Merge commit 'v3.4.8' into android-t114-3.4-rebased

Linux v3.4.8

Conflicts:
	drivers/net/tun.c
	kernel/power/suspend.c

Change-Id: Ia26546425cd20f127dbf4dd58cfca41bda47d23d
Signed-off-by: Varun Wadekar <vwadekar@nvidia.com>

9 files changed, 199 insertions, 94 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 8da837be0c82..df76291d692b 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -584,7 +584,8 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 		if (bitmap_bh == NULL)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_BLOCKS_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
 			i, ext4_free_group_clusters(sb, gdp), x);
 		bitmap_count += x;
diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c
index fa3af81ac565..bbde5d582978 100644
--- a/fs/ext4/bitmap.c
+++ b/fs/ext4/bitmap.c
@@ -11,21 +11,15 @@
 #include <linux/jbd2.h>
 #include "ext4.h"
 
-#ifdef EXT4FS_DEBUG
-
 static const int nibblemap[] = {4, 3, 3, 2, 3, 2, 2, 1, 3, 2, 2, 1, 2, 1, 1, 0};
 
-unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars)
+unsigned int ext4_count_free(char *bitmap, unsigned int numchars)
 {
 	unsigned int i, sum = 0;
 
-	if (!map)
-		return 0;
 	for (i = 0; i < numchars; i++)
-		sum += nibblemap[map->b_data[i] & 0xf] +
-			nibblemap[(map->b_data[i] >> 4) & 0xf];
+		sum += nibblemap[bitmap[i] & 0xf] +
+			nibblemap[(bitmap[i] >> 4) & 0xf];
 	return sum;
 }
 
-#endif  /*  EXT4FS_DEBUG  */
-
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0e01e90add8b..47d1c8cda0cb 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1140,8 +1140,7 @@ struct ext4_sb_info {
 	unsigned long s_desc_per_block;	/* Number of group descriptors per block */
 	ext4_group_t s_groups_count;	/* Number of groups in the fs */
 	ext4_group_t s_blockfile_groups;/* Groups acceptable for non-extent files */
-	unsigned long s_overhead_last;  /* Last calculated overhead */
-	unsigned long s_blocks_last;    /* Last seen block count */
+	unsigned long s_overhead;  /* # of fs overhead clusters */
 	unsigned int s_cluster_ratio;	/* Number of blocks per cluster */
 	unsigned int s_cluster_bits;	/* log2 of s_cluster_ratio */
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
@@ -1783,7 +1782,7 @@ struct mmpd_data {
 # define NORET_AND	noreturn,
 
 /* bitmap.c */
-extern unsigned int ext4_count_free(struct buffer_head *, unsigned);
+extern unsigned int ext4_count_free(char *bitmap, unsigned numchars);
 
 /* balloc.c */
 extern unsigned int ext4_block_group(struct super_block *sb,
@@ -1950,6 +1949,7 @@ extern int ext4_group_extend(struct super_block *sb,
 extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count);
 
 /* super.c */
+extern int ext4_calculate_overhead(struct super_block *sb);
 extern void *ext4_kvmalloc(size_t size, gfp_t flags);
 extern void *ext4_kvzalloc(size_t size, gfp_t flags);
 extern void ext4_kvfree(void *ptr);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index abcdeab67f52..6b7daa45f6bf 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2503,10 +2503,10 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 {
 	struct super_block *sb = inode->i_sb;
 	int depth = ext_depth(inode);
-	struct ext4_ext_path *path;
+	struct ext4_ext_path *path = NULL;
 	ext4_fsblk_t partial_cluster = 0;
 	handle_t *handle;
-	int i, err;
+	int i = 0, err;
 
 	ext_debug("truncate since %u to %u\n", start, end);
 
@@ -2539,8 +2539,12 @@ again:
 		}
 		depth = ext_depth(inode);
 		ex = path[depth].p_ext;
-		if (!ex)
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			path = NULL;
 			goto cont;
+		}
 
 		ee_block = le32_to_cpu(ex->ee_block);
 
@@ -2570,8 +2574,6 @@ again:
 			if (err < 0)
 				goto out;
 		}
-		ext4_ext_drop_refs(path);
-		kfree(path);
 	}
 cont:
 
@@ -2580,19 +2582,27 @@ cont:
 	 * after i_size and walking into the tree depth-wise.
 	 */
 	depth = ext_depth(inode);
-	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1), GFP_NOFS);
-	if (path == NULL) {
-		ext4_journal_stop(handle);
-		return -ENOMEM;
-	}
-	path[0].p_depth = depth;
-	path[0].p_hdr = ext_inode_hdr(inode);
+	if (path) {
+		int k = i = depth;
+		while (--k > 0)
+			path[k].p_block =
+				le16_to_cpu(path[k].p_hdr->eh_entries)+1;
+	} else {
+		path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+			       GFP_NOFS);
+		if (path == NULL) {
+			ext4_journal_stop(handle);
+			return -ENOMEM;
+		}
+		path[0].p_depth = depth;
+		path[0].p_hdr = ext_inode_hdr(inode);
 
-	if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
-		err = -EIO;
-		goto out;
+		if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+			err = -EIO;
+			goto out;
+		}
 	}
-	i = err = 0;
+	err = 0;
 
 	while (i >= 0 && err == 0) {
 		if (i == depth) {
@@ -2706,8 +2716,10 @@ cont:
 out:
 	ext4_ext_drop_refs(path);
 	kfree(path);
-	if (err == -EAGAIN)
+	if (err == -EAGAIN) {
+		path = NULL;
 		goto again;
+	}
 	ext4_journal_stop(handle);
 
 	return err;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 8900f8b2ad48..0ee374d27fdb 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1013,7 +1013,8 @@ unsigned long ext4_count_free_inodes(struct super_block *sb)
 		if (!bitmap_bh)
 			continue;
 
-		x = ext4_count_free(bitmap_bh, EXT4_INODES_PER_GROUP(sb) / 8);
+		x = ext4_count_free(bitmap_bh->b_data,
+				    EXT4_INODES_PER_GROUP(sb) / 8);
 		printk(KERN_DEBUG "group %lu: stored = %d, counted = %lu\n",
 			(unsigned long) i, ext4_free_inodes_count(sb, gdp), x);
 		bitmap_count += x;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c77b0bd2c711..55a654d86182 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -279,6 +279,15 @@ void ext4_da_update_reserve_space(struct inode *inode,
 		used = ei->i_reserved_data_blocks;
 	}
 
+	if (unlikely(ei->i_allocated_meta_blocks > ei->i_reserved_meta_blocks)) {
+		ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, allocated %d "
+			 "with only %d reserved metadata blocks\n", __func__,
+			 inode->i_ino, ei->i_allocated_meta_blocks,
+			 ei->i_reserved_meta_blocks);
+		WARN_ON(1);
+		ei->i_allocated_meta_blocks = ei->i_reserved_meta_blocks;
+	}
+
 	/* Update per-inode reservations */
 	ei->i_reserved_data_blocks -= used;
 	ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks;
@@ -1104,6 +1113,17 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	unsigned int md_needed;
 	int ret;
+	ext4_lblk_t save_last_lblock;
+	int save_len;
+
+	/*
+	 * We will charge metadata quota at writeout time; this saves
+	 * us from metadata over-estimation, though we may go over by
+	 * a small amount in the end.  Here we just reserve for data.
+	 */
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+	if (ret)
+		return ret;
 
 	/*
 	 * recalculate the amount of metadata blocks to reserve
@@ -1112,32 +1132,31 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock)
 	 */
 repeat:
 	spin_lock(&ei->i_block_reservation_lock);
+	/*
+	 * ext4_calc_metadata_amount() has side effects, which we have
+	 * to be prepared undo if we fail to claim space.
+	 */
+	save_len = ei->i_da_metadata_calc_len;
+	save_last_lblock = ei->i_da_metadata_calc_last_lblock;
 	md_needed = EXT4_NUM_B2C(sbi,
 				 ext4_calc_metadata_amount(inode, lblock));
 	trace_ext4_da_reserve_space(inode, md_needed);
-	spin_unlock(&ei->i_block_reservation_lock);
 
 	/*
-	 * We will charge metadata quota at writeout time; this saves
-	 * us from metadata over-estimation, though we may go over by
-	 * a small amount in the end.  Here we just reserve for data.
-	 */
-	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
-	if (ret)
-		return ret;
-	/*
 	 * We do still charge estimated metadata to the sb though;
 	 * we cannot afford to run out of free blocks.
 	 */
 	if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) {
-		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+		ei->i_da_metadata_calc_len = save_len;
+		ei->i_da_metadata_calc_last_lblock = save_last_lblock;
+		spin_unlock(&ei->i_block_reservation_lock);
 		if (ext4_should_retry_alloc(inode->i_sb, &retries)) {
 			yield();
 			goto repeat;
 		}
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
 		return -ENOSPC;
 	}
-	spin_lock(&ei->i_block_reservation_lock);
 	ei->i_reserved_data_blocks++;
 	ei->i_reserved_meta_blocks += md_needed;
 	spin_unlock(&ei->i_block_reservation_lock);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 1365903a5144..9727522e2716 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -261,7 +261,6 @@ group_extend_out:
 		err = ext4_move_extents(filp, donor_filp, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
 		mnt_drop_write_file(filp);
-		mnt_drop_write(filp->f_path.mnt);
 
 		if (copy_to_user((struct move_extent __user *)arg,
 				 &me, sizeof(me)))
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 53589ff8824b..3407a62590d6 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1141,7 +1141,7 @@ static void ext4_update_super(struct super_block *sb,
 	struct ext4_new_group_data *group_data = flex_gd->groups;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	int i;
+	int i, ret;
 
 	BUG_ON(flex_gd->count == 0 || group_data == NULL);
 	/*
@@ -1216,6 +1216,11 @@ static void ext4_update_super(struct super_block *sb,
 			   &sbi->s_flex_groups[flex_group].free_inodes);
 	}
 
+	/*
+	 * Update the fs overhead information
+	 */
+	ext4_calculate_overhead(sb);
+
 	if (test_opt(sb, DEBUG))
 		printk(KERN_DEBUG "EXT4-fs: added group %u:"
 		       "%llu blocks(%llu free %llu reserved)\n", flex_gd->count,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 7449e77b9728..65f3e0d203ae 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2944,6 +2944,114 @@ static void ext4_destroy_lazyinit_thread(void)
 	kthread_stop(ext4_lazyinit_task);
 }
 
+/*
+ * Note: calculating the overhead so we can be compatible with
+ * historical BSD practice is quite difficult in the face of
+ * clusters/bigalloc.  This is because multiple metadata blocks from
+ * different block group can end up in the same allocation cluster.
+ * Calculating the exact overhead in the face of clustered allocation
+ * requires either O(all block bitmaps) in memory or O(number of block
+ * groups**2) in time.  We will still calculate the superblock for
+ * older file systems --- and if we come across with a bigalloc file
+ * system with zero in s_overhead_clusters the estimate will be close to
+ * correct especially for very large cluster sizes --- but for newer
+ * file systems, it's better to calculate this figure once at mkfs
+ * time, and store it in the superblock.  If the superblock value is
+ * present (even for non-bigalloc file systems), we will use it.
+ */
+static int count_overhead(struct super_block *sb, ext4_group_t grp,
+			  char *buf)
+{
+	struct ext4_sb_info	*sbi = EXT4_SB(sb);
+	struct ext4_group_desc	*gdp;
+	ext4_fsblk_t		first_block, last_block, b;
+	ext4_group_t		i, ngroups = ext4_get_groups_count(sb);
+	int			s, j, count = 0;
+
+	first_block = le32_to_cpu(sbi->s_es->s_first_data_block) +
+		(grp * EXT4_BLOCKS_PER_GROUP(sb));
+	last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1;
+	for (i = 0; i < ngroups; i++) {
+		gdp = ext4_get_group_desc(sb, i, NULL);
+		b = ext4_block_bitmap(sb, gdp);
+		if (b >= first_block && b <= last_block) {
+			ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
+			count++;
+		}
+		b = ext4_inode_bitmap(sb, gdp);
+		if (b >= first_block && b <= last_block) {
+			ext4_set_bit(EXT4_B2C(sbi, b - first_block), buf);
+			count++;
+		}
+		b = ext4_inode_table(sb, gdp);
+		if (b >= first_block && b + sbi->s_itb_per_group <= last_block)
+			for (j = 0; j < sbi->s_itb_per_group; j++, b++) {
+				int c = EXT4_B2C(sbi, b - first_block);
+				ext4_set_bit(c, buf);
+				count++;
+			}
+		if (i != grp)
+			continue;
+		s = 0;
+		if (ext4_bg_has_super(sb, grp)) {
+			ext4_set_bit(s++, buf);
+			count++;
+		}
+		for (j = ext4_bg_num_gdb(sb, grp); j > 0; j--) {
+			ext4_set_bit(EXT4_B2C(sbi, s++), buf);
+			count++;
+		}
+	}
+	if (!count)
+		return 0;
+	return EXT4_CLUSTERS_PER_GROUP(sb) -
+		ext4_count_free(buf, EXT4_CLUSTERS_PER_GROUP(sb) / 8);
+}
+
+/*
+ * Compute the overhead and stash it in sbi->s_overhead
+ */
+int ext4_calculate_overhead(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+	ext4_group_t i, ngroups = ext4_get_groups_count(sb);
+	ext4_fsblk_t overhead = 0;
+	char *buf = (char *) get_zeroed_page(GFP_KERNEL);
+
+	memset(buf, 0, PAGE_SIZE);
+	if (!buf)
+		return -ENOMEM;
+
+	/*
+	 * Compute the overhead (FS structures).  This is constant
+	 * for a given filesystem unless the number of block groups
+	 * changes so we cache the previous value until it does.
+	 */
+
+	/*
+	 * All of the blocks before first_data_block are overhead
+	 */
+	overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
+
+	/*
+	 * Add the overhead found in each block group
+	 */
+	for (i = 0; i < ngroups; i++) {
+		int blks;
+
+		blks = count_overhead(sb, i, buf);
+		overhead += blks;
+		if (blks)
+			memset(buf, 0, PAGE_SIZE);
+		cond_resched();
+	}
+	sbi->s_overhead = overhead;
+	smp_wmb();
+	free_page((unsigned long) buf);
+	return 0;
+}
+
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
 	char *orig_data = kstrdup(data, GFP_KERNEL);
@@ -3559,6 +3667,18 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 no_journal:
 	/*
+	 * Get the # of file system overhead blocks from the
+	 * superblock if present.
+	 */
+	if (es->s_overhead_clusters)
+		sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters);
+	else {
+		ret = ext4_calculate_overhead(sb);
+		if (ret)
+			goto failed_mount_wq;
+	}
+
+	/*
 	 * The maximum number of concurrent works can be high and
 	 * concurrency isn't really necessary.  Limit it to 1.
 	 */
@@ -4421,67 +4541,21 @@ restore_opts:
 	return err;
 }
 
-/*
- * Note: calculating the overhead so we can be compatible with
- * historical BSD practice is quite difficult in the face of
- * clusters/bigalloc.  This is because multiple metadata blocks from
- * different block group can end up in the same allocation cluster.
- * Calculating the exact overhead in the face of clustered allocation
- * requires either O(all block bitmaps) in memory or O(number of block
- * groups**2) in time.  We will still calculate the superblock for
- * older file systems --- and if we come across with a bigalloc file
- * system with zero in s_overhead_clusters the estimate will be close to
- * correct especially for very large cluster sizes --- but for newer
- * file systems, it's better to calculate this figure once at mkfs
- * time, and store it in the superblock.  If the superblock value is
- * present (even for non-bigalloc file systems), we will use it.
- */
 static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
-	struct ext4_group_desc *gdp;
+	ext4_fsblk_t overhead = 0;
 	u64 fsid;
 	s64 bfree;
 
-	if (test_opt(sb, MINIX_DF)) {
-		sbi->s_overhead_last = 0;
-	} else if (es->s_overhead_clusters) {
-		sbi->s_overhead_last = le32_to_cpu(es->s_overhead_clusters);
-	} else if (sbi->s_blocks_last != ext4_blocks_count(es)) {
-		ext4_group_t i, ngroups = ext4_get_groups_count(sb);
-		ext4_fsblk_t overhead = 0;
-
-		/*
-		 * Compute the overhead (FS structures).  This is constant
-		 * for a given filesystem unless the number of block groups
-		 * changes so we cache the previous value until it does.
-		 */
-
-		/*
-		 * All of the blocks before first_data_block are
-		 * overhead
-		 */
-		overhead = EXT4_B2C(sbi, le32_to_cpu(es->s_first_data_block));
-
-		/*
-		 * Add the overhead found in each block group
-		 */
-		for (i = 0; i < ngroups; i++) {
-			gdp = ext4_get_group_desc(sb, i, NULL);
-			overhead += ext4_num_overhead_clusters(sb, i, gdp);
-			cond_resched();
-		}
-		sbi->s_overhead_last = overhead;
-		smp_wmb();
-		sbi->s_blocks_last = ext4_blocks_count(es);
-	}
+	if (!test_opt(sb, MINIX_DF))
+		overhead = sbi->s_overhead;
 
 	buf->f_type = EXT4_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_blocks = (ext4_blocks_count(es) -
-			 EXT4_C2B(sbi, sbi->s_overhead_last));
+	buf->f_blocks = ext4_blocks_count(es) - EXT4_C2B(sbi, sbi->s_overhead);
 	bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) -
 		percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter);
 	/* prevent underflow in case that few free space is available */