Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/tytso/ext4

Pull ext4 changes from Ted Ts'o:
 "Ext4 updates for 3.13.  Mostly bug fixes and cleanups"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: add prototypes for macro-generated functions
  ext4: return non-zero st_blocks for inline data
  ext4: use prandom_u32() instead of get_random_bytes()
  ext4: remove unreachable code after ext4_can_extents_be_merged()
  ext4: remove unreachable code in ext4_can_extents_be_merged()
  ext4: avoid bh leak in retry path of ext4_expand_extra_isize_ea()
  ext4: don't count free clusters from a corrupt block group
  ext4: fix FITRIM in no journal mode
  ext4: drop set but otherwise unused variable from ext4_add_dirent_to_inline()
  ext4: change ext4_read_inline_dir() to return 0 on success
  ext4: pair trace_ext4_writepages & trace_ext4_writepages_result
  ext4: add ratelimiting to ext4 messages
  ext4: fix performance regression in ext4_writepages
  ext4: fixup kerndoc annotation of mpage_map_and_submit_extent()
  ext4: fix assertion in ext4_add_complete_io()

fs/ext4/balloc.c

@@ -640,6 +640,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 	struct ext4_group_desc *gdp;
 	ext4_group_t i;
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct ext4_group_info *grp;
 #ifdef EXT4FS_DEBUG
 	struct ext4_super_block *es;
 	ext4_fsblk_t bitmap_count;
@@ -655,7 +656,11 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += ext4_free_group_clusters(sb, gdp);
+		grp = NULL;
+		if (EXT4_SB(sb)->s_group_info)
+			grp = ext4_get_group_info(sb, i);
+		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			desc_count += ext4_free_group_clusters(sb, gdp);
 		brelse(bitmap_bh);
 		bitmap_bh = ext4_read_block_bitmap(sb, i);
 		if (bitmap_bh == NULL)
@@ -679,7 +684,11 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += ext4_free_group_clusters(sb, gdp);
+		grp = NULL;
+		if (EXT4_SB(sb)->s_group_info)
+			grp = ext4_get_group_info(sb, i);
+		if (!grp || !EXT4_MB_GRP_BBITMAP_CORRUPT(grp))
+			desc_count += ext4_free_group_clusters(sb, gdp);
 	}
 
 	return desc_count;

fs/ext4/ext4.h

@@ -29,6 +29,7 @@
 #include <linux/wait.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
+#include <linux/ratelimit.h>
 #include <crypto/hash.h>
 #ifdef __KERNEL__
 #include <linux/compat.h>
@@ -1314,6 +1315,11 @@ struct ext4_sb_info {
 	unsigned long s_es_last_sorted;
 	struct percpu_counter s_extent_cache_cnt;
 	spinlock_t s_es_lru_lock ____cacheline_aligned_in_smp;
+
+	/* Ratelimit ext4 messages. */
+	struct ratelimit_state s_err_ratelimit_state;
+	struct ratelimit_state s_warning_ratelimit_state;
+	struct ratelimit_state s_msg_ratelimit_state;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1396,7 +1402,18 @@ static inline void ext4_clear_inode_##name(struct inode *inode, int bit) \
 	clear_bit(bit + (offset), &EXT4_I(inode)->i_##field);		\
 }
 
+/* Add these declarations here only so that these functions can be
+ * found by name.  Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_flag(struct inode *inode, int bit);
+static inline void ext4_set_inode_flag(struct inode *inode, int bit);
+static inline void ext4_clear_inode_flag(struct inode *inode, int bit);
 EXT4_INODE_BIT_FNS(flag, flags, 0)
+
+/* Add these declarations here only so that these functions can be
+ * found by name.  Otherwise, they are very hard to locate. */
+static inline int ext4_test_inode_state(struct inode *inode, int bit);
+static inline void ext4_set_inode_state(struct inode *inode, int bit);
+static inline void ext4_clear_inode_state(struct inode *inode, int bit);
 #if (BITS_PER_LONG < 64)
 EXT4_INODE_BIT_FNS(state, state_flags, 0)
 

fs/ext4/extents.c

@@ -1666,7 +1666,7 @@ int
 ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 				struct ext4_extent *ex2)
 {
-	unsigned short ext1_ee_len, ext2_ee_len, max_len;
+	unsigned short ext1_ee_len, ext2_ee_len;
 
 	/*
 	 * Make sure that both extents are initialized. We don't merge
@@ -1677,11 +1677,6 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	if (ext4_ext_is_uninitialized(ex1) || ext4_ext_is_uninitialized(ex2))
 		return 0;
 
-	if (ext4_ext_is_uninitialized(ex1))
-		max_len = EXT_UNINIT_MAX_LEN;
-	else
-		max_len = EXT_INIT_MAX_LEN;
-
 	ext1_ee_len = ext4_ext_get_actual_len(ex1);
 	ext2_ee_len = ext4_ext_get_actual_len(ex2);
 
@@ -1694,7 +1689,7 @@ ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1,
 	 * as an RO_COMPAT feature, refuse to merge to extents if
 	 * this can result in the top bit of ee_len being set.
 	 */
-	if (ext1_ee_len + ext2_ee_len > max_len)
+	if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN)
 		return 0;
 #ifdef AGGRESSIVE_TEST
 	if (ext1_ee_len >= 4)
@@ -1720,7 +1715,6 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 	struct ext4_extent_header *eh;
 	unsigned int depth, len;
 	int merge_done = 0;
-	int uninitialized = 0;
 
 	depth = ext_depth(inode);
 	BUG_ON(path[depth].p_hdr == NULL);
@@ -1730,12 +1724,8 @@ static int ext4_ext_try_to_merge_right(struct inode *inode,
 		if (!ext4_can_extents_be_merged(inode, ex, ex + 1))
 			break;
 		/* merge with next extent! */
-		if (ext4_ext_is_uninitialized(ex))
-			uninitialized = 1;
 		ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 				+ ext4_ext_get_actual_len(ex + 1));
-		if (uninitialized)
-			ext4_ext_mark_uninitialized(ex);
 
 		if (ex + 1 < EXT_LAST_EXTENT(eh)) {
 			len = (EXT_LAST_EXTENT(eh) - ex - 1)
@@ -1890,7 +1880,6 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 	struct ext4_ext_path *npath = NULL;
 	int depth, len, err;
 	ext4_lblk_t next;
-	unsigned uninitialized = 0;
 	int mb_flags = 0;
 
 	if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
@@ -1942,18 +1931,8 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 			if (err)
 				return err;
 
-			/*
-			 * ext4_can_extents_be_merged should have checked
-			 * that either both extents are uninitialized, or
-			 * both aren't. Thus we need to check only one of
-			 * them here.
-			 */
-			if (ext4_ext_is_uninitialized(ex))
-				uninitialized = 1;
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
-			if (uninitialized)
-				ext4_ext_mark_uninitialized(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;
@@ -1976,20 +1955,10 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
 			if (err)
 				return err;
 
-			/*
-			 * ext4_can_extents_be_merged should have checked
-			 * that either both extents are uninitialized, or
-			 * both aren't. Thus we need to check only one of
-			 * them here.
-			 */
-			if (ext4_ext_is_uninitialized(ex))
-				uninitialized = 1;
 			ex->ee_block = newext->ee_block;
 			ext4_ext_store_pblock(ex, ext4_ext_pblock(newext));
 			ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)
 					+ ext4_ext_get_actual_len(newext));
-			if (uninitialized)
-				ext4_ext_mark_uninitialized(ex);
 			eh = path[depth].p_hdr;
 			nearex = ex;
 			goto merge;

fs/ext4/ialloc.c

@@ -432,7 +432,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
 			ext4fs_dirhash(qstr->name, qstr->len, &hinfo);
 			grp = hinfo.hash;
 		} else
-			get_random_bytes(&grp, sizeof(grp));
+			grp = prandom_u32();
 		parent_group = (unsigned)grp % ngroups;
 		for (i = 0; i < ngroups; i++) {
 			g = (parent_group + i) % ngroups;

fs/ext4/inline.c

@@ -994,11 +994,9 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	struct inode	*dir = dentry->d_parent->d_inode;
 	const char	*name = dentry->d_name.name;
 	int		namelen = dentry->d_name.len;
-	unsigned short	reclen;
 	int		err;
 	struct ext4_dir_entry_2 *de;
 
-	reclen = EXT4_DIR_REC_LEN(namelen);
 	err = ext4_find_dest_de(dir, inode, iloc->bh,
 				inline_start, inline_size,
 				name, namelen, &de);
@@ -1442,6 +1440,7 @@ int ext4_read_inline_dir(struct file *file,
 	if (ret < 0)
 		goto out;
 
+	ret = 0;
 	sb = inode->i_sb;
 	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
 	offset = ctx->pos;

fs/ext4/inode.c

@@ -2178,6 +2178,9 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
  *
  * @handle - handle for journal operations
  * @mpd - extent to map
+ * @give_up_on_write - we set this to true iff there is a fatal error and there
+ *                     is no hope of writing the data. The caller should discard
+ *                     dirty pages to avoid infinite loops.
  *
  * The function maps extent starting at mpd->lblk of length mpd->len. If it is
  * delayed, blocks are allocated, if it is unwritten, we may need to convert
@@ -2295,6 +2298,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 	struct address_space *mapping = mpd->inode->i_mapping;
 	struct pagevec pvec;
 	unsigned int nr_pages;
+	long left = mpd->wbc->nr_to_write;
 	pgoff_t index = mpd->first_page;
 	pgoff_t end = mpd->last_page;
 	int tag;
@@ -2330,6 +2334,17 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			if (page->index > end)
 				goto out;
 
+			/*
+			 * Accumulated enough dirty pages? This doesn't apply
+			 * to WB_SYNC_ALL mode. For integrity sync we have to
+			 * keep going because someone may be concurrently
+			 * dirtying pages, and we might have synced a lot of
+			 * newly appeared dirty pages, but have not synced all
+			 * of the old dirty pages.
+			 */
+			if (mpd->wbc->sync_mode == WB_SYNC_NONE && left <= 0)
+				goto out;
+
 			/* If we can't merge this page, we are done. */
 			if (mpd->map.m_len > 0 && mpd->next_page != page->index)
 				goto out;
@@ -2364,19 +2379,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
 			if (err <= 0)
 				goto out;
 			err = 0;
-
-			/*
-			 * Accumulated enough dirty pages? This doesn't apply
-			 * to WB_SYNC_ALL mode. For integrity sync we have to
-			 * keep going because someone may be concurrently
-			 * dirtying pages, and we might have synced a lot of
-			 * newly appeared dirty pages, but have not synced all
-			 * of the old dirty pages.
-			 */
-			if (mpd->wbc->sync_mode == WB_SYNC_NONE &&
-			    mpd->next_page - mpd->first_page >=
-							mpd->wbc->nr_to_write)
-				goto out;
+			left--;
 		}
 		pagevec_release(&pvec);
 		cond_resched();
@@ -2420,16 +2423,15 @@ static int ext4_writepages(struct address_space *mapping,
 	 * because that could violate lock ordering on umount
 	 */
 	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
-		return 0;
+		goto out_writepages;
 
 	if (ext4_should_journal_data(inode)) {
 		struct blk_plug plug;
-		int ret;
 
 		blk_start_plug(&plug);
 		ret = write_cache_pages(mapping, wbc, __writepage, mapping);
 		blk_finish_plug(&plug);
-		return ret;
+		goto out_writepages;
 	}
 
 	/*
@@ -2442,8 +2444,10 @@ static int ext4_writepages(struct address_space *mapping,
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
-		return -EROFS;
+	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+		ret = -EROFS;
+		goto out_writepages;
+	}
 
 	if (ext4_should_dioread_nolock(inode)) {
 		/*
@@ -4689,6 +4693,15 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	inode = dentry->d_inode;
 	generic_fillattr(inode, stat);
 
+	/*
+	 * If there is inline data in the inode, the inode will normally not
+	 * have data blocks allocated (it may have an external xattr block).
+	 * Report at least one sector for such files, so tools like tar, rsync,
+	 * others doen't incorrectly think the file is completely sparse.
+	 */
+	if (unlikely(ext4_has_inline_data(inode)))
+		stat->blocks += (stat->size + 511) >> 9;
+
 	/*
 	 * We can't update i_blocks if the block allocation is delayed
 	 * otherwise in the case of system crash before the real block
@@ -4700,9 +4713,8 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	 * blocks for this file.
 	 */
 	delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb),
-				EXT4_I(inode)->i_reserved_data_blocks);
-
-	stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits-9);
+				   EXT4_I(inode)->i_reserved_data_blocks);
+	stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9);
 	return 0;
 }
 

fs/ext4/mballoc.c

@@ -4794,8 +4794,8 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 					 " group:%d block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
 					 err);
-		}
-
+		} else
+			EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
 
 		ext4_lock_group(sb, block_group);
 		mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);

fs/ext4/mmp.c

@@ -259,7 +259,7 @@ static unsigned int mmp_new_seq(void)
 	u32 new_seq;
 
 	do {
-		get_random_bytes(&new_seq, sizeof(u32));
+		new_seq = prandom_u32();
 	} while (new_seq > EXT4_MMP_SEQ_MAX);
 
 	return new_seq;

fs/ext4/page-io.c

@@ -197,14 +197,15 @@ static void dump_completed_IO(struct inode *inode, struct list_head *head)
 static void ext4_add_complete_io(ext4_io_end_t *io_end)
 {
 	struct ext4_inode_info *ei = EXT4_I(io_end->inode);
+	struct ext4_sb_info *sbi = EXT4_SB(io_end->inode->i_sb);
 	struct workqueue_struct *wq;
 	unsigned long flags;
 
 	/* Only reserved conversions from writeback should enter here */
 	WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
-	WARN_ON(!io_end->handle);
+	WARN_ON(!io_end->handle && sbi->s_journal);
 	spin_lock_irqsave(&ei->i_completed_io_lock, flags);
-	wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+	wq = sbi->rsv_conversion_wq;
 	if (list_empty(&ei->i_rsv_conversion_list))
 		queue_work(wq, &ei->i_rsv_conversion_work);
 	list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);