summaryrefslogtreecommitdiff
path: root/fs/ext4/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/super.c')
-rw-r--r--fs/ext4/super.c725
1 files changed, 532 insertions, 193 deletions
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ceebaf853beb..c6e0cb3d1f4a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -74,7 +74,6 @@ static const char *ext4_decode_error(struct super_block *sb, int errno,
static int ext4_remount(struct super_block *sb, int *flags, char *data);
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ext4_unfreeze(struct super_block *sb);
-static void ext4_write_super(struct super_block *sb);
static int ext4_freeze(struct super_block *sb);
static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data);
@@ -112,6 +111,48 @@ static struct file_system_type ext3_fs_type = {
#define IS_EXT3_SB(sb) (0)
#endif
+static int ext4_verify_csum_type(struct super_block *sb,
+ struct ext4_super_block *es)
+{
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ return 1;
+
+ return es->s_checksum_type == EXT4_CRC32C_CHKSUM;
+}
+
+static __le32 ext4_superblock_csum(struct super_block *sb,
+ struct ext4_super_block *es)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ int offset = offsetof(struct ext4_super_block, s_checksum);
+ __u32 csum;
+
+ csum = ext4_chksum(sbi, ~0, (char *)es, offset);
+
+ return cpu_to_le32(csum);
+}
+
+int ext4_superblock_csum_verify(struct super_block *sb,
+ struct ext4_super_block *es)
+{
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ return 1;
+
+ return es->s_checksum == ext4_superblock_csum(sb, es);
+}
+
+void ext4_superblock_csum_set(struct super_block *sb,
+ struct ext4_super_block *es)
+{
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ return;
+
+ es->s_checksum = ext4_superblock_csum(sb, es);
+}
+
void *ext4_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
@@ -285,38 +326,17 @@ static void ext4_put_nojournal(handle_t *handle)
/*
* Wrappers for jbd2_journal_start/end.
- *
- * The only special thing we need to do here is to make sure that all
- * journal_end calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- *
- * To avoid j_barrier hold in userspace when a user calls freeze(),
- * ext4 prevents a new handle from being started by s_frozen, which
- * is in an upper layer.
*/
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
{
journal_t *journal;
- handle_t *handle;
trace_ext4_journal_start(sb, nblocks, _RET_IP_);
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
+ WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
journal = EXT4_SB(sb)->s_journal;
- handle = ext4_journal_current_handle();
-
- /*
- * If a handle has been started, it should be allowed to
- * finish, otherwise deadlock could happen between freeze
- * and others(e.g. truncate) due to the restart of the
- * journal handle if the filesystem is forzen and active
- * handles are not stopped.
- */
- if (!handle)
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
-
if (!journal)
return ext4_get_nojournal();
/*
@@ -331,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks)
return jbd2_journal_start(journal, nblocks);
}
-/*
- * The only special thing we need to do here is to make sure that all
- * jbd2_journal_stop calls result in the superblock being marked dirty, so
- * that sync() will call the filesystem's write_super callback if
- * appropriate.
- */
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
@@ -497,6 +511,7 @@ void __ext4_error(struct super_block *sb, const char *function,
printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n",
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
@@ -853,7 +868,7 @@ static void ext4_put_super(struct super_block *sb)
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
- if (sb->s_dirt || !(sb->s_flags & MS_RDONLY))
+ if (!(sb->s_flags & MS_RDONLY))
ext4_commit_super(sb, 1);
if (sbi->s_proc) {
@@ -905,6 +920,8 @@ static void ext4_put_super(struct super_block *sb)
unlock_super(sb);
kobject_put(&sbi->s_kobj);
wait_for_completion(&sbi->s_kobj_unregister);
+ if (sbi->s_chksum_driver)
+ crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->s_blockgroup_lock);
kfree(sbi);
}
@@ -931,6 +948,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
ei->i_da_metadata_calc_len = 0;
+ ei->i_da_metadata_calc_last_lblock = 0;
spin_lock_init(&(ei->i_block_reservation_lock));
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
@@ -1007,7 +1025,7 @@ static void destroy_inodecache(void)
void ext4_clear_inode(struct inode *inode)
{
invalidate_inode_buffers(inode);
- end_writeback(inode);
+ clear_inode(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
if (EXT4_I(inode)->jinode) {
@@ -1092,12 +1110,18 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot);
static int ext4_write_info(struct super_block *sb, int type);
static int ext4_quota_on(struct super_block *sb, int type, int format_id,
struct path *path);
+static int ext4_quota_on_sysfile(struct super_block *sb, int type,
+ int format_id);
static int ext4_quota_off(struct super_block *sb, int type);
+static int ext4_quota_off_sysfile(struct super_block *sb, int type);
static int ext4_quota_on_mount(struct super_block *sb, int type);
static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
size_t len, loff_t off);
static ssize_t ext4_quota_write(struct super_block *sb, int type,
const char *data, size_t len, loff_t off);
+static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
+ unsigned int flags);
+static int ext4_enable_quotas(struct super_block *sb);
static const struct dquot_operations ext4_quota_operations = {
.get_reserved_space = ext4_get_reserved_space,
@@ -1119,6 +1143,16 @@ static const struct quotactl_ops ext4_qctl_operations = {
.get_dqblk = dquot_get_dqblk,
.set_dqblk = dquot_set_dqblk
};
+
+static const struct quotactl_ops ext4_qctl_sysfile_operations = {
+ .quota_on_meta = ext4_quota_on_sysfile,
+ .quota_off = ext4_quota_off_sysfile,
+ .quota_sync = dquot_quota_sync,
+ .get_info = dquot_get_dqinfo,
+ .set_info = dquot_set_dqinfo,
+ .get_dqblk = dquot_get_dqblk,
+ .set_dqblk = dquot_set_dqblk
+};
#endif
static const struct super_operations ext4_sops = {
@@ -1149,7 +1183,6 @@ static const struct super_operations ext4_nojournal_sops = {
.dirty_inode = ext4_dirty_inode,
.drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
- .write_super = ext4_write_super,
.put_super = ext4_put_super,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
@@ -1305,20 +1338,20 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
ext4_msg(sb, KERN_ERR,
"Cannot change journaled "
"quota options when quota turned on");
- return 0;
+ return -1;
}
qname = match_strdup(args);
if (!qname) {
ext4_msg(sb, KERN_ERR,
"Not enough memory for storing quotafile name");
- return 0;
+ return -1;
}
if (sbi->s_qf_names[qtype] &&
strcmp(sbi->s_qf_names[qtype], qname)) {
ext4_msg(sb, KERN_ERR,
"%s quota file already specified", QTYPE2NAME(qtype));
kfree(qname);
- return 0;
+ return -1;
}
sbi->s_qf_names[qtype] = qname;
if (strchr(sbi->s_qf_names[qtype], '/')) {
@@ -1326,7 +1359,7 @@ static int set_qf_name(struct super_block *sb, int qtype, substring_t *args)
"quotafile must be on filesystem root");
kfree(sbi->s_qf_names[qtype]);
sbi->s_qf_names[qtype] = NULL;
- return 0;
+ return -1;
}
set_opt(sb, QUOTA);
return 1;
@@ -1341,7 +1374,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
sbi->s_qf_names[qtype]) {
ext4_msg(sb, KERN_ERR, "Cannot change journaled quota options"
" when quota turned on");
- return 0;
+ return -1;
}
/*
* The space will be released later when all options are confirmed
@@ -1448,8 +1481,20 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
const struct mount_opts *m;
+ kuid_t uid;
+ kgid_t gid;
int arg = 0;
+#ifdef CONFIG_QUOTA
+ if (token == Opt_usrjquota)
+ return set_qf_name(sb, USRQUOTA, &args[0]);
+ else if (token == Opt_grpjquota)
+ return set_qf_name(sb, GRPQUOTA, &args[0]);
+ else if (token == Opt_offusrjquota)
+ return clear_qf_name(sb, USRQUOTA);
+ else if (token == Opt_offgrpjquota)
+ return clear_qf_name(sb, GRPQUOTA);
+#endif
if (args->from && match_int(args, &arg))
return -1;
switch (token) {
@@ -1464,10 +1509,20 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
"Ignoring removed %s option", opt);
return 1;
case Opt_resuid:
- sbi->s_resuid = arg;
+ uid = make_kuid(current_user_ns(), arg);
+ if (!uid_valid(uid)) {
+ ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg);
+ return -1;
+ }
+ sbi->s_resuid = uid;
return 1;
case Opt_resgid:
- sbi->s_resgid = arg;
+ gid = make_kgid(current_user_ns(), arg);
+ if (!gid_valid(gid)) {
+ ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg);
+ return -1;
+ }
+ sbi->s_resgid = gid;
return 1;
case Opt_abort:
sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
@@ -1549,18 +1604,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
sbi->s_mount_opt |= m->mount_opt;
}
#ifdef CONFIG_QUOTA
- } else if (token == Opt_usrjquota) {
- if (!set_qf_name(sb, USRQUOTA, &args[0]))
- return -1;
- } else if (token == Opt_grpjquota) {
- if (!set_qf_name(sb, GRPQUOTA, &args[0]))
- return -1;
- } else if (token == Opt_offusrjquota) {
- if (!clear_qf_name(sb, USRQUOTA))
- return -1;
- } else if (token == Opt_offgrpjquota) {
- if (!clear_qf_name(sb, GRPQUOTA))
- return -1;
} else if (m->flags & MOPT_QFMT) {
if (sb_any_quota_loaded(sb) &&
sbi->s_jquota_fmt != m->mount_opt) {
@@ -1599,7 +1642,9 @@ static int parse_options(char *options, struct super_block *sb,
unsigned int *journal_ioprio,
int is_remount)
{
+#ifdef CONFIG_QUOTA
struct ext4_sb_info *sbi = EXT4_SB(sb);
+#endif
char *p;
substring_t args[MAX_OPT_ARGS];
int token;
@@ -1732,12 +1777,14 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
SEQ_OPTS_PRINT("%s", token2str(m->token));
}
- if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID ||
+ if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) ||
le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID)
- SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid);
- if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID ||
+ SEQ_OPTS_PRINT("resuid=%u",
+ from_kuid_munged(&init_user_ns, sbi->s_resuid));
+ if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) ||
le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID)
- SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid);
+ SEQ_OPTS_PRINT("resgid=%u",
+ from_kgid_munged(&init_user_ns, sbi->s_resgid));
def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors);
if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO)
SEQ_OPTS_PUTS("errors=remount-ro");
@@ -1908,43 +1955,69 @@ failed:
return 0;
}
-__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
- struct ext4_group_desc *gdp)
+static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group,
+ struct ext4_group_desc *gdp)
{
+ int offset;
__u16 crc = 0;
+ __le32 le_group = cpu_to_le32(block_group);
- if (sbi->s_es->s_feature_ro_compat &
- cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
- int offset = offsetof(struct ext4_group_desc, bg_checksum);
- __le32 le_group = cpu_to_le32(block_group);
-
- crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
- crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
- crc = crc16(crc, (__u8 *)gdp, offset);
- offset += sizeof(gdp->bg_checksum); /* skip checksum */
- /* for checksum of struct ext4_group_desc do the rest...*/
- if ((sbi->s_es->s_feature_incompat &
- cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
- offset < le16_to_cpu(sbi->s_es->s_desc_size))
- crc = crc16(crc, (__u8 *)gdp + offset,
- le16_to_cpu(sbi->s_es->s_desc_size) -
- offset);
+ if ((sbi->s_es->s_feature_ro_compat &
+ cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) {
+ /* Use new metadata_csum algorithm */
+ __u16 old_csum;
+ __u32 csum32;
+
+ old_csum = gdp->bg_checksum;
+ gdp->bg_checksum = 0;
+ csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group,
+ sizeof(le_group));
+ csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp,
+ sbi->s_desc_size);
+ gdp->bg_checksum = old_csum;
+
+ crc = csum32 & 0xFFFF;
+ goto out;
}
+ /* old crc16 code */
+ offset = offsetof(struct ext4_group_desc, bg_checksum);
+
+ crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid));
+ crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group));
+ crc = crc16(crc, (__u8 *)gdp, offset);
+ offset += sizeof(gdp->bg_checksum); /* skip checksum */
+ /* for checksum of struct ext4_group_desc do the rest...*/
+ if ((sbi->s_es->s_feature_incompat &
+ cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) &&
+ offset < le16_to_cpu(sbi->s_es->s_desc_size))
+ crc = crc16(crc, (__u8 *)gdp + offset,
+ le16_to_cpu(sbi->s_es->s_desc_size) -
+ offset);
+
+out:
return cpu_to_le16(crc);
}
-int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group,
+int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group,
struct ext4_group_desc *gdp)
{
- if ((sbi->s_es->s_feature_ro_compat &
- cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) &&
- (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp)))
+ if (ext4_has_group_desc_csum(sb) &&
+ (gdp->bg_checksum != ext4_group_desc_csum(EXT4_SB(sb),
+ block_group, gdp)))
return 0;
return 1;
}
+void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group,
+ struct ext4_group_desc *gdp)
+{
+ if (!ext4_has_group_desc_csum(sb))
+ return;
+ gdp->bg_checksum = ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp);
+}
+
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
ext4_group_t *first_not_zeroed)
@@ -1999,7 +2072,7 @@ static int ext4_check_descriptors(struct super_block *sb,
return 0;
}
ext4_lock_group(sb, i);
- if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
+ if (!ext4_group_desc_csum_verify(sb, i, gdp)) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Checksum for group %u failed (%u!=%u)",
i, le16_to_cpu(ext4_group_desc_csum(sbi, i,
@@ -2366,18 +2439,6 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
-static ssize_t extent_cache_hits_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_hits);
-}
-
-static ssize_t extent_cache_misses_show(struct ext4_attr *a,
- struct ext4_sb_info *sbi, char *buf)
-{
- return snprintf(buf, PAGE_SIZE, "%lu\n", sbi->extent_cache_misses);
-}
-
static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
struct ext4_sb_info *sbi,
const char *buf, size_t count)
@@ -2415,6 +2476,23 @@ static ssize_t sbi_ui_store(struct ext4_attr *a,
return count;
}
+static ssize_t trigger_test_error(struct ext4_attr *a,
+ struct ext4_sb_info *sbi,
+ const char *buf, size_t count)
+{
+ int len = count;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (len && buf[len-1] == '\n')
+ len--;
+
+ if (len)
+ ext4_error(sbi->s_sb, "%.*s", len, buf);
+ return count;
+}
+
#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
@@ -2435,8 +2513,6 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
EXT4_RO_ATTR(delayed_allocation_blocks);
EXT4_RO_ATTR(session_write_kbytes);
EXT4_RO_ATTR(lifetime_write_kbytes);
-EXT4_RO_ATTR(extent_cache_hits);
-EXT4_RO_ATTR(extent_cache_misses);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, sbi_ui_show,
inode_readahead_blks_store, s_inode_readahead_blks);
EXT4_RW_ATTR_SBI_UI(inode_goal, s_inode_goal);
@@ -2447,13 +2523,12 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
- ATTR_LIST(extent_cache_hits),
- ATTR_LIST(extent_cache_misses),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
@@ -2463,6 +2538,7 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(max_writeback_mb_bump),
+ ATTR_LIST(trigger_fs_error),
NULL,
};
@@ -2573,6 +2649,16 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
"extents feature\n");
return 0;
}
+
+#ifndef CONFIG_QUOTA
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+ !readonly) {
+ ext4_msg(sb, KERN_ERR,
+ "Filesystem with quota feature cannot be mounted RDWR "
+ "without CONFIG_QUOTA");
+ return 0;
+ }
+#endif /* CONFIG_QUOTA */
return 1;
}
@@ -2635,6 +2721,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
sb = elr->lr_super;
ngroups = EXT4_SB(sb)->s_groups_count;
+ sb_start_write(sb);
for (group = elr->lr_next_group; group < ngroups; group++) {
gdp = ext4_get_group_desc(sb, group, NULL);
if (!gdp) {
@@ -2661,6 +2748,7 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
elr->lr_next_sched = jiffies + elr->lr_timeout;
elr->lr_next_group = group + 1;
}
+ sb_end_write(sb);
return ret;
}
@@ -2959,6 +3047,156 @@ static void ext4_destroy_lazyinit_thread(void)
kthread_stop(ext4_lazyinit_task);
}
+static int set_journal_csum_feature_set(struct super_block *sb)
+{
+ int ret = 1;
+ int compat, incompat;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ /* journal checksum v2 */
+ compat = 0;
+ incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+ } else {
+ /* journal checksum v1 */
+ compat = JBD2_FEATURE_COMPAT_CHECKSUM;
+ incompat = 0;
+ }
+
+ if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+ ret = jbd2_journal_set_features(sbi->s_journal,
+ compat, 0,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+ incompat);
+ } else if (test_opt(sb, JOURNAL_CHECKSUM)) {
+ ret = jbd2_journal_set_features(sbi->s_journal,
+ compat, 0,
+ incompat);
+ jbd2_journal_clear_features(sbi->s_journal, 0, 0,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+ } else {
+ jbd2_journal_clear_features(sbi->s_journal,
+ JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+ JBD2_FEATURE_INCOMPAT_CSUM_V2);
+ }
+
+ return ret;
+}
+
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc. This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time. We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock. If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
+static int count_overhead(struct super_block *sb, ext4_group_t grp,
+ char *buf)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_group_desc *gdp;
+ ext4_fsblk_t first_block, last_block, b;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+ int s, j, count = 0;
+
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC))
+ return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) +
+ sbi->s_itb_per_group + 2);
+
+ first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
+ (grp * EXT4_BLOCKS_PER_GROUP(sb));
+ last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
+ for (i = 0; i < ngroups; i++) {
+ gdp = ext4_get_group_desc(sb, i, NULL);
+ b = ext4_block_bitmap(sb, gdp);
+ if (b >= first_block && b <= last_block) {
+ ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
+ count++;
+ }
+ b = ext4_inode_bitmap(sb, gdp);
+ if (b >= first_block && b <= last_block) {
+ ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
+ count++;
+ }
+ b = ext4_inode_table(sb, gdp);
+ if (b >= first_block && b + sbi->s_itb_per_group <= last_block)
+ for (j = 0; j < sbi->s_itb_per_group; j++, b++) {
+ int c = EXT4_B2C(sbi, b - first_block);
+ ext4_set_bit(c, buf);
+ count++;
+ }
+ if (i != grp)
+ continue;
+ s = 0;
+ if (ext4_bg_has_super(sb, grp)) {
+ ext4_set_bit(s++, buf);
+ count++;
+ }
+ for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) {
+ ext4_set_bit(EXT4_B2C(sbi, s++), buf);
+ count++;
+ }
+ }
+ if (!count)
+ return 0;
+ return EXT4_CLUSTERS_PER_GROUP(sb) -
+ ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8);
+}
+
+/*
+ * Compute the overhead and stash it in sbi->s_overhead
+ */
+int ext4_calculate_overhead(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+ ext4_fsblk_t overhead = 0;
+ char *buf = (char *) get_zeroed_page(GFP_KERNEL);
+
+ memset(buf, 0, PAGE_SIZE);
+ if (!buf)
+ return -ENOMEM;
+
+ /*
+ * Compute the overhead (FS structures). This is constant
+ * for a given filesystem unless the number of block groups
+ * changes so we cache the previous value until it does.
+ */
+
+ /*
+ * All of the blocks before first_data_block are overhead
+ */
+ overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
+
+ /*
+ * Add the overhead found in each block group
+ */
+ for (i = 0; i < ngroups; i++) {
+ int blks;
+
+ blks = count_overhead(sb, i, buf);
+ overhead += blks;
+ if (blks)
+ memset(buf, 0, PAGE_SIZE);
+ cond_resched();
+ }
+ sbi->s_overhead = overhead;
+ smp_wmb();
+ free_page((unsigned long) buf);
+ return 0;
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
{
char *orig_data = kstrdup(data, GFP_KERNEL);
@@ -2995,9 +3233,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto out_free_orig;
}
sb->s_fs_info = sbi;
+ sbi->s_sb = sb;
sbi->s_mount_opt = 0;
- sbi->s_resuid = EXT4_DEF_RESUID;
- sbi->s_resgid = EXT4_DEF_RESGID;
+ sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID);
+ sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID);
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sb_block = sb_block;
if (sb->s_bdev->bd_part)
@@ -3034,13 +3273,54 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* Note: s_es must be initialized as soon as possible because
* some ext4 macro-instructions depend on its value
*/
- es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+ es = (struct ext4_super_block *) (bh->b_data + offset);
sbi->s_es = es;
sb->s_magic = le16_to_cpu(es->s_magic);
if (sb->s_magic != EXT4_SUPER_MAGIC)
goto cantfind_ext4;
sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written);
+ /* Warn if metadata_csum and gdt_csum are both set. */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) &&
+ EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM))
+ ext4_warning(sb, KERN_INFO "metadata_csum and uninit_bg are "
+ "redundant flags; please run fsck.");
+
+ /* Check for a known checksum algorithm */
+ if (!ext4_verify_csum_type(sb, es)) {
+ ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
+ "unknown checksum algorithm.");
+ silent = 1;
+ goto cantfind_ext4;
+ }
+
+ /* Load the checksum driver */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
+ 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.");
+ ret = PTR_ERR(sbi->s_chksum_driver);
+ sbi->s_chksum_driver = NULL;
+ goto failed_mount;
+ }
+ }
+
+ /* Check superblock checksum */
+ if (!ext4_superblock_csum_verify(sb, es)) {
+ ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with "
+ "invalid superblock checksum. Run e2fsck?");
+ silent = 1;
+ goto cantfind_ext4;
+ }
+
+ /* Precompute checksum seed for all metadata */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))
+ sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
+ sizeof(es->s_uuid));
+
/* Set defaults before we parse the mount options */
def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
set_opt(sb, INIT_INODE_TABLE);
@@ -3076,8 +3356,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (def_mount_opts & EXT4_DEFM_DISCARD)
set_opt(sb, DISCARD);
- sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
- sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
+ sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
+ sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ;
sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME;
sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME;
@@ -3202,7 +3482,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"Can't read superblock on 2nd try");
goto failed_mount;
}
- es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
+ es = (struct ext4_super_block *)(bh->b_data + offset);
sbi->s_es = es;
if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
ext4_msg(sb, KERN_ERR,
@@ -3394,6 +3674,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
GFP_KERNEL);
if (sbi->s_group_desc == NULL) {
ext4_msg(sb, KERN_ERR, "not enough memory");
+ ret = -ENOMEM;
goto failed_mount;
}
@@ -3451,6 +3732,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
+ ret = err;
goto failed_mount3;
}
@@ -3470,6 +3752,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
#ifdef CONFIG_QUOTA
sb->s_qcop = &ext4_qctl_operations;
sb->dq_op = &ext4_quota_operations;
+
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ /* Use qctl operations for hidden quota files. */
+ sb->s_qcop = &ext4_qctl_sysfile_operations;
+ }
#endif
memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
@@ -3508,26 +3795,17 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto no_journal;
}
- if (ext4_blocks_count(es) > 0xffffffffULL &&
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT) &&
!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
JBD2_FEATURE_INCOMPAT_64BIT)) {
ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature");
goto failed_mount_wq;
}
- if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
- jbd2_journal_set_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
- } else if (test_opt(sb, JOURNAL_CHECKSUM)) {
- jbd2_journal_set_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
- jbd2_journal_clear_features(sbi->s_journal, 0, 0,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
- } else {
- jbd2_journal_clear_features(sbi->s_journal,
- JBD2_FEATURE_COMPAT_CHECKSUM, 0,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+ if (!set_journal_csum_feature_set(sb)) {
+ ext4_msg(sb, KERN_ERR, "Failed to set journal checksum "
+ "feature set");
+ goto failed_mount_wq;
}
/* We have now updated the journal if required, so we can
@@ -3574,6 +3852,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
no_journal:
/*
+ * Get the # of file system overhead blocks from the
+ * superblock if present.
+ */
+ if (es->s_overhead_clusters)
+ sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters);
+ else {
+ ret = ext4_calculate_overhead(sb);
+ if (ret)
+ goto failed_mount_wq;
+ }
+
+ /*
* The maximum number of concurrent works can be high and
* concurrency isn't really necessary. Limit it to 1.
*/
@@ -3608,7 +3898,8 @@ no_journal:
goto failed_mount4;
}
- ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY);
+ if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
+ sb->s_flags |= MS_RDONLY;
/* determine the minimum size of new large inodes, if present */
if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
@@ -3643,7 +3934,7 @@ no_journal:
}
ext4_ext_init(sb);
- err = ext4_mb_init(sb, needs_recovery);
+ err = ext4_mb_init(sb);
if (err) {
ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)",
err);
@@ -3678,6 +3969,16 @@ no_journal:
} else
descr = "out journal";
+#ifdef CONFIG_QUOTA
+ /* Enable quota usage during mount. */
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA) &&
+ !(sb->s_flags & MS_RDONLY)) {
+ ret = ext4_enable_quotas(sb);
+ if (ret)
+ goto failed_mount7;
+ }
+#endif /* CONFIG_QUOTA */
+
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
"Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
@@ -3726,6 +4027,8 @@ failed_mount2:
brelse(sbi->s_group_desc[i]);
ext4_kvfree(sbi->s_group_desc);
failed_mount:
+ if (sbi->s_chksum_driver)
+ crypto_free_shash(sbi->s_chksum_driver);
if (sbi->s_proc) {
remove_proc_entry("options", sbi->s_proc);
remove_proc_entry(sb->s_id, ext4_proc_root);
@@ -3849,7 +4152,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
goto out_bdev;
}
- es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
+ es = (struct ext4_super_block *) (bh->b_data + offset);
if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
@@ -4039,8 +4342,8 @@ static int ext4_commit_super(struct super_block *sb, int sync)
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
&EXT4_SB(sb)->s_freeinodes_counter));
- sb->s_dirt = 0;
BUFFER_TRACE(sbh, "marking dirty");
+ ext4_superblock_csum_set(sb, es);
mark_buffer_dirty(sbh);
if (sync) {
error = sync_dirty_buffer(sbh);
@@ -4121,6 +4424,7 @@ static void ext4_clear_journal_err(struct super_block *sb,
ext4_commit_super(sb, 1);
jbd2_journal_clear_err(journal);
+ jbd2_journal_update_sb_errno(journal);
}
}
@@ -4137,21 +4441,12 @@ int ext4_force_commit(struct super_block *sb)
return 0;
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
+ if (journal)
ret = ext4_journal_force_commit(journal);
- }
return ret;
}
-static void ext4_write_super(struct super_block *sb)
-{
- lock_super(sb);
- ext4_commit_super(sb, 1);
- unlock_super(sb);
-}
-
static int ext4_sync_fs(struct super_block *sb, int wait)
{
int ret = 0;
@@ -4160,6 +4455,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->dio_unwritten_wq);
+ /*
+ * Writeback quota in non-journalled quota case - journalled quota has
+ * no dirty dquots
+ */
+ dquot_writeback_dquots(sb, -1);
if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
jbd2_log_wait_commit(sbi->s_journal, target);
@@ -4172,9 +4472,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
* gives us a chance to flush the journal completely and mark the fs clean.
*
* Note that only this function cannot bring a filesystem to be in a clean
- * state independently, because ext4 prevents a new handle from being started
- * by @sb->s_frozen, which stays in an upper layer. It thus needs help from
- * the upper layer.
+ * state independently. It relies on upper layer to stop all data & metadata
+ * modifications.
*/
static int ext4_freeze(struct super_block *sb)
{
@@ -4201,7 +4500,7 @@ static int ext4_freeze(struct super_block *sb)
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
error = ext4_commit_super(sb, 1);
out:
- /* we rely on s_frozen to stop further updates */
+ /* we rely on upper layer to stop further updates */
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
return error;
}
@@ -4229,8 +4528,8 @@ static int ext4_unfreeze(struct super_block *sb)
struct ext4_mount_options {
unsigned long s_mount_opt;
unsigned long s_mount_opt2;
- uid_t s_resuid;
- gid_t s_resgid;
+ kuid_t s_resuid;
+ kgid_t s_resgid;
unsigned long s_commit_interval;
u32 s_min_batch_time, s_max_batch_time;
#ifdef CONFIG_QUOTA
@@ -4335,7 +4634,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
struct ext4_group_desc *gdp =
ext4_get_group_desc(sb, g, NULL);
- if (!ext4_group_desc_csum_verify(sbi, g, gdp)) {
+ if (!ext4_group_desc_csum_verify(sb, g, gdp)) {
ext4_msg(sb, KERN_ERR,
"ext4_remount: Checksum for group %u failed (%u!=%u)",
g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)),
@@ -4397,16 +4696,26 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
if (sbi->s_journal == NULL)
ext4_commit_super(sb, 1);
+ unlock_super(sb);
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
if (old_opts.s_qf_names[i] &&
old_opts.s_qf_names[i] != sbi->s_qf_names[i])
kfree(old_opts.s_qf_names[i]);
+ if (enable_quota) {
+ if (sb_any_quota_suspended(sb))
+ dquot_resume(sb, -1);
+ else if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
+ EXT4_FEATURE_RO_COMPAT_QUOTA)) {
+ err = ext4_enable_quotas(sb);
+ if (err) {
+ lock_super(sb);
+ goto restore_opts;
+ }
+ }
+ }
#endif
- unlock_super(sb);
- if (enable_quota)
- dquot_resume(sb, -1);
ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
kfree(orig_data);
@@ -4435,67 +4744,21 @@ restore_opts:
return err;
}
-/*
- * Note: calculating the overhead so we can be compatible with
- * historical BSD practice is quite difficult in the face of
- * clusters/bigalloc. This is because multiple metadata blocks from
- * different block group can end up in the same allocation cluster.
- * Calculating the exact overhead in the face of clustered allocation
- * requires either O(all block bitmaps) in memory or O(number of block
- * groups**2) in time. We will still calculate the superblock for
- * older file systems --- and if we come across with a bigalloc file
- * system with zero in s_overhead_clusters the estimate will be close to
- * correct especially for very large cluster sizes --- but for newer
- * file systems, it's better to calculate this figure once at mkfs
- * time, and store it in the superblock. If the superblock value is
- * present (even for non-bigalloc file systems), we will use it.
- */
static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
- struct ext4_group_desc *gdp;
+ ext4_fsblk_t overhead = 0;
u64 fsid;
s64 bfree;
- if (test_opt(sb, MINIX_DF)) {
- sbi->s_overhead_last = 0;
- } else if (es->s_overhead_clusters) {
- sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
- } else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
- ext4_group_t i, ngroups = ext4_get_groups_count(sb);
- ext4_fsblk_t overhead = 0;
-
- /*
- * Compute the overhead (FS structures). This is constant
- * for a given filesystem unless the number of block groups
- * changes so we cache the previous value until it does.
- */
-
- /*
- * All of the blocks before first_data_block are
- * overhead
- */
- overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
-
- /*
- * Add the overhead found in each block group
- */
- for (i = 0; i < ngroups; i++) {
- gdp = ext4_get_group_desc(sb, i, NULL);
- overhead += ext4_num_overhead_clusters(sb, i, gdp);
- cond_resched();
- }
- sbi->s_overhead_last = overhead;
- smp_wmb();
- sbi->s_blocks_last = ext4_blocks_count(es);
- }
+ if (!test_opt(sb, MINIX_DF))
+ overhead = sbi->s_overhead;
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = (ext4_blocks_count(es) -
- EXT4_C2B(sbi, sbi->s_overhead_last));
+ buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead);
bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
/* prevent underflow in case that few free space is available */
@@ -4665,6 +4928,74 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
return dquot_quota_on(sb, type, format_id, path);
}
+static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
+ unsigned int flags)
+{
+ int err;
+ struct inode *qf_inode;
+ unsigned long qf_inums[MAXQUOTAS] = {
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
+ };
+
+ BUG_ON(!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA));
+
+ if (!qf_inums[type])
+ return -EPERM;
+
+ qf_inode = ext4_iget(sb, qf_inums[type]);
+ if (IS_ERR(qf_inode)) {
+ ext4_error(sb, "Bad quota inode # %lu", qf_inums[type]);
+ return PTR_ERR(qf_inode);
+ }
+
+ err = dquot_enable(qf_inode, type, format_id, flags);
+ iput(qf_inode);
+
+ return err;
+}
+
+/* Enable usage tracking for all quota types. */
+static int ext4_enable_quotas(struct super_block *sb)
+{
+ int type, err = 0;
+ unsigned long qf_inums[MAXQUOTAS] = {
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_usr_quota_inum),
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_grp_quota_inum)
+ };
+
+ sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE;
+ for (type = 0; type < MAXQUOTAS; type++) {
+ if (qf_inums[type]) {
+ err = ext4_quota_enable(sb, type, QFMT_VFS_V1,
+ DQUOT_USAGE_ENABLED);
+ if (err) {
+ ext4_warning(sb,
+ "Failed to enable quota (type=%d) "
+ "tracking. Please run e2fsck to fix.",
+ type);
+ return err;
+ }
+ }
+ }
+ return 0;
+}
+
+/*
+ * quota_on function that is used when QUOTA feature is set.
+ */
+static int ext4_quota_on_sysfile(struct super_block *sb, int type,
+ int format_id)
+{
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
+ return -EINVAL;
+
+ /*
+ * USAGE was enabled at mount time. Only need to enable LIMITS now.
+ */
+ return ext4_quota_enable(sb, type, format_id, DQUOT_LIMITS_ENABLED);
+}
+
static int ext4_quota_off(struct super_block *sb, int type)
{
struct inode *inode = sb_dqopt(sb)->files[type];
@@ -4691,6 +5022,18 @@ out:
return dquot_quota_off(sb, type);
}
+/*
+ * quota_off function that is used when QUOTA feature is set.
+ */
+static int ext4_quota_off_sysfile(struct super_block *sb, int type)
+{
+ if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA))
+ return -EINVAL;
+
+ /* Disable only the limits. */
+ return dquot_disable(sb, type, DQUOT_LIMITS_ENABLED);
+}
+
/* Read data from quotafile - avoid pagecache and such because we cannot afford
* acquiring the locks... As quota files are never truncated and quota code
* itself serializes the operations (and no one else should touch the files)
@@ -4760,7 +5103,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
return -EIO;
}
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
@@ -4776,16 +5118,13 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
err = ext4_handle_dirty_metadata(handle, NULL, bh);
brelse(bh);
out:
- if (err) {
- mutex_unlock(&inode->i_mutex);
+ if (err)
return err;
- }
if (inode->i_size < off + len) {
i_size_write(inode, off + len);
EXT4_I(inode)->i_disksize = inode->i_size;
ext4_mark_inode_dirty(handle, inode);
}
- mutex_unlock(&inode->i_mutex);
return len;
}