ext4: perform dax_device lookup at mount

The ->iomap_begin() operation is a hot path, so cache the
fs_dax_get_by_host() result at mount time to avoid the incurring the
hash lookup overhead on a per-i/o basis.

Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Reviewed-by: Jan Kara <jack@suse.cz>
Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

fs/ext4/ext4.h

@@ -1528,6 +1528,7 @@ struct ext4_sb_info {
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
+	struct dax_device *s_daxdev;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)

fs/ext4/inode.c

@@ -3404,7 +3404,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
-	struct block_device *bdev;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;
 	unsigned long last_block = (offset + length - 1) >> blkbits;
@@ -3473,12 +3473,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	}
 
 	iomap->flags = 0;
-	bdev = inode->i_sb->s_bdev;
-	iomap->bdev = bdev;
-	if (blk_queue_dax(bdev->bd_queue))
-		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
-	else
-		iomap->dax_dev = NULL;
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->dax_dev = sbi->s_daxdev;
 	iomap->offset = first_block << blkbits;
 
 	if (ret == 0) {
@@ -3511,7 +3507,6 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 	int blkbits = inode->i_blkbits;
 	bool truncate = false;
 
-	fs_put_dax(iomap->dax_dev);
 	if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
 		return 0;
 

fs/ext4/super.c

@@ -951,6 +951,7 @@ static void ext4_put_super(struct super_block *sb)
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
+	fs_put_dax(sbi->s_daxdev);
 	kfree(sbi);
 }
 
@@ -3377,6 +3378,7 @@ static void ext4_set_resv_clusters(struct super_block *sb)
 
 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);
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
@@ -3399,6 +3401,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
 	ext4_group_t first_not_zeroed;
 
+	sbi->s_daxdev = dax_dev;
 	if ((data && !orig_data) || !sbi)
 		goto out_free_base;
 
@@ -4378,6 +4381,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 out_free_base:
 	kfree(sbi);
 	kfree(orig_data);
+	fs_put_dax(dax_dev);
 	return err ? err : ret;
 }