#include <linux/ctype.h>
#include <linux/log2.h>
#include <linux/crc16.h>
+#include <linux/cleancache.h>
#include <asm/uaccess.h>
#include <linux/kthread.h>
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);
+static inline int ext2_feature_set_ok(struct super_block *sb);
+static inline int ext3_feature_set_ok(struct super_block *sb);
static int ext4_feature_set_ok(struct super_block *sb, int readonly);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
static void ext4_clear_request_list(void);
+#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
+static struct file_system_type ext2_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "ext2",
+ .mount = ext4_mount,
+ .kill_sb = kill_block_super,
+ .fs_flags = FS_REQUIRES_DEV,
+};
+#define IS_EXT2_SB(sb) ((sb)->s_bdev->bd_holder == &ext2_fs_type)
+#else
+#define IS_EXT2_SB(sb) (0)
+#endif
+
+
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
.owner = THIS_MODULE,
* 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;
if (sb->s_flags & MS_RDONLY)
return ERR_PTR(-EROFS);
- vfs_check_frozen(sb, SB_FREEZE_TRANS);
- /* Special case here: if the journal has aborted behind our
- * backs (eg. EIO in the commit thread), then we still need to
- * take the FS itself readonly cleanly. */
journal = EXT4_SB(sb)->s_journal;
- if (journal) {
- if (is_journal_aborted(journal)) {
- ext4_abort(sb, "Detected aborted journal");
- return ERR_PTR(-EROFS);
- }
- return jbd2_journal_start(journal, nblocks);
+ 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();
+ /*
+ * Special case here: if the journal has aborted behind our
+ * backs (eg. EIO in the commit thread), then we still need to
+ * take the FS itself readonly cleanly.
+ */
+ if (is_journal_aborted(journal)) {
+ ext4_abort(sb, "Detected aborted journal");
+ return ERR_PTR(-EROFS);
}
- return ext4_get_nojournal();
+ return jbd2_journal_start(journal, nblocks);
}
/*
invalidate_bdev(sbi->journal_bdev);
ext4_blkdev_remove(sbi);
}
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
sb->s_fs_info = NULL;
/*
* Now that we are completely done shutting down the
if (!test_opt(sb, INIT_INODE_TABLE))
seq_puts(seq, ",noinit_inode_table");
- else if (sbi->s_li_wait_mult)
+ else if (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT)
seq_printf(seq, ",init_inode_table=%u",
(unsigned) sbi->s_li_wait_mult);
const char *data, size_t len, loff_t off);
static const struct dquot_operations ext4_quota_operations = {
-#ifdef CONFIG_QUOTA
.get_reserved_space = ext4_get_reserved_space,
-#endif
.write_dquot = ext4_write_dquot,
.acquire_dquot = ext4_acquire_dquot,
.release_dquot = ext4_release_dquot,
ext4_msg(sb, KERN_WARNING,
"warning: mounting fs with errors, "
"running e2fsck is recommended");
- else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
+ else if ((__s16) le16_to_cpu(es->s_max_mnt_count) > 0 &&
le16_to_cpu(es->s_mnt_count) >=
(unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
ext4_msg(sb, KERN_WARNING,
EXT4_INODES_PER_GROUP(sb),
sbi->s_mount_opt, sbi->s_mount_opt2);
+ cleancache_init_fs(sb);
return res;
}
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)
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);
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),
mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
}
-static void ext4_lazyinode_timeout(unsigned long data)
-{
- struct task_struct *p = (struct task_struct *)data;
- wake_up_process(p);
-}
-
/* Find next suitable group and run ext4_init_inode_table */
static int ext4_run_li_request(struct ext4_li_request *elr)
{
ret = ext4_init_inode_table(sb, group,
elr->lr_timeout ? 0 : 1);
if (elr->lr_timeout == 0) {
- timeout = jiffies - timeout;
- if (elr->lr_sbi->s_li_wait_mult)
- timeout *= elr->lr_sbi->s_li_wait_mult;
- else
- timeout *= 20;
+ timeout = (jiffies - timeout) *
+ elr->lr_sbi->s_li_wait_mult;
elr->lr_timeout = timeout;
}
elr->lr_next_sched = jiffies + elr->lr_timeout;
/*
* Remove lr_request from the list_request and free the
- * request tructure. Should be called with li_list_mtx held
+ * request structure. Should be called with li_list_mtx held
*/
static void ext4_remove_li_request(struct ext4_li_request *elr)
{
static void ext4_unregister_li_request(struct super_block *sb)
{
- struct ext4_li_request *elr = EXT4_SB(sb)->s_li_request;
-
- if (!ext4_li_info)
+ mutex_lock(&ext4_li_mtx);
+ if (!ext4_li_info) {
+ mutex_unlock(&ext4_li_mtx);
return;
+ }
mutex_lock(&ext4_li_info->li_list_mtx);
- ext4_remove_li_request(elr);
+ ext4_remove_li_request(EXT4_SB(sb)->s_li_request);
mutex_unlock(&ext4_li_info->li_list_mtx);
+ mutex_unlock(&ext4_li_mtx);
}
static struct task_struct *ext4_lazyinit_task;
struct ext4_lazy_init *eli = (struct ext4_lazy_init *)arg;
struct list_head *pos, *n;
struct ext4_li_request *elr;
- unsigned long next_wakeup;
- DEFINE_WAIT(wait);
+ unsigned long next_wakeup, cur;
BUG_ON(NULL == eli);
- eli->li_timer.data = (unsigned long)current;
- eli->li_timer.function = ext4_lazyinode_timeout;
-
- eli->li_task = current;
- wake_up(&eli->li_wait_task);
-
cont_thread:
while (true) {
next_wakeup = MAX_JIFFY_OFFSET;
if (freezing(current))
refrigerator();
- if ((time_after_eq(jiffies, next_wakeup)) ||
+ cur = jiffies;
+ if ((time_after_eq(cur, next_wakeup)) ||
(MAX_JIFFY_OFFSET == next_wakeup)) {
cond_resched();
continue;
}
- eli->li_timer.expires = next_wakeup;
- add_timer(&eli->li_timer);
- prepare_to_wait(&eli->li_wait_daemon, &wait,
- TASK_INTERRUPTIBLE);
- if (time_before(jiffies, next_wakeup))
- schedule();
- finish_wait(&eli->li_wait_daemon, &wait);
+ schedule_timeout_interruptible(next_wakeup - cur);
+
if (kthread_should_stop()) {
ext4_clear_request_list();
goto exit_thread;
goto cont_thread;
}
mutex_unlock(&eli->li_list_mtx);
- del_timer_sync(&ext4_li_info->li_timer);
- eli->li_task = NULL;
- wake_up(&eli->li_wait_task);
-
kfree(ext4_li_info);
- ext4_lazyinit_task = NULL;
ext4_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
if (IS_ERR(ext4_lazyinit_task)) {
int err = PTR_ERR(ext4_lazyinit_task);
ext4_clear_request_list();
- del_timer_sync(&ext4_li_info->li_timer);
kfree(ext4_li_info);
ext4_li_info = NULL;
printk(KERN_CRIT "EXT4: error %d creating inode table "
return err;
}
ext4_li_info->li_state |= EXT4_LAZYINIT_RUNNING;
-
- wait_event(ext4_li_info->li_wait_task, ext4_li_info->li_task != NULL);
return 0;
}
if (!eli)
return -ENOMEM;
- eli->li_task = NULL;
INIT_LIST_HEAD(&eli->li_request_list);
mutex_init(&eli->li_list_mtx);
- init_waitqueue_head(&eli->li_wait_daemon);
- init_waitqueue_head(&eli->li_wait_task);
- init_timer(&eli->li_timer);
eli->li_state |= EXT4_LAZYINIT_QUIT;
ext4_li_info = eli;
ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
int ret = 0;
- if (sbi->s_li_request != NULL)
+ if (sbi->s_li_request != NULL) {
+ /*
+ * Reset timeout so it can be computed again, because
+ * s_li_wait_mult might have changed.
+ */
+ sbi->s_li_request->lr_timeout = 0;
return 0;
+ }
if (first_not_zeroed == ngroups ||
(sb->s_flags & MS_RDONLY) ||
- !test_opt(sb, INIT_INODE_TABLE)) {
- sbi->s_li_request = NULL;
- return 0;
- }
-
- if (first_not_zeroed == ngroups) {
- sbi->s_li_request = NULL;
+ !test_opt(sb, INIT_INODE_TABLE))
return 0;
- }
elr = ext4_li_request_new(sb, first_not_zeroed);
if (!elr)
mutex_unlock(&ext4_li_info->li_list_mtx);
sbi->s_li_request = elr;
+ /*
+ * set elr to NULL here since it has been inserted to
+ * the request_list and the removal and free of it is
+ * handled by ext4_clear_request_list from now on.
+ */
+ elr = NULL;
if (!(ext4_li_info->li_state & EXT4_LAZYINIT_RUNNING)) {
ret = ext4_run_lazyinit_thread();
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
+ /*
+ * set default s_li_wait_mult for lazyinit, for the case there is
+ * no mount option specified.
+ */
+ sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
+
if (!parse_options((char *) sbi->s_es->s_mount_opts, sb,
&journal_devnum, &journal_ioprio, NULL, 0)) {
ext4_msg(sb, KERN_WARNING,
"feature flags set on rev 0 fs, "
"running e2fsck is recommended");
+ if (IS_EXT2_SB(sb)) {
+ if (ext2_feature_set_ok(sb))
+ ext4_msg(sb, KERN_INFO, "mounting ext2 file system "
+ "using the ext4 subsystem");
+ else {
+ ext4_msg(sb, KERN_ERR, "couldn't mount as ext2 due "
+ "to feature incompatibilities");
+ goto failed_mount;
+ }
+ }
+
+ if (IS_EXT3_SB(sb)) {
+ if (ext3_feature_set_ok(sb))
+ ext4_msg(sb, KERN_INFO, "mounting ext3 file system "
+ "using the ext4 subsystem");
+ else {
+ ext4_msg(sb, KERN_ERR, "couldn't mount as ext3 due "
+ "to feature incompatibilities");
+ goto failed_mount;
+ }
+ }
+
/*
* Check feature flags regardless of the revision level, since we
* previously didn't change the revision level when setting the flags,
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
spin_lock_init(&sbi->s_next_gen_lock);
+ init_timer(&sbi->s_err_report);
+ sbi->s_err_report.function = print_daily_error_info;
+ sbi->s_err_report.data = (unsigned long) sb;
+
err = percpu_counter_init(&sbi->s_freeblocks_counter,
ext4_count_free_blocks(sb));
if (!err) {
EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_RECOVER));
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_MMP) &&
+ !(sb->s_flags & MS_RDONLY))
+ if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block)))
+ goto failed_mount3;
+
/*
* The first inode we look at is the journal inode. Don't try
* root first: it may be modified in the journal!
goto failed_mount_wq;
} else {
clear_opt(sb, DATA_FLAGS);
- set_opt(sb, WRITEBACK_DATA);
sbi->s_journal = NULL;
needs_recovery = 0;
goto no_journal;
"Opts: %s%s%s", descr, sbi->s_es->s_mount_opts,
*sbi->s_es->s_mount_opts ? "; " : "", orig_data);
- init_timer(&sbi->s_err_report);
- sbi->s_err_report.function = print_daily_error_info;
- sbi->s_err_report.data = (unsigned long) sb;
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
sbi->s_journal = NULL;
}
failed_mount3:
+ del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups) {
if (is_vmalloc_addr(sbi->s_flex_groups))
vfree(sbi->s_flex_groups);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
+ if (sbi->s_mmp_tsk)
+ kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
for (i = 0; i < db_count; i++)
brelse(sbi->s_group_desc[i]);
/*
* LVM calls this function before a (read-only) snapshot is created. This
* 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.
*/
static int ext4_freeze(struct super_block *sb)
{
int enable_quota = 0;
ext4_group_t g;
unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
- int err;
+ int err = 0;
#ifdef CONFIG_QUOTA
int i;
#endif
goto restore_opts;
if (!ext4_setup_super(sb, es, 0))
sb->s_flags &= ~MS_RDONLY;
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb,
+ EXT4_FEATURE_INCOMPAT_MMP))
+ if (ext4_multi_mount_protect(sb,
+ le64_to_cpu(es->s_mmp_block))) {
+ err = -EROFS;
+ goto restore_opts;
+ }
enable_quota = 1;
}
}
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
u64 fsid;
+ s64 bfree;
if (test_opt(sb, MINIX_DF)) {
sbi->s_overhead_last = 0;
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
- buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
+ bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
+ /* prevent underflow in case that few free space is available */
+ buf->f_bfree = max_t(s64, bfree, 0);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
static int ext4_quota_off(struct super_block *sb, int type)
{
+ struct inode *inode = sb_dqopt(sb)->files[type];
+ handle_t *handle;
+
/* Force all delayed allocation blocks to be allocated.
* Caller already holds s_umount sem */
if (test_opt(sb, DELALLOC))
sync_filesystem(sb);
+ if (!inode)
+ goto out;
+
+ /* Update modification times of quota files when userspace can
+ * start looking at them */
+ handle = ext4_journal_start(inode, 1);
+ if (IS_ERR(handle))
+ goto out;
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ ext4_mark_inode_dirty(handle, inode);
+ ext4_journal_stop(handle);
+
+out:
return dquot_quota_off(sb, type);
}
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);
}
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- ext4_mark_inode_dirty(handle, inode);
mutex_unlock(&inode->i_mutex);
return len;
}
}
#if !defined(CONFIG_EXT2_FS) && !defined(CONFIG_EXT2_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
-static struct file_system_type ext2_fs_type = {
- .owner = THIS_MODULE,
- .name = "ext2",
- .mount = ext4_mount,
- .kill_sb = kill_block_super,
- .fs_flags = FS_REQUIRES_DEV,
-};
-
static inline void register_as_ext2(void)
{
int err = register_filesystem(&ext2_fs_type);
{
unregister_filesystem(&ext2_fs_type);
}
+
+static inline int ext2_feature_set_ok(struct super_block *sb)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP))
+ return 0;
+ if (sb->s_flags & MS_RDONLY)
+ return 1;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))
+ return 0;
+ return 1;
+}
MODULE_ALIAS("ext2");
#else
static inline void register_as_ext2(void) { }
static inline void unregister_as_ext2(void) { }
+static inline int ext2_feature_set_ok(struct super_block *sb) { return 0; }
#endif
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
{
unregister_filesystem(&ext3_fs_type);
}
+
+static inline int ext3_feature_set_ok(struct super_block *sb)
+{
+ if (EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))
+ return 0;
+ if (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL))
+ return 0;
+ if (sb->s_flags & MS_RDONLY)
+ return 1;
+ if (EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))
+ return 0;
+ return 1;
+}
MODULE_ALIAS("ext3");
#else
static inline void register_as_ext3(void) { }
static inline void unregister_as_ext3(void) { }
+static inline int ext3_feature_set_ok(struct super_block *sb) { return 0; }
#endif
static struct file_system_type ext4_fs_type = {
err = init_inodecache();
if (err)
goto out1;
- register_as_ext2();
register_as_ext3();
+ register_as_ext2();
err = register_filesystem(&ext4_fs_type);
if (err)
goto out;
projects / karo-tx-linux.git / blobdiff