summaryrefslogtreecommitdiff
path: root/fs/ext3
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext3')
-rw-r--r--fs/ext3/acl.c2
-rw-r--r--fs/ext3/dir.c14
-rw-r--r--fs/ext3/file.c1
-rw-r--r--fs/ext3/inode.c2
-rw-r--r--fs/ext3/ioctl.c6
-rw-r--r--fs/ext3/namei.c83
-rw-r--r--fs/ext3/super.c67
7 files changed, 139 insertions, 36 deletions
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index 1e5038d9a01b..d34e9967430a 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -489,7 +489,7 @@ ext3_xattr_set_acl(struct inode *inode, int type, const void *value,
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
- if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EPERM;
if (value) {
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 852869840f24..c00723a99f44 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -136,12 +136,14 @@ static int ext3_readdir(struct file * filp,
err = ext3_get_blocks_handle(NULL, inode, blk, 1,
&map_bh, 0, 0);
if (err > 0) {
- page_cache_readahead(sb->s_bdev->bd_inode->i_mapping,
- &filp->f_ra,
- filp,
- map_bh.b_blocknr >>
- (PAGE_CACHE_SHIFT - inode->i_blkbits),
- 1);
+ pgoff_t index = map_bh.b_blocknr >>
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ if (!ra_has_index(&filp->f_ra, index))
+ page_cache_sync_readahead(
+ sb->s_bdev->bd_inode->i_mapping,
+ &filp->f_ra, filp,
+ index, 1);
+ filp->f_ra.prev_index = index;
bh = ext3_bread(NULL, inode, blk, 0, &err);
}
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 1e6f13864536..acc4913d3019 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -120,7 +120,6 @@ const struct file_operations ext3_file_operations = {
.open = generic_file_open,
.release = ext3_release_file,
.fsync = ext3_sync_file,
- .sendfile = generic_file_sendfile,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2a85ddee4740..de4e3161e479 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -3195,7 +3195,7 @@ int ext3_change_inode_journal_flag(struct inode *inode, int val)
*/
journal = EXT3_JOURNAL(inode);
- if (is_journal_aborted(journal) || IS_RDONLY(inode))
+ if (is_journal_aborted(journal))
return -EROFS;
journal_lock_updates(journal);
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 965006dba6be..4a2a02c95bf9 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -41,7 +41,7 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
if (IS_RDONLY(inode))
return -EROFS;
- if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
@@ -122,7 +122,7 @@ flags_err:
__u32 generation;
int err;
- if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EPERM;
if (IS_RDONLY(inode))
return -EROFS;
@@ -181,7 +181,7 @@ flags_err:
if (IS_RDONLY(inode))
return -EROFS;
- if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EACCES;
if (get_user(rsv_window_size, (int __user *)arg))
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index 9bb046df827a..c1fa1908dba0 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -140,7 +140,8 @@ struct dx_frame
struct dx_map_entry
{
u32 hash;
- u32 offs;
+ u16 offs;
+ u16 size;
};
#ifdef CONFIG_EXT3_INDEX
@@ -379,13 +380,28 @@ dx_probe(struct dentry *dentry, struct inode *dir,
entries = (struct dx_entry *) (((char *)&root->info) +
root->info.info_length);
- assert(dx_get_limit(entries) == dx_root_limit(dir,
- root->info.info_length));
+
+ if (dx_get_limit(entries) != dx_root_limit(dir,
+ root->info.info_length)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: limit != root limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail;
+ }
+
dxtrace (printk("Look up %x", hash));
while (1)
{
count = dx_get_count(entries);
- assert (count && count <= dx_get_limit(entries));
+ if (!count || count > dx_get_limit(entries)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: no count or count > limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail2;
+ }
+
p = entries + 1;
q = entries + count - 1;
while (p <= q)
@@ -423,8 +439,15 @@ dx_probe(struct dentry *dentry, struct inode *dir,
if (!(bh = ext3_bread (NULL,dir, dx_get_block(at), 0, err)))
goto fail2;
at = entries = ((struct dx_node *) bh->b_data)->entries;
- assert (dx_get_limit(entries) == dx_node_limit (dir));
+ if (dx_get_limit(entries) != dx_node_limit (dir)) {
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "dx entry: limit != node limit");
+ brelse(bh);
+ *err = ERR_BAD_DX_DIR;
+ goto fail2;
+ }
frame++;
+ frame->bh = NULL;
}
fail2:
while (frame >= frame_in) {
@@ -432,6 +455,10 @@ fail2:
frame--;
}
fail:
+ if (*err == ERR_BAD_DX_DIR)
+ ext3_warning(dir->i_sb, __FUNCTION__,
+ "Corrupt dir inode %ld, running e2fsck is "
+ "recommended.", dir->i_ino);
return NULL;
}
@@ -671,6 +698,10 @@ errout:
* Directory block splitting, compacting
*/
+/*
+ * Create map of hash values, offsets, and sizes, stored at end of block.
+ * Returns number of entries mapped.
+ */
static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
{
@@ -684,7 +715,8 @@ static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
ext3fs_dirhash(de->name, de->name_len, &h);
map_tail--;
map_tail->hash = h.hash;
- map_tail->offs = (u32) ((char *) de - base);
+ map_tail->offs = (u16) ((char *) de - base);
+ map_tail->size = le16_to_cpu(de->rec_len);
count++;
cond_resched();
}
@@ -694,6 +726,7 @@ static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
return count;
}
+/* Sort map by hash value */
static void dx_sort_map (struct dx_map_entry *map, unsigned count)
{
struct dx_map_entry *p, *q, *top = map + count - 1;
@@ -1019,6 +1052,11 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
if (!inode)
return ERR_PTR(-EACCES);
+
+ if (is_bad_inode(inode)) {
+ iput(inode);
+ return ERR_PTR(-ENOENT);
+ }
}
return d_splice_alias(inode, dentry);
}
@@ -1054,6 +1092,11 @@ struct dentry *ext3_get_parent(struct dentry *child)
if (!inode)
return ERR_PTR(-EACCES);
+ if (is_bad_inode(inode)) {
+ iput(inode);
+ return ERR_PTR(-ENOENT);
+ }
+
parent = d_alloc_anon(inode);
if (!parent) {
iput(inode);
@@ -1081,6 +1124,10 @@ static inline void ext3_set_de_type(struct super_block *sb,
}
#ifdef CONFIG_EXT3_INDEX
+/*
+ * Move count entries from end of map between two memory locations.
+ * Returns pointer to last entry moved.
+ */
static struct ext3_dir_entry_2 *
dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
{
@@ -1099,6 +1146,10 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
return (struct ext3_dir_entry_2 *) (to - rec_len);
}
+/*
+ * Compact each dir entry in the range to the minimal rec_len.
+ * Returns pointer to last entry in range.
+ */
static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
{
struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base;
@@ -1121,6 +1172,11 @@ static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
return prev;
}
+/*
+ * Split a full leaf block to make room for a new dir entry.
+ * Allocate a new block, and move entries so that they are approx. equally full.
+ * Returns pointer to de in block into which the new entry will be inserted.
+ */
static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
struct buffer_head **bh,struct dx_frame *frame,
struct dx_hash_info *hinfo, int *error)
@@ -1132,7 +1188,7 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
u32 hash2;
struct dx_map_entry *map;
char *data1 = (*bh)->b_data, *data2;
- unsigned split;
+ unsigned split, move, size, i;
struct ext3_dir_entry_2 *de = NULL, *de2;
int err = 0;
@@ -1160,8 +1216,19 @@ static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
count = dx_make_map ((struct ext3_dir_entry_2 *) data1,
blocksize, hinfo, map);
map -= count;
- split = count/2; // need to adjust to actual middle
dx_sort_map (map, count);
+ /* Split the existing block in the middle, size-wise */
+ size = 0;
+ move = 0;
+ for (i = count-1; i >= 0; i--) {
+ /* is more than half of this entry in 2nd half of the block? */
+ if (size + map[i].size/2 > blocksize/2)
+ break;
+ size += map[i].size;
+ move++;
+ }
+ /* map index at which we will split */
+ split = count - move;
hash2 = map[split].hash;
continued = hash2 == map[split - 1].hash;
dxtrace(printk("Split block %i at %x, %i/%i\n",
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 6e3062913a92..9537316a0714 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -29,12 +29,14 @@
#include <linux/parser.h>
#include <linux/smp_lock.h>
#include <linux/buffer_head.h>
+#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/random.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/quotaops.h>
#include <linux/seq_file.h>
+#include <linux/log2.h>
#include <asm/uaccess.h>
@@ -459,6 +461,14 @@ static struct inode *ext3_alloc_inode(struct super_block *sb)
static void ext3_destroy_inode(struct inode *inode)
{
+ if (!list_empty(&(EXT3_I(inode)->i_orphan))) {
+ printk("EXT3 Inode %p: orphan list check failed!\n",
+ EXT3_I(inode));
+ print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 4,
+ EXT3_I(inode), sizeof(struct ext3_inode_info),
+ false);
+ dump_stack();
+ }
kmem_cache_free(ext3_inode_cachep, EXT3_I(inode));
}
@@ -480,7 +490,7 @@ static int init_inodecache(void)
sizeof(struct ext3_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_MEM_SPREAD),
- init_once, NULL);
+ init_once);
if (ext3_inode_cachep == NULL)
return -ENOMEM;
return 0;
@@ -1211,7 +1221,7 @@ static int ext3_check_descriptors (struct super_block * sb)
return 0;
}
if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
- le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group >
+ le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
last_block)
{
ext3_error (sb, "ext3_check_descriptors",
@@ -1566,7 +1576,7 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
if ((sbi->s_inode_size < EXT3_GOOD_OLD_INODE_SIZE) ||
- (sbi->s_inode_size & (sbi->s_inode_size - 1)) ||
+ (!is_power_of_2(sbi->s_inode_size)) ||
(sbi->s_inode_size > blocksize)) {
printk (KERN_ERR
"EXT3-fs: unsupported inode size: %d\n",
@@ -2075,6 +2085,7 @@ static int ext3_create_journal(struct super_block * sb,
unsigned int journal_inum)
{
journal_t *journal;
+ int err;
if (sb->s_flags & MS_RDONLY) {
printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to "
@@ -2082,13 +2093,15 @@ static int ext3_create_journal(struct super_block * sb,
return -EROFS;
}
- if (!(journal = ext3_get_journal(sb, journal_inum)))
+ journal = ext3_get_journal(sb, journal_inum);
+ if (!journal)
return -EINVAL;
printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n",
journal_inum);
- if (journal_create(journal)) {
+ err = journal_create(journal);
+ if (err) {
printk(KERN_ERR "EXT3-fs: error creating journal.\n");
journal_destroy(journal);
return -EIO;
@@ -2139,12 +2152,14 @@ static void ext3_mark_recovery_complete(struct super_block * sb,
journal_lock_updates(journal);
journal_flush(journal);
+ lock_super(sb);
if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
sb->s_flags & MS_RDONLY) {
EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
sb->s_dirt = 0;
ext3_commit_super(sb, es, 1);
}
+ unlock_super(sb);
journal_unlock_updates(journal);
}
@@ -2333,7 +2348,13 @@ static int ext3_remount (struct super_block * sb, int * flags, char * data)
(sbi->s_mount_state & EXT3_VALID_FS))
es->s_state = cpu_to_le16(sbi->s_mount_state);
+ /*
+ * We have to unlock super so that we can wait for
+ * transactions.
+ */
+ unlock_super(sb);
ext3_mark_recovery_complete(sb, es);
+ lock_super(sb);
} else {
__le32 ret;
if ((ret = EXT3_HAS_RO_COMPAT_FEATURE(sb,
@@ -2406,19 +2427,19 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
struct super_block *sb = dentry->d_sb;
struct ext3_sb_info *sbi = EXT3_SB(sb);
struct ext3_super_block *es = sbi->s_es;
- ext3_fsblk_t overhead;
- int i;
u64 fsid;
- if (test_opt (sb, MINIX_DF))
- overhead = 0;
- else {
- unsigned long ngroups;
- ngroups = EXT3_SB(sb)->s_groups_count;
+ if (test_opt(sb, MINIX_DF)) {
+ sbi->s_overhead_last = 0;
+ } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
+ unsigned long ngroups = sbi->s_groups_count, i;
+ ext3_fsblk_t overhead = 0;
smp_rmb();
/*
- * Compute the overhead (FS structures)
+ * Compute the overhead (FS structures). This is constant
+ * for a given filesystem unless the number of block groups
+ * changes so we cache the previous value until it does.
*/
/*
@@ -2442,18 +2463,23 @@ static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf)
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
- overhead += (ngroups * (2 + EXT3_SB(sb)->s_itb_per_group));
+ overhead += ngroups * (2 + sbi->s_itb_per_group);
+ sbi->s_overhead_last = overhead;
+ smp_wmb();
+ sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
}
buf->f_type = EXT3_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = le32_to_cpu(es->s_blocks_count) - overhead;
+ buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
+ es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
+ es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT3_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
@@ -2552,8 +2578,11 @@ static int ext3_release_dquot(struct dquot *dquot)
handle = ext3_journal_start(dquot_to_inode(dquot),
EXT3_QUOTA_DEL_BLOCKS(dquot->dq_sb));
- if (IS_ERR(handle))
+ if (IS_ERR(handle)) {
+ /* Release dquot anyway to avoid endless cycle in dqput() */
+ dquot_release(dquot);
return PTR_ERR(handle);
+ }
ret = dquot_release(dquot);
err = ext3_journal_stop(handle);
if (!ret)
@@ -2686,6 +2715,12 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type,
struct buffer_head *bh;
handle_t *handle = journal_current_handle();
+ if (!handle) {
+ printk(KERN_WARNING "EXT3-fs: Quota write (off=%Lu, len=%Lu)"
+ " cancelled because transaction is not started.\n",
+ (unsigned long long)off, (unsigned long long)len);
+ return -EIO;
+ }
mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
while (towrite > 0) {
tocopy = sb->s_blocksize - offset < towrite ?
generated by cgit v1.2.3 (git 2.0.4) at 2024-07-02 06:14:19 +0000