summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-10-07 15:15:33 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-07 15:15:33 -0700
commit2eee010d092903ee95716b6c2fbd9d3289839aa4 (patch)
tree77755f1b46dcf2e238b3cbd43f840ec56628e38d /fs/ext4
parent513a4befae06c4469abfb836e8f71977de58c636 (diff)
parent18017479cabaeb5c659d789f04ecf7939f8ee28f (diff)
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "Lots of bug fixes and cleanups" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (40 commits) ext4: remove unused variable ext4: use journal inode to determine journal overhead ext4: create function to read journal inode ext4: unmap metadata when zeroing blocks ext4: remove plugging from ext4_file_write_iter() ext4: allow unlocked direct IO when pages are cached ext4: require encryption feature for EXT4_IOC_SET_ENCRYPTION_POLICY fscrypto: use standard macros to compute length of fname ciphertext ext4: do not unnecessarily null-terminate encrypted symlink data ext4: release bh in make_indexed_dir ext4: Allow parallel DIO reads ext4: allow DAX writeback for hole punch jbd2: fix lockdep annotation in add_transaction_credits() blockgroup_lock.h: simplify definition of NR_BG_LOCKS blockgroup_lock.h: remove debris from bgl_lock_ptr() conversion fscrypto: make filename crypto functions return 0 on success fscrypto: rename completion callbacks to reflect usage fscrypto: remove unnecessary includes fscrypto: improved validation when loading inode encryption metadata ext4: fix memory leak when symlink decryption fails ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/dir.c8
-rw-r--r--fs/ext4/ext4.h35
-rw-r--r--fs/ext4/extents.c27
-rw-r--r--fs/ext4/file.c10
-rw-r--r--fs/ext4/fsync.c9
-rw-r--r--fs/ext4/ialloc.c2
-rw-r--r--fs/ext4/inode.c71
-rw-r--r--fs/ext4/ioctl.c11
-rw-r--r--fs/ext4/move_extent.c7
-rw-r--r--fs/ext4/namei.c22
-rw-r--r--fs/ext4/page-io.c4
-rw-r--r--fs/ext4/super.c126
-rw-r--r--fs/ext4/symlink.c10
-rw-r--r--fs/ext4/xattr.c340
14 files changed, 372 insertions, 310 deletions
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 67415e0e6af0..e8b365000d73 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -260,11 +260,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
/* Directory is encrypted */
err = fscrypt_fname_disk_to_usr(inode,
0, 0, &de_name, &fstr);
+ de_name = fstr;
fstr.len = save_len;
- if (err < 0)
+ if (err)
goto errout;
if (!dir_emit(ctx,
- fstr.name, err,
+ de_name.name, de_name.len,
le32_to_cpu(de->inode),
get_dtype(sb, de->file_type)))
goto done;
@@ -627,7 +628,7 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
int buf_size)
{
struct ext4_dir_entry_2 *de;
- int nlen, rlen;
+ int rlen;
unsigned int offset = 0;
char *top;
@@ -637,7 +638,6 @@ int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf,
if (ext4_check_dir_entry(dir, NULL, de, bh,
buf, buf_size, offset))
return -EFSCORRUPTED;
- nlen = EXT4_DIR_REC_LEN(de->name_len);
rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
offset += rlen;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ea31931386ec..282a51b07c57 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -262,6 +262,9 @@ struct ext4_io_submit {
(s)->s_first_ino)
#endif
#define EXT4_BLOCK_ALIGN(size, blkbits) ALIGN((size), (1 << (blkbits)))
+#define EXT4_MAX_BLOCKS(size, offset, blkbits) \
+ ((EXT4_BLOCK_ALIGN(size + offset, blkbits) >> blkbits) - (offset >> \
+ blkbits))
/* Translate a block number to a cluster number */
#define EXT4_B2C(sbi, blk) ((blk) >> (sbi)->s_cluster_bits)
@@ -1117,9 +1120,15 @@ struct ext4_inode_info {
#define EXT4_MOUNT_POSIX_ACL 0x08000 /* POSIX Access Control Lists */
#define EXT4_MOUNT_NO_AUTO_DA_ALLOC 0x10000 /* No auto delalloc mapping */
#define EXT4_MOUNT_BARRIER 0x20000 /* Use block barriers */
-#define EXT4_MOUNT_QUOTA 0x80000 /* Some quota option set */
-#define EXT4_MOUNT_USRQUOTA 0x100000 /* "old" user quota */
-#define EXT4_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */
+#define EXT4_MOUNT_QUOTA 0x40000 /* Some quota option set */
+#define EXT4_MOUNT_USRQUOTA 0x80000 /* "old" user quota,
+ * enable enforcement for hidden
+ * quota files */
+#define EXT4_MOUNT_GRPQUOTA 0x100000 /* "old" group quota, enable
+ * enforcement for hidden quota
+ * files */
+#define EXT4_MOUNT_PRJQUOTA 0x200000 /* Enable project quota
+ * enforcement */
#define EXT4_MOUNT_DIOREAD_NOLOCK 0x400000 /* Enable support for dio read nolocking */
#define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */
#define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */
@@ -1636,26 +1645,6 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
* Feature set definitions
*/
-/* Use the ext4_{has,set,clear}_feature_* helpers; these will be removed */
-#define EXT4_HAS_COMPAT_FEATURE(sb,mask) \
- ((EXT4_SB(sb)->s_es->s_feature_compat & cpu_to_le32(mask)) != 0)
-#define EXT4_HAS_RO_COMPAT_FEATURE(sb,mask) \
- ((EXT4_SB(sb)->s_es->s_feature_ro_compat & cpu_to_le32(mask)) != 0)
-#define EXT4_HAS_INCOMPAT_FEATURE(sb,mask) \
- ((EXT4_SB(sb)->s_es->s_feature_incompat & cpu_to_le32(mask)) != 0)
-#define EXT4_SET_COMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_compat |= cpu_to_le32(mask)
-#define EXT4_SET_RO_COMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_ro_compat |= cpu_to_le32(mask)
-#define EXT4_SET_INCOMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_incompat |= cpu_to_le32(mask)
-#define EXT4_CLEAR_COMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_compat &= ~cpu_to_le32(mask)
-#define EXT4_CLEAR_RO_COMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_ro_compat &= ~cpu_to_le32(mask)
-#define EXT4_CLEAR_INCOMPAT_FEATURE(sb,mask) \
- EXT4_SB(sb)->s_es->s_feature_incompat &= ~cpu_to_le32(mask)
-
#define EXT4_FEATURE_COMPAT_DIR_PREALLOC 0x0001
#define EXT4_FEATURE_COMPAT_IMAGIC_INODES 0x0002
#define EXT4_FEATURE_COMPAT_HAS_JOURNAL 0x0004
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d7ccb7f51dfc..c930a0110fb4 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4679,6 +4679,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
unsigned int credits;
loff_t epos;
+ BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
map.m_lblk = offset;
map.m_len = len;
/*
@@ -4693,13 +4694,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
* credits to insert 1 extent into extent tree
*/
credits = ext4_chunk_trans_blocks(inode, len);
- /*
- * We can only call ext_depth() on extent based inodes
- */
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- depth = ext_depth(inode);
- else
- depth = -1;
+ depth = ext_depth(inode);
retry:
while (ret >= 0 && len) {
@@ -4966,13 +4961,8 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
trace_ext4_fallocate_enter(inode, offset, len, mode);
lblk = offset >> blkbits;
- /*
- * We can't just convert len to max_blocks because
- * If blocksize = 4096 offset = 3072 and len = 2048
- */
- max_blocks = (EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits)
- - lblk;
+ max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
if (mode & FALLOC_FL_KEEP_SIZE)
flags |= EXT4_GET_BLOCKS_KEEP_SIZE;
@@ -5035,12 +5025,8 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
unsigned int credits, blkbits = inode->i_blkbits;
map.m_lblk = offset >> blkbits;
- /*
- * We can't just convert len to max_blocks because
- * If blocksize = 4096 offset = 3072 and len = 2048
- */
- max_blocks = ((EXT4_BLOCK_ALIGN(len + offset, blkbits) >> blkbits) -
- map.m_lblk);
+ max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
+
/*
* This is somewhat ugly but the idea is clear: When transaction is
* reserved, everything goes into it. Otherwise we rather start several
@@ -5734,6 +5720,9 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
+ } else {
+ ext4_ext_drop_refs(path);
+ kfree(path);
}
ret = ext4_es_remove_extent(inode, offset_lblk,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 261ac3734c58..25f763f2201a 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -91,9 +91,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
- struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(iocb->ki_filp);
- struct blk_plug plug;
int o_direct = iocb->ki_flags & IOCB_DIRECT;
int unaligned_aio = 0;
int overwrite = 0;
@@ -134,18 +132,16 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (o_direct) {
size_t length = iov_iter_count(from);
loff_t pos = iocb->ki_pos;
- blk_start_plug(&plug);
/* check whether we do a DIO overwrite or not */
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
- !file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
+ pos + length <= i_size_read(inode)) {
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
int err, len;
map.m_lblk = pos >> blkbits;
- map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
- - map.m_lblk;
+ map.m_len = EXT4_MAX_BLOCKS(length, pos, blkbits);
len = map.m_len;
err = ext4_map_blocks(NULL, inode, &map, 0);
@@ -171,8 +167,6 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret > 0)
ret = generic_write_sync(iocb, ret);
- if (o_direct)
- blk_finish_plug(&plug);
return ret;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 5c4372512ef7..88effb1053c7 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -61,6 +61,13 @@ static int ext4_sync_parent(struct inode *inode)
break;
iput(inode);
inode = next;
+ /*
+ * The directory inode may have gone through rmdir by now. But
+ * the inode itself and its blocks are still allocated (we hold
+ * a reference to the inode so it didn't go through
+ * ext4_evict_inode()) and so we are safe to flush metadata
+ * blocks and the inode.
+ */
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
break;
@@ -107,7 +114,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (!journal) {
ret = __generic_file_fsync(file, start, end, datasync);
- if (!ret && !hlist_empty(&inode->i_dentry))
+ if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
goto issue_flush;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 9e66cd1d7b78..170421edfdfe 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -802,7 +802,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
} else
inode_init_owner(inode, dir, mode);
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+ if (ext4_has_feature_project(sb) &&
ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT))
ei->i_projid = EXT4_I(dir)->i_projid;
else
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c6ea25a190f8..cd918823b352 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -647,11 +647,19 @@ found:
/*
* We have to zeroout blocks before inserting them into extent
* status tree. Otherwise someone could look them up there and
- * use them before they are really zeroed.
+ * use them before they are really zeroed. We also have to
+ * unmap metadata before zeroing as otherwise writeback can
+ * overwrite zeros with stale data from block device.
*/
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
+ ext4_lblk_t i;
+
+ for (i = 0; i < map->m_len; i++) {
+ unmap_underlying_metadata(inode->i_sb->s_bdev,
+ map->m_pblk + i);
+ }
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
@@ -1649,6 +1657,8 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd,
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
if (invalidate) {
+ if (page_mapped(page))
+ clear_page_dirty_for_io(page);
block_invalidatepage(page, 0, PAGE_SIZE);
ClearPageUptodate(page);
}
@@ -3526,35 +3536,31 @@ out:
static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
{
- int unlocked = 0;
- struct inode *inode = iocb->ki_filp->f_mapping->host;
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ struct inode *inode = mapping->host;
ssize_t ret;
- if (ext4_should_dioread_nolock(inode)) {
- /*
- * Nolock dioread optimization may be dynamically disabled
- * via ext4_inode_block_unlocked_dio(). Check inode's state
- * while holding extra i_dio_count ref.
- */
- inode_dio_begin(inode);
- smp_mb();
- if (unlikely(ext4_test_inode_state(inode,
- EXT4_STATE_DIOREAD_LOCK)))
- inode_dio_end(inode);
- else
- unlocked = 1;
- }
+ /*
+ * Shared inode_lock is enough for us - it protects against concurrent
+ * writes & truncates and since we take care of writing back page cache,
+ * we are protected against page writeback as well.
+ */
+ inode_lock_shared(inode);
if (IS_DAX(inode)) {
- ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
- NULL, unlocked ? 0 : DIO_LOCKING);
+ ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block, NULL, 0);
} else {
+ size_t count = iov_iter_count(iter);
+
+ ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
+ iocb->ki_pos + count);
+ if (ret)
+ goto out_unlock;
ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
iter, ext4_dio_get_block,
- NULL, NULL,
- unlocked ? 0 : DIO_LOCKING);
+ NULL, NULL, 0);
}
- if (unlocked)
- inode_dio_end(inode);
+out_unlock:
+ inode_unlock_shared(inode);
return ret;
}
@@ -3890,7 +3896,7 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
}
/*
- * ext4_punch_hole: punches a hole in a file by releaseing the blocks
+ * ext4_punch_hole: punches a hole in a file by releasing the blocks
* associated with the given offset and length
*
* @inode: File inode
@@ -3919,7 +3925,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
* Write out all dirty pages to avoid race conditions
* Then release them.
*/
- if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
ret = filemap_write_and_wait_range(mapping, offset,
offset + length - 1);
if (ret)
@@ -4414,7 +4420,7 @@ static inline void ext4_iget_extra_inode(struct inode *inode,
int ext4_get_projid(struct inode *inode, kprojid_t *projid)
{
- if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_PROJECT))
+ if (!ext4_has_feature_project(inode->i_sb))
return -EOPNOTSUPP;
*projid = EXT4_I(inode)->i_projid;
return 0;
@@ -4481,7 +4487,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low);
i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low);
- if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+ if (ext4_has_feature_project(sb) &&
EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE &&
EXT4_FITS_IN_INODE(raw_inode, ei, i_projid))
i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid);
@@ -4814,14 +4820,14 @@ static int ext4_do_update_inode(handle_t *handle,
* Fix up interoperability with old kernels. Otherwise, old inodes get
* re-used with the upper 16 bits of the uid/gid intact
*/
- if (!ei->i_dtime) {
+ if (ei->i_dtime && list_empty(&ei->i_orphan)) {
+ raw_inode->i_uid_high = 0;
+ raw_inode->i_gid_high = 0;
+ } else {
raw_inode->i_uid_high =
cpu_to_le16(high_16_bits(i_uid));
raw_inode->i_gid_high =
cpu_to_le16(high_16_bits(i_gid));
- } else {
- raw_inode->i_uid_high = 0;
- raw_inode->i_gid_high = 0;
}
} else {
raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid));
@@ -4885,8 +4891,7 @@ static int ext4_do_update_inode(handle_t *handle,
}
}
- BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_PROJECT) &&
+ BUG_ON(!ext4_has_feature_project(inode->i_sb) &&
i_projid != EXT4_DEF_PROJID);
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE &&
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 1bb7df5e4536..bf5ae8ebbc97 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -19,8 +19,6 @@
#include "ext4_jbd2.h"
#include "ext4.h"
-#define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
-
/**
* Swap memory between @a and @b for @len bytes.
*
@@ -310,8 +308,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
struct ext4_inode *raw_inode;
struct dquot *transfer_to[MAXQUOTAS] = { };
- if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
- EXT4_FEATURE_RO_COMPAT_PROJECT)) {
+ if (!ext4_has_feature_project(sb)) {
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
else
@@ -772,6 +769,9 @@ resizefs_out:
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct fscrypt_policy policy;
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+
if (copy_from_user(&policy,
(struct fscrypt_policy __user *)arg,
sizeof(policy)))
@@ -842,8 +842,7 @@ resizefs_out:
ext4_get_inode_flags(ei);
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
- if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_RO_COMPAT_PROJECT)) {
+ if (ext4_has_feature_project(inode->i_sb)) {
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
EXT4_I(inode)->i_projid);
}
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index a920c5d29fac..6fc14def0c70 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -598,6 +598,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
return -EOPNOTSUPP;
}
+ if (ext4_encrypted_inode(orig_inode) ||
+ ext4_encrypted_inode(donor_inode)) {
+ ext4_msg(orig_inode->i_sb, KERN_ERR,
+ "Online defrag not supported for encrypted files");
+ return -EOPNOTSUPP;
+ }
+
/* Protect orig and donor inodes against a truncate */
lock_two_nondirectories(orig_inode, donor_inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 34c0142caf6a..c344b819cffa 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -639,7 +639,7 @@ static struct stats dx_show_leaf(struct inode *dir,
res = fscrypt_fname_alloc_buffer(
dir, len,
&fname_crypto_str);
- if (res < 0)
+ if (res)
printk(KERN_WARNING "Error "
"allocating crypto "
"buffer--skipping "
@@ -647,7 +647,7 @@ static struct stats dx_show_leaf(struct inode *dir,
res = fscrypt_fname_disk_to_usr(dir,
0, 0, &de_name,
&fname_crypto_str);
- if (res < 0) {
+ if (res) {
printk(KERN_WARNING "Error "
"converting filename "
"from disk to usr"
@@ -1011,7 +1011,7 @@ static int htree_dirblock_to_tree(struct file *dir_file,
err = fscrypt_fname_disk_to_usr(dir, hinfo->hash,
hinfo->minor_hash, &de_name,
&fname_crypto_str);
- if (err < 0) {
+ if (err) {
count = err;
goto errout;
}
@@ -2044,33 +2044,31 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
frame->entries = entries;
frame->at = entries;
frame->bh = bh;
- bh = bh2;
retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
if (retval)
goto out_frames;
- retval = ext4_handle_dirty_dirent_node(handle, dir, bh);
+ retval = ext4_handle_dirty_dirent_node(handle, dir, bh2);
if (retval)
goto out_frames;
- de = do_split(handle,dir, &bh, frame, &fname->hinfo);
+ de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
if (IS_ERR(de)) {
retval = PTR_ERR(de);
goto out_frames;
}
- dx_release(frames);
- retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
- brelse(bh);
- return retval;
+ retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2);
out_frames:
/*
* Even if the block split failed, we have to properly write
* out all the changes we did so far. Otherwise we can end up
* with corrupted filesystem.
*/
- ext4_mark_inode_dirty(handle, dir);
+ if (retval)
+ ext4_mark_inode_dirty(handle, dir);
dx_release(frames);
+ brelse(bh2);
return retval;
}
@@ -3144,7 +3142,7 @@ static int ext4_symlink(struct inode *dir,
istr.name = (const unsigned char *) symname;
istr.len = len;
err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
- if (err < 0)
+ if (err)
goto err_drop_inode;
sd->len = cpu_to_le16(ostr.len);
disk_link.name = (char *) sd;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index a6132a730967..b4cbee936cf8 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -405,14 +405,12 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
{
struct page *data_page = NULL;
struct inode *inode = page->mapping->host;
- unsigned block_start, blocksize;
+ unsigned block_start;
struct buffer_head *bh, *head;
int ret = 0;
int nr_submitted = 0;
int nr_to_submit = 0;
- blocksize = 1 << inode->i_blkbits;
-
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3ec8708989ca..6db81fbcbaa6 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -78,6 +78,8 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
+static struct inode *ext4_get_journal_inode(struct super_block *sb,
+ unsigned int journal_inum);
/*
* Lock ordering
@@ -1267,7 +1269,7 @@ enum {
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
- Opt_usrquota, Opt_grpquota, Opt_i_version, Opt_dax,
+ Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
@@ -1327,6 +1329,7 @@ static const match_table_t tokens = {
{Opt_noquota, "noquota"},
{Opt_quota, "quota"},
{Opt_usrquota, "usrquota"},
+ {Opt_prjquota, "prjquota"},
{Opt_barrier, "barrier=%u"},
{Opt_barrier, "barrier"},
{Opt_nobarrier, "nobarrier"},
@@ -1546,8 +1549,11 @@ static const struct mount_opts {
MOPT_SET | MOPT_Q},
{Opt_grpquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_GRPQUOTA,
MOPT_SET | MOPT_Q},
+ {Opt_prjquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_PRJQUOTA,
+ MOPT_SET | MOPT_Q},
{Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA |
- EXT4_MOUNT_GRPQUOTA), MOPT_CLEAR | MOPT_Q},
+ EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA),
+ MOPT_CLEAR | MOPT_Q},
{Opt_usrjquota, 0, MOPT_Q},
{Opt_grpjquota, 0, MOPT_Q},
{Opt_offusrjquota, 0, MOPT_Q},
@@ -1836,13 +1842,17 @@ static int parse_options(char *options, struct super_block *sb,
return 0;
}
#ifdef CONFIG_QUOTA
- if (ext4_has_feature_quota(sb) &&
- (test_opt(sb, USRQUOTA) || test_opt(sb, GRPQUOTA))) {
- ext4_msg(sb, KERN_INFO, "Quota feature enabled, usrquota and grpquota "
- "mount options ignored.");
- clear_opt(sb, USRQUOTA);
- clear_opt(sb, GRPQUOTA);
- } else if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+ /*
+ * We do the test below only for project quotas. 'usrquota' and
+ * 'grpquota' mount options are allowed even without quota feature
+ * to support legacy quotas in quota files.
+ */
+ if (test_opt(sb, PRJQUOTA) && !ext4_has_feature_project(sb)) {
+ ext4_msg(sb, KERN_ERR, "Project quota feature not enabled. "
+ "Cannot enable project quota enforcement.");
+ return 0;
+ }
+ if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
if (test_opt(sb, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
clear_opt(sb, USRQUOTA);
@@ -2741,7 +2751,6 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
sb = elr->lr_super;
ngroups = EXT4_SB(sb)->s_groups_count;
- sb_start_write(sb);
for (group = elr->lr_next_group; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp) {
@@ -2768,8 +2777,6 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
- sb_end_write(sb);
-
return ret;
}
@@ -2834,19 +2841,43 @@ cont_thread:
mutex_unlock(&eli->li_list_mtx);
goto exit_thread;
}
-
list_for_each_safe(pos, n, &eli->li_request_list) {
+ int err = 0;
+ int progress = 0;
elr = list_entry(pos, struct ext4_li_request,
lr_request);
- if (time_after_eq(jiffies, elr->lr_next_sched)) {
- if (ext4_run_li_request(elr) != 0) {
- /* error, remove the lazy_init job */
- ext4_remove_li_request(elr);
- continue;
+ if (time_before(jiffies, elr->lr_next_sched)) {
+ if (time_before(elr->lr_next_sched, next_wakeup))
+ next_wakeup = elr->lr_next_sched;
+ continue;
+ }
+ if (down_read_trylock(&elr->lr_super->s_umount)) {
+ if (sb_start_write_trylock(elr->lr_super)) {
+ progress = 1;
+ /*
+ * We hold sb->s_umount, sb can not
+ * be removed from the list, it is
+ * now safe to drop li_list_mtx
+ */
+ mutex_unlock(&eli->li_list_mtx);
+ err = ext4_run_li_request(elr);
+ sb_end_write(elr->lr_super);
+ mutex_lock(&eli->li_list_mtx);
+ n = pos->next;
}
+ up_read((&elr->lr_super->s_umount));
+ }
+ /* error, remove the lazy_init job */
+ if (err) {
+ ext4_remove_li_request(elr);
+ continue;
+ }
+ if (!progress) {
+ elr->lr_next_sched = jiffies +
+ (prandom_u32()
+ % (EXT4_DEF_LI_MAX_START_DELAY * HZ));
}
-
if (time_before(elr->lr_next_sched, next_wakeup))
next_wakeup = elr->lr_next_sched;
}
@@ -3179,6 +3210,8 @@ int ext4_calculate_overhead(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ struct inode *j_inode;
+ unsigned int j_blocks, j_inum = le32_to_cpu(es->s_journal_inum);
ext4_group_t i, ngroups = ext4_get_groups_count(sb);
ext4_fsblk_t overhead = 0;
char *buf = (char *) get_zeroed_page(GFP_NOFS);
@@ -3209,10 +3242,23 @@ int ext4_calculate_overhead(struct super_block *sb)
memset(buf, 0, PAGE_SIZE);
cond_resched();
}
- /* Add the internal journal blocks as well */
+
+ /*
+ * Add the internal journal blocks whether the journal has been
+ * loaded or not
+ */
if (sbi->s_journal && !sbi->journal_bdev)
overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
-
+ else if (ext4_has_feature_journal(sb) && !sbi->s_journal) {
+ j_inode = ext4_get_journal_inode(sb, j_inum);
+ if (j_inode) {
+ j_blocks = j_inode->i_size >> sb->s_blocksize_bits;
+ overhead += EXT4_NUM_B2C(sbi, j_blocks);
+ iput(j_inode);
+ } else {
+ ext4_msg(sb, KERN_ERR, "can't get journal size");
+ }
+ }
sbi->s_overhead = overhead;
smp_wmb();
free_page((unsigned long) buf);
@@ -4208,18 +4254,16 @@ static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
write_unlock(&journal->j_state_lock);
}
-static journal_t *ext4_get_journal(struct super_block *sb,
- unsigned int journal_inum)
+static struct inode *ext4_get_journal_inode(struct super_block *sb,
+ unsigned int journal_inum)
{
struct inode *journal_inode;
- journal_t *journal;
-
- BUG_ON(!ext4_has_feature_journal(sb));
-
- /* First, test for the existence of a valid inode on disk. Bad
- * things happen if we iget() an unused inode, as the subsequent
- * iput() will try to delete it. */
+ /*
+ * Test for the existence of a valid inode on disk. Bad things
+ * happen if we iget() an unused inode, as the subsequent iput()
+ * will try to delete it.
+ */
journal_inode = ext4_iget(sb, journal_inum);
if (IS_ERR(journal_inode)) {
ext4_msg(sb, KERN_ERR, "no journal found");
@@ -4239,6 +4283,20 @@ static journal_t *ext4_get_journal(struct super_block *sb,
iput(journal_inode);
return NULL;
}
+ return journal_inode;
+}
+
+static journal_t *ext4_get_journal(struct super_block *sb,
+ unsigned int journal_inum)
+{
+ struct inode *journal_inode;
+ journal_t *journal;
+
+ BUG_ON(!ext4_has_feature_journal(sb));
+
+ journal_inode = ext4_get_journal_inode(sb, journal_inum);
+ if (!journal_inode)
+ return NULL;
journal = jbd2_journal_init_inode(journal_inode);
if (!journal) {
@@ -5250,12 +5308,18 @@ static int ext4_enable_quotas(struct super_block *sb)
le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum),
le32_to_cpu(EXT4_SB(sb)->s_es->s_prj_quota_inum)
};
+ bool quota_mopt[EXT4_MAXQUOTAS] = {
+ test_opt(sb, USRQUOTA),
+ test_opt(sb, GRPQUOTA),
+ test_opt(sb, PRJQUOTA),
+ };
sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
for (type = 0; type < EXT4_MAXQUOTAS; type++) {
if (qf_inums[type]) {
err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
- DQUOT_USAGE_ENABLED);
+ DQUOT_USAGE_ENABLED |
+ (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
if (err) {
ext4_warning(sb,
"Failed to enable quota tracking "
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 4d83d9e05f2e..fdf1c6154745 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -30,7 +30,6 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
char *caddr, *paddr = NULL;
struct fscrypt_str cstr, pstr;
struct fscrypt_symlink_data *sd;
- loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
int res;
u32 max_size = inode->i_sb->s_blocksize;
@@ -49,7 +48,6 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
if (IS_ERR(cpage))
return ERR_CAST(cpage);
caddr = page_address(cpage);
- caddr[size] = 0;
}
/* Symlink is encrypted */
@@ -65,16 +63,14 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry,
res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
if (res)
goto errout;
+ paddr = pstr.name;
res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
- if (res < 0)
+ if (res)
goto errout;
- paddr = pstr.name;
-
/* Null-terminate the name */
- if (res <= pstr.len)
- paddr[res] = '\0';
+ paddr[pstr.len] = '\0';
if (cpage)
put_page(cpage);
set_delayed_call(done, kfree_link, paddr);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 2eb935ca5d9e..c15d63389957 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -199,6 +199,8 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
}
while (!IS_LAST_ENTRY(entry)) {
+ if (entry->e_value_block != 0)
+ return -EFSCORRUPTED;
if (entry->e_value_size != 0 &&
(value_start + le16_to_cpu(entry->e_value_offs) <
(void *)e + sizeof(__u32) ||
@@ -641,7 +643,7 @@ 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)) {
- if (!last->e_value_block && last->e_value_size) {
+ if (last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < *min_offs)
*min_offs = offs;
@@ -661,7 +663,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
/* Compute min_offs and last. */
last = s->first;
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
- if (!last->e_value_block && last->e_value_size) {
+ if (last->e_value_size) {
size_t offs = le16_to_cpu(last->e_value_offs);
if (offs < min_offs)
min_offs = offs;
@@ -669,7 +671,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
}
free = min_offs - ((void *)last - s->base) - sizeof(__u32);
if (!s->not_found) {
- if (!s->here->e_value_block && s->here->e_value_size) {
+ if (s->here->e_value_size) {
size_t size = le32_to_cpu(s->here->e_value_size);
free += EXT4_XATTR_SIZE(size);
}
@@ -691,7 +693,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
s->here->e_name_len = name_len;
memcpy(s->here->e_name, i->name, name_len);
} else {
- if (!s->here->e_value_block && s->here->e_value_size) {
+ if (s->here->e_value_size) {
void *first_val = s->base + min_offs;
size_t offs = le16_to_cpu(s->here->e_value_offs);
void *val = s->base + offs;
@@ -725,8 +727,7 @@ ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
last = s->first;
while (!IS_LAST_ENTRY(last)) {
size_t o = le16_to_cpu(last->e_value_offs);
- if (!last->e_value_block &&
- last->e_value_size && o < offs)
+ if (last->e_value_size && o < offs)
last->e_value_offs =
cpu_to_le16(o + size);
last = EXT4_XATTR_NEXT(last);
@@ -1318,18 +1319,19 @@ retry:
*/
static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
int value_offs_shift, void *to,
- void *from, size_t n, int blocksize)
+ void *from, size_t n)
{
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);
+
/* Adjust the value offsets of the entries */
for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
- if (!last->e_value_block && last->e_value_size) {
+ if (last->e_value_size) {
new_offs = le16_to_cpu(last->e_value_offs) +
value_offs_shift;
- BUG_ON(new_offs + le32_to_cpu(last->e_value_size)
- > blocksize);
last->e_value_offs = cpu_to_le16(new_offs);
}
}
@@ -1338,6 +1340,141 @@ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
}
/*
+ * 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_offs, value_size;
+ struct ext4_xattr_info i = {
+ .value = NULL,
+ .value_len = 0,
+ .name_index = entry->e_name_index,
+ };
+ struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
+ int error;
+
+ value_offs = le16_to_cpu(entry->e_value_offs);
+ value_size = le32_to_cpu(entry->e_value_size);
+
+ 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 */
+ 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 */
+ error = ext4_xattr_ibody_set(handle, inode, &i, is);
+ if (error)
+ goto out;
+
+ i.name = b_entry_name;
+ 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_SIZE(le32_to_cpu(last->e_value_size)) +
+ EXT4_XATTR_LEN(last->e_name_len);
+ 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 +
+ 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;
+}
+
+/*
* Expand an inode by new_extra_isize bytes when EAs are present.
* Returns 0 on success or negative error number on failure.
*/
@@ -1345,14 +1482,11 @@ 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 ext4_xattr_entry *entry, *last, *first;
struct buffer_head *bh = NULL;
- struct ext4_xattr_ibody_find *is = NULL;
- struct ext4_xattr_block_find *bs = NULL;
- char *buffer = NULL, *b_entry_name = NULL;
- size_t min_offs, free;
+ size_t min_offs;
+ size_t ifree, bfree;
int total_ino;
- void *base, *start, *end;
+ 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 */
@@ -1368,34 +1502,24 @@ retry:
goto out;
header = IHDR(inode, raw_inode);
- entry = IFIRST(header);
/*
* Check if enough free space is available in the inode to shift the
* entries ahead by new_extra_isize.
*/
- base = start = entry;
+ base = IFIRST(header);
end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
min_offs = end - base;
- last = entry;
total_ino = sizeof(struct ext4_xattr_ibody_header);
error = xattr_check_inode(inode, header, end);
if (error)
goto cleanup;
- free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
- if (free >= isize_diff) {
- entry = IFIRST(header);
- ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
- - new_extra_isize, (void *)raw_inode +
- EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
- (void *)header, total_ino,
- inode->i_sb->s_blocksize);
- EXT4_I(inode)->i_extra_isize = new_extra_isize;
- goto out;
- }
+ ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino);
+ if (ifree >= isize_diff)
+ goto shift;
/*
* Enough free space isn't available in the inode, check if
@@ -1413,146 +1537,44 @@ retry:
goto cleanup;
}
base = BHDR(bh);
- first = BFIRST(bh);
end = bh->b_data + bh->b_size;
min_offs = end - base;
- free = ext4_xattr_free_space(first, &min_offs, base, NULL);
- if (free < isize_diff) {
+ bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base,
+ NULL);
+ if (bfree + ifree < isize_diff) {
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 = -1;
+ error = -ENOSPC;
goto cleanup;
}
} else {
- free = inode->i_sb->s_blocksize;
+ bfree = inode->i_sb->s_blocksize;
}
- while (isize_diff > 0) {
- size_t offs, size, entry_size;
- struct ext4_xattr_entry *small_entry = NULL;
- struct ext4_xattr_info i = {
- .value = NULL,
- .value_len = 0,
- };
- unsigned int total_size; /* EA entry size + value size */
- unsigned int shift_bytes; /* No. of bytes to shift EAs by? */
- unsigned int min_total_size = ~0U;
-
- is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
- bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
- if (!is || !bs) {
- error = -ENOMEM;
- goto cleanup;
- }
-
- is->s.not_found = -ENODATA;
- bs->s.not_found = -ENODATA;
- is->iloc.bh = NULL;
- bs->bh = NULL;
-
- last = IFIRST(header);
- /* Find the entry best suited to be pushed into EA block */
- entry = NULL;
- for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
- total_size =
- EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
- EXT4_XATTR_LEN(last->e_name_len);
- if (total_size <= free && total_size < min_total_size) {
- if (total_size < isize_diff) {
- small_entry = last;
- } else {
- entry = last;
- min_total_size = total_size;
- }
- }
- }
-
- if (entry == NULL) {
- if (small_entry) {
- entry = small_entry;
- } else {
- if (!tried_min_extra_isize &&
- s_min_extra_isize) {
- tried_min_extra_isize++;
- new_extra_isize = s_min_extra_isize;
- kfree(is); is = NULL;
- kfree(bs); bs = NULL;
- brelse(bh);
- goto retry;
- }
- error = -1;
- goto cleanup;
- }
- }
- offs = le16_to_cpu(entry->e_value_offs);
- size = le32_to_cpu(entry->e_value_size);
- entry_size = EXT4_XATTR_LEN(entry->e_name_len);
- i.name_index = entry->e_name_index,
- buffer = kmalloc(EXT4_XATTR_SIZE(size), GFP_NOFS);
- b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
- if (!buffer || !b_entry_name) {
- error = -ENOMEM;
- goto cleanup;
+ 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;
}
- /* Save the entry name and the entry value */
- memcpy(buffer, (void *)IFIRST(header) + offs,
- EXT4_XATTR_SIZE(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 cleanup;
-
- error = ext4_xattr_ibody_find(inode, &i, is);
- if (error)
- goto cleanup;
-
- /* Remove the chosen entry from the inode */
- error = ext4_xattr_ibody_set(handle, inode, &i, is);
- if (error)
- goto cleanup;
- total_ino -= entry_size;
-
- entry = IFIRST(header);
- if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
- shift_bytes = isize_diff;
- else
- shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
- /* Adjust the offsets and shift the remaining entries ahead */
- ext4_xattr_shift_entries(entry, -shift_bytes,
- (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
- EXT4_I(inode)->i_extra_isize + shift_bytes,
- (void *)header, total_ino, inode->i_sb->s_blocksize);
-
- isize_diff -= shift_bytes;
- EXT4_I(inode)->i_extra_isize += shift_bytes;
- header = IHDR(inode, raw_inode);
-
- i.name = b_entry_name;
- i.value = buffer;
- i.value_len = size;
- error = ext4_xattr_block_find(inode, &i, bs);
- if (error)
- goto cleanup;
-
- /* Add entry which was removed from the inode into the block */
- error = ext4_xattr_block_set(handle, inode, &i, bs);
- if (error)
- goto cleanup;
- kfree(b_entry_name);
- kfree(buffer);
- b_entry_name = NULL;
- buffer = NULL;
- brelse(is->iloc.bh);
- kfree(is);
- kfree(bs);
+ goto cleanup;
}
+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;
brelse(bh);
out:
ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
@@ -1560,12 +1582,6 @@ out:
return 0;
cleanup:
- kfree(b_entry_name);
- kfree(buffer);
- if (is)
- brelse(is->iloc.bh);
- kfree(is);
- kfree(bs);
brelse(bh);
/*
* We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
@@ -1734,7 +1750,7 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
*name++;
}
- if (entry->e_value_block == 0 && entry->e_value_size != 0) {
+ if (entry->e_value_size != 0) {
__le32 *value = (__le32 *)((char *)header +
le16_to_cpu(entry->e_value_offs));
for (n = (le32_to_cpu(entry->e_value_size) +