* [PATCH 24/32] ext2, ext4: make mb block cache names more explicit
@ 2017-06-22 1:49 Tahsin Erdogan
2017-06-22 1:49 ` [PATCH 25/32] ext4: add ext4_is_quota_file() Tahsin Erdogan
` (8 more replies)
0 siblings, 9 replies; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
There will be a second mb_cache instance that tracks ea_inodes. Make
existing names more explicit so that it is clear that they refer to
xattr block cache.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v2:
- renamed s_mb_cache to s_mb_block_cache in both ext2 and ext4
- renamed local variables named ext[24]_mb_cache to mb_block_cache
- renamed macro EXT4_GET_MB_CACHE() to MB_BLOCK_CACHE()
- added MB_BLOCK_CACHE() to ext2 for consistency with ext4
fs/ext2/ext2.h | 2 +-
fs/ext2/super.c | 16 ++++++-------
fs/ext2/xattr.c | 36 +++++++++++++++--------------
fs/ext4/ext4.h | 2 +-
fs/ext4/super.c | 18 +++++++--------
fs/ext4/xattr.c | 71 ++++++++++++++++++++++++++++++---------------------------
6 files changed, 75 insertions(+), 70 deletions(-)
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 03f5ce1d3dbe..23ebb92484c6 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -113,7 +113,7 @@ struct ext2_sb_info {
* of the mount options.
*/
spinlock_t s_lock;
- struct mb_cache *s_mb_cache;
+ struct mb_cache *s_ea_block_cache;
};
static inline spinlock_t *
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 9c2028b50e5c..7b1bc9059863 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -147,9 +147,9 @@ static void ext2_put_super (struct super_block * sb)
ext2_quota_off_umount(sb);
- if (sbi->s_mb_cache) {
- ext2_xattr_destroy_cache(sbi->s_mb_cache);
- sbi->s_mb_cache = NULL;
+ if (sbi->s_ea_block_cache) {
+ ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
+ sbi->s_ea_block_cache = NULL;
}
if (!(sb->s_flags & MS_RDONLY)) {
struct ext2_super_block *es = sbi->s_es;
@@ -1131,9 +1131,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
}
#ifdef CONFIG_EXT2_FS_XATTR
- sbi->s_mb_cache = ext2_xattr_create_cache();
- if (!sbi->s_mb_cache) {
- ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+ sbi->s_ea_block_cache = ext2_xattr_create_cache();
+ if (!sbi->s_ea_block_cache) {
+ ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
goto failed_mount3;
}
#endif
@@ -1182,8 +1182,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
sb->s_id);
goto failed_mount;
failed_mount3:
- if (sbi->s_mb_cache)
- ext2_xattr_destroy_cache(sbi->s_mb_cache);
+ if (sbi->s_ea_block_cache)
+ ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 1e5f76070580..1b9b1268d418 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -121,6 +121,8 @@ const struct xattr_handler *ext2_xattr_handlers[] = {
NULL
};
+#define EA_BLOCK_CACHE(inode) (EXT2_SB(inode->i_sb)->s_ea_block_cache)
+
static inline const struct xattr_handler *
ext2_xattr_handler(int name_index)
{
@@ -150,7 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
size_t name_len, size;
char *end;
int error;
- struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
@@ -195,7 +197,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get",
goto found;
entry = next;
}
- if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
error = -ENODATA;
goto cleanup;
@@ -208,7 +210,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get",
le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
goto bad_block;
- if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
if (buffer) {
error = -ERANGE;
@@ -246,7 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
char *end;
size_t rest = buffer_size;
int error;
- struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
@@ -281,7 +283,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list",
goto bad_block;
entry = next;
}
- if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+ if (ext2_xattr_cache_insert(ea_block_cache, bh))
ea_idebug(inode, "cache insert failed");
/* list the attribute names */
@@ -493,7 +495,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set",
* This must happen under buffer lock for
* ext2_xattr_set2() to reliably detect modified block
*/
- mb_cache_entry_delete(EXT2_SB(sb)->s_mb_cache, hash,
+ mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
bh->b_blocknr);
/* keep the buffer locked while modifying it. */
@@ -627,7 +629,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
struct super_block *sb = inode->i_sb;
struct buffer_head *new_bh = NULL;
int error;
- struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
if (header) {
new_bh = ext2_xattr_cache_find(inode, header);
@@ -655,7 +657,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
don't need to change the reference count. */
new_bh = old_bh;
get_bh(new_bh);
- ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+ ext2_xattr_cache_insert(ea_block_cache, new_bh);
} else {
/* We need to allocate a new block */
ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -676,7 +678,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
memcpy(new_bh->b_data, header, new_bh->b_size);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
- ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+ ext2_xattr_cache_insert(ea_block_cache, new_bh);
ext2_xattr_update_super_block(sb);
}
@@ -721,7 +723,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
* This must happen under buffer lock for
* ext2_xattr_set2() to reliably detect freed block
*/
- mb_cache_entry_delete(ext2_mb_cache, hash,
+ mb_cache_entry_delete(ea_block_cache, hash,
old_bh->b_blocknr);
/* Free the old block. */
ea_bdebug(old_bh, "freeing");
@@ -795,7 +797,7 @@ ext2_xattr_delete_inode(struct inode *inode)
* This must happen under buffer lock for ext2_xattr_set2() to
* reliably detect freed block
*/
- mb_cache_entry_delete(EXT2_SB(inode->i_sb)->s_mb_cache, hash,
+ mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
bh->b_blocknr);
ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
get_bh(bh);
@@ -897,13 +899,13 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
{
__u32 hash = le32_to_cpu(header->h_hash);
struct mb_cache_entry *ce;
- struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
again:
- ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
+ ce = mb_cache_entry_find_first(ea_block_cache, hash);
while (ce) {
struct buffer_head *bh;
@@ -924,7 +926,7 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
* entry is still hashed is reliable.
*/
if (hlist_bl_unhashed(&ce->e_hash_list)) {
- mb_cache_entry_put(ext2_mb_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
unlock_buffer(bh);
brelse(bh);
goto again;
@@ -937,14 +939,14 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
} else if (!ext2_xattr_cmp(header, HDR(bh))) {
ea_bdebug(bh, "b_count=%d",
atomic_read(&(bh->b_count)));
- mb_cache_entry_touch(ext2_mb_cache, ce);
- mb_cache_entry_put(ext2_mb_cache, ce);
+ mb_cache_entry_touch(ea_block_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
return bh;
}
unlock_buffer(bh);
brelse(bh);
}
- ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
+ ce = mb_cache_entry_find_next(ea_block_cache, ce);
}
return NULL;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 580fdb753f29..e4a75c643731 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1516,7 +1516,7 @@ struct ext4_sb_info {
struct list_head s_es_list; /* List of inodes with reclaimable extents */
long s_es_nr_inode;
struct ext4_es_stats s_es_stats;
- struct mb_cache *s_mb_cache;
+ struct mb_cache *s_ea_block_cache;
spinlock_t s_es_lock ____cacheline_aligned_in_smp;
/* Ratelimit ext4 messages. */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b02a23ec92ca..380389740575 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -927,9 +927,9 @@ static void ext4_put_super(struct super_block *sb)
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
- if (sbi->s_mb_cache) {
- ext4_xattr_destroy_cache(sbi->s_mb_cache);
- sbi->s_mb_cache = NULL;
+ if (sbi->s_ea_block_cache) {
+ ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+ sbi->s_ea_block_cache = NULL;
}
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
@@ -4061,9 +4061,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
no_journal:
- sbi->s_mb_cache = ext4_xattr_create_cache();
- if (!sbi->s_mb_cache) {
- ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+ sbi->s_ea_block_cache = ext4_xattr_create_cache();
+ if (!sbi->s_ea_block_cache) {
+ ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
goto failed_mount_wq;
}
@@ -4296,9 +4296,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (EXT4_SB(sb)->rsv_conversion_wq)
destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
failed_mount_wq:
- if (sbi->s_mb_cache) {
- ext4_xattr_destroy_cache(sbi->s_mb_cache);
- sbi->s_mb_cache = NULL;
+ if (sbi->s_ea_block_cache) {
+ ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+ sbi->s_ea_block_cache = NULL;
}
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fb437efa8688..fd73dbc92c21 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -72,10 +72,11 @@
# define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
-static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
-static struct buffer_head *ext4_xattr_cache_find(struct inode *,
- struct ext4_xattr_header *,
- struct mb_cache_entry **);
+static void ext4_xattr_block_cache_insert(struct mb_cache *,
+ struct buffer_head *);
+static struct buffer_head *
+ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
+ struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
@@ -104,8 +105,8 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
NULL
};
-#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \
- inode->i_sb->s_fs_info)->s_mb_cache)
+#define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \
+ inode->i_sb->s_fs_info)->s_ea_block_cache)
#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
@@ -374,7 +375,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
struct ext4_xattr_entry *entry;
size_t size;
int error;
- struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
name_index, name, buffer, (long)buffer_size);
@@ -395,7 +396,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
error = -EFSCORRUPTED;
goto cleanup;
}
- ext4_xattr_cache_insert(ext4_mb_cache, bh);
+ ext4_xattr_block_cache_insert(ea_block_cache, bh);
entry = BFIRST(bh);
error = ext4_xattr_find_entry(&entry, name_index, name, 1);
if (error)
@@ -541,7 +542,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
struct inode *inode = d_inode(dentry);
struct buffer_head *bh = NULL;
int error;
- struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
ea_idebug(inode, "buffer=%p, buffer_size=%ld",
buffer, (long)buffer_size);
@@ -563,7 +563,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
error = -EFSCORRUPTED;
goto cleanup;
}
- ext4_xattr_cache_insert(ext4_mb_cache, bh);
+ ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh);
error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
@@ -660,7 +660,7 @@ static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
struct buffer_head *bh)
{
- struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
u32 hash, ref;
int error = 0;
@@ -678,7 +678,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
- mb_cache_entry_delete(ext4_mb_cache, hash, bh->b_blocknr);
+ mb_cache_entry_delete(ea_block_cache, hash, bh->b_blocknr);
get_bh(bh);
unlock_buffer(bh);
ext4_free_blocks(handle, inode, bh, 0, 1,
@@ -690,11 +690,11 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
struct mb_cache_entry *ce;
- ce = mb_cache_entry_get(ext4_mb_cache, hash,
+ ce = mb_cache_entry_get(ea_block_cache, hash,
bh->b_blocknr);
if (ce) {
ce->e_reusable = 1;
- mb_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
}
}
@@ -1096,7 +1096,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
struct ext4_xattr_search *s = &s_copy;
struct mb_cache_entry *ce = NULL;
int error = 0;
- struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
#define header(x) ((struct ext4_xattr_header *)(x))
@@ -1115,7 +1115,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
* ext4_xattr_block_set() to reliably detect modified
* block
*/
- mb_cache_entry_delete(ext4_mb_cache, hash,
+ mb_cache_entry_delete(ea_block_cache, hash,
bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
error = ext4_xattr_set_entry(i, s, handle, inode);
@@ -1123,8 +1123,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base),
s->here);
- ext4_xattr_cache_insert(ext4_mb_cache,
- bs->bh);
+ ext4_xattr_block_cache_insert(ea_block_cache,
+ bs->bh);
}
ext4_xattr_block_csum_set(inode, bs->bh);
unlock_buffer(bs->bh);
@@ -1177,7 +1177,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
inserted:
if (!IS_LAST_ENTRY(s->first)) {
- new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
+ new_bh = ext4_xattr_block_cache_find(inode, header(s->base),
+ &ce);
if (new_bh) {
/* We found an identical block in the cache. */
if (new_bh == bs->bh)
@@ -1222,7 +1223,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
EXT4_C2B(EXT4_SB(sb),
1));
brelse(new_bh);
- mb_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
ce = NULL;
new_bh = NULL;
goto inserted;
@@ -1241,8 +1242,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
if (error)
goto cleanup_dquot;
}
- mb_cache_entry_touch(ext4_mb_cache, ce);
- mb_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_touch(ea_block_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
ce = NULL;
} else if (bs->bh && s->base == bs->bh->b_data) {
/* We were modifying this block in-place. */
@@ -1292,7 +1293,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
ext4_xattr_block_csum_set(inode, new_bh);
set_buffer_uptodate(new_bh);
unlock_buffer(new_bh);
- ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
+ ext4_xattr_block_cache_insert(ea_block_cache, new_bh);
error = ext4_handle_dirty_metadata(handle, inode,
new_bh);
if (error)
@@ -1310,7 +1311,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
cleanup:
if (ce)
- mb_cache_entry_put(ext4_mb_cache, ce);
+ mb_cache_entry_put(ea_block_cache, ce);
brelse(new_bh);
if (!(bs->bh && s->base == bs->bh->b_data))
kfree(s->base);
@@ -2150,15 +2151,16 @@ void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array)
}
/*
- * ext4_xattr_cache_insert()
+ * ext4_xattr_block_cache_insert()
*
- * Create a new entry in the extended attribute cache, and insert
+ * Create a new entry in the extended attribute block cache, and insert
* it unless such an entry is already in the cache.
*
* Returns 0, or a negative error number on failure.
*/
static void
-ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
+ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
+ struct buffer_head *bh)
{
struct ext4_xattr_header *header = BHDR(bh);
__u32 hash = le32_to_cpu(header->h_hash);
@@ -2166,7 +2168,7 @@ ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
EXT4_XATTR_REFCOUNT_MAX;
int error;
- error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+ error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash,
bh->b_blocknr, reusable);
if (error) {
if (error == -EBUSY)
@@ -2216,7 +2218,7 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
}
/*
- * ext4_xattr_cache_find()
+ * ext4_xattr_block_cache_find()
*
* Find an identical extended attribute block.
*
@@ -2224,17 +2226,18 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
* not found or an error occurred.
*/
static struct buffer_head *
-ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
- struct mb_cache_entry **pce)
+ext4_xattr_block_cache_find(struct inode *inode,
+ struct ext4_xattr_header *header,
+ struct mb_cache_entry **pce)
{
__u32 hash = le32_to_cpu(header->h_hash);
struct mb_cache_entry *ce;
- struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+ struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
- ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
+ ce = mb_cache_entry_find_first(ea_block_cache, hash);
while (ce) {
struct buffer_head *bh;
@@ -2247,7 +2250,7 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
return bh;
}
brelse(bh);
- ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
+ ce = mb_cache_entry_find_next(ea_block_cache, ce);
}
return NULL;
}
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 25/32] ext4: add ext4_is_quota_file()
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:39 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion Tahsin Erdogan
` (7 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
IS_NOQUOTA() indicates whether quota is disabled for an inode. Ext4
also uses it to check whether an inode is for a quota file. The
distinction currently doesn't matter because quota is disabled only
for the quota files. When we start disabling quota for other inodes
in the future, we will want to make the distinction clear.
Replace IS_NOQUOTA() call with ext4_is_quota_file() at places where
we are checking for quota files.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
fs/ext4/ext4.h | 2 ++
fs/ext4/inode.c | 2 +-
fs/ext4/ioctl.c | 4 ++--
fs/ext4/mballoc.c | 2 +-
fs/ext4/move_extent.c | 2 +-
5 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e4a75c643731..3b02bd897b61 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2099,6 +2099,8 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
}
+#define ext4_is_quota_file(inode) IS_NOQUOTA(inode)
+
/*
* This structure is stuffed into the struct file's private_data field
* for directories. It is where we put information so that we can do
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8ee20b586567..cf91532765a4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -739,7 +739,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
if (map->m_flags & EXT4_MAP_NEW &&
!(map->m_flags & EXT4_MAP_UNWRITTEN) &&
!(flags & EXT4_GET_BLOCKS_ZERO) &&
- !IS_NOQUOTA(inode) &&
+ !ext4_is_quota_file(inode) &&
ext4_should_order_data(inode)) {
if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
ret = ext4_jbd2_inode_add_wait(handle, inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 0c21e22acd74..dde8deb11e59 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -218,7 +218,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
unsigned int jflag;
/* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode))
+ if (ext4_is_quota_file(inode))
goto flags_out;
oldflags = ei->i_flags;
@@ -342,7 +342,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
err = -EPERM;
inode_lock(inode);
/* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode))
+ if (ext4_is_quota_file(inode))
goto out_unlock;
err = ext4_get_inode_loc(inode, &iloc);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b7928cddd539..d109a2a2fea0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4464,7 +4464,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
trace_ext4_request_blocks(ar);
/* Allow to use superuser reservation for quota file */
- if (IS_NOQUOTA(ar->inode))
+ if (ext4_is_quota_file(ar->inode))
ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) {
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index c992ef2c2f94..9bb36909ec92 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -484,7 +484,7 @@ mext_check_arguments(struct inode *orig_inode,
return -EBUSY;
}
- if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
+ if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) {
ext4_debug("ext4 move extent: The argument files should "
"not be quota files [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
2017-06-22 1:49 ` [PATCH 25/32] ext4: add ext4_is_quota_file() Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:43 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 27/32] ext4: xattr inode deduplication Tahsin Erdogan
` (6 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
During inode deletion, journal credits that will be needed are hard to
determine, that is why we have journal extend/restart calls in several
places. Whenever a transaction is restarted, filesystem must be in a
consistent state because there is no atomicity guarantee beyond a
restart call.
Add ext4_xattr_ensure_credits() helper function which takes care of
journal extend/restart logic. It also handles getting jbd2 write access
and dirty metadata calls. This function is called at every iteration of
handling an ea_inode reference.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v3: fixed checkpatch.pl warnings about long lines and indented label
v2: made ext4_xattr_ensure_credits() static
fs/ext4/inode.c | 66 ++++-----------
fs/ext4/xattr.c | 258 ++++++++++++++++++++++++++++++++++++--------------------
fs/ext4/xattr.h | 3 +-
3 files changed, 184 insertions(+), 143 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cf91532765a4..cd007f9757d1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -239,7 +239,11 @@ void ext4_evict_inode(struct inode *inode)
*/
sb_start_intwrite(inode->i_sb);
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, extra_credits);
+ if (!IS_NOQUOTA(inode))
+ extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
+
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
+ ext4_blocks_for_truncate(inode)+extra_credits);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -251,36 +255,9 @@ void ext4_evict_inode(struct inode *inode)
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
+
if (IS_SYNC(inode))
ext4_handle_sync(handle);
-
- /*
- * Delete xattr inode before deleting the main inode.
- */
- err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array);
- if (err) {
- ext4_warning(inode->i_sb,
- "couldn't delete inode's xattr (err %d)", err);
- goto stop_handle;
- }
-
- if (!IS_NOQUOTA(inode))
- extra_credits += 2 * EXT4_QUOTA_DEL_BLOCKS(inode->i_sb);
-
- if (!ext4_handle_has_enough_credits(handle,
- ext4_blocks_for_truncate(inode) + extra_credits)) {
- err = ext4_journal_extend(handle,
- ext4_blocks_for_truncate(inode) + extra_credits);
- if (err > 0)
- err = ext4_journal_restart(handle,
- ext4_blocks_for_truncate(inode) + extra_credits);
- if (err != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", err);
- goto stop_handle;
- }
- }
-
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
@@ -298,25 +275,17 @@ void ext4_evict_inode(struct inode *inode)
}
}
- /*
- * ext4_ext_truncate() doesn't reserve any slop when it
- * restarts journal transactions; therefore there may not be
- * enough credits left in the handle to remove the inode from
- * the orphan list and set the dtime field.
- */
- if (!ext4_handle_has_enough_credits(handle, extra_credits)) {
- err = ext4_journal_extend(handle, extra_credits);
- if (err > 0)
- err = ext4_journal_restart(handle, extra_credits);
- if (err != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", err);
- stop_handle:
- ext4_journal_stop(handle);
- ext4_orphan_del(NULL, inode);
- sb_end_intwrite(inode->i_sb);
- goto no_delete;
- }
+ /* Remove xattr references. */
+ err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array,
+ extra_credits);
+ if (err) {
+ ext4_warning(inode->i_sb, "xattr delete (err %d)", err);
+stop_handle:
+ ext4_journal_stop(handle);
+ ext4_orphan_del(NULL, inode);
+ sb_end_intwrite(inode->i_sb);
+ ext4_xattr_inode_array_free(ea_inode_array);
+ goto no_delete;
}
/*
@@ -342,7 +311,6 @@ void ext4_evict_inode(struct inode *inode)
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
-
ext4_journal_stop(handle);
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fd73dbc92c21..94f04b9fb421 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -108,6 +108,10 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
#define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \
inode->i_sb->s_fs_info)->s_ea_block_cache)
+static int
+ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
+ struct inode *inode);
+
#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
{
@@ -652,6 +656,128 @@ static void ext4_xattr_update_super_block(handle_t *handle,
}
}
+static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
+ int credits, struct buffer_head *bh,
+ bool dirty, bool block_csum)
+{
+ int error;
+
+ if (!ext4_handle_valid(handle))
+ return 0;
+
+ if (handle->h_buffer_credits >= credits)
+ return 0;
+
+ error = ext4_journal_extend(handle, credits - handle->h_buffer_credits);
+ if (!error)
+ return 0;
+ if (error < 0) {
+ ext4_warning(inode->i_sb, "Extend journal (error %d)", error);
+ return error;
+ }
+
+ if (bh && dirty) {
+ if (block_csum)
+ ext4_xattr_block_csum_set(inode, bh);
+ error = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (error) {
+ ext4_warning(inode->i_sb, "Handle metadata (error %d)",
+ error);
+ return error;
+ }
+ }
+
+ error = ext4_journal_restart(handle, credits);
+ if (error) {
+ ext4_warning(inode->i_sb, "Restart journal (error %d)", error);
+ return error;
+ }
+
+ if (bh) {
+ error = ext4_journal_get_write_access(handle, bh);
+ if (error) {
+ ext4_warning(inode->i_sb,
+ "Get write access failed (error %d)",
+ error);
+ return error;
+ }
+ }
+ return 0;
+}
+
+static void
+ext4_xattr_inode_remove_all(handle_t *handle, struct inode *parent,
+ struct buffer_head *bh,
+ struct ext4_xattr_entry *first, bool block_csum,
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
+{
+ struct inode *ea_inode;
+ struct ext4_xattr_entry *entry;
+ bool dirty = false;
+ unsigned int ea_ino;
+ int err;
+ int credits;
+
+ /* One credit for dec ref on ea_inode, one for orphan list addition, */
+ credits = 2 + extra_credits;
+
+ for (entry = first; !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry)) {
+ if (!entry->e_value_inum)
+ continue;
+ ea_ino = le32_to_cpu(entry->e_value_inum);
+ err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+ if (err)
+ continue;
+
+ err = ext4_expand_inode_array(ea_inode_array, ea_inode);
+ if (err) {
+ ext4_warning_inode(ea_inode,
+ "Expand inode array err=%d", err);
+ iput(ea_inode);
+ continue;
+ }
+
+ err = ext4_xattr_ensure_credits(handle, parent, credits, bh,
+ dirty, block_csum);
+ if (err) {
+ ext4_warning_inode(ea_inode, "Ensure credits err=%d",
+ err);
+ continue;
+ }
+
+ inode_lock(ea_inode);
+ clear_nlink(ea_inode);
+ ext4_orphan_add(handle, ea_inode);
+ inode_unlock(ea_inode);
+
+ /*
+ * Forget about ea_inode within the same transaction that
+ * decrements the ref count. This avoids duplicate decrements in
+ * case the rest of the work spills over to subsequent
+ * transactions.
+ */
+ entry->e_value_inum = 0;
+ entry->e_value_size = 0;
+
+ dirty = true;
+ }
+
+ if (dirty) {
+ /*
+ * Note that we are deliberately skipping csum calculation for
+ * the final update because we do not expect any journal
+ * restarts until xattr block is freed.
+ */
+
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ ext4_warning_inode(parent,
+ "handle dirty metadata err=%d", err);
+ }
+}
+
/*
* Release the xattr block BH: If the reference count is > 1, decrement it;
* otherwise free the block.
@@ -1984,42 +2110,6 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
return 0;
}
-/**
- * Add xattr inode to orphan list
- */
-static int
-ext4_xattr_inode_orphan_add(handle_t *handle, struct inode *inode, int credits,
- struct ext4_xattr_inode_array *ea_inode_array)
-{
- int idx = 0, error = 0;
- struct inode *ea_inode;
-
- if (ea_inode_array == NULL)
- return 0;
-
- for (; idx < ea_inode_array->count; ++idx) {
- if (!ext4_handle_has_enough_credits(handle, credits)) {
- error = ext4_journal_extend(handle, credits);
- if (error > 0)
- error = ext4_journal_restart(handle, credits);
-
- if (error != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal "
- "(err %d)", error);
- return error;
- }
- }
- ea_inode = ea_inode_array->inodes[idx];
- inode_lock(ea_inode);
- ext4_orphan_add(handle, ea_inode);
- inode_unlock(ea_inode);
- /* the inode's i_count will be released by caller */
- }
-
- return 0;
-}
-
/*
* ext4_xattr_delete_inode()
*
@@ -2032,16 +2122,23 @@ ext4_xattr_inode_orphan_add(handle_t *handle, struct inode *inode, int credits,
*/
int
ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
- struct ext4_xattr_inode_array **ea_inode_array)
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
{
struct buffer_head *bh = NULL;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
- struct ext4_iloc iloc;
- struct ext4_xattr_entry *entry;
- struct inode *ea_inode;
- unsigned int ea_ino;
- int credits = 3, error = 0;
+ struct ext4_iloc iloc = { .bh = NULL };
+ int error;
+
+ error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
+ NULL /* bh */,
+ false /* dirty */,
+ false /* block_csum */);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error);
+ goto cleanup;
+ }
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
goto delete_external_ea;
@@ -2049,31 +2146,20 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
error = ext4_get_inode_loc(inode, &iloc);
if (error)
goto cleanup;
+
+ error = ext4_journal_get_write_access(handle, iloc.bh);
+ if (error)
+ goto cleanup;
+
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
- for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
- entry = EXT4_XATTR_NEXT(entry)) {
- if (!entry->e_value_inum)
- continue;
- ea_ino = le32_to_cpu(entry->e_value_inum);
- error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (error)
- continue;
- error = ext4_expand_inode_array(ea_inode_array, ea_inode);
- if (error) {
- iput(ea_inode);
- brelse(iloc.bh);
- goto cleanup;
- }
- entry->e_value_inum = 0;
- }
- brelse(iloc.bh);
+ ext4_xattr_inode_remove_all(handle, inode, iloc.bh, IFIRST(header),
+ false /* block_csum */, ea_inode_array,
+ extra_credits);
delete_external_ea:
if (!EXT4_I(inode)->i_file_acl) {
- /* add xattr inode to orphan list */
- error = ext4_xattr_inode_orphan_add(handle, inode, credits,
- *ea_inode_array);
+ error = 0;
goto cleanup;
}
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
@@ -2091,46 +2177,32 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
goto cleanup;
}
- for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
- entry = EXT4_XATTR_NEXT(entry)) {
- if (!entry->e_value_inum)
- continue;
- ea_ino = le32_to_cpu(entry->e_value_inum);
- error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (error)
- continue;
- error = ext4_expand_inode_array(ea_inode_array, ea_inode);
- if (error)
- goto cleanup;
- entry->e_value_inum = 0;
- }
-
- /* add xattr inode to orphan list */
- error = ext4_xattr_inode_orphan_add(handle, inode, credits,
- *ea_inode_array);
- if (error)
- goto cleanup;
-
- if (!IS_NOQUOTA(inode))
- credits += 2 * EXT4_QUOTA_DEL_BLOCKS(inode->i_sb);
-
- if (!ext4_handle_has_enough_credits(handle, credits)) {
- error = ext4_journal_extend(handle, credits);
- if (error > 0)
- error = ext4_journal_restart(handle, credits);
+ if (ext4_has_feature_ea_inode(inode->i_sb)) {
+ error = ext4_journal_get_write_access(handle, bh);
if (error) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", error);
+ EXT4_ERROR_INODE(inode, "write access %llu",
+ EXT4_I(inode)->i_file_acl);
goto cleanup;
}
+ ext4_xattr_inode_remove_all(handle, inode, bh,
+ BFIRST(bh),
+ true /* block_csum */,
+ ea_inode_array,
+ extra_credits);
}
ext4_xattr_release_block(handle, inode, bh);
+ /* Update i_file_acl within the same transaction that releases block. */
EXT4_I(inode)->i_file_acl = 0;
-
+ error = ext4_mark_inode_dirty(handle, inode);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
+ error);
+ goto cleanup;
+ }
cleanup:
+ brelse(iloc.bh);
brelse(bh);
-
return error;
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index adf761518a73..b2005a2716d9 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -169,7 +169,8 @@ extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len);
extern int ext4_xattr_inode_unlink(struct inode *inode, unsigned long ea_ino);
extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
- struct ext4_xattr_inode_array **array);
+ struct ext4_xattr_inode_array **array,
+ int extra_credits);
extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 27/32] ext4: xattr inode deduplication
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
2017-06-22 1:49 ` [PATCH 25/32] ext4: add ext4_is_quota_file() Tahsin Erdogan
2017-06-22 1:49 ` [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:45 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges Tahsin Erdogan
` (5 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
Ext4 now supports xattr values that are up to 64k in size (vfs limit).
Large xattr values are stored in external inodes each one holding a
single value. Once written the data blocks of these inodes are immutable.
The real world use cases are expected to have a lot of value duplication
such as inherited acls etc. To reduce data duplication on disk, this patch
implements a deduplicator that allows sharing of xattr inodes.
The deduplication is based on an in-memory hash lookup that is a best
effort sharing scheme. When a xattr inode is read from disk (i.e.
getxattr() call), its crc32c hash is added to a hash table. Before
creating a new xattr inode for a value being set, the hash table is
checked to see if an existing inode holds an identical value. If such an
inode is found, the ref count on that inode is incremented. On value
removal the ref count is decremented and if it reaches zero the inode is
deleted.
The quota charging for such inodes is manually managed. Every reference
holder is charged the full size as if there was no sharing happening.
This is consistent with how xattr blocks are also charged.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v6:
- Fixed error message "Failed to create an s_ea_inode_cache"
v5:
- made ext4_meta_trans_blocks() static again since there are no
remaining users outside of inode.c
- initialize sbi->s_csum_seed when ea_inode feature is enabled
- use l_i_version to hold lower 32 bits of the xattr ref count.
This avoids clashes with old implementations which use i_mtime.
Since l_i_version is not available in HURD_COMPAT mode, fail mount
request when both ea_inode feature and HURD_COMPAT are set.
- when hash validation fails, fall back to old implementation
which has a backref to parent.
- fixed checkpatch.pl warning about using unsigned alone
v4:
- eliminated xattr entry in the xattr inode to avoid complexity and
recursion in xattr update path. Now the ref count and hash are stored
in i_[c/m/a]time.tv_sec fields.
- some clean up in ext4_xattr_set_entry() to reduce code duplication and
complexity
v3:
- use s_csum_seed for hash calculations when available
- return error on stored vs calculated hash mismatch
v2:
- make dependency on crc32c dynamic
- update ext4_has_metadata_csum() and ext4_has_group_desc_csum() so that
they do not misinterpret existence of EXT4_SB(sb)->s_chksum_driver
fs/ext4/acl.c | 5 +-
fs/ext4/ext4.h | 23 +-
fs/ext4/inode.c | 13 +-
fs/ext4/super.c | 37 +-
fs/ext4/xattr.c | 1038 +++++++++++++++++++++++++++++++++++++++++--------------
fs/ext4/xattr.h | 17 +-
fs/mbcache.c | 9 +-
7 files changed, 848 insertions(+), 294 deletions(-)
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 74f7ac539e00..8db03e5c78bc 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -238,7 +238,10 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
if (error)
return error;
retry:
- credits = ext4_xattr_set_credits(inode, acl_size);
+ error = ext4_xattr_set_credits(inode, acl_size, &credits);
+ if (error)
+ return error;
+
handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 3b02bd897b61..dc06287ddec8 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1517,6 +1517,7 @@ struct ext4_sb_info {
long s_es_nr_inode;
struct ext4_es_stats s_es_stats;
struct mb_cache *s_ea_block_cache;
+ struct mb_cache *s_ea_inode_cache;
spinlock_t s_es_lock ____cacheline_aligned_in_smp;
/* Ratelimit ext4 messages. */
@@ -2099,7 +2100,11 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
}
-#define ext4_is_quota_file(inode) IS_NOQUOTA(inode)
+static inline bool ext4_is_quota_file(struct inode *inode)
+{
+ return IS_NOQUOTA(inode) &&
+ !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
+}
/*
* This structure is stuffed into the struct file's private_data field
@@ -2482,7 +2487,6 @@ extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
extern void ext4_set_inode_flags(struct inode *);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
-extern int ext4_meta_trans_blocks(struct inode *, int nrblocks, int chunk);
extern int ext4_writepage_trans_blocks(struct inode *);
extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
@@ -2709,19 +2713,20 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
extern int ext4_register_li_request(struct super_block *sb,
ext4_group_t first_not_zeroed);
-static inline int ext4_has_group_desc_csum(struct super_block *sb)
-{
- return ext4_has_feature_gdt_csum(sb) ||
- EXT4_SB(sb)->s_chksum_driver != NULL;
-}
-
static inline int ext4_has_metadata_csum(struct super_block *sb)
{
WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
!EXT4_SB(sb)->s_chksum_driver);
- return (EXT4_SB(sb)->s_chksum_driver != NULL);
+ return ext4_has_feature_metadata_csum(sb) &&
+ (EXT4_SB(sb)->s_chksum_driver != NULL);
}
+
+static inline int ext4_has_group_desc_csum(struct super_block *sb)
+{
+ return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
+}
+
static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
{
return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cd007f9757d1..ea95bd9eab81 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -139,6 +139,8 @@ static void ext4_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
static int __ext4_journalled_writepage(struct page *page, unsigned int len);
static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh);
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+ int pextents);
/*
* Test whether an inode is a fast symlink.
@@ -4843,8 +4845,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
}
brelse(iloc.bh);
ext4_set_inode_flags(inode);
- if (ei->i_flags & EXT4_EA_INODE_FL)
+
+ if (ei->i_flags & EXT4_EA_INODE_FL) {
ext4_xattr_inode_set_class(inode);
+
+ inode_lock(inode);
+ inode->i_flags |= S_NOQUOTA;
+ inode_unlock(inode);
+ }
+
unlock_new_inode(inode);
return inode;
@@ -5503,7 +5512,7 @@ static int ext4_index_trans_blocks(struct inode *inode, int lblocks,
*
* Also account for superblock, inode, quota and xattr blocks
*/
-int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
+static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
int pextents)
{
ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 380389740575..d501f8256dc4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -927,6 +927,10 @@ static void ext4_put_super(struct super_block *sb)
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
+ if (sbi->s_ea_inode_cache) {
+ ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+ sbi->s_ea_inode_cache = NULL;
+ }
if (sbi->s_ea_block_cache) {
ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
sbi->s_ea_block_cache = NULL;
@@ -1178,7 +1182,10 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
if (res)
return res;
retry:
- credits = ext4_xattr_set_credits(inode, len);
+ res = ext4_xattr_set_credits(inode, len, &credits);
+ if (res)
+ return res;
+
handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -3445,7 +3452,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
/* Load the checksum driver */
- if (ext4_has_feature_metadata_csum(sb)) {
+ if (ext4_has_feature_metadata_csum(sb) ||
+ ext4_has_feature_ea_inode(sb)) {
sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
if (IS_ERR(sbi->s_chksum_driver)) {
ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
@@ -3467,7 +3475,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
/* Precompute checksum seed for all metadata */
if (ext4_has_feature_csum_seed(sb))
sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed);
- else if (ext4_has_metadata_csum(sb))
+ else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb))
sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
sizeof(es->s_uuid));
@@ -3597,6 +3605,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"The Hurd can't support 64-bit file systems");
goto failed_mount;
}
+
+ /*
+ * ea_inode feature uses l_i_version field which is not
+ * available in HURD_COMPAT mode.
+ */
+ if (ext4_has_feature_ea_inode(sb)) {
+ ext4_msg(sb, KERN_ERR,
+ "ea_inode feature is not supported for Hurd");
+ goto failed_mount;
+ }
}
if (IS_EXT2_SB(sb)) {
@@ -4067,6 +4085,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount_wq;
}
+ if (ext4_has_feature_ea_inode(sb)) {
+ sbi->s_ea_inode_cache = ext4_xattr_create_cache();
+ if (!sbi->s_ea_inode_cache) {
+ ext4_msg(sb, KERN_ERR,
+ "Failed to create ea_inode_cache");
+ goto failed_mount_wq;
+ }
+ }
+
if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
(blocksize != PAGE_SIZE)) {
ext4_msg(sb, KERN_ERR,
@@ -4296,6 +4323,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (EXT4_SB(sb)->rsv_conversion_wq)
destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
failed_mount_wq:
+ if (sbi->s_ea_inode_cache) {
+ ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+ sbi->s_ea_inode_cache = NULL;
+ }
if (sbi->s_ea_block_cache) {
ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
sbi->s_ea_block_cache = NULL;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 94f04b9fb421..15c9f736dcc4 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -108,6 +108,9 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
#define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \
inode->i_sb->s_fs_info)->s_ea_block_cache)
+#define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \
+ inode->i_sb->s_fs_info)->s_ea_inode_cache)
+
static int
ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
struct inode *inode);
@@ -280,15 +283,44 @@ ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
return cmp ? -ENODATA : 0;
}
+static u32
+ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size)
+{
+ return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size);
+}
+
+static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode)
+{
+ return ((u64)ea_inode->i_ctime.tv_sec << 32) |
+ ((u32)ea_inode->i_version);
+}
+
+static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count)
+{
+ ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32);
+ ea_inode->i_version = (u32)ref_count;
+}
+
+static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode)
+{
+ return (u32)ea_inode->i_atime.tv_sec;
+}
+
+static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash)
+{
+ ea_inode->i_atime.tv_sec = hash;
+}
+
/*
* Read the EA value from an inode.
*/
static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
{
unsigned long block = 0;
- struct buffer_head *bh = NULL;
+ struct buffer_head *bh;
int blocksize = ea_inode->i_sb->s_blocksize;
size_t csize, copied = 0;
+ void *copy_pos = buf;
while (copied < size) {
csize = (size - copied) > blocksize ? blocksize : size - copied;
@@ -298,10 +330,10 @@ static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
if (!bh)
return -EFSCORRUPTED;
- memcpy(buf, bh->b_data, csize);
+ memcpy(copy_pos, bh->b_data, csize);
brelse(bh);
- buf += csize;
+ copy_pos += csize;
block += 1;
copied += csize;
}
@@ -317,29 +349,24 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
inode = ext4_iget(parent->i_sb, ea_ino);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
- ext4_error(parent->i_sb, "error while reading EA inode %lu "
- "err=%d", ea_ino, err);
+ ext4_error(parent->i_sb,
+ "error while reading EA inode %lu err=%d", ea_ino,
+ err);
return err;
}
if (is_bad_inode(inode)) {
- ext4_error(parent->i_sb, "error while reading EA inode %lu "
- "is_bad_inode", ea_ino);
+ ext4_error(parent->i_sb,
+ "error while reading EA inode %lu is_bad_inode",
+ ea_ino);
err = -EIO;
goto error;
}
- if (EXT4_XATTR_INODE_GET_PARENT(inode) != parent->i_ino ||
- inode->i_generation != parent->i_generation) {
- ext4_error(parent->i_sb, "Backpointer from EA inode %lu "
- "to parent is invalid.", ea_ino);
- err = -EINVAL;
- goto error;
- }
-
if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
- ext4_error(parent->i_sb, "EA inode %lu does not have "
- "EXT4_EA_INODE_FL flag set.\n", ea_ino);
+ ext4_error(parent->i_sb,
+ "EA inode %lu does not have EXT4_EA_INODE_FL flag",
+ ea_ino);
err = -EINVAL;
goto error;
}
@@ -351,6 +378,20 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
return err;
}
+static int
+ext4_xattr_inode_verify_hash(struct inode *ea_inode, void *buffer, size_t size)
+{
+ u32 hash;
+
+ /* Verify stored hash matches calculated hash. */
+ hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size);
+ if (hash != ext4_xattr_inode_get_hash(ea_inode))
+ return -EFSCORRUPTED;
+ return 0;
+}
+
+#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec)
+
/*
* Read the value from the EA inode.
*/
@@ -358,17 +399,53 @@ static int
ext4_xattr_inode_get(struct inode *inode, unsigned long ea_ino, void *buffer,
size_t size)
{
+ struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
struct inode *ea_inode;
- int ret;
+ int err;
- ret = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (ret)
- return ret;
+ err = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
+ if (err) {
+ ea_inode = NULL;
+ goto out;
+ }
- ret = ext4_xattr_inode_read(ea_inode, buffer, size);
- iput(ea_inode);
+ if (i_size_read(ea_inode) != size) {
+ ext4_warning_inode(ea_inode,
+ "ea_inode file size=%llu entry size=%zu",
+ i_size_read(ea_inode), size);
+ err = -EFSCORRUPTED;
+ goto out;
+ }
- return ret;
+ err = ext4_xattr_inode_read(ea_inode, buffer, size);
+ if (err)
+ goto out;
+
+ err = ext4_xattr_inode_verify_hash(ea_inode, buffer, size);
+ /*
+ * Compatibility check for old Lustre ea_inode implementation. Old
+ * version does not have hash validation, but it has a backpointer
+ * from ea_inode to the parent inode.
+ */
+ if (err == -EFSCORRUPTED) {
+ if (EXT4_XATTR_INODE_GET_PARENT(ea_inode) != inode->i_ino ||
+ ea_inode->i_generation != inode->i_generation) {
+ ext4_warning_inode(ea_inode,
+ "EA inode hash validation failed");
+ goto out;
+ }
+ /* Do not add ea_inode to the cache. */
+ ea_inode_cache = NULL;
+ } else if (err)
+ goto out;
+
+ if (ea_inode_cache)
+ mb_cache_entry_create(ea_inode_cache, GFP_NOFS,
+ ext4_xattr_inode_get_hash(ea_inode),
+ ea_inode->i_ino, true /* reusable */);
+out:
+ iput(ea_inode);
+ return err;
}
static int
@@ -656,6 +733,101 @@ static void ext4_xattr_update_super_block(handle_t *handle,
}
}
+static inline size_t round_up_cluster(struct inode *inode, size_t length)
+{
+ struct super_block *sb = inode->i_sb;
+ size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits +
+ inode->i_blkbits);
+ size_t mask = ~(cluster_size - 1);
+
+ return (length + cluster_size - 1) & mask;
+}
+
+static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len)
+{
+ int err;
+
+ err = dquot_alloc_inode(inode);
+ if (err)
+ return err;
+ err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len));
+ if (err)
+ dquot_free_inode(inode);
+ return err;
+}
+
+static void ext4_xattr_inode_free_quota(struct inode *inode, size_t len)
+{
+ dquot_free_space_nodirty(inode, round_up_cluster(inode, len));
+ dquot_free_inode(inode);
+}
+
+static int __ext4_xattr_set_credits(struct super_block *sb,
+ struct buffer_head *block_bh,
+ size_t value_len)
+{
+ int credits;
+ int blocks;
+
+ /*
+ * 1) Owner inode update
+ * 2) Ref count update on old xattr block
+ * 3) new xattr block
+ * 4) block bitmap update for new xattr block
+ * 5) group descriptor for new xattr block
+ */
+ credits = 5;
+
+ /* We are done if ea_inode feature is not enabled. */
+ if (!ext4_has_feature_ea_inode(sb))
+ return credits;
+
+ /* New ea_inode, inode map, block bitmap, group descriptor. */
+ credits += 4;
+
+ /* Data blocks. */
+ blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+
+ /* Indirection block or one level of extent tree. */
+ blocks += 1;
+
+ /* Block bitmap and group descriptor updates for each block. */
+ credits += blocks * 2;
+
+ /* Blocks themselves. */
+ credits += blocks;
+
+ /* Dereference ea_inode holding old xattr value.
+ * Old ea_inode, inode map, block bitmap, group descriptor.
+ */
+ credits += 4;
+
+ /* Data blocks for old ea_inode. */
+ blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits;
+
+ /* Indirection block or one level of extent tree for old ea_inode. */
+ blocks += 1;
+
+ /* Block bitmap and group descriptor updates for each block. */
+ credits += blocks * 2;
+
+ /* Quota updates. */
+ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb);
+
+ /* We may need to clone the existing xattr block in which case we need
+ * to increment ref counts for existing ea_inodes referenced by it.
+ */
+ if (block_bh) {
+ struct ext4_xattr_entry *entry = BFIRST(block_bh);
+
+ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry))
+ if (entry->e_value_inum)
+ /* Ref count update on ea_inode. */
+ credits += 1;
+ }
+ return credits;
+}
+
static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
int credits, struct buffer_head *bh,
bool dirty, bool block_csum)
@@ -705,12 +877,140 @@ static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
return 0;
}
+static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
+ int ref_change)
+{
+ struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
+ struct ext4_iloc iloc;
+ s64 ref_count;
+ u32 hash;
+ int ret;
+
+ inode_lock(ea_inode);
+
+ ret = ext4_reserve_inode_write(handle, ea_inode, &iloc);
+ if (ret) {
+ iloc.bh = NULL;
+ goto out;
+ }
+
+ ref_count = ext4_xattr_inode_get_ref(ea_inode);
+ ref_count += ref_change;
+ ext4_xattr_inode_set_ref(ea_inode, ref_count);
+
+ if (ref_change > 0) {
+ WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld",
+ ea_inode->i_ino, ref_count);
+
+ if (ref_count == 1) {
+ WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u",
+ ea_inode->i_ino, ea_inode->i_nlink);
+
+ set_nlink(ea_inode, 1);
+ ext4_orphan_del(handle, ea_inode);
+
+ hash = ext4_xattr_inode_get_hash(ea_inode);
+ mb_cache_entry_create(ea_inode_cache, GFP_NOFS, hash,
+ ea_inode->i_ino,
+ true /* reusable */);
+ }
+ } else {
+ WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
+ ea_inode->i_ino, ref_count);
+
+ if (ref_count == 0) {
+ WARN_ONCE(ea_inode->i_nlink != 1,
+ "EA inode %lu i_nlink=%u",
+ ea_inode->i_ino, ea_inode->i_nlink);
+
+ clear_nlink(ea_inode);
+ ext4_orphan_add(handle, ea_inode);
+
+ hash = ext4_xattr_inode_get_hash(ea_inode);
+ mb_cache_entry_delete(ea_inode_cache, hash,
+ ea_inode->i_ino);
+ }
+ }
+
+ ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc);
+ iloc.bh = NULL;
+ if (ret)
+ ext4_warning_inode(ea_inode,
+ "ext4_mark_iloc_dirty() failed ret=%d", ret);
+out:
+ brelse(iloc.bh);
+ inode_unlock(ea_inode);
+ return ret;
+}
+
+static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode)
+{
+ return ext4_xattr_inode_update_ref(handle, ea_inode, 1);
+}
+
+static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode)
+{
+ return ext4_xattr_inode_update_ref(handle, ea_inode, -1);
+}
+
+static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent,
+ struct ext4_xattr_entry *first)
+{
+ struct inode *ea_inode;
+ struct ext4_xattr_entry *entry;
+ struct ext4_xattr_entry *failed_entry;
+ unsigned int ea_ino;
+ int err, saved_err;
+
+ for (entry = first; !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry)) {
+ if (!entry->e_value_inum)
+ continue;
+ ea_ino = le32_to_cpu(entry->e_value_inum);
+ err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+ if (err)
+ goto cleanup;
+ err = ext4_xattr_inode_inc_ref(handle, ea_inode);
+ if (err) {
+ ext4_warning_inode(ea_inode, "inc ref error %d", err);
+ iput(ea_inode);
+ goto cleanup;
+ }
+ iput(ea_inode);
+ }
+ return 0;
+
+cleanup:
+ saved_err = err;
+ failed_entry = entry;
+
+ for (entry = first; entry != failed_entry;
+ entry = EXT4_XATTR_NEXT(entry)) {
+ if (!entry->e_value_inum)
+ continue;
+ ea_ino = le32_to_cpu(entry->e_value_inum);
+ err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+ if (err) {
+ ext4_warning(parent->i_sb,
+ "cleanup ea_ino %u iget error %d", ea_ino,
+ err);
+ continue;
+ }
+ err = ext4_xattr_inode_dec_ref(handle, ea_inode);
+ if (err)
+ ext4_warning_inode(ea_inode, "cleanup dec ref error %d",
+ err);
+ iput(ea_inode);
+ }
+ return saved_err;
+}
+
static void
-ext4_xattr_inode_remove_all(handle_t *handle, struct inode *parent,
- struct buffer_head *bh,
- struct ext4_xattr_entry *first, bool block_csum,
- struct ext4_xattr_inode_array **ea_inode_array,
- int extra_credits)
+ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent,
+ struct buffer_head *bh,
+ struct ext4_xattr_entry *first, bool block_csum,
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits, bool skip_quota)
{
struct inode *ea_inode;
struct ext4_xattr_entry *entry;
@@ -747,10 +1047,16 @@ ext4_xattr_inode_remove_all(handle_t *handle, struct inode *parent,
continue;
}
- inode_lock(ea_inode);
- clear_nlink(ea_inode);
- ext4_orphan_add(handle, ea_inode);
- inode_unlock(ea_inode);
+ err = ext4_xattr_inode_dec_ref(handle, ea_inode);
+ if (err) {
+ ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d",
+ err);
+ continue;
+ }
+
+ if (!skip_quota)
+ ext4_xattr_inode_free_quota(parent,
+ le32_to_cpu(entry->e_value_size));
/*
* Forget about ea_inode within the same transaction that
@@ -784,7 +1090,9 @@ ext4_xattr_inode_remove_all(handle_t *handle, struct inode *parent,
*/
static void
ext4_xattr_release_block(handle_t *handle, struct inode *inode,
- struct buffer_head *bh)
+ struct buffer_head *bh,
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
{
struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
u32 hash, ref;
@@ -807,6 +1115,14 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
mb_cache_entry_delete(ea_block_cache, hash, bh->b_blocknr);
get_bh(bh);
unlock_buffer(bh);
+
+ if (ext4_has_feature_ea_inode(inode->i_sb))
+ ext4_xattr_inode_dec_ref_all(handle, inode, bh,
+ BFIRST(bh),
+ true /* block_csum */,
+ ea_inode_array,
+ extra_credits,
+ true /* skip_quota */);
ext4_free_blocks(handle, inode, bh, 0, 1,
EXT4_FREE_BLOCKS_METADATA |
EXT4_FREE_BLOCKS_FORGET);
@@ -878,8 +1194,8 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
{
struct buffer_head *bh = NULL;
unsigned long block = 0;
- unsigned blocksize = ea_inode->i_sb->s_blocksize;
- unsigned max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
+ int blocksize = ea_inode->i_sb->s_blocksize;
+ int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
int csize, wsize = 0;
int ret = 0;
int retries = 0;
@@ -947,7 +1263,7 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
* Create an inode to store the value of a large EA.
*/
static struct inode *ext4_xattr_inode_create(handle_t *handle,
- struct inode *inode)
+ struct inode *inode, u32 hash)
{
struct inode *ea_inode = NULL;
uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
@@ -965,67 +1281,115 @@ static struct inode *ext4_xattr_inode_create(handle_t *handle,
ea_inode->i_fop = &ext4_file_operations;
ext4_set_aops(ea_inode);
ext4_xattr_inode_set_class(ea_inode);
- ea_inode->i_generation = inode->i_generation;
- EXT4_I(ea_inode)->i_flags |= EXT4_EA_INODE_FL;
-
- /*
- * A back-pointer from EA inode to parent inode will be useful
- * for e2fsck.
- */
- EXT4_XATTR_INODE_SET_PARENT(ea_inode, inode->i_ino);
unlock_new_inode(ea_inode);
- err = ext4_inode_attach_jinode(ea_inode);
+ ext4_xattr_inode_set_ref(ea_inode, 1);
+ ext4_xattr_inode_set_hash(ea_inode, hash);
+ err = ext4_mark_inode_dirty(handle, ea_inode);
+ if (!err)
+ err = ext4_inode_attach_jinode(ea_inode);
if (err) {
iput(ea_inode);
return ERR_PTR(err);
}
+
+ /*
+ * Xattr inodes are shared therefore quota charging is performed
+ * at a higher level.
+ */
+ dquot_free_inode(ea_inode);
+ dquot_drop(ea_inode);
+ inode_lock(ea_inode);
+ ea_inode->i_flags |= S_NOQUOTA;
+ inode_unlock(ea_inode);
}
return ea_inode;
}
-/*
- * Unlink the inode storing the value of the EA.
- */
-int ext4_xattr_inode_unlink(struct inode *inode, unsigned long ea_ino)
+static struct inode *
+ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
+ size_t value_len, u32 hash)
{
- struct inode *ea_inode = NULL;
- int err;
+ struct inode *ea_inode;
+ struct mb_cache_entry *ce;
+ struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
+ void *ea_data;
- err = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (err)
- return err;
+ ce = mb_cache_entry_find_first(ea_inode_cache, hash);
+ if (!ce)
+ return NULL;
- clear_nlink(ea_inode);
- iput(ea_inode);
+ ea_data = ext4_kvmalloc(value_len, GFP_NOFS);
+ if (!ea_data) {
+ mb_cache_entry_put(ea_inode_cache, ce);
+ return NULL;
+ }
- return 0;
+ while (ce) {
+ ea_inode = ext4_iget(inode->i_sb, ce->e_value);
+ if (!IS_ERR(ea_inode) &&
+ !is_bad_inode(ea_inode) &&
+ (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) &&
+ i_size_read(ea_inode) == value_len &&
+ !ext4_xattr_inode_read(ea_inode, ea_data, value_len) &&
+ !ext4_xattr_inode_verify_hash(ea_inode, ea_data,
+ value_len) &&
+ !memcmp(value, ea_data, value_len)) {
+ mb_cache_entry_touch(ea_inode_cache, ce);
+ mb_cache_entry_put(ea_inode_cache, ce);
+ kvfree(ea_data);
+ return ea_inode;
+ }
+
+ if (!IS_ERR(ea_inode))
+ iput(ea_inode);
+ ce = mb_cache_entry_find_next(ea_inode_cache, ce);
+ }
+ kvfree(ea_data);
+ return NULL;
}
/*
* Add value of the EA in an inode.
*/
-static int ext4_xattr_inode_set(handle_t *handle, struct inode *inode,
- unsigned long *ea_ino, const void *value,
- size_t value_len)
+static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
+ const void *value, size_t value_len,
+ struct inode **ret_inode)
{
struct inode *ea_inode;
+ u32 hash;
int err;
+ hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len);
+ ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash);
+ if (ea_inode) {
+ err = ext4_xattr_inode_inc_ref(handle, ea_inode);
+ if (err) {
+ iput(ea_inode);
+ return err;
+ }
+
+ *ret_inode = ea_inode;
+ return 0;
+ }
+
/* Create an inode for the EA value */
- ea_inode = ext4_xattr_inode_create(handle, inode);
+ ea_inode = ext4_xattr_inode_create(handle, inode, hash);
if (IS_ERR(ea_inode))
return PTR_ERR(ea_inode);
err = ext4_xattr_inode_write(handle, ea_inode, value, value_len);
- if (err)
- clear_nlink(ea_inode);
- else
- *ea_ino = ea_inode->i_ino;
+ if (err) {
+ ext4_xattr_inode_dec_ref(handle, ea_inode);
+ iput(ea_inode);
+ return err;
+ }
- iput(ea_inode);
+ mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
+ ea_inode->i_ino, true /* reusable */);
- return err;
+ *ret_inode = ea_inode;
+ return 0;
}
static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
@@ -1033,9 +1397,37 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
handle_t *handle, struct inode *inode)
{
struct ext4_xattr_entry *last;
- size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
+ struct ext4_xattr_entry *here = s->here;
+ size_t min_offs = s->end - s->base, name_len = strlen(i->name);
int in_inode = i->in_inode;
- int rc;
+ struct inode *old_ea_inode = NULL;
+ struct inode *new_ea_inode = NULL;
+ size_t old_size, new_size;
+ int ret;
+
+ /* Space used by old and new values. */
+ old_size = (!s->not_found && !here->e_value_inum) ?
+ EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0;
+ new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0;
+
+ /*
+ * Optimization for the simple case when old and new values have the
+ * same padded sizes. Not applicable if external inodes are involved.
+ */
+ if (new_size && new_size == old_size) {
+ size_t offs = le16_to_cpu(here->e_value_offs);
+ void *val = s->base + offs;
+
+ here->e_value_size = cpu_to_le32(i->value_len);
+ if (i->value == EXT4_ZERO_XATTR_VALUE) {
+ memset(val, 0, new_size);
+ } else {
+ memcpy(val, i->value, i->value_len);
+ /* Clear padding bytes. */
+ memset(val + i->value_len, 0, new_size - i->value_len);
+ }
+ return 0;
+ }
/* Compute min_offs and last. */
last = s->first;
@@ -1046,122 +1438,148 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
min_offs = offs;
}
}
- free = min_offs - ((void *)last - s->base) - sizeof(__u32);
- if (!s->not_found) {
- if (!in_inode &&
- !s->here->e_value_inum && s->here->e_value_size) {
- size_t size = le32_to_cpu(s->here->e_value_size);
- free += EXT4_XATTR_SIZE(size);
- }
- free += EXT4_XATTR_LEN(name_len);
- }
+
+ /* Check whether we have enough space. */
if (i->value) {
- size_t value_len = EXT4_XATTR_SIZE(i->value_len);
+ size_t free;
- if (in_inode)
- value_len = 0;
+ free = min_offs - ((void *)last - s->base) - sizeof(__u32);
+ if (!s->not_found)
+ free += EXT4_XATTR_LEN(name_len) + old_size;
- if (free < EXT4_XATTR_LEN(name_len) + value_len)
- return -ENOSPC;
+ if (free < EXT4_XATTR_LEN(name_len) + new_size) {
+ ret = -ENOSPC;
+ goto out;
+ }
}
- if (i->value && s->not_found) {
- /* Insert the new name. */
- size_t size = EXT4_XATTR_LEN(name_len);
- size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
- memmove((void *)s->here + size, s->here, rest);
- memset(s->here, 0, size);
- s->here->e_name_index = i->name_index;
- s->here->e_name_len = name_len;
- memcpy(s->here->e_name, i->name, name_len);
- } else {
- if (!s->here->e_value_inum && s->here->e_value_size &&
- s->here->e_value_offs > 0) {
- void *first_val = s->base + min_offs;
- size_t offs = le16_to_cpu(s->here->e_value_offs);
- void *val = s->base + offs;
- size_t size = EXT4_XATTR_SIZE(
- le32_to_cpu(s->here->e_value_size));
-
- if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
- /* The old and the new value have the same
- size. Just replace. */
- s->here->e_value_size =
- cpu_to_le32(i->value_len);
- if (i->value == EXT4_ZERO_XATTR_VALUE) {
- memset(val, 0, size);
- } else {
- /* Clear pad bytes first. */
- memset(val + size - EXT4_XATTR_PAD, 0,
- EXT4_XATTR_PAD);
- memcpy(val, i->value, i->value_len);
- }
- return 0;
- }
+ /*
+ * Getting access to old and new ea inodes is subject to failures.
+ * Finish that work before doing any modifications to the xattr data.
+ */
+ if (!s->not_found && here->e_value_inum) {
+ ret = ext4_xattr_inode_iget(inode,
+ le32_to_cpu(here->e_value_inum),
+ &old_ea_inode);
+ if (ret) {
+ old_ea_inode = NULL;
+ goto out;
+ }
+ }
+ if (i->value && in_inode) {
+ WARN_ON_ONCE(!i->value_len);
- /* Remove the old value. */
- memmove(first_val + size, first_val, val - first_val);
- memset(first_val, 0, size);
- s->here->e_value_size = 0;
- s->here->e_value_offs = 0;
- min_offs += size;
-
- /* Adjust all value offsets. */
- last = s->first;
- while (!IS_LAST_ENTRY(last)) {
- size_t o = le16_to_cpu(last->e_value_offs);
- if (!last->e_value_inum &&
- last->e_value_size && o < offs)
- last->e_value_offs =
- cpu_to_le16(o + size);
- last = EXT4_XATTR_NEXT(last);
- }
+ ret = ext4_xattr_inode_alloc_quota(inode, i->value_len);
+ if (ret)
+ goto out;
+
+ ret = ext4_xattr_inode_lookup_create(handle, inode, i->value,
+ i->value_len,
+ &new_ea_inode);
+ if (ret) {
+ new_ea_inode = NULL;
+ ext4_xattr_inode_free_quota(inode, i->value_len);
+ goto out;
}
- if (s->here->e_value_inum) {
- ext4_xattr_inode_unlink(inode,
- le32_to_cpu(s->here->e_value_inum));
- s->here->e_value_inum = 0;
+ }
+
+ if (old_ea_inode) {
+ /* We are ready to release ref count on the old_ea_inode. */
+ ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode);
+ if (ret) {
+ /* Release newly required ref count on new_ea_inode. */
+ if (new_ea_inode) {
+ int err;
+
+ err = ext4_xattr_inode_dec_ref(handle,
+ new_ea_inode);
+ if (err)
+ ext4_warning_inode(new_ea_inode,
+ "dec ref new_ea_inode err=%d",
+ err);
+ ext4_xattr_inode_free_quota(inode,
+ i->value_len);
+ }
+ goto out;
}
- if (!i->value) {
- /* Remove the old name. */
- size_t size = EXT4_XATTR_LEN(name_len);
- last = ENTRY((void *)last - size);
- memmove(s->here, (void *)s->here + size,
- (void *)last - (void *)s->here + sizeof(__u32));
- memset(last, 0, size);
+
+ ext4_xattr_inode_free_quota(inode,
+ le32_to_cpu(here->e_value_size));
+ }
+
+ /* No failures allowed past this point. */
+
+ if (!s->not_found && here->e_value_offs) {
+ /* Remove the old value. */
+ void *first_val = s->base + min_offs;
+ size_t offs = le16_to_cpu(here->e_value_offs);
+ void *val = s->base + offs;
+
+ memmove(first_val + old_size, first_val, val - first_val);
+ memset(first_val, 0, old_size);
+ min_offs += old_size;
+
+ /* Adjust all value offsets. */
+ last = s->first;
+ while (!IS_LAST_ENTRY(last)) {
+ size_t o = le16_to_cpu(last->e_value_offs);
+
+ if (!last->e_value_inum &&
+ last->e_value_size && o < offs)
+ last->e_value_offs = cpu_to_le16(o + old_size);
+ last = EXT4_XATTR_NEXT(last);
}
}
+ if (!i->value) {
+ /* Remove old name. */
+ size_t size = EXT4_XATTR_LEN(name_len);
+
+ last = ENTRY((void *)last - size);
+ memmove(here, (void *)here + size,
+ (void *)last - (void *)here + sizeof(__u32));
+ memset(last, 0, size);
+ } else if (s->not_found) {
+ /* Insert new name. */
+ size_t size = EXT4_XATTR_LEN(name_len);
+ size_t rest = (void *)last - (void *)here + sizeof(__u32);
+
+ memmove((void *)here + size, here, rest);
+ memset(here, 0, size);
+ here->e_name_index = i->name_index;
+ here->e_name_len = name_len;
+ memcpy(here->e_name, i->name, name_len);
+ } else {
+ /* This is an update, reset value info. */
+ here->e_value_inum = 0;
+ here->e_value_offs = 0;
+ here->e_value_size = 0;
+ }
+
if (i->value) {
- /* Insert the new value. */
+ /* Insert new value. */
if (in_inode) {
- unsigned long ea_ino =
- le32_to_cpu(s->here->e_value_inum);
- rc = ext4_xattr_inode_set(handle, inode, &ea_ino,
- i->value, i->value_len);
- if (rc)
- goto out;
- s->here->e_value_inum = cpu_to_le32(ea_ino);
- s->here->e_value_offs = 0;
+ here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino);
} else if (i->value_len) {
- size_t size = EXT4_XATTR_SIZE(i->value_len);
- void *val = s->base + min_offs - size;
- s->here->e_value_offs = cpu_to_le16(min_offs - size);
- s->here->e_value_inum = 0;
+ void *val = s->base + min_offs - new_size;
+
+ here->e_value_offs = cpu_to_le16(min_offs - new_size);
if (i->value == EXT4_ZERO_XATTR_VALUE) {
- memset(val, 0, size);
+ memset(val, 0, new_size);
} else {
- /* Clear the pad bytes first. */
- memset(val + size - EXT4_XATTR_PAD, 0,
- EXT4_XATTR_PAD);
memcpy(val, i->value, i->value_len);
+ /* Clear padding bytes. */
+ memset(val + i->value_len, 0,
+ new_size - i->value_len);
}
}
- s->here->e_value_size = cpu_to_le32(i->value_len);
+ here->e_value_size = cpu_to_le32(i->value_len);
}
-
+ ret = 0;
out:
- return rc;
+ iput(old_ea_inode);
+ iput(new_ea_inode);
+ return ret;
}
struct ext4_xattr_block_find {
@@ -1223,6 +1641,8 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
struct mb_cache_entry *ce = NULL;
int error = 0;
struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
+ struct inode *ea_inode = NULL;
+ size_t old_ea_inode_size = 0;
#define header(x) ((struct ext4_xattr_header *)(x))
@@ -1277,6 +1697,24 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
header(s->base)->h_refcount = cpu_to_le32(1);
s->here = ENTRY(s->base + offset);
s->end = s->base + bs->bh->b_size;
+
+ /*
+ * If existing entry points to an xattr inode, we need
+ * to prevent ext4_xattr_set_entry() from decrementing
+ * ref count on it because the reference belongs to the
+ * original block. In this case, make the entry look
+ * like it has an empty value.
+ */
+ if (!s->not_found && s->here->e_value_inum) {
+ /*
+ * Defer quota free call for previous inode
+ * until success is guaranteed.
+ */
+ old_ea_inode_size = le32_to_cpu(
+ s->here->e_value_size);
+ s->here->e_value_inum = 0;
+ s->here->e_value_size = 0;
+ }
}
} else {
/* Allocate a buffer where we construct the new block. */
@@ -1298,6 +1736,24 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
goto bad_block;
if (error)
goto cleanup;
+
+ if (i->value && s->here->e_value_inum) {
+ unsigned int ea_ino;
+
+ /*
+ * A ref count on ea_inode has been taken as part of the call to
+ * ext4_xattr_set_entry() above. We would like to drop this
+ * extra ref but we have to wait until the xattr block is
+ * initialized and has its own ref count on the ea_inode.
+ */
+ ea_ino = le32_to_cpu(s->here->e_value_inum);
+ error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
+ if (error) {
+ ea_inode = NULL;
+ goto cleanup;
+ }
+ }
+
if (!IS_LAST_ENTRY(s->first))
ext4_xattr_rehash(header(s->base), s->here);
@@ -1408,6 +1864,22 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
EXT4_FREE_BLOCKS_METADATA);
goto cleanup;
}
+ error = ext4_xattr_inode_inc_ref_all(handle, inode,
+ ENTRY(header(s->base)+1));
+ if (error)
+ goto getblk_failed;
+ if (ea_inode) {
+ /* Drop the extra ref on ea_inode. */
+ error = ext4_xattr_inode_dec_ref(handle,
+ ea_inode);
+ if (error)
+ ext4_warning_inode(ea_inode,
+ "dec ref error=%d",
+ error);
+ iput(ea_inode);
+ ea_inode = NULL;
+ }
+
lock_buffer(new_bh);
error = ext4_journal_get_create_access(handle, new_bh);
if (error) {
@@ -1427,15 +1899,38 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
}
}
+ if (old_ea_inode_size)
+ ext4_xattr_inode_free_quota(inode, old_ea_inode_size);
+
/* Update the inode. */
EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
/* Drop the previous xattr block. */
- if (bs->bh && bs->bh != new_bh)
- ext4_xattr_release_block(handle, inode, bs->bh);
+ if (bs->bh && bs->bh != new_bh) {
+ struct ext4_xattr_inode_array *ea_inode_array = NULL;
+
+ ext4_xattr_release_block(handle, inode, bs->bh,
+ &ea_inode_array,
+ 0 /* extra_credits */);
+ ext4_xattr_inode_array_free(ea_inode_array);
+ }
error = 0;
cleanup:
+ if (ea_inode) {
+ int error2;
+
+ error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
+ if (error2)
+ ext4_warning_inode(ea_inode, "dec ref error=%d",
+ error2);
+
+ /* If there was an error, revert the quota charge. */
+ if (error)
+ ext4_xattr_inode_free_quota(inode,
+ i_size_read(ea_inode));
+ iput(ea_inode);
+ }
if (ce)
mb_cache_entry_put(ea_block_cache, ce);
brelse(new_bh);
@@ -1560,6 +2055,22 @@ static int ext4_xattr_value_same(struct ext4_xattr_search *s,
return !memcmp(value, i->value, i->value_len);
}
+static struct buffer_head *ext4_xattr_get_block(struct inode *inode)
+{
+ struct buffer_head *bh;
+ int error;
+
+ if (!EXT4_I(inode)->i_file_acl)
+ return NULL;
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ if (!bh)
+ return ERR_PTR(-EIO);
+ error = ext4_xattr_check_block(inode, bh);
+ if (error)
+ return ERR_PTR(error);
+ return bh;
+}
+
/*
* ext4_xattr_set_handle()
*
@@ -1602,9 +2113,18 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
/* Check journal credits under write lock. */
if (ext4_handle_valid(handle)) {
+ struct buffer_head *bh;
int credits;
- credits = ext4_xattr_set_credits(inode, value_len);
+ bh = ext4_xattr_get_block(inode);
+ if (IS_ERR(bh)) {
+ error = PTR_ERR(bh);
+ goto cleanup;
+ }
+
+ credits = __ext4_xattr_set_credits(inode->i_sb, bh, value_len);
+ brelse(bh);
+
if (!ext4_handle_has_enough_credits(handle, credits)) {
error = -ENOSPC;
goto cleanup;
@@ -1640,6 +2160,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
if (flags & XATTR_CREATE)
goto cleanup;
}
+
if (!value) {
if (!is.s.not_found)
error = ext4_xattr_ibody_set(handle, inode, &i, &is);
@@ -1708,34 +2229,29 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
return error;
}
-int ext4_xattr_set_credits(struct inode *inode, size_t value_len)
+int ext4_xattr_set_credits(struct inode *inode, size_t value_len, int *credits)
{
- struct super_block *sb = inode->i_sb;
- int credits;
-
- if (!EXT4_SB(sb)->s_journal)
- return 0;
+ struct buffer_head *bh;
+ int err;
- credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
+ *credits = 0;
- /*
- * In case of inline data, we may push out the data to a block,
- * so we need to reserve credits for this eventuality
- */
- if (ext4_has_inline_data(inode))
- credits += ext4_writepage_trans_blocks(inode) + 1;
-
- if (ext4_has_feature_ea_inode(sb)) {
- int nrblocks = (value_len + sb->s_blocksize - 1) >>
- sb->s_blocksize_bits;
+ if (!EXT4_SB(inode->i_sb)->s_journal)
+ return 0;
- /* For new inode */
- credits += EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + 3;
+ down_read(&EXT4_I(inode)->xattr_sem);
- /* For data blocks of EA inode */
- credits += ext4_meta_trans_blocks(inode, nrblocks, 0);
+ bh = ext4_xattr_get_block(inode);
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
+ } else {
+ *credits = __ext4_xattr_set_credits(inode->i_sb, bh, value_len);
+ brelse(bh);
+ err = 0;
}
- return credits;
+
+ up_read(&EXT4_I(inode)->xattr_sem);
+ return err;
}
/*
@@ -1760,7 +2276,10 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
return error;
retry:
- credits = ext4_xattr_set_credits(inode, value_len);
+ error = ext4_xattr_set_credits(inode, value_len, &credits);
+ if (error)
+ return error;
+
handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
@@ -2066,10 +2585,10 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
return error;
}
-
#define EIA_INCR 16 /* must be 2^n */
#define EIA_MASK (EIA_INCR - 1)
-/* Add the large xattr @inode into @ea_inode_array for later deletion.
+
+/* Add the large xattr @inode into @ea_inode_array for deferred iput().
* If @ea_inode_array is new or full it will be grown and the old
* contents copied over.
*/
@@ -2114,21 +2633,19 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
* ext4_xattr_delete_inode()
*
* Free extended attribute resources associated with this inode. Traverse
- * all entries and unlink any xattr inodes associated with this inode. This
- * is called immediately before an inode is freed. We have exclusive
- * access to the inode. If an orphan inode is deleted it will also delete any
- * xattr block and all xattr inodes. They are checked by ext4_xattr_inode_iget()
- * to ensure they belong to the parent inode and were not deleted already.
+ * all entries and decrement reference on any xattr inodes associated with this
+ * inode. This is called immediately before an inode is freed. We have exclusive
+ * access to the inode. If an orphan inode is deleted it will also release its
+ * references on xattr block and xattr inodes.
*/
-int
-ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
- struct ext4_xattr_inode_array **ea_inode_array,
- int extra_credits)
+int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
{
struct buffer_head *bh = NULL;
struct ext4_xattr_ibody_header *header;
- struct ext4_inode *raw_inode;
struct ext4_iloc iloc = { .bh = NULL };
+ struct ext4_xattr_entry *entry;
int error;
error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
@@ -2140,66 +2657,71 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
goto cleanup;
}
- if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
- goto delete_external_ea;
+ if (ext4_has_feature_ea_inode(inode->i_sb) &&
+ ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
- error = ext4_get_inode_loc(inode, &iloc);
- if (error)
- goto cleanup;
-
- error = ext4_journal_get_write_access(handle, iloc.bh);
- if (error)
- goto cleanup;
+ error = ext4_get_inode_loc(inode, &iloc);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "inode loc (error %d)", error);
+ goto cleanup;
+ }
- raw_inode = ext4_raw_inode(&iloc);
- header = IHDR(inode, raw_inode);
- ext4_xattr_inode_remove_all(handle, inode, iloc.bh, IFIRST(header),
- false /* block_csum */, ea_inode_array,
- extra_credits);
+ error = ext4_journal_get_write_access(handle, iloc.bh);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "write access (error %d)",
+ error);
+ goto cleanup;
+ }
-delete_external_ea:
- if (!EXT4_I(inode)->i_file_acl) {
- error = 0;
- goto cleanup;
- }
- bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
- if (!bh) {
- EXT4_ERROR_INODE(inode, "block %llu read error",
- EXT4_I(inode)->i_file_acl);
- error = -EIO;
- goto cleanup;
- }
- if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
- BHDR(bh)->h_blocks != cpu_to_le32(1)) {
- EXT4_ERROR_INODE(inode, "bad block %llu",
- EXT4_I(inode)->i_file_acl);
- error = -EFSCORRUPTED;
- goto cleanup;
+ header = IHDR(inode, ext4_raw_inode(&iloc));
+ if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC))
+ ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh,
+ IFIRST(header),
+ false /* block_csum */,
+ ea_inode_array,
+ extra_credits,
+ false /* skip_quota */);
}
- if (ext4_has_feature_ea_inode(inode->i_sb)) {
- error = ext4_journal_get_write_access(handle, bh);
- if (error) {
- EXT4_ERROR_INODE(inode, "write access %llu",
+ if (EXT4_I(inode)->i_file_acl) {
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ if (!bh) {
+ EXT4_ERROR_INODE(inode, "block %llu read error",
EXT4_I(inode)->i_file_acl);
+ error = -EIO;
+ goto cleanup;
+ }
+ error = ext4_xattr_check_block(inode, bh);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "bad block %llu (error %d)",
+ EXT4_I(inode)->i_file_acl, error);
goto cleanup;
}
- ext4_xattr_inode_remove_all(handle, inode, bh,
- BFIRST(bh),
- true /* block_csum */,
- ea_inode_array,
- extra_credits);
- }
- ext4_xattr_release_block(handle, inode, bh);
- /* Update i_file_acl within the same transaction that releases block. */
- EXT4_I(inode)->i_file_acl = 0;
- error = ext4_mark_inode_dirty(handle, inode);
- if (error) {
- EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
- error);
- goto cleanup;
+ if (ext4_has_feature_ea_inode(inode->i_sb)) {
+ for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry))
+ if (entry->e_value_inum)
+ ext4_xattr_inode_free_quota(inode,
+ le32_to_cpu(entry->e_value_size));
+
+ }
+
+ ext4_xattr_release_block(handle, inode, bh, ea_inode_array,
+ extra_credits);
+ /*
+ * Update i_file_acl value in the same transaction that releases
+ * block.
+ */
+ EXT4_I(inode)->i_file_acl = 0;
+ error = ext4_mark_inode_dirty(handle, inode);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
+ error);
+ goto cleanup;
+ }
}
+ error = 0;
cleanup:
brelse(iloc.bh);
brelse(bh);
@@ -2208,17 +2730,13 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array)
{
- struct inode *ea_inode;
- int idx = 0;
+ int idx;
if (ea_inode_array == NULL)
return;
- for (; idx < ea_inode_array->count; ++idx) {
- ea_inode = ea_inode_array->inodes[idx];
- clear_nlink(ea_inode);
- iput(ea_inode);
- }
+ for (idx = 0; idx < ea_inode_array->count; ++idx)
+ iput(ea_inode_array->inodes[idx]);
kfree(ea_inode_array);
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index b2005a2716d9..67616cb9a059 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -69,19 +69,6 @@ struct ext4_xattr_entry {
EXT4_I(inode)->i_extra_isize))
#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
-/*
- * Link EA inode back to parent one using i_mtime field.
- * Extra integer type conversion added to ignore higher
- * bits in i_mtime.tv_sec which might be set by ext4_get()
- */
-#define EXT4_XATTR_INODE_SET_PARENT(inode, inum) \
-do { \
- (inode)->i_mtime.tv_sec = inum; \
-} while(0)
-
-#define EXT4_XATTR_INODE_GET_PARENT(inode) \
-((__u32)(inode)->i_mtime.tv_sec)
-
/*
* The minimum size of EA value when you start storing it in an external inode
* size of block - size of header - size of 1 entry - 4 null bytes
@@ -165,9 +152,9 @@ extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
-extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len);
+extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len,
+ int *credits);
-extern int ext4_xattr_inode_unlink(struct inode *inode, unsigned long ea_ino);
extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
struct ext4_xattr_inode_array **array,
int extra_credits);
diff --git a/fs/mbcache.c b/fs/mbcache.c
index 45a8d52dc991..d818fd236787 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -13,10 +13,11 @@
* mb_cache_entry_delete()).
*
* Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
- * They use hash of a block contents as a key and block number as a value.
- * That's why keys need not be unique (different xattr blocks may end up having
- * the same hash). However block number always uniquely identifies a cache
- * entry.
+ * Ext4 also uses it for deduplication of xattr values stored in inodes.
+ * They use hash of data as a key and provide a value that may represent a
+ * block or inode number. That's why keys need not be unique (hash of different
+ * data may be the same). However user provided value always uniquely
+ * identifies a cache entry.
*
* We provide functions for creation and removal of entries, search by key,
* and a special "delete entry with given key-value pair" operation. Fixed
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (2 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 27/32] ext4: xattr inode deduplication Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:47 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 29/32] ext4: reserve space for xattr entries/names Tahsin Erdogan
` (4 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
Ext4 ea_inode feature allows storing xattr values in external inodes to
be able to store values that are bigger than a block in size. Ext4 also
has deduplication support for these type of inodes. With deduplication,
the actual storage waste is eliminated but the users of such inodes are
still charged full quota for the inodes as if there was no sharing
happening in the background.
This design requires ext4 to manually charge the users because the
inodes are shared.
An implication of this is that, if someone calls chown on a file that
has such references we need to transfer the quota for the file and xattr
inodes. Current dquot_transfer() function implicitly transfers one inode
charge. With ea_inode feature, we would like to transfer multiple inode
charges.
Add get_inode_usage callback which can interrogate the total number of
inodes that were charged for a given inode.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Acked-by: Jan Kara <jack@suse.cz>
---
v3: added Acked-by
v2:
- added get_inode_usage() callback to query total inodes charge to
be transferred
fs/ext4/inode.c | 7 +++++++
fs/ext4/ioctl.c | 6 ++++++
fs/ext4/super.c | 21 ++++++++++----------
fs/ext4/xattr.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++
fs/ext4/xattr.h | 2 ++
fs/quota/dquot.c | 16 +++++++++++----
include/linux/quota.h | 2 ++
7 files changed, 94 insertions(+), 14 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ea95bd9eab81..cd22de0b5d2c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5295,7 +5295,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
error = PTR_ERR(handle);
goto err_out;
}
+
+ /* dquot_transfer() calls back ext4_get_inode_usage() which
+ * counts xattr inode references.
+ */
+ down_read(&EXT4_I(inode)->xattr_sem);
error = dquot_transfer(inode, attr);
+ up_read(&EXT4_I(inode)->xattr_sem);
+
if (error) {
ext4_journal_stop(handle);
return error;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index dde8deb11e59..42b3a73143cf 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -373,7 +373,13 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
+
+ /* __dquot_transfer() calls back ext4_get_inode_usage() which
+ * counts xattr inode references.
+ */
+ down_read(&EXT4_I(inode)->xattr_sem);
err = __dquot_transfer(inode, transfer_to);
+ up_read(&EXT4_I(inode)->xattr_sem);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d501f8256dc4..5ac76e8d4013 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1263,16 +1263,17 @@ static struct dquot **ext4_get_dquots(struct inode *inode)
}
static const struct dquot_operations ext4_quota_operations = {
- .get_reserved_space = ext4_get_reserved_space,
- .write_dquot = ext4_write_dquot,
- .acquire_dquot = ext4_acquire_dquot,
- .release_dquot = ext4_release_dquot,
- .mark_dirty = ext4_mark_dquot_dirty,
- .write_info = ext4_write_info,
- .alloc_dquot = dquot_alloc,
- .destroy_dquot = dquot_destroy,
- .get_projid = ext4_get_projid,
- .get_next_id = ext4_get_next_id,
+ .get_reserved_space = ext4_get_reserved_space,
+ .write_dquot = ext4_write_dquot,
+ .acquire_dquot = ext4_acquire_dquot,
+ .release_dquot = ext4_release_dquot,
+ .mark_dirty = ext4_mark_dquot_dirty,
+ .write_info = ext4_write_info,
+ .alloc_dquot = dquot_alloc,
+ .destroy_dquot = dquot_destroy,
+ .get_projid = ext4_get_projid,
+ .get_inode_usage = ext4_get_inode_usage,
+ .get_next_id = ext4_get_next_id,
};
static const struct quotactl_ops ext4_qctl_operations = {
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 15c9f736dcc4..a3f8bf4558f3 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -733,6 +733,60 @@ static void ext4_xattr_update_super_block(handle_t *handle,
}
}
+int ext4_get_inode_usage(struct inode *inode, qsize_t *usage)
+{
+ struct ext4_iloc iloc = { .bh = NULL };
+ struct buffer_head *bh = NULL;
+ struct ext4_inode *raw_inode;
+ struct ext4_xattr_ibody_header *header;
+ struct ext4_xattr_entry *entry;
+ qsize_t ea_inode_refs = 0;
+ void *end;
+ int ret;
+
+ lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem);
+
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
+ ret = ext4_get_inode_loc(inode, &iloc);
+ if (ret)
+ goto out;
+ raw_inode = ext4_raw_inode(&iloc);
+ header = IHDR(inode, raw_inode);
+ end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+ ret = xattr_check_inode(inode, header, end);
+ if (ret)
+ goto out;
+
+ for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry))
+ if (entry->e_value_inum)
+ ea_inode_refs++;
+ }
+
+ if (EXT4_I(inode)->i_file_acl) {
+ bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+ if (!bh) {
+ ret = -EIO;
+ goto out;
+ }
+
+ if (ext4_xattr_check_block(inode, bh)) {
+ ret = -EFSCORRUPTED;
+ goto out;
+ }
+
+ for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry))
+ if (entry->e_value_inum)
+ ea_inode_refs++;
+ }
+ *usage = ea_inode_refs + 1;
+out:
+ brelse(iloc.bh);
+ brelse(bh);
+ return ret;
+}
+
static inline size_t round_up_cluster(struct inode *inode, size_t length)
{
struct super_block *sb = inode->i_sb;
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index 67616cb9a059..26119a67c8c3 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -193,3 +193,5 @@ extern void ext4_xattr_inode_set_class(struct inode *ea_inode);
#else
static inline void ext4_xattr_inode_set_class(struct inode *ea_inode) { }
#endif
+
+extern int ext4_get_inode_usage(struct inode *inode, qsize_t *usage);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 48813aeaab80..53a17496c5c5 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1910,6 +1910,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
{
qsize_t space, cur_space;
qsize_t rsv_space = 0;
+ qsize_t inode_usage = 1;
struct dquot *transfer_from[MAXQUOTAS] = {};
int cnt, ret = 0;
char is_valid[MAXQUOTAS] = {};
@@ -1919,6 +1920,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
if (IS_NOQUOTA(inode))
return 0;
+
+ if (inode->i_sb->dq_op->get_inode_usage) {
+ ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage);
+ if (ret)
+ return ret;
+ }
+
/* Initialize the arrays */
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
warn_to[cnt].w_type = QUOTA_NL_NOWARN;
@@ -1946,7 +1954,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
continue;
is_valid[cnt] = 1;
transfer_from[cnt] = i_dquot(inode)[cnt];
- ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]);
+ ret = check_idq(transfer_to[cnt], inode_usage, &warn_to[cnt]);
if (ret)
goto over_quota;
ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]);
@@ -1963,7 +1971,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
/* Due to IO error we might not have transfer_from[] structure */
if (transfer_from[cnt]) {
int wtype;
- wtype = info_idq_free(transfer_from[cnt], 1);
+ wtype = info_idq_free(transfer_from[cnt], inode_usage);
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn_from_inodes[cnt],
transfer_from[cnt], wtype);
@@ -1971,13 +1979,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
if (wtype != QUOTA_NL_NOWARN)
prepare_warning(&warn_from_space[cnt],
transfer_from[cnt], wtype);
- dquot_decr_inodes(transfer_from[cnt], 1);
+ dquot_decr_inodes(transfer_from[cnt], inode_usage);
dquot_decr_space(transfer_from[cnt], cur_space);
dquot_free_reserved_space(transfer_from[cnt],
rsv_space);
}
- dquot_incr_inodes(transfer_to[cnt], 1);
+ dquot_incr_inodes(transfer_to[cnt], inode_usage);
dquot_incr_space(transfer_to[cnt], cur_space);
dquot_resv_space(transfer_to[cnt], rsv_space);
diff --git a/include/linux/quota.h b/include/linux/quota.h
index 3434eef2a5aa..bfd077ca6ac3 100644
--- a/include/linux/quota.h
+++ b/include/linux/quota.h
@@ -332,6 +332,8 @@ struct dquot_operations {
* quota code only */
qsize_t *(*get_reserved_space) (struct inode *);
int (*get_projid) (struct inode *, kprojid_t *);/* Get project ID */
+ /* Get number of inodes that were charged for a given inode */
+ int (*get_inode_usage) (struct inode *, qsize_t *);
/* Get next ID with active quota structure */
int (*get_next_id) (struct super_block *sb, struct kqid *qid);
};
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 29/32] ext4: reserve space for xattr entries/names
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (3 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:49 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes Tahsin Erdogan
` (3 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
New ea_inode feature allows putting large xattr values into external
inodes. struct ext4_xattr_entry and the attribute name however have to
remain in the inode extra space or external attribute block. Once that
space is exhausted, no further entries can be added. Some of that space
could also be used by values that fit in there at the time of addition.
So, a single xattr entry whose value barely fits in the external block
could prevent further entries being added.
To mitigate the problem, this patch introduces a notion of reserve in
the
external attribute block that cannot be used by value data. This reserve
is enforced when ea_inode feature is enabled. The amount of reserve is
arbitrarily chosen to be min(block_size/8, 1024). The table below shows
how much space is reserved for each block size and the guaranteed
mininum
number of entries that can be placed in the external attribute block.
block size reserved bytes entries (name length = 16)
1k 128 3
2k 256 7
4k 512 15
8k 1024 31
16k 1024 31
32k 1024 31
64k 1024 31
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
fs/ext4/xattr.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index a3f8bf4558f3..835b3dca5b65 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1446,6 +1446,12 @@ static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
return 0;
}
+/*
+ * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode
+ * feature is enabled.
+ */
+#define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U)
+
static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
struct ext4_xattr_search *s,
handle_t *handle, struct inode *inode)
@@ -1505,6 +1511,20 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
ret = -ENOSPC;
goto out;
}
+
+ /*
+ * If storing the value in an external inode is an option,
+ * reserve space for xattr entries/names in the external
+ * attribute block so that a long value does not occupy the
+ * whole space and prevent futher entries being added.
+ */
+ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size &&
+ (s->end - s->base) == i_blocksize(inode) &&
+ (min_offs + old_size - new_size) <
+ EXT4_XATTR_BLOCK_RESERVE(inode)) {
+ ret = -ENOSPC;
+ goto out;
+ }
}
/*
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (4 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 29/32] ext4: reserve space for xattr entries/names Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:52 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 31/32] ext4: strong binding of xattr inode references Tahsin Erdogan
` (2 subsequent siblings)
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
When an extended attribute block is modified, ext4_xattr_hash_entry()
recalculates e_hash for the entry that is pointed by s->here. This is
unnecessary if the modification is to remove an entry.
Currently, if the removed entry is the last one and there are other
entries remaining, hash calculation targets the just erased entry which
has been filled with zeroes and effectively does nothing. If the removed
entry is not the last one and there are more entries, this time it will
recalculate hash on the next entry which is totally unnecessary.
Fix these by moving the decision on when to recalculate hash to
ext4_xattr_set_entry().
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
fs/ext4/xattr.c | 50 ++++++++++++++++++++++++++------------------------
1 file changed, 26 insertions(+), 24 deletions(-)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 835b3dca5b65..9cb15f2069bd 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -77,8 +77,9 @@ static void ext4_xattr_block_cache_insert(struct mb_cache *,
static struct buffer_head *
ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
struct mb_cache_entry **);
-static void ext4_xattr_rehash(struct ext4_xattr_header *,
- struct ext4_xattr_entry *);
+static void ext4_xattr_hash_entry(struct ext4_xattr_entry *entry,
+ void *value_base);
+static void ext4_xattr_rehash(struct ext4_xattr_header *);
static const struct xattr_handler * const ext4_xattr_handler_map[] = {
[EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler,
@@ -1454,7 +1455,8 @@ static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
struct ext4_xattr_search *s,
- handle_t *handle, struct inode *inode)
+ handle_t *handle, struct inode *inode,
+ bool is_block)
{
struct ext4_xattr_entry *last;
struct ext4_xattr_entry *here = s->here;
@@ -1518,8 +1520,8 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
* attribute block so that a long value does not occupy the
* whole space and prevent futher entries being added.
*/
- if (ext4_has_feature_ea_inode(inode->i_sb) && new_size &&
- (s->end - s->base) == i_blocksize(inode) &&
+ if (ext4_has_feature_ea_inode(inode->i_sb) &&
+ new_size && is_block &&
(min_offs + old_size - new_size) <
EXT4_XATTR_BLOCK_RESERVE(inode)) {
ret = -ENOSPC;
@@ -1649,6 +1651,13 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
}
here->e_value_size = cpu_to_le32(i->value_len);
}
+
+ if (is_block) {
+ if (i->value)
+ ext4_xattr_hash_entry(here, s->base);
+ ext4_xattr_rehash((struct ext4_xattr_header *)s->base);
+ }
+
ret = 0;
out:
iput(old_ea_inode);
@@ -1738,14 +1747,11 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
mb_cache_entry_delete(ea_block_cache, hash,
bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
- error = ext4_xattr_set_entry(i, s, handle, inode);
- if (!error) {
- if (!IS_LAST_ENTRY(s->first))
- ext4_xattr_rehash(header(s->base),
- s->here);
+ error = ext4_xattr_set_entry(i, s, handle, inode,
+ true /* is_block */);
+ if (!error)
ext4_xattr_block_cache_insert(ea_block_cache,
bs->bh);
- }
ext4_xattr_block_csum_set(inode, bs->bh);
unlock_buffer(bs->bh);
if (error == -EFSCORRUPTED)
@@ -1805,7 +1811,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
s->end = s->base + sb->s_blocksize;
}
- error = ext4_xattr_set_entry(i, s, handle, inode);
+ error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */);
if (error == -EFSCORRUPTED)
goto bad_block;
if (error)
@@ -1828,9 +1834,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
}
}
- if (!IS_LAST_ENTRY(s->first))
- ext4_xattr_rehash(header(s->base), s->here);
-
inserted:
if (!IS_LAST_ENTRY(s->first)) {
new_bh = ext4_xattr_block_cache_find(inode, header(s->base),
@@ -2063,7 +2066,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
- error = ext4_xattr_set_entry(i, s, handle, inode);
+ error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
if (error) {
if (error == -ENOSPC &&
ext4_has_inline_data(inode)) {
@@ -2075,7 +2078,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
error = ext4_xattr_ibody_find(inode, i, is);
if (error)
return error;
- error = ext4_xattr_set_entry(i, s, handle, inode);
+ error = ext4_xattr_set_entry(i, s, handle, inode,
+ false /* is_block */);
}
if (error)
return error;
@@ -2101,7 +2105,7 @@ static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
if (EXT4_I(inode)->i_extra_isize == 0)
return -ENOSPC;
- error = ext4_xattr_set_entry(i, s, handle, inode);
+ error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
if (error)
return error;
header = IHDR(inode, ext4_raw_inode(&is->iloc));
@@ -2927,8 +2931,8 @@ ext4_xattr_block_cache_find(struct inode *inode,
*
* Compute the hash of an extended attribute.
*/
-static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
- struct ext4_xattr_entry *entry)
+static void ext4_xattr_hash_entry(struct ext4_xattr_entry *entry,
+ void *value_base)
{
__u32 hash = 0;
char *name = entry->e_name;
@@ -2941,7 +2945,7 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
}
if (!entry->e_value_inum && entry->e_value_size) {
- __le32 *value = (__le32 *)((char *)header +
+ __le32 *value = (__le32 *)((char *)value_base +
le16_to_cpu(entry->e_value_offs));
for (n = (le32_to_cpu(entry->e_value_size) +
EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
@@ -2963,13 +2967,11 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
*
* Re-compute the extended attribute hash value after an entry has changed.
*/
-static void ext4_xattr_rehash(struct ext4_xattr_header *header,
- struct ext4_xattr_entry *entry)
+static void ext4_xattr_rehash(struct ext4_xattr_header *header)
{
struct ext4_xattr_entry *here;
__u32 hash = 0;
- ext4_xattr_hash_entry(header, entry);
here = ENTRY(header+1);
while (!IS_LAST_ENTRY(here)) {
if (!here->e_hash) {
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 31/32] ext4: strong binding of xattr inode references
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (5 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 15:54 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 32/32] ext4: add nombcache mount option Tahsin Erdogan
2017-06-22 15:30 ` [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Theodore Ts'o
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
To verify that a xattr entry is not pointing to the wrong xattr inode,
we currently check that the target inode has EXT4_EA_INODE_FL flag set and
also the entry size matches the target inode size.
For stronger validation, also incorporate crc32c hash of the value into
the e_hash field. This is done regardless of whether the entry lives in
the inode body or external attribute block.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v2: naming updates to adapt to other patch changes in the series
fs/ext4/xattr.c | 104 +++++++++++++++++++++++++++++++++++---------------------
1 file changed, 65 insertions(+), 39 deletions(-)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 9cb15f2069bd..3f16dc979012 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -77,8 +77,8 @@ static void ext4_xattr_block_cache_insert(struct mb_cache *,
static struct buffer_head *
ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
struct mb_cache_entry **);
-static void ext4_xattr_hash_entry(struct ext4_xattr_entry *entry,
- void *value_base);
+static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
+ size_t value_count);
static void ext4_xattr_rehash(struct ext4_xattr_header *);
static const struct xattr_handler * const ext4_xattr_handler_map[] = {
@@ -380,7 +380,9 @@ static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
}
static int
-ext4_xattr_inode_verify_hash(struct inode *ea_inode, void *buffer, size_t size)
+ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
+ struct ext4_xattr_entry *entry, void *buffer,
+ size_t size)
{
u32 hash;
@@ -388,23 +390,35 @@ ext4_xattr_inode_verify_hash(struct inode *ea_inode, void *buffer, size_t size)
hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size);
if (hash != ext4_xattr_inode_get_hash(ea_inode))
return -EFSCORRUPTED;
+
+ if (entry) {
+ __le32 e_hash, tmp_data;
+
+ /* Verify entry hash. */
+ tmp_data = cpu_to_le32(hash);
+ e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len,
+ &tmp_data, 1);
+ if (e_hash != entry->e_hash)
+ return -EFSCORRUPTED;
+ }
return 0;
}
#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec)
/*
- * Read the value from the EA inode.
+ * Read xattr value from the EA inode.
*/
static int
-ext4_xattr_inode_get(struct inode *inode, unsigned long ea_ino, void *buffer,
- size_t size)
+ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry,
+ void *buffer, size_t size)
{
struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
struct inode *ea_inode;
int err;
- err = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
+ err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum),
+ &ea_inode);
if (err) {
ea_inode = NULL;
goto out;
@@ -422,7 +436,7 @@ ext4_xattr_inode_get(struct inode *inode, unsigned long ea_ino, void *buffer,
if (err)
goto out;
- err = ext4_xattr_inode_verify_hash(ea_inode, buffer, size);
+ err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size);
/*
* Compatibility check for old Lustre ea_inode implementation. Old
* version does not have hash validation, but it has a backpointer
@@ -489,9 +503,8 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
if (size > buffer_size)
goto cleanup;
if (entry->e_value_inum) {
- error = ext4_xattr_inode_get(inode,
- le32_to_cpu(entry->e_value_inum),
- buffer, size);
+ error = ext4_xattr_inode_get(inode, entry, buffer,
+ size);
if (error)
goto cleanup;
} else {
@@ -539,9 +552,8 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
if (size > buffer_size)
goto cleanup;
if (entry->e_value_inum) {
- error = ext4_xattr_inode_get(inode,
- le32_to_cpu(entry->e_value_inum),
- buffer, size);
+ error = ext4_xattr_inode_get(inode, entry, buffer,
+ size);
if (error)
goto cleanup;
} else {
@@ -1387,8 +1399,8 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
(EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) &&
i_size_read(ea_inode) == value_len &&
!ext4_xattr_inode_read(ea_inode, ea_data, value_len) &&
- !ext4_xattr_inode_verify_hash(ea_inode, ea_data,
- value_len) &&
+ !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data,
+ value_len) &&
!memcmp(value, ea_data, value_len)) {
mb_cache_entry_touch(ea_inode_cache, ce);
mb_cache_entry_put(ea_inode_cache, ce);
@@ -1652,12 +1664,36 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
here->e_value_size = cpu_to_le32(i->value_len);
}
- if (is_block) {
- if (i->value)
- ext4_xattr_hash_entry(here, s->base);
- ext4_xattr_rehash((struct ext4_xattr_header *)s->base);
+ if (i->value) {
+ __le32 hash = 0;
+
+ /* Entry hash calculation. */
+ if (in_inode) {
+ __le32 crc32c_hash;
+
+ /*
+ * Feed crc32c hash instead of the raw value for entry
+ * hash calculation. This is to avoid walking
+ * potentially long value buffer again.
+ */
+ crc32c_hash = cpu_to_le32(
+ ext4_xattr_inode_get_hash(new_ea_inode));
+ hash = ext4_xattr_hash_entry(here->e_name,
+ here->e_name_len,
+ &crc32c_hash, 1);
+ } else if (is_block) {
+ __le32 *value = s->base + min_offs - new_size;
+
+ hash = ext4_xattr_hash_entry(here->e_name,
+ here->e_name_len, value,
+ new_size >> 2);
+ }
+ here->e_hash = hash;
}
+ if (is_block)
+ ext4_xattr_rehash((struct ext4_xattr_header *)s->base);
+
ret = 0;
out:
iput(old_ea_inode);
@@ -2439,9 +2475,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
/* Save the entry name and the entry value */
if (entry->e_value_inum) {
- error = ext4_xattr_inode_get(inode,
- le32_to_cpu(entry->e_value_inum),
- buffer, value_size);
+ error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
if (error)
goto out;
} else {
@@ -2931,30 +2965,22 @@ ext4_xattr_block_cache_find(struct inode *inode,
*
* Compute the hash of an extended attribute.
*/
-static void ext4_xattr_hash_entry(struct ext4_xattr_entry *entry,
- void *value_base)
+static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
+ size_t value_count)
{
__u32 hash = 0;
- char *name = entry->e_name;
- int n;
- for (n = 0; n < entry->e_name_len; n++) {
+ while (name_len--) {
hash = (hash << NAME_HASH_SHIFT) ^
(hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
*name++;
}
-
- if (!entry->e_value_inum && entry->e_value_size) {
- __le32 *value = (__le32 *)((char *)value_base +
- le16_to_cpu(entry->e_value_offs));
- for (n = (le32_to_cpu(entry->e_value_size) +
- EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
- hash = (hash << VALUE_HASH_SHIFT) ^
- (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
- le32_to_cpu(*value++);
- }
+ while (value_count--) {
+ hash = (hash << VALUE_HASH_SHIFT) ^
+ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+ le32_to_cpu(*value++);
}
- entry->e_hash = cpu_to_le32(hash);
+ return cpu_to_le32(hash);
}
#undef NAME_HASH_SHIFT
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* [PATCH 32/32] ext4: add nombcache mount option
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (6 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 31/32] ext4: strong binding of xattr inode references Tahsin Erdogan
@ 2017-06-22 1:49 ` Tahsin Erdogan
2017-06-22 16:00 ` Theodore Ts'o
2017-06-22 15:30 ` [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Theodore Ts'o
8 siblings, 1 reply; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-22 1:49 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
The main purpose of mb cache is to achieve deduplication in
extended attributes. In use cases where opportunity for deduplication
is unlikely, it only adds overhead.
Add a mount option to explicitly turn off mb cache.
Suggested-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v2:
- updated definition of EXT4_MOUNT_NO_MBCACHE to be 0x00001
fs/ext4/ext4.h | 1 +
fs/ext4/super.c | 34 +++++++++++++++++++++++-----------
fs/ext4/xattr.c | 52 +++++++++++++++++++++++++++++++++++-----------------
3 files changed, 59 insertions(+), 28 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index dc06287ddec8..7d66e1dade45 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1114,6 +1114,7 @@ struct ext4_inode_info {
/*
* Mount flags set via mount options or defaults
*/
+#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */
#define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */
#define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */
#define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5ac76e8d4013..1fec35bd4084 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1336,7 +1336,7 @@ enum {
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
- Opt_max_dir_size_kb, Opt_nojournal_checksum,
+ Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
};
static const match_table_t tokens = {
@@ -1419,6 +1419,8 @@ static const match_table_t tokens = {
{Opt_noinit_itable, "noinit_itable"},
{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
+ {Opt_nombcache, "nombcache"},
+ {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */
{Opt_removed, "check=none"}, /* mount option from ext2/3 */
{Opt_removed, "nocheck"}, /* mount option from ext2/3 */
{Opt_removed, "reservation"}, /* mount option from ext2/3 */
@@ -1626,6 +1628,7 @@ static const struct mount_opts {
{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
{Opt_max_dir_size_kb, 0, MOPT_GTE0},
{Opt_test_dummy_encryption, 0, MOPT_GTE0},
+ {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
{Opt_err, 0, 0}
};
@@ -4080,19 +4083,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
no_journal:
- sbi->s_ea_block_cache = ext4_xattr_create_cache();
- if (!sbi->s_ea_block_cache) {
- ext4_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
- goto failed_mount_wq;
- }
-
- if (ext4_has_feature_ea_inode(sb)) {
- sbi->s_ea_inode_cache = ext4_xattr_create_cache();
- if (!sbi->s_ea_inode_cache) {
+ if (!test_opt(sb, NO_MBCACHE)) {
+ sbi->s_ea_block_cache = ext4_xattr_create_cache();
+ if (!sbi->s_ea_block_cache) {
ext4_msg(sb, KERN_ERR,
- "Failed to create ea_inode_cache");
+ "Failed to create ea_block_cache");
goto failed_mount_wq;
}
+
+ if (ext4_has_feature_ea_inode(sb)) {
+ sbi->s_ea_inode_cache = ext4_xattr_create_cache();
+ if (!sbi->s_ea_inode_cache) {
+ ext4_msg(sb, KERN_ERR,
+ "Failed to create ea_inode_cache");
+ goto failed_mount_wq;
+ }
+ }
}
if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
@@ -4989,6 +4995,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
}
+ if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) {
+ ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+
if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
"dax flag with busy inodes while remounting");
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 3f16dc979012..ce12c3fb7e59 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -976,10 +976,13 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
set_nlink(ea_inode, 1);
ext4_orphan_del(handle, ea_inode);
- hash = ext4_xattr_inode_get_hash(ea_inode);
- mb_cache_entry_create(ea_inode_cache, GFP_NOFS, hash,
- ea_inode->i_ino,
- true /* reusable */);
+ if (ea_inode_cache) {
+ hash = ext4_xattr_inode_get_hash(ea_inode);
+ mb_cache_entry_create(ea_inode_cache,
+ GFP_NOFS, hash,
+ ea_inode->i_ino,
+ true /* reusable */);
+ }
}
} else {
WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
@@ -993,9 +996,11 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
clear_nlink(ea_inode);
ext4_orphan_add(handle, ea_inode);
- hash = ext4_xattr_inode_get_hash(ea_inode);
- mb_cache_entry_delete(ea_inode_cache, hash,
- ea_inode->i_ino);
+ if (ea_inode_cache) {
+ hash = ext4_xattr_inode_get_hash(ea_inode);
+ mb_cache_entry_delete(ea_inode_cache, hash,
+ ea_inode->i_ino);
+ }
}
}
@@ -1179,7 +1184,9 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
* This must happen under buffer lock for
* ext4_xattr_block_set() to reliably detect freed block
*/
- mb_cache_entry_delete(ea_block_cache, hash, bh->b_blocknr);
+ if (ea_block_cache)
+ mb_cache_entry_delete(ea_block_cache, hash,
+ bh->b_blocknr);
get_bh(bh);
unlock_buffer(bh);
@@ -1199,11 +1206,13 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
struct mb_cache_entry *ce;
- ce = mb_cache_entry_get(ea_block_cache, hash,
- bh->b_blocknr);
- if (ce) {
- ce->e_reusable = 1;
- mb_cache_entry_put(ea_block_cache, ce);
+ if (ea_block_cache) {
+ ce = mb_cache_entry_get(ea_block_cache, hash,
+ bh->b_blocknr);
+ if (ce) {
+ ce->e_reusable = 1;
+ mb_cache_entry_put(ea_block_cache, ce);
+ }
}
}
@@ -1382,6 +1391,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
void *ea_data;
+ if (!ea_inode_cache)
+ return NULL;
+
ce = mb_cache_entry_find_first(ea_inode_cache, hash);
if (!ce)
return NULL;
@@ -1452,8 +1464,9 @@ static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
return err;
}
- mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
- ea_inode->i_ino, true /* reusable */);
+ if (EA_INODE_CACHE(inode))
+ mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
+ ea_inode->i_ino, true /* reusable */);
*ret_inode = ea_inode;
return 0;
@@ -1780,8 +1793,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
* ext4_xattr_block_set() to reliably detect modified
* block
*/
- mb_cache_entry_delete(ea_block_cache, hash,
- bs->bh->b_blocknr);
+ if (ea_block_cache)
+ mb_cache_entry_delete(ea_block_cache, hash,
+ bs->bh->b_blocknr);
ea_bdebug(bs->bh, "modifying in-place");
error = ext4_xattr_set_entry(i, s, handle, inode,
true /* is_block */);
@@ -2870,6 +2884,8 @@ ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
EXT4_XATTR_REFCOUNT_MAX;
int error;
+ if (!ea_block_cache)
+ return;
error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash,
bh->b_blocknr, reusable);
if (error) {
@@ -2936,6 +2952,8 @@ ext4_xattr_block_cache_find(struct inode *inode,
struct mb_cache_entry *ce;
struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
+ if (!ea_block_cache)
+ return NULL;
if (!header->h_hash)
return NULL; /* never share */
ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
* Re: [PATCH 24/32] ext2, ext4: make mb block cache names more explicit
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
` (7 preceding siblings ...)
2017-06-22 1:49 ` [PATCH 32/32] ext4: add nombcache mount option Tahsin Erdogan
@ 2017-06-22 15:30 ` Theodore Ts'o
8 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:30 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:31PM -0700, Tahsin Erdogan wrote:
> There will be a second mb_cache instance that tracks ea_inodes. Make
> existing names more explicit so that it is clear that they refer to
> xattr block cache.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Thanks, applied.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 25/32] ext4: add ext4_is_quota_file()
2017-06-22 1:49 ` [PATCH 25/32] ext4: add ext4_is_quota_file() Tahsin Erdogan
@ 2017-06-22 15:39 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:39 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:32PM -0700, Tahsin Erdogan wrote:
> IS_NOQUOTA() indicates whether quota is disabled for an inode. Ext4
> also uses it to check whether an inode is for a quota file. The
> distinction currently doesn't matter because quota is disabled only
> for the quota files. When we start disabling quota for other inodes
> in the future, we will want to make the distinction clear.
>
> Replace IS_NOQUOTA() call with ext4_is_quota_file() at places where
> we are checking for quota files.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Added to the ext4 patch queue, thanks.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion
2017-06-22 1:49 ` [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion Tahsin Erdogan
@ 2017-06-22 15:43 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:43 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:33PM -0700, Tahsin Erdogan wrote:
> During inode deletion, journal credits that will be needed are hard to
> determine, that is why we have journal extend/restart calls in several
> places. Whenever a transaction is restarted, filesystem must be in a
> consistent state because there is no atomicity guarantee beyond a
> restart call.
>
> Add ext4_xattr_ensure_credits() helper function which takes care of
> journal extend/restart logic. It also handles getting jbd2 write access
> and dirty metadata calls. This function is called at every iteration of
> handling an ea_inode reference.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Applied, thanks.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 27/32] ext4: xattr inode deduplication
2017-06-22 1:49 ` [PATCH 27/32] ext4: xattr inode deduplication Tahsin Erdogan
@ 2017-06-22 15:45 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:45 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:34PM -0700, Tahsin Erdogan wrote:
> Ext4 now supports xattr values that are up to 64k in size (vfs limit).
> Large xattr values are stored in external inodes each one holding a
> single value. Once written the data blocks of these inodes are immutable.
>
> The real world use cases are expected to have a lot of value duplication
> such as inherited acls etc. To reduce data duplication on disk, this patch
> implements a deduplicator that allows sharing of xattr inodes.
>
> The deduplication is based on an in-memory hash lookup that is a best
> effort sharing scheme. When a xattr inode is read from disk (i.e.
> getxattr() call), its crc32c hash is added to a hash table. Before
> creating a new xattr inode for a value being set, the hash table is
> checked to see if an existing inode holds an identical value. If such an
> inode is found, the ref count on that inode is incremented. On value
> removal the ref count is decremented and if it reaches zero the inode is
> deleted.
>
> The quota charging for such inodes is manually managed. Every reference
> holder is charged the full size as if there was no sharing happening.
> This is consistent with how xattr blocks are also charged.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Applied, thanks
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges
2017-06-22 1:49 ` [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges Tahsin Erdogan
@ 2017-06-22 15:47 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:47 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:35PM -0700, Tahsin Erdogan wrote:
> Ext4 ea_inode feature allows storing xattr values in external inodes to
> be able to store values that are bigger than a block in size. Ext4 also
> has deduplication support for these type of inodes. With deduplication,
> the actual storage waste is eliminated but the users of such inodes are
> still charged full quota for the inodes as if there was no sharing
> happening in the background.
>
> This design requires ext4 to manually charge the users because the
> inodes are shared.
>
> An implication of this is that, if someone calls chown on a file that
> has such references we need to transfer the quota for the file and xattr
> inodes. Current dquot_transfer() function implicitly transfers one inode
> charge. With ea_inode feature, we would like to transfer multiple inode
> charges.
>
> Add get_inode_usage callback which can interrogate the total number of
> inodes that were charged for a given inode.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
> Acked-by: Jan Kara <jack@suse.cz>
Thanks, applied.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 29/32] ext4: reserve space for xattr entries/names
2017-06-22 1:49 ` [PATCH 29/32] ext4: reserve space for xattr entries/names Tahsin Erdogan
@ 2017-06-22 15:49 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:49 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:36PM -0700, Tahsin Erdogan wrote:
> New ea_inode feature allows putting large xattr values into external
> inodes. struct ext4_xattr_entry and the attribute name however have to
> remain in the inode extra space or external attribute block. Once that
> space is exhausted, no further entries can be added. Some of that space
> could also be used by values that fit in there at the time of addition.
>
> So, a single xattr entry whose value barely fits in the external block
> could prevent further entries being added.
>
> To mitigate the problem, this patch introduces a notion of reserve in
> the
> external attribute block that cannot be used by value data. This reserve
> is enforced when ea_inode feature is enabled. The amount of reserve is
> arbitrarily chosen to be min(block_size/8, 1024). The table below shows
> how much space is reserved for each block size and the guaranteed
> mininum
> number of entries that can be placed in the external attribute block.
>
> block size reserved bytes entries (name length = 16)
> 1k 128 3
> 2k 256 7
> 4k 512 15
> 8k 1024 31
> 16k 1024 31
> 32k 1024 31
> 64k 1024 31
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Thanks, applied.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes
2017-06-22 1:49 ` [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes Tahsin Erdogan
@ 2017-06-22 15:52 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:52 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:37PM -0700, Tahsin Erdogan wrote:
> When an extended attribute block is modified, ext4_xattr_hash_entry()
> recalculates e_hash for the entry that is pointed by s->here. This is
> unnecessary if the modification is to remove an entry.
>
> Currently, if the removed entry is the last one and there are other
> entries remaining, hash calculation targets the just erased entry which
> has been filled with zeroes and effectively does nothing. If the removed
> entry is not the last one and there are more entries, this time it will
> recalculate hash on the next entry which is totally unnecessary.
>
> Fix these by moving the decision on when to recalculate hash to
> ext4_xattr_set_entry().
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Thanks, applied.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 31/32] ext4: strong binding of xattr inode references
2017-06-22 1:49 ` [PATCH 31/32] ext4: strong binding of xattr inode references Tahsin Erdogan
@ 2017-06-22 15:54 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 15:54 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:38PM -0700, Tahsin Erdogan wrote:
> To verify that a xattr entry is not pointing to the wrong xattr inode,
> we currently check that the target inode has EXT4_EA_INODE_FL flag set and
> also the entry size matches the target inode size.
>
> For stronger validation, also incorporate crc32c hash of the value into
> the e_hash field. This is done regardless of whether the entry lives in
> the inode body or external attribute block.
>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Added to the ext4 patch queue, thanks.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* Re: [PATCH 32/32] ext4: add nombcache mount option
2017-06-22 1:49 ` [PATCH 32/32] ext4: add nombcache mount option Tahsin Erdogan
@ 2017-06-22 16:00 ` Theodore Ts'o
0 siblings, 0 replies; 19+ messages in thread
From: Theodore Ts'o @ 2017-06-22 16:00 UTC (permalink / raw)
To: Tahsin Erdogan
Cc: Andreas Dilger, Darrick J . Wong, Jan Kara, linux-ext4, linux-kernel
On Wed, Jun 21, 2017 at 06:49:39PM -0700, Tahsin Erdogan wrote:
> The main purpose of mb cache is to achieve deduplication in
> extended attributes. In use cases where opportunity for deduplication
> is unlikely, it only adds overhead.
>
> Add a mount option to explicitly turn off mb cache.
>
> Suggested-by: Andreas Dilger <adilger@dilger.ca>
> Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Applied, thanks.
- Ted
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion
2017-06-21 21:21 [PATCH 01/32] ext4: xattr-in-inode support Tahsin Erdogan
@ 2017-06-21 21:21 ` Tahsin Erdogan
0 siblings, 0 replies; 19+ messages in thread
From: Tahsin Erdogan @ 2017-06-21 21:21 UTC (permalink / raw)
To: Andreas Dilger, Darrick J . Wong, Jan Kara, Theodore Ts'o,
linux-ext4
Cc: linux-kernel, Tahsin Erdogan
During inode deletion, journal credits that will be needed are hard to
determine, that is why we have journal extend/restart calls in several
places. Whenever a transaction is restarted, filesystem must be in a
consistent state because there is no atomicity guarantee beyond a
restart call.
Add ext4_xattr_ensure_credits() helper function which takes care of
journal extend/restart logic. It also handles getting jbd2 write access
and dirty metadata calls. This function is called at every iteration of
handling an ea_inode reference.
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
---
v3: fixed checkpatch.pl warnings about long lines and indented label
v2: made ext4_xattr_ensure_credits() static
fs/ext4/inode.c | 66 ++++-----------
fs/ext4/xattr.c | 258 ++++++++++++++++++++++++++++++++++++--------------------
fs/ext4/xattr.h | 3 +-
3 files changed, 184 insertions(+), 143 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cf91532765a4..cd007f9757d1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -239,7 +239,11 @@ void ext4_evict_inode(struct inode *inode)
*/
sb_start_intwrite(inode->i_sb);
- handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, extra_credits);
+ if (!IS_NOQUOTA(inode))
+ extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
+
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
+ ext4_blocks_for_truncate(inode)+extra_credits);
if (IS_ERR(handle)) {
ext4_std_error(inode->i_sb, PTR_ERR(handle));
/*
@@ -251,36 +255,9 @@ void ext4_evict_inode(struct inode *inode)
sb_end_intwrite(inode->i_sb);
goto no_delete;
}
+
if (IS_SYNC(inode))
ext4_handle_sync(handle);
-
- /*
- * Delete xattr inode before deleting the main inode.
- */
- err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array);
- if (err) {
- ext4_warning(inode->i_sb,
- "couldn't delete inode's xattr (err %d)", err);
- goto stop_handle;
- }
-
- if (!IS_NOQUOTA(inode))
- extra_credits += 2 * EXT4_QUOTA_DEL_BLOCKS(inode->i_sb);
-
- if (!ext4_handle_has_enough_credits(handle,
- ext4_blocks_for_truncate(inode) + extra_credits)) {
- err = ext4_journal_extend(handle,
- ext4_blocks_for_truncate(inode) + extra_credits);
- if (err > 0)
- err = ext4_journal_restart(handle,
- ext4_blocks_for_truncate(inode) + extra_credits);
- if (err != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", err);
- goto stop_handle;
- }
- }
-
inode->i_size = 0;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
@@ -298,25 +275,17 @@ void ext4_evict_inode(struct inode *inode)
}
}
- /*
- * ext4_ext_truncate() doesn't reserve any slop when it
- * restarts journal transactions; therefore there may not be
- * enough credits left in the handle to remove the inode from
- * the orphan list and set the dtime field.
- */
- if (!ext4_handle_has_enough_credits(handle, extra_credits)) {
- err = ext4_journal_extend(handle, extra_credits);
- if (err > 0)
- err = ext4_journal_restart(handle, extra_credits);
- if (err != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", err);
- stop_handle:
- ext4_journal_stop(handle);
- ext4_orphan_del(NULL, inode);
- sb_end_intwrite(inode->i_sb);
- goto no_delete;
- }
+ /* Remove xattr references. */
+ err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array,
+ extra_credits);
+ if (err) {
+ ext4_warning(inode->i_sb, "xattr delete (err %d)", err);
+stop_handle:
+ ext4_journal_stop(handle);
+ ext4_orphan_del(NULL, inode);
+ sb_end_intwrite(inode->i_sb);
+ ext4_xattr_inode_array_free(ea_inode_array);
+ goto no_delete;
}
/*
@@ -342,7 +311,6 @@ void ext4_evict_inode(struct inode *inode)
ext4_clear_inode(inode);
else
ext4_free_inode(handle, inode);
-
ext4_journal_stop(handle);
sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 5f36121c5a00..353a323f30b1 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -108,6 +108,10 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
#define MB_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \
inode->i_sb->s_fs_info)->s_mb_block_cache)
+static int
+ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
+ struct inode *inode);
+
#ifdef CONFIG_LOCKDEP
void ext4_xattr_inode_set_class(struct inode *ea_inode)
{
@@ -652,6 +656,128 @@ static void ext4_xattr_update_super_block(handle_t *handle,
}
}
+static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
+ int credits, struct buffer_head *bh,
+ bool dirty, bool block_csum)
+{
+ int error;
+
+ if (!ext4_handle_valid(handle))
+ return 0;
+
+ if (handle->h_buffer_credits >= credits)
+ return 0;
+
+ error = ext4_journal_extend(handle, credits - handle->h_buffer_credits);
+ if (!error)
+ return 0;
+ if (error < 0) {
+ ext4_warning(inode->i_sb, "Extend journal (error %d)", error);
+ return error;
+ }
+
+ if (bh && dirty) {
+ if (block_csum)
+ ext4_xattr_block_csum_set(inode, bh);
+ error = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (error) {
+ ext4_warning(inode->i_sb, "Handle metadata (error %d)",
+ error);
+ return error;
+ }
+ }
+
+ error = ext4_journal_restart(handle, credits);
+ if (error) {
+ ext4_warning(inode->i_sb, "Restart journal (error %d)", error);
+ return error;
+ }
+
+ if (bh) {
+ error = ext4_journal_get_write_access(handle, bh);
+ if (error) {
+ ext4_warning(inode->i_sb,
+ "Get write access failed (error %d)",
+ error);
+ return error;
+ }
+ }
+ return 0;
+}
+
+static void
+ext4_xattr_inode_remove_all(handle_t *handle, struct inode *parent,
+ struct buffer_head *bh,
+ struct ext4_xattr_entry *first, bool block_csum,
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
+{
+ struct inode *ea_inode;
+ struct ext4_xattr_entry *entry;
+ bool dirty = false;
+ unsigned int ea_ino;
+ int err;
+ int credits;
+
+ /* One credit for dec ref on ea_inode, one for orphan list addition, */
+ credits = 2 + extra_credits;
+
+ for (entry = first; !IS_LAST_ENTRY(entry);
+ entry = EXT4_XATTR_NEXT(entry)) {
+ if (!entry->e_value_inum)
+ continue;
+ ea_ino = le32_to_cpu(entry->e_value_inum);
+ err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+ if (err)
+ continue;
+
+ err = ext4_expand_inode_array(ea_inode_array, ea_inode);
+ if (err) {
+ ext4_warning_inode(ea_inode,
+ "Expand inode array err=%d", err);
+ iput(ea_inode);
+ continue;
+ }
+
+ err = ext4_xattr_ensure_credits(handle, parent, credits, bh,
+ dirty, block_csum);
+ if (err) {
+ ext4_warning_inode(ea_inode, "Ensure credits err=%d",
+ err);
+ continue;
+ }
+
+ inode_lock(ea_inode);
+ clear_nlink(ea_inode);
+ ext4_orphan_add(handle, ea_inode);
+ inode_unlock(ea_inode);
+
+ /*
+ * Forget about ea_inode within the same transaction that
+ * decrements the ref count. This avoids duplicate decrements in
+ * case the rest of the work spills over to subsequent
+ * transactions.
+ */
+ entry->e_value_inum = 0;
+ entry->e_value_size = 0;
+
+ dirty = true;
+ }
+
+ if (dirty) {
+ /*
+ * Note that we are deliberately skipping csum calculation for
+ * the final update because we do not expect any journal
+ * restarts until xattr block is freed.
+ */
+
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ ext4_warning_inode(parent,
+ "handle dirty metadata err=%d", err);
+ }
+}
+
/*
* Release the xattr block BH: If the reference count is > 1, decrement it;
* otherwise free the block.
@@ -1984,42 +2110,6 @@ ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
return 0;
}
-/**
- * Add xattr inode to orphan list
- */
-static int
-ext4_xattr_inode_orphan_add(handle_t *handle, struct inode *inode, int credits,
- struct ext4_xattr_inode_array *ea_inode_array)
-{
- int idx = 0, error = 0;
- struct inode *ea_inode;
-
- if (ea_inode_array == NULL)
- return 0;
-
- for (; idx < ea_inode_array->count; ++idx) {
- if (!ext4_handle_has_enough_credits(handle, credits)) {
- error = ext4_journal_extend(handle, credits);
- if (error > 0)
- error = ext4_journal_restart(handle, credits);
-
- if (error != 0) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal "
- "(err %d)", error);
- return error;
- }
- }
- ea_inode = ea_inode_array->inodes[idx];
- inode_lock(ea_inode);
- ext4_orphan_add(handle, ea_inode);
- inode_unlock(ea_inode);
- /* the inode's i_count will be released by caller */
- }
-
- return 0;
-}
-
/*
* ext4_xattr_delete_inode()
*
@@ -2032,16 +2122,23 @@ ext4_xattr_inode_orphan_add(handle_t *handle, struct inode *inode, int credits,
*/
int
ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
- struct ext4_xattr_inode_array **ea_inode_array)
+ struct ext4_xattr_inode_array **ea_inode_array,
+ int extra_credits)
{
struct buffer_head *bh = NULL;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
- struct ext4_iloc iloc;
- struct ext4_xattr_entry *entry;
- struct inode *ea_inode;
- unsigned int ea_ino;
- int credits = 3, error = 0;
+ struct ext4_iloc iloc = { .bh = NULL };
+ int error;
+
+ error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
+ NULL /* bh */,
+ false /* dirty */,
+ false /* block_csum */);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error);
+ goto cleanup;
+ }
if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR))
goto delete_external_ea;
@@ -2049,31 +2146,20 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
error = ext4_get_inode_loc(inode, &iloc);
if (error)
goto cleanup;
+
+ error = ext4_journal_get_write_access(handle, iloc.bh);
+ if (error)
+ goto cleanup;
+
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
- for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
- entry = EXT4_XATTR_NEXT(entry)) {
- if (!entry->e_value_inum)
- continue;
- ea_ino = le32_to_cpu(entry->e_value_inum);
- error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (error)
- continue;
- error = ext4_expand_inode_array(ea_inode_array, ea_inode);
- if (error) {
- iput(ea_inode);
- brelse(iloc.bh);
- goto cleanup;
- }
- entry->e_value_inum = 0;
- }
- brelse(iloc.bh);
+ ext4_xattr_inode_remove_all(handle, inode, iloc.bh, IFIRST(header),
+ false /* block_csum */, ea_inode_array,
+ extra_credits);
delete_external_ea:
if (!EXT4_I(inode)->i_file_acl) {
- /* add xattr inode to orphan list */
- error = ext4_xattr_inode_orphan_add(handle, inode, credits,
- *ea_inode_array);
+ error = 0;
goto cleanup;
}
bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
@@ -2091,46 +2177,32 @@ ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
goto cleanup;
}
- for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
- entry = EXT4_XATTR_NEXT(entry)) {
- if (!entry->e_value_inum)
- continue;
- ea_ino = le32_to_cpu(entry->e_value_inum);
- error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
- if (error)
- continue;
- error = ext4_expand_inode_array(ea_inode_array, ea_inode);
- if (error)
- goto cleanup;
- entry->e_value_inum = 0;
- }
-
- /* add xattr inode to orphan list */
- error = ext4_xattr_inode_orphan_add(handle, inode, credits,
- *ea_inode_array);
- if (error)
- goto cleanup;
-
- if (!IS_NOQUOTA(inode))
- credits += 2 * EXT4_QUOTA_DEL_BLOCKS(inode->i_sb);
-
- if (!ext4_handle_has_enough_credits(handle, credits)) {
- error = ext4_journal_extend(handle, credits);
- if (error > 0)
- error = ext4_journal_restart(handle, credits);
+ if (ext4_has_feature_ea_inode(inode->i_sb)) {
+ error = ext4_journal_get_write_access(handle, bh);
if (error) {
- ext4_warning(inode->i_sb,
- "couldn't extend journal (err %d)", error);
+ EXT4_ERROR_INODE(inode, "write access %llu",
+ EXT4_I(inode)->i_file_acl);
goto cleanup;
}
+ ext4_xattr_inode_remove_all(handle, inode, bh,
+ BFIRST(bh),
+ true /* block_csum */,
+ ea_inode_array,
+ extra_credits);
}
ext4_xattr_release_block(handle, inode, bh);
+ /* Update i_file_acl within the same transaction that releases block. */
EXT4_I(inode)->i_file_acl = 0;
-
+ error = ext4_mark_inode_dirty(handle, inode);
+ if (error) {
+ EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
+ error);
+ goto cleanup;
+ }
cleanup:
+ brelse(iloc.bh);
brelse(bh);
-
return error;
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index adf761518a73..b2005a2716d9 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -169,7 +169,8 @@ extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len);
extern int ext4_xattr_inode_unlink(struct inode *inode, unsigned long ea_ino);
extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
- struct ext4_xattr_inode_array **array);
+ struct ext4_xattr_inode_array **array,
+ int extra_credits);
extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
--
2.13.1.611.g7e3b11ae1-goog
^ permalink raw reply related [flat|nested] 19+ messages in thread
end of thread, other threads:[~2017-06-22 16:00 UTC | newest]
Thread overview: 19+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-06-22 1:49 [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Tahsin Erdogan
2017-06-22 1:49 ` [PATCH 25/32] ext4: add ext4_is_quota_file() Tahsin Erdogan
2017-06-22 15:39 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion Tahsin Erdogan
2017-06-22 15:43 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 27/32] ext4: xattr inode deduplication Tahsin Erdogan
2017-06-22 15:45 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 28/32] quota: add get_inode_usage callback to transfer multi-inode charges Tahsin Erdogan
2017-06-22 15:47 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 29/32] ext4: reserve space for xattr entries/names Tahsin Erdogan
2017-06-22 15:49 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 30/32] ext4: eliminate xattr entry e_hash recalculation for removes Tahsin Erdogan
2017-06-22 15:52 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 31/32] ext4: strong binding of xattr inode references Tahsin Erdogan
2017-06-22 15:54 ` Theodore Ts'o
2017-06-22 1:49 ` [PATCH 32/32] ext4: add nombcache mount option Tahsin Erdogan
2017-06-22 16:00 ` Theodore Ts'o
2017-06-22 15:30 ` [PATCH 24/32] ext2, ext4: make mb block cache names more explicit Theodore Ts'o
-- strict thread matches above, loose matches on Subject: below --
2017-06-21 21:21 [PATCH 01/32] ext4: xattr-in-inode support Tahsin Erdogan
2017-06-21 21:21 ` [PATCH 26/32] ext4: cleanup transaction restarts during inode deletion Tahsin Erdogan
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).