linux/fs/ext4/xattr.c

2307 lines
60 KiB
C
Raw Normal View History

/*
* linux/fs/ext4/xattr.c
*
* Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
*
* Fix by Harrison Xing <harrison@mountainviewdata.com>.
* Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>.
* Extended attributes for symlinks and special files added per
* suggestion of Luka Renko <luka.renko@hermes.si>.
* xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>,
* Red Hat Inc.
* ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz
* and Andreas Gruenbacher <agruen@suse.de>.
*/
/*
* Extended attributes are stored directly in inodes (on file systems with
* inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl
* field contains the block number if an inode uses an additional block. All
* attributes must fit in the inode and one additional block. Blocks that
* contain the identical set of attributes may be shared among several inodes.
* Identical blocks are detected by keeping a cache of blocks that have
* recently been accessed.
*
* The attributes in inodes and on blocks have a different header; the entries
* are stored in the same format:
*
* +------------------+
* | header |
* | entry 1 | |
* | entry 2 | | growing downwards
* | entry 3 | v
* | four null bytes |
* | . . . |
* | value 1 | ^
* | value 3 | | growing upwards
* | value 2 | |
* +------------------+
*
* The header is followed by multiple entry descriptors. In disk blocks, the
* entry descriptors are kept sorted. In inodes, they are unsorted. The
* attribute values are aligned to the end of the block in no specific order.
*
* Locking strategy
* ----------------
* EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem.
* EA blocks are only changed if they are exclusive to an inode, so
* holding xattr_sem also means that nothing but the EA block's reference
* count can change. Multiple writers to the same block are synchronized
* by the buffer lock.
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "xattr.h"
#include "acl.h"
#ifdef EXT4_XATTR_DEBUG
# define ea_idebug(inode, fmt, ...) \
printk(KERN_DEBUG "inode %s:%lu: " fmt "\n", \
inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...) \
printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \
bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__)
#else
# define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct ext4_xattr_header *,
struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
static const struct xattr_handler * const ext4_xattr_handler_map[] = {
[EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
[EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
[EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_SECURITY
[EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler,
#endif
};
const struct xattr_handler *ext4_xattr_handlers[] = {
&ext4_xattr_user_handler,
&ext4_xattr_trusted_handler,
#ifdef CONFIG_EXT4_FS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_EXT4_FS_SECURITY
&ext4_xattr_security_handler,
#endif
NULL
};
#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \
inode->i_sb->s_fs_info)->s_mb_cache)
ext4: fix lockdep warning about recursive inode locking Setting a large xattr value may require writing the attribute contents to an external inode. In this case we may need to lock the xattr inode along with the parent inode. This doesn't pose a deadlock risk because xattr inodes are not directly visible to the user and their access is restricted. Assign a lockdep subclass to xattr inode's lock. ============================================ WARNING: possible recursive locking detected 4.12.0-rc1+ #740 Not tainted -------------------------------------------- python/1822 is trying to acquire lock: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff804912ca>] ext4_xattr_set_entry+0x65a/0x7b0 but task is already holding lock: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803d6687>] vfs_setxattr+0x57/0xb0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&sb->s_type->i_mutex_key#15); lock(&sb->s_type->i_mutex_key#15); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by python/1822: #0: (sb_writers#10){.+.+.+}, at: [<ffffffff803d0eef>] mnt_want_write+0x1f/0x50 #1: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803d6687>] vfs_setxattr+0x57/0xb0 #2: (jbd2_handle){.+.+..}, at: [<ffffffff80493f40>] start_this_handle+0xf0/0x420 #3: (&ei->xattr_sem){++++..}, at: [<ffffffff804920ba>] ext4_xattr_set_handle+0x9a/0x4f0 stack backtrace: CPU: 0 PID: 1822 Comm: python Not tainted 4.12.0-rc1+ #740 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x9e __lock_acquire+0x5f3/0x1750 lock_acquire+0xb5/0x1d0 down_write+0x2c/0x60 ext4_xattr_set_entry+0x65a/0x7b0 ext4_xattr_block_set+0x1b2/0x9b0 ext4_xattr_set_handle+0x322/0x4f0 ext4_xattr_set+0x144/0x1a0 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x12e/0x150 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:17:10 +08:00
#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
{
lockdep_set_subclass(&ea_inode->i_rwsem, 1);
}
#endif
static __le32 ext4_xattr_block_csum(struct inode *inode,
sector_t block_nr,
struct ext4_xattr_header *hdr)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
__u32 csum;
__le64 dsk_block_nr = cpu_to_le64(block_nr);
__u32 dummy_csum = 0;
int offset = offsetof(struct ext4_xattr_header, h_checksum);
csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&dsk_block_nr,
sizeof(dsk_block_nr));
csum = ext4_chksum(sbi, csum, (__u8 *)hdr, offset);
csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));
offset += sizeof(dummy_csum);
csum = ext4_chksum(sbi, csum, (__u8 *)hdr + offset,
EXT4_BLOCK_SIZE(inode->i_sb) - offset);
return cpu_to_le32(csum);
}
static int ext4_xattr_block_csum_verify(struct inode *inode,
struct buffer_head *bh)
{
struct ext4_xattr_header *hdr = BHDR(bh);
int ret = 1;
if (ext4_has_metadata_csum(inode->i_sb)) {
lock_buffer(bh);
ret = (hdr->h_checksum == ext4_xattr_block_csum(inode,
bh->b_blocknr, hdr));
unlock_buffer(bh);
}
return ret;
}
static void ext4_xattr_block_csum_set(struct inode *inode,
struct buffer_head *bh)
{
if (ext4_has_metadata_csum(inode->i_sb))
BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode,
bh->b_blocknr, BHDR(bh));
}
static inline const struct xattr_handler *
ext4_xattr_handler(int name_index)
{
const struct xattr_handler *handler = NULL;
if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map))
handler = ext4_xattr_handler_map[name_index];
return handler;
}
static int
ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
void *value_start)
{
struct ext4_xattr_entry *e = entry;
/* Find the end of the names list */
while (!IS_LAST_ENTRY(e)) {
struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
if ((void *)next >= end)
return -EFSCORRUPTED;
e = next;
}
/* Check the values */
while (!IS_LAST_ENTRY(entry)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (entry->e_value_size != 0 &&
entry->e_value_inum == 0) {
u16 offs = le16_to_cpu(entry->e_value_offs);
u32 size = le32_to_cpu(entry->e_value_size);
void *value;
/*
* The value cannot overlap the names, and the value
* with padding cannot extend beyond 'end'. Check both
* the padded and unpadded sizes, since the size may
* overflow to 0 when adding padding.
*/
if (offs > end - value_start)
return -EFSCORRUPTED;
value = value_start + offs;
if (value < (void *)e + sizeof(u32) ||
size > end - value ||
EXT4_XATTR_SIZE(size) > end - value)
return -EFSCORRUPTED;
}
entry = EXT4_XATTR_NEXT(entry);
}
return 0;
}
static inline int
ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
{
int error;
if (buffer_verified(bh))
return 0;
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1))
return -EFSCORRUPTED;
if (!ext4_xattr_block_csum_verify(inode, bh))
return -EFSBADCRC;
error = ext4_xattr_check_entries(BFIRST(bh), bh->b_data + bh->b_size,
bh->b_data);
if (!error)
set_buffer_verified(bh);
return error;
}
static int
__xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
void *end, const char *function, unsigned int line)
{
int error = -EFSCORRUPTED;
if (end - (void *)header < sizeof(*header) + sizeof(u32) ||
(header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
goto errout;
error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header));
errout:
if (error)
__ext4_error_inode(inode, function, line, 0,
"corrupted in-inode xattr");
return error;
}
#define xattr_check_inode(inode, header, end) \
__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
static int
ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
const char *name, int sorted)
{
struct ext4_xattr_entry *entry;
size_t name_len;
int cmp = 1;
if (name == NULL)
return -EINVAL;
name_len = strlen(name);
entry = *pentry;
for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
cmp = name_index - entry->e_name_index;
if (!cmp)
cmp = name_len - entry->e_name_len;
if (!cmp)
cmp = memcmp(name, entry->e_name, name_len);
if (cmp <= 0 && (sorted || cmp == 0))
break;
}
*pentry = entry;
return cmp ? -ENODATA : 0;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
/*
* Read the EA value from an inode.
*/
static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
{
unsigned long block = 0;
struct buffer_head *bh = NULL;
int blocksize = ea_inode->i_sb->s_blocksize;
size_t csize, copied = 0;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
while (copied < size) {
csize = (size - copied) > blocksize ? blocksize : size - copied;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
bh = ext4_bread(NULL, ea_inode, block, 0);
if (IS_ERR(bh))
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
return PTR_ERR(bh);
if (!bh)
return -EFSCORRUPTED;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
memcpy(buf, bh->b_data, csize);
brelse(bh);
buf += csize;
block += 1;
copied += csize;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
return 0;
}
static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
struct inode **ea_inode)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
{
struct inode *inode;
int err;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
inode = ext4_iget(parent->i_sb, ea_ino);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_error(parent->i_sb, "error while reading EA inode %lu "
"err=%d", ea_ino, err);
return err;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
if (is_bad_inode(inode)) {
ext4_error(parent->i_sb, "error while reading EA inode %lu "
"is_bad_inode", ea_ino);
err = -EIO;
goto error;
}
if (EXT4_XATTR_INODE_GET_PARENT(inode) != parent->i_ino ||
inode->i_generation != parent->i_generation) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_error(parent->i_sb, "Backpointer from EA inode %lu "
"to parent is invalid.", ea_ino);
err = -EINVAL;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
goto error;
}
if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_error(parent->i_sb, "EA inode %lu does not have "
"EXT4_EA_INODE_FL flag set.\n", ea_ino);
err = -EINVAL;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
goto error;
}
*ea_inode = inode;
return 0;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error:
iput(inode);
return err;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
/*
* Read the value from the EA inode.
*/
static int
ext4_xattr_inode_get(struct inode *inode, unsigned long ea_ino, void *buffer,
size_t size)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
{
struct inode *ea_inode;
int ret;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ret = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
if (ret)
return ret;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ret = ext4_xattr_inode_read(ea_inode, buffer, size);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
iput(ea_inode);
return ret;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
static int
ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
struct buffer_head *bh = NULL;
struct ext4_xattr_entry *entry;
size_t size;
int error;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
error = -ENODATA;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
ea_idebug(inode, "reading block %llu",
(unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh)
goto cleanup;
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(inode, bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
ext4_xattr_cache_insert(ext4_mb_cache, bh);
entry = BFIRST(bh);
error = ext4_xattr_find_entry(&entry, name_index, name, 1);
if (error)
goto cleanup;
size = le32_to_cpu(entry->e_value_size);
if (buffer) {
error = -ERANGE;
if (size > buffer_size)
goto cleanup;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (entry->e_value_inum) {
error = ext4_xattr_inode_get(inode,
le32_to_cpu(entry->e_value_inum),
buffer, size);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (error)
goto cleanup;
} else {
memcpy(buffer, bh->b_data +
le16_to_cpu(entry->e_value_offs), size);
}
}
error = size;
cleanup:
brelse(bh);
return error;
}
int
ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
struct ext4_xattr_ibody_header *header;
struct ext4_xattr_entry *entry;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
size_t size;
void *end;
int error;
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return -ENODATA;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
entry = IFIRST(header);
error = ext4_xattr_find_entry(&entry, name_index, name, 0);
if (error)
goto cleanup;
size = le32_to_cpu(entry->e_value_size);
if (buffer) {
error = -ERANGE;
if (size > buffer_size)
goto cleanup;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (entry->e_value_inum) {
error = ext4_xattr_inode_get(inode,
le32_to_cpu(entry->e_value_inum),
buffer, size);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (error)
goto cleanup;
} else {
memcpy(buffer, (void *)IFIRST(header) +
le16_to_cpu(entry->e_value_offs), size);
}
}
error = size;
cleanup:
brelse(iloc.bh);
return error;
}
/*
* ext4_xattr_get()
*
* Copy an extended attribute into the buffer
* provided, or compute the buffer size required.
* Buffer is NULL to compute the size of the buffer required.
*
* Returns a negative error number on failure, or the number of bytes
* used / required on success.
*/
int
ext4_xattr_get(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
int error;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
if (strlen(name) > 255)
return -ERANGE;
down_read(&EXT4_I(inode)->xattr_sem);
error = ext4_xattr_ibody_get(inode, name_index, name, buffer,
buffer_size);
if (error == -ENODATA)
error = ext4_xattr_block_get(inode, name_index, name, buffer,
buffer_size);
up_read(&EXT4_I(inode)->xattr_sem);
return error;
}
static int
ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
const struct xattr_handler *handler =
ext4_xattr_handler(entry->e_name_index);
if (handler && (!handler->list || handler->list(dentry))) {
const char *prefix = handler->prefix ?: handler->name;
size_t prefix_len = strlen(prefix);
size_t size = prefix_len + entry->e_name_len + 1;
if (buffer) {
if (size > rest)
return -ERANGE;
memcpy(buffer, prefix, prefix_len);
buffer += prefix_len;
memcpy(buffer, entry->e_name, entry->e_name_len);
buffer += entry->e_name_len;
*buffer++ = 0;
}
rest -= size;
}
}
return buffer_size - rest; /* total size */
}
static int
ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
int error;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
error = 0;
if (!EXT4_I(inode)->i_file_acl)
goto cleanup;
ea_idebug(inode, "reading block %llu",
(unsigned long long)EXT4_I(inode)->i_file_acl);
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bh)
goto cleanup;
ea_bdebug(bh, "b_count=%d, refcount=%d",
atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
if (ext4_xattr_check_block(inode, bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
ext4_xattr_cache_insert(ext4_mb_cache, bh);
error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
return error;
}
static int
ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
void *end;
int error;
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
return 0;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
error = ext4_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
brelse(iloc.bh);
return error;
}
/*
* Inode operation listxattr()
*
* d_inode(dentry)->i_rwsem: don't care
*
* Copy a list of attribute names into the buffer
* provided, or compute the buffer size required.
* Buffer is NULL to compute the size of the buffer required.
*
* Returns a negative error number on failure, or the number of bytes
* used / required on success.
*/
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int ret, ret2;
down_read(&EXT4_I(d_inode(dentry))->xattr_sem);
ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
if (ret < 0)
goto errout;
if (buffer) {
buffer += ret;
buffer_size -= ret;
}
ret = ext4_xattr_block_list(dentry, buffer, buffer_size);
if (ret < 0)
goto errout;
ret += ret2;
errout:
up_read(&EXT4_I(d_inode(dentry))->xattr_sem);
return ret;
}
/*
* If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is
* not set, set it.
*/
static void ext4_xattr_update_super_block(handle_t *handle,
struct super_block *sb)
{
if (ext4_has_feature_xattr(sb))
return;
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
ext4_set_feature_xattr(sb);
ext4_handle_dirty_super(handle, sb);
}
}
/*
ext4: fix jbd2 warning under heavy xattr load When heavily exercising xattr code the assertion that jbd2_journal_dirty_metadata() shouldn't return error was triggered: WARNING: at /srv/autobuild-ceph/gitbuilder.git/build/fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0x1ba/0x260() CPU: 0 PID: 8877 Comm: ceph-osd Tainted: G W 3.10.0-ceph-00049-g68d04c9 #1 Hardware name: Dell Inc. PowerEdge R410/01V648, BIOS 1.6.3 02/07/2011 ffffffff81a1d3c8 ffff880214469928 ffffffff816311b0 ffff880214469968 ffffffff8103fae0 ffff880214469958 ffff880170a9dc30 ffff8802240fbe80 0000000000000000 ffff88020b366000 ffff8802256e7510 ffff880214469978 Call Trace: [<ffffffff816311b0>] dump_stack+0x19/0x1b [<ffffffff8103fae0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8103fb2a>] warn_slowpath_null+0x1a/0x20 [<ffffffff81267c2a>] jbd2_journal_dirty_metadata+0x1ba/0x260 [<ffffffff81245093>] __ext4_handle_dirty_metadata+0xa3/0x140 [<ffffffff812561f3>] ext4_xattr_release_block+0x103/0x1f0 [<ffffffff81256680>] ext4_xattr_block_set+0x1e0/0x910 [<ffffffff8125795b>] ext4_xattr_set_handle+0x38b/0x4a0 [<ffffffff810a319d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81257b32>] ext4_xattr_set+0xc2/0x140 [<ffffffff81258547>] ext4_xattr_user_set+0x47/0x50 [<ffffffff811935ce>] generic_setxattr+0x6e/0x90 [<ffffffff81193ecb>] __vfs_setxattr_noperm+0x7b/0x1c0 [<ffffffff811940d4>] vfs_setxattr+0xc4/0xd0 [<ffffffff8119421e>] setxattr+0x13e/0x1e0 [<ffffffff811719c7>] ? __sb_start_write+0xe7/0x1b0 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118c65c>] ? fget_light+0x3c/0x130 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118f1f8>] ? __mnt_want_write+0x58/0x70 [<ffffffff811946be>] SyS_fsetxattr+0xbe/0x100 [<ffffffff816407c2>] system_call_fastpath+0x16/0x1b The reason for the warning is that buffer_head passed into jbd2_journal_dirty_metadata() didn't have journal_head attached. This is caused by the following race of two ext4_xattr_release_block() calls: CPU1 CPU2 ext4_xattr_release_block() ext4_xattr_release_block() lock_buffer(bh); /* False */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); unlock_buffer(bh); lock_buffer(bh); /* True */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) get_bh(bh); ext4_free_blocks() ... jbd2_journal_forget() jbd2_journal_unfile_buffer() -> JH is gone error = ext4_handle_dirty_xattr_block(handle, inode, bh); -> triggers the warning We fix the problem by moving ext4_handle_dirty_xattr_block() under the buffer lock. Sadly this cannot be done in nojournal mode as that function can call sync_dirty_buffer() which would deadlock. Luckily in nojournal mode the race is harmless (we only dirty already freed buffer) and thus for nojournal mode we leave the dirtying outside of the buffer lock. Reported-by: Sage Weil <sage@inktank.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-04-07 22:54:21 +08:00
* Release the xattr block BH: If the reference count is > 1, decrement it;
* otherwise free the block.
*/
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
u32 hash, ref;
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
int error = 0;
BUFFER_TRACE(bh, "get_write_access");
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
error = ext4_journal_get_write_access(handle, bh);
if (error)
goto out;
lock_buffer(bh);
hash = le32_to_cpu(BHDR(bh)->h_hash);
ref = le32_to_cpu(BHDR(bh)->h_refcount);
if (ref == 1) {
ea_bdebug(bh, "refcount now=0; freeing");
/*
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr);
get_bh(bh);
ext4: fix jbd2 warning under heavy xattr load When heavily exercising xattr code the assertion that jbd2_journal_dirty_metadata() shouldn't return error was triggered: WARNING: at /srv/autobuild-ceph/gitbuilder.git/build/fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0x1ba/0x260() CPU: 0 PID: 8877 Comm: ceph-osd Tainted: G W 3.10.0-ceph-00049-g68d04c9 #1 Hardware name: Dell Inc. PowerEdge R410/01V648, BIOS 1.6.3 02/07/2011 ffffffff81a1d3c8 ffff880214469928 ffffffff816311b0 ffff880214469968 ffffffff8103fae0 ffff880214469958 ffff880170a9dc30 ffff8802240fbe80 0000000000000000 ffff88020b366000 ffff8802256e7510 ffff880214469978 Call Trace: [<ffffffff816311b0>] dump_stack+0x19/0x1b [<ffffffff8103fae0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8103fb2a>] warn_slowpath_null+0x1a/0x20 [<ffffffff81267c2a>] jbd2_journal_dirty_metadata+0x1ba/0x260 [<ffffffff81245093>] __ext4_handle_dirty_metadata+0xa3/0x140 [<ffffffff812561f3>] ext4_xattr_release_block+0x103/0x1f0 [<ffffffff81256680>] ext4_xattr_block_set+0x1e0/0x910 [<ffffffff8125795b>] ext4_xattr_set_handle+0x38b/0x4a0 [<ffffffff810a319d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81257b32>] ext4_xattr_set+0xc2/0x140 [<ffffffff81258547>] ext4_xattr_user_set+0x47/0x50 [<ffffffff811935ce>] generic_setxattr+0x6e/0x90 [<ffffffff81193ecb>] __vfs_setxattr_noperm+0x7b/0x1c0 [<ffffffff811940d4>] vfs_setxattr+0xc4/0xd0 [<ffffffff8119421e>] setxattr+0x13e/0x1e0 [<ffffffff811719c7>] ? __sb_start_write+0xe7/0x1b0 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118c65c>] ? fget_light+0x3c/0x130 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118f1f8>] ? __mnt_want_write+0x58/0x70 [<ffffffff811946be>] SyS_fsetxattr+0xbe/0x100 [<ffffffff816407c2>] system_call_fastpath+0x16/0x1b The reason for the warning is that buffer_head passed into jbd2_journal_dirty_metadata() didn't have journal_head attached. This is caused by the following race of two ext4_xattr_release_block() calls: CPU1 CPU2 ext4_xattr_release_block() ext4_xattr_release_block() lock_buffer(bh); /* False */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); unlock_buffer(bh); lock_buffer(bh); /* True */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) get_bh(bh); ext4_free_blocks() ... jbd2_journal_forget() jbd2_journal_unfile_buffer() -> JH is gone error = ext4_handle_dirty_xattr_block(handle, inode, bh); -> triggers the warning We fix the problem by moving ext4_handle_dirty_xattr_block() under the buffer lock. Sadly this cannot be done in nojournal mode as that function can call sync_dirty_buffer() which would deadlock. Luckily in nojournal mode the race is harmless (we only dirty already freed buffer) and thus for nojournal mode we leave the dirtying outside of the buffer lock. Reported-by: Sage Weil <sage@inktank.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-04-07 22:54:21 +08:00
unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
} else {
ref--;
BHDR(bh)->h_refcount = cpu_to_le32(ref);
if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
struct mb_cache_entry *ce;
ce = mb_cache_entry_get(ext4_mb_cache, hash,
bh->b_blocknr);
if (ce) {
ce->e_reusable = 1;
mb_cache_entry_put(ext4_mb_cache, ce);
}
}
ext4_xattr_block_csum_set(inode, bh);
ext4: fix jbd2 warning under heavy xattr load When heavily exercising xattr code the assertion that jbd2_journal_dirty_metadata() shouldn't return error was triggered: WARNING: at /srv/autobuild-ceph/gitbuilder.git/build/fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0x1ba/0x260() CPU: 0 PID: 8877 Comm: ceph-osd Tainted: G W 3.10.0-ceph-00049-g68d04c9 #1 Hardware name: Dell Inc. PowerEdge R410/01V648, BIOS 1.6.3 02/07/2011 ffffffff81a1d3c8 ffff880214469928 ffffffff816311b0 ffff880214469968 ffffffff8103fae0 ffff880214469958 ffff880170a9dc30 ffff8802240fbe80 0000000000000000 ffff88020b366000 ffff8802256e7510 ffff880214469978 Call Trace: [<ffffffff816311b0>] dump_stack+0x19/0x1b [<ffffffff8103fae0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8103fb2a>] warn_slowpath_null+0x1a/0x20 [<ffffffff81267c2a>] jbd2_journal_dirty_metadata+0x1ba/0x260 [<ffffffff81245093>] __ext4_handle_dirty_metadata+0xa3/0x140 [<ffffffff812561f3>] ext4_xattr_release_block+0x103/0x1f0 [<ffffffff81256680>] ext4_xattr_block_set+0x1e0/0x910 [<ffffffff8125795b>] ext4_xattr_set_handle+0x38b/0x4a0 [<ffffffff810a319d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81257b32>] ext4_xattr_set+0xc2/0x140 [<ffffffff81258547>] ext4_xattr_user_set+0x47/0x50 [<ffffffff811935ce>] generic_setxattr+0x6e/0x90 [<ffffffff81193ecb>] __vfs_setxattr_noperm+0x7b/0x1c0 [<ffffffff811940d4>] vfs_setxattr+0xc4/0xd0 [<ffffffff8119421e>] setxattr+0x13e/0x1e0 [<ffffffff811719c7>] ? __sb_start_write+0xe7/0x1b0 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118c65c>] ? fget_light+0x3c/0x130 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118f1f8>] ? __mnt_want_write+0x58/0x70 [<ffffffff811946be>] SyS_fsetxattr+0xbe/0x100 [<ffffffff816407c2>] system_call_fastpath+0x16/0x1b The reason for the warning is that buffer_head passed into jbd2_journal_dirty_metadata() didn't have journal_head attached. This is caused by the following race of two ext4_xattr_release_block() calls: CPU1 CPU2 ext4_xattr_release_block() ext4_xattr_release_block() lock_buffer(bh); /* False */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); unlock_buffer(bh); lock_buffer(bh); /* True */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) get_bh(bh); ext4_free_blocks() ... jbd2_journal_forget() jbd2_journal_unfile_buffer() -> JH is gone error = ext4_handle_dirty_xattr_block(handle, inode, bh); -> triggers the warning We fix the problem by moving ext4_handle_dirty_xattr_block() under the buffer lock. Sadly this cannot be done in nojournal mode as that function can call sync_dirty_buffer() which would deadlock. Luckily in nojournal mode the race is harmless (we only dirty already freed buffer) and thus for nojournal mode we leave the dirtying outside of the buffer lock. Reported-by: Sage Weil <sage@inktank.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-04-07 22:54:21 +08:00
/*
* Beware of this ugliness: Releasing of xattr block references
* from different inodes can race and so we have to protect
* from a race where someone else frees the block (and releases
* its journal_head) before we are done dirtying the buffer. In
* nojournal mode this race is harmless and we actually cannot
* call ext4_handle_dirty_metadata() with locked buffer as
ext4: fix jbd2 warning under heavy xattr load When heavily exercising xattr code the assertion that jbd2_journal_dirty_metadata() shouldn't return error was triggered: WARNING: at /srv/autobuild-ceph/gitbuilder.git/build/fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0x1ba/0x260() CPU: 0 PID: 8877 Comm: ceph-osd Tainted: G W 3.10.0-ceph-00049-g68d04c9 #1 Hardware name: Dell Inc. PowerEdge R410/01V648, BIOS 1.6.3 02/07/2011 ffffffff81a1d3c8 ffff880214469928 ffffffff816311b0 ffff880214469968 ffffffff8103fae0 ffff880214469958 ffff880170a9dc30 ffff8802240fbe80 0000000000000000 ffff88020b366000 ffff8802256e7510 ffff880214469978 Call Trace: [<ffffffff816311b0>] dump_stack+0x19/0x1b [<ffffffff8103fae0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8103fb2a>] warn_slowpath_null+0x1a/0x20 [<ffffffff81267c2a>] jbd2_journal_dirty_metadata+0x1ba/0x260 [<ffffffff81245093>] __ext4_handle_dirty_metadata+0xa3/0x140 [<ffffffff812561f3>] ext4_xattr_release_block+0x103/0x1f0 [<ffffffff81256680>] ext4_xattr_block_set+0x1e0/0x910 [<ffffffff8125795b>] ext4_xattr_set_handle+0x38b/0x4a0 [<ffffffff810a319d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81257b32>] ext4_xattr_set+0xc2/0x140 [<ffffffff81258547>] ext4_xattr_user_set+0x47/0x50 [<ffffffff811935ce>] generic_setxattr+0x6e/0x90 [<ffffffff81193ecb>] __vfs_setxattr_noperm+0x7b/0x1c0 [<ffffffff811940d4>] vfs_setxattr+0xc4/0xd0 [<ffffffff8119421e>] setxattr+0x13e/0x1e0 [<ffffffff811719c7>] ? __sb_start_write+0xe7/0x1b0 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118c65c>] ? fget_light+0x3c/0x130 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118f1f8>] ? __mnt_want_write+0x58/0x70 [<ffffffff811946be>] SyS_fsetxattr+0xbe/0x100 [<ffffffff816407c2>] system_call_fastpath+0x16/0x1b The reason for the warning is that buffer_head passed into jbd2_journal_dirty_metadata() didn't have journal_head attached. This is caused by the following race of two ext4_xattr_release_block() calls: CPU1 CPU2 ext4_xattr_release_block() ext4_xattr_release_block() lock_buffer(bh); /* False */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); unlock_buffer(bh); lock_buffer(bh); /* True */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) get_bh(bh); ext4_free_blocks() ... jbd2_journal_forget() jbd2_journal_unfile_buffer() -> JH is gone error = ext4_handle_dirty_xattr_block(handle, inode, bh); -> triggers the warning We fix the problem by moving ext4_handle_dirty_xattr_block() under the buffer lock. Sadly this cannot be done in nojournal mode as that function can call sync_dirty_buffer() which would deadlock. Luckily in nojournal mode the race is harmless (we only dirty already freed buffer) and thus for nojournal mode we leave the dirtying outside of the buffer lock. Reported-by: Sage Weil <sage@inktank.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-04-07 22:54:21 +08:00
* that function can call sync_dirty_buffer() so for that case
* we handle the dirtying after unlocking the buffer.
*/
if (ext4_handle_valid(handle))
error = ext4_handle_dirty_metadata(handle, inode, bh);
unlock_buffer(bh);
ext4: fix jbd2 warning under heavy xattr load When heavily exercising xattr code the assertion that jbd2_journal_dirty_metadata() shouldn't return error was triggered: WARNING: at /srv/autobuild-ceph/gitbuilder.git/build/fs/jbd2/transaction.c:1237 jbd2_journal_dirty_metadata+0x1ba/0x260() CPU: 0 PID: 8877 Comm: ceph-osd Tainted: G W 3.10.0-ceph-00049-g68d04c9 #1 Hardware name: Dell Inc. PowerEdge R410/01V648, BIOS 1.6.3 02/07/2011 ffffffff81a1d3c8 ffff880214469928 ffffffff816311b0 ffff880214469968 ffffffff8103fae0 ffff880214469958 ffff880170a9dc30 ffff8802240fbe80 0000000000000000 ffff88020b366000 ffff8802256e7510 ffff880214469978 Call Trace: [<ffffffff816311b0>] dump_stack+0x19/0x1b [<ffffffff8103fae0>] warn_slowpath_common+0x70/0xa0 [<ffffffff8103fb2a>] warn_slowpath_null+0x1a/0x20 [<ffffffff81267c2a>] jbd2_journal_dirty_metadata+0x1ba/0x260 [<ffffffff81245093>] __ext4_handle_dirty_metadata+0xa3/0x140 [<ffffffff812561f3>] ext4_xattr_release_block+0x103/0x1f0 [<ffffffff81256680>] ext4_xattr_block_set+0x1e0/0x910 [<ffffffff8125795b>] ext4_xattr_set_handle+0x38b/0x4a0 [<ffffffff810a319d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff81257b32>] ext4_xattr_set+0xc2/0x140 [<ffffffff81258547>] ext4_xattr_user_set+0x47/0x50 [<ffffffff811935ce>] generic_setxattr+0x6e/0x90 [<ffffffff81193ecb>] __vfs_setxattr_noperm+0x7b/0x1c0 [<ffffffff811940d4>] vfs_setxattr+0xc4/0xd0 [<ffffffff8119421e>] setxattr+0x13e/0x1e0 [<ffffffff811719c7>] ? __sb_start_write+0xe7/0x1b0 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118c65c>] ? fget_light+0x3c/0x130 [<ffffffff8118f2e8>] ? mnt_want_write_file+0x28/0x60 [<ffffffff8118f1f8>] ? __mnt_want_write+0x58/0x70 [<ffffffff811946be>] SyS_fsetxattr+0xbe/0x100 [<ffffffff816407c2>] system_call_fastpath+0x16/0x1b The reason for the warning is that buffer_head passed into jbd2_journal_dirty_metadata() didn't have journal_head attached. This is caused by the following race of two ext4_xattr_release_block() calls: CPU1 CPU2 ext4_xattr_release_block() ext4_xattr_release_block() lock_buffer(bh); /* False */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) } else { le32_add_cpu(&BHDR(bh)->h_refcount, -1); unlock_buffer(bh); lock_buffer(bh); /* True */ if (BHDR(bh)->h_refcount == cpu_to_le32(1)) get_bh(bh); ext4_free_blocks() ... jbd2_journal_forget() jbd2_journal_unfile_buffer() -> JH is gone error = ext4_handle_dirty_xattr_block(handle, inode, bh); -> triggers the warning We fix the problem by moving ext4_handle_dirty_xattr_block() under the buffer lock. Sadly this cannot be done in nojournal mode as that function can call sync_dirty_buffer() which would deadlock. Luckily in nojournal mode the race is harmless (we only dirty already freed buffer) and thus for nojournal mode we leave the dirtying outside of the buffer lock. Reported-by: Sage Weil <sage@inktank.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-04-07 22:54:21 +08:00
if (!ext4_handle_valid(handle))
error = ext4_handle_dirty_metadata(handle, inode, bh);
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
if (IS_SYNC(inode))
ext4_handle_sync(handle);
dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
ea_bdebug(bh, "refcount now=%d; releasing",
le32_to_cpu(BHDR(bh)->h_refcount));
}
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
out:
ext4_std_error(inode->i_sb, error);
return;
}
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/*
* Find the available free space for EAs. This also returns the total number of
* bytes used by EA entries.
*/
static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
size_t *min_offs, void *base, int *total)
{
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!last->e_value_inum && last->e_value_size) {
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < *min_offs)
*min_offs = offs;
}
if (total)
*total += EXT4_XATTR_LEN(last->e_name_len);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
}
return (*min_offs - ((void *)last - base) - sizeof(__u32));
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
/*
* Write the value of the EA in an inode.
*/
static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
const void *buf, int bufsize)
{
struct buffer_head *bh = NULL;
unsigned long block = 0;
unsigned blocksize = ea_inode->i_sb->s_blocksize;
unsigned max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
int csize, wsize = 0;
int ret = 0;
int retries = 0;
retry:
while (ret >= 0 && ret < max_blocks) {
struct ext4_map_blocks map;
map.m_lblk = block += ret;
map.m_len = max_blocks -= ret;
ret = ext4_map_blocks(handle, ea_inode, &map,
EXT4_GET_BLOCKS_CREATE);
if (ret <= 0) {
ext4_mark_inode_dirty(handle, ea_inode);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(ea_inode->i_sb, &retries)) {
ret = 0;
goto retry;
}
break;
}
}
if (ret < 0)
return ret;
block = 0;
while (wsize < bufsize) {
if (bh != NULL)
brelse(bh);
csize = (bufsize - wsize) > blocksize ? blocksize :
bufsize - wsize;
bh = ext4_getblk(handle, ea_inode, block, 0);
if (IS_ERR(bh))
return PTR_ERR(bh);
ret = ext4_journal_get_write_access(handle, bh);
if (ret)
goto out;
memcpy(bh->b_data, buf, csize);
set_buffer_uptodate(bh);
ext4_handle_dirty_metadata(handle, ea_inode, bh);
buf += csize;
wsize += csize;
block += 1;
}
inode_lock(ea_inode);
i_size_write(ea_inode, wsize);
ext4_update_i_disksize(ea_inode, wsize);
inode_unlock(ea_inode);
ext4_mark_inode_dirty(handle, ea_inode);
out:
brelse(bh);
return ret;
}
/*
* Create an inode to store the value of a large EA.
*/
static struct inode *ext4_xattr_inode_create(handle_t *handle,
struct inode *inode)
{
struct inode *ea_inode = NULL;
uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
ext4: attach jinode after creation of xattr inode In data=ordered mode jinode needs to be attached to the xattr inode when writing data to it. Attachment normally occurs during file open for regular files. Since we are not using file interface to write to the xattr inode, the jinode attach needs to be done manually. Otherwise the following crash occurs in data=ordered mode. BUG: unable to handle kernel NULL pointer dereference at (null) IP: jbd2_journal_file_inode+0x37/0x110 PGD 13b3c0067 P4D 13b3c0067 PUD 137660067 PMD 0 Oops: 0000 [#1] SMP CPU: 3 PID: 1877 Comm: python Not tainted 4.12.0-rc1+ #749 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88010e368980 task.stack: ffffc90000374000 RIP: 0010:jbd2_journal_file_inode+0x37/0x110 RSP: 0018:ffffc90000377980 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880123b06230 RCX: 0000000000280000 RDX: 0000000000000006 RSI: 0000000000000000 RDI: ffff88012c8585d0 RBP: ffffc900003779b0 R08: 0000000000000202 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000400 R12: ffff8801111f81c0 R13: ffff88013b2b6800 R14: ffffc90000377ab0 R15: 0000000000000001 FS: 00007f0c99b77740(0000) GS:ffff88013fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000136d91000 CR4: 00000000000006e0 Call Trace: jbd2_journal_inode_add_write+0xe/0x10 ext4_map_blocks+0x59e/0x620 ext4_xattr_set_entry+0x501/0x7d0 ext4_xattr_block_set+0x1b2/0x9b0 ext4_xattr_set_handle+0x322/0x4f0 ext4_xattr_set+0x144/0x1a0 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x12e/0x150 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:24:31 +08:00
int err;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
/*
* Let the next inode be the goal, so we try and allocate the EA inode
* in the same group, or nearby one.
*/
ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG | 0600, NULL, inode->i_ino + 1, owner,
ext4: do not set posix acls on xattr inodes We don't need acls on xattr inodes because they are not directly accessible from user mode. Besides lockdep complains about recursive locking of xattr_sem as seen below. ============================================= [ INFO: possible recursive locking detected ] 4.11.0-rc8+ #402 Not tainted --------------------------------------------- python/1894 is trying to acquire lock: (&ei->xattr_sem){++++..}, at: [<ffffffff804878a6>] ext4_xattr_get+0x66/0x270 but task is already holding lock: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&ei->xattr_sem); lock(&ei->xattr_sem); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by python/1894: #0: (sb_writers#10){.+.+.+}, at: [<ffffffff803d829f>] mnt_want_write+0x1f/0x50 #1: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803dda27>] vfs_setxattr+0x57/0xb0 #2: (&ei->xattr_sem){++++..}, at: [<ffffffff80489500>] ext4_xattr_set_handle+0xa0/0x5d0 stack backtrace: CPU: 0 PID: 1894 Comm: python Not tainted 4.11.0-rc8+ #402 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x99 __lock_acquire+0x5f3/0x1830 lock_acquire+0xb5/0x1d0 down_read+0x2f/0x60 ext4_xattr_get+0x66/0x270 ext4_get_acl+0x43/0x1e0 get_acl+0x72/0xf0 posix_acl_create+0x5e/0x170 ext4_init_acl+0x21/0xc0 __ext4_new_inode+0xffd/0x16b0 ext4_xattr_set_entry+0x5ea/0xb70 ext4_xattr_block_set+0x1b5/0x970 ext4_xattr_set_handle+0x351/0x5d0 ext4_xattr_set+0x124/0x180 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x129/0x160 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:21:39 +08:00
EXT4_EA_INODE_FL);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!IS_ERR(ea_inode)) {
ea_inode->i_op = &ext4_file_inode_operations;
ea_inode->i_fop = &ext4_file_operations;
ext4_set_aops(ea_inode);
ext4: fix lockdep warning about recursive inode locking Setting a large xattr value may require writing the attribute contents to an external inode. In this case we may need to lock the xattr inode along with the parent inode. This doesn't pose a deadlock risk because xattr inodes are not directly visible to the user and their access is restricted. Assign a lockdep subclass to xattr inode's lock. ============================================ WARNING: possible recursive locking detected 4.12.0-rc1+ #740 Not tainted -------------------------------------------- python/1822 is trying to acquire lock: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff804912ca>] ext4_xattr_set_entry+0x65a/0x7b0 but task is already holding lock: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803d6687>] vfs_setxattr+0x57/0xb0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&sb->s_type->i_mutex_key#15); lock(&sb->s_type->i_mutex_key#15); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by python/1822: #0: (sb_writers#10){.+.+.+}, at: [<ffffffff803d0eef>] mnt_want_write+0x1f/0x50 #1: (&sb->s_type->i_mutex_key#15){+.+...}, at: [<ffffffff803d6687>] vfs_setxattr+0x57/0xb0 #2: (jbd2_handle){.+.+..}, at: [<ffffffff80493f40>] start_this_handle+0xf0/0x420 #3: (&ei->xattr_sem){++++..}, at: [<ffffffff804920ba>] ext4_xattr_set_handle+0x9a/0x4f0 stack backtrace: CPU: 0 PID: 1822 Comm: python Not tainted 4.12.0-rc1+ #740 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x67/0x9e __lock_acquire+0x5f3/0x1750 lock_acquire+0xb5/0x1d0 down_write+0x2c/0x60 ext4_xattr_set_entry+0x65a/0x7b0 ext4_xattr_block_set+0x1b2/0x9b0 ext4_xattr_set_handle+0x322/0x4f0 ext4_xattr_set+0x144/0x1a0 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x12e/0x150 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:17:10 +08:00
ext4_xattr_inode_set_class(ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ea_inode->i_generation = inode->i_generation;
EXT4_I(ea_inode)->i_flags |= EXT4_EA_INODE_FL;
/*
* A back-pointer from EA inode to parent inode will be useful
* for e2fsck.
*/
EXT4_XATTR_INODE_SET_PARENT(ea_inode, inode->i_ino);
unlock_new_inode(ea_inode);
ext4: attach jinode after creation of xattr inode In data=ordered mode jinode needs to be attached to the xattr inode when writing data to it. Attachment normally occurs during file open for regular files. Since we are not using file interface to write to the xattr inode, the jinode attach needs to be done manually. Otherwise the following crash occurs in data=ordered mode. BUG: unable to handle kernel NULL pointer dereference at (null) IP: jbd2_journal_file_inode+0x37/0x110 PGD 13b3c0067 P4D 13b3c0067 PUD 137660067 PMD 0 Oops: 0000 [#1] SMP CPU: 3 PID: 1877 Comm: python Not tainted 4.12.0-rc1+ #749 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff88010e368980 task.stack: ffffc90000374000 RIP: 0010:jbd2_journal_file_inode+0x37/0x110 RSP: 0018:ffffc90000377980 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff880123b06230 RCX: 0000000000280000 RDX: 0000000000000006 RSI: 0000000000000000 RDI: ffff88012c8585d0 RBP: ffffc900003779b0 R08: 0000000000000202 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000400 R12: ffff8801111f81c0 R13: ffff88013b2b6800 R14: ffffc90000377ab0 R15: 0000000000000001 FS: 00007f0c99b77740(0000) GS:ffff88013fd80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000136d91000 CR4: 00000000000006e0 Call Trace: jbd2_journal_inode_add_write+0xe/0x10 ext4_map_blocks+0x59e/0x620 ext4_xattr_set_entry+0x501/0x7d0 ext4_xattr_block_set+0x1b2/0x9b0 ext4_xattr_set_handle+0x322/0x4f0 ext4_xattr_set+0x144/0x1a0 ext4_xattr_user_set+0x34/0x40 __vfs_setxattr+0x66/0x80 __vfs_setxattr_noperm+0x69/0x1c0 vfs_setxattr+0xa2/0xb0 setxattr+0x12e/0x150 path_setxattr+0x87/0xb0 SyS_setxattr+0xf/0x20 entry_SYSCALL_64_fastpath+0x18/0xad Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-06-22 09:24:31 +08:00
err = ext4_inode_attach_jinode(ea_inode);
if (err) {
iput(ea_inode);
return ERR_PTR(err);
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
return ea_inode;
}
/*
* Unlink the inode storing the value of the EA.
*/
int ext4_xattr_inode_unlink(struct inode *inode, unsigned long ea_ino)
{
struct inode *ea_inode = NULL;
int err;
err = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (err)
return err;
clear_nlink(ea_inode);
iput(ea_inode);
return 0;
}
/*
* Add value of the EA in an inode.
*/
static int ext4_xattr_inode_set(handle_t *handle, struct inode *inode,
unsigned long *ea_ino, const void *value,
size_t value_len)
{
struct inode *ea_inode;
int err;
/* Create an inode for the EA value */
ea_inode = ext4_xattr_inode_create(handle, inode);
if (IS_ERR(ea_inode))
return PTR_ERR(ea_inode);
err = ext4_xattr_inode_write(handle, ea_inode, value, value_len);
if (err)
clear_nlink(ea_inode);
else
*ea_ino = ea_inode->i_ino;
iput(ea_inode);
return err;
}
static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
struct ext4_xattr_search *s,
handle_t *handle, struct inode *inode)
{
struct ext4_xattr_entry *last;
size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int in_inode = i->in_inode;
int rc;
/* Compute min_offs and last. */
last = s->first;
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!last->e_value_inum && last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
min_offs = offs;
}
}
free = min_offs - ((void *)last - s->base) - sizeof(__u32);
if (!s->not_found) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!in_inode &&
!s->here->e_value_inum && s->here->e_value_size) {
size_t size = le32_to_cpu(s->here->e_value_size);
free += EXT4_XATTR_SIZE(size);
}
free += EXT4_XATTR_LEN(name_len);
}
if (i->value) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
size_t value_len = EXT4_XATTR_SIZE(i->value_len);
if (in_inode)
value_len = 0;
if (free < EXT4_XATTR_LEN(name_len) + value_len)
return -ENOSPC;
}
if (i->value && s->not_found) {
/* Insert the new name. */
size_t size = EXT4_XATTR_LEN(name_len);
size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
memmove((void *)s->here + size, s->here, rest);
memset(s->here, 0, size);
s->here->e_name_index = i->name_index;
s->here->e_name_len = name_len;
memcpy(s->here->e_name, i->name, name_len);
} else {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!s->here->e_value_inum && s->here->e_value_size &&
s->here->e_value_offs > 0) {
void *first_val = s->base + min_offs;
size_t offs = le16_to_cpu(s->here->e_value_offs);
void *val = s->base + offs;
size_t size = EXT4_XATTR_SIZE(
le32_to_cpu(s->here->e_value_size));
if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
/* The old and the new value have the same
size. Just replace. */
s->here->e_value_size =
cpu_to_le32(i->value_len);
if (i->value == EXT4_ZERO_XATTR_VALUE) {
memset(val, 0, size);
} else {
/* Clear pad bytes first. */
memset(val + size - EXT4_XATTR_PAD, 0,
EXT4_XATTR_PAD);
memcpy(val, i->value, i->value_len);
}
return 0;
}
/* Remove the old value. */
memmove(first_val + size, first_val, val - first_val);
memset(first_val, 0, size);
s->here->e_value_size = 0;
s->here->e_value_offs = 0;
min_offs += size;
/* Adjust all value offsets. */
last = s->first;
while (!IS_LAST_ENTRY(last)) {
size_t o = le16_to_cpu(last->e_value_offs);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!last->e_value_inum &&
last->e_value_size && o < offs)
last->e_value_offs =
cpu_to_le16(o + size);
last = EXT4_XATTR_NEXT(last);
}
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (s->here->e_value_inum) {
ext4_xattr_inode_unlink(inode,
le32_to_cpu(s->here->e_value_inum));
s->here->e_value_inum = 0;
}
if (!i->value) {
/* Remove the old name. */
size_t size = EXT4_XATTR_LEN(name_len);
last = ENTRY((void *)last - size);
memmove(s->here, (void *)s->here + size,
(void *)last - (void *)s->here + sizeof(__u32));
memset(last, 0, size);
}
}
if (i->value) {
/* Insert the new value. */
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (in_inode) {
unsigned long ea_ino =
le32_to_cpu(s->here->e_value_inum);
rc = ext4_xattr_inode_set(handle, inode, &ea_ino,
i->value, i->value_len);
if (rc)
goto out;
s->here->e_value_inum = cpu_to_le32(ea_ino);
s->here->e_value_offs = 0;
} else if (i->value_len) {
size_t size = EXT4_XATTR_SIZE(i->value_len);
void *val = s->base + min_offs - size;
s->here->e_value_offs = cpu_to_le16(min_offs - size);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
s->here->e_value_inum = 0;
if (i->value == EXT4_ZERO_XATTR_VALUE) {
memset(val, 0, size);
} else {
/* Clear the pad bytes first. */
memset(val + size - EXT4_XATTR_PAD, 0,
EXT4_XATTR_PAD);
memcpy(val, i->value, i->value_len);
}
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
s->here->e_value_size = cpu_to_le32(i->value_len);
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
out:
return rc;
}
struct ext4_xattr_block_find {
struct ext4_xattr_search s;
struct buffer_head *bh;
};
static int
ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
struct ext4_xattr_block_find *bs)
{
struct super_block *sb = inode->i_sb;
int error;
ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
i->name_index, i->name, i->value, (long)i->value_len);
if (EXT4_I(inode)->i_file_acl) {
/* The inode already has an extended attribute block. */
bs->bh = sb_bread(sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bs->bh)
goto cleanup;
ea_bdebug(bs->bh, "b_count=%d, refcount=%d",
atomic_read(&(bs->bh->b_count)),
le32_to_cpu(BHDR(bs->bh)->h_refcount));
if (ext4_xattr_check_block(inode, bs->bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
/* Find the named attribute. */
bs->s.base = BHDR(bs->bh);
bs->s.first = BFIRST(bs->bh);
bs->s.end = bs->bh->b_data + bs->bh->b_size;
bs->s.here = bs->s.first;
error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
i->name, 1);
if (error && error != -ENODATA)
goto cleanup;
bs->s.not_found = error;
}
error = 0;
cleanup:
return error;
}
static int
ext4_xattr_block_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_block_find *bs)
{
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
struct ext4_xattr_search s_copy = bs->s;
struct ext4_xattr_search *s = &s_copy;
struct mb_cache_entry *ce = NULL;
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
int error = 0;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
#define header(x) ((struct ext4_xattr_header *)(x))
if (s->base) {
BUFFER_TRACE(bs->bh, "get_write_access");
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
error = ext4_journal_get_write_access(handle, bs->bh);
if (error)
goto cleanup;
lock_buffer(bs->bh);
if (header(s->base)->h_refcount == cpu_to_le32(1)) {
__u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash);
/*
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect modified
* block
*/
mb_cache_entry_delete_block(ext4_mb_cache, hash,
bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_set_entry(i, s, handle, inode);
if (!error) {
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base),
s->here);
ext4_xattr_cache_insert(ext4_mb_cache,
bs->bh);
}
ext4_xattr_block_csum_set(inode, bs->bh);
unlock_buffer(bs->bh);
if (error == -EFSCORRUPTED)
goto bad_block;
if (!error)
error = ext4_handle_dirty_metadata(handle,
inode,
bs->bh);
if (error)
goto cleanup;
goto inserted;
} else {
int offset = (char *)s->here - bs->bh->b_data;
[PATCH] ext[34]: EA block reference count racing fix There are race issues around ext[34] xattr block release code. ext[34]_xattr_release_block() checks the reference count of xattr block (h_refcount) and frees that xattr block if it is the last one reference it. Unlike ext2, the check of this counter is unprotected by any lock. ext[34]_xattr_release_block() will free the mb_cache entry before freeing that xattr block. There is a small window between the check for the re h_refcount ==1 and the call to mb_cache_entry_free(). During this small window another inode might find this xattr block from the mbcache and reuse it, racing a refcount updates. The xattr block will later be freed by the first inode without notice other inode is still use it. Later if that block is reallocated as a datablock for other file, then more serious problem might happen. We need put a lock around places checking the refount as well to avoid racing issue. Another place need this kind of protection is in ext3_xattr_block_set(), where it will modify the xattr block content in- the-fly if the refcount is 1 (means it's the only inode reference it). This will also fix another issue: the xattr block may not get freed at all if no lock is to protect the refcount check at the release time. It is possible that the last two inodes could release the shared xattr block at the same time. But both of them think they are not the last one so only decreased the h_refcount without freeing xattr block at all. We need to call lock_buffer() after ext3_journal_get_write_access() to avoid deadlock (because the later will call lock_buffer()/unlock_buffer () as well). Signed-off-by: Mingming Cao <cmm@us.ibm.com> Cc: Andreas Gruenbacher <agruen@suse.de> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-03-01 12:13:35 +08:00
unlock_buffer(bs->bh);
ea_bdebug(bs->bh, "cloning");
s->base = kmalloc(bs->bh->b_size, GFP_NOFS);
error = -ENOMEM;
if (s->base == NULL)
goto cleanup;
memcpy(s->base, BHDR(bs->bh), bs->bh->b_size);
s->first = ENTRY(header(s->base)+1);
header(s->base)->h_refcount = cpu_to_le32(1);
s->here = ENTRY(s->base + offset);
s->end = s->base + bs->bh->b_size;
}
} else {
/* Allocate a buffer where we construct the new block. */
s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
/* assert(header == s->base) */
error = -ENOMEM;
if (s->base == NULL)
goto cleanup;
header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
header(s->base)->h_blocks = cpu_to_le32(1);
header(s->base)->h_refcount = cpu_to_le32(1);
s->first = ENTRY(header(s->base)+1);
s->here = ENTRY(header(s->base)+1);
s->end = s->base + sb->s_blocksize;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_set_entry(i, s, handle, inode);
if (error == -EFSCORRUPTED)
goto bad_block;
if (error)
goto cleanup;
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base), s->here);
inserted:
if (!IS_LAST_ENTRY(s->first)) {
new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
if (new_bh) {
/* We found an identical block in the cache. */
if (new_bh == bs->bh)
ea_bdebug(new_bh, "keeping");
else {
u32 ref;
WARN_ON_ONCE(dquot_initialize_needed(inode));
/* The old block is released after updating
the inode. */
error = dquot_alloc_block(inode,
EXT4_C2B(EXT4_SB(sb), 1));
if (error)
goto cleanup;
BUFFER_TRACE(new_bh, "get_write_access");
error = ext4_journal_get_write_access(handle,
new_bh);
if (error)
goto cleanup_dquot;
lock_buffer(new_bh);
/*
* We have to be careful about races with
* freeing, rehashing or adding references to
* xattr block. Once we hold buffer lock xattr
* block's state is stable so we can check
* whether the block got freed / rehashed or
* not. Since we unhash mbcache entry under
* buffer lock when freeing / rehashing xattr
* block, checking whether entry is still
* hashed is reliable. Same rules hold for
* e_reusable handling.
*/
if (hlist_bl_unhashed(&ce->e_hash_list) ||
!ce->e_reusable) {
/*
* Undo everything and check mbcache
* again.
*/
unlock_buffer(new_bh);
dquot_free_block(inode,
EXT4_C2B(EXT4_SB(sb),
1));
brelse(new_bh);
mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
new_bh = NULL;
goto inserted;
}
ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1;
BHDR(new_bh)->h_refcount = cpu_to_le32(ref);
if (ref >= EXT4_XATTR_REFCOUNT_MAX)
ce->e_reusable = 0;
ea_bdebug(new_bh, "reusing; refcount now=%d",
ref);
ext4_xattr_block_csum_set(inode, new_bh);
unlock_buffer(new_bh);
error = ext4_handle_dirty_metadata(handle,
inode,
new_bh);
if (error)
goto cleanup_dquot;
}
mb_cache_entry_touch(ext4_mb_cache, ce);
mb_cache_entry_put(ext4_mb_cache, ce);
ce = NULL;
} else if (bs->bh && s->base == bs->bh->b_data) {
/* We were modifying this block in-place. */
ea_bdebug(bs->bh, "keeping this block");
new_bh = bs->bh;
get_bh(new_bh);
} else {
/* We need to allocate a new block */
ext4_fsblk_t goal, block;
WARN_ON_ONCE(dquot_initialize_needed(inode));
goal = ext4_group_first_block_no(sb,
EXT4_I(inode)->i_block_group);
/* non-extent files can't have physical blocks past 2^32 */
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
block = ext4_new_meta_blocks(handle, inode, goal, 0,
NULL, &error);
if (error)
goto cleanup;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
BUG_ON(block > EXT4_MAX_BLOCK_FILE_PHYS);
ea_idebug(inode, "creating block %llu",
(unsigned long long)block);
new_bh = sb_getblk(sb, block);
if (unlikely(!new_bh)) {
error = -ENOMEM;
getblk_failed:
ext4_free_blocks(handle, inode, NULL, block, 1,
EXT4_FREE_BLOCKS_METADATA);
goto cleanup;
}
lock_buffer(new_bh);
error = ext4_journal_get_create_access(handle, new_bh);
if (error) {
unlock_buffer(new_bh);
error = -EIO;
goto getblk_failed;
}
memcpy(new_bh->b_data, s->base, new_bh->b_size);
ext4_xattr_block_csum_set(inode, new_bh);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
error = ext4_handle_dirty_metadata(handle, inode,
new_bh);
if (error)
goto cleanup;
}
}
/* Update the inode. */
EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
/* Drop the previous xattr block. */
if (bs->bh && bs->bh != new_bh)
ext4_xattr_release_block(handle, inode, bs->bh);
error = 0;
cleanup:
if (ce)
mb_cache_entry_put(ext4_mb_cache, ce);
brelse(new_bh);
if (!(bs->bh && s->base == bs->bh->b_data))
kfree(s->base);
return error;
cleanup_dquot:
dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1));
goto cleanup;
bad_block:
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
goto cleanup;
#undef header
}
int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
{
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
int error;
if (EXT4_I(inode)->i_extra_isize == 0)
return 0;
raw_inode = ext4_raw_inode(&is->iloc);
header = IHDR(inode, raw_inode);
is->s.base = is->s.first = IFIRST(header);
is->s.here = is->s.first;
is->s.end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
error = xattr_check_inode(inode, header, is->s.end);
if (error)
return error;
/* Find the named attribute. */
error = ext4_xattr_find_entry(&is->s.here, i->name_index,
i->name, 0);
if (error && error != -ENODATA)
return error;
is->s.not_found = error;
}
return 0;
}
int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
{
struct ext4_xattr_ibody_header *header;
struct ext4_xattr_search *s = &is->s;
int error;
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_set_entry(i, s, handle, inode);
if (error) {
if (error == -ENOSPC &&
ext4_has_inline_data(inode)) {
error = ext4_try_to_evict_inline_data(handle, inode,
EXT4_XATTR_LEN(strlen(i->name) +
EXT4_XATTR_SIZE(i->value_len)));
if (error)
return error;
error = ext4_xattr_ibody_find(inode, i, is);
if (error)
return error;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_set_entry(i, s, handle, inode);
}
if (error)
return error;
}
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
} else {
header->h_magic = cpu_to_le32(0);
ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
}
return 0;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_info *i,
struct ext4_xattr_ibody_find *is)
{
struct ext4_xattr_ibody_header *header;
struct ext4_xattr_search *s = &is->s;
int error;
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_set_entry(i, s, handle, inode);
if (error)
return error;
header = IHDR(inode, ext4_raw_inode(&is->iloc));
if (!IS_LAST_ENTRY(s->first)) {
header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
} else {
header->h_magic = cpu_to_le32(0);
ext4_clear_inode_state(inode, EXT4_STATE_XATTR);
}
return 0;
}
static int ext4_xattr_value_same(struct ext4_xattr_search *s,
struct ext4_xattr_info *i)
{
void *value;
/* When e_value_inum is set the value is stored externally. */
if (s->here->e_value_inum)
return 0;
if (le32_to_cpu(s->here->e_value_size) != i->value_len)
return 0;
value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs);
return !memcmp(value, i->value, i->value_len);
}
/*
* ext4_xattr_set_handle()
*
* Create, replace or remove an extended attribute for this inode. Value
* is NULL to remove an existing extended attribute, and non-NULL to
* either replace an existing extended attribute, or create a new extended
* attribute. The flags XATTR_REPLACE and XATTR_CREATE
* specify that an extended attribute must exist and must not exist
* previous to the call, respectively.
*
* Returns 0, or a negative error number on failure.
*/
int
ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
const char *name, const void *value, size_t value_len,
int flags)
{
struct ext4_xattr_info i = {
.name_index = name_index,
.name = name,
.value = value,
.value_len = value_len,
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
.in_inode = 0,
};
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_block_find bs = {
.s = { .not_found = -ENODATA, },
};
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
int no_expand;
int error;
if (!name)
return -EINVAL;
if (strlen(name) > 255)
return -ERANGE;
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
ext4_write_lock_xattr(inode, &no_expand);
error = ext4_reserve_inode_write(handle, inode, &is.iloc);
if (error)
goto cleanup;
if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) {
struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
}
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto cleanup;
if (is.s.not_found)
error = ext4_xattr_block_find(inode, &i, &bs);
if (error)
goto cleanup;
if (is.s.not_found && bs.s.not_found) {
error = -ENODATA;
if (flags & XATTR_REPLACE)
goto cleanup;
error = 0;
if (!value)
goto cleanup;
} else {
error = -EEXIST;
if (flags & XATTR_CREATE)
goto cleanup;
}
if (!value) {
if (!is.s.not_found)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_ibody_set(handle, inode, &i, &is);
else if (!bs.s.not_found)
error = ext4_xattr_block_set(handle, inode, &i, &bs);
} else {
error = 0;
/* Xattr value did not change? Save us some work and bail out */
if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i))
goto cleanup;
if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
goto cleanup;
if (ext4_has_feature_ea_inode(inode->i_sb) &&
(EXT4_XATTR_SIZE(i.value_len) >
EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize)))
i.in_inode = 1;
retry_inode:
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_ibody_set(handle, inode, &i, &is);
if (!error && !bs.s.not_found) {
i.value = NULL;
error = ext4_xattr_block_set(handle, inode, &i, &bs);
} else if (error == -ENOSPC) {
if (EXT4_I(inode)->i_file_acl && !bs.s.base) {
error = ext4_xattr_block_find(inode, &i, &bs);
if (error)
goto cleanup;
}
error = ext4_xattr_block_set(handle, inode, &i, &bs);
if (!error && !is.s.not_found) {
i.value = NULL;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_ibody_set(handle, inode, &i,
&is);
} else if (error == -ENOSPC) {
/*
* Xattr does not fit in the block, store at
* external inode if possible.
*/
if (ext4_has_feature_ea_inode(inode->i_sb) &&
!i.in_inode) {
i.in_inode = 1;
goto retry_inode;
}
}
}
}
if (!error) {
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = current_time(inode);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
if (!value)
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
no_expand = 0;
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
* error != 0.
*/
is.iloc.bh = NULL;
if (IS_SYNC(inode))
ext4_handle_sync(handle);
}
cleanup:
brelse(is.iloc.bh);
brelse(bs.bh);
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
ext4_write_unlock_xattr(inode, &no_expand);
return error;
}
/*
* ext4_xattr_set()
*
* Like ext4_xattr_set_handle, but start from an inode. This extended
* attribute modification is a filesystem transaction by itself.
*
* Returns 0, or a negative error number on failure.
*/
int
ext4_xattr_set(struct inode *inode, int name_index, const char *name,
const void *value, size_t value_len, int flags)
{
handle_t *handle;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
struct super_block *sb = inode->i_sb;
int error, retries = 0;
int credits = ext4_jbd2_credits_xattr(inode);
error = dquot_initialize(inode);
if (error)
return error;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (ext4_has_feature_ea_inode(sb)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int nrblocks = (value_len + sb->s_blocksize - 1) >>
sb->s_blocksize_bits;
/* For new inode */
credits += EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + 3;
/* For data blocks of EA inode */
credits += ext4_meta_trans_blocks(inode, nrblocks, 0);
}
retry:
handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
} else {
int error2;
error = ext4_xattr_set_handle(handle, inode, name_index, name,
value, value_len, flags);
error2 = ext4_journal_stop(handle);
if (error == -ENOSPC &&
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_should_retry_alloc(sb, &retries))
goto retry;
if (error == 0)
error = error2;
}
return error;
}
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/*
* Shift the EA entries in the inode to create space for the increased
* i_extra_isize.
*/
static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
int value_offs_shift, void *to,
void *from, size_t n)
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
{
struct ext4_xattr_entry *last = entry;
int new_offs;
/* We always shift xattr headers further thus offsets get lower */
BUG_ON(value_offs_shift > 0);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/* Adjust the value offsets of the entries */
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!last->e_value_inum && last->e_value_size) {
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
new_offs = le16_to_cpu(last->e_value_offs) +
value_offs_shift;
last->e_value_offs = cpu_to_le16(new_offs);
}
}
/* Shift the entries by n bytes */
memmove(to, from, n);
}
/*
* Move xattr pointed to by 'entry' from inode into external xattr block
*/
static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
struct ext4_inode *raw_inode,
struct ext4_xattr_entry *entry)
{
struct ext4_xattr_ibody_find *is = NULL;
struct ext4_xattr_block_find *bs = NULL;
char *buffer = NULL, *b_entry_name = NULL;
size_t value_size = le32_to_cpu(entry->e_value_size);
struct ext4_xattr_info i = {
.value = NULL,
.value_len = 0,
.name_index = entry->e_name_index,
.in_inode = !!entry->e_value_inum,
};
struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
int error;
is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
buffer = kmalloc(value_size, GFP_NOFS);
b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
if (!is || !bs || !buffer || !b_entry_name) {
error = -ENOMEM;
goto out;
}
is->s.not_found = -ENODATA;
bs->s.not_found = -ENODATA;
is->iloc.bh = NULL;
bs->bh = NULL;
/* Save the entry name and the entry value */
if (entry->e_value_inum) {
error = ext4_xattr_inode_get(inode,
le32_to_cpu(entry->e_value_inum),
buffer, value_size);
if (error)
goto out;
} else {
size_t value_offs = le16_to_cpu(entry->e_value_offs);
memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
}
memcpy(b_entry_name, entry->e_name, entry->e_name_len);
b_entry_name[entry->e_name_len] = '\0';
i.name = b_entry_name;
error = ext4_get_inode_loc(inode, &is->iloc);
if (error)
goto out;
error = ext4_xattr_ibody_find(inode, &i, is);
if (error)
goto out;
/* Remove the chosen entry from the inode */
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto out;
i.value = buffer;
i.value_len = value_size;
error = ext4_xattr_block_find(inode, &i, bs);
if (error)
goto out;
/* Add entry which was removed from the inode into the block */
error = ext4_xattr_block_set(handle, inode, &i, bs);
if (error)
goto out;
error = 0;
out:
kfree(b_entry_name);
kfree(buffer);
if (is)
brelse(is->iloc.bh);
kfree(is);
kfree(bs);
return error;
}
static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
struct ext4_inode *raw_inode,
int isize_diff, size_t ifree,
size_t bfree, int *total_ino)
{
struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
struct ext4_xattr_entry *small_entry;
struct ext4_xattr_entry *entry;
struct ext4_xattr_entry *last;
unsigned int entry_size; /* EA entry size */
unsigned int total_size; /* EA entry size + value size */
unsigned int min_total_size;
int error;
while (isize_diff > ifree) {
entry = NULL;
small_entry = NULL;
min_total_size = ~0U;
last = IFIRST(header);
/* Find the entry best suited to be pushed into EA block */
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
total_size = EXT4_XATTR_LEN(last->e_name_len);
if (!last->e_value_inum)
total_size += EXT4_XATTR_SIZE(
le32_to_cpu(last->e_value_size));
if (total_size <= bfree &&
total_size < min_total_size) {
if (total_size + ifree < isize_diff) {
small_entry = last;
} else {
entry = last;
min_total_size = total_size;
}
}
}
if (entry == NULL) {
if (small_entry == NULL)
return -ENOSPC;
entry = small_entry;
}
entry_size = EXT4_XATTR_LEN(entry->e_name_len);
total_size = entry_size;
if (!entry->e_value_inum)
total_size += EXT4_XATTR_SIZE(
le32_to_cpu(entry->e_value_size));
error = ext4_xattr_move_to_block(handle, inode, raw_inode,
entry);
if (error)
return error;
*total_ino -= entry_size;
ifree += total_size;
bfree -= total_size;
}
return 0;
}
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/*
* Expand an inode by new_extra_isize bytes when EAs are present.
* Returns 0 on success or negative error number on failure.
*/
int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
struct ext4_inode *raw_inode, handle_t *handle)
{
struct ext4_xattr_ibody_header *header;
struct buffer_head *bh = NULL;
size_t min_offs;
size_t ifree, bfree;
int total_ino;
void *base, *end;
int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
int isize_diff; /* How much do we need to grow i_extra_isize */
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
int no_expand;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
return 0;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
retry:
isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
goto out;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
header = IHDR(inode, raw_inode);
/*
* Check if enough free space is available in the inode to shift the
* entries ahead by new_extra_isize.
*/
base = IFIRST(header);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
min_offs = end - base;
total_ino = sizeof(struct ext4_xattr_ibody_header);
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino);
if (ifree >= isize_diff)
goto shift;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/*
* Enough free space isn't available in the inode, check if
* EA block can hold new_extra_isize bytes.
*/
if (EXT4_I(inode)->i_file_acl) {
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
error = -EIO;
if (!bh)
goto cleanup;
if (ext4_xattr_check_block(inode, bh)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
goto cleanup;
}
base = BHDR(bh);
end = bh->b_data + bh->b_size;
min_offs = end - base;
bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base,
NULL);
if (bfree + ifree < isize_diff) {
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
brelse(bh);
goto retry;
}
error = -ENOSPC;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
goto cleanup;
}
} else {
bfree = inode->i_sb->s_blocksize;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
}
error = ext4_xattr_make_inode_space(handle, inode, raw_inode,
isize_diff, ifree, bfree,
&total_ino);
if (error) {
if (error == -ENOSPC && !tried_min_extra_isize &&
s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
brelse(bh);
goto retry;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
}
goto cleanup;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
}
shift:
/* Adjust the offsets and shift the remaining entries ahead */
ext4_xattr_shift_entries(IFIRST(header), EXT4_I(inode)->i_extra_isize
- new_extra_isize, (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
(void *)header, total_ino);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
brelse(bh);
out:
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
ext4_write_unlock_xattr(inode, &no_expand);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
return 0;
cleanup:
brelse(bh);
/*
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
* Inode size expansion failed; don't try again
*/
ext4: fix deadlock between inline_data and ext4_expand_extra_isize_ea() The xattr_sem deadlock problems fixed in commit 2e81a4eeedca: "ext4: avoid deadlock when expanding inode size" didn't include the use of xattr_sem in fs/ext4/inline.c. With the addition of project quota which added a new extra inode field, this exposed deadlocks in the inline_data code similar to the ones fixed by 2e81a4eeedca. The deadlock can be reproduced via: dmesg -n 7 mke2fs -t ext4 -O inline_data -Fq -I 256 /dev/vdc 32768 mount -t ext4 -o debug_want_extra_isize=24 /dev/vdc /vdc mkdir /vdc/a umount /vdc mount -t ext4 /dev/vdc /vdc echo foo > /vdc/a/foo and looks like this: [ 11.158815] [ 11.160276] ============================================= [ 11.161960] [ INFO: possible recursive locking detected ] [ 11.161960] 4.10.0-rc3-00015-g011b30a8a3cf #160 Tainted: G W [ 11.161960] --------------------------------------------- [ 11.161960] bash/2519 is trying to acquire lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1225a4b>] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] [ 11.161960] but task is already holding lock: [ 11.161960] (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] other info that might help us debug this: [ 11.161960] Possible unsafe locking scenario: [ 11.161960] [ 11.161960] CPU0 [ 11.161960] ---- [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] lock(&ei->xattr_sem); [ 11.161960] [ 11.161960] *** DEADLOCK *** [ 11.161960] [ 11.161960] May be due to missing lock nesting notation [ 11.161960] [ 11.161960] 4 locks held by bash/2519: [ 11.161960] #0: (sb_writers#3){.+.+.+}, at: [<c11a2414>] mnt_want_write+0x1e/0x3e [ 11.161960] #1: (&type->i_mutex_dir_key){++++++}, at: [<c119508b>] path_openat+0x338/0x67a [ 11.161960] #2: (jbd2_handle){++++..}, at: [<c123314a>] start_this_handle+0x582/0x622 [ 11.161960] #3: (&ei->xattr_sem){++++..}, at: [<c1227941>] ext4_try_add_inline_entry+0x3a/0x152 [ 11.161960] [ 11.161960] stack backtrace: [ 11.161960] CPU: 0 PID: 2519 Comm: bash Tainted: G W 4.10.0-rc3-00015-g011b30a8a3cf #160 [ 11.161960] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.1-1 04/01/2014 [ 11.161960] Call Trace: [ 11.161960] dump_stack+0x72/0xa3 [ 11.161960] __lock_acquire+0xb7c/0xcb9 [ 11.161960] ? kvm_clock_read+0x1f/0x29 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] ? __lock_is_held+0x36/0x66 [ 11.161960] lock_acquire+0x106/0x18a [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] down_write+0x39/0x72 [ 11.161960] ? ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ext4_expand_extra_isize_ea+0x3d/0x4cd [ 11.161960] ? _raw_read_unlock+0x22/0x2c [ 11.161960] ? jbd2_journal_extend+0x1e2/0x262 [ 11.161960] ? __ext4_journal_get_write_access+0x3d/0x60 [ 11.161960] ext4_mark_inode_dirty+0x17d/0x26d [ 11.161960] ? ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_add_dirent_to_inline.isra.12+0xa5/0xb2 [ 11.161960] ext4_try_add_inline_entry+0x69/0x152 [ 11.161960] ext4_add_entry+0xa3/0x848 [ 11.161960] ? __brelse+0x14/0x2f [ 11.161960] ? _raw_spin_unlock_irqrestore+0x44/0x4f [ 11.161960] ext4_add_nondir+0x17/0x5b [ 11.161960] ext4_create+0xcf/0x133 [ 11.161960] ? ext4_mknod+0x12f/0x12f [ 11.161960] lookup_open+0x39e/0x3fb [ 11.161960] ? __wake_up+0x1a/0x40 [ 11.161960] ? lock_acquire+0x11e/0x18a [ 11.161960] path_openat+0x35c/0x67a [ 11.161960] ? sched_clock_cpu+0xd7/0xf2 [ 11.161960] do_filp_open+0x36/0x7c [ 11.161960] ? _raw_spin_unlock+0x22/0x2c [ 11.161960] ? __alloc_fd+0x169/0x173 [ 11.161960] do_sys_open+0x59/0xcc [ 11.161960] SyS_open+0x1d/0x1f [ 11.161960] do_int80_syscall_32+0x4f/0x61 [ 11.161960] entry_INT80_32+0x2f/0x2f [ 11.161960] EIP: 0xb76ad469 [ 11.161960] EFLAGS: 00000286 CPU: 0 [ 11.161960] EAX: ffffffda EBX: 08168ac8 ECX: 00008241 EDX: 000001b6 [ 11.161960] ESI: b75e46bc EDI: b7755000 EBP: bfbdb108 ESP: bfbdafc0 [ 11.161960] DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Cc: stable@vger.kernel.org # 3.10 (requires 2e81a4eeedca as a prereq) Reported-by: George Spelvin <linux@sciencehorizons.net> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2017-01-12 10:50:46 +08:00
no_expand = 1;
ext4_write_unlock_xattr(inode, &no_expand);
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
return error;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
#define EIA_INCR 16 /* must be 2^n */
#define EIA_MASK (EIA_INCR - 1)
/* Add the large xattr @ino into @lea_ino_array for later deletion.
* If @lea_ino_array is new or full it will be grown and the old
* contents copied over.
*/
static int
ext4_expand_ino_array(struct ext4_xattr_ino_array **lea_ino_array, __u32 ino)
{
if (*lea_ino_array == NULL) {
/*
* Start with 15 inodes, so it fits into a power-of-two size.
* If *lea_ino_array is NULL, this is essentially offsetof()
*/
(*lea_ino_array) =
kmalloc(offsetof(struct ext4_xattr_ino_array,
xia_inodes[EIA_MASK]),
GFP_NOFS);
if (*lea_ino_array == NULL)
return -ENOMEM;
(*lea_ino_array)->xia_count = 0;
} else if (((*lea_ino_array)->xia_count & EIA_MASK) == EIA_MASK) {
/* expand the array once all 15 + n * 16 slots are full */
struct ext4_xattr_ino_array *new_array = NULL;
int count = (*lea_ino_array)->xia_count;
/* if new_array is NULL, this is essentially offsetof() */
new_array = kmalloc(
offsetof(struct ext4_xattr_ino_array,
xia_inodes[count + EIA_INCR]),
GFP_NOFS);
if (new_array == NULL)
return -ENOMEM;
memcpy(new_array, *lea_ino_array,
offsetof(struct ext4_xattr_ino_array,
xia_inodes[count]));
kfree(*lea_ino_array);
*lea_ino_array = new_array;
}
(*lea_ino_array)->xia_inodes[(*lea_ino_array)->xia_count++] = ino;
return 0;
}
/**
* Add xattr inode to orphan list
*/
static int
ext4_xattr_inode_orphan_add(handle_t *handle, struct inode *inode,
int credits, struct ext4_xattr_ino_array *lea_ino_array)
{
struct inode *ea_inode;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int idx = 0, error = 0;
if (lea_ino_array == NULL)
return 0;
for (; idx < lea_ino_array->xia_count; ++idx) {
if (!ext4_handle_has_enough_credits(handle, credits)) {
error = ext4_journal_extend(handle, credits);
if (error > 0)
error = ext4_journal_restart(handle, credits);
if (error != 0) {
ext4_warning(inode->i_sb,
"couldn't extend journal "
"(err %d)", error);
return error;
}
}
error = ext4_xattr_inode_iget(inode,
lea_ino_array->xia_inodes[idx], &ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (error)
continue;
inode_lock(ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_orphan_add(handle, ea_inode);
inode_unlock(ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
/* the inode's i_count will be released by caller */
}
return 0;
}
ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields We need to make sure that existing ext3 filesystems can also avail the new fields that have been added to the ext4 inode. We use s_want_extra_isize and s_min_extra_isize to decide by how much we should expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set then we expand the inode by max(s_want_extra_isize, s_min_extra_isize , sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is still an open question about whether users should be able to set s_*_extra_isize smaller than the known fields or not. This patch also adds the functionality to expand inodes to include the newly added fields. We start by trying to expand by s_want_extra_isize bytes and if its fails we try to expand by s_min_extra_isize bytes. This is done by changing the i_extra_isize if enough space is available in the inode and no EAs are present. If EAs are present and there is enough space in the inode then the EAs in the inode are shifted to make space. If enough space is not available in the inode due to the EAs then 1 or more EAs are shifted to the external EA block. In the worst case when even the external EA block does not have enough space we inform the user that some EA would need to be deleted or s_min_extra_isize would have to be reduced. Signed-off-by: Andreas Dilger <adilger@clusterfs.com> Signed-off-by: Kalpak Shah <kalpak@clusterfs.com> Signed-off-by: Mingming Cao <cmm@us.ibm.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2007-07-18 21:19:57 +08:00
/*
* ext4_xattr_delete_inode()
*
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
* Free extended attribute resources associated with this inode. Traverse
* all entries and unlink any xattr inodes associated with this inode. This
* is called immediately before an inode is freed. We have exclusive
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
* access to the inode. If an orphan inode is deleted it will also delete any
* xattr block and all xattr inodes. They are checked by ext4_xattr_inode_iget()
* to ensure they belong to the parent inode and were not deleted already.
*/
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int
ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
struct ext4_xattr_ino_array **lea_ino_array)
{
struct buffer_head *bh = NULL;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
struct ext4_xattr_entry *entry;
unsigned int ea_ino;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int credits = 3, error = 0;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
goto delete_external_ea;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
goto cleanup;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
entry = EXT4_XATTR_NEXT(entry)) {
if (!entry->e_value_inum)
continue;
ea_ino = le32_to_cpu(entry->e_value_inum);
error = ext4_expand_ino_array(lea_ino_array, ea_ino);
if (error) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
brelse(iloc.bh);
goto cleanup;
}
entry->e_value_inum = 0;
}
brelse(iloc.bh);
delete_external_ea:
if (!EXT4_I(inode)->i_file_acl) {
/* add xattr inode to orphan list */
error = ext4_xattr_inode_orphan_add(handle, inode, credits,
*lea_ino_array);
goto cleanup;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
}
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
if (!bh) {
EXT4_ERROR_INODE(inode, "block %llu read error",
EXT4_I(inode)->i_file_acl);
error = -EIO;
goto cleanup;
}
if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
BHDR(bh)->h_blocks != cpu_to_le32(1)) {
EXT4_ERROR_INODE(inode, "bad block %llu",
EXT4_I(inode)->i_file_acl);
error = -EFSCORRUPTED;
goto cleanup;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
entry = EXT4_XATTR_NEXT(entry)) {
if (!entry->e_value_inum)
continue;
ea_ino = le32_to_cpu(entry->e_value_inum);
error = ext4_expand_ino_array(lea_ino_array, ea_ino);
if (error)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
goto cleanup;
entry->e_value_inum = 0;
}
/* add xattr inode to orphan list */
error = ext4_xattr_inode_orphan_add(handle, inode, credits,
*lea_ino_array);
if (error)
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
goto cleanup;
if (!IS_NOQUOTA(inode))
credits += 2 * EXT4_QUOTA_DEL_BLOCKS(inode->i_sb);
if (!ext4_handle_has_enough_credits(handle, credits)) {
error = ext4_journal_extend(handle, credits);
if (error > 0)
error = ext4_journal_restart(handle, credits);
if (error) {
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
ext4_warning(inode->i_sb,
"couldn't extend journal (err %d)", error);
goto cleanup;
}
}
ext4_xattr_release_block(handle, inode, bh);
EXT4_I(inode)->i_file_acl = 0;
cleanup:
brelse(bh);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
return error;
}
void
ext4_xattr_inode_array_free(struct inode *inode,
struct ext4_xattr_ino_array *lea_ino_array)
{
struct inode *ea_inode;
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
int idx = 0;
int err;
if (lea_ino_array == NULL)
return;
for (; idx < lea_ino_array->xia_count; ++idx) {
err = ext4_xattr_inode_iget(inode,
lea_ino_array->xia_inodes[idx], &ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (err)
continue;
/* for inode's i_count get from ext4_xattr_delete_inode */
iput(ea_inode);
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
clear_nlink(ea_inode);
iput(ea_inode);
}
kfree(lea_ino_array);
}
/*
* ext4_xattr_cache_insert()
*
* Create a new entry in the extended attribute cache, and insert
* it unless such an entry is already in the cache.
*
* Returns 0, or a negative error number on failure.
*/
static void
ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
{
struct ext4_xattr_header *header = BHDR(bh);
__u32 hash = le32_to_cpu(header->h_hash);
int reusable = le32_to_cpu(header->h_refcount) <
EXT4_XATTR_REFCOUNT_MAX;
int error;
error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
bh->b_blocknr, reusable);
if (error) {
if (error == -EBUSY)
ea_bdebug(bh, "already in cache");
} else
ea_bdebug(bh, "inserting [%x]", (int)hash);
}
/*
* ext4_xattr_cmp()
*
* Compare two extended attribute blocks for equality.
*
* Returns 0 if the blocks are equal, 1 if they differ, and
* a negative error number on errors.
*/
static int
ext4_xattr_cmp(struct ext4_xattr_header *header1,
struct ext4_xattr_header *header2)
{
struct ext4_xattr_entry *entry1, *entry2;
entry1 = ENTRY(header1+1);
entry2 = ENTRY(header2+1);
while (!IS_LAST_ENTRY(entry1)) {
if (IS_LAST_ENTRY(entry2))
return 1;
if (entry1->e_hash != entry2->e_hash ||
entry1->e_name_index != entry2->e_name_index ||
entry1->e_name_len != entry2->e_name_len ||
entry1->e_value_size != entry2->e_value_size ||
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
entry1->e_value_inum != entry2->e_value_inum ||
memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
return 1;
if (!entry1->e_value_inum &&
memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
(char *)header2 + le16_to_cpu(entry2->e_value_offs),
le32_to_cpu(entry1->e_value_size)))
return 1;
entry1 = EXT4_XATTR_NEXT(entry1);
entry2 = EXT4_XATTR_NEXT(entry2);
}
if (!IS_LAST_ENTRY(entry2))
return 1;
return 0;
}
/*
* ext4_xattr_cache_find()
*
* Find an identical extended attribute block.
*
* Returns a pointer to the block found, or NULL if such a block was
* not found or an error occurred.
*/
static struct buffer_head *
ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
struct mb_cache_entry **pce)
{
__u32 hash = le32_to_cpu(header->h_hash);
struct mb_cache_entry *ce;
struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
while (ce) {
struct buffer_head *bh;
bh = sb_bread(inode->i_sb, ce->e_block);
if (!bh) {
EXT4_ERROR_INODE(inode, "block %lu read error",
(unsigned long) ce->e_block);
} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
*pce = ce;
return bh;
}
brelse(bh);
ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
}
return NULL;
}
#define NAME_HASH_SHIFT 5
#define VALUE_HASH_SHIFT 16
/*
* ext4_xattr_hash_entry()
*
* Compute the hash of an extended attribute.
*/
static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
struct ext4_xattr_entry *entry)
{
__u32 hash = 0;
char *name = entry->e_name;
int n;
for (n = 0; n < entry->e_name_len; n++) {
hash = (hash << NAME_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
*name++;
}
ext4: xattr-in-inode support Large xattr support is implemented for EXT4_FEATURE_INCOMPAT_EA_INODE. If the size of an xattr value is larger than will fit in a single external block, then the xattr value will be saved into the body of an external xattr inode. The also helps support a larger number of xattr, since only the headers will be stored in the in-inode space or the single external block. The inode is referenced from the xattr header via "e_value_inum", which was formerly "e_value_block", but that field was never used. The e_value_size still contains the xattr size so that listing xattrs does not need to look up the inode if the data is not accessed. struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ __le32 e_value_inum; /* inode in which value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ }; The xattr inode is marked with the EXT4_EA_INODE_FL flag and also holds a back-reference to the owning inode in its i_mtime field, allowing the ext4/e2fsck to verify the correct inode is accessed. [ Applied fix by Dan Carpenter to avoid freeing an ERR_PTR. ] Lustre-Jira: https://jira.hpdd.intel.com/browse/LU-80 Lustre-bugzilla: https://bugzilla.lustre.org/show_bug.cgi?id=4424 Signed-off-by: Kalpak Shah <kalpak.shah@sun.com> Signed-off-by: James Simmons <uja.ornl@gmail.com> Signed-off-by: Andreas Dilger <andreas.dilger@intel.com> Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
2017-06-22 09:10:32 +08:00
if (!entry->e_value_inum && entry->e_value_size) {
__le32 *value = (__le32 *)((char *)header +
le16_to_cpu(entry->e_value_offs));
for (n = (le32_to_cpu(entry->e_value_size) +
EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
hash = (hash << VALUE_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
le32_to_cpu(*value++);
}
}
entry->e_hash = cpu_to_le32(hash);
}
#undef NAME_HASH_SHIFT
#undef VALUE_HASH_SHIFT
#define BLOCK_HASH_SHIFT 16
/*
* ext4_xattr_rehash()
*
* Re-compute the extended attribute hash value after an entry has changed.
*/
static void ext4_xattr_rehash(struct ext4_xattr_header *header,
struct ext4_xattr_entry *entry)
{
struct ext4_xattr_entry *here;
__u32 hash = 0;
ext4_xattr_hash_entry(header, entry);
here = ENTRY(header+1);
while (!IS_LAST_ENTRY(here)) {
if (!here->e_hash) {
/* Block is not shared if an entry's hash value == 0 */
hash = 0;
break;
}
hash = (hash << BLOCK_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^
le32_to_cpu(here->e_hash);
here = EXT4_XATTR_NEXT(here);
}
header->h_hash = cpu_to_le32(hash);
}
#undef BLOCK_HASH_SHIFT
#define HASH_BUCKET_BITS 10
struct mb_cache *
ext4_xattr_create_cache(void)
{
return mb_cache_create(HASH_BUCKET_BITS);
}
void ext4_xattr_destroy_cache(struct mb_cache *cache)
{
if (cache)
mb_cache_destroy(cache);
}