f2fs: sync to upstream
https://git.kernel.org/cgit/linux/kernel/git/jaegeuk/f2fs.git/commit/?h=linux-3.4&id=994642cfdbc08f1eda7ff48504f779cbcc9e3067
Change-Id: I5beb230d4a5dc3ef3913f5bfc4c28b39bcb755b1
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 4ab9c76..a79d960 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -39,6 +39,12 @@
static struct kmem_cache *f2fs_inode_cachep;
static struct kset *f2fs_kset;
+/* f2fs-wide shrinker description */
+static struct shrinker f2fs_shrinker_info = {
+ .shrink = f2fs_shrink_scan,
+ .seeks = DEFAULT_SEEKS,
+};
+
enum {
Opt_gc_background,
Opt_disable_roll_forward,
@@ -57,6 +63,9 @@
Opt_flush_merge,
Opt_nobarrier,
Opt_fastboot,
+ Opt_extent_cache,
+ Opt_noextent_cache,
+ Opt_noinline_data,
Opt_err,
};
@@ -78,6 +87,9 @@
{Opt_flush_merge, "flush_merge"},
{Opt_nobarrier, "nobarrier"},
{Opt_fastboot, "fastboot"},
+ {Opt_extent_cache, "extent_cache"},
+ {Opt_noextent_cache, "noextent_cache"},
+ {Opt_noinline_data, "noinline_data"},
{Opt_err, NULL},
};
@@ -202,6 +214,7 @@
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, cp_interval);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
@@ -218,6 +231,7 @@
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
+ ATTR_LIST(cp_interval),
NULL,
};
@@ -254,6 +268,7 @@
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct request_queue *q;
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
@@ -278,11 +293,16 @@
if (!name)
return -ENOMEM;
- if (strlen(name) == 2 && !strncmp(name, "on", 2))
+ if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
set_opt(sbi, BG_GC);
- else if (strlen(name) == 3 && !strncmp(name, "off", 3))
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
clear_opt(sbi, BG_GC);
- else {
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, FORCE_FG_GC);
+ } else {
kfree(name);
return -EINVAL;
}
@@ -298,7 +318,14 @@
return -EINVAL;
break;
case Opt_discard:
- set_opt(sbi, DISCARD);
+ q = bdev_get_queue(sb->s_bdev);
+ if (blk_queue_discard(q)) {
+ set_opt(sbi, DISCARD);
+ } else {
+ f2fs_msg(sb, KERN_WARNING,
+ "mounting with \"discard\" option, but "
+ "the device does not support discard");
+ }
break;
case Opt_noheap:
set_opt(sbi, NOHEAP);
@@ -367,6 +394,15 @@
case Opt_fastboot:
set_opt(sbi, FASTBOOT);
break;
+ case Opt_extent_cache:
+ set_opt(sbi, EXTENT_CACHE);
+ break;
+ case Opt_noextent_cache:
+ clear_opt(sbi, EXTENT_CACHE);
+ break;
+ case Opt_noinline_data:
+ clear_opt(sbi, INLINE_DATA);
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -392,9 +428,7 @@
atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
- rwlock_init(&fi->ext.ext_lock);
init_rwsem(&fi->i_sem);
- INIT_RADIX_TREE(&fi->inmem_root, GFP_NOFS);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
@@ -406,6 +440,9 @@
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ fi->i_crypt_info = NULL;
+#endif
return &fi->vfs_inode;
}
@@ -418,8 +455,31 @@
* - f2fs_gc -> iput -> evict
* - inode_wait_for_writeback(inode)
*/
- if (!inode_unhashed(inode) && inode->i_state & I_SYNC)
+ if (!inode_unhashed(inode) && inode->i_state & I_SYNC) {
+ if (!inode->i_nlink && !is_bad_inode(inode)) {
+ /* to avoid evict_inode call simultaneously */
+ atomic_inc(&inode->i_count);
+ spin_unlock(&inode->i_lock);
+
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ commit_inmem_pages(inode, true);
+
+ i_size_write(inode, 0);
+
+ if (F2FS_HAS_BLOCKS(inode))
+ f2fs_truncate(inode, true);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ if (F2FS_I(inode)->i_crypt_info)
+ f2fs_free_encryption_info(inode,
+ F2FS_I(inode)->i_crypt_info);
+#endif
+ spin_lock(&inode->i_lock);
+ atomic_dec(&inode->i_count);
+ }
return 0;
+ }
return generic_drop_inode(inode);
}
@@ -454,9 +514,11 @@
}
kobject_del(&sbi->s_kobj);
- f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
+ /* prevent remaining shrinker jobs */
+ mutex_lock(&sbi->umount_mutex);
+
/*
* We don't need to do checkpoint when superblock is clean.
* But, the previous checkpoint was not done by umount, it needs to do
@@ -470,6 +532,9 @@
write_checkpoint(sbi, &cpc);
}
+ /* write_checkpoint can update stat informaion */
+ f2fs_destroy_stats(sbi);
+
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
@@ -477,6 +542,9 @@
release_dirty_inode(sbi);
release_discard_addrs(sbi);
+ f2fs_leave_shrinker(sbi);
+ mutex_unlock(&sbi->umount_mutex);
+
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -510,7 +578,7 @@
} else {
f2fs_balance_fs(sbi);
}
- f2fs_trace_ios(NULL, NULL, 1);
+ f2fs_trace_ios(NULL, 1);
return 0;
}
@@ -563,10 +631,14 @@
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
- if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
- seq_printf(seq, ",background_gc=%s", "on");
- else
+ if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) {
+ if (test_opt(sbi, FORCE_FG_GC))
+ seq_printf(seq, ",background_gc=%s", "sync");
+ else
+ seq_printf(seq, ",background_gc=%s", "on");
+ } else {
seq_printf(seq, ",background_gc=%s", "off");
+ }
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
if (test_opt(sbi, DISCARD))
@@ -591,6 +663,8 @@
seq_puts(seq, ",disable_ext_identify");
if (test_opt(sbi, INLINE_DATA))
seq_puts(seq, ",inline_data");
+ else
+ seq_puts(seq, ",noinline_data");
if (test_opt(sbi, INLINE_DENTRY))
seq_puts(seq, ",inline_dentry");
if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
@@ -599,6 +673,10 @@
seq_puts(seq, ",nobarrier");
if (test_opt(sbi, FASTBOOT))
seq_puts(seq, ",fastboot");
+ if (test_opt(sbi, EXTENT_CACHE))
+ seq_puts(seq, ",extent_cache");
+ else
+ seq_puts(seq, ",noextent_cache");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
return 0;
@@ -619,7 +697,7 @@
struct seg_entry *se = get_seg_entry(sbi, i);
if ((i % 10) == 0)
- seq_printf(seq, "%-5d", i);
+ seq_printf(seq, "%-10d", i);
seq_printf(seq, "%d|%-3u", se->type,
get_valid_blocks(sbi, i, 1));
if ((i % 10) == 9 || i == (total_segs - 1))
@@ -644,6 +722,23 @@
.release = single_release,
};
+static void default_options(struct f2fs_sb_info *sbi)
+{
+ /* init some FS parameters */
+ sbi->active_logs = NR_CURSEG_TYPE;
+
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, INLINE_DATA);
+ set_opt(sbi, EXTENT_CACHE);
+
+#ifdef CONFIG_F2FS_FS_XATTR
+ set_opt(sbi, XATTR_USER);
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+ set_opt(sbi, POSIX_ACL);
+#endif
+}
+
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -651,6 +746,7 @@
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
+ bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
sync_filesystem(sb);
@@ -662,7 +758,7 @@
active_logs = sbi->active_logs;
sbi->mount_opt.opt = 0;
- sbi->active_logs = NR_CURSEG_TYPE;
+ default_options(sbi);
/* parse mount options */
err = parse_options(sb, data);
@@ -676,6 +772,14 @@
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
+ /* disallow enable/disable extent_cache dynamically */
+ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "switch extent_cache option is not allowed");
+ goto restore_opts;
+ }
+
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
@@ -905,7 +1009,11 @@
atomic_set(&sbi->nr_pages[i], 0);
sbi->dir_level = DEF_DIR_LEVEL;
+ sbi->cp_interval = DEF_CP_INTERVAL;
clear_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ INIT_LIST_HEAD(&sbi->s_list);
+ mutex_init(&sbi->umount_mutex);
}
/*
@@ -915,29 +1023,36 @@
*/
static int read_raw_super_block(struct super_block *sb,
struct f2fs_super_block **raw_super,
- struct buffer_head **raw_super_buf)
+ struct buffer_head **raw_super_buf,
+ int *recovery)
{
int block = 0;
+ struct buffer_head *buffer;
+ struct f2fs_super_block *super;
+ int err = 0;
retry:
- *raw_super_buf = sb_bread(sb, block);
- if (!*raw_super_buf) {
+ buffer = sb_bread(sb, block);
+ if (!buffer) {
+ *recovery = 1;
f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
block + 1);
if (block == 0) {
block++;
goto retry;
} else {
- return -EIO;
+ err = -EIO;
+ goto out;
}
}
- *raw_super = (struct f2fs_super_block *)
- ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+ super = (struct f2fs_super_block *)
+ ((char *)(buffer)->b_data + F2FS_SUPER_OFFSET);
/* sanity checking of raw super */
- if (sanity_check_raw_super(sb, *raw_super)) {
- brelse(*raw_super_buf);
+ if (sanity_check_raw_super(sb, super)) {
+ brelse(buffer);
+ *recovery = 1;
f2fs_msg(sb, KERN_ERR,
"Can't find valid F2FS filesystem in %dth superblock",
block + 1);
@@ -945,25 +1060,76 @@
block++;
goto retry;
} else {
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
}
+ if (!*raw_super) {
+ *raw_super_buf = buffer;
+ *raw_super = super;
+ } else {
+ /* already have a valid superblock */
+ brelse(buffer);
+ }
+
+ /* check the validity of the second superblock */
+ if (block == 0) {
+ block++;
+ goto retry;
+ }
+
+out:
+ /* No valid superblock */
+ if (!*raw_super)
+ return err;
+
return 0;
}
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
+{
+ struct buffer_head *sbh = sbi->raw_super_buf;
+ sector_t block = sbh->b_blocknr;
+ int err;
+
+ /* write back-up superblock first */
+ sbh->b_blocknr = block ? 0 : 1;
+ mark_buffer_dirty(sbh);
+ err = sync_dirty_buffer(sbh);
+
+ sbh->b_blocknr = block;
+
+ /* if we are in recovery path, skip writing valid superblock */
+ if (recover || err)
+ goto out;
+
+ /* write current valid superblock */
+ mark_buffer_dirty(sbh);
+ err = sync_dirty_buffer(sbh);
+out:
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
+ return err;
+}
+
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
struct f2fs_sb_info *sbi;
- struct f2fs_super_block *raw_super = NULL;
+ struct f2fs_super_block *raw_super;
struct buffer_head *raw_super_buf;
struct inode *root;
- long err = -EINVAL;
- bool retry = true;
+ long err;
+ bool retry = true, need_fsck = false;
char *options = NULL;
- int i;
+ int recovery, i;
try_onemore:
+ err = -EINVAL;
+ raw_super = NULL;
+ raw_super_buf = NULL;
+ recovery = 0;
+
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
@@ -975,22 +1141,12 @@
goto free_sbi;
}
- err = read_raw_super_block(sb, &raw_super, &raw_super_buf);
+ err = read_raw_super_block(sb, &raw_super, &raw_super_buf, &recovery);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
- /* init some FS parameters */
- sbi->active_logs = NR_CURSEG_TYPE;
-
- set_opt(sbi, BG_GC);
-
-#ifdef CONFIG_F2FS_FS_XATTR
- set_opt(sbi, XATTR_USER);
-#endif
-#ifdef CONFIG_F2FS_FS_POSIX_ACL
- set_opt(sbi, POSIX_ACL);
-#endif
+ default_options(sbi);
/* parse mount options */
options = kstrdup((const char *)data, GFP_KERNEL);
if (data && !options) {
@@ -1023,7 +1179,9 @@
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
- clear_sbi_flag(sbi, SBI_POR_DOING);
+
+ /* disallow all the data/node/meta page writes */
+ set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
@@ -1072,6 +1230,8 @@
INIT_LIST_HEAD(&sbi->dir_inode_list);
spin_lock_init(&sbi->dir_inode_lock);
+ init_extent_cache_info(sbi);
+
init_ino_entry_info(sbi);
/* setup f2fs internal modules */
@@ -1098,8 +1258,12 @@
goto free_nm;
}
+ f2fs_join_shrinker(sbi);
+
/* if there are nt orphan nodes free them */
- recover_orphan_inodes(sbi);
+ err = recover_orphan_inodes(sbi);
+ if (err)
+ goto free_node_inode;
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
@@ -1131,14 +1295,6 @@
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
- if (test_opt(sbi, DISCARD)) {
- struct request_queue *q = bdev_get_queue(sb->s_bdev);
- if (!blk_queue_discard(q))
- f2fs_msg(sb, KERN_WARNING,
- "mounting with \"discard\" option, but "
- "the device does not support discard");
- }
-
sbi->s_kobj.kset = f2fs_kset;
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
@@ -1146,9 +1302,6 @@
if (err)
goto free_proc;
- if (!retry)
- set_sbi_flag(sbi, SBI_NEED_FSCK);
-
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
@@ -1160,13 +1313,20 @@
err = -EROFS;
goto free_kobj;
}
+
+ if (need_fsck)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
err = recover_fsync_data(sbi);
if (err) {
+ need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
}
+ /* recover_fsync_data() cleared this already */
+ clear_sbi_flag(sbi, SBI_POR_DOING);
/*
* If filesystem is not mounted as read-only then
@@ -1179,6 +1339,15 @@
goto free_kobj;
}
kfree(options);
+
+ /* recover broken superblock */
+ if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
+ f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
+ f2fs_commit_super(sbi, true);
+ }
+
+ sbi->cp_expires = round_jiffies_up(jiffies);
+
return 0;
free_kobj:
@@ -1193,7 +1362,10 @@
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
+ mutex_lock(&sbi->umount_mutex);
+ f2fs_leave_shrinker(sbi);
iput(sbi->node_inode);
+ mutex_unlock(&sbi->umount_mutex);
free_nm:
destroy_node_manager(sbi);
free_sm:
@@ -1212,7 +1384,7 @@
/* give only one another chance */
if (retry) {
- retry = 0;
+ retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
@@ -1277,20 +1449,34 @@
err = create_checkpoint_caches();
if (err)
goto free_segment_manager_caches;
+ err = create_extent_cache();
+ if (err)
+ goto free_checkpoint_caches;
f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
if (!f2fs_kset) {
err = -ENOMEM;
- goto free_checkpoint_caches;
+ goto free_extent_cache;
}
- err = register_filesystem(&f2fs_fs_type);
+ err = f2fs_init_crypto();
if (err)
goto free_kset;
+
+ register_shrinker(&f2fs_shrinker_info);
+
+ err = register_filesystem(&f2fs_fs_type);
+ if (err)
+ goto free_shrinker;
f2fs_create_root_stats();
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
return 0;
+free_shrinker:
+ unregister_shrinker(&f2fs_shrinker_info);
+ f2fs_exit_crypto();
free_kset:
kset_unregister(f2fs_kset);
+free_extent_cache:
+ destroy_extent_cache();
free_checkpoint_caches:
destroy_checkpoint_caches();
free_segment_manager_caches:
@@ -1307,7 +1493,10 @@
{
remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
+ unregister_shrinker(&f2fs_shrinker_info);
unregister_filesystem(&f2fs_fs_type);
+ f2fs_exit_crypto();
+ destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();