Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "In addition to some ext4 bug fixes and cleanups, this cycle we add the
  orphan_file feature, which eliminates bottlenecks when doing a large
  number of parallel truncates and file deletions, and move the discard
  operation out of the jbd2 commit thread when using the discard mount
  option, to better support devices with slow discard operations"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
  ext4: make the updating inode data procedure atomic
  ext4: remove an unnecessary if statement in __ext4_get_inode_loc()
  ext4: move inode eio simulation behind io completeion
  ext4: Improve scalability of ext4 orphan file handling
  ext4: Orphan file documentation
  ext4: Speedup ext4 orphan inode handling
  ext4: Move orphan inode handling into a separate file
  ext4: Support for checksumming from journal triggers
  ext4: fix race writing to an inline_data file while its xattrs are changing
  jbd2: add sparse annotations for add_transaction_credits()
  ext4: fix sparse warnings
  ext4: Make sure quota files are not grabbed accidentally
  ext4: fix e2fsprogs checksum failure for mounted filesystem
  ext4: if zeroout fails fall back to splitting the extent node
  ext4: reduce arguments of ext4_fc_add_dentry_tlv
  ext4: flush background discard kwork when retry allocation
  ext4: get discard out of jbd2 commit kthread contex
  ext4: remove the repeated comment of ext4_trim_all_free
  ext4: add new helper interface ext4_try_to_trim_range()
  ext4: remove the 'group' parameter of ext4_trim_extent
  ...

1 files changed, 54 insertions, 184 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d6df62fc810c..136940af00b8 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -80,7 +80,6 @@ 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);
@@ -1173,6 +1172,7 @@ static void ext4_put_super(struct super_block *sb)
 
 	flush_work(&sbi->s_error_work);
 	destroy_workqueue(sbi->rsv_conversion_wq);
+	ext4_release_orphan_info(sb);
 
 	/*
 	 * Unregister sysfs before destroying jbd2 journal.
@@ -1198,6 +1198,7 @@ static void ext4_put_super(struct super_block *sb)
 
 	if (!sb_rdonly(sb) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
+		ext4_clear_feature_orphan_present(sb);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
 	if (!sb_rdonly(sb))
@@ -1582,14 +1583,12 @@ 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,
 			 const struct path *path);
-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 struct dquot **ext4_get_dquots(struct inode *inode)
 {
@@ -2684,8 +2683,11 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
 	ext4_update_tstamp(es, s_mtime);
-	if (sbi->s_journal)
+	if (sbi->s_journal) {
 		ext4_set_feature_journal_needs_recovery(sb);
+		if (ext4_has_feature_orphan_file(sb))
+			ext4_set_feature_orphan_present(sb);
+	}
 
 	err = ext4_commit_super(sb);
 done:
@@ -2967,169 +2969,6 @@ static int ext4_check_descriptors(struct super_block *sb,
 	return 1;
 }
 
-/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
- * the superblock) which were deleted from all directories, but held open by
- * a process at the time of a crash.  We walk the list and try to delete these
- * inodes at recovery time (only with a read-write filesystem).
- *
- * In order to keep the orphan inode chain consistent during traversal (in
- * case of crash during recovery), we link each inode into the superblock
- * orphan list_head and handle it the same way as an inode deletion during
- * normal operation (which journals the operations for us).
- *
- * We only do an iget() and an iput() on each inode, which is very safe if we
- * accidentally point at an in-use or already deleted inode.  The worst that
- * can happen in this case is that we get a "bit already cleared" message from
- * ext4_free_inode().  The only reason we would point at a wrong inode is if
- * e2fsck was run on this filesystem, and it must have already done the orphan
- * inode cleanup for us, so we can safely abort without any further action.
- */
-static void ext4_orphan_cleanup(struct super_block *sb,
-				struct ext4_super_block *es)
-{
-	unsigned int s_flags = sb->s_flags;
-	int ret, nr_orphans = 0, nr_truncates = 0;
-#ifdef CONFIG_QUOTA
-	int quota_update = 0;
-	int i;
-#endif
-	if (!es->s_last_orphan) {
-		jbd_debug(4, "no orphan inodes to clean up\n");
-		return;
-	}
-
-	if (bdev_read_only(sb->s_bdev)) {
-		ext4_msg(sb, KERN_ERR, "write access "
-			"unavailable, skipping orphan cleanup");
-		return;
-	}
-
-	/* Check if feature set would not allow a r/w mount */
-	if (!ext4_feature_set_ok(sb, 0)) {
-		ext4_msg(sb, KERN_INFO, "Skipping orphan cleanup due to "
-			 "unknown ROCOMPAT features");
-		return;
-	}
-
-	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
-		/* don't clear list on RO mount w/ errors */
-		if (es->s_last_orphan && !(s_flags & SB_RDONLY)) {
-			ext4_msg(sb, KERN_INFO, "Errors on filesystem, "
-				  "clearing orphan list.\n");
-			es->s_last_orphan = 0;
-		}
-		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
-		return;
-	}
-
-	if (s_flags & SB_RDONLY) {
-		ext4_msg(sb, KERN_INFO, "orphan cleanup on readonly fs");
-		sb->s_flags &= ~SB_RDONLY;
-	}
-#ifdef CONFIG_QUOTA
-	/*
-	 * Turn on quotas which were not enabled for read-only mounts if
-	 * filesystem has quota feature, so that they are updated correctly.
-	 */
-	if (ext4_has_feature_quota(sb) && (s_flags & SB_RDONLY)) {
-		int ret = ext4_enable_quotas(sb);
-
-		if (!ret)
-			quota_update = 1;
-		else
-			ext4_msg(sb, KERN_ERR,
-				"Cannot turn on quotas: error %d", ret);
-	}
-
-	/* Turn on journaled quotas used for old sytle */
-	for (i = 0; i < EXT4_MAXQUOTAS; i++) {
-		if (EXT4_SB(sb)->s_qf_names[i]) {
-			int ret = ext4_quota_on_mount(sb, i);
-
-			if (!ret)
-				quota_update = 1;
-			else
-				ext4_msg(sb, KERN_ERR,
-					"Cannot turn on journaled "
-					"quota: type %d: error %d", i, ret);
-		}
-	}
-#endif
-
-	while (es->s_last_orphan) {
-		struct inode *inode;
-
-		/*
-		 * We may have encountered an error during cleanup; if
-		 * so, skip the rest.
-		 */
-		if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
-			jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
-			es->s_last_orphan = 0;
-			break;
-		}
-
-		inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
-		if (IS_ERR(inode)) {
-			es->s_last_orphan = 0;
-			break;
-		}
-
-		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
-		dquot_initialize(inode);
-		if (inode->i_nlink) {
-			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);
-			inode_lock(inode);
-			truncate_inode_pages(inode->i_mapping, inode->i_size);
-			ret = ext4_truncate(inode);
-			if (ret) {
-				/*
-				 * We need to clean up the in-core orphan list
-				 * manually if ext4_truncate() failed to get a
-				 * transaction handle.
-				 */
-				ext4_orphan_del(NULL, inode);
-				ext4_std_error(inode->i_sb, ret);
-			}
-			inode_unlock(inode);
-			nr_truncates++;
-		} else {
-			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++;
-		}
-		iput(inode);  /* The delete magic happens here! */
-	}
-
-#define PLURAL(x) (x), ((x) == 1) ? "" : "s"
-
-	if (nr_orphans)
-		ext4_msg(sb, KERN_INFO, "%d orphan inode%s deleted",
-		       PLURAL(nr_orphans));
-	if (nr_truncates)
-		ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up",
-		       PLURAL(nr_truncates));
-#ifdef CONFIG_QUOTA
-	/* Turn off quotas if they were enabled for orphan cleanup */
-	if (quota_update) {
-		for (i = 0; i < EXT4_MAXQUOTAS; i++) {
-			if (sb_dqopt(sb)->files[i])
-				dquot_quota_off(sb, i);
-		}
-	}
-#endif
-	sb->s_flags = s_flags; /* Restore SB_RDONLY status */
-}
-
 /*
  * Maximal extent format file size.
  * Resulting logical blkno at s_maxbytes must fit in our on-disk
@@ -3309,7 +3148,7 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
  * Returns 1 if this filesystem can be mounted as requested,
  * 0 if it cannot be.
  */
-static int ext4_feature_set_ok(struct super_block *sb, int readonly)
+int ext4_feature_set_ok(struct super_block *sb, int readonly)
 {
 	if (ext4_has_unknown_ext4_incompat_features(sb)) {
 		ext4_msg(sb, KERN_ERR,
@@ -4011,6 +3850,20 @@ static const char *ext4_quota_mode(struct super_block *sb)
 #endif
 }
 
+static void ext4_setup_csum_trigger(struct super_block *sb,
+				    enum ext4_journal_trigger_type type,
+				    void (*trigger)(
+					struct jbd2_buffer_trigger_type *type,
+					struct buffer_head *bh,
+					void *mapped_data,
+					size_t size))
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	sbi->s_journal_triggers[type].sb = sb;
+	sbi->s_journal_triggers[type].tr_triggers.t_frozen = trigger;
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
@@ -4109,6 +3962,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		silent = 1;
 		goto cantfind_ext4;
 	}
+	ext4_setup_csum_trigger(sb, EXT4_JTR_ORPHAN_FILE,
+				ext4_orphan_file_block_trigger);
 
 	/* Load the checksum driver */
 	sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
@@ -4773,6 +4628,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_root = NULL;
 
 	needs_recovery = (es->s_last_orphan != 0 ||
+			  ext4_has_feature_orphan_present(sb) ||
 			  ext4_has_feature_journal_needs_recovery(sb));
 
 	if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb))
@@ -5029,6 +4885,14 @@ no_journal:
 		err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
 					  GFP_KERNEL);
 	}
+	/*
+	 * Update the checksum after updating free space/inode
+	 * counters.  Otherwise the superblock can have an incorrect
+	 * checksum in the buffer cache until it is written out and
+	 * e2fsprogs programs trying to open a file system immediately
+	 * after it is mounted can fail.
+	 */
+	ext4_superblock_csum_set(sb);
 	if (!err)
 		err = percpu_counter_init(&sbi->s_dirs_counter,
 					  ext4_count_dirs(sb), GFP_KERNEL);
@@ -5063,12 +4927,15 @@ no_journal:
 	if (err)
 		goto failed_mount7;
 
+	err = ext4_init_orphan_info(sb);
+	if (err)
+		goto failed_mount8;
 #ifdef CONFIG_QUOTA
 	/* Enable quota usage during mount. */
 	if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) {
 		err = ext4_enable_quotas(sb);
 		if (err)
-			goto failed_mount8;
+			goto failed_mount9;
 	}
 #endif  /* CONFIG_QUOTA */
 
@@ -5087,7 +4954,7 @@ no_journal:
 		ext4_msg(sb, KERN_INFO, "recovery complete");
 		err = ext4_mark_recovery_complete(sb, es);
 		if (err)
-			goto failed_mount8;
+			goto failed_mount9;
 	}
 	if (EXT4_SB(sb)->s_journal) {
 		if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
@@ -5133,6 +5000,8 @@ cantfind_ext4:
 		ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem");
 	goto failed_mount;
 
+failed_mount9:
+	ext4_release_orphan_info(sb);
 failed_mount8:
 	ext4_unregister_sysfs(sb);
 	kobject_put(&sbi->s_kobj);
@@ -5643,8 +5512,15 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
 	if (err < 0)
 		goto out;
 
-	if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
+	if (sb_rdonly(sb) && (ext4_has_feature_journal_needs_recovery(sb) ||
+	    ext4_has_feature_orphan_present(sb))) {
+		if (!ext4_orphan_file_empty(sb)) {
+			ext4_error(sb, "Orphan file not empty on read-only fs.");
+			err = -EFSCORRUPTED;
+			goto out;
+		}
 		ext4_clear_feature_journal_needs_recovery(sb);
+		ext4_clear_feature_orphan_present(sb);
 		ext4_commit_super(sb);
 	}
 out:
@@ -5787,6 +5663,8 @@ static int ext4_freeze(struct super_block *sb)
 
 		/* Journal blocked and flushed, clear needs_recovery flag. */
 		ext4_clear_feature_journal_needs_recovery(sb);
+		if (ext4_orphan_file_empty(sb))
+			ext4_clear_feature_orphan_present(sb);
 	}
 
 	error = ext4_commit_super(sb);
@@ -5809,6 +5687,8 @@ static int ext4_unfreeze(struct super_block *sb)
 	if (EXT4_SB(sb)->s_journal) {
 		/* Reset the needs_recovery flag before the fs is unlocked. */
 		ext4_set_feature_journal_needs_recovery(sb);
+		if (ext4_has_feature_orphan_file(sb))
+			ext4_set_feature_orphan_present(sb);
 	}
 
 	ext4_commit_super(sb);
@@ -6012,7 +5892,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 			 * around from a previously readonly bdev mount,
 			 * require a full umount/remount for now.
 			 */
-			if (es->s_last_orphan) {
+			if (es->s_last_orphan || !ext4_orphan_file_empty(sb)) {
 				ext4_msg(sb, KERN_WARNING, "Couldn't "
 				       "remount RDWR because of unprocessed "
 				       "orphan inode list.  Please "
@@ -6309,16 +6189,6 @@ static int ext4_write_info(struct super_block *sb, int type)
 	return ret;
 }
 
-/*
- * Turn on quotas during mount time - we need to find
- * the quota file and such...
- */
-static int ext4_quota_on_mount(struct super_block *sb, int type)
-{
-	return dquot_quota_on_mount(sb, get_qf_name(sb, EXT4_SB(sb), type),
-					EXT4_SB(sb)->s_jquota_fmt, type);
-}
-
 static void lockdep_set_quota_inode(struct inode *inode, int subclass)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -6448,7 +6318,7 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id,
 }
 
 /* Enable usage tracking for all quota types. */
-static int ext4_enable_quotas(struct super_block *sb)
+int ext4_enable_quotas(struct super_block *sb)
 {
 	int type, err = 0;
 	unsigned long qf_inums[EXT4_MAXQUOTAS] = {
@@ -6606,7 +6476,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type,
 	if (!bh)
 		goto out;
 	BUFFER_TRACE(bh, "get write access");
-	err = ext4_journal_get_write_access(handle, bh);
+	err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE);
 	if (err) {
 		brelse(bh);
 		return err;