Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: Patch up how we claim metadata blocks for quota purposes
  ext4: Ensure zeroout blocks have no dirty metadata
  ext4: return correct wbc.nr_to_write in ext4_da_writepages
  ext4: Update documentation to correct the inode_readahead_blks option name
  jbd2: don't use __GFP_NOFAIL in journal_init_common()
  ext4: flush delalloc blocks when space is low
  fs-writeback: Add helper function to start writeback if idle
  ext4: Eliminate potential double free on error path
  ext4: fix unsigned long long printk warning in super.c
  ext4, jbd2: Add barriers for file systems with exernal journals
  ext4: replace BUG() with return -EIO in ext4_ext_get_blocks
  ext4: add module aliases for ext2 and ext3
  ext4: Don't ask about supporting ext2/3 in ext4 if ext4 is not configured
  ext4: remove unused #include <linux/version.h>

Documentation/filesystems/ext4.txt

@@ -196,7 +196,7 @@ nobarrier		This also requires an IO stack which can support
 			also be used to enable or disable barriers, for
 			consistency with other ext4 mount options.
 
-inode_readahead=n	This tuning parameter controls the maximum
+inode_readahead_blks=n	This tuning parameter controls the maximum
 			number of inode table blocks that ext4's inode
 			table readahead algorithm will pre-read into
 			the buffer cache.  The default value is 32 blocks.

fs/ext4/Kconfig

@@ -28,6 +28,7 @@ config EXT4_FS
 
 config EXT4_USE_FOR_EXT23
 	bool "Use ext4 for ext2/ext3 file systems"
+	depends on EXT4_FS
 	depends on EXT3_FS=n || EXT2_FS=n
 	default y
 	help

fs/ext4/block_validity.c

@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
-#include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
 #include "ext4.h"

fs/ext4/extents.c

@@ -3023,6 +3023,14 @@ static int ext4_convert_unwritten_extents_dio(handle_t *handle,
 	return err;
 }
 
+static void unmap_underlying_metadata_blocks(struct block_device *bdev,
+			sector_t block, int count)
+{
+	int i;
+	for (i = 0; i < count; i++)
+                unmap_underlying_metadata(bdev, block + i);
+}
+
 static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 			ext4_lblk_t iblock, unsigned int max_blocks,
@@ -3098,6 +3106,18 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	} else
 		allocated = ret;
 	set_buffer_new(bh_result);
+	/*
+	 * if we allocated more blocks than requested
+	 * we need to make sure we unmap the extra block
+	 * allocated. The actual needed block will get
+	 * unmapped later when we find the buffer_head marked
+	 * new.
+	 */
+	if (allocated > max_blocks) {
+		unmap_underlying_metadata_blocks(inode->i_sb->s_bdev,
+					newblock + max_blocks,
+					allocated - max_blocks);
+	}
 map_out:
 	set_buffer_mapped(bh_result);
 out1:
@@ -3190,7 +3210,13 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	 * this situation is possible, though, _during_ tree modification;
 	 * this is why assert can't be put in ext4_ext_find_extent()
 	 */
-	BUG_ON(path[depth].p_ext == NULL && depth != 0);
+	if (path[depth].p_ext == NULL && depth != 0) {
+		ext4_error(inode->i_sb, __func__, "bad extent address "
+			   "inode: %lu, iblock: %d, depth: %d",
+			   inode->i_ino, iblock, depth);
+		err = -EIO;
+		goto out2;
+	}
 	eh = path[depth].p_hdr;
 
 	ex = path[depth].p_ext;

fs/ext4/fsync.c

@@ -88,9 +88,21 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
 		return ext4_force_commit(inode->i_sb);
 
 	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
-	if (jbd2_log_start_commit(journal, commit_tid))
+	if (jbd2_log_start_commit(journal, commit_tid)) {
+		/*
+		 * When the journal is on a different device than the
+		 * fs data disk, we need to issue the barrier in
+		 * writeback mode.  (In ordered mode, the jbd2 layer
+		 * will take care of issuing the barrier.  In
+		 * data=journal, all of the data blocks are written to
+		 * the journal device.)
+		 */
+		if (ext4_should_writeback_data(inode) &&
+		    (journal->j_fs_dev != journal->j_dev) &&
+		    (journal->j_flags & JBD2_BARRIER))
+			blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
 		jbd2_log_wait_commit(journal, commit_tid);
-	else if (journal->j_flags & JBD2_BARRIER)
+	} else if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
 	return ret;
 }

fs/ext4/inode.c

@@ -1043,43 +1043,47 @@ static int ext4_calc_metadata_amount(struct inode *inode, int blocks)
 	return ext4_indirect_calc_metadata_amount(inode, blocks);
 }
 
+/*
+ * Called with i_data_sem down, which is important since we can call
+ * ext4_discard_preallocations() from here.
+ */
 static void ext4_da_update_reserve_space(struct inode *inode, int used)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	int total, mdb, mdb_free, mdb_claim = 0;
-
-	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-	/* recalculate the number of metablocks still need to be reserved */
-	total = EXT4_I(inode)->i_reserved_data_blocks - used;
-	mdb = ext4_calc_metadata_amount(inode, total);
-
-	/* figure out how many metablocks to release */
-	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-	mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int mdb_free = 0;
+
+	spin_lock(&ei->i_block_reservation_lock);
+	if (unlikely(used > ei->i_reserved_data_blocks)) {
+		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d "
+			 "with only %d reserved data blocks\n",
+			 __func__, inode->i_ino, used,
+			 ei->i_reserved_data_blocks);
+		WARN_ON(1);
+		used = ei->i_reserved_data_blocks;
+	}
 
-	if (mdb_free) {
-		/* Account for allocated meta_blocks */
-		mdb_claim = EXT4_I(inode)->i_allocated_meta_blocks;
-		BUG_ON(mdb_free < mdb_claim);
-		mdb_free -= mdb_claim;
+	/* Update per-inode reservations */
+	ei->i_reserved_data_blocks -= used;
+	used += ei->i_allocated_meta_blocks;
+	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
+	ei->i_allocated_meta_blocks = 0;
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter, used);
 
-		/* update fs dirty blocks counter */
+	if (ei->i_reserved_data_blocks == 0) {
+		/*
+		 * We can release all of the reserved metadata blocks
+		 * only when we have written all of the delayed
+		 * allocation blocks.
+		 */
+		mdb_free = ei->i_allocated_meta_blocks;
 		percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free);
-		EXT4_I(inode)->i_allocated_meta_blocks = 0;
-		EXT4_I(inode)->i_reserved_meta_blocks = mdb;
+		ei->i_allocated_meta_blocks = 0;
 	}
-
-	/* update per-inode reservations */
-	BUG_ON(used  > EXT4_I(inode)->i_reserved_data_blocks);
-	EXT4_I(inode)->i_reserved_data_blocks -= used;
-	percpu_counter_sub(&sbi->s_dirtyblocks_counter, used + mdb_claim);
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	vfs_dq_claim_block(inode, used + mdb_claim);
-
-	/*
-	 * free those over-booking quota for metadata blocks
-	 */
+	/* Update quota subsystem */
+	vfs_dq_claim_block(inode, used);
 	if (mdb_free)
 		vfs_dq_release_reservation_block(inode, mdb_free);
 
@@ -1088,7 +1092,8 @@ static void ext4_da_update_reserve_space(struct inode *inode, int used)
 	 * there aren't any writers on the inode, we can discard the
 	 * inode's preallocations.
 	 */
-	if (!total && (atomic_read(&inode->i_writecount) == 0))
+	if ((ei->i_reserved_data_blocks == 0) &&
+	    (atomic_read(&inode->i_writecount) == 0))
 		ext4_discard_preallocations(inode);
 }
 
@@ -1801,7 +1806,8 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 {
 	int retries = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	unsigned long md_needed, mdblocks, total = 0;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned long md_needed, md_reserved, total = 0;
 
 	/*
 	 * recalculate the amount of metadata blocks to reserve
@@ -1809,35 +1815,44 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 	 * worse case is one extent per block
 	 */
 repeat:
-	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-	total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks;
-	mdblocks = ext4_calc_metadata_amount(inode, total);
-	BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks);
-
-	md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks;
+	spin_lock(&ei->i_block_reservation_lock);
+	md_reserved = ei->i_reserved_meta_blocks;
+	md_needed = ext4_calc_metadata_amount(inode, nrblocks);
 	total = md_needed + nrblocks;
-	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+	spin_unlock(&ei->i_block_reservation_lock);
 
 	/*
 	 * Make quota reservation here to prevent quota overflow
 	 * later. Real quota accounting is done at pages writeout
 	 * time.
 	 */
-	if (vfs_dq_reserve_block(inode, total))
+	if (vfs_dq_reserve_block(inode, total)) {
+		/* 
+		 * We tend to badly over-estimate the amount of
+		 * metadata blocks which are needed, so if we have
+		 * reserved any metadata blocks, try to force out the
+		 * inode and see if we have any better luck.
+		 */
+		if (md_reserved && retries++ <= 3)
+			goto retry;
 		return -EDQUOT;
+	}
 
 	if (ext4_claim_free_blocks(sbi, total)) {
 		vfs_dq_release_reservation_block(inode, total);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
+		retry:
+			if (md_reserved)
+				write_inode_now(inode, (retries == 3));
 			yield();
 			goto repeat;
 		}
 		return -ENOSPC;
 	}
-	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
-	EXT4_I(inode)->i_reserved_data_blocks += nrblocks;
-	EXT4_I(inode)->i_reserved_meta_blocks += md_needed;
-	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
+	spin_lock(&ei->i_block_reservation_lock);
+	ei->i_reserved_data_blocks += nrblocks;
+	ei->i_reserved_meta_blocks += md_needed;
+	spin_unlock(&ei->i_block_reservation_lock);
 
 	return 0;       /* success */
 }
@@ -1845,49 +1860,45 @@ static int ext4_da_reserve_space(struct inode *inode, int nrblocks)
 static void ext4_da_release_space(struct inode *inode, int to_free)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	int total, mdb, mdb_free, release;
+	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	if (!to_free)
 		return;		/* Nothing to release, exit */
 
 	spin_lock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	if (!EXT4_I(inode)->i_reserved_data_blocks) {
+	if (unlikely(to_free > ei->i_reserved_data_blocks)) {
 		/*
-		 * if there is no reserved blocks, but we try to free some
-		 * then the counter is messed up somewhere.
-		 * but since this function is called from invalidate
-		 * page, it's harmless to return without any action
+		 * if there aren't enough reserved blocks, then the
+		 * counter is messed up somewhere.  Since this
+		 * function is called from invalidate page, it's
+		 * harmless to return without any action.
 		 */
-		printk(KERN_INFO "ext4 delalloc try to release %d reserved "
-			    "blocks for inode %lu, but there is no reserved "
-			    "data blocks\n", to_free, inode->i_ino);
-		spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
-		return;
+		ext4_msg(inode->i_sb, KERN_NOTICE, "ext4_da_release_space: "
+			 "ino %lu, to_free %d with only %d reserved "
+			 "data blocks\n", inode->i_ino, to_free,
+			 ei->i_reserved_data_blocks);
+		WARN_ON(1);
+		to_free = ei->i_reserved_data_blocks;
 	}
+	ei->i_reserved_data_blocks -= to_free;
 
-	/* recalculate the number of metablocks still need to be reserved */
-	total = EXT4_I(inode)->i_reserved_data_blocks - to_free;
-	mdb = ext4_calc_metadata_amount(inode, total);
-
-	/* figure out how many metablocks to release */
-	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-	mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb;
-
-	release = to_free + mdb_free;
-
-	/* update fs dirty blocks counter for truncate case */
-	percpu_counter_sub(&sbi->s_dirtyblocks_counter, release);
+	if (ei->i_reserved_data_blocks == 0) {
+		/*
+		 * We can release all of the reserved metadata blocks
+		 * only when we have written all of the delayed
+		 * allocation blocks.
+		 */
+		to_free += ei->i_allocated_meta_blocks;
+		ei->i_allocated_meta_blocks = 0;
+	}
 
-	/* update per-inode reservations */
-	BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks);
-	EXT4_I(inode)->i_reserved_data_blocks -= to_free;
+	/* update fs dirty blocks counter */
+	percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free);
 
-	BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks);
-	EXT4_I(inode)->i_reserved_meta_blocks = mdb;
 	spin_unlock(&EXT4_I(inode)->i_block_reservation_lock);
 
-	vfs_dq_release_reservation_block(inode, release);
+	vfs_dq_release_reservation_block(inode, to_free);
 }
 
 static void ext4_da_page_release_reservation(struct page *page,
@@ -2967,7 +2978,6 @@ static int ext4_da_writepages(struct address_space *mapping,
 out_writepages:
 	if (!no_nrwrite_index_update)
 		wbc->no_nrwrite_index_update = 0;
-	if (wbc->nr_to_write > nr_to_writebump)
 	wbc->nr_to_write -= nr_to_writebump;
 	wbc->range_start = range_start;
 	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
@@ -2993,11 +3003,18 @@ static int ext4_nonda_switch(struct super_block *sb)
 	if (2 * free_blocks < 3 * dirty_blocks ||
 		free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) {
 		/*
-		 * free block count is less that 150% of dirty blocks
-		 * or free blocks is less that watermark
+		 * free block count is less than 150% of dirty blocks
+		 * or free blocks is less than watermark
 		 */
 		return 1;
 	}
+	/*
+	 * Even if we don't switch but are nearing capacity,
+	 * start pushing delalloc when 1/2 of free blocks are dirty.
+	 */
+	if (free_blocks < 2 * dirty_blocks)
+		writeback_inodes_sb_if_idle(sb);
+
 	return 0;
 }
 

fs/ext4/mballoc.h

@@ -17,7 +17,6 @@
 #include <linux/proc_fs.h>
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
-#include <linux/version.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
 #include "ext4_jbd2.h"

fs/ext4/super.c

@@ -2174,9 +2174,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_attr *a,
 	struct super_block *sb = sbi->s_buddy_cache->i_sb;
 
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
-			sbi->s_kbytes_written + 
+			(unsigned long long)(sbi->s_kbytes_written +
 			((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
-			  EXT4_SB(sb)->s_sectors_written_start) >> 1));
+			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
 static ssize_t inode_readahead_blks_store(struct ext4_attr *a,
@@ -4005,6 +4005,7 @@ static inline void unregister_as_ext2(void)
 {
 	unregister_filesystem(&ext2_fs_type);
 }
+MODULE_ALIAS("ext2");
 #else
 static inline void register_as_ext2(void) { }
 static inline void unregister_as_ext2(void) { }
@@ -4031,6 +4032,7 @@ static inline void unregister_as_ext3(void)
 {
 	unregister_filesystem(&ext3_fs_type);
 }
+MODULE_ALIAS("ext3");
 #else
 static inline void register_as_ext3(void) { }
 static inline void unregister_as_ext3(void) { }

fs/ext4/xattr.c

@@ -1332,6 +1332,8 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			goto cleanup;
 		kfree(b_entry_name);
 		kfree(buffer);
+		b_entry_name = NULL;
+		buffer = NULL;
 		brelse(is->iloc.bh);
 		kfree(is);
 		kfree(bs);

fs/fs-writeback.c

@@ -1186,6 +1186,23 @@ void writeback_inodes_sb(struct super_block *sb)
 }
 EXPORT_SYMBOL(writeback_inodes_sb);
 
+/**
+ * writeback_inodes_sb_if_idle	-	start writeback if none underway
+ * @sb: the superblock
+ *
+ * Invoke writeback_inodes_sb if no writeback is currently underway.
+ * Returns 1 if writeback was started, 0 if not.
+ */
+int writeback_inodes_sb_if_idle(struct super_block *sb)
+{
+	if (!writeback_in_progress(sb->s_bdi)) {
+		writeback_inodes_sb(sb);
+		return 1;
+	} else
+		return 0;
+}
+EXPORT_SYMBOL(writeback_inodes_sb_if_idle);
+
 /**
  * sync_inodes_sb	-	sync sb inode pages
  * @sb: the superblock

fs/jbd2/checkpoint.c

@@ -22,6 +22,7 @@
 #include <linux/jbd2.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 #include <trace/events/jbd2.h>
 
 /*
@@ -515,6 +516,20 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
 	journal->j_tail_sequence = first_tid;
 	journal->j_tail = blocknr;
 	spin_unlock(&journal->j_state_lock);
+
+	/*
+	 * If there is an external journal, we need to make sure that
+	 * any data blocks that were recently written out --- perhaps
+	 * by jbd2_log_do_checkpoint() --- are flushed out before we
+	 * drop the transactions from the external journal.  It's
+	 * unlikely this will be necessary, especially with a
+	 * appropriately sized journal, but we need this to guarantee
+	 * correctness.  Fortunately jbd2_cleanup_journal_tail()
+	 * doesn't get called all that often.
+	 */
+	if ((journal->j_fs_dev != journal->j_dev) &&
+	    (journal->j_flags & JBD2_BARRIER))
+		blkdev_issue_flush(journal->j_fs_dev, NULL);
 	if (!(journal->j_flags & JBD2_ABORT))
 		jbd2_journal_update_superblock(journal, 1);
 	return 0;

fs/jbd2/commit.c

@@ -259,6 +259,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 			ret = err;
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
+		commit_transaction->t_flushed_data_blocks = 1;
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
@@ -708,8 +709,17 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		}
 	}
 
-	/* Done it all: now write the commit record asynchronously. */
+	/* 
+	 * If the journal is not located on the file system device,
+	 * then we must flush the file system device before we issue
+	 * the commit record
+	 */
+	if (commit_transaction->t_flushed_data_blocks &&
+	    (journal->j_fs_dev != journal->j_dev) &&
+	    (journal->j_flags & JBD2_BARRIER))
+		blkdev_issue_flush(journal->j_fs_dev, NULL);
 
+	/* Done it all: now write the commit record asynchronously. */
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal,
 				      JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
 		err = journal_submit_commit_record(journal, commit_transaction,
@@ -720,13 +730,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			blkdev_issue_flush(journal->j_dev, NULL);
 	}
 
-	/*
-	 * This is the right place to wait for data buffers both for ASYNC
-	 * and !ASYNC commit. If commit is ASYNC, we need to wait only after
-	 * the commit block went to disk (which happens above). If commit is
-	 * SYNC, we need to wait for data buffers before we start writing
-	 * commit block, which happens below in such setting.
-	 */
 	err = journal_finish_inode_data_buffers(journal, commit_transaction);
 	if (err) {
 		printk(KERN_WARNING

fs/jbd2/journal.c

@@ -814,7 +814,7 @@ static journal_t * journal_init_common (void)
 	journal_t *journal;
 	int err;
 
-	journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
+	journal = kzalloc(sizeof(*journal), GFP_KERNEL);
 	if (!journal)
 		goto fail;
 

include/linux/jbd2.h

@@ -653,6 +653,7 @@ struct transaction_s
 	 * waiting for it to finish.
 	 */
 	unsigned int t_synchronous_commit:1;
+	unsigned int t_flushed_data_blocks:1;
 
 	/*
 	 * For use by the filesystem to store fs-specific data

include/linux/writeback.h

@@ -70,6 +70,7 @@ struct writeback_control {
 struct bdi_writeback;
 int inode_wait(void *);
 void writeback_inodes_sb(struct super_block *);
+int writeback_inodes_sb_if_idle(struct super_block *);
 void sync_inodes_sb(struct super_block *);
 void writeback_inodes_wbc(struct writeback_control *wbc);
 long wb_do_writeback(struct bdi_writeback *wb, int force_wait);