dax: return the partition offset from fs_dax_get_by_bdev

Prepare for the removal of the block_device from the DAX I/O path by
returning the partition offset from fs_dax_get_by_bdev so that the file
systems have it at hand for use during I/O.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Link: https://lore.kernel.org/r/20211129102203.2243509-26-hch@lst.de
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 45d931aefd06307bfacb5bfaada375b365a461b3..e7152a6c4cc4005d9668e47819ee20a198a96d7d 100644 (file)
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -69,17 +69,20 @@ EXPORT_SYMBOL_GPL(dax_remove_host);
 /**
  * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
  * @bdev: block device to find a dax_device for
+ * @start_off: returns the byte offset into the dax_device that @bdev starts
  */
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off)
 {
        struct dax_device *dax_dev;
+       u64 part_size;
        int id;
 
        if (!blk_queue_dax(bdev->bd_disk->queue))
                return NULL;
 
-       if ((get_start_sect(bdev) * SECTOR_SIZE) % PAGE_SIZE ||
-           (bdev_nr_sectors(bdev) * SECTOR_SIZE) % PAGE_SIZE) {
+       *start_off = get_start_sect(bdev) * SECTOR_SIZE;
+       part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE;
+       if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) {
                pr_info("%pg: error: unaligned partition for dax\n", bdev);
                return NULL;
        }

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4eba27e75c230e24a5788953d4eb293b42cb3eec..4e997c02bb0a090e3deeab6197bff28aa27b0e18 100644 (file)
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
                             struct mapped_device *md)
 {
        struct block_device *bdev;
-
+       u64 part_off;
        int r;
 
        BUG_ON(td->dm_dev.bdev);
@@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
        }
 
        td->dm_dev.bdev = bdev;
-       td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev);
+       td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off);
        return 0;
 }
 

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 3265688af7f9f575a40c27355f397b84bfa6aa69..c1e65346e9f15180346907f3f7184e1e3fc42555 100644 (file)
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -51,6 +51,7 @@ struct erofs_device_info {
        char *path;
        struct block_device *bdev;
        struct dax_device *dax_dev;
+       u64 dax_part_off;
 
        u32 blocks;
        u32 mapped_blkaddr;
@@ -109,6 +110,7 @@ struct erofs_sb_info {
 #endif /* CONFIG_EROFS_FS_ZIP */
        struct erofs_dev_context *devs;
        struct dax_device *dax_dev;
+       u64 dax_part_off;
        u64 total_blocks;
        u32 primarydevice_blocks;
 

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 0aed886473c8da05fa1ad3d0493ee53d740e1eb0..71efce16024d9acca3a980eebd8e68f0e7672881 100644 (file)
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -312,7 +312,7 @@ static int erofs_init_devices(struct super_block *sb,
                        goto err_out;
                }
                dif->bdev = bdev;
-               dif->dax_dev = fs_dax_get_by_bdev(bdev);
+               dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
                dif->blocks = le32_to_cpu(dis->blocks);
                dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
                sbi->total_blocks += dif->blocks;
@@ -644,7 +644,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
        sb->s_fs_info = sbi;
        sbi->opt = ctx->opt;
-       sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+       sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off);
        sbi->devs = ctx->devs;
        ctx->devs = NULL;
 

diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 3be9dd6412b789be147cc7c331124df964dfa481..d4f306aa5aceb1f77494f01c1cb3d83c2c22c7b4 100644 (file)
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -118,6 +118,7 @@ struct ext2_sb_info {
        spinlock_t s_lock;
        struct mb_cache *s_ea_block_cache;
        struct dax_device *s_daxdev;
+       u64 s_dax_part_off;
 };
 
 static inline spinlock_t *

diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7e23482862e69c0e5f63586ed24b12a96b367eee..94f1fbd7d3ac221f832612936d2165a5695880ac 100644 (file)
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -831,7 +831,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
        }
        sb->s_fs_info = sbi;
        sbi->s_sb_block = sb_block;
-       sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+       sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 
        spin_lock_init(&sbi->s_lock);
        ret = -EINVAL;

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 404dd50856e5d294c38e746c97dd50183d650eb0..9cc55bcda6ba44a5cbe0118c48e3aea1906acfbf 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1697,6 +1697,7 @@ struct ext4_sb_info {
         */
        struct percpu_rw_semaphore s_writepages_rwsem;
        struct dax_device *s_daxdev;
+       u64 s_dax_part_off;
 #ifdef CONFIG_EXT4_DEBUG
        unsigned long s_simulate_fail;
 #endif

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 8d7e3449c64729d7dbf325d1c6c4cad644565386..56228e33e52a29e4f8edcbdd7393b230203c5d75 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3913,7 +3913,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
        if (!sbi->s_blockgroup_lock)
                goto out_free_base;
 
-       sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+       sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
        sb->s_fs_info = sbi;
        sbi->s_sb = sb;
        sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 4d4553ffa7050c2e0211fe664bffe0e8b7be3b15..bbb0fbd34e649064ca764131bec26b68cfe3c751 100644 (file)
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1945,7 +1945,7 @@ xfs_alloc_buftarg(
        btp->bt_mount = mp;
        btp->bt_dev =  bdev->bd_dev;
        btp->bt_bdev = bdev;
-       btp->bt_daxdev = fs_dax_get_by_bdev(bdev);
+       btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
 
        /*
         * Buffer IO error rate limiting. Limit it to no more than 10 messages

diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index bd7f709f0d23254c3fcf8f685a2cb3d719417bc4..edcb6254fa6a87b3d7dbd88413670075dab0a19d 100644 (file)
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -89,6 +89,7 @@ typedef struct xfs_buftarg {
        dev_t                   bt_dev;
        struct block_device     *bt_bdev;
        struct dax_device       *bt_daxdev;
+       u64                     bt_dax_part_off;
        struct xfs_mount        *bt_mount;
        unsigned int            bt_meta_sectorsize;
        size_t                  bt_meta_sectormask;

diff --git a/include/linux/dax.h b/include/linux/dax.h
index b79036743e7fac0819028b140fd635fb39ade27b..f6f353382cc90ff81d7225cc43cfa17b390d42ed 100644 (file)
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -117,7 +117,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
        put_dax(dax_dev);
 }
 
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
+               u64 *start_off);
 int dax_writeback_mapping_range(struct address_space *mapping,
                struct dax_device *dax_dev, struct writeback_control *wbc);
 
@@ -138,7 +139,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
 {
 }
 
-static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
+               u64 *start_off)
 {
        return NULL;
 }