aboutsummaryrefslogtreecommitdiff
path: root/fs/ext4/super.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/super.c')
-rw-r--r--fs/ext4/super.c493
1 files changed, 345 insertions, 148 deletions
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94cc84db7c9..6df7bc611db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -59,6 +59,7 @@ static struct kset *ext4_kset;
static struct ext4_lazy_init *ext4_li_info;
static struct mutex ext4_li_mtx;
static struct ext4_features *ext4_feat;
+static int ext4_mballoc_ready;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
@@ -69,6 +70,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb,
static void ext4_clear_journal_err(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_sync_fs(struct super_block *sb, int wait);
+static int ext4_sync_fs_nojournal(struct super_block *sb, int wait);
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);
@@ -136,8 +138,8 @@ static __le32 ext4_superblock_csum(struct super_block *sb,
return cpu_to_le32(csum);
}
-int ext4_superblock_csum_verify(struct super_block *sb,
- struct ext4_super_block *es)
+static 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))
@@ -161,7 +163,7 @@ void *ext4_kvmalloc(size_t size, gfp_t flags)
{
void *ret;
- ret = kmalloc(size, flags);
+ ret = kmalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags, PAGE_KERNEL);
return ret;
@@ -171,7 +173,7 @@ void *ext4_kvzalloc(size_t size, gfp_t flags)
{
void *ret;
- ret = kzalloc(size, flags);
+ ret = kzalloc(size, flags | __GFP_NOWARN);
if (!ret)
ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
return ret;
@@ -398,6 +400,11 @@ static void ext4_handle_error(struct super_block *sb)
}
if (test_opt(sb, ERRORS_RO)) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+ /*
+ * Make sure updated value of ->s_mount_flags will be visible
+ * before ->s_flags update
+ */
+ smp_wmb();
sb->s_flags |= MS_RDONLY;
}
if (test_opt(sb, ERRORS_PANIC))
@@ -405,26 +412,32 @@ static void ext4_handle_error(struct super_block *sb)
sb->s_id);
}
+#define ext4_error_ratelimit(sb) \
+ ___ratelimit(&(EXT4_SB(sb)->s_err_ratelimit_state), \
+ "EXT4-fs error")
+
void __ext4_error(struct super_block *sb, const char *function,
unsigned int line, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- 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);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ 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);
}
-void ext4_error_inode(struct inode *inode, const char *function,
- unsigned int line, ext4_fsblk_t block,
- const char *fmt, ...)
+void __ext4_error_inode(struct inode *inode, const char *function,
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
struct va_format vaf;
@@ -432,28 +445,29 @@ void ext4_error_inode(struct inode *inode, const char *function,
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: block %llu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, &vaf);
+ else
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
+ "inode #%lu: comm %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: block %llu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, &vaf);
- else
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: "
- "inode #%lu: comm %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
-void ext4_error_file(struct file *file, const char *function,
- unsigned int line, ext4_fsblk_t block,
- const char *fmt, ...)
+void __ext4_error_file(struct file *file, const char *function,
+ unsigned int line, ext4_fsblk_t block,
+ const char *fmt, ...)
{
va_list args;
struct va_format vaf;
@@ -463,27 +477,28 @@ void ext4_error_file(struct file *file, const char *function,
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
+ if (ext4_error_ratelimit(inode->i_sb)) {
+ path = d_path(&(file->f_path), pathname, sizeof(pathname));
+ if (IS_ERR(path))
+ path = "(unknown)";
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ if (block)
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "block %llu: comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ block, current->comm, path, &vaf);
+ else
+ printk(KERN_CRIT
+ "EXT4-fs error (device %s): %s:%d: inode #%lu: "
+ "comm %s: path %s: %pV\n",
+ inode->i_sb->s_id, function, line, inode->i_ino,
+ current->comm, path, &vaf);
+ va_end(args);
+ }
save_error_info(inode->i_sb, function, line);
- path = d_path(&(file->f_path), pathname, sizeof(pathname));
- if (IS_ERR(path))
- path = "(unknown)";
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- if (block)
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "block %llu: comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- block, current->comm, path, &vaf);
- else
- printk(KERN_CRIT
- "EXT4-fs error (device %s): %s:%d: inode #%lu: "
- "comm %s: path %s: %pV\n",
- inode->i_sb->s_id, function, line, inode->i_ino,
- current->comm, path, &vaf);
- va_end(args);
-
ext4_handle_error(inode->i_sb);
}
@@ -537,11 +552,13 @@ void __ext4_std_error(struct super_block *sb, const char *function,
(sb->s_flags & MS_RDONLY))
return;
- errstr = ext4_decode_error(sb, errno, nbuf);
- printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
- sb->s_id, function, line, errstr);
- save_error_info(sb, function, line);
+ if (ext4_error_ratelimit(sb)) {
+ errstr = ext4_decode_error(sb, errno, nbuf);
+ printk(KERN_CRIT "EXT4-fs error (device %s) in %s:%d: %s\n",
+ sb->s_id, function, line, errstr);
+ }
+ save_error_info(sb, function, line);
ext4_handle_error(sb);
}
@@ -570,8 +587,13 @@ void __ext4_abort(struct super_block *sb, const char *function,
if ((sb->s_flags & MS_RDONLY) == 0) {
ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
- sb->s_flags |= MS_RDONLY;
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ /*
+ * Make sure updated value of ->s_mount_flags will be visible
+ * before ->s_flags update
+ */
+ smp_wmb();
+ sb->s_flags |= MS_RDONLY;
if (EXT4_SB(sb)->s_journal)
jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
save_error_info(sb, function, line);
@@ -580,11 +602,15 @@ void __ext4_abort(struct super_block *sb, const char *function,
panic("EXT4-fs panic from previous error\n");
}
-void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+void __ext4_msg(struct super_block *sb,
+ const char *prefix, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
@@ -598,6 +624,10 @@ void __ext4_warning(struct super_block *sb, const char *function,
struct va_format vaf;
va_list args;
+ if (!___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state),
+ "EXT4-fs warning"))
+ return;
+
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
@@ -621,18 +651,20 @@ __acquires(bitlock)
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
- va_start(args, fmt);
-
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
- sb->s_id, function, line, grp);
- if (ino)
- printk(KERN_CONT "inode %lu: ", ino);
- if (block)
- printk(KERN_CONT "block %llu:", (unsigned long long) block);
- printk(KERN_CONT "%pV\n", &vaf);
- va_end(args);
+ if (ext4_error_ratelimit(sb)) {
+ va_start(args, fmt);
+ vaf.fmt = fmt;
+ vaf.va = &args;
+ printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: group %u, ",
+ sb->s_id, function, line, grp);
+ if (ino)
+ printk(KERN_CONT "inode %lu: ", ino);
+ if (block)
+ printk(KERN_CONT "block %llu:",
+ (unsigned long long) block);
+ printk(KERN_CONT "%pV\n", &vaf);
+ va_end(args);
+ }
if (test_opt(sb, ERRORS_CONT)) {
ext4_commit_super(sb, 0);
@@ -750,8 +782,8 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
- flush_workqueue(sbi->dio_unwritten_wq);
- destroy_workqueue(sbi->dio_unwritten_wq);
+ flush_workqueue(sbi->rsv_conversion_wq);
+ destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
err = jbd2_journal_destroy(sbi->s_journal);
@@ -760,8 +792,8 @@ static void ext4_put_super(struct super_block *sb)
ext4_abort(sb, "Couldn't clean up the journal");
}
- ext4_es_unregister_shrinker(sb);
- del_timer(&sbi->s_err_report);
+ ext4_es_unregister_shrinker(sbi);
+ del_timer_sync(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
ext4_ext_release(sb);
@@ -814,6 +846,10 @@ 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_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
sb->s_fs_info = NULL;
@@ -843,12 +879,14 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
return NULL;
ei->vfs_inode.i_version = 1;
+ spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
ext4_es_init_tree(&ei->i_es_tree);
rwlock_init(&ei->i_es_lock);
INIT_LIST_HEAD(&ei->i_es_lru);
ei->i_es_lru_nr = 0;
+ ei->i_touch_when = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
@@ -859,13 +897,13 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_reserved_quota = 0;
#endif
ei->jinode = NULL;
- INIT_LIST_HEAD(&ei->i_completed_io_list);
+ INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
atomic_set(&ei->i_unwritten, 0);
- INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work);
+ INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
return &ei->vfs_inode;
}
@@ -908,7 +946,7 @@ static void init_once(void *foo)
inode_init_once(&ei->vfs_inode);
}
-static int init_inodecache(void)
+static int __init init_inodecache(void)
{
ext4_inode_cachep = kmem_cache_create("ext4_inode_cache",
sizeof(struct ext4_inode_info),
@@ -1093,6 +1131,7 @@ static const struct super_operations ext4_nojournal_sops = {
.dirty_inode = ext4_dirty_inode,
.drop_inode = ext4_drop_inode,
.evict_inode = ext4_evict_inode,
+ .sync_fs = ext4_sync_fs_nojournal,
.put_super = ext4_put_super,
.statfs = ext4_statfs,
.remount_fs = ext4_remount,
@@ -1116,8 +1155,8 @@ enum {
Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
- Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
- Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
+ Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
+ Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
@@ -1161,6 +1200,7 @@ static const match_table_t tokens = {
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_dev, "journal_dev=%u"},
+ {Opt_journal_path, "journal_path=%s"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
@@ -1320,6 +1360,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
#define MOPT_NO_EXT2 0x0100
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
+#define MOPT_STRING 0x0400
static const struct mount_opts {
int token;
@@ -1341,7 +1382,7 @@ static const struct mount_opts {
{Opt_delalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
- MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+ MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
@@ -1369,6 +1410,7 @@ static const struct mount_opts {
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
{Opt_journal_dev, 0, MOPT_GTE0},
+ {Opt_journal_path, 0, MOPT_STRING},
{Opt_journal_ioprio, 0, MOPT_GTE0},
{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
@@ -1462,7 +1504,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
- if (args->from && match_int(args, &arg))
+ if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
@@ -1483,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
} else if (token == Opt_max_batch_time) {
- if (arg == 0)
- arg = EXT4_DEF_MAX_BATCH_TIME;
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
sbi->s_min_batch_time = arg;
@@ -1526,6 +1566,44 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
*journal_devnum = arg;
+ } else if (token == Opt_journal_path) {
+ char *journal_path;
+ struct inode *journal_inode;
+ struct path path;
+ int error;
+
+ if (is_remount) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
+ return -1;
+ }
+ journal_path = match_strdup(&args[0]);
+ if (!journal_path) {
+ ext4_msg(sb, KERN_ERR, "error: could not dup "
+ "journal device string");
+ return -1;
+ }
+
+ error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+ if (error) {
+ ext4_msg(sb, KERN_ERR, "error: could not find "
+ "journal device path: error %d", error);
+ kfree(journal_path);
+ return -1;
+ }
+
+ journal_inode = path.dentry->d_inode;
+ if (!S_ISBLK(journal_inode->i_mode)) {
+ ext4_msg(sb, KERN_ERR, "error: journal path %s "
+ "is not a block device", journal_path);
+ path_put(&path);
+ kfree(journal_path);
+ return -1;
+ }
+
+ *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+ path_put(&path);
+ kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
if (arg > 7) {
ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
@@ -1684,12 +1762,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq,
if (sbi->s_qf_names[GRPQUOTA])
seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]);
-
- if (test_opt(sb, USRQUOTA))
- seq_puts(seq, ",usrquota");
-
- if (test_opt(sb, GRPQUOTA))
- seq_puts(seq, ",grpquota");
#endif
}
@@ -1830,7 +1902,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (!(sbi->s_mount_state & EXT4_VALID_FS))
ext4_msg(sb, KERN_WARNING, "warning: mounting unchecked fs, "
"running e2fsck is recommended");
- else if ((sbi->s_mount_state & EXT4_ERROR_FS))
+ else if (sbi->s_mount_state & EXT4_ERROR_FS)
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
@@ -1908,7 +1980,6 @@ static int ext4_fill_flex_info(struct super_block *sb)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_group_desc *gdp = NULL;
ext4_group_t flex_group;
- unsigned int groups_per_flex = 0;
int i, err;
sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
@@ -1916,7 +1987,6 @@ static int ext4_fill_flex_info(struct super_block *sb)
sbi->s_log_groups_per_flex = 0;
return 1;
}
- groups_per_flex = 1U << sbi->s_log_groups_per_flex;
err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count);
if (err)
@@ -2164,19 +2234,22 @@ static void ext4_orphan_cleanup(struct super_block *sb,
list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
dquot_initialize(inode);
if (inode->i_nlink) {
- ext4_msg(sb, KERN_DEBUG,
- "%s: truncating inode %lu to %lld bytes",
- __func__, inode->i_ino, inode->i_size);
+ if (test_opt(sb, DEBUG))
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: truncating inode %lu to %lld bytes",
+ __func__, inode->i_ino, inode->i_size);
jbd_debug(2, "truncating inode %lu to %lld bytes\n",
inode->i_ino, inode->i_size);
mutex_lock(&inode->i_mutex);
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
ext4_truncate(inode);
mutex_unlock(&inode->i_mutex);
nr_truncates++;
} else {
- ext4_msg(sb, KERN_DEBUG,
- "%s: deleting unreferenced inode %lu",
- __func__, inode->i_ino);
+ if (test_opt(sb, DEBUG))
+ ext4_msg(sb, KERN_DEBUG,
+ "%s: deleting unreferenced inode %lu",
+ __func__, inode->i_ino);
jbd_debug(2, "deleting unreferenced inode %lu\n",
inode->i_ino);
nr_orphans++;
@@ -2330,6 +2403,16 @@ static ext4_fsblk_t descriptor_loc(struct super_block *sb,
if (ext4_bg_has_super(sb, bg))
has_super = 1;
+ /*
+ * If we have a meta_bg fs with 1k blocks, group 0's GDT is at
+ * block 2, not 1. If s_first_data_block == 0 (bigalloc is enabled
+ * on modern mke2fs or blksize > 1k on older mke2fs) then we must
+ * compensate.
+ */
+ if (sb->s_blocksize == 1024 && nr == 0 &&
+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+ has_super++;
+
return (has_super + ext4_group_first_block_no(sb, bg));
}
@@ -2377,7 +2460,10 @@ struct ext4_attr {
ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *);
ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *,
const char *, size_t);
- int offset;
+ union {
+ int offset;
+ int deprecated_val;
+ } u;
};
static int parse_strtoull(const char *buf,
@@ -2446,7 +2532,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
static ssize_t sbi_ui_show(struct ext4_attr *a,
struct ext4_sb_info *sbi, char *buf)
{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+ unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
}
@@ -2455,7 +2541,7 @@ static ssize_t sbi_ui_store(struct ext4_attr *a,
struct ext4_sb_info *sbi,
const char *buf, size_t count)
{
- unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset);
+ unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset);
unsigned long t;
int ret;
@@ -2504,12 +2590,20 @@ static ssize_t trigger_test_error(struct ext4_attr *a,
return count;
}
+static ssize_t sbi_deprecated_show(struct ext4_attr *a,
+ struct ext4_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val);
+}
+
#define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \
static struct ext4_attr ext4_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
.show = _show, \
.store = _store, \
- .offset = offsetof(struct ext4_sb_info, _elname), \
+ .u = { \
+ .offset = offsetof(struct ext4_sb_info, _elname),\
+ }, \
}
#define EXT4_ATTR(name, mode, show, store) \
static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
@@ -2520,6 +2614,14 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store)
#define EXT4_RW_ATTR_SBI_UI(name, elname) \
EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname)
#define ATTR_LIST(name) &ext4_attr_##name.attr
+#define EXT4_DEPRECATED_ATTR(_name, _val) \
+static struct ext4_attr ext4_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0444 }, \
+ .show = sbi_deprecated_show, \
+ .u = { \
+ .deprecated_val = _val, \
+ }, \
+}
EXT4_RO_ATTR(delayed_allocation_blocks);
EXT4_RO_ATTR(session_write_kbytes);
@@ -2534,9 +2636,15 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan);
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_DEPRECATED_ATTR(max_writeback_mb_bump, 128);
EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(err_ratelimit_burst, s_err_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_interval_ms, s_warning_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
+EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
static struct attribute *ext4_attrs[] = {
ATTR_LIST(delayed_allocation_blocks),
@@ -2554,6 +2662,12 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(max_writeback_mb_bump),
ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
+ ATTR_LIST(err_ratelimit_interval_ms),
+ ATTR_LIST(err_ratelimit_burst),
+ ATTR_LIST(warning_ratelimit_interval_ms),
+ ATTR_LIST(warning_ratelimit_burst),
+ ATTR_LIST(msg_ratelimit_interval_ms),
+ ATTR_LIST(msg_ratelimit_burst),
NULL,
};
@@ -2693,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg)
es = sbi->s_es;
if (es->s_error_count)
- ext4_msg(sb, KERN_NOTICE, "error count: %u",
+ /* fsck newer than v1.41.13 is needed to clean this condition. */
+ ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
le32_to_cpu(es->s_error_count));
if (es->s_first_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_first_error_time),
(int) sizeof(es->s_first_error_func),
es->s_first_error_func,
@@ -2710,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg)
printk("\n");
}
if (es->s_last_error_time) {
- printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
sb->s_id, le32_to_cpu(es->s_last_error_time),
(int) sizeof(es->s_last_error_func),
es->s_last_error_func,
@@ -2968,7 +3083,6 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr;
- unsigned long rnd;
elr = kzalloc(sizeof(*elr), GFP_KERNEL);
if (!elr)
@@ -2983,10 +3097,8 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
* spread the inode table initialization requests
* better.
*/
- get_random_bytes(&rnd, sizeof(rnd));
- elr->lr_next_sched = jiffies + (unsigned long)rnd %
- (EXT4_DEF_LI_MAX_START_DELAY * HZ);
-
+ elr->lr_next_sched = jiffies + (prandom_u32() %
+ (EXT4_DEF_LI_MAX_START_DELAY * HZ));
return elr;
}
@@ -3219,19 +3331,28 @@ int ext4_calculate_overhead(struct super_block *sb)
}
-static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi)
+static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
/*
+ * There's no need to reserve anything when we aren't using extents.
+ * The space estimates are exact, there are no unwritten extents,
+ * hole punching doesn't need new metadata... This is needed especially
+ * to keep ext2/3 backward compatibility.
+ */
+ if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS))
+ return 0;
+ /*
* By default we reserve 2% or 4096 clusters, whichever is smaller.
* This should cover the situations where we can not afford to run
* out of space like for example punch hole, or converting
- * uninitialized extents in delalloc path. In most cases such
+ * unwritten extents in delalloc path. In most cases such
* allocation would require 1, or 2 blocks, higher numbers are
* very rare.
*/
- resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits;
+ resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >>
+ EXT4_SB(sb)->s_cluster_bits;
do_div(resv_clusters, 50);
resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096);
@@ -3451,7 +3572,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and delalloc");
+ "both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DELALLOC))
@@ -3469,6 +3590,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
+ if (es->s_creator_os == cpu_to_le32(EXT4_OS_HURD)) {
+ set_opt2(sb, HURD_COMPAT);
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_64BIT)) {
+ ext4_msg(sb, KERN_ERR,
+ "The Hurd can't support 64-bit file systems");
+ goto failed_mount;
+ }
+ }
+
if (IS_EXT2_SB(sb)) {
if (ext2_feature_set_ok(sb))
ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
@@ -3586,23 +3717,25 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb));
- /* Do we have standard group size of blocksize * 8 blocks ? */
- if (sbi->s_blocks_per_group == blocksize << 3)
- set_opt2(sb, STD_GROUP_SIZE);
-
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
- i = le32_to_cpu(es->s_flags);
- if (i & EXT2_FLAGS_UNSIGNED_HASH)
- sbi->s_hash_unsigned = 3;
- else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
- sbi->s_hash_unsigned = 3;
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
#else
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
+ }
}
/* Handle clustersize */
@@ -3659,6 +3792,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
+ /* Do we have standard group size of clustersize * 8 blocks ? */
+ if (sbi->s_blocks_per_group == clustersize << 3)
+ set_opt2(sb, STD_GROUP_SIZE);
+
/*
* Test whether we have more sectors than will fit in sector_t,
* and whether the max offset is addressable by the page cache.
@@ -3763,7 +3900,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_err_report.data = (unsigned long) sb;
/* Register extent status tree shrinker */
- ext4_es_register_shrinker(sb);
+ ext4_es_register_shrinker(sbi);
err = percpu_counter_init(&sbi->s_freeclusters_counter,
ext4_count_free_clusters(sb));
@@ -3787,7 +3924,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
sbi->s_stripe = ext4_get_stripe_size(sbi);
- sbi->s_max_writeback_mb_bump = 128;
sbi->s_extent_max_zeroout_kb = 32;
/*
@@ -3899,6 +4035,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
percpu_counter_set(&sbi->s_dirtyclusters_counter, 0);
no_journal:
+ if (ext4_mballoc_ready) {
+ sbi->s_mb_cache = ext4_xattr_create_cache(sb->s_id);
+ if (!sbi->s_mb_cache) {
+ ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+ goto failed_mount_wq;
+ }
+ }
+
/*
* Get the # of file system overhead blocks from the
* superblock if present.
@@ -3915,12 +4059,12 @@ no_journal:
* The maximum number of concurrent works can be high and
* concurrency isn't really necessary. Limit it to 1.
*/
- EXT4_SB(sb)->dio_unwritten_wq =
- alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
- if (!EXT4_SB(sb)->dio_unwritten_wq) {
- printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
+ EXT4_SB(sb)->rsv_conversion_wq =
+ alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+ if (!EXT4_SB(sb)->rsv_conversion_wq) {
+ printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
ret = -ENOMEM;
- goto failed_mount_wq;
+ goto failed_mount4;
}
/*
@@ -3975,10 +4119,10 @@ no_journal:
"available");
}
- err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi));
+ err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb));
if (err) {
ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for "
- "reserved pool", ext4_calculate_resv_clusters(sbi));
+ "reserved pool", ext4_calculate_resv_clusters(sb));
goto failed_mount4a;
}
@@ -4050,6 +4194,11 @@ no_journal:
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
+ /* Enable message ratelimiting. Default is 10 messages per 5 secs. */
+ ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10);
+ ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
+
kfree(orig_data);
return 0;
@@ -4074,15 +4223,16 @@ failed_mount4a:
sb->s_root = NULL;
failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
- destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq);
+ if (EXT4_SB(sb)->rsv_conversion_wq)
+ destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
failed_mount_wq:
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
}
failed_mount3:
- ext4_es_unregister_shrinker(sb);
- del_timer(&sbi->s_err_report);
+ ext4_es_unregister_shrinker(sbi);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeclusters_counter);
@@ -4517,19 +4667,50 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
{
int ret = 0;
tid_t target;
+ bool needs_barrier = false;
struct ext4_sb_info *sbi = EXT4_SB(sb);
trace_ext4_sync_fs(sb, wait);
- flush_workqueue(sbi->dio_unwritten_wq);
+ flush_workqueue(sbi->rsv_conversion_wq);
/*
* Writeback quota in non-journalled quota case - journalled quota has
* no dirty dquots
*/
dquot_writeback_dquots(sb, -1);
+ /*
+ * Data writeback is possible w/o journal transaction, so barrier must
+ * being sent at the end of the function. But we can skip it if
+ * transaction_commit will do it for us.
+ */
+ target = jbd2_get_latest_transaction(sbi->s_journal);
+ if (wait && sbi->s_journal->j_flags & JBD2_BARRIER &&
+ !jbd2_trans_will_send_data_barrier(sbi->s_journal, target))
+ needs_barrier = true;
+
if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
- jbd2_log_wait_commit(sbi->s_journal, target);
+ ret = jbd2_log_wait_commit(sbi->s_journal, target);
+ }
+ if (needs_barrier) {
+ int err;
+ err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+ if (!ret)
+ ret = err;
}
+
+ return ret;
+}
+
+static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
+{
+ int ret = 0;
+
+ trace_ext4_sync_fs(sb, wait);
+ flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
+ dquot_writeback_dquots(sb, -1);
+ if (wait && test_opt(sb, BARRIER))
+ ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+
return ret;
}
@@ -4652,6 +4833,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dioread_nolock");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
@@ -4672,6 +4868,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
if (*flags & MS_RDONLY) {
+ err = sync_filesystem(sb);
+ if (err < 0)
+ goto restore_opts;
err = dquot_suspend(sb, -1);
if (err < 0)
goto restore_opts;
@@ -5178,6 +5377,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
bh = ext4_bread(handle, inode, blk, 1, &err);
if (!bh)
goto out;
+ BUFFER_TRACE(bh, "get write access");
err = ext4_journal_get_write_access(handle, bh);
if (err) {
brelse(bh);
@@ -5353,11 +5553,9 @@ static int __init ext4_init_fs(void)
err = ext4_init_mballoc();
if (err)
- goto out3;
-
- err = ext4_init_xattr();
- if (err)
goto out2;
+ else
+ ext4_mballoc_ready = 1;
err = init_inodecache();
if (err)
goto out1;
@@ -5373,10 +5571,9 @@ out:
unregister_as_ext3();
destroy_inodecache();
out1:
- ext4_exit_xattr();
-out2:
+ ext4_mballoc_ready = 0;
ext4_exit_mballoc();
-out3:
+out2:
ext4_exit_feat_adverts();
out4:
if (ext4_proc_root)
@@ -5399,13 +5596,13 @@ static void __exit ext4_exit_fs(void)
unregister_as_ext3();
unregister_filesystem(&ext4_fs_type);
destroy_inodecache();
- ext4_exit_xattr();
ext4_exit_mballoc();
ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
ext4_exit_system_zone();
ext4_exit_pageio();
+ ext4_exit_es();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 12:36:32 +0000