aboutsummaryrefslogtreecommitdiff
path: root/fs/ext3
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext3')
-rw-r--r--fs/ext3/acl.c251
-rw-r--r--fs/ext3/acl.h9
-rw-r--r--fs/ext3/balloc.c14
-rw-r--r--fs/ext3/bitmap.c12
-rw-r--r--fs/ext3/dir.c212
-rw-r--r--fs/ext3/file.c11
-rw-r--r--fs/ext3/fsync.c17
-rw-r--r--fs/ext3/ialloc.c2
-rw-r--r--fs/ext3/inode.c198
-rw-r--r--fs/ext3/ioctl.c2
-rw-r--r--fs/ext3/namei.c104
-rw-r--r--fs/ext3/namei.h19
-rw-r--r--fs/ext3/resize.c12
-rw-r--r--fs/ext3/super.c178
-rw-r--r--fs/ext3/xattr.c12
-rw-r--r--fs/ext3/xattr.h2
-rw-r--r--fs/ext3/xattr_security.c5
17 files changed, 470 insertions, 590 deletions
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index c76832c8d19..8bbaf5bcf98 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -48,16 +48,23 @@ ext3_acl_from_disk(const void *value, size_t size)
case ACL_OTHER:
value = (char *)value +
sizeof(ext3_acl_entry_short);
- acl->a_entries[n].e_id = ACL_UNDEFINED_ID;
break;
case ACL_USER:
+ value = (char *)value + sizeof(ext3_acl_entry);
+ if ((char *)value > end)
+ goto fail;
+ acl->a_entries[n].e_uid =
+ make_kuid(&init_user_ns,
+ le32_to_cpu(entry->e_id));
+ break;
case ACL_GROUP:
value = (char *)value + sizeof(ext3_acl_entry);
if ((char *)value > end)
goto fail;
- acl->a_entries[n].e_id =
- le32_to_cpu(entry->e_id);
+ acl->a_entries[n].e_gid =
+ make_kgid(&init_user_ns,
+ le32_to_cpu(entry->e_id));
break;
default:
@@ -91,14 +98,19 @@ ext3_acl_to_disk(const struct posix_acl *acl, size_t *size)
ext_acl->a_version = cpu_to_le32(EXT3_ACL_VERSION);
e = (char *)ext_acl + sizeof(ext3_acl_header);
for (n=0; n < acl->a_count; n++) {
+ const struct posix_acl_entry *acl_e = &acl->a_entries[n];
ext3_acl_entry *entry = (ext3_acl_entry *)e;
- entry->e_tag = cpu_to_le16(acl->a_entries[n].e_tag);
- entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
- switch(acl->a_entries[n].e_tag) {
+ entry->e_tag = cpu_to_le16(acl_e->e_tag);
+ entry->e_perm = cpu_to_le16(acl_e->e_perm);
+ switch(acl_e->e_tag) {
case ACL_USER:
+ entry->e_id = cpu_to_le32(
+ from_kuid(&init_user_ns, acl_e->e_uid));
+ e += sizeof(ext3_acl_entry);
+ break;
case ACL_GROUP:
- entry->e_id =
- cpu_to_le32(acl->a_entries[n].e_id);
+ entry->e_id = cpu_to_le32(
+ from_kgid(&init_user_ns, acl_e->e_gid));
e += sizeof(ext3_acl_entry);
break;
@@ -133,13 +145,6 @@ ext3_get_acl(struct inode *inode, int type)
struct posix_acl *acl;
int retval;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return NULL;
-
- acl = get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
-
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
@@ -178,7 +183,7 @@ ext3_get_acl(struct inode *inode, int type)
* inode->i_mutex: down unless called from ext3_new_inode
*/
static int
-ext3_set_acl(handle_t *handle, struct inode *inode, int type,
+__ext3_set_acl(handle_t *handle, struct inode *inode, int type,
struct posix_acl *acl)
{
int name_index;
@@ -186,9 +191,6 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type,
size_t size = 0;
int error;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
-
switch(type) {
case ACL_TYPE_ACCESS:
name_index = EXT3_XATTR_INDEX_POSIX_ACL_ACCESS;
@@ -231,204 +233,49 @@ ext3_set_acl(handle_t *handle, struct inode *inode, int type,
return error;
}
-/*
- * Initialize the ACLs of a new inode. Called from ext3_new_inode.
- *
- * dir->i_mutex: down
- * inode->i_mutex: up (access to inode is still exclusive)
- */
-int
-ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
-{
- struct posix_acl *acl = NULL;
- int error = 0;
-
- if (!S_ISLNK(inode->i_mode)) {
- if (test_opt(dir->i_sb, POSIX_ACL)) {
- acl = ext3_get_acl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- }
- if (!acl)
- inode->i_mode &= ~current_umask();
- }
- if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
- if (S_ISDIR(inode->i_mode)) {
- error = ext3_set_acl(handle, inode,
- ACL_TYPE_DEFAULT, acl);
- if (error)
- goto cleanup;
- }
- error = posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
- if (error < 0)
- return error;
-
- if (error > 0) {
- /* This is an extended ACL */
- error = ext3_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
- }
- }
-cleanup:
- posix_acl_release(acl);
- return error;
-}
-
-/*
- * Does chmod for an inode that may have an Access Control List. The
- * inode->i_mode field must be updated to the desired value by the caller
- * before calling this function.
- * Returns 0 on success, or a negative error number.
- *
- * We change the ACL rather than storing some ACL entries in the file
- * mode permission bits (which would be more efficient), because that
- * would break once additional permissions (like ACL_APPEND, ACL_DELETE
- * for directories) are added. There are no more bits available in the
- * file mode.
- *
- * inode->i_mutex: down
- */
int
-ext3_acl_chmod(struct inode *inode)
+ext3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
- struct posix_acl *acl;
handle_t *handle;
- int retries = 0;
- int error;
+ int error, retries = 0;
- if (S_ISLNK(inode->i_mode))
- return -EOPNOTSUPP;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return 0;
- acl = ext3_get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
- error = posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
- if (error)
- return error;
retry:
- handle = ext3_journal_start(inode,
- EXT3_DATA_TRANS_BLOCKS(inode->i_sb));
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- ext3_std_error(inode->i_sb, error);
- goto out;
- }
- error = ext3_set_acl(handle, inode, ACL_TYPE_ACCESS, acl);
+ handle = ext3_journal_start(inode, EXT3_DATA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+ error = __ext3_set_acl(handle, inode, type, acl);
ext3_journal_stop(handle);
- if (error == -ENOSPC &&
- ext3_should_retry_alloc(inode->i_sb, &retries))
+ if (error == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
-out:
- posix_acl_release(acl);
return error;
}
/*
- * Extended attribute handlers
+ * Initialize the ACLs of a new inode. Called from ext3_new_inode.
+ *
+ * dir->i_mutex: down
+ * inode->i_mutex: up (access to inode is still exclusive)
*/
-static size_t
-ext3_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_len)
- memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
- return size;
-}
-
-static size_t
-ext3_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
- const char *name, size_t name_len, int type)
-{
- const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
-
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return 0;
- if (list && size <= list_len)
- memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
- return size;
-}
-
-static int
-ext3_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
- size_t size, int type)
+int
+ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
{
- struct posix_acl *acl;
+ struct posix_acl *default_acl, *acl;
int error;
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(dentry->d_sb, POSIX_ACL))
- return -EOPNOTSUPP;
-
- acl = ext3_get_acl(dentry->d_inode, type);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- if (acl == NULL)
- return -ENODATA;
- error = posix_acl_to_xattr(acl, buffer, size);
- posix_acl_release(acl);
-
- return error;
-}
-
-static int
-ext3_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags, int type)
-{
- struct inode *inode = dentry->d_inode;
- handle_t *handle;
- struct posix_acl *acl;
- int error, retries = 0;
-
- if (strcmp(name, "") != 0)
- return -EINVAL;
- if (!test_opt(inode->i_sb, POSIX_ACL))
- return -EOPNOTSUPP;
- if (!inode_owner_or_capable(inode))
- return -EPERM;
-
- if (value) {
- acl = posix_acl_from_xattr(value, size);
- if (IS_ERR(acl))
- return PTR_ERR(acl);
- else if (acl) {
- error = posix_acl_valid(acl);
- if (error)
- goto release_and_out;
- }
- } else
- acl = NULL;
-
-retry:
- handle = ext3_journal_start(inode, EXT3_DATA_TRANS_BLOCKS(inode->i_sb));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
- error = ext3_set_acl(handle, inode, type, acl);
- ext3_journal_stop(handle);
- if (error == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
+ error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+ if (error)
+ return error;
-release_and_out:
- posix_acl_release(acl);
+ if (default_acl) {
+ error = __ext3_set_acl(handle, inode, ACL_TYPE_DEFAULT,
+ default_acl);
+ posix_acl_release(default_acl);
+ }
+ if (acl) {
+ if (!error)
+ error = __ext3_set_acl(handle, inode, ACL_TYPE_ACCESS,
+ acl);
+ posix_acl_release(acl);
+ }
return error;
}
-
-const struct xattr_handler ext3_xattr_acl_access_handler = {
- .prefix = POSIX_ACL_XATTR_ACCESS,
- .flags = ACL_TYPE_ACCESS,
- .list = ext3_xattr_list_acl_access,
- .get = ext3_xattr_get_acl,
- .set = ext3_xattr_set_acl,
-};
-
-const struct xattr_handler ext3_xattr_acl_default_handler = {
- .prefix = POSIX_ACL_XATTR_DEFAULT,
- .flags = ACL_TYPE_DEFAULT,
- .list = ext3_xattr_list_acl_default,
- .get = ext3_xattr_get_acl,
- .set = ext3_xattr_set_acl,
-};
diff --git a/fs/ext3/acl.h b/fs/ext3/acl.h
index dbc921e458c..ea1c69edab9 100644
--- a/fs/ext3/acl.h
+++ b/fs/ext3/acl.h
@@ -55,18 +55,13 @@ static inline int ext3_acl_count(size_t size)
/* acl.c */
extern struct posix_acl *ext3_get_acl(struct inode *inode, int type);
-extern int ext3_acl_chmod (struct inode *);
+extern int ext3_set_acl(struct inode *inode, struct posix_acl *acl, int type);
extern int ext3_init_acl (handle_t *, struct inode *, struct inode *);
#else /* CONFIG_EXT3_FS_POSIX_ACL */
#include <linux/sched.h>
#define ext3_get_acl NULL
-
-static inline int
-ext3_acl_chmod(struct inode *inode)
-{
- return 0;
-}
+#define ext3_set_acl NULL
static inline int
ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 25cd6089211..158b5d4ce06 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -483,7 +483,7 @@ void ext3_discard_reservation(struct inode *inode)
* ext3_free_blocks_sb() -- Free given blocks and update quota
* @handle: handle to this transaction
* @sb: super block
- * @block: start physcial block to free
+ * @block: start physical block to free
* @count: number of blocks to free
* @pdquot_freed_blocks: pointer to quota
*/
@@ -1727,10 +1727,7 @@ allocated:
percpu_counter_sub(&sbi->s_freeblocks_counter, num);
BUFFER_TRACE(gdp_bh, "journal_dirty_metadata for group descriptor");
- err = ext3_journal_dirty_metadata(handle, gdp_bh);
- if (!fatal)
- fatal = err;
-
+ fatal = ext3_journal_dirty_metadata(handle, gdp_bh);
if (fatal)
goto out;
@@ -1813,7 +1810,7 @@ ext3_fsblk_t ext3_count_free_blocks(struct super_block *sb)
brelse(bitmap_bh);
printk("ext3_count_free_blocks: stored = "E3FSBLK
", computed = "E3FSBLK", "E3FSBLK"\n",
- le32_to_cpu(es->s_free_blocks_count),
+ (ext3_fsblk_t)le32_to_cpu(es->s_free_blocks_count),
desc_count, bitmap_count);
return bitmap_count;
#else
@@ -2101,8 +2098,9 @@ int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range)
end = start + (range->len >> sb->s_blocksize_bits) - 1;
minlen = range->minlen >> sb->s_blocksize_bits;
- if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) ||
- unlikely(start >= max_blks))
+ if (minlen > EXT3_BLOCKS_PER_GROUP(sb) ||
+ start >= max_blks ||
+ range->len < sb->s_blocksize)
return -EINVAL;
if (end >= max_blks)
end = max_blks - 1;
diff --git a/fs/ext3/bitmap.c b/fs/ext3/bitmap.c
index 909d13e2656..ef9c643e8e9 100644
--- a/fs/ext3/bitmap.c
+++ b/fs/ext3/bitmap.c
@@ -11,19 +11,9 @@
#ifdef EXT3FS_DEBUG
-static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
-
unsigned long ext3_count_free (struct buffer_head * map, unsigned int numchars)
{
- unsigned int i;
- unsigned long sum = 0;
-
- if (!map)
- return (0);
- for (i = 0; i < numchars; i++)
- sum += nibblemap[map->b_data[i] & 0xf] +
- nibblemap[(map->b_data[i] >> 4) & 0xf];
- return (sum);
+ return numchars * BITS_PER_BYTE - memweight(map->b_data, numchars);
}
#endif /* EXT3FS_DEBUG */
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 92490e9f85c..17742eed2c1 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -28,8 +28,7 @@ static unsigned char ext3_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
-static int ext3_dx_readdir(struct file * filp,
- void * dirent, filldir_t filldir);
+static int ext3_dx_readdir(struct file *, struct dir_context *);
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
@@ -42,7 +41,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
/**
* Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
* indexing).
*
* Return 1 if it is a dx dir, 0 if not
@@ -91,36 +90,30 @@ int ext3_check_dir_entry (const char * function, struct inode * dir,
return error_msg == NULL ? 1 : 0;
}
-static int ext3_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int ext3_readdir(struct file *file, struct dir_context *ctx)
{
- int error = 0;
unsigned long offset;
- int i, stored;
+ int i;
struct ext3_dir_entry_2 *de;
int err;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
- int ret = 0;
int dir_has_error = 0;
if (is_dx_dir(inode)) {
- err = ext3_dx_readdir(filp, dirent, filldir);
- if (err != ERR_BAD_DX_DIR) {
- ret = err;
- goto out;
- }
+ err = ext3_dx_readdir(file, ctx);
+ if (err != ERR_BAD_DX_DIR)
+ return err;
/*
* We don't set the inode dirty flag since it's not
* critical that it get flushed back to the disk.
*/
- EXT3_I(filp->f_path.dentry->d_inode)->i_flags &= ~EXT3_INDEX_FL;
+ EXT3_I(inode)->i_flags &= ~EXT3_INDEX_FL;
}
- stored = 0;
- offset = filp->f_pos & (sb->s_blocksize - 1);
+ offset = ctx->pos & (sb->s_blocksize - 1);
- while (!error && !stored && filp->f_pos < inode->i_size) {
- unsigned long blk = filp->f_pos >> EXT3_BLOCK_SIZE_BITS(sb);
+ while (ctx->pos < inode->i_size) {
+ unsigned long blk = ctx->pos >> EXT3_BLOCK_SIZE_BITS(sb);
struct buffer_head map_bh;
struct buffer_head *bh = NULL;
@@ -129,12 +122,12 @@ static int ext3_readdir(struct file * filp,
if (err > 0) {
pgoff_t index = map_bh.b_blocknr >>
(PAGE_CACHE_SHIFT - inode->i_blkbits);
- if (!ra_has_index(&filp->f_ra, index))
+ if (!ra_has_index(&file->f_ra, index))
page_cache_sync_readahead(
sb->s_bdev->bd_inode->i_mapping,
- &filp->f_ra, filp,
+ &file->f_ra, file,
index, 1);
- filp->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
+ file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT;
bh = ext3_bread(NULL, inode, blk, 0, &err);
}
@@ -146,22 +139,21 @@ static int ext3_readdir(struct file * filp,
if (!dir_has_error) {
ext3_error(sb, __func__, "directory #%lu "
"contains a hole at offset %lld",
- inode->i_ino, filp->f_pos);
+ inode->i_ino, ctx->pos);
dir_has_error = 1;
}
/* corrupt size? Maybe no more blocks to read */
- if (filp->f_pos > inode->i_blocks << 9)
+ if (ctx->pos > inode->i_blocks << 9)
break;
- filp->f_pos += sb->s_blocksize - offset;
+ ctx->pos += sb->s_blocksize - offset;
continue;
}
-revalidate:
/* If the dir block has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the block
* to make sure. */
- if (filp->f_version != inode->i_version) {
+ if (offset && file->f_version != inode->i_version) {
for (i = 0; i < sb->s_blocksize && i < offset; ) {
de = (struct ext3_dir_entry_2 *)
(bh->b_data + i);
@@ -177,53 +169,40 @@ revalidate:
i += ext3_rec_len_from_disk(de->rec_len);
}
offset = i;
- filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
+ ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1))
| offset;
- filp->f_version = inode->i_version;
+ file->f_version = inode->i_version;
}
- while (!error && filp->f_pos < inode->i_size
+ while (ctx->pos < inode->i_size
&& offset < sb->s_blocksize) {
de = (struct ext3_dir_entry_2 *) (bh->b_data + offset);
if (!ext3_check_dir_entry ("ext3_readdir", inode, de,
bh, offset)) {
- /* On error, skip the f_pos to the
+ /* On error, skip the to the
next block. */
- filp->f_pos = (filp->f_pos |
+ ctx->pos = (ctx->pos |
(sb->s_blocksize - 1)) + 1;
- brelse (bh);
- ret = stored;
- goto out;
+ break;
}
offset += ext3_rec_len_from_disk(de->rec_len);
if (le32_to_cpu(de->inode)) {
- /* We might block in the next section
- * if the data destination is
- * currently swapped out. So, use a
- * version stamp to detect whether or
- * not the directory has been modified
- * during the copy operation.
- */
- u64 version = filp->f_version;
-
- error = filldir(dirent, de->name,
- de->name_len,
- filp->f_pos,
- le32_to_cpu(de->inode),
- get_dtype(sb, de->file_type));
- if (error)
- break;
- if (version != filp->f_version)
- goto revalidate;
- stored ++;
+ if (!dir_emit(ctx, de->name, de->name_len,
+ le32_to_cpu(de->inode),
+ get_dtype(sb, de->file_type))) {
+ brelse(bh);
+ return 0;
+ }
}
- filp->f_pos += ext3_rec_len_from_disk(de->rec_len);
+ ctx->pos += ext3_rec_len_from_disk(de->rec_len);
}
offset = 0;
brelse (bh);
+ if (ctx->pos < inode->i_size)
+ if (!dir_relax(inode))
+ return 0;
}
-out:
- return ret;
+ return 0;
}
static inline int is_32bit_api(void)
@@ -296,16 +275,17 @@ static inline loff_t ext3_get_htree_eof(struct file *filp)
* NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX)
* will be invalid once the directory was converted into a dx directory
*/
-loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin)
+static loff_t ext3_dir_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
int dx_dir = is_dx_dir(inode);
+ loff_t htree_max = ext3_get_htree_eof(file);
if (likely(dx_dir))
- return generic_file_llseek_size(file, offset, origin,
- ext3_get_htree_eof(file));
+ return generic_file_llseek_size(file, offset, whence,
+ htree_max, htree_max);
else
- return generic_file_llseek(file, offset, origin);
+ return generic_file_llseek(file, offset, whence);
}
/*
@@ -329,43 +309,17 @@ struct fname {
*/
static void free_rb_tree_fname(struct rb_root *root)
{
- struct rb_node *n = root->rb_node;
- struct rb_node *parent;
- struct fname *fname;
-
- while (n) {
- /* Do the node's children first */
- if (n->rb_left) {
- n = n->rb_left;
- continue;
- }
- if (n->rb_right) {
- n = n->rb_right;
- continue;
- }
- /*
- * The node has no children; free it, and then zero
- * out parent's link to it. Finally go to the
- * beginning of the loop and try to free the parent
- * node.
- */
- parent = rb_parent(n);
- fname = rb_entry(n, struct fname, rb_hash);
- while (fname) {
- struct fname * old = fname;
+ struct fname *fname, *next;
+
+ rbtree_postorder_for_each_entry_safe(fname, next, root, rb_hash)
+ do {
+ struct fname *old = fname;
fname = fname->next;
- kfree (old);
- }
- if (!parent)
- *root = RB_ROOT;
- else if (parent->rb_left == n)
- parent->rb_left = NULL;
- else if (parent->rb_right == n)
- parent->rb_right = NULL;
- n = parent;
- }
-}
+ kfree(old);
+ } while (fname);
+ *root = RB_ROOT;
+}
static struct dir_private_info *ext3_htree_create_dir_info(struct file *filp,
loff_t pos)
@@ -451,62 +405,54 @@ int ext3_htree_store_dirent(struct file *dir_file, __u32 hash,
* for all entres on the fname linked list. (Normally there is only
* one entry on the linked list, unless there are 62 bit hash collisions.)
*/
-static int call_filldir(struct file * filp, void * dirent,
- filldir_t filldir, struct fname *fname)
+static bool call_filldir(struct file *file, struct dir_context *ctx,
+ struct fname *fname)
{
- struct dir_private_info *info = filp->private_data;
- loff_t curr_pos;
- struct inode *inode = filp->f_path.dentry->d_inode;
- struct super_block * sb;
- int error;
-
- sb = inode->i_sb;
+ struct dir_private_info *info = file->private_data;
+ struct inode *inode = file_inode(file);
+ struct super_block *sb = inode->i_sb;
if (!fname) {
printk("call_filldir: called with null fname?!?\n");
- return 0;
+ return true;
}
- curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
+ ctx->pos = hash2pos(file, fname->hash, fname->minor_hash);
while (fname) {
- error = filldir(dirent, fname->name,
- fname->name_len, curr_pos,
+ if (!dir_emit(ctx, fname->name, fname->name_len,
fname->inode,
- get_dtype(sb, fname->file_type));
- if (error) {
- filp->f_pos = curr_pos;
+ get_dtype(sb, fname->file_type))) {
info->extra_fname = fname;
- return error;
+ return false;
}
fname = fname->next;
}
- return 0;
+ return true;
}
-static int ext3_dx_readdir(struct file * filp,
- void * dirent, filldir_t filldir)
+static int ext3_dx_readdir(struct file *file, struct dir_context *ctx)
{
- struct dir_private_info *info = filp->private_data;
- struct inode *inode = filp->f_path.dentry->d_inode;
+ struct dir_private_info *info = file->private_data;
+ struct inode *inode = file_inode(file);
struct fname *fname;
int ret;
if (!info) {
- info = ext3_htree_create_dir_info(filp, filp->f_pos);
+ info = ext3_htree_create_dir_info(file, ctx->pos);
if (!info)
return -ENOMEM;
- filp->private_data = info;
+ file->private_data = info;
}
- if (filp->f_pos == ext3_get_htree_eof(filp))
+ if (ctx->pos == ext3_get_htree_eof(file))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
- if (info->last_pos != filp->f_pos) {
+ if (info->last_pos != ctx->pos) {
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp, filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
+ info->curr_hash = pos2maj_hash(file, ctx->pos);
+ info->curr_minor_hash = pos2min_hash(file, ctx->pos);
}
/*
@@ -514,7 +460,7 @@ static int ext3_dx_readdir(struct file * filp,
* chain, return them first.
*/
if (info->extra_fname) {
- if (call_filldir(filp, dirent, filldir, info->extra_fname))
+ if (!call_filldir(file, ctx, info->extra_fname))
goto finished;
info->extra_fname = NULL;
goto next_node;
@@ -528,17 +474,17 @@ static int ext3_dx_readdir(struct file * filp,
* cached entries.
*/
if ((!info->curr_node) ||
- (filp->f_version != inode->i_version)) {
+ (file->f_version != inode->i_version)) {
info->curr_node = NULL;
free_rb_tree_fname(&info->root);
- filp->f_version = inode->i_version;
- ret = ext3_htree_fill_tree(filp, info->curr_hash,
+ file->f_version = inode->i_version;
+ ret = ext3_htree_fill_tree(file, info->curr_hash,
info->curr_minor_hash,
&info->next_hash);
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = ext3_get_htree_eof(filp);
+ ctx->pos = ext3_get_htree_eof(file);
break;
}
info->curr_node = rb_first(&info->root);
@@ -547,7 +493,7 @@ static int ext3_dx_readdir(struct file * filp,
fname = rb_entry(info->curr_node, struct fname, rb_hash);
info->curr_hash = fname->hash;
info->curr_minor_hash = fname->minor_hash;
- if (call_filldir(filp, dirent, filldir, fname))
+ if (!call_filldir(file, ctx, fname))
break;
next_node:
info->curr_node = rb_next(info->curr_node);
@@ -558,7 +504,7 @@ static int ext3_dx_readdir(struct file * filp,
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = ext3_get_htree_eof(filp);
+ ctx->pos = ext3_get_htree_eof(file);
break;
}
info->curr_hash = info->next_hash;
@@ -566,7 +512,7 @@ static int ext3_dx_readdir(struct file * filp,
}
}
finished:
- info->last_pos = filp->f_pos;
+ info->last_pos = ctx->pos;
return 0;
}
@@ -581,7 +527,7 @@ static int ext3_release_dir (struct inode * inode, struct file * filp)
const struct file_operations ext3_dir_operations = {
.llseek = ext3_dir_llseek,
.read = generic_read_dir,
- .readdir = ext3_readdir,
+ .iterate = ext3_readdir,
.unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 25cb413277e..a062fa1e1b1 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -50,10 +50,10 @@ static int ext3_release_file (struct inode * inode, struct file * filp)
const struct file_operations ext3_file_operations = {
.llseek = generic_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.unlocked_ioctl = ext3_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext3_compat_ioctl,
@@ -63,7 +63,7 @@ const struct file_operations ext3_file_operations = {
.release = ext3_release_file,
.fsync = ext3_sync_file,
.splice_read = generic_file_splice_read,
- .splice_write = generic_file_splice_write,
+ .splice_write = iter_file_splice_write,
};
const struct inode_operations ext3_file_inode_operations = {
@@ -75,6 +75,7 @@ const struct inode_operations ext3_file_inode_operations = {
.removexattr = generic_removexattr,
#endif
.get_acl = ext3_get_acl,
+ .set_acl = ext3_set_acl,
.fiemap = ext3_fiemap,
};
diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c
index d4dff278cbd..1cb9c7e10c6 100644
--- a/fs/ext3/fsync.c
+++ b/fs/ext3/fsync.c
@@ -48,9 +48,13 @@ int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
trace_ext3_sync_file_enter(file, datasync);
- if (inode->i_sb->s_flags & MS_RDONLY)
+ if (inode->i_sb->s_flags & MS_RDONLY) {
+ /* Make sure that we read updated state */
+ smp_rmb();
+ if (EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS)
+ return -EROFS;
return 0;
-
+ }
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (ret)
goto out;
@@ -92,8 +96,13 @@ int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* disk caches manually so that data really is on persistent
* storage
*/
- if (needs_barrier)
- blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ if (needs_barrier) {
+ int err;
+
+ err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ if (!ret)
+ ret = err;
+ }
out:
trace_ext3_sync_file_exit(inode, ret);
return ret;
diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c
index 082afd78b10..a1b810230cc 100644
--- a/fs/ext3/ialloc.c
+++ b/fs/ext3/ialloc.c
@@ -215,7 +215,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent)
int best_ndir = inodes_per_group;
int best_group = -1;
- get_random_bytes(&group, sizeof(group));
+ group = prandom_u32();
parent_group = (unsigned)group % ngroups;
for (i = 0; i < ngroups; i++) {
group = (parent_group + i) % ngroups;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 9a4a5c48b1c..2c6ccc49ba2 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,6 +27,7 @@
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/namei.h>
+#include <linux/aio.h>
#include "ext3.h"
#include "xattr.h"
#include "acl.h"
@@ -218,7 +219,8 @@ void ext3_evict_inode (struct inode *inode)
*/
if (inode->i_nlink && ext3_should_journal_data(inode) &&
EXT3_SB(inode->i_sb)->s_journal &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+ inode->i_ino != EXT3_JOURNAL_INO) {
tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
@@ -226,7 +228,7 @@ void ext3_evict_inode (struct inode *inode)
log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
ext3_discard_reservation(inode);
rsv = ei->i_block_alloc_info;
@@ -676,6 +678,10 @@ static int ext3_alloc_branch(handle_t *handle, struct inode *inode,
* parent to disk.
*/
bh = sb_getblk(inode->i_sb, new_blocks[n-1]);
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
+ goto failed;
+ }
branch[n].bh = bh;
lock_buffer(bh);
BUFFER_TRACE(bh, "call get_create_access");
@@ -717,7 +723,7 @@ failed:
BUFFER_TRACE(branch[i].bh, "call journal_forget");
ext3_journal_forget(handle, branch[i].bh);
}
- for (i = 0; i <indirect_blks; i++)
+ for (i = 0; i < indirect_blks; i++)
ext3_free_blocks(handle, inode, new_blocks[i], 1);
ext3_free_blocks(handle, inode, new_blocks[i], num);
@@ -1071,16 +1077,15 @@ struct buffer_head *ext3_getblk(handle_t *handle, struct inode *inode,
* mapped. 0 in case of a HOLE.
*/
if (err > 0) {
- if (err > 1)
- WARN_ON(1);
+ WARN_ON(err > 1);
err = 0;
}
*errp = err;
if (!err && buffer_mapped(&dummy)) {
struct buffer_head *bh;
bh = sb_getblk(inode->i_sb, dummy.b_blocknr);
- if (!bh) {
- *errp = -EIO;
+ if (unlikely(!bh)) {
+ *errp = -ENOMEM;
goto err;
}
if (buffer_new(&dummy)) {
@@ -1554,56 +1559,17 @@ static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
}
/*
- * Note that we always start a transaction even if we're not journalling
- * data. This is to preserve ordering: any hole instantiation within
- * __block_write_full_page -> ext3_get_block() should be journalled
- * along with the data so we don't crash and then get metadata which
+ * Note that whenever we need to map blocks we start a transaction even if
+ * we're not journalling data. This is to preserve ordering: any hole
+ * instantiation within __block_write_full_page -> ext3_get_block() should be
+ * journalled along with the data so we don't crash and then get metadata which
* refers to old data.
*
* In all journalling modes block_write_full_page() will start the I/O.
*
- * Problem:
- *
- * ext3_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
- * ext3_writepage()
- *
- * Similar for:
- *
- * ext3_file_write() -> generic_file_write() -> __alloc_pages() -> ...
- *
- * Same applies to ext3_get_block(). We will deadlock on various things like
- * lock_journal and i_truncate_mutex.
- *
- * Setting PF_MEMALLOC here doesn't work - too many internal memory
- * allocations fail.
- *
- * 16May01: If we're reentered then journal_current_handle() will be
- * non-zero. We simply *return*.
- *
- * 1 July 2001: @@@ FIXME:
- * In journalled data mode, a data buffer may be metadata against the
- * current transaction. But the same file is part of a shared mapping
- * and someone does a writepage() on it.
- *
- * We will move the buffer onto the async_data list, but *after* it has
- * been dirtied. So there's a small window where we have dirty data on
- * BJ_Metadata.
- *
- * Note that this only applies to the last partial page in the file. The
- * bit which block_write_full_page() uses prepare/commit for. (That's
- * broken code anyway: it's wrong for msync()).
- *
- * It's a rare case: affects the final partial page, for journalled data
- * where the file is subject to bith write() and writepage() in the same
- * transction. To fix it we'll need a custom block_write_full_page().
- * We'll probably need that anyway for journalling writepage() output.
- *
* We don't honour synchronous mounts for writepage(). That would be
* disastrous. Any write() or metadata operation will sync the fs for
* us.
- *
- * AKPM2: if all the page's buffers are mapped to disk and !data=journal,
- * we don't need to open a transaction here.
*/
static int ext3_ordered_writepage(struct page *page,
struct writeback_control *wbc)
@@ -1668,12 +1634,9 @@ static int ext3_ordered_writepage(struct page *page,
* block_write_full_page() succeeded. Otherwise they are unmapped,
* and generally junk.
*/
- if (ret == 0) {
- err = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
+ if (ret == 0)
+ ret = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
NULL, journal_dirty_data_fn);
- if (!ret)
- ret = err;
- }
walk_page_buffers(handle, page_bufs, 0,
PAGE_CACHE_SIZE, NULL, bput_one);
err = ext3_journal_stop(handle);
@@ -1753,17 +1716,17 @@ static int ext3_journalled_writepage(struct page *page,
WARN_ON_ONCE(IS_RDONLY(inode) &&
!(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ERROR_FS));
- if (ext3_journal_current_handle())
- goto no_write;
-
trace_ext3_journalled_writepage(page);
- handle = ext3_journal_start(inode, ext3_writepage_trans_blocks(inode));
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto no_write;
- }
-
if (!page_has_buffers(page) || PageChecked(page)) {
+ if (ext3_journal_current_handle())
+ goto no_write;
+
+ handle = ext3_journal_start(inode,
+ ext3_writepage_trans_blocks(inode));
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto no_write;
+ }
/*
* It's mmapped pagecache. Add buffers and journal it. There
* doesn't seem much point in redirtying the page here.
@@ -1786,17 +1749,18 @@ static int ext3_journalled_writepage(struct page *page,
atomic_set(&EXT3_I(inode)->i_datasync_tid,
handle->h_transaction->t_tid);
unlock_page(page);
+ err = ext3_journal_stop(handle);
+ if (!ret)
+ ret = err;
} else {
/*
- * It may be a page full of checkpoint-mode buffers. We don't
- * really know unless we go poke around in the buffer_heads.
- * But block_write_full_page will do the right thing.
+ * It is a page full of checkpoint-mode buffers. Go and write
+ * them. They should have been already mapped when they went
+ * to the journal so provide NULL get_block function to catch
+ * errors.
*/
- ret = block_write_full_page(page, ext3_get_block, wbc);
+ ret = block_write_full_page(page, NULL, wbc);
}
- err = ext3_journal_stop(handle);
- if (!ret)
- ret = err;
out:
return ret;
@@ -1820,19 +1784,20 @@ ext3_readpages(struct file *file, struct address_space *mapping,
return mpage_readpages(mapping, pages, nr_pages, ext3_get_block);
}
-static void ext3_invalidatepage(struct page *page, unsigned long offset)
+static void ext3_invalidatepage(struct page *page, unsigned int offset,
+ unsigned int length)
{
journal_t *journal = EXT3_JOURNAL(page->mapping->host);
- trace_ext3_invalidatepage(page, offset);
+ trace_ext3_invalidatepage(page, offset, length);
/*
* If it's a full truncate we just forget about the pending dirtying
*/
- if (offset == 0)
+ if (offset == 0 && length == PAGE_CACHE_SIZE)
ClearPageChecked(page);
- journal_invalidatepage(journal, page, offset);
+ journal_invalidatepage(journal, page, offset, length);
}
static int ext3_releasepage(struct page *page, gfp_t wait)
@@ -1856,8 +1821,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
* VFS code falls back into buffered path in that case so we are safe.
*/
static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
- const struct iovec *iov, loff_t offset,
- unsigned long nr_segs)
+ struct iov_iter *iter, loff_t offset)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
@@ -1865,10 +1829,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
handle_t *handle;
ssize_t ret;
int orphan = 0;
- size_t count = iov_length(iov, nr_segs);
+ size_t count = iov_iter_count(iter);
int retries = 0;
- trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw);
+ trace_ext3_direct_IO_enter(inode, offset, count, rw);
if (rw == WRITE) {
loff_t final_size = offset + count;
@@ -1892,15 +1856,14 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
}
retry:
- ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
- ext3_get_block);
+ ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again.
*/
if (unlikely((rw & WRITE) && ret < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;
if (end > isize)
ext3_truncate_failed_direct_write(inode);
@@ -1919,6 +1882,8 @@ retry:
* and pretend the write failed... */
ext3_truncate_failed_direct_write(inode);
ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext3_orphan_del(NULL, inode);
goto out;
}
if (inode->i_nlink)
@@ -1943,8 +1908,7 @@ retry:
ret = err;
}
out:
- trace_ext3_direct_IO_exit(inode, offset,
- iov_length(iov, nr_segs), rw, ret);
+ trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
return ret;
}
@@ -1979,6 +1943,7 @@ static const struct address_space_operations ext3_ordered_aops = {
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .is_dirty_writeback = buffer_check_dirty_writeback,
.error_remove_page = generic_error_remove_page,
};
@@ -2730,12 +2695,12 @@ static int __ext3_get_inode_loc(struct inode *inode,
return -EIO;
bh = sb_getblk(inode->i_sb, block);
- if (!bh) {
+ if (unlikely(!bh)) {
ext3_error (inode->i_sb, "ext3_get_inode_loc",
"unable to read inode block - "
"inode=%lu, block="E3FSBLK,
inode->i_ino, block);
- return -EIO;
+ return -ENOMEM;
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
@@ -2784,7 +2749,7 @@ static int __ext3_get_inode_loc(struct inode *inode,
bitmap_bh = sb_getblk(inode->i_sb,
le32_to_cpu(desc->bg_inode_bitmap));
- if (!bitmap_bh)
+ if (unlikely(!bitmap_bh))
goto make_io;
/*
@@ -3072,6 +3037,8 @@ static int ext3_do_update_inode(handle_t *handle,
struct ext3_inode_info *ei = EXT3_I(inode);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+ int need_datasync = 0;
+ __le32 disksize;
uid_t i_uid;
gid_t i_gid;
@@ -3113,7 +3080,11 @@ again:
raw_inode->i_gid_high = 0;
}
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
- raw_inode->i_size = cpu_to_le32(ei->i_disksize);
+ disksize = cpu_to_le32(ei->i_disksize);
+ if (disksize != raw_inode->i_size) {
+ need_datasync = 1;
+ raw_inode->i_size = disksize;
+ }
raw_inode->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
raw_inode->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
raw_inode->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
@@ -3129,8 +3100,11 @@ again:
if (!S_ISREG(inode->i_mode)) {
raw_inode->i_dir_acl = cpu_to_le32(ei->i_dir_acl);
} else {
- raw_inode->i_size_high =
- cpu_to_le32(ei->i_disksize >> 32);
+ disksize = cpu_to_le32(ei->i_disksize >> 32);
+ if (disksize != raw_inode->i_size_high) {
+ raw_inode->i_size_high = disksize;
+ need_datasync = 1;
+ }
if (ei->i_disksize > 0x7fffffffULL) {
struct super_block *sb = inode->i_sb;
if (!EXT3_HAS_RO_COMPAT_FEATURE(sb,
@@ -3183,6 +3157,8 @@ again:
ext3_clear_inode_state(inode, EXT3_STATE_NEW);
atomic_set(&ei->i_sync_tid, handle->h_transaction->t_tid);
+ if (need_datasync)
+ atomic_set(&ei->i_datasync_tid, handle->h_transaction->t_tid);
out_brelse:
brelse (bh);
ext3_std_error(inode->i_sb, err);
@@ -3194,21 +3170,20 @@ out_brelse:
*
* We are called from a few places:
*
- * - Within generic_file_write() for O_SYNC files.
+ * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files.
* Here, there will be no transaction running. We wait for any running
- * trasnaction to commit.
+ * transaction to commit.
*
- * - Within sys_sync(), kupdate and such.
- * We wait on commit, if tol to.
+ * - Within flush work (for sys_sync(), kupdate and such).
+ * We wait on commit, if told to.
*
- * - Within prune_icache() (PF_MEMALLOC == true)
- * Here we simply return. We can't afford to block kswapd on the
- * journal commit.
+ * - Within iput_final() -> write_inode_now()
+ * We wait on commit, if told to.
*
* In all cases it is actually safe for us to return without doing anything,
* because the inode has been copied into a raw inode buffer in
- * ext3_mark_inode_dirty(). This is a correctness thing for O_SYNC and for
- * knfsd.
+ * ext3_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL
+ * writeback.
*
* Note that we are absolutely dependent upon all inode dirtiers doing the
* right thing: they *must* call mark_inode_dirty() after dirtying info in
@@ -3220,13 +3195,13 @@ out_brelse:
* stuff();
* inode->i_size = expr;
*
- * is in error because a kswapd-driven write_inode() could occur while
- * `stuff()' is running, and the new i_size will be lost. Plus the inode
- * will no longer be on the superblock's dirty inode list.
+ * is in error because write_inode() could occur while `stuff()' is running,
+ * and the new i_size will be lost. Plus the inode will no longer be on the
+ * superblock's dirty inode list.
*/
int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
{
- if (current->flags & PF_MEMALLOC)
+ if (WARN_ON_ONCE(current->flags & PF_MEMALLOC))
return 0;
if (ext3_journal_current_handle()) {
@@ -3235,7 +3210,12 @@ int ext3_write_inode(struct inode *inode, struct writeback_control *wbc)
return -EIO;
}
- if (wbc->sync_mode != WB_SYNC_ALL)
+ /*
+ * No need to force transaction in WB_SYNC_NONE mode. Also
+ * ext3_sync_fs() will force the commit after everything is
+ * written.
+ */
+ if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
return 0;
return ext3_force_commit(inode->i_sb);
@@ -3347,7 +3327,7 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr)
mark_inode_dirty(inode);
if (ia_valid & ATTR_MODE)
- rc = ext3_acl_chmod(inode);
+ rc = posix_acl_chmod(inode, inode->i_mode);
err_out:
ext3_std_error(inode->i_sb, error);
@@ -3459,14 +3439,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
* inode out, but prune_icache isn't a user-visible syncing function.
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
- *
- * Is this efficient/effective? Well, we're being nice to the system
- * by cleaning up our inodes proactively so they can be reaped
- * without I/O. But we are potentially leaving up to five seconds'
- * worth of inodes floating about which prune_icache wants us to
- * write out. One way to fix that would be to get prune_icache()
- * to do a write_super() to free up some memory. It has the desired
- * effect.
*/
int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode)
{
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 677a5c27dc6..4d96e9a6453 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -14,7 +14,7 @@
long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
struct ext3_inode_info *ei = EXT3_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 85286dbe275..f197736dccf 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -36,7 +36,6 @@
#define NAMEI_RA_CHUNKS 2
#define NAMEI_RA_BLOCKS 4
#define NAMEI_RA_SIZE (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)
-#define NAMEI_RA_INDEX(c,b) (((c) * NAMEI_RA_BLOCKS) + (b))
static struct buffer_head *ext3_append(handle_t *handle,
struct inode *inode,
@@ -46,8 +45,7 @@ static struct buffer_head *ext3_append(handle_t *handle,
*block = inode->i_size >> inode->i_sb->s_blocksize_bits;
- bh = ext3_bread(handle, inode, *block, 1, err);
- if (bh) {
+ if ((bh = ext3_dir_bread(handle, inode, *block, 1, err))) {
inode->i_size += inode->i_sb->s_blocksize;
EXT3_I(inode)->i_disksize = inode->i_size;
*err = ext3_journal_get_write_access(handle, bh);
@@ -339,8 +337,10 @@ dx_probe(struct qstr *entry, struct inode *dir,
u32 hash;
frame->bh = NULL;
- if (!(bh = ext3_bread (NULL,dir, 0, 0, err)))
+ if (!(bh = ext3_dir_bread(NULL, dir, 0, 0, err))) {
+ *err = ERR_BAD_DX_DIR;
goto fail;
+ }
root = (struct dx_root *) bh->b_data;
if (root->info.hash_version != DX_HASH_TEA &&
root->info.hash_version != DX_HASH_HALF_MD4 &&
@@ -436,8 +436,10 @@ dx_probe(struct qstr *entry, struct inode *dir,
frame->entries = entries;
frame->at = at;
if (!indirect--) return frame;
- if (!(bh = ext3_bread (NULL,dir, dx_get_block(at), 0, err)))
+ if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(at), 0, err))) {
+ *err = ERR_BAD_DX_DIR;
goto fail2;
+ }
at = entries = ((struct dx_node *) bh->b_data)->entries;
if (dx_get_limit(entries) != dx_node_limit (dir)) {
ext3_warning(dir->i_sb, __func__,
@@ -535,8 +537,8 @@ static int ext3_htree_next_block(struct inode *dir, __u32 hash,
* block so no check is necessary
*/
while (num_frames--) {
- if (!(bh = ext3_bread(NULL, dir, dx_get_block(p->at),
- 0, &err)))
+ if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(p->at),
+ 0, &err)))
return err; /* Failure */
p++;
brelse (p->bh);
@@ -559,10 +561,11 @@ static int htree_dirblock_to_tree(struct file *dir_file,
{
struct buffer_head *bh;
struct ext3_dir_entry_2 *de, *top;
- int err, count = 0;
+ int err = 0, count = 0;
dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));
- if (!(bh = ext3_bread (NULL, dir, block, 0, &err)))
+
+ if (!(bh = ext3_dir_bread(NULL, dir, block, 0, &err)))
return err;
de = (struct ext3_dir_entry_2 *) bh->b_data;
@@ -573,11 +576,8 @@ static int htree_dirblock_to_tree(struct file *dir_file,
if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
+((char *)de - bh->b_data))) {
- /* On error, skip the f_pos to the next block. */
- dir_file->f_pos = (dir_file->f_pos |
- (dir->i_sb->s_blocksize - 1)) + 1;
- brelse (bh);
- return count;
+ /* silently ignore the rest of the block */
+ break;
}
ext3fs_dirhash(de->name, de->name_len, hinfo);
if ((hinfo->hash < start_hash) ||
@@ -620,7 +620,7 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
start_minor_hash));
- dir = dir_file->f_path.dentry->d_inode;
+ dir = file_inode(dir_file);
if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
if (hinfo.hash_version <= DX_HASH_TEA)
@@ -634,7 +634,7 @@ int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
}
hinfo.hash = start_hash;
hinfo.minor_hash = 0;
- frame = dx_probe(NULL, dir_file->f_path.dentry->d_inode, &hinfo, frames, &err);
+ frame = dx_probe(NULL, file_inode(dir_file), &hinfo, frames, &err);
if (!frame)
return err;
@@ -976,7 +976,7 @@ static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
return NULL;
do {
block = dx_get_block(frame->at);
- if (!(bh = ext3_bread (NULL,dir, block, 0, err)))
+ if (!(bh = ext3_dir_bread (NULL, dir, block, 0, err)))
goto errout;
retval = search_dirblock(bh, dir, entry,
@@ -1458,9 +1458,9 @@ static int ext3_add_entry (handle_t *handle, struct dentry *dentry,
}
blocks = dir->i_size >> sb->s_blocksize_bits;
for (block = 0; block < blocks; block++) {
- bh = ext3_bread(handle, dir, block, 0, &retval);
- if(!bh)
+ if (!(bh = ext3_dir_bread(handle, dir, block, 0, &retval)))
return retval;
+
retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
if (retval != -ENOSPC)
return retval;
@@ -1500,7 +1500,7 @@ static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
entries = frame->entries;
at = frame->at;
- if (!(bh = ext3_bread(handle,dir, dx_get_block(frame->at), 0, &err)))
+ if (!(bh = ext3_dir_bread(handle, dir, dx_get_block(frame->at), 0, &err)))
goto cleanup;
BUFFER_TRACE(bh, "get_write_access");
@@ -1671,8 +1671,8 @@ static int ext3_add_nondir(handle_t *handle,
int err = ext3_add_entry(handle, dentry, inode);
if (!err) {
ext3_mark_inode_dirty(handle, inode);
- d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ d_instantiate(dentry, inode);
return 0;
}
drop_nlink(inode);
@@ -1759,6 +1759,44 @@ retry:
return err;
}
+static int ext3_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ handle_t *handle;
+ struct inode *inode;
+ int err, retries = 0;
+
+ dquot_initialize(dir);
+
+retry:
+ handle = ext3_journal_start(dir, EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ 4 + EXT3_XATTR_TRANS_BLOCKS);
+
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ inode = ext3_new_inode (handle, dir, NULL, mode);
+ err = PTR_ERR(inode);
+ if (!IS_ERR(inode)) {
+ inode->i_op = &ext3_file_inode_operations;
+ inode->i_fop = &ext3_file_operations;
+ ext3_set_aops(inode);
+ d_tmpfile(dentry, inode);
+ err = ext3_orphan_add(handle, inode);
+ if (err)
+ goto err_unlock_inode;
+ mark_inode_dirty(inode);
+ unlock_new_inode(inode);
+ }
+ ext3_journal_stop(handle);
+ if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
+ goto retry;
+ return err;
+err_unlock_inode:
+ ext3_journal_stop(handle);
+ unlock_new_inode(inode);
+ return err;
+}
+
static int ext3_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
{
handle_t *handle;
@@ -1790,8 +1828,7 @@ retry:
inode->i_op = &ext3_dir_inode_operations;
inode->i_fop = &ext3_dir_operations;
inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize;
- dir_block = ext3_bread (handle, inode, 0, 1, &err);
- if (!dir_block)
+ if (!(dir_block = ext3_dir_bread(handle, inode, 0, 1, &err)))
goto out_clear_inode;
BUFFER_TRACE(dir_block, "get_write_access");
@@ -1836,8 +1873,8 @@ out_clear_inode:
if (err)
goto out_clear_inode;
- d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ d_instantiate(dentry, inode);
out_stop:
brelse(dir_block);
ext3_journal_stop(handle);
@@ -1859,7 +1896,7 @@ static int empty_dir (struct inode * inode)
sb = inode->i_sb;
if (inode->i_size < EXT3_DIR_REC_LEN(1) + EXT3_DIR_REC_LEN(2) ||
- !(bh = ext3_bread (NULL, inode, 0, 0, &err))) {
+ !(bh = ext3_dir_bread(NULL, inode, 0, 0, &err))) {
if (err)
ext3_error(inode->i_sb, __func__,
"error %d reading directory #%lu offset 0",
@@ -1890,9 +1927,8 @@ static int empty_dir (struct inode * inode)
(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
err = 0;
brelse (bh);
- bh = ext3_bread (NULL, inode,
- offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err);
- if (!bh) {
+ if (!(bh = ext3_dir_bread (NULL, inode,
+ offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err))) {
if (err)
ext3_error(sb, __func__,
"error %d reading directory"
@@ -2302,7 +2338,7 @@ static int ext3_link (struct dentry * old_dentry,
retry:
handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
- EXT3_INDEX_EXTRA_TRANS_BLOCKS);
+ EXT3_INDEX_EXTRA_TRANS_BLOCKS + 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -2316,6 +2352,11 @@ retry:
err = ext3_add_entry(handle, dentry, inode);
if (!err) {
ext3_mark_inode_dirty(handle, inode);
+ /* this can happen only for tmpfile being
+ * linked the first time
+ */
+ if (inode->i_nlink == 1)
+ ext3_orphan_del(handle, inode);
d_instantiate(dentry, inode);
} else {
drop_nlink(inode);
@@ -2388,7 +2429,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
goto end_rename;
}
retval = -EIO;
- dir_bh = ext3_bread (handle, old_inode, 0, 0, &retval);
+ dir_bh = ext3_dir_bread(handle, old_inode, 0, 0, &retval);
if (!dir_bh)
goto end_rename;
if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
@@ -2518,6 +2559,7 @@ const struct inode_operations ext3_dir_inode_operations = {
.mkdir = ext3_mkdir,
.rmdir = ext3_rmdir,
.mknod = ext3_mknod,
+ .tmpfile = ext3_tmpfile,
.rename = ext3_rename,
.setattr = ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
@@ -2527,6 +2569,7 @@ const struct inode_operations ext3_dir_inode_operations = {
.removexattr = generic_removexattr,
#endif
.get_acl = ext3_get_acl,
+ .set_acl = ext3_set_acl,
};
const struct inode_operations ext3_special_inode_operations = {
@@ -2538,4 +2581,5 @@ const struct inode_operations ext3_special_inode_operations = {
.removexattr = generic_removexattr,
#endif
.get_acl = ext3_get_acl,
+ .set_acl = ext3_set_acl,
};
diff --git a/fs/ext3/namei.h b/fs/ext3/namei.h
index f2ce2b0065c..46304d8c9f0 100644
--- a/fs/ext3/namei.h
+++ b/fs/ext3/namei.h
@@ -6,3 +6,22 @@
*/
extern struct dentry *ext3_get_parent(struct dentry *child);
+
+static inline struct buffer_head *ext3_dir_bread(handle_t *handle,
+ struct inode *inode,
+ int block, int create,
+ int *err)
+{
+ struct buffer_head *bh;
+
+ bh = ext3_bread(handle, inode, block, create, err);
+
+ if (!bh && !(*err)) {
+ *err = -EIO;
+ ext3_error(inode->i_sb, __func__,
+ "Directory hole detected on inode %lu\n",
+ inode->i_ino);
+ return NULL;
+ }
+ return bh;
+}
diff --git a/fs/ext3/resize.c b/fs/ext3/resize.c
index 0f814f3450d..27105655502 100644
--- a/fs/ext3/resize.c
+++ b/fs/ext3/resize.c
@@ -116,8 +116,8 @@ static struct buffer_head *bclean(handle_t *handle, struct super_block *sb,
int err;
bh = sb_getblk(sb, blk);
- if (!bh)
- return ERR_PTR(-EIO);
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
if ((err = ext3_journal_get_write_access(handle, bh))) {
brelse(bh);
bh = ERR_PTR(err);
@@ -234,8 +234,8 @@ static int setup_new_group_blocks(struct super_block *sb,
goto exit_bh;
gdb = sb_getblk(sb, block);
- if (!gdb) {
- err = -EIO;
+ if (unlikely(!gdb)) {
+ err = -ENOMEM;
goto exit_bh;
}
if ((err = ext3_journal_get_write_access(handle, gdb))) {
@@ -722,8 +722,8 @@ static void update_backups(struct super_block *sb,
break;
bh = sb_getblk(sb, group * bpg + blk_off);
- if (!bh) {
- err = -EIO;
+ if (unlikely(!bh)) {
+ err = -ENOMEM;
break;
}
ext3_debug("update metadata backup %#04lx\n",
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 8c3a44b7c37..08cdfe5461e 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -27,6 +27,7 @@
#include <linux/seq_file.h>
#include <linux/log2.h>
#include <linux/cleancache.h>
+#include <linux/namei.h>
#include <asm/uaccess.h>
@@ -64,11 +65,6 @@ static int ext3_freeze(struct super_block *sb);
/*
* Wrappers for journal_start/end.
- *
- * The only special thing we need to do here is to make sure that all
- * journal_end calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
*/
handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
{
@@ -90,12 +86,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks)
return journal_start(journal, nblocks);
}
-/*
- * The only special thing we need to do here is to make sure that all
- * journal_stop calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- */
int __ext3_journal_stop(const char *where, handle_t *handle)
{
struct super_block *sb;
@@ -185,6 +175,11 @@ static void ext3_handle_error(struct super_block *sb)
if (test_opt (sb, ERRORS_RO)) {
ext3_msg(sb, KERN_CRIT,
"error: remounting filesystem read-only");
+ /*
+ * Make sure updated value of ->s_mount_state will be visible
+ * before ->s_flags update.
+ */
+ smp_wmb();
sb->s_flags |= MS_RDONLY;
}
ext3_commit_super(sb, es, 1);
@@ -302,8 +297,14 @@ void ext3_abort(struct super_block *sb, const char *function,
ext3_msg(sb, KERN_CRIT,
"error: remounting filesystem read-only");
EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
- sb->s_flags |= MS_RDONLY;
set_opt(EXT3_SB(sb)->s_mount_opt, ABORT);
+ /*
+ * Make sure updated value of ->s_mount_state will be visible
+ * before ->s_flags update.
+ */
+ smp_wmb();
+ sb->s_flags |= MS_RDONLY;
+
if (EXT3_SB(sb)->s_journal)
journal_abort(EXT3_SB(sb)->s_journal, -EIO);
}
@@ -364,7 +365,7 @@ static struct block_device *ext3_blkdev_get(dev_t dev, struct super_block *sb)
return bdev;
fail:
- ext3_msg(sb, "error: failed to open journal device %s: %ld",
+ ext3_msg(sb, KERN_ERR, "error: failed to open journal device %s: %ld",
__bdevname(dev, b), PTR_ERR(bdev));
return NULL;
@@ -373,22 +374,19 @@ fail:
/*
* Release the journal device
*/
-static int ext3_blkdev_put(struct block_device *bdev)
+static void ext3_blkdev_put(struct block_device *bdev)
{
- return blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
-static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
+static void ext3_blkdev_remove(struct ext3_sb_info *sbi)
{
struct block_device *bdev;
- int ret = -ENODEV;
-
bdev = sbi->journal_bdev;
if (bdev) {
- ret = ext3_blkdev_put(bdev);
+ ext3_blkdev_put(bdev);
sbi->journal_bdev = NULL;
}
- return ret;
}
static inline struct inode *orphan_list_entry(struct list_head *l)
@@ -529,7 +527,7 @@ static void init_once(void *foo)
inode_init_once(&ei->vfs_inode);
}
-static int init_inodecache(void)
+static int __init init_inodecache(void)
{
ext3_inode_cachep = kmem_cache_create("ext3_inode_cache",
sizeof(struct ext3_inode_info),
@@ -543,6 +541,11 @@ static int init_inodecache(void)
static void destroy_inodecache(void)
{
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
kmem_cache_destroy(ext3_inode_cachep);
}
@@ -817,6 +820,7 @@ enum {
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
+ Opt_journal_path,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
@@ -858,6 +862,7 @@ static const match_table_t tokens = {
{Opt_journal_update, "journal=update"},
{Opt_journal_inum, "journal=%u"},
{Opt_journal_dev, "journal_dev=%u"},
+ {Opt_journal_path, "journal_path=%s"},
{Opt_abort, "abort"},
{Opt_data_journal, "data=journal"},
{Opt_data_ordered, "data=ordered"},
@@ -893,7 +898,7 @@ static ext3_fsblk_t get_sb_block(void **data, struct super_block *sb)
/*todo: use simple_strtoll with >32bit ext3 */
sb_block = simple_strtoul(options, &options, 0);
if (*options && *options != ',') {
- ext3_msg(sb, "error: invalid sb specification: %s",
+ ext3_msg(sb, KERN_ERR, "error: invalid sb specification: %s",
(char *) *data);
return 1;
}
@@ -922,21 +927,24 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
"Not enough memory for storing quotafile name");
return 0;
}
- if (sbi->s_qf_names[qtype] &&
- strcmp(sbi->s_qf_names[qtype], qname)) {
- ext3_msg(sb, KERN_ERR,
- "%s quota file already specified", QTYPE2NAME(qtype));
+ if (sbi->s_qf_names[qtype]) {
+ int same = !strcmp(sbi->s_qf_names[qtype], qname);
+
kfree(qname);
- return 0;
+ if (!same) {
+ ext3_msg(sb, KERN_ERR,
+ "%s quota file already specified",
+ QTYPE2NAME(qtype));
+ }
+ return same;
}
- sbi->s_qf_names[qtype] = qname;
- if (strchr(sbi->s_qf_names[qtype], '/')) {
+ if (strchr(qname, '/')) {
ext3_msg(sb, KERN_ERR,
"quotafile must be on filesystem root");
- kfree(sbi->s_qf_names[qtype]);
- sbi->s_qf_names[qtype] = NULL;
+ kfree(qname);
return 0;
}
+ sbi->s_qf_names[qtype] = qname;
set_opt(sbi->s_mount_opt, QUOTA);
return 1;
}
@@ -951,11 +959,10 @@ static int clear_qf_name(struct super_block *sb, int qtype) {
" when quota turned on");
return 0;
}
- /*
- * The space will be released later when all options are confirmed
- * to be correct
- */
- sbi->s_qf_names[qtype] = NULL;
+ if (sbi->s_qf_names[qtype]) {
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ }
return 1;
}
#endif
@@ -971,6 +978,11 @@ static int parse_options (char *options, struct super_block *sb,
int option;
kuid_t uid;
kgid_t gid;
+ char *journal_path;
+ struct inode *journal_inode;
+ struct path path;
+ int error;
+
#ifdef CONFIG_QUOTA
int qfmt;
#endif
@@ -986,7 +998,7 @@ static int parse_options (char *options, struct super_block *sb,
* Initialize args struct so we know whether arg was
* found; some options take optional arguments.
*/
- args[0].to = args[0].from = 0;
+ args[0].to = args[0].from = NULL;
token = match_token(p, tokens, args);
switch (token) {
case Opt_bsd_df:
@@ -1007,7 +1019,7 @@ static int parse_options (char *options, struct super_block *sb,
uid = make_kuid(current_user_ns(), option);
if (!uid_valid(uid)) {
ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option);
- return -1;
+ return 0;
}
sbi->s_resuid = uid;
@@ -1018,7 +1030,7 @@ static int parse_options (char *options, struct super_block *sb,
gid = make_kgid(current_user_ns(), option);
if (!gid_valid(gid)) {
ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option);
- return -1;
+ return 0;
}
sbi->s_resgid = gid;
break;
@@ -1125,6 +1137,41 @@ static int parse_options (char *options, struct super_block *sb,
return 0;
*journal_devnum = option;
break;
+ case Opt_journal_path:
+ if (is_remount) {
+ ext3_msg(sb, KERN_ERR, "error: cannot specify "
+ "journal on remount");
+ return 0;
+ }
+
+ journal_path = match_strdup(&args[0]);
+ if (!journal_path) {
+ ext3_msg(sb, KERN_ERR, "error: could not dup "
+ "journal device string");
+ return 0;
+ }
+
+ error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+ if (error) {
+ ext3_msg(sb, KERN_ERR, "error: could not find "
+ "journal device path: error %d", error);
+ kfree(journal_path);
+ return 0;
+ }
+
+ journal_inode = path.dentry->d_inode;
+ if (!S_ISBLK(journal_inode->i_mode)) {
+ ext3_msg(sb, KERN_ERR, "error: journal path %s "
+ "is not a block device", journal_path);
+ path_put(&path);
+ kfree(journal_path);
+ return 0;
+ }
+
+ *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+ path_put(&path);
+ kfree(journal_path);
+ break;
case Opt_noload:
set_opt (sbi->s_mount_opt, NOLOAD);
break;
@@ -1490,10 +1537,12 @@ static void ext3_orphan_cleanup (struct super_block * sb,
}
if (EXT3_SB(sb)->s_mount_state & EXT3_ERROR_FS) {
- if (es->s_last_orphan)
+ /* don't clear list on RO mount w/ errors */
+ if (es->s_last_orphan && !(s_flags & MS_RDONLY)) {
jbd_debug(1, "Errors on filesystem, "
"clearing orphan list.\n");
- es->s_last_orphan = 0;
+ es->s_last_orphan = 0;
+ }
jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
return;
}
@@ -1665,9 +1714,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
return -ENOMEM;
}
sb->s_fs_info = sbi;
- sbi->s_mount_opt = 0;
- sbi->s_resuid = make_kuid(&init_user_ns, EXT3_DEF_RESUID);
- sbi->s_resgid = make_kgid(&init_user_ns, EXT3_DEF_RESGID);
sbi->s_sb_block = sb_block;
blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
@@ -2058,7 +2104,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
goto failed_mount3;
}
- ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
+ if (ext3_setup_super(sb, es, sb->s_flags & MS_RDONLY))
+ sb->s_flags |= MS_RDONLY;
EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
ext3_orphan_cleanup(sb, es);
@@ -2526,6 +2573,11 @@ static int ext3_sync_fs(struct super_block *sb, int wait)
tid_t target;
trace_ext3_sync_fs(sb, wait);
+ /*
+ * Writeback quota in non-journalled quota case - journalled quota has
+ * no dirty dquots
+ */
+ dquot_writeback_dquots(sb, -1);
if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
if (wait)
log_wait_commit(EXT3_SB(sb)->s_journal, target);
@@ -2576,11 +2628,9 @@ out:
static int ext3_unfreeze(struct super_block *sb)
{
if (!(sb->s_flags & MS_RDONLY)) {
- lock_super(sb);
/* Reser the needs_recovery flag before the fs is unlocked. */
EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);
- unlock_super(sb);
journal_unlock_updates(EXT3_SB(sb)->s_journal);
}
return 0;
@@ -2599,8 +2649,9 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
int i;
#endif
+ sync_filesystem(sb);
+
/* Store the original options */
- lock_super(sb);
old_sb_flags = sb->s_flags;
old_opts.s_mount_opt = sbi->s_mount_opt;
old_opts.s_resuid = sbi->s_resuid;
@@ -2609,7 +2660,18 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
#ifdef CONFIG_QUOTA
old_opts.s_jquota_fmt = sbi->s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++)
- old_opts.s_qf_names[i] = sbi->s_qf_names[i];
+ if (sbi->s_qf_names[i]) {
+ old_opts.s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
+ GFP_KERNEL);
+ if (!old_opts.s_qf_names[i]) {
+ int j;
+
+ for (j = 0; j < i; j++)
+ kfree(old_opts.s_qf_names[j]);
+ return -ENOMEM;
+ }
+ } else
+ old_opts.s_qf_names[i] = NULL;
#endif
/*
@@ -2702,12 +2764,8 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
- if (old_opts.s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(old_opts.s_qf_names[i]);
+ kfree(old_opts.s_qf_names[i]);
#endif
- unlock_super(sb);
-
if (enable_quota)
dquot_resume(sb, -1);
return 0;
@@ -2720,13 +2778,10 @@ restore_opts:
#ifdef CONFIG_QUOTA
sbi->s_jquota_fmt = old_opts.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
- if (sbi->s_qf_names[i] &&
- old_opts.s_qf_names[i] != sbi->s_qf_names[i])
- kfree(sbi->s_qf_names[i]);
+ kfree(sbi->s_qf_names[i]);
sbi->s_qf_names[i] = old_opts.s_qf_names[i];
}
#endif
- unlock_super(sb);
return err;
}
@@ -2772,6 +2827,10 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
* bitmap, and an inode table.
*/
overhead += ngroups * (2 + sbi->s_itb_per_group);
+
+ /* Add the journal blocks as well */
+ overhead += sbi->s_journal->j_maxlen;
+
sbi->s_overhead_last = overhead;
smp_wmb();
sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
@@ -2808,7 +2867,7 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
static inline struct inode *dquot_to_inode(struct dquot *dquot)
{
- return sb_dqopt(dquot->dq_sb)->files[dquot->dq_type];
+ return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type];
}
static int ext3_write_dquot(struct dquot *dquot)
@@ -3065,6 +3124,7 @@ static struct file_system_type ext3_fs_type = {
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("ext3");
static int __init init_ext3_fs(void)
{
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index d22ebb7a4f5..c6874be6d58 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -102,8 +102,8 @@ static struct mb_cache *ext3_xattr_cache;
static const struct xattr_handler *ext3_xattr_handler_map[] = {
[EXT3_XATTR_INDEX_USER] = &ext3_xattr_user_handler,
#ifdef CONFIG_EXT3_FS_POSIX_ACL
- [EXT3_XATTR_INDEX_POSIX_ACL_ACCESS] = &ext3_xattr_acl_access_handler,
- [EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT] = &ext3_xattr_acl_default_handler,
+ [EXT3_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler,
+ [EXT3_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler,
#endif
[EXT3_XATTR_INDEX_TRUSTED] = &ext3_xattr_trusted_handler,
#ifdef CONFIG_EXT3_FS_SECURITY
@@ -115,8 +115,8 @@ const struct xattr_handler *ext3_xattr_handlers[] = {
&ext3_xattr_user_handler,
&ext3_xattr_trusted_handler,
#ifdef CONFIG_EXT3_FS_POSIX_ACL
- &ext3_xattr_acl_access_handler,
- &ext3_xattr_acl_default_handler,
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_handler,
#endif
#ifdef CONFIG_EXT3_FS_SECURITY
&ext3_xattr_security_handler,
@@ -813,10 +813,10 @@ inserted:
ea_idebug(inode, "creating block %d", block);
new_bh = sb_getblk(sb, block);
- if (!new_bh) {
+ if (unlikely(!new_bh)) {
getblk_failed:
ext3_free_blocks(handle, inode, block, 1);
- error = -EIO;
+ error = -ENOMEM;
goto cleanup;
}
lock_buffer(new_bh);
diff --git a/fs/ext3/xattr.h b/fs/ext3/xattr.h
index 2be4f69bfa6..32e93ebf803 100644
--- a/fs/ext3/xattr.h
+++ b/fs/ext3/xattr.h
@@ -60,8 +60,6 @@ struct ext3_xattr_entry {
extern const struct xattr_handler ext3_xattr_user_handler;
extern const struct xattr_handler ext3_xattr_trusted_handler;
-extern const struct xattr_handler ext3_xattr_acl_access_handler;
-extern const struct xattr_handler ext3_xattr_acl_default_handler;
extern const struct xattr_handler ext3_xattr_security_handler;
extern ssize_t ext3_listxattr(struct dentry *, char *, size_t);
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 3387664ad70..722c2bf9645 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -43,8 +43,9 @@ ext3_xattr_security_set(struct dentry *dentry, const char *name,
name, value, size, flags);
}
-int ext3_initxattrs(struct inode *inode, const struct xattr *xattr_array,
- void *fs_info)
+static int ext3_initxattrs(struct inode *inode,
+ const struct xattr *xattr_array,
+ void *fs_info)
{
const struct xattr *xattr;
handle_t *handle = fs_info;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 15:23:18 +0000