REF 256) is no longer the last key in leaf X, so it returns with path->nodes[0] == leaf X and path->slots[0] == N, pointing to the new item with key (257 INODE_REF 666) btrfs_listxattr's loop iteration sees that the type of the key pointed by the path is different from the type BTRFS_XATTR_ITEM_KEY and so it breaks the loop and stops looking for more xattr items --> the application doesn't get any xattr listed for our inode So fix this by breaking the loop only if the key's type is greater than BTRFS_XATTR_ITEM_KEY and skip the current key if its type is smaller. Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-11-09 18:06:38 +00:00
if (found_key.type > BTRFS_XATTR_ITEM_KEY)
break;
Btrfs: fix race when listing an inode's xattrs When listing a inode's xattrs we have a time window where we race against a concurrent operation for adding a new hard link for our inode that makes us not return any xattr to user space. In order for this to happen, the first xattr of our inode needs to be at slot 0 of a leaf and the previous leaf must still have room for an inode ref (or extref) item, and this can happen because an inode's listxattrs callback does not lock the inode's i_mutex (nor does the VFS does it for us), but adding a hard link to an inode makes the VFS lock the inode's i_mutex before calling the inode's link callback. If we have the following leafs: Leaf X (has N items) Leaf Y [ ... (257 INODE_ITEM 0) (257 INODE_REF 256) ] [ (257 XATTR_ITEM 12345), ... ] slot N - 2 slot N - 1 slot 0 The race illustrated by the following sequence diagram is possible: CPU 1 CPU 2 btrfs_listxattr() searches for key (257 XATTR_ITEM 0) gets path with path->nodes[0] == leaf X and path->slots[0] == N because path->slots[0] is >= btrfs_header_nritems(leaf X), it calls btrfs_next_leaf() btrfs_next_leaf() releases the path adds key (257 INODE_REF 666) to the end of leaf X (slot N), and leaf X now has N + 1 items searches for the key (257 INODE_REF 256), with path->keep_locks == 1, because that is the last key it saw in leaf X before releasing the path ends up at leaf X again and it verifies that the key (257 INODE_REF 256) is no longer the last key in leaf X, so it returns with path->nodes[0] == leaf X and path->slots[0] == N, pointing to the new item with key (257 INODE_REF 666) btrfs_listxattr's loop iteration sees that the type of the key pointed by the path is different from the type BTRFS_XATTR_ITEM_KEY and so it breaks the loop and stops looking for more xattr items --> the application doesn't get any xattr listed for our inode So fix this by breaking the loop only if the key's type is greater than BTRFS_XATTR_ITEM_KEY and skip the current key if its type is smaller. Cc: stable@vger.kernel.org Signed-off-by: Filipe Manana <fdmanana@suse.com>
2015-11-09 18:06:38 +00:00
if (found_key.type < BTRFS_XATTR_ITEM_KEY)
continue;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
item_size = btrfs_item_size(leaf, slot);
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
cur = 0;
while (cur < item_size) {
u16 name_len = btrfs_dir_name_len(leaf, di);
u16 data_len = btrfs_dir_data_len(leaf, di);
u32 this_len = sizeof(*di) + name_len + data_len;
unsigned long name_ptr = (unsigned long)(di + 1);
total_size += name_len + 1;
/*
* We are just looking for how big our buffer needs to
* be.
*/
if (!size)
goto next;
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
if (!buffer || (name_len + 1) > size_left) {
iter_ret = -ERANGE;
break;
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
}
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
read_extent_buffer(leaf, buffer, name_ptr, name_len);
buffer[name_len] = '\0';
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
size_left -= name_len + 1;
buffer += name_len + 1;
next:
Btrfs: fix listxattrs not listing all xattrs packed in the same item In the listxattrs handler, we were not listing all the xattrs that are packed in the same btree item, which happens when multiple xattrs have a name that when crc32c hashed produce the same checksum value. Fix this by processing them all. The following test case for xfstests reproduces the issue: seq=`basename $0` seqres=$RESULT_DIR/$seq echo "QA output created by $seq" tmp=/tmp/$$ status=1 # failure is the default! trap "_cleanup; exit \$status" 0 1 2 3 15 _cleanup() { cd / rm -f $tmp.* } # get standard environment, filters and checks . ./common/rc . ./common/filter . ./common/attr # real QA test starts here _supported_fs generic _supported_os Linux _require_scratch _require_attrs rm -f $seqres.full _scratch_mkfs >>$seqres.full 2>&1 _scratch_mount # Create our test file with a few xattrs. The first 3 xattrs have a name # that when given as input to a crc32c function result in the same checksum. # This made btrfs list only one of the xattrs through listxattrs system call # (because it packs xattrs with the same name checksum into the same btree # item). touch $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.foobar -v 123 $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.WvG1c1Td -v qwerty $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.J3__T_Km3dVsW_ -v hello $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.something -v pizza $SCRATCH_MNT/testfile $SETFATTR_PROG -n user.ping -v pong $SCRATCH_MNT/testfile # Now call getfattr with --dump, which calls the listxattrs system call. # It should list all the xattrs we have set before. $GETFATTR_PROG --absolute-names --dump $SCRATCH_MNT/testfile | _filter_scratch status=0 exit Signed-off-by: Filipe Manana <fdmanana@suse.com> Signed-off-by: Chris Mason <clm@fb.com>
2016-02-21 15:03:02 +00:00
cur += this_len;
di = (struct btrfs_dir_item *)((char *)di + this_len);
}
}
if (iter_ret < 0)
ret = iter_ret;
else
ret = total_size;
btrfs_free_path(path);
return ret;
}
static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *name, void *buffer, size_t size)
{
name = xattr_full_name(handler, name);
return btrfs_getxattr(inode, name, buffer, size);
}
static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:27 +00:00
struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *buffer,
size_t size, int flags)
{
if (btrfs_root_readonly(BTRFS_I(inode)->root))
return -EROFS;
name = xattr_full_name(handler, name);
return btrfs_setxattr_trans(inode, name, buffer, size, flags);
}
static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:27 +00:00
struct user_namespace *mnt_userns,
struct dentry *unused, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
int ret;
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
name = xattr_full_name(handler, name);
ret = btrfs_validate_prop(BTRFS_I(inode), name, value, size);
if (ret)
return ret;
if (btrfs_ignore_prop(BTRFS_I(inode), name))
return 0;
trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans))
return PTR_ERR(trans);
ret = btrfs_set_prop(trans, inode, name, value, size, flags);
if (!ret) {
inode_inc_iversion(inode);
inode->i_ctime = current_time(inode);
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
if (ret)
btrfs_abort_transaction(trans, ret);
}
btrfs_end_transaction(trans);
return ret;
}
static const struct xattr_handler btrfs_security_xattr_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.get = btrfs_xattr_handler_get,
.set = btrfs_xattr_handler_set,
};
static const struct xattr_handler btrfs_trusted_xattr_handler = {
.prefix = XATTR_TRUSTED_PREFIX,
.get = btrfs_xattr_handler_get,
.set = btrfs_xattr_handler_set,
};
static const struct xattr_handler btrfs_user_xattr_handler = {
.prefix = XATTR_USER_PREFIX,
.get = btrfs_xattr_handler_get,
.set = btrfs_xattr_handler_set,
};
static const struct xattr_handler btrfs_btrfs_xattr_handler = {
.prefix = XATTR_BTRFS_PREFIX,
.get = btrfs_xattr_handler_get,
.set = btrfs_xattr_handler_set_prop,
};
const struct xattr_handler *btrfs_xattr_handlers[] = {
&btrfs_security_xattr_handler,
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
&btrfs_trusted_xattr_handler,
&btrfs_user_xattr_handler,
&btrfs_btrfs_xattr_handler,
NULL,
};
static int btrfs_initxattrs(struct inode *inode,
const struct xattr *xattr_array, void *fs_private)
{
struct btrfs_trans_handle *trans = fs_private;
const struct xattr *xattr;
unsigned int nofs_flag;
char *name;
int err = 0;
/*
* We're holding a transaction handle, so use a NOFS memory allocation
* context to avoid deadlock if reclaim happens.
*/
nofs_flag = memalloc_nofs_save();
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
name = kmalloc(XATTR_SECURITY_PREFIX_LEN +
strlen(xattr->name) + 1, GFP_KERNEL);
if (!name) {
err = -ENOMEM;
break;
}
strcpy(name, XATTR_SECURITY_PREFIX);
strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
err = btrfs_setxattr(trans, inode, name, xattr->value,
xattr->value_len, 0);
kfree(name);
if (err < 0)
break;
}
memalloc_nofs_restore(nofs_flag);
return err;
}
int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir,
const struct qstr *qstr)
{
return security_inode_init_security(inode, dir, qstr,
&btrfs_initxattrs, trans);
}