decouple DAX from block devices v2

decouple DAX from block devices v2

[Christoph Hellwig]

Hi Dan,

this series decouples the DAX from the block layer so that the
block_device is not needed at all for the DAX I/O path.

Changes since v1:
 - rebase on latest v5.16-rc
 - ensure the new dax zeroing helpers are always declared
 - fix a dax_dev leak in pmem_attach_disk
 - remove '\n' from an xfs format string
 - fix a pre-existing error handling bug in alloc_dev
 - fix a few whitespace issues
 - tighten an error check
 - use s64/u64 a little more
 - improve a few commit messages
 - add a CONFIG_FS_DAX ifdef to stub out IOMAP_DAX
 - improve how IOMAP_DAX is introduced and better document why it is
   added

[PATCH 01/29] dm: fix alloc_dax error handling in alloc_dev

[Christoph Hellwig]

Make sure ->dax_dev is NULL on error so that the cleanup path doesn't
trip over an ERR_PTR.

Reported-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/md/dm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 662742a310cbb..acc84dc1bded5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1786,8 +1786,10 @@ static struct mapped_device *alloc_dev(int minor)
 	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
 		md->dax_dev = alloc_dax(md, md->disk->disk_name,
 					&dm_dax_ops, 0);
-		if (IS_ERR(md->dax_dev))
+		if (IS_ERR(md->dax_dev)) {
+			md->dax_dev = NULL;
 			goto bad;
+		}
 	}
 
 	format_dev_t(md->name, MKDEV(_major, minor));
-- 
2.30.2

[PATCH 02/29] dm: make the DAX support depend on CONFIG_FS_DAX

[Christoph Hellwig]

The device mapper DAX support is all hanging off a block device and thus
can't be used with device dax.  Make it depend on CONFIG_FS_DAX instead
of CONFIG_DAX_DRIVER.  This also means that bdev_dax_pgoff only needs to
be built under CONFIG_FS_DAX now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/dax/super.c        | 6 ++----
 drivers/md/dm-linear.c     | 2 +-
 drivers/md/dm-log-writes.c | 2 +-
 drivers/md/dm-stripe.c     | 2 +-
 drivers/md/dm-writecache.c | 2 +-
 drivers/md/dm.c            | 2 +-
 6 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index b882cf8106ea3..e20d0cef10a18 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -63,7 +63,7 @@ static int dax_host_hash(const char *host)
 	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
 }
 
-#ifdef CONFIG_BLOCK
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
 #include <linux/blkdev.h>
 
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
@@ -80,7 +80,6 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 }
 EXPORT_SYMBOL(bdev_dax_pgoff);
 
-#if IS_ENABLED(CONFIG_FS_DAX)
 /**
  * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
  * @host: alternate name for the device registered by a dax driver
@@ -219,8 +218,7 @@ bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dax_supported);
-#endif /* CONFIG_FS_DAX */
-#endif /* CONFIG_BLOCK */
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
 enum dax_device_flags {
 	/* !alive + rcu grace period == no new operations / mappings */
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 66ba16713f696..0a260c35aeeed 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -162,7 +162,7 @@ static int linear_iterate_devices(struct dm_target *ti,
 	return fn(ti, lc->dev, lc->start, ti->len, data);
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn)
 {
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 0b3ef977ceeba..3155875d4e5b0 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -901,7 +901,7 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit
 	limits->io_min = limits->physical_block_size;
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
 static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes,
 		   struct iov_iter *i)
 {
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 6660b6b53d5bf..f084607220293 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -300,7 +300,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn)
 {
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 4b8991cde223d..4f31591d2d25e 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -38,7 +38,7 @@
 #define BITMAP_GRANULARITY	PAGE_SIZE
 #endif
 
-#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_FS_DAX)
 #define DM_WRITECACHE_HAS_PMEM
 #endif
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index acc84dc1bded5..b93fcc91176e5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1783,7 +1783,7 @@ static struct mapped_device *alloc_dev(int minor)
 	md->disk->private_data = md;
 	sprintf(md->disk->disk_name, "dm-%d", minor);
 
-	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
+	if (IS_ENABLED(CONFIG_FS_DAX)) {
 		md->dax_dev = alloc_dax(md, md->disk->disk_name,
 					&dm_dax_ops, 0);
 		if (IS_ERR(md->dax_dev)) {
-- 
2.30.2

[PATCH 03/29] dax: remove CONFIG_DAX_DRIVER

[Christoph Hellwig]

CONFIG_DAX_DRIVER only selects CONFIG_DAX now, so remove it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/Kconfig        | 4 ----
 drivers/nvdimm/Kconfig     | 2 +-
 drivers/s390/block/Kconfig | 2 +-
 fs/fuse/Kconfig            | 2 +-
 4 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index d2834c2cfa10d..954ab14ba7778 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -1,8 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config DAX_DRIVER
-	select DAX
-	bool
-
 menuconfig DAX
 	tristate "DAX: direct access to differentiated memory"
 	select SRCU
diff --git a/drivers/nvdimm/Kconfig b/drivers/nvdimm/Kconfig
index b7d1eb38b27d4..347fe7afa5830 100644
--- a/drivers/nvdimm/Kconfig
+++ b/drivers/nvdimm/Kconfig
@@ -22,7 +22,7 @@ if LIBNVDIMM
 config BLK_DEV_PMEM
 	tristate "PMEM: Persistent memory block device support"
 	default LIBNVDIMM
-	select DAX_DRIVER
+	select DAX
 	select ND_BTT if BTT
 	select ND_PFN if NVDIMM_PFN
 	help
diff --git a/drivers/s390/block/Kconfig b/drivers/s390/block/Kconfig
index d0416dbd0cd81..e3710a762abae 100644
--- a/drivers/s390/block/Kconfig
+++ b/drivers/s390/block/Kconfig
@@ -5,7 +5,7 @@ comment "S/390 block device drivers"
 config DCSSBLK
 	def_tristate m
 	select FS_DAX_LIMITED
-	select DAX_DRIVER
+	select DAX
 	prompt "DCSSBLK support"
 	depends on S390 && BLOCK
 	help
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 40ce9a1c12e5d..038ed0b9aaa5d 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -45,7 +45,7 @@ config FUSE_DAX
 	select INTERVAL_TREE
 	depends on VIRTIO_FS
 	depends on FS_DAX
-	depends on DAX_DRIVER
+	depends on DAX
 	help
 	  This allows bypassing guest page cache and allows mapping host page
 	  cache directly in guest address space.
-- 
2.30.2

[PATCH 04/29] dax: simplify the dax_device <-> gendisk association

[Christoph Hellwig]

Replace the dax_host_hash with an xarray indexed by the pointer value
of the gendisk, and require explicitly calls from the block drivers that
want to associate their gendisk with a dax_device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/dax/bus.c            |   6 +-
 drivers/dax/super.c          | 109 +++++++++--------------------------
 drivers/md/dm.c              |   6 +-
 drivers/nvdimm/pmem.c        |  10 +++-
 drivers/s390/block/dcssblk.c |  11 +++-
 fs/fuse/virtio_fs.c          |   2 +-
 include/linux/dax.h          |  19 ++++--
 7 files changed, 66 insertions(+), 97 deletions(-)

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 6cc4da4c713d9..bd7af2f7c5b0a 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1323,10 +1323,10 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 	}
 
 	/*
-	 * No 'host' or dax_operations since there is no access to this
-	 * device outside of mmap of the resulting character device.
+	 * No dax_operations since there is no access to this device outside of
+	 * mmap of the resulting character device.
 	 */
-	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
+	dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC);
 	if (IS_ERR(dax_dev)) {
 		rc = PTR_ERR(dax_dev);
 		goto err_alloc_dax;
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index e20d0cef10a18..bf77c3da5d56d 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -7,10 +7,8 @@
 #include <linux/mount.h>
 #include <linux/pseudo_fs.h>
 #include <linux/magic.h>
-#include <linux/genhd.h>
 #include <linux/pfn_t.h>
 #include <linux/cdev.h>
-#include <linux/hash.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/dax.h>
@@ -21,15 +19,12 @@
  * struct dax_device - anchor object for dax services
  * @inode: core vfs
  * @cdev: optional character interface for "device dax"
- * @host: optional name for lookups where the device path is not available
  * @private: dax driver private data
  * @flags: state and boolean properties
  */
 struct dax_device {
-	struct hlist_node list;
 	struct inode inode;
 	struct cdev cdev;
-	const char *host;
 	void *private;
 	unsigned long flags;
 	const struct dax_operations *ops;
@@ -42,10 +37,6 @@ static DEFINE_IDA(dax_minor_ida);
 static struct kmem_cache *dax_cache __read_mostly;
 static struct super_block *dax_superblock __read_mostly;
 
-#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head))
-static struct hlist_head dax_host_list[DAX_HASH_SIZE];
-static DEFINE_SPINLOCK(dax_host_lock);
-
 int dax_read_lock(void)
 {
 	return srcu_read_lock(&dax_srcu);
@@ -58,13 +49,22 @@ void dax_read_unlock(int id)
 }
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
-static int dax_host_hash(const char *host)
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
+#include <linux/blkdev.h>
+
+static DEFINE_XARRAY(dax_hosts);
+
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
-	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
+	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
 }
+EXPORT_SYMBOL_GPL(dax_add_host);
 
-#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
-#include <linux/blkdev.h>
+void dax_remove_host(struct gendisk *disk)
+{
+	xa_erase(&dax_hosts, (unsigned long)disk);
+}
+EXPORT_SYMBOL_GPL(dax_remove_host);
 
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 		pgoff_t *pgoff)
@@ -81,41 +81,24 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 EXPORT_SYMBOL(bdev_dax_pgoff);
 
 /**
- * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
- * @host: alternate name for the device registered by a dax driver
+ * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
+ * @bdev: block device to find a dax_device for
  */
-static struct dax_device *dax_get_by_host(const char *host)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 {
-	struct dax_device *dax_dev, *found = NULL;
-	int hash, id;
+	struct dax_device *dax_dev;
+	int id;
 
-	if (!host)
+	if (!blk_queue_dax(bdev->bd_disk->queue))
 		return NULL;
 
-	hash = dax_host_hash(host);
-
 	id = dax_read_lock();
-	spin_lock(&dax_host_lock);
-	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
-		if (!dax_alive(dax_dev)
-				|| strcmp(host, dax_dev->host) != 0)
-			continue;
-
-		if (igrab(&dax_dev->inode))
-			found = dax_dev;
-		break;
-	}
-	spin_unlock(&dax_host_lock);
+	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
+	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
+		dax_dev = NULL;
 	dax_read_unlock(id);
 
-	return found;
-}
-
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
-{
-	if (!blk_queue_dax(bdev->bd_disk->queue))
-		return NULL;
-	return dax_get_by_host(bdev->bd_disk->disk_name);
+	return dax_dev;
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 
@@ -361,12 +344,7 @@ void kill_dax(struct dax_device *dax_dev)
 		return;
 
 	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
-
 	synchronize_srcu(&dax_srcu);
-
-	spin_lock(&dax_host_lock);
-	hlist_del_init(&dax_dev->list);
-	spin_unlock(&dax_host_lock);
 }
 EXPORT_SYMBOL_GPL(kill_dax);
 
@@ -398,8 +376,6 @@ static struct dax_device *to_dax_dev(struct inode *inode)
 static void dax_free_inode(struct inode *inode)
 {
 	struct dax_device *dax_dev = to_dax_dev(inode);
-	kfree(dax_dev->host);
-	dax_dev->host = NULL;
 	if (inode->i_rdev)
 		ida_simple_remove(&dax_minor_ida, iminor(inode));
 	kmem_cache_free(dax_cache, dax_dev);
@@ -474,54 +450,25 @@ static struct dax_device *dax_dev_get(dev_t devt)
 	return dax_dev;
 }
 
-static void dax_add_host(struct dax_device *dax_dev, const char *host)
-{
-	int hash;
-
-	/*
-	 * Unconditionally init dax_dev since it's coming from a
-	 * non-zeroed slab cache
-	 */
-	INIT_HLIST_NODE(&dax_dev->list);
-	dax_dev->host = host;
-	if (!host)
-		return;
-
-	hash = dax_host_hash(host);
-	spin_lock(&dax_host_lock);
-	hlist_add_head(&dax_dev->list, &dax_host_list[hash]);
-	spin_unlock(&dax_host_lock);
-}
-
-struct dax_device *alloc_dax(void *private, const char *__host,
-		const struct dax_operations *ops, unsigned long flags)
+struct dax_device *alloc_dax(void *private, const struct dax_operations *ops,
+		unsigned long flags)
 {
 	struct dax_device *dax_dev;
-	const char *host;
 	dev_t devt;
 	int minor;
 
-	if (ops && !ops->zero_page_range) {
-		pr_debug("%s: error: device does not provide dax"
-			 " operation zero_page_range()\n",
-			 __host ? __host : "Unknown");
+	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
 		return ERR_PTR(-EINVAL);
-	}
-
-	host = kstrdup(__host, GFP_KERNEL);
-	if (__host && !host)
-		return ERR_PTR(-ENOMEM);
 
 	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
 	if (minor < 0)
-		goto err_minor;
+		return ERR_PTR(-ENOMEM);
 
 	devt = MKDEV(MAJOR(dax_devt), minor);
 	dax_dev = dax_dev_get(devt);
 	if (!dax_dev)
 		goto err_dev;
 
-	dax_add_host(dax_dev, host);
 	dax_dev->ops = ops;
 	dax_dev->private = private;
 	if (flags & DAXDEV_F_SYNC)
@@ -531,8 +478,6 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 
  err_dev:
 	ida_simple_remove(&dax_minor_ida, minor);
- err_minor:
-	kfree(host);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(alloc_dax);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b93fcc91176e5..a8c650276b321 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1683,6 +1683,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	bioset_exit(&md->io_bs);
 
 	if (md->dax_dev) {
+		dax_remove_host(md->disk);
 		kill_dax(md->dax_dev);
 		put_dax(md->dax_dev);
 		md->dax_dev = NULL;
@@ -1784,12 +1785,13 @@ static struct mapped_device *alloc_dev(int minor)
 	sprintf(md->disk->disk_name, "dm-%d", minor);
 
 	if (IS_ENABLED(CONFIG_FS_DAX)) {
-		md->dax_dev = alloc_dax(md, md->disk->disk_name,
-					&dm_dax_ops, 0);
+		md->dax_dev = alloc_dax(md, &dm_dax_ops, 0);
 		if (IS_ERR(md->dax_dev)) {
 			md->dax_dev = NULL;
 			goto bad;
 		}
+		if (dax_add_host(md->dax_dev, md->disk))
+			goto bad;
 	}
 
 	format_dev_t(md->name, MKDEV(_major, minor));
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index fe7ece1534e1e..1018f0d44acb8 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -379,6 +379,7 @@ static void pmem_release_disk(void *__pmem)
 {
 	struct pmem_device *pmem = __pmem;
 
+	dax_remove_host(pmem->disk);
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);
 	del_gendisk(pmem->disk);
@@ -497,17 +498,20 @@ static int pmem_attach_disk(struct device *dev,
 
 	if (is_nvdimm_sync(nd_region))
 		flags = DAXDEV_F_SYNC;
-	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
+	dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags);
 	if (IS_ERR(dax_dev)) {
 		rc = PTR_ERR(dax_dev);
 		goto out;
 	}
+	rc = dax_add_host(dax_dev, disk);
+	if (rc)
+		goto out_cleanup_dax;
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
 
 	rc = device_add_disk(dev, disk, pmem_attribute_groups);
 	if (rc)
-		goto out_cleanup_dax;
+		goto out_remove_host;
 	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
 		return -ENOMEM;
 
@@ -519,6 +523,8 @@ static int pmem_attach_disk(struct device *dev,
 		dev_warn(dev, "'badblocks' notification disabled\n");
 	return 0;
 
+out_remove_host:
+	dax_remove_host(pmem->disk);
 out_cleanup_dax:
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 27ab888b44d0a..657e492f2bc26 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -687,18 +687,21 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	if (rc)
 		goto put_dev;
 
-	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
-			&dcssblk_dax_ops, DAXDEV_F_SYNC);
+	dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops,
+			DAXDEV_F_SYNC);
 	if (IS_ERR(dev_info->dax_dev)) {
 		rc = PTR_ERR(dev_info->dax_dev);
 		dev_info->dax_dev = NULL;
 		goto put_dev;
 	}
+	rc = dax_add_host(dev_info->dax_dev, dev_info->gd);
+	if (rc)
+		goto out_dax;
 
 	get_device(&dev_info->dev);
 	rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL);
 	if (rc)
-		goto out_dax;
+		goto out_dax_host;
 
 	switch (dev_info->segment_type) {
 		case SEG_TYPE_SR:
@@ -714,6 +717,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	rc = count;
 	goto out;
 
+out_dax_host:
+	dax_remove_host(dev_info->gd);
 out_dax:
 	put_device(&dev_info->dev);
 	kill_dax(dev_info->dax_dev);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 4cfa4bc1f5794..242cc1c0d7ed7 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
 	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
 		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
 
-	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
+	fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0);
 	if (IS_ERR(fs->dax_dev))
 		return PTR_ERR(fs->dax_dev);
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8623caa673889..e2e9a67004cbd 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -11,9 +11,11 @@
 
 typedef unsigned long dax_entry_t;
 
+struct dax_device;
+struct gendisk;
 struct iomap_ops;
 struct iomap;
-struct dax_device;
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -39,8 +41,8 @@ struct dax_operations {
 };
 
 #if IS_ENABLED(CONFIG_DAX)
-struct dax_device *alloc_dax(void *private, const char *host,
-		const struct dax_operations *ops, unsigned long flags);
+struct dax_device *alloc_dax(void *private, const struct dax_operations *ops,
+		unsigned long flags);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
@@ -68,7 +70,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	return dax_synchronous(dax_dev);
 }
 #else
-static inline struct dax_device *alloc_dax(void *private, const char *host,
+static inline struct dax_device *alloc_dax(void *private,
 		const struct dax_operations *ops, unsigned long flags)
 {
 	/*
@@ -107,6 +109,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 struct writeback_control;
 int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
+void dax_remove_host(struct gendisk *disk);
 bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors);
@@ -128,6 +132,13 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
+static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
+{
+	return 0;
+}
+static inline void dax_remove_host(struct gendisk *disk)
+{
+}
 #define generic_fsdax_supported		NULL
 
 static inline bool dax_supported(struct dax_device *dax_dev,
-- 
2.30.2

[PATCH 05/29] dax: remove the pgmap sanity checks in generic_fsdax_supported

[Christoph Hellwig]

Drivers that register a dax_dev should make sure it works, no need
to double check from the file system.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c | 49 +--------------------------------------------
 1 file changed, 1 insertion(+), 48 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index bf77c3da5d56d..c8500b7e2d8a2 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -106,13 +106,9 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors)
 {
-	bool dax_enabled = false;
 	pgoff_t pgoff, pgoff_end;
-	void *kaddr, *end_kaddr;
-	pfn_t pfn, end_pfn;
 	sector_t last_page;
-	long len, len2;
-	int err, id;
+	int err;
 
 	if (blocksize != PAGE_SIZE) {
 		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
@@ -137,49 +133,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
 		return false;
 	}
 
-	id = dax_read_lock();
-	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
-	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
-
-	if (len < 1 || len2 < 1) {
-		pr_info("%pg: error: dax access failed (%ld)\n",
-				bdev, len < 1 ? len : len2);
-		dax_read_unlock(id);
-		return false;
-	}
-
-	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
-		/*
-		 * An arch that has enabled the pmem api should also
-		 * have its drivers support pfn_t_devmap()
-		 *
-		 * This is a developer warning and should not trigger in
-		 * production. dax_flush() will crash since it depends
-		 * on being able to do (page_address(pfn_to_page())).
-		 */
-		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
-		dax_enabled = true;
-	} else if (pfn_t_devmap(pfn) && pfn_t_devmap(end_pfn)) {
-		struct dev_pagemap *pgmap, *end_pgmap;
-
-		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
-		end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL);
-		if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX
-				&& pfn_t_to_page(pfn)->pgmap == pgmap
-				&& pfn_t_to_page(end_pfn)->pgmap == pgmap
-				&& pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr))
-				&& pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr)))
-			dax_enabled = true;
-		put_dev_pagemap(pgmap);
-		put_dev_pagemap(end_pgmap);
-
-	}
-	dax_read_unlock(id);
-
-	if (!dax_enabled) {
-		pr_info("%pg: error: dax support not enabled\n", bdev);
-		return false;
-	}
 	return true;
 }
 EXPORT_SYMBOL_GPL(generic_fsdax_supported);
-- 
2.30.2

[PATCH 06/29] dax: move the partition alignment check into fs_dax_get_by_bdev

[Christoph Hellwig]

fs_dax_get_by_bdev is the primary interface to find a dax device for a
block device, so move the partition alignment check there instead of
wiring it up through ->dax_supported.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/super.c | 23 ++++++-----------------
 1 file changed, 6 insertions(+), 17 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index c8500b7e2d8a2..f2cef47bdeafd 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -92,6 +92,12 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 	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) {
+		pr_info("%pg: error: unaligned partition for dax\n", bdev);
+		return NULL;
+	}
+
 	id = dax_read_lock();
 	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
 	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
@@ -106,10 +112,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
 		struct block_device *bdev, int blocksize, sector_t start,
 		sector_t sectors)
 {
-	pgoff_t pgoff, pgoff_end;
-	sector_t last_page;
-	int err;
-
 	if (blocksize != PAGE_SIZE) {
 		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
 		return false;
@@ -120,19 +122,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
 		return false;
 	}
 
-	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
-	if (err) {
-		pr_info("%pg: error: unaligned partition for dax\n", bdev);
-		return false;
-	}
-
-	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
-	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
-	if (err) {
-		pr_info("%pg: error: unaligned partition for dax\n", bdev);
-		return false;
-	}
-
 	return true;
 }
 EXPORT_SYMBOL_GPL(generic_fsdax_supported);
-- 
2.30.2

[PATCH 07/29] xfs: factor out a xfs_setup_dax_always helper

[Christoph Hellwig]

Factor out another DAX setup helper to simplify future changes.  Also
move the experimental warning after the checks to not clutter the log
too much if the setup failed.

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>
---
 fs/xfs/xfs_super.c | 47 +++++++++++++++++++++++++++-------------------
 1 file changed, 28 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e21459f9923a8..875fd3151d6c9 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -340,6 +340,32 @@ xfs_buftarg_is_dax(
 			bdev_nr_sectors(bt->bt_bdev));
 }
 
+static int
+xfs_setup_dax_always(
+	struct xfs_mount	*mp)
+{
+	struct super_block	*sb = mp->m_super;
+
+	if (!xfs_buftarg_is_dax(sb, mp->m_ddev_targp) &&
+	   (!mp->m_rtdev_targp || !xfs_buftarg_is_dax(sb, mp->m_rtdev_targp))) {
+		xfs_alert(mp,
+			"DAX unsupported by block device. Turning off DAX.");
+		goto disable_dax;
+	}
+
+	if (xfs_has_reflink(mp)) {
+		xfs_alert(mp, "DAX and reflink cannot be used together!");
+		return -EINVAL;
+	}
+
+	xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+	return 0;
+
+disable_dax:
+	xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
+	return 0;
+}
+
 STATIC int
 xfs_blkdev_get(
 	xfs_mount_t		*mp,
@@ -1593,26 +1619,9 @@ xfs_fs_fill_super(
 		sb->s_flags |= SB_I_VERSION;
 
 	if (xfs_has_dax_always(mp)) {
-		bool rtdev_is_dax = false, datadev_is_dax;
-
-		xfs_warn(mp,
-		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-
-		datadev_is_dax = xfs_buftarg_is_dax(sb, mp->m_ddev_targp);
-		if (mp->m_rtdev_targp)
-			rtdev_is_dax = xfs_buftarg_is_dax(sb,
-						mp->m_rtdev_targp);
-		if (!rtdev_is_dax && !datadev_is_dax) {
-			xfs_alert(mp,
-			"DAX unsupported by block device. Turning off DAX.");
-			xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
-		}
-		if (xfs_has_reflink(mp)) {
-			xfs_alert(mp,
-		"DAX and reflink cannot be used together!");
-			error = -EINVAL;
+		error = xfs_setup_dax_always(mp);
+		if (error)
 			goto out_filestream_unmount;
-		}
 	}
 
 	if (xfs_has_discard(mp)) {
-- 
2.30.2

[PATCH 08/29] dax: remove dax_capable

[Christoph Hellwig]

Just open code the block size and dax_dev == NULL checks in the callers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> [erofs]
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 drivers/dax/super.c          | 36 ------------------------------------
 drivers/md/dm-table.c        | 22 +++++++++++-----------
 drivers/md/dm.c              | 21 ---------------------
 drivers/md/dm.h              |  4 ----
 drivers/nvdimm/pmem.c        |  1 -
 drivers/s390/block/dcssblk.c |  1 -
 fs/erofs/super.c             | 11 +++++++----
 fs/ext2/super.c              |  6 ++++--
 fs/ext4/super.c              |  9 ++++++---
 fs/xfs/xfs_super.c           | 21 ++++++++-------------
 include/linux/dax.h          | 14 --------------
 11 files changed, 36 insertions(+), 110 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index f2cef47bdeafd..90b5733f5a709 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -107,42 +107,6 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 	return dax_dev;
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-
-bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
-{
-	if (blocksize != PAGE_SIZE) {
-		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
-		return false;
-	}
-
-	if (!dax_dev) {
-		pr_debug("%pg: error: dax unsupported by block device\n", bdev);
-		return false;
-	}
-
-	return true;
-}
-EXPORT_SYMBOL_GPL(generic_fsdax_supported);
-
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len)
-{
-	bool ret = false;
-	int id;
-
-	if (!dax_dev)
-		return false;
-
-	id = dax_read_lock();
-	if (dax_alive(dax_dev) && dax_dev->ops->dax_supported)
-		ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize,
-						  start, len);
-	dax_read_unlock(id);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dax_supported);
 #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
 enum dax_device_flags {
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index aa173f5bdc3dd..e43096cfe9e22 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -806,12 +806,14 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
 EXPORT_SYMBOL_GPL(dm_table_set_type);
 
 /* validate the dax capability of the target device span */
-int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
+static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
 			sector_t start, sector_t len, void *data)
 {
-	int blocksize = *(int *) data;
+	if (dev->dax_dev)
+		return false;
 
-	return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+	DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev);
+	return true;
 }
 
 /* Check devices support synchronous DAX */
@@ -821,8 +823,8 @@ static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_de
 	return !dev->dax_dev || !dax_synchronous(dev->dax_dev);
 }
 
-bool dm_table_supports_dax(struct dm_table *t,
-			   iterate_devices_callout_fn iterate_fn, int *blocksize)
+static bool dm_table_supports_dax(struct dm_table *t,
+			   iterate_devices_callout_fn iterate_fn)
 {
 	struct dm_target *ti;
 	unsigned i;
@@ -835,7 +837,7 @@ bool dm_table_supports_dax(struct dm_table *t,
 			return false;
 
 		if (!ti->type->iterate_devices ||
-		    ti->type->iterate_devices(ti, iterate_fn, blocksize))
+		    ti->type->iterate_devices(ti, iterate_fn, NULL))
 			return false;
 	}
 
@@ -862,7 +864,6 @@ static int dm_table_determine_type(struct dm_table *t)
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
-	int page_size = PAGE_SIZE;
 
 	if (t->type != DM_TYPE_NONE) {
 		/* target already set the table's type */
@@ -906,7 +907,7 @@ static int dm_table_determine_type(struct dm_table *t)
 verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
-		if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) ||
+		if (dm_table_supports_dax(t, device_not_dax_capable) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
 		}
@@ -1976,7 +1977,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
 	bool wc = false, fua = false;
-	int page_size = PAGE_SIZE;
 	int r;
 
 	/*
@@ -2010,9 +2010,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) {
+	if (dm_table_supports_dax(t, device_not_dax_capable)) {
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
-		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL))
+		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
 			set_dax_synchronous(t->md->dax_dev);
 	}
 	else
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a8c650276b321..4eba27e75c230 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1027,26 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
-static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	struct dm_table *map;
-	bool ret = false;
-	int srcu_idx;
-
-	map = dm_get_live_table(md, &srcu_idx);
-	if (!map)
-		goto out;
-
-	ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize);
-
-out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
 static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 				    void *addr, size_t bytes, struct iov_iter *i)
 {
@@ -3044,7 +3024,6 @@ static const struct block_device_operations dm_rq_blk_dops = {
 
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
-	.dax_supported = dm_dax_supported,
 	.copy_from_iter = dm_dax_copy_from_iter,
 	.copy_to_iter = dm_dax_copy_to_iter,
 	.zero_page_range = dm_dax_zero_page_range,
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 742d9c80efe19..9013dc1a7b002 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -73,10 +73,6 @@ bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
-bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn,
-			   int *blocksize);
-int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
-			   sector_t start, sector_t len, void *data);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 1018f0d44acb8..4190c8c46ca88 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -321,7 +321,6 @@ static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
-	.dax_supported = generic_fsdax_supported,
 	.copy_from_iter = pmem_copy_from_iter,
 	.copy_to_iter = pmem_copy_to_iter,
 	.zero_page_range = pmem_dax_zero_page_range,
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 657e492f2bc26..e65e83764d1ce 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -72,7 +72,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
-	.dax_supported = generic_fsdax_supported,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
 	.copy_to_iter = dcssblk_dax_copy_to_iter,
 	.zero_page_range = dcssblk_dax_zero_page_range,
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 6a969b1e0ee6b..0aed886473c8d 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -652,10 +652,13 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	if (test_opt(&sbi->opt, DAX_ALWAYS) &&
-	    !dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) {
-		errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
-		clear_opt(&sbi->opt, DAX_ALWAYS);
+	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
+		BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE);
+
+		if (!sbi->dax_dev) {
+			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+		}
 	}
 	sb->s_flags |= SB_RDONLY | SB_NOATIME;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index d8d580b609baa..a964066a80aa7 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -946,11 +946,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (test_opt(sb, DAX)) {
-		if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
-				bdev_nr_sectors(sb->s_bdev))) {
+		if (!dax_dev) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			clear_opt(sbi->s_mount_opt, DAX);
+		} else if (blocksize != PAGE_SIZE) {
+			ext2_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+			clear_opt(sbi->s_mount_opt, DAX);
 		}
 	}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4e33b5eca694d..fd3d68f10ee55 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4299,9 +4299,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
-			bdev_nr_sectors(sb->s_bdev)))
-		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+	if (dax_dev) {
+		if (blocksize == PAGE_SIZE)
+			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+		else
+			ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+	}
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 875fd3151d6c9..c4297206f4834 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -331,28 +331,23 @@ xfs_set_inode_alloc(
 	return xfs_is_inode32(mp) ? maxagi : agcount;
 }
 
-static bool
-xfs_buftarg_is_dax(
-	struct super_block	*sb,
-	struct xfs_buftarg	*bt)
-{
-	return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0,
-			bdev_nr_sectors(bt->bt_bdev));
-}
-
 static int
 xfs_setup_dax_always(
 	struct xfs_mount	*mp)
 {
-	struct super_block	*sb = mp->m_super;
-
-	if (!xfs_buftarg_is_dax(sb, mp->m_ddev_targp) &&
-	   (!mp->m_rtdev_targp || !xfs_buftarg_is_dax(sb, mp->m_rtdev_targp))) {
+	if (!mp->m_ddev_targp->bt_daxdev &&
+	    (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) {
 		xfs_alert(mp,
 			"DAX unsupported by block device. Turning off DAX.");
 		goto disable_dax;
 	}
 
+	if (mp->m_super->s_blocksize != PAGE_SIZE) {
+		xfs_alert(mp,
+			"DAX not supported for blocksize. Turning off DAX.");
+		goto disable_dax;
+	}
+
 	if (xfs_has_reflink(mp)) {
 		xfs_alert(mp, "DAX and reflink cannot be used together!");
 		return -EINVAL;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index e2e9a67004cbd..439c3c70e347b 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -111,12 +111,6 @@ int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
 int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
 void dax_remove_host(struct gendisk *disk);
-bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors);
-
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
 
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
@@ -139,14 +133,6 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 static inline void dax_remove_host(struct gendisk *disk)
 {
 }
-#define generic_fsdax_supported		NULL
-
-static inline bool dax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t len)
-{
-	return false;
-}
 
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
-- 
2.30.2

[PATCH 09/29] dm-linear: add a linear_dax_pgoff helper

[Christoph Hellwig]

Add a helper to perform the entire remapping for DAX accesses.  This
helper open codes bdev_dax_pgoff given that the alignment checks have
already been done by the submitting file system and don't need to be
repeated.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/md/dm-linear.c | 49 +++++++++++++-----------------------------
 1 file changed, 15 insertions(+), 34 deletions(-)

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 0a260c35aeeed..90de42f6743ac 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -163,63 +163,44 @@ static int linear_iterate_devices(struct dm_target *ti,
 }
 
 #if IS_ENABLED(CONFIG_FS_DAX)
+static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
+{
+	struct linear_c *lc = ti->private;
+	sector_t sector = linear_map_sector(ti, *pgoff << PAGE_SECTORS_SHIFT);
+
+	*pgoff = (get_start_sect(lc->dev->bdev) + sector) >> PAGE_SECTORS_SHIFT;
+	return lc->dev->dax_dev;
+}
+
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn)
 {
-	long ret;
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-
-	dev_sector = linear_map_sector(ti, sector);
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
-	if (ret)
-		return ret;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
+
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
 static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
-	dev_sector = linear_map_sector(ti, sector);
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
-	dev_sector = linear_map_sector(ti, sector);
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 				      size_t nr_pages)
 {
-	int ret;
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-
-	dev_sector = linear_map_sector(ti, sector);
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
-	if (ret)
-		return ret;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
+
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
-- 
2.30.2

[PATCH 10/29] dm-log-writes: add a log_writes_dax_pgoff helper

[Christoph Hellwig]

Add a helper to perform the entire remapping for DAX accesses.  This
helper open codes bdev_dax_pgoff given that the alignment checks have
already been done by the submitting file system and don't need to be
repeated.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/md/dm-log-writes.c | 42 +++++++++++++++-----------------------
 1 file changed, 17 insertions(+), 25 deletions(-)

diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 3155875d4e5b0..cdb22e7a1d0da 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -947,17 +947,21 @@ static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes,
 	return 0;
 }
 
+static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
+		pgoff_t *pgoff)
+{
+	struct log_writes_c *lc = ti->private;
+
+	*pgoff += (get_start_sect(lc->dev->bdev) >> PAGE_SECTORS_SHIFT);
+	return lc->dev->dax_dev;
+}
+
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 					 long nr_pages, void **kaddr, pfn_t *pfn)
 {
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
-	int ret;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages * PAGE_SIZE, &pgoff);
-	if (ret)
-		return ret;
-	return dax_direct_access(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
 static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
@@ -966,11 +970,9 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
 {
 	struct log_writes_c *lc = ti->private;
 	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 	int err;
 
-	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-
 	/* Don't bother doing anything if logging has been disabled */
 	if (!lc->logging_enabled)
 		goto dax_copy;
@@ -981,34 +983,24 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
 		return 0;
 	}
 dax_copy:
-	return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
+	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
 					  pgoff_t pgoff, void *addr, size_t bytes,
 					  struct iov_iter *i)
 {
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
+	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 					  size_t nr_pages)
 {
-	int ret;
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
-	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT,
-			     &pgoff);
-	if (ret)
-		return ret;
-	return dax_zero_page_range(lc->dev->dax_dev, pgoff,
-				   nr_pages << PAGE_SHIFT);
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT);
 }
 
 #else
-- 
2.30.2

[PATCH 11/29] dm-stripe: add a stripe_dax_pgoff helper

[Christoph Hellwig]

Add a helper to perform the entire remapping for DAX accesses.  This
helper open codes bdev_dax_pgoff given that the alignment checks have
already been done by the submitting file system and don't need to be
repeated.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/md/dm-stripe.c | 63 ++++++++++--------------------------------
 1 file changed, 15 insertions(+), 48 deletions(-)

diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index f084607220293..50dba3f39274c 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -301,83 +301,50 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 }
 
 #if IS_ENABLED(CONFIG_FS_DAX)
-static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 {
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
 	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
 	struct block_device *bdev;
+	sector_t dev_sector;
 	uint32_t stripe;
-	long ret;
 
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	stripe_map_sector(sc, *pgoff * PAGE_SECTORS, &stripe, &dev_sector);
 	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
 	bdev = sc->stripe[stripe].dev->bdev;
 
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
-	if (ret)
-		return ret;
+	*pgoff = (get_start_sect(bdev) + dev_sector) >> PAGE_SECTORS_SHIFT;
+	return sc->stripe[stripe].dev->dax_dev;
+}
+
+static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
+		long nr_pages, void **kaddr, pfn_t *pfn)
+{
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
+
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
 static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
-
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i)
 {
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
-
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
 static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 				      size_t nr_pages)
 {
-	int ret;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
-
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
-	if (ret)
-		return ret;
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
-- 
2.30.2

[PATCH 12/29] fsdax: remove a pointless __force cast in copy_cow_page_dax

[Christoph Hellwig]

Despite its name copy_user_page expected kernel addresses, which is what
we already have.

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>
---
 fs/dax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/dax.c b/fs/dax.c
index 4e3e5a283a916..73bd1439d8089 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -728,7 +728,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
 		return rc;
 	}
 	vto = kmap_atomic(to);
-	copy_user_page(vto, (void __force *)kaddr, vaddr, to);
+	copy_user_page(vto, kaddr, vaddr, to);
 	kunmap_atomic(vto);
 	dax_read_unlock(id);
 	return 0;
-- 
2.30.2

[PATCH 13/29] fsdax: use a saner calling convention for copy_cow_page_dax

[Christoph Hellwig]

Just pass the vm_fault and iomap_iter structures, and figure out the rest
locally.  Note that this requires moving dax_iomap_sector up in the file.

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>
---
 fs/dax.c | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 73bd1439d8089..e51b4129d1b65 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -709,26 +709,31 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 	return __dax_invalidate_entry(mapping, index, false);
 }
 
-static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev,
-			     sector_t sector, struct page *to, unsigned long vaddr)
+static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos)
 {
+	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
+}
+
+static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
+{
+	sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos);
 	void *vto, *kaddr;
 	pgoff_t pgoff;
 	long rc;
 	int id;
 
-	rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
+	rc = bdev_dax_pgoff(iter->iomap.bdev, sector, PAGE_SIZE, &pgoff);
 	if (rc)
 		return rc;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
 	}
-	vto = kmap_atomic(to);
-	copy_user_page(vto, kaddr, vaddr, to);
+	vto = kmap_atomic(vmf->cow_page);
+	copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
 	kunmap_atomic(vto);
 	dax_read_unlock(id);
 	return 0;
@@ -1005,11 +1010,6 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
-static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos)
-{
-	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
-}
-
 static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 			 pfn_t *pfnp)
 {
@@ -1332,19 +1332,16 @@ static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
 static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
 		const struct iomap_iter *iter)
 {
-	sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos);
-	unsigned long vaddr = vmf->address;
 	vm_fault_t ret;
 	int error = 0;
 
 	switch (iter->iomap.type) {
 	case IOMAP_HOLE:
 	case IOMAP_UNWRITTEN:
-		clear_user_highpage(vmf->cow_page, vaddr);
+		clear_user_highpage(vmf->cow_page, vmf->address);
 		break;
 	case IOMAP_MAPPED:
-		error = copy_cow_page_dax(iter->iomap.bdev, iter->iomap.dax_dev,
-					  sector, vmf->cow_page, vaddr);
+		error = copy_cow_page_dax(vmf, iter);
 		break;
 	default:
 		WARN_ON_ONCE(1);
-- 
2.30.2

[PATCH 14/29] fsdax: simplify the pgoff calculation

[Christoph Hellwig]

Replace the two steps of dax_iomap_sector and bdev_dax_pgoff with a
single dax_iomap_pgoff helper that avoids lots of cumbersome sector
conversions.

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>
---
 drivers/dax/super.c | 14 --------------
 fs/dax.c            | 35 ++++++++++-------------------------
 include/linux/dax.h |  1 -
 3 files changed, 10 insertions(+), 40 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 90b5733f5a709..45d931aefd063 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -66,20 +66,6 @@ void dax_remove_host(struct gendisk *disk)
 }
 EXPORT_SYMBOL_GPL(dax_remove_host);
 
-int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
-		pgoff_t *pgoff)
-{
-	sector_t start_sect = bdev ? get_start_sect(bdev) : 0;
-	phys_addr_t phys_off = (start_sect + sector) * 512;
-
-	if (pgoff)
-		*pgoff = PHYS_PFN(phys_off);
-	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
-		return -EINVAL;
-	return 0;
-}
-EXPORT_SYMBOL(bdev_dax_pgoff);
-
 /**
  * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
  * @bdev: block device to find a dax_device for
diff --git a/fs/dax.c b/fs/dax.c
index e51b4129d1b65..5364549d67a48 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -709,23 +709,22 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 	return __dax_invalidate_entry(mapping, index, false);
 }
 
-static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos)
+static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
 {
-	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
+	phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset;
+
+	if (iomap->bdev)
+		paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT);
+	return PHYS_PFN(paddr);
 }
 
 static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
 {
-	sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos);
+	pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);
 	void *vto, *kaddr;
-	pgoff_t pgoff;
 	long rc;
 	int id;
 
-	rc = bdev_dax_pgoff(iter->iomap.bdev, sector, PAGE_SIZE, &pgoff);
-	if (rc)
-		return rc;
-
 	id = dax_read_lock();
 	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
@@ -1013,14 +1012,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 			 pfn_t *pfnp)
 {
-	const sector_t sector = dax_iomap_sector(iomap, pos);
-	pgoff_t pgoff;
+	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	int id, rc;
 	long length;
 
-	rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
-	if (rc)
-		return rc;
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
 				   NULL, pfnp);
@@ -1129,7 +1124,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
-	pgoff_t pgoff;
+	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	long rc, id;
 	void *kaddr;
 	bool page_aligned = false;
@@ -1140,10 +1135,6 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 	    (size == PAGE_SIZE))
 		page_aligned = true;
 
-	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
-	if (rc)
-		return rc;
-
 	id = dax_read_lock();
 
 	if (page_aligned)
@@ -1169,7 +1160,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	const struct iomap *iomap = &iomi->iomap;
 	loff_t length = iomap_length(iomi);
 	loff_t pos = iomi->pos;
-	struct block_device *bdev = iomap->bdev;
 	struct dax_device *dax_dev = iomap->dax_dev;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
@@ -1203,9 +1193,8 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		const size_t size = ALIGN(length + offset, PAGE_SIZE);
-		const sector_t sector = dax_iomap_sector(iomap, pos);
+		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 		ssize_t map_len;
-		pgoff_t pgoff;
 		void *kaddr;
 
 		if (fatal_signal_pending(current)) {
@@ -1213,10 +1202,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 			break;
 		}
 
-		ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
-		if (ret)
-			break;
-
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
 				&kaddr, NULL);
 		if (map_len < 0) {
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 439c3c70e347b..324363b798ecd 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -107,7 +107,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 #endif
 
 struct writeback_control;
-int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #if IS_ENABLED(CONFIG_FS_DAX)
 int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
 void dax_remove_host(struct gendisk *disk);
-- 
2.30.2

[PATCH 15/29] xfs: add xfs_zero_range and xfs_truncate_page helpers

[Christoph Hellwig]

From: Shiyang Ruan <ruansy.fnst@fujitsu.com>

Add helpers to prepare for using different DAX operations.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
[hch: split from a larger patch + slight cleanups]
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>
---
 fs/xfs/xfs_bmap_util.c |  7 +++----
 fs/xfs/xfs_file.c      |  3 +--
 fs/xfs/xfs_iomap.c     | 25 +++++++++++++++++++++++++
 fs/xfs/xfs_iomap.h     |  4 ++++
 fs/xfs/xfs_iops.c      |  7 +++----
 fs/xfs/xfs_reflink.c   |  3 +--
 6 files changed, 37 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 73a36b7be3bd1..797ea0c8b14e1 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1001,7 +1001,7 @@ xfs_free_file_space(
 
 	/*
 	 * Now that we've unmap all full blocks we'll have to zero out any
-	 * partial block at the beginning and/or end.  iomap_zero_range is smart
+	 * partial block at the beginning and/or end.  xfs_zero_range is smart
 	 * enough to skip any holes, including those we just created, but we
 	 * must take care not to zero beyond EOF and enlarge i_size.
 	 */
@@ -1009,15 +1009,14 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
-			&xfs_buffered_write_iomap_ops);
+	error = xfs_zero_range(ip, offset, len, NULL);
 	if (error)
 		return error;
 
 	/*
 	 * If we zeroed right up to EOF and EOF straddles a page boundary we
 	 * must make sure that the post-EOF area is also zeroed because the
-	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
+	 * page could be mmap'd and xfs_zero_range doesn't do that for us.
 	 * Writeback of the eof page will do this, albeit clumsily.
 	 */
 	if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) {
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 27594738b0d18..8d4c5ca261bd7 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -437,8 +437,7 @@ xfs_file_write_checks(
 		}
 
 		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
-		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
-				NULL, &xfs_buffered_write_iomap_ops);
+		error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL);
 		if (error)
 			return error;
 	} else
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 093758440ad53..d6d71ae9f2ae4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1311,3 +1311,28 @@ xfs_xattr_iomap_begin(
 const struct iomap_ops xfs_xattr_iomap_ops = {
 	.iomap_begin		= xfs_xattr_iomap_begin,
 };
+
+int
+xfs_zero_range(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	loff_t			len,
+	bool			*did_zero)
+{
+	struct inode		*inode = VFS_I(ip);
+
+	return iomap_zero_range(inode, pos, len, did_zero,
+				&xfs_buffered_write_iomap_ops);
+}
+
+int
+xfs_truncate_page(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	bool			*did_zero)
+{
+	struct inode		*inode = VFS_I(ip);
+
+	return iomap_truncate_page(inode, pos, did_zero,
+				   &xfs_buffered_write_iomap_ops);
+}
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 7d3703556d0e0..f1a281ab9328c 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -20,6 +20,10 @@ xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
 		struct xfs_bmbt_irec *, u16);
 
+int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len,
+		bool *did_zero);
+int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, bool *did_zero);
+
 static inline xfs_filblks_t
 xfs_aligned_fsb_count(
 	xfs_fileoff_t		offset_fsb,
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a607d6aca5c4d..ab5ef52b2a9ff 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,8 +911,8 @@ xfs_setattr_size(
 	 */
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
-		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
-				&did_zeroing, &xfs_buffered_write_iomap_ops);
+		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
+				&did_zeroing);
 	} else {
 		/*
 		 * iomap won't detect a dirty page over an unwritten block (or a
@@ -924,8 +924,7 @@ xfs_setattr_size(
 						     newsize);
 		if (error)
 			return error;
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_buffered_write_iomap_ops);
+		error = xfs_truncate_page(ip, newsize, &did_zeroing);
 	}
 
 	if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cb0edb1d68ef1..facce5c076d83 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1269,8 +1269,7 @@ xfs_reflink_zero_posteof(
 		return 0;
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
-	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
-			&xfs_buffered_write_iomap_ops);
+	return xfs_zero_range(ip, isize, pos - isize, NULL);
 }
 
 /*
-- 
2.30.2

[PATCH 16/29] fsdax: simplify the offset check in dax_iomap_zero

[Christoph Hellwig]

The file relative offset must have the same alignment as the storage
offset, so use that and get rid of the call to iomap_sector.

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>
---
 fs/dax.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 5364549d67a48..d7a923d152240 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1123,7 +1123,6 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 
 s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
-	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
 	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	long rc, id;
 	void *kaddr;
@@ -1131,8 +1130,7 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 	unsigned offset = offset_in_page(pos);
 	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
-	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
-	    (size == PAGE_SIZE))
+	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
 		page_aligned = true;
 
 	id = dax_read_lock();
-- 
2.30.2

[PATCH 17/29] fsdax: factor out a dax_memzero helper

[Christoph Hellwig]

Factor out a helper for the "manual" zeroing of a DAX range to clean
up dax_iomap_zero a lot.

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>
---
 fs/dax.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d7a923d152240..d5db1297a0bb6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1121,34 +1121,36 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 }
 #endif /* CONFIG_FS_DAX_PMD */
 
+static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
+		unsigned int offset, size_t size)
+{
+	void *kaddr;
+	long ret;
+
+	ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	if (ret > 0) {
+		memset(kaddr + offset, 0, size);
+		dax_flush(dax_dev, kaddr + offset, size);
+	}
+	return ret;
+}
+
 s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	long rc, id;
-	void *kaddr;
-	bool page_aligned = false;
 	unsigned offset = offset_in_page(pos);
 	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
-	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
-		page_aligned = true;
-
 	id = dax_read_lock();
-
-	if (page_aligned)
+	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
 		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
-		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
-	if (rc < 0) {
-		dax_read_unlock(id);
-		return rc;
-	}
-
-	if (!page_aligned) {
-		memset(kaddr + offset, 0, size);
-		dax_flush(iomap->dax_dev, kaddr + offset, size);
-	}
+		rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
 	dax_read_unlock(id);
+
+	if (rc < 0)
+		return rc;
 	return size;
 }
 
-- 
2.30.2

[PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code

[Christoph Hellwig]

Unshare the DAX and iomap buffered I/O page zeroing code.  This code
previously did a IS_DAX check deep inside the iomap code, which in
fact was the only DAX check in the code.  Instead move these checks
into the callers.  Most callers already have DAX special casing anyway
and XFS will need it for reflink support as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 fs/dax.c               | 77 ++++++++++++++++++++++++++++++++++--------
 fs/ext2/inode.c        |  7 ++--
 fs/ext4/inode.c        |  5 +--
 fs/iomap/buffered-io.c | 35 +++++++------------
 fs/xfs/xfs_iomap.c     |  7 +++-
 include/linux/dax.h    |  7 +++-
 6 files changed, 94 insertions(+), 44 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d5db1297a0bb6..43d58b4219fd0 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
-s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
+static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
-	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
-	long rc, id;
-	unsigned offset = offset_in_page(pos);
-	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
+	const struct iomap *iomap = &iter->iomap;
+	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	loff_t pos = iter->pos;
+	u64 length = iomap_length(iter);
+	s64 written = 0;
+
+	/* already zeroed?  we're done. */
+	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+		return length;
+
+	do {
+		unsigned offset = offset_in_page(pos);
+		unsigned size = min_t(u64, PAGE_SIZE - offset, length);
+		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
+		long rc;
+		int id;
 
-	id = dax_read_lock();
-	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
-	else
-		rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
-	dax_read_unlock(id);
+		id = dax_read_lock();
+		if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
+			rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
+		else
+			rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
+		dax_read_unlock(id);
 
-	if (rc < 0)
-		return rc;
-	return size;
+		if (rc < 0)
+			return rc;
+		pos += size;
+		length -= size;
+		written += size;
+		if (did_zero)
+			*did_zero = true;
+	} while (length > 0);
+
+	return written;
+}
+
+int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= inode,
+		.pos		= pos,
+		.len		= len,
+		.flags		= IOMAP_ZERO,
+	};
+	int ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = dax_zero_iter(&iter, did_zero);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dax_zero_range);
+
+int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!off)
+		return 0;
+	return dax_zero_range(inode, pos, blocksize - off, did_zero, ops);
 }
+EXPORT_SYMBOL_GPL(dax_truncate_page);
 
 static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		struct iov_iter *iter)
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 333fa62661d56..01d69618277de 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -36,6 +36,7 @@
 #include <linux/iomap.h>
 #include <linux/namei.h>
 #include <linux/uio.h>
+#include <linux/dax.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xattr.h"
@@ -1297,9 +1298,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode_dio_wait(inode);
 
 	if (IS_DAX(inode)) {
-		error = iomap_zero_range(inode, newsize,
-					 PAGE_ALIGN(newsize) - newsize, NULL,
-					 &ext2_iomap_ops);
+		error = dax_zero_range(inode, newsize,
+				       PAGE_ALIGN(newsize) - newsize, NULL,
+				       &ext2_iomap_ops);
 	} else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index bfd3545f1e5d9..d316a2009489b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/iomap.h>
 #include <linux/iversion.h>
+#include <linux/dax.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -3780,8 +3781,8 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		length = max;
 
 	if (IS_DAX(inode)) {
-		return iomap_zero_range(inode, from, length, NULL,
-					&ext4_iomap_ops);
+		return dax_zero_range(inode, from, length, NULL,
+				      &ext4_iomap_ops);
 	}
 	return __ext4_block_zero_page_range(handle, mapping, from, length);
 }
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 71a36ae120ee8..f3176cf90351f 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -876,26 +876,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
-static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length)
-{
-	struct page *page;
-	int status;
-	unsigned offset = offset_in_page(pos);
-	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
-
-	status = iomap_write_begin(iter, pos, bytes, &page);
-	if (status)
-		return status;
-
-	zero_user(page, offset, bytes);
-	mark_page_accessed(page);
-
-	return iomap_write_end(iter, pos, bytes, bytes, page);
-}
-
 static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
-	struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
@@ -906,12 +888,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		return length;
 
 	do {
-		s64 bytes;
+		unsigned offset = offset_in_page(pos);
+		size_t bytes = min_t(u64, PAGE_SIZE - offset, length);
+		struct page *page;
+		int status;
 
-		if (IS_DAX(iter->inode))
-			bytes = dax_iomap_zero(pos, length, iomap);
-		else
-			bytes = __iomap_zero_iter(iter, pos, length);
+		status = iomap_write_begin(iter, pos, bytes, &page);
+		if (status)
+			return status;
+
+		zero_user(page, offset, bytes);
+		mark_page_accessed(page);
+
+		bytes = iomap_write_end(iter, pos, bytes, bytes, page);
 		if (bytes < 0)
 			return bytes;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d6d71ae9f2ae4..6a0c3b307bd73 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -28,7 +28,6 @@
 #include "xfs_dquot.h"
 #include "xfs_reflink.h"
 
-
 #define XFS_ALLOC_ALIGN(mp, off) \
 	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
 
@@ -1321,6 +1320,9 @@ xfs_zero_range(
 {
 	struct inode		*inode = VFS_I(ip);
 
+	if (IS_DAX(inode))
+		return dax_zero_range(inode, pos, len, did_zero,
+				      &xfs_buffered_write_iomap_ops);
 	return iomap_zero_range(inode, pos, len, did_zero,
 				&xfs_buffered_write_iomap_ops);
 }
@@ -1333,6 +1335,9 @@ xfs_truncate_page(
 {
 	struct inode		*inode = VFS_I(ip);
 
+	if (IS_DAX(inode))
+		return dax_truncate_page(inode, pos, did_zero,
+					&xfs_buffered_write_iomap_ops);
 	return iomap_truncate_page(inode, pos, did_zero,
 				   &xfs_buffered_write_iomap_ops);
 }
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 324363b798ecd..b79036743e7fa 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t;
 struct dax_device;
 struct gendisk;
 struct iomap_ops;
+struct iomap_iter;
 struct iomap;
 
 struct dax_operations {
@@ -170,6 +171,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
 }
 #endif
 
+int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops);
+int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops);
+
 #if IS_ENABLED(CONFIG_DAX)
 int dax_read_lock(void);
 void dax_read_unlock(int id);
@@ -204,7 +210,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
-- 
2.30.2

[PATCH 19/29] ext2: cleanup the dax handling in ext2_fill_super

[Christoph Hellwig]

Only call fs_dax_get_by_bdev once the sbi has been allocated and remove
the need for the dax_dev local variable.

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>
---
 fs/ext2/super.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index a964066a80aa7..7e23482862e69 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -802,7 +802,6 @@ static unsigned long descriptor_loc(struct super_block *sb,
 
 static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	struct buffer_head * bh;
 	struct ext2_sb_info * sbi;
 	struct ext2_super_block * es;
@@ -822,17 +821,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
-		goto failed;
+		return -ENOMEM;
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
 	if (!sbi->s_blockgroup_lock) {
 		kfree(sbi);
-		goto failed;
+		return -ENOMEM;
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
-	sbi->s_daxdev = dax_dev;
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
 
 	spin_lock_init(&sbi->s_lock);
 	ret = -EINVAL;
@@ -946,7 +945,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (test_opt(sb, DAX)) {
-		if (!dax_dev) {
+		if (!sbi->s_daxdev) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			clear_opt(sbi->s_mount_opt, DAX);
@@ -1201,11 +1200,10 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 failed_mount:
 	brelse(bh);
 failed_sbi:
+	fs_put_dax(sbi->s_daxdev);
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-failed:
-	fs_put_dax(dax_dev);
 	return ret;
 }
 
-- 
2.30.2

[PATCH 20/29] ext4: cleanup the dax handling in ext4_fill_super

[Christoph Hellwig]

Only call fs_dax_get_by_bdev once the sbi has been allocated and remove
the need for the dax_dev local variable.

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>
---
 fs/ext4/super.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index fd3d68f10ee55..8d7e3449c6472 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3878,7 +3878,6 @@ static void ext4_setup_csum_trigger(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, **group_desc;
 	struct ext4_super_block *es = NULL;
@@ -3909,12 +3908,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if ((data && !orig_data) || !sbi)
 		goto out_free_base;
 
-	sbi->s_daxdev = dax_dev;
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
 	if (!sbi->s_blockgroup_lock)
 		goto out_free_base;
 
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
 	sb->s_fs_info = sbi;
 	sbi->s_sb = sb;
 	sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
@@ -4299,7 +4298,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		goto failed_mount;
 	}
 
-	if (dax_dev) {
+	if (sbi->s_daxdev) {
 		if (blocksize == PAGE_SIZE)
 			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
 		else
@@ -5095,10 +5094,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 out_fail:
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
+	fs_put_dax(sbi->s_daxdev);
 out_free_base:
 	kfree(sbi);
 	kfree(orig_data);
-	fs_put_dax(dax_dev);
 	return err ? err : ret;
 }
 
-- 
2.30.2

[PATCH 21/29] xfs: move dax device handling into xfs_{alloc,free}_buftarg

[Christoph Hellwig]

Hide the DAX device lookup from the xfs_super.c code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 fs/xfs/xfs_buf.c   |  8 ++++----
 fs/xfs/xfs_buf.h   |  4 ++--
 fs/xfs/xfs_super.c | 26 +++++---------------------
 3 files changed, 11 insertions(+), 27 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 631c5a61d89b7..4d4553ffa7050 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1892,6 +1892,7 @@ xfs_free_buftarg(
 	list_lru_destroy(&btp->bt_lru);
 
 	blkdev_issue_flush(btp->bt_bdev);
+	fs_put_dax(btp->bt_daxdev);
 
 	kmem_free(btp);
 }
@@ -1932,11 +1933,10 @@ xfs_setsize_buftarg_early(
 	return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
 }
 
-xfs_buftarg_t *
+struct xfs_buftarg *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct block_device	*bdev,
-	struct dax_device	*dax_dev)
+	struct block_device	*bdev)
 {
 	xfs_buftarg_t		*btp;
 
@@ -1945,7 +1945,7 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_daxdev = dax_dev;
+	btp->bt_daxdev = fs_dax_get_by_bdev(bdev);
 
 	/*
 	 * 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 6b0200b8007d1..bd7f709f0d232 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -338,8 +338,8 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
 /*
  *	Handling of buftargs.
  */
-extern struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *,
-		struct block_device *, struct dax_device *);
+struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
+		struct block_device *bdev);
 extern void xfs_free_buftarg(struct xfs_buftarg *);
 extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index c4297206f4834..3584cfc3c5930 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -391,26 +391,19 @@ STATIC void
 xfs_close_devices(
 	struct xfs_mount	*mp)
 {
-	struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev;
-
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
 		struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
-		struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev;
 
 		xfs_free_buftarg(mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
 	}
 	if (mp->m_rtdev_targp) {
 		struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
-		struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev;
 
 		xfs_free_buftarg(mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
-		fs_put_dax(dax_rtdev);
 	}
 	xfs_free_buftarg(mp->m_ddev_targp);
-	fs_put_dax(dax_ddev);
 }
 
 /*
@@ -428,8 +421,6 @@ xfs_open_devices(
 	struct xfs_mount	*mp)
 {
 	struct block_device	*ddev = mp->m_super->s_bdev;
-	struct dax_device	*dax_ddev = fs_dax_get_by_bdev(ddev);
-	struct dax_device	*dax_logdev = NULL, *dax_rtdev = NULL;
 	struct block_device	*logdev = NULL, *rtdev = NULL;
 	int			error;
 
@@ -439,8 +430,7 @@ xfs_open_devices(
 	if (mp->m_logname) {
 		error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
 		if (error)
-			goto out;
-		dax_logdev = fs_dax_get_by_bdev(logdev);
+			return error;
 	}
 
 	if (mp->m_rtname) {
@@ -454,25 +444,24 @@ xfs_open_devices(
 			error = -EINVAL;
 			goto out_close_rtdev;
 		}
-		dax_rtdev = fs_dax_get_by_bdev(rtdev);
 	}
 
 	/*
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = -ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev);
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -488,14 +477,9 @@ xfs_open_devices(
 	xfs_free_buftarg(mp->m_ddev_targp);
  out_close_rtdev:
 	xfs_blkdev_put(rtdev);
-	fs_put_dax(dax_rtdev);
  out_close_logdev:
-	if (logdev && logdev != ddev) {
+	if (logdev && logdev != ddev)
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
-	}
- out:
-	fs_put_dax(dax_ddev);
 	return error;
 }
 
-- 
2.30.2

[PATCH 22/29] xfs: use xfs_direct_write_iomap_ops for DAX zeroing

[Christoph Hellwig]

While the buffered write iomap ops do work due to the fact that zeroing
never allocates blocks, the DAX zeroing should use the direct ops just
like actual DAX 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>
---
 fs/xfs/xfs_iomap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 6a0c3b307bd73..9b7f92c6aef33 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1322,7 +1322,7 @@ xfs_zero_range(
 
 	if (IS_DAX(inode))
 		return dax_zero_range(inode, pos, len, did_zero,
-				      &xfs_buffered_write_iomap_ops);
+				      &xfs_direct_write_iomap_ops);
 	return iomap_zero_range(inode, pos, len, did_zero,
 				&xfs_buffered_write_iomap_ops);
 }
@@ -1337,7 +1337,7 @@ xfs_truncate_page(
 
 	if (IS_DAX(inode))
 		return dax_truncate_page(inode, pos, did_zero,
-					&xfs_buffered_write_iomap_ops);
+					&xfs_direct_write_iomap_ops);
 	return iomap_truncate_page(inode, pos, did_zero,
 				   &xfs_buffered_write_iomap_ops);
 }
-- 
2.30.2

[PATCH 23/29] xfs: pass the mapping flags to xfs_bmbt_to_iomap

[Christoph Hellwig]

To prepare for looking at the IOMAP_DAX flag in xfs_bmbt_to_iomap pass in
the input mapping flags to xfs_bmbt_to_iomap.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_bmap.c |  4 ++--
 fs/xfs/xfs_aops.c        |  2 +-
 fs/xfs/xfs_iomap.c       | 35 ++++++++++++++++++++---------------
 fs/xfs/xfs_iomap.h       |  5 +++--
 fs/xfs/xfs_pnfs.c        |  2 +-
 5 files changed, 27 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4dccd4d90622d..74198dd82b035 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4551,7 +4551,7 @@ xfs_bmapi_convert_delalloc(
 	 * the extent.  Just return the real extent at this offset.
 	 */
 	if (!isnullstartblock(bma.got.br_startblock)) {
-		xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+		xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
 		*seq = READ_ONCE(ifp->if_seq);
 		goto out_trans_cancel;
 	}
@@ -4598,7 +4598,7 @@ xfs_bmapi_convert_delalloc(
 	XFS_STATS_INC(mp, xs_xstrat_quick);
 
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
-	xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+	xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
 	*seq = READ_ONCE(ifp->if_seq);
 
 	if (whichfork == XFS_COW_FORK)
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index c8c15c3c31471..6ac3449a68ba0 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -359,7 +359,7 @@ xfs_map_blocks(
 	    isnullstartblock(imap.br_startblock))
 		goto allocate_blocks;
 
-	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0);
 	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 9b7f92c6aef33..d6beb1502f8bc 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -53,7 +53,8 @@ xfs_bmbt_to_iomap(
 	struct xfs_inode	*ip,
 	struct iomap		*iomap,
 	struct xfs_bmbt_irec	*imap,
-	u16			flags)
+	unsigned int		mapping_flags,
+	u16			iomap_flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
@@ -79,7 +80,7 @@ xfs_bmbt_to_iomap(
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
 	iomap->bdev = target->bt_bdev;
 	iomap->dax_dev = target->bt_daxdev;
-	iomap->flags = flags;
+	iomap->flags = iomap_flags;
 
 	if (xfs_ipincount(ip) &&
 	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
@@ -799,7 +800,7 @@ xfs_direct_write_iomap_begin(
 
 	xfs_iunlock(ip, lockmode);
 	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags);
 
 allocate_blocks:
 	error = -EAGAIN;
@@ -830,18 +831,19 @@ xfs_direct_write_iomap_begin(
 		return error;
 
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags | IOMAP_F_NEW);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
+				 iomap_flags | IOMAP_F_NEW);
 
 out_found_cow:
 	xfs_iunlock(ip, lockmode);
 	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
 	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
 	if (imap.br_startblock != HOLESTARTBLOCK) {
-		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
+		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
 		if (error)
 			return error;
 	}
-	return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED);
 
 out_unlock:
 	if (lockmode)
@@ -1051,23 +1053,24 @@ xfs_buffered_write_iomap_begin(
 	 */
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, IOMAP_F_NEW);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW);
 
 found_imap:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 
 found_cow:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	if (imap.br_startoff <= offset_fsb) {
-		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
+		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
 		if (error)
 			return error;
-		return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+		return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
+					 IOMAP_F_SHARED);
 	}
 
 	xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
-	return xfs_bmbt_to_iomap(ip, iomap, &cmap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0);
 
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1176,7 +1179,8 @@ xfs_read_iomap_begin(
 	if (error)
 		return error;
 	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared ? IOMAP_F_SHARED : 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
+				 shared ? IOMAP_F_SHARED : 0);
 }
 
 const struct iomap_ops xfs_read_iomap_ops = {
@@ -1235,7 +1239,8 @@ xfs_seek_iomap_begin(
 		if (data_fsb < cow_fsb + cmap.br_blockcount)
 			end_fsb = min(end_fsb, data_fsb);
 		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
-		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
+					  IOMAP_F_SHARED);
 		/*
 		 * This is a COW extent, so we must probe the page cache
 		 * because there could be dirty page cache being backed
@@ -1257,7 +1262,7 @@ xfs_seek_iomap_begin(
 	imap.br_state = XFS_EXT_NORM;
 done:
 	xfs_trim_extent(&imap, offset_fsb, end_fsb);
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
@@ -1304,7 +1309,7 @@ xfs_xattr_iomap_begin(
 	if (error)
 		return error;
 	ASSERT(nimaps);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 }
 
 const struct iomap_ops xfs_xattr_iomap_ops = {
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index f1a281ab9328c..657cc02290f22 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -17,8 +17,9 @@ int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 		xfs_fileoff_t end_fsb);
 
-int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
-		struct xfs_bmbt_irec *, u16);
+int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap,
+		struct xfs_bmbt_irec *imap, unsigned int mapping_flags,
+		u16 iomap_flags);
 
 int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len,
 		bool *did_zero);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 5e1d29d8b2e73..7ce1ea11fc3f3 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -173,7 +173,7 @@ xfs_fs_map_blocks(
 	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0);
 	*device_generation = mp->m_generation;
 	return error;
 out_unlock:
-- 
2.30.2

[PATCH 24/29] iomap: add a IOMAP_DAX flag

[Christoph Hellwig]

Add a flag so that the file system can easily detect DAX operations
based just on the iomap operation requested instead of looking at
inode state using IS_DAX.  This will be needed to apply the to be
added partition offset only for operations that actually use DAX,
but not things like fiemap that are based on the block device.
In the long run it should also allow turning the bdev, dax_dev
and inline_data into a union.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 fs/dax.c              | 7 ++++---
 fs/ext4/inode.c       | 4 ++--
 fs/xfs/xfs_iomap.c    | 7 ++++---
 fs/xfs/xfs_iomap.h    | 3 ++-
 fs/xfs/xfs_pnfs.c     | 2 +-
 include/linux/iomap.h | 5 +++++
 6 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 43d58b4219fd0..148e8b0967f35 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1180,7 +1180,7 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 		.inode		= inode,
 		.pos		= pos,
 		.len		= len,
-		.flags		= IOMAP_ZERO,
+		.flags		= IOMAP_DAX | IOMAP_ZERO,
 	};
 	int ret;
 
@@ -1308,6 +1308,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		.inode		= iocb->ki_filp->f_mapping->host,
 		.pos		= iocb->ki_pos,
 		.len		= iov_iter_count(iter),
+		.flags		= IOMAP_DAX,
 	};
 	loff_t done = 0;
 	int ret;
@@ -1461,7 +1462,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		.inode		= mapping->host,
 		.pos		= (loff_t)vmf->pgoff << PAGE_SHIFT,
 		.len		= PAGE_SIZE,
-		.flags		= IOMAP_FAULT,
+		.flags		= IOMAP_DAX | IOMAP_FAULT,
 	};
 	vm_fault_t ret = 0;
 	void *entry;
@@ -1570,7 +1571,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct iomap_iter iter = {
 		.inode		= mapping->host,
 		.len		= PMD_SIZE,
-		.flags		= IOMAP_FAULT,
+		.flags		= IOMAP_DAX | IOMAP_FAULT,
 	};
 	vm_fault_t ret = VM_FAULT_FALLBACK;
 	pgoff_t max_pgoff;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d316a2009489b..89c4a174bd393 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3349,8 +3349,8 @@ static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
 	 * DAX and direct I/O are the only two operations that are currently
 	 * supported with IOMAP_WRITE.
 	 */
-	WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
-	if (IS_DAX(inode))
+	WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
+	if (flags & IOMAP_DAX)
 		m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
 	/*
 	 * We use i_size instead of i_disksize here because delalloc writeback
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d6beb1502f8bc..0ed3e7674353b 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -188,6 +188,7 @@ xfs_iomap_write_direct(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		offset_fsb,
 	xfs_fileoff_t		count_fsb,
+	unsigned int		flags,
 	struct xfs_bmbt_irec	*imap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -229,7 +230,7 @@ xfs_iomap_write_direct(
 	 * the reserve block pool for bmbt block allocation if there is no space
 	 * left but we need to do unwritten extent conversion.
 	 */
-	if (IS_DAX(VFS_I(ip))) {
+	if (flags & IOMAP_DAX) {
 		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
 		if (imap->br_state == XFS_EXT_UNWRITTEN) {
 			force = true;
@@ -620,7 +621,7 @@ imap_needs_alloc(
 	    imap->br_startblock == DELAYSTARTBLOCK)
 		return true;
 	/* we convert unwritten extents before copying the data for DAX */
-	if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN)
+	if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN)
 		return true;
 	return false;
 }
@@ -826,7 +827,7 @@ xfs_direct_write_iomap_begin(
 	xfs_iunlock(ip, lockmode);
 
 	error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb,
-			&imap);
+			flags, &imap);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 657cc02290f22..e88dc162c785e 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -12,7 +12,8 @@ struct xfs_inode;
 struct xfs_bmbt_irec;
 
 int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap);
+		xfs_fileoff_t count_fsb, unsigned int flags,
+		struct xfs_bmbt_irec *imap);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 		xfs_fileoff_t end_fsb);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 7ce1ea11fc3f3..d6334abbc0b3e 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -155,7 +155,7 @@ xfs_fs_map_blocks(
 		xfs_iunlock(ip, lock_flags);
 
 		error = xfs_iomap_write_direct(ip, offset_fsb,
-				end_fsb - offset_fsb, &imap);
+				end_fsb - offset_fsb, 0, &imap);
 		if (error)
 			goto out_unlock;
 
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 6d1b08d0ae930..5b9432f9f79eb 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -141,6 +141,11 @@ struct iomap_page_ops {
 #define IOMAP_NOWAIT		(1 << 5) /* do not block */
 #define IOMAP_OVERWRITE_ONLY	(1 << 6) /* only pure overwrites allowed */
 #define IOMAP_UNSHARE		(1 << 7) /* unshare_file_range */
+#ifdef CONFIG_FS_DAX
+#define IOMAP_DAX		(1 << 8) /* DAX mapping */
+#else
+#define IOMAP_DAX		0
+#endif /* CONFIG_FS_DAX */
 
 struct iomap_ops {
 	/*
-- 
2.30.2

[PATCH 25/29] dax: return the partition offset from fs_dax_get_by_bdev

[Christoph Hellwig]

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>
---
 drivers/dax/super.c | 9 ++++++---
 drivers/md/dm.c     | 4 ++--
 fs/erofs/internal.h | 2 ++
 fs/erofs/super.c    | 4 ++--
 fs/ext2/ext2.h      | 1 +
 fs/ext2/super.c     | 2 +-
 fs/ext4/ext4.h      | 1 +
 fs/ext4/super.c     | 2 +-
 fs/xfs/xfs_buf.c    | 2 +-
 fs/xfs/xfs_buf.h    | 1 +
 include/linux/dax.h | 6 ++++--
 11 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 45d931aefd063..e7152a6c4cc40 100644
--- 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 4eba27e75c230..4e997c02bb0a0 100644
--- 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 3265688af7f9f..c1e65346e9f15 100644
--- 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 0aed886473c8d..71efce16024d9 100644
--- 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 3be9dd6412b78..d4f306aa5aceb 100644
--- 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 7e23482862e69..94f1fbd7d3ac2 100644
--- 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 404dd50856e5d..9cc55bcda6ba4 100644
--- 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 8d7e3449c6472..56228e33e52a2 100644
--- 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 4d4553ffa7050..bbb0fbd34e649 100644
--- 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 bd7f709f0d232..edcb6254fa6a8 100644
--- 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 b79036743e7fa..f6f353382cc90 100644
--- 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;
 }
-- 
2.30.2

[PATCH 26/29] fsdax: shift partition offset handling into the file systems

[Christoph Hellwig]

Remove the last user of ->bdev in dax.c by requiring the file system to
pass in an address that already includes the DAX offset.  As part of the
only set ->bdev or ->daxdev when actually required in the ->iomap_begin
methods.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> [erofs]
---
 fs/dax.c            |  6 +-----
 fs/erofs/data.c     | 11 +++++++++--
 fs/erofs/internal.h |  1 +
 fs/ext2/inode.c     |  8 ++++++--
 fs/ext4/inode.c     | 16 +++++++++++-----
 fs/xfs/xfs_iomap.c  | 10 ++++++++--
 6 files changed, 36 insertions(+), 16 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 148e8b0967f35..e0eecd8e3a8f8 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -711,11 +711,7 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 
 static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
 {
-	phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset;
-
-	if (iomap->bdev)
-		paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT);
-	return PHYS_PFN(paddr);
+	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
 }
 
 static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 0e35ef3f9f3d7..9b1bb177ce303 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -159,6 +159,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 	/* primary device by default */
 	map->m_bdev = sb->s_bdev;
 	map->m_daxdev = EROFS_SB(sb)->dax_dev;
+	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
 
 	if (map->m_deviceid) {
 		down_read(&devs->rwsem);
@@ -169,6 +170,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 		}
 		map->m_bdev = dif->bdev;
 		map->m_daxdev = dif->dax_dev;
+		map->m_dax_part_off = dif->dax_part_off;
 		up_read(&devs->rwsem);
 	} else if (devs->extra_devices) {
 		down_read(&devs->rwsem);
@@ -185,6 +187,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 				map->m_pa -= startoff;
 				map->m_bdev = dif->bdev;
 				map->m_daxdev = dif->dax_dev;
+				map->m_dax_part_off = dif->dax_part_off;
 				break;
 			}
 		}
@@ -215,9 +218,13 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret)
 		return ret;
 
-	iomap->bdev = mdev.m_bdev;
-	iomap->dax_dev = mdev.m_daxdev;
 	iomap->offset = map.m_la;
+	if (flags & IOMAP_DAX) {
+		iomap->dax_dev = mdev.m_daxdev;
+		iomap->offset += mdev.m_dax_part_off;
+	} else {
+		iomap->bdev = mdev.m_bdev;
+	}
 	iomap->length = map.m_llen;
 	iomap->flags = 0;
 	iomap->private = NULL;
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index c1e65346e9f15..5c2a83876220c 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -438,6 +438,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
 struct erofs_map_dev {
 	struct block_device *m_bdev;
 	struct dax_device *m_daxdev;
+	u64 m_dax_part_off;
 
 	erofs_off_t m_pa;
 	unsigned int m_deviceid;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 01d69618277de..602578b72d8c5 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -817,9 +817,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		return ret;
 
 	iomap->flags = 0;
-	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64)first_block << blkbits;
-	iomap->dax_dev = sbi->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = sbi->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
@@ -828,6 +830,8 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	} else {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64)bno << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += sbi->s_dax_part_off;
 		iomap->length = (u64)ret << blkbits;
 		iomap->flags |= IOMAP_F_MERGED;
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 89c4a174bd393..ccafcbc146d3e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3272,7 +3272,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 
 static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 			   struct ext4_map_blocks *map, loff_t offset,
-			   loff_t length)
+			   loff_t length, unsigned int flags)
 {
 	u8 blkbits = inode->i_blkbits;
 
@@ -3289,8 +3289,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_NEW)
 		iomap->flags |= IOMAP_F_NEW;
 
-	iomap->bdev = inode->i_sb->s_bdev;
-	iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64) map->m_lblk << blkbits;
 	iomap->length = (u64) map->m_len << blkbits;
 
@@ -3310,9 +3312,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_UNWRITTEN) {
 		iomap->type = IOMAP_UNWRITTEN;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else if (map->m_flags & EXT4_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3421,7 +3427,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret < 0)
 		return ret;
 out:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 
 	return 0;
 }
@@ -3541,7 +3547,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 		delalloc = ext4_iomap_is_delalloc(inode, &map);
 
 set_iomap:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 	if (delalloc && iomap->type == IOMAP_HOLE)
 		iomap->type = IOMAP_DELALLOC;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0ed3e7674353b..e552ce541ec2d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -71,15 +71,21 @@ xfs_bmbt_to_iomap(
 		iomap->type = IOMAP_DELALLOC;
 	} else {
 		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
+		if (mapping_flags & IOMAP_DAX)
+			iomap->addr += target->bt_dax_part_off;
+
 		if (imap->br_state == XFS_EXT_UNWRITTEN)
 			iomap->type = IOMAP_UNWRITTEN;
 		else
 			iomap->type = IOMAP_MAPPED;
+
 	}
 	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
-	iomap->bdev = target->bt_bdev;
-	iomap->dax_dev = target->bt_daxdev;
+	if (mapping_flags & IOMAP_DAX)
+		iomap->dax_dev = target->bt_daxdev;
+	else
+		iomap->bdev = target->bt_bdev;
 	iomap->flags = iomap_flags;
 
 	if (xfs_ipincount(ip) &&
-- 
2.30.2

[PATCH 27/29] dax: fix up some of the block device related ifdefs

[Christoph Hellwig]

The DAX device <-> block device association is only enabled if
CONFIG_BLOCK is enabled.  Update dax.h to account for that and use
the right conditions for the fs_put_dax stub as well.

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>
---
 include/linux/dax.h | 33 ++++++++++++++++-----------------
 1 file changed, 16 insertions(+), 17 deletions(-)

diff --git a/include/linux/dax.h b/include/linux/dax.h
index f6f353382cc90..87ae4c9b1d65b 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -108,24 +108,15 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 #endif
 
 struct writeback_control;
-#if IS_ENABLED(CONFIG_FS_DAX)
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
 int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
 void dax_remove_host(struct gendisk *disk);
-
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
+		u64 *start_off);
 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,
-		u64 *start_off);
-int dax_writeback_mapping_range(struct address_space *mapping,
-		struct dax_device *dax_dev, struct writeback_control *wbc);
-
-struct page *dax_layout_busy_page(struct address_space *mapping);
-struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
-dax_entry_t dax_lock_page(struct page *page);
-void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
 static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
@@ -134,17 +125,25 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 static inline void dax_remove_host(struct gendisk *disk)
 {
 }
-
-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,
 		u64 *start_off)
 {
 	return NULL;
 }
+static inline void fs_put_dax(struct dax_device *dax_dev)
+{
+}
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
+#if IS_ENABLED(CONFIG_FS_DAX)
+int dax_writeback_mapping_range(struct address_space *mapping,
+		struct dax_device *dax_dev, struct writeback_control *wbc);
+
+struct page *dax_layout_busy_page(struct address_space *mapping);
+struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
+dax_entry_t dax_lock_page(struct page *page);
+void dax_unlock_page(struct page *page, dax_entry_t cookie);
+#else
 static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 {
 	return NULL;
-- 
2.30.2

[PATCH 28/29] iomap: build the block based code conditionally

[Christoph Hellwig]

Only build the block based iomap code if CONFIG_BLOCK is set.  Currently
that is always the case, but it will change soon.

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>
---
 fs/Kconfig        | 4 ++--
 fs/iomap/Makefile | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/Kconfig b/fs/Kconfig
index a6313a969bc5f..6d608330a096e 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -15,11 +15,11 @@ config VALIDATE_FS_PARSER
 	  Enable this to perform validation of the parameter description for a
 	  filesystem when it is registered.
 
-if BLOCK
-
 config FS_IOMAP
 	bool
 
+if BLOCK
+
 source "fs/ext2/Kconfig"
 source "fs/ext4/Kconfig"
 source "fs/jbd2/Kconfig"
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
index 4143a3ff89dbc..fc070184b7faa 100644
--- a/fs/iomap/Makefile
+++ b/fs/iomap/Makefile
@@ -9,9 +9,9 @@ ccflags-y += -I $(srctree)/$(src)		# needed for trace events
 obj-$(CONFIG_FS_IOMAP)		+= iomap.o
 
 iomap-y				+= trace.o \
-				   buffered-io.o \
+				   iter.o
+iomap-$(CONFIG_BLOCK)		+= buffered-io.o \
 				   direct-io.o \
 				   fiemap.o \
-				   iter.o \
 				   seek.o
 iomap-$(CONFIG_SWAP)		+= swapfile.o
-- 
2.30.2

[PATCH 29/29] fsdax: don't require CONFIG_BLOCK

[Christoph Hellwig]

The file system DAX code now does not require the block code.  So allow
building a kernel with fuse DAX but not block layer.

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>
---
 fs/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/Kconfig b/fs/Kconfig
index 6d608330a096e..7a2b11c0b8036 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -42,6 +42,8 @@ source "fs/nilfs2/Kconfig"
 source "fs/f2fs/Kconfig"
 source "fs/zonefs/Kconfig"
 
+endif # BLOCK
+
 config FS_DAX
 	bool "File system based Direct Access (DAX) support"
 	depends on MMU
@@ -89,8 +91,6 @@ config FS_DAX_PMD
 config FS_DAX_LIMITED
 	bool
 
-endif # BLOCK
-
 # Posix ACL utility routines
 #
 # Note: Posix ACLs can be implemented without these helpers.  Never use
-- 
2.30.2

Re: [PATCH 04/29] dax: simplify the dax_device <-> gendisk association

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:38AM +0100, Christoph Hellwig wrote:
> Replace the dax_host_hash with an xarray indexed by the pointer value
> of the gendisk, and require explicitly calls from the block drivers that
> want to associate their gendisk with a dax_device.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Acked-by: Mike Snitzer <snitzer@redhat.com>

Nice cleanup from the fs side!
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  drivers/dax/bus.c            |   6 +-
>  drivers/dax/super.c          | 109 +++++++++--------------------------
>  drivers/md/dm.c              |   6 +-
>  drivers/nvdimm/pmem.c        |  10 +++-
>  drivers/s390/block/dcssblk.c |  11 +++-
>  fs/fuse/virtio_fs.c          |   2 +-
>  include/linux/dax.h          |  19 ++++--
>  7 files changed, 66 insertions(+), 97 deletions(-)
> 
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index 6cc4da4c713d9..bd7af2f7c5b0a 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -1323,10 +1323,10 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
>  	}
>  
>  	/*
> -	 * No 'host' or dax_operations since there is no access to this
> -	 * device outside of mmap of the resulting character device.
> +	 * No dax_operations since there is no access to this device outside of
> +	 * mmap of the resulting character device.
>  	 */
> -	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
> +	dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC);
>  	if (IS_ERR(dax_dev)) {
>  		rc = PTR_ERR(dax_dev);
>  		goto err_alloc_dax;
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index e20d0cef10a18..bf77c3da5d56d 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -7,10 +7,8 @@
>  #include <linux/mount.h>
>  #include <linux/pseudo_fs.h>
>  #include <linux/magic.h>
> -#include <linux/genhd.h>
>  #include <linux/pfn_t.h>
>  #include <linux/cdev.h>
> -#include <linux/hash.h>
>  #include <linux/slab.h>
>  #include <linux/uio.h>
>  #include <linux/dax.h>
> @@ -21,15 +19,12 @@
>   * struct dax_device - anchor object for dax services
>   * @inode: core vfs
>   * @cdev: optional character interface for "device dax"
> - * @host: optional name for lookups where the device path is not available
>   * @private: dax driver private data
>   * @flags: state and boolean properties
>   */
>  struct dax_device {
> -	struct hlist_node list;
>  	struct inode inode;
>  	struct cdev cdev;
> -	const char *host;
>  	void *private;
>  	unsigned long flags;
>  	const struct dax_operations *ops;
> @@ -42,10 +37,6 @@ static DEFINE_IDA(dax_minor_ida);
>  static struct kmem_cache *dax_cache __read_mostly;
>  static struct super_block *dax_superblock __read_mostly;
>  
> -#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head))
> -static struct hlist_head dax_host_list[DAX_HASH_SIZE];
> -static DEFINE_SPINLOCK(dax_host_lock);
> -
>  int dax_read_lock(void)
>  {
>  	return srcu_read_lock(&dax_srcu);
> @@ -58,13 +49,22 @@ void dax_read_unlock(int id)
>  }
>  EXPORT_SYMBOL_GPL(dax_read_unlock);
>  
> -static int dax_host_hash(const char *host)
> +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
> +#include <linux/blkdev.h>
> +
> +static DEFINE_XARRAY(dax_hosts);
> +
> +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
>  {
> -	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
> +	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
>  }
> +EXPORT_SYMBOL_GPL(dax_add_host);
>  
> -#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
> -#include <linux/blkdev.h>
> +void dax_remove_host(struct gendisk *disk)
> +{
> +	xa_erase(&dax_hosts, (unsigned long)disk);
> +}
> +EXPORT_SYMBOL_GPL(dax_remove_host);
>  
>  int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
>  		pgoff_t *pgoff)
> @@ -81,41 +81,24 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
>  EXPORT_SYMBOL(bdev_dax_pgoff);
>  
>  /**
> - * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
> - * @host: alternate name for the device registered by a dax driver
> + * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
> + * @bdev: block device to find a dax_device for
>   */
> -static struct dax_device *dax_get_by_host(const char *host)
> +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
>  {
> -	struct dax_device *dax_dev, *found = NULL;
> -	int hash, id;
> +	struct dax_device *dax_dev;
> +	int id;
>  
> -	if (!host)
> +	if (!blk_queue_dax(bdev->bd_disk->queue))
>  		return NULL;
>  
> -	hash = dax_host_hash(host);
> -
>  	id = dax_read_lock();
> -	spin_lock(&dax_host_lock);
> -	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
> -		if (!dax_alive(dax_dev)
> -				|| strcmp(host, dax_dev->host) != 0)
> -			continue;
> -
> -		if (igrab(&dax_dev->inode))
> -			found = dax_dev;
> -		break;
> -	}
> -	spin_unlock(&dax_host_lock);
> +	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
> +	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
> +		dax_dev = NULL;
>  	dax_read_unlock(id);
>  
> -	return found;
> -}
> -
> -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
> -{
> -	if (!blk_queue_dax(bdev->bd_disk->queue))
> -		return NULL;
> -	return dax_get_by_host(bdev->bd_disk->disk_name);
> +	return dax_dev;
>  }
>  EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
>  
> @@ -361,12 +344,7 @@ void kill_dax(struct dax_device *dax_dev)
>  		return;
>  
>  	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
> -
>  	synchronize_srcu(&dax_srcu);
> -
> -	spin_lock(&dax_host_lock);
> -	hlist_del_init(&dax_dev->list);
> -	spin_unlock(&dax_host_lock);
>  }
>  EXPORT_SYMBOL_GPL(kill_dax);
>  
> @@ -398,8 +376,6 @@ static struct dax_device *to_dax_dev(struct inode *inode)
>  static void dax_free_inode(struct inode *inode)
>  {
>  	struct dax_device *dax_dev = to_dax_dev(inode);
> -	kfree(dax_dev->host);
> -	dax_dev->host = NULL;
>  	if (inode->i_rdev)
>  		ida_simple_remove(&dax_minor_ida, iminor(inode));
>  	kmem_cache_free(dax_cache, dax_dev);
> @@ -474,54 +450,25 @@ static struct dax_device *dax_dev_get(dev_t devt)
>  	return dax_dev;
>  }
>  
> -static void dax_add_host(struct dax_device *dax_dev, const char *host)
> -{
> -	int hash;
> -
> -	/*
> -	 * Unconditionally init dax_dev since it's coming from a
> -	 * non-zeroed slab cache
> -	 */
> -	INIT_HLIST_NODE(&dax_dev->list);
> -	dax_dev->host = host;
> -	if (!host)
> -		return;
> -
> -	hash = dax_host_hash(host);
> -	spin_lock(&dax_host_lock);
> -	hlist_add_head(&dax_dev->list, &dax_host_list[hash]);
> -	spin_unlock(&dax_host_lock);
> -}
> -
> -struct dax_device *alloc_dax(void *private, const char *__host,
> -		const struct dax_operations *ops, unsigned long flags)
> +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops,
> +		unsigned long flags)
>  {
>  	struct dax_device *dax_dev;
> -	const char *host;
>  	dev_t devt;
>  	int minor;
>  
> -	if (ops && !ops->zero_page_range) {
> -		pr_debug("%s: error: device does not provide dax"
> -			 " operation zero_page_range()\n",
> -			 __host ? __host : "Unknown");
> +	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
>  		return ERR_PTR(-EINVAL);
> -	}
> -
> -	host = kstrdup(__host, GFP_KERNEL);
> -	if (__host && !host)
> -		return ERR_PTR(-ENOMEM);
>  
>  	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
>  	if (minor < 0)
> -		goto err_minor;
> +		return ERR_PTR(-ENOMEM);
>  
>  	devt = MKDEV(MAJOR(dax_devt), minor);
>  	dax_dev = dax_dev_get(devt);
>  	if (!dax_dev)
>  		goto err_dev;
>  
> -	dax_add_host(dax_dev, host);
>  	dax_dev->ops = ops;
>  	dax_dev->private = private;
>  	if (flags & DAXDEV_F_SYNC)
> @@ -531,8 +478,6 @@ struct dax_device *alloc_dax(void *private, const char *__host,
>  
>   err_dev:
>  	ida_simple_remove(&dax_minor_ida, minor);
> - err_minor:
> -	kfree(host);
>  	return ERR_PTR(-ENOMEM);
>  }
>  EXPORT_SYMBOL_GPL(alloc_dax);
> diff --git a/drivers/md/dm.c b/drivers/md/dm.c
> index b93fcc91176e5..a8c650276b321 100644
> --- a/drivers/md/dm.c
> +++ b/drivers/md/dm.c
> @@ -1683,6 +1683,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
>  	bioset_exit(&md->io_bs);
>  
>  	if (md->dax_dev) {
> +		dax_remove_host(md->disk);
>  		kill_dax(md->dax_dev);
>  		put_dax(md->dax_dev);
>  		md->dax_dev = NULL;
> @@ -1784,12 +1785,13 @@ static struct mapped_device *alloc_dev(int minor)
>  	sprintf(md->disk->disk_name, "dm-%d", minor);
>  
>  	if (IS_ENABLED(CONFIG_FS_DAX)) {
> -		md->dax_dev = alloc_dax(md, md->disk->disk_name,
> -					&dm_dax_ops, 0);
> +		md->dax_dev = alloc_dax(md, &dm_dax_ops, 0);
>  		if (IS_ERR(md->dax_dev)) {
>  			md->dax_dev = NULL;
>  			goto bad;
>  		}
> +		if (dax_add_host(md->dax_dev, md->disk))
> +			goto bad;
>  	}
>  
>  	format_dev_t(md->name, MKDEV(_major, minor));
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index fe7ece1534e1e..1018f0d44acb8 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -379,6 +379,7 @@ static void pmem_release_disk(void *__pmem)
>  {
>  	struct pmem_device *pmem = __pmem;
>  
> +	dax_remove_host(pmem->disk);
>  	kill_dax(pmem->dax_dev);
>  	put_dax(pmem->dax_dev);
>  	del_gendisk(pmem->disk);
> @@ -497,17 +498,20 @@ static int pmem_attach_disk(struct device *dev,
>  
>  	if (is_nvdimm_sync(nd_region))
>  		flags = DAXDEV_F_SYNC;
> -	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
> +	dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags);
>  	if (IS_ERR(dax_dev)) {
>  		rc = PTR_ERR(dax_dev);
>  		goto out;
>  	}
> +	rc = dax_add_host(dax_dev, disk);
> +	if (rc)
> +		goto out_cleanup_dax;
>  	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
>  	pmem->dax_dev = dax_dev;
>  
>  	rc = device_add_disk(dev, disk, pmem_attribute_groups);
>  	if (rc)
> -		goto out_cleanup_dax;
> +		goto out_remove_host;
>  	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
>  		return -ENOMEM;
>  
> @@ -519,6 +523,8 @@ static int pmem_attach_disk(struct device *dev,
>  		dev_warn(dev, "'badblocks' notification disabled\n");
>  	return 0;
>  
> +out_remove_host:
> +	dax_remove_host(pmem->disk);
>  out_cleanup_dax:
>  	kill_dax(pmem->dax_dev);
>  	put_dax(pmem->dax_dev);
> diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
> index 27ab888b44d0a..657e492f2bc26 100644
> --- a/drivers/s390/block/dcssblk.c
> +++ b/drivers/s390/block/dcssblk.c
> @@ -687,18 +687,21 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
>  	if (rc)
>  		goto put_dev;
>  
> -	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
> -			&dcssblk_dax_ops, DAXDEV_F_SYNC);
> +	dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops,
> +			DAXDEV_F_SYNC);
>  	if (IS_ERR(dev_info->dax_dev)) {
>  		rc = PTR_ERR(dev_info->dax_dev);
>  		dev_info->dax_dev = NULL;
>  		goto put_dev;
>  	}
> +	rc = dax_add_host(dev_info->dax_dev, dev_info->gd);
> +	if (rc)
> +		goto out_dax;
>  
>  	get_device(&dev_info->dev);
>  	rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL);
>  	if (rc)
> -		goto out_dax;
> +		goto out_dax_host;
>  
>  	switch (dev_info->segment_type) {
>  		case SEG_TYPE_SR:
> @@ -714,6 +717,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
>  	rc = count;
>  	goto out;
>  
> +out_dax_host:
> +	dax_remove_host(dev_info->gd);
>  out_dax:
>  	put_device(&dev_info->dev);
>  	kill_dax(dev_info->dax_dev);
> diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
> index 4cfa4bc1f5794..242cc1c0d7ed7 100644
> --- a/fs/fuse/virtio_fs.c
> +++ b/fs/fuse/virtio_fs.c
> @@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
>  	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
>  		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
>  
> -	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
> +	fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0);
>  	if (IS_ERR(fs->dax_dev))
>  		return PTR_ERR(fs->dax_dev);
>  
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 8623caa673889..e2e9a67004cbd 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -11,9 +11,11 @@
>  
>  typedef unsigned long dax_entry_t;
>  
> +struct dax_device;
> +struct gendisk;
>  struct iomap_ops;
>  struct iomap;
> -struct dax_device;
> +
>  struct dax_operations {
>  	/*
>  	 * direct_access: translate a device-relative
> @@ -39,8 +41,8 @@ struct dax_operations {
>  };
>  
>  #if IS_ENABLED(CONFIG_DAX)
> -struct dax_device *alloc_dax(void *private, const char *host,
> -		const struct dax_operations *ops, unsigned long flags);
> +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops,
> +		unsigned long flags);
>  void put_dax(struct dax_device *dax_dev);
>  void kill_dax(struct dax_device *dax_dev);
>  void dax_write_cache(struct dax_device *dax_dev, bool wc);
> @@ -68,7 +70,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
>  	return dax_synchronous(dax_dev);
>  }
>  #else
> -static inline struct dax_device *alloc_dax(void *private, const char *host,
> +static inline struct dax_device *alloc_dax(void *private,
>  		const struct dax_operations *ops, unsigned long flags)
>  {
>  	/*
> @@ -107,6 +109,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
>  struct writeback_control;
>  int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
>  #if IS_ENABLED(CONFIG_FS_DAX)
> +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
> +void dax_remove_host(struct gendisk *disk);
>  bool generic_fsdax_supported(struct dax_device *dax_dev,
>  		struct block_device *bdev, int blocksize, sector_t start,
>  		sector_t sectors);
> @@ -128,6 +132,13 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
>  dax_entry_t dax_lock_page(struct page *page);
>  void dax_unlock_page(struct page *page, dax_entry_t cookie);
>  #else
> +static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
> +{
> +	return 0;
> +}
> +static inline void dax_remove_host(struct gendisk *disk)
> +{
> +}
>  #define generic_fsdax_supported		NULL
>  
>  static inline bool dax_supported(struct dax_device *dax_dev,
> -- 
> 2.30.2
> 

Re: [PATCH 05/29] dax: remove the pgmap sanity checks in generic_fsdax_supported

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:39AM +0100, Christoph Hellwig wrote:
> Drivers that register a dax_dev should make sure it works, no need
> to double check from the file system.
> 
> 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>

--D

> ---
>  drivers/dax/super.c | 49 +--------------------------------------------
>  1 file changed, 1 insertion(+), 48 deletions(-)
> 
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index bf77c3da5d56d..c8500b7e2d8a2 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -106,13 +106,9 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
>  		struct block_device *bdev, int blocksize, sector_t start,
>  		sector_t sectors)
>  {
> -	bool dax_enabled = false;
>  	pgoff_t pgoff, pgoff_end;
> -	void *kaddr, *end_kaddr;
> -	pfn_t pfn, end_pfn;
>  	sector_t last_page;
> -	long len, len2;
> -	int err, id;
> +	int err;
>  
>  	if (blocksize != PAGE_SIZE) {
>  		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
> @@ -137,49 +133,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
>  		return false;
>  	}
>  
> -	id = dax_read_lock();
> -	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
> -	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
> -
> -	if (len < 1 || len2 < 1) {
> -		pr_info("%pg: error: dax access failed (%ld)\n",
> -				bdev, len < 1 ? len : len2);
> -		dax_read_unlock(id);
> -		return false;
> -	}
> -
> -	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
> -		/*
> -		 * An arch that has enabled the pmem api should also
> -		 * have its drivers support pfn_t_devmap()
> -		 *
> -		 * This is a developer warning and should not trigger in
> -		 * production. dax_flush() will crash since it depends
> -		 * on being able to do (page_address(pfn_to_page())).
> -		 */
> -		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
> -		dax_enabled = true;
> -	} else if (pfn_t_devmap(pfn) && pfn_t_devmap(end_pfn)) {
> -		struct dev_pagemap *pgmap, *end_pgmap;
> -
> -		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
> -		end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL);
> -		if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX
> -				&& pfn_t_to_page(pfn)->pgmap == pgmap
> -				&& pfn_t_to_page(end_pfn)->pgmap == pgmap
> -				&& pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr))
> -				&& pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr)))
> -			dax_enabled = true;
> -		put_dev_pagemap(pgmap);
> -		put_dev_pagemap(end_pgmap);
> -
> -	}
> -	dax_read_unlock(id);
> -
> -	if (!dax_enabled) {
> -		pr_info("%pg: error: dax support not enabled\n", bdev);
> -		return false;
> -	}
>  	return true;
>  }
>  EXPORT_SYMBOL_GPL(generic_fsdax_supported);
> -- 
> 2.30.2
> 

Re: [PATCH 06/29] dax: move the partition alignment check into fs_dax_get_by_bdev

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:40AM +0100, Christoph Hellwig wrote:
> fs_dax_get_by_bdev is the primary interface to find a dax device for a
> block device, so move the partition alignment check there instead of
> wiring it up through ->dax_supported.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Dan Williams <dan.j.williams@intel.com>

Makes more sense than the old "get the dax device and /then/ check if
it's ok to use it" strategy.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  drivers/dax/super.c | 23 ++++++-----------------
>  1 file changed, 6 insertions(+), 17 deletions(-)
> 
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index c8500b7e2d8a2..f2cef47bdeafd 100644
> --- a/drivers/dax/super.c
> +++ b/drivers/dax/super.c
> @@ -92,6 +92,12 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
>  	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) {
> +		pr_info("%pg: error: unaligned partition for dax\n", bdev);
> +		return NULL;
> +	}
> +
>  	id = dax_read_lock();
>  	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
>  	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
> @@ -106,10 +112,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
>  		struct block_device *bdev, int blocksize, sector_t start,
>  		sector_t sectors)
>  {
> -	pgoff_t pgoff, pgoff_end;
> -	sector_t last_page;
> -	int err;
> -
>  	if (blocksize != PAGE_SIZE) {
>  		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
>  		return false;
> @@ -120,19 +122,6 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
>  		return false;
>  	}
>  
> -	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
> -	if (err) {
> -		pr_info("%pg: error: unaligned partition for dax\n", bdev);
> -		return false;
> -	}
> -
> -	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
> -	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
> -	if (err) {
> -		pr_info("%pg: error: unaligned partition for dax\n", bdev);
> -		return false;
> -	}
> -
>  	return true;
>  }
>  EXPORT_SYMBOL_GPL(generic_fsdax_supported);
> -- 
> 2.30.2
> 

Re: [PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:52AM +0100, Christoph Hellwig wrote:
> Unshare the DAX and iomap buffered I/O page zeroing code.  This code
> previously did a IS_DAX check deep inside the iomap code, which in
> fact was the only DAX check in the code.  Instead move these checks
> into the callers.  Most callers already have DAX special casing anyway
> and XFS will need it for reflink support as well.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Dan Williams <dan.j.williams@intel.com>

Hooray, less dax entanglement!

Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  fs/dax.c               | 77 ++++++++++++++++++++++++++++++++++--------
>  fs/ext2/inode.c        |  7 ++--
>  fs/ext4/inode.c        |  5 +--
>  fs/iomap/buffered-io.c | 35 +++++++------------
>  fs/xfs/xfs_iomap.c     |  7 +++-
>  include/linux/dax.h    |  7 +++-
>  6 files changed, 94 insertions(+), 44 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index d5db1297a0bb6..43d58b4219fd0 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
>  	return ret;
>  }
>  
> -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
> +static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
>  {
> -	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
> -	long rc, id;
> -	unsigned offset = offset_in_page(pos);
> -	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
> +	const struct iomap *iomap = &iter->iomap;
> +	const struct iomap *srcmap = iomap_iter_srcmap(iter);
> +	loff_t pos = iter->pos;
> +	u64 length = iomap_length(iter);
> +	s64 written = 0;
> +
> +	/* already zeroed?  we're done. */
> +	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
> +		return length;
> +
> +	do {
> +		unsigned offset = offset_in_page(pos);
> +		unsigned size = min_t(u64, PAGE_SIZE - offset, length);
> +		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
> +		long rc;
> +		int id;
>  
> -	id = dax_read_lock();
> -	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
> -		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
> -	else
> -		rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
> -	dax_read_unlock(id);
> +		id = dax_read_lock();
> +		if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
> +			rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
> +		else
> +			rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
> +		dax_read_unlock(id);
>  
> -	if (rc < 0)
> -		return rc;
> -	return size;
> +		if (rc < 0)
> +			return rc;
> +		pos += size;
> +		length -= size;
> +		written += size;
> +		if (did_zero)
> +			*did_zero = true;
> +	} while (length > 0);
> +
> +	return written;
> +}
> +
> +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
> +		const struct iomap_ops *ops)
> +{
> +	struct iomap_iter iter = {
> +		.inode		= inode,
> +		.pos		= pos,
> +		.len		= len,
> +		.flags		= IOMAP_ZERO,
> +	};
> +	int ret;
> +
> +	while ((ret = iomap_iter(&iter, ops)) > 0)
> +		iter.processed = dax_zero_iter(&iter, did_zero);
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(dax_zero_range);
> +
> +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
> +		const struct iomap_ops *ops)
> +{
> +	unsigned int blocksize = i_blocksize(inode);
> +	unsigned int off = pos & (blocksize - 1);
> +
> +	/* Block boundary? Nothing to do */
> +	if (!off)
> +		return 0;
> +	return dax_zero_range(inode, pos, blocksize - off, did_zero, ops);
>  }
> +EXPORT_SYMBOL_GPL(dax_truncate_page);
>  
>  static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
>  		struct iov_iter *iter)
> diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
> index 333fa62661d56..01d69618277de 100644
> --- a/fs/ext2/inode.c
> +++ b/fs/ext2/inode.c
> @@ -36,6 +36,7 @@
>  #include <linux/iomap.h>
>  #include <linux/namei.h>
>  #include <linux/uio.h>
> +#include <linux/dax.h>
>  #include "ext2.h"
>  #include "acl.h"
>  #include "xattr.h"
> @@ -1297,9 +1298,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
>  	inode_dio_wait(inode);
>  
>  	if (IS_DAX(inode)) {
> -		error = iomap_zero_range(inode, newsize,
> -					 PAGE_ALIGN(newsize) - newsize, NULL,
> -					 &ext2_iomap_ops);
> +		error = dax_zero_range(inode, newsize,
> +				       PAGE_ALIGN(newsize) - newsize, NULL,
> +				       &ext2_iomap_ops);
>  	} else if (test_opt(inode->i_sb, NOBH))
>  		error = nobh_truncate_page(inode->i_mapping,
>  				newsize, ext2_get_block);
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index bfd3545f1e5d9..d316a2009489b 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -41,6 +41,7 @@
>  #include <linux/bitops.h>
>  #include <linux/iomap.h>
>  #include <linux/iversion.h>
> +#include <linux/dax.h>
>  
>  #include "ext4_jbd2.h"
>  #include "xattr.h"
> @@ -3780,8 +3781,8 @@ static int ext4_block_zero_page_range(handle_t *handle,
>  		length = max;
>  
>  	if (IS_DAX(inode)) {
> -		return iomap_zero_range(inode, from, length, NULL,
> -					&ext4_iomap_ops);
> +		return dax_zero_range(inode, from, length, NULL,
> +				      &ext4_iomap_ops);
>  	}
>  	return __ext4_block_zero_page_range(handle, mapping, from, length);
>  }
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 71a36ae120ee8..f3176cf90351f 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -876,26 +876,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
>  }
>  EXPORT_SYMBOL_GPL(iomap_file_unshare);
>  
> -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length)
> -{
> -	struct page *page;
> -	int status;
> -	unsigned offset = offset_in_page(pos);
> -	unsigned bytes = min_t(u64, PAGE_SIZE - offset, length);
> -
> -	status = iomap_write_begin(iter, pos, bytes, &page);
> -	if (status)
> -		return status;
> -
> -	zero_user(page, offset, bytes);
> -	mark_page_accessed(page);
> -
> -	return iomap_write_end(iter, pos, bytes, bytes, page);
> -}
> -
>  static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
>  {
> -	struct iomap *iomap = &iter->iomap;
>  	const struct iomap *srcmap = iomap_iter_srcmap(iter);
>  	loff_t pos = iter->pos;
>  	loff_t length = iomap_length(iter);
> @@ -906,12 +888,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
>  		return length;
>  
>  	do {
> -		s64 bytes;
> +		unsigned offset = offset_in_page(pos);
> +		size_t bytes = min_t(u64, PAGE_SIZE - offset, length);
> +		struct page *page;
> +		int status;
>  
> -		if (IS_DAX(iter->inode))
> -			bytes = dax_iomap_zero(pos, length, iomap);
> -		else
> -			bytes = __iomap_zero_iter(iter, pos, length);
> +		status = iomap_write_begin(iter, pos, bytes, &page);
> +		if (status)
> +			return status;
> +
> +		zero_user(page, offset, bytes);
> +		mark_page_accessed(page);
> +
> +		bytes = iomap_write_end(iter, pos, bytes, bytes, page);
>  		if (bytes < 0)
>  			return bytes;
>  
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index d6d71ae9f2ae4..6a0c3b307bd73 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -28,7 +28,6 @@
>  #include "xfs_dquot.h"
>  #include "xfs_reflink.h"
>  
> -
>  #define XFS_ALLOC_ALIGN(mp, off) \
>  	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
>  
> @@ -1321,6 +1320,9 @@ xfs_zero_range(
>  {
>  	struct inode		*inode = VFS_I(ip);
>  
> +	if (IS_DAX(inode))
> +		return dax_zero_range(inode, pos, len, did_zero,
> +				      &xfs_buffered_write_iomap_ops);
>  	return iomap_zero_range(inode, pos, len, did_zero,
>  				&xfs_buffered_write_iomap_ops);
>  }
> @@ -1333,6 +1335,9 @@ xfs_truncate_page(
>  {
>  	struct inode		*inode = VFS_I(ip);
>  
> +	if (IS_DAX(inode))
> +		return dax_truncate_page(inode, pos, did_zero,
> +					&xfs_buffered_write_iomap_ops);
>  	return iomap_truncate_page(inode, pos, did_zero,
>  				   &xfs_buffered_write_iomap_ops);
>  }
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 324363b798ecd..b79036743e7fa 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t;
>  struct dax_device;
>  struct gendisk;
>  struct iomap_ops;
> +struct iomap_iter;
>  struct iomap;
>  
>  struct dax_operations {
> @@ -170,6 +171,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
>  }
>  #endif
>  
> +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
> +		const struct iomap_ops *ops);
> +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
> +		const struct iomap_ops *ops);
> +
>  #if IS_ENABLED(CONFIG_DAX)
>  int dax_read_lock(void);
>  void dax_read_unlock(int id);
> @@ -204,7 +210,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
>  int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
>  int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
>  				      pgoff_t index);
> -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
>  static inline bool dax_mapping(struct address_space *mapping)
>  {
>  	return mapping->host && IS_DAX(mapping->host);
> -- 
> 2.30.2
> 

Re: [PATCH 23/29] xfs: pass the mapping flags to xfs_bmbt_to_iomap

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:57AM +0100, Christoph Hellwig wrote:
> To prepare for looking at the IOMAP_DAX flag in xfs_bmbt_to_iomap pass in
> the input mapping flags to xfs_bmbt_to_iomap.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Thanks for changing the argument names to be less confusing,
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  fs/xfs/libxfs/xfs_bmap.c |  4 ++--
>  fs/xfs/xfs_aops.c        |  2 +-
>  fs/xfs/xfs_iomap.c       | 35 ++++++++++++++++++++---------------
>  fs/xfs/xfs_iomap.h       |  5 +++--
>  fs/xfs/xfs_pnfs.c        |  2 +-
>  5 files changed, 27 insertions(+), 21 deletions(-)
> 
> diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
> index 4dccd4d90622d..74198dd82b035 100644
> --- a/fs/xfs/libxfs/xfs_bmap.c
> +++ b/fs/xfs/libxfs/xfs_bmap.c
> @@ -4551,7 +4551,7 @@ xfs_bmapi_convert_delalloc(
>  	 * the extent.  Just return the real extent at this offset.
>  	 */
>  	if (!isnullstartblock(bma.got.br_startblock)) {
> -		xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
> +		xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
>  		*seq = READ_ONCE(ifp->if_seq);
>  		goto out_trans_cancel;
>  	}
> @@ -4598,7 +4598,7 @@ xfs_bmapi_convert_delalloc(
>  	XFS_STATS_INC(mp, xs_xstrat_quick);
>  
>  	ASSERT(!isnullstartblock(bma.got.br_startblock));
> -	xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
> +	xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
>  	*seq = READ_ONCE(ifp->if_seq);
>  
>  	if (whichfork == XFS_COW_FORK)
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index c8c15c3c31471..6ac3449a68ba0 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -359,7 +359,7 @@ xfs_map_blocks(
>  	    isnullstartblock(imap.br_startblock))
>  		goto allocate_blocks;
>  
> -	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
> +	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0);
>  	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
>  	return 0;
>  allocate_blocks:
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index 9b7f92c6aef33..d6beb1502f8bc 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -53,7 +53,8 @@ xfs_bmbt_to_iomap(
>  	struct xfs_inode	*ip,
>  	struct iomap		*iomap,
>  	struct xfs_bmbt_irec	*imap,
> -	u16			flags)
> +	unsigned int		mapping_flags,
> +	u16			iomap_flags)
>  {
>  	struct xfs_mount	*mp = ip->i_mount;
>  	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
> @@ -79,7 +80,7 @@ xfs_bmbt_to_iomap(
>  	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
>  	iomap->bdev = target->bt_bdev;
>  	iomap->dax_dev = target->bt_daxdev;
> -	iomap->flags = flags;
> +	iomap->flags = iomap_flags;
>  
>  	if (xfs_ipincount(ip) &&
>  	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
> @@ -799,7 +800,7 @@ xfs_direct_write_iomap_begin(
>  
>  	xfs_iunlock(ip, lockmode);
>  	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags);
>  
>  allocate_blocks:
>  	error = -EAGAIN;
> @@ -830,18 +831,19 @@ xfs_direct_write_iomap_begin(
>  		return error;
>  
>  	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags | IOMAP_F_NEW);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
> +				 iomap_flags | IOMAP_F_NEW);
>  
>  out_found_cow:
>  	xfs_iunlock(ip, lockmode);
>  	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
>  	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
>  	if (imap.br_startblock != HOLESTARTBLOCK) {
> -		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
> +		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
>  		if (error)
>  			return error;
>  	}
> -	return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
> +	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED);
>  
>  out_unlock:
>  	if (lockmode)
> @@ -1051,23 +1053,24 @@ xfs_buffered_write_iomap_begin(
>  	 */
>  	xfs_iunlock(ip, XFS_ILOCK_EXCL);
>  	trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, IOMAP_F_NEW);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW);
>  
>  found_imap:
>  	xfs_iunlock(ip, XFS_ILOCK_EXCL);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
>  
>  found_cow:
>  	xfs_iunlock(ip, XFS_ILOCK_EXCL);
>  	if (imap.br_startoff <= offset_fsb) {
> -		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
> +		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
>  		if (error)
>  			return error;
> -		return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
> +		return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
> +					 IOMAP_F_SHARED);
>  	}
>  
>  	xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
> -	return xfs_bmbt_to_iomap(ip, iomap, &cmap, 0);
> +	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0);
>  
>  out_unlock:
>  	xfs_iunlock(ip, XFS_ILOCK_EXCL);
> @@ -1176,7 +1179,8 @@ xfs_read_iomap_begin(
>  	if (error)
>  		return error;
>  	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared ? IOMAP_F_SHARED : 0);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
> +				 shared ? IOMAP_F_SHARED : 0);
>  }
>  
>  const struct iomap_ops xfs_read_iomap_ops = {
> @@ -1235,7 +1239,8 @@ xfs_seek_iomap_begin(
>  		if (data_fsb < cow_fsb + cmap.br_blockcount)
>  			end_fsb = min(end_fsb, data_fsb);
>  		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
> -		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
> +		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
> +					  IOMAP_F_SHARED);
>  		/*
>  		 * This is a COW extent, so we must probe the page cache
>  		 * because there could be dirty page cache being backed
> @@ -1257,7 +1262,7 @@ xfs_seek_iomap_begin(
>  	imap.br_state = XFS_EXT_NORM;
>  done:
>  	xfs_trim_extent(&imap, offset_fsb, end_fsb);
> -	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
> +	error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
>  out_unlock:
>  	xfs_iunlock(ip, lockmode);
>  	return error;
> @@ -1304,7 +1309,7 @@ xfs_xattr_iomap_begin(
>  	if (error)
>  		return error;
>  	ASSERT(nimaps);
> -	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
> +	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
>  }
>  
>  const struct iomap_ops xfs_xattr_iomap_ops = {
> diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
> index f1a281ab9328c..657cc02290f22 100644
> --- a/fs/xfs/xfs_iomap.h
> +++ b/fs/xfs/xfs_iomap.h
> @@ -17,8 +17,9 @@ int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
>  xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
>  		xfs_fileoff_t end_fsb);
>  
> -int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
> -		struct xfs_bmbt_irec *, u16);
> +int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap,
> +		struct xfs_bmbt_irec *imap, unsigned int mapping_flags,
> +		u16 iomap_flags);
>  
>  int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len,
>  		bool *did_zero);
> diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
> index 5e1d29d8b2e73..7ce1ea11fc3f3 100644
> --- a/fs/xfs/xfs_pnfs.c
> +++ b/fs/xfs/xfs_pnfs.c
> @@ -173,7 +173,7 @@ xfs_fs_map_blocks(
>  	}
>  	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
>  
> -	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
> +	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0);
>  	*device_generation = mp->m_generation;
>  	return error;
>  out_unlock:
> -- 
> 2.30.2
> 

Re: [PATCH 24/29] iomap: add a IOMAP_DAX flag

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:58AM +0100, Christoph Hellwig wrote:
> Add a flag so that the file system can easily detect DAX operations
> based just on the iomap operation requested instead of looking at
> inode state using IS_DAX.  This will be needed to apply the to be
> added partition offset only for operations that actually use DAX,
> but not things like fiemap that are based on the block device.
> In the long run it should also allow turning the bdev, dax_dev
> and inline_data into a union.

Heh. :)

Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Dan Williams <dan.j.williams@intel.com>
> ---
>  fs/dax.c              | 7 ++++---
>  fs/ext4/inode.c       | 4 ++--
>  fs/xfs/xfs_iomap.c    | 7 ++++---
>  fs/xfs/xfs_iomap.h    | 3 ++-
>  fs/xfs/xfs_pnfs.c     | 2 +-
>  include/linux/iomap.h | 5 +++++
>  6 files changed, 18 insertions(+), 10 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 43d58b4219fd0..148e8b0967f35 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1180,7 +1180,7 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
>  		.inode		= inode,
>  		.pos		= pos,
>  		.len		= len,
> -		.flags		= IOMAP_ZERO,
> +		.flags		= IOMAP_DAX | IOMAP_ZERO,
>  	};
>  	int ret;
>  
> @@ -1308,6 +1308,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
>  		.inode		= iocb->ki_filp->f_mapping->host,
>  		.pos		= iocb->ki_pos,
>  		.len		= iov_iter_count(iter),
> +		.flags		= IOMAP_DAX,
>  	};
>  	loff_t done = 0;
>  	int ret;
> @@ -1461,7 +1462,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  		.inode		= mapping->host,
>  		.pos		= (loff_t)vmf->pgoff << PAGE_SHIFT,
>  		.len		= PAGE_SIZE,
> -		.flags		= IOMAP_FAULT,
> +		.flags		= IOMAP_DAX | IOMAP_FAULT,
>  	};
>  	vm_fault_t ret = 0;
>  	void *entry;
> @@ -1570,7 +1571,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  	struct iomap_iter iter = {
>  		.inode		= mapping->host,
>  		.len		= PMD_SIZE,
> -		.flags		= IOMAP_FAULT,
> +		.flags		= IOMAP_DAX | IOMAP_FAULT,
>  	};
>  	vm_fault_t ret = VM_FAULT_FALLBACK;
>  	pgoff_t max_pgoff;
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index d316a2009489b..89c4a174bd393 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3349,8 +3349,8 @@ static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
>  	 * DAX and direct I/O are the only two operations that are currently
>  	 * supported with IOMAP_WRITE.
>  	 */
> -	WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
> -	if (IS_DAX(inode))
> +	WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
> +	if (flags & IOMAP_DAX)
>  		m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
>  	/*
>  	 * We use i_size instead of i_disksize here because delalloc writeback
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index d6beb1502f8bc..0ed3e7674353b 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -188,6 +188,7 @@ xfs_iomap_write_direct(
>  	struct xfs_inode	*ip,
>  	xfs_fileoff_t		offset_fsb,
>  	xfs_fileoff_t		count_fsb,
> +	unsigned int		flags,
>  	struct xfs_bmbt_irec	*imap)
>  {
>  	struct xfs_mount	*mp = ip->i_mount;
> @@ -229,7 +230,7 @@ xfs_iomap_write_direct(
>  	 * the reserve block pool for bmbt block allocation if there is no space
>  	 * left but we need to do unwritten extent conversion.
>  	 */
> -	if (IS_DAX(VFS_I(ip))) {
> +	if (flags & IOMAP_DAX) {
>  		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
>  		if (imap->br_state == XFS_EXT_UNWRITTEN) {
>  			force = true;
> @@ -620,7 +621,7 @@ imap_needs_alloc(
>  	    imap->br_startblock == DELAYSTARTBLOCK)
>  		return true;
>  	/* we convert unwritten extents before copying the data for DAX */
> -	if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN)
> +	if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN)
>  		return true;
>  	return false;
>  }
> @@ -826,7 +827,7 @@ xfs_direct_write_iomap_begin(
>  	xfs_iunlock(ip, lockmode);
>  
>  	error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb,
> -			&imap);
> +			flags, &imap);
>  	if (error)
>  		return error;
>  
> diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
> index 657cc02290f22..e88dc162c785e 100644
> --- a/fs/xfs/xfs_iomap.h
> +++ b/fs/xfs/xfs_iomap.h
> @@ -12,7 +12,8 @@ struct xfs_inode;
>  struct xfs_bmbt_irec;
>  
>  int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
> -		xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap);
> +		xfs_fileoff_t count_fsb, unsigned int flags,
> +		struct xfs_bmbt_irec *imap);
>  int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
>  xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
>  		xfs_fileoff_t end_fsb);
> diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
> index 7ce1ea11fc3f3..d6334abbc0b3e 100644
> --- a/fs/xfs/xfs_pnfs.c
> +++ b/fs/xfs/xfs_pnfs.c
> @@ -155,7 +155,7 @@ xfs_fs_map_blocks(
>  		xfs_iunlock(ip, lock_flags);
>  
>  		error = xfs_iomap_write_direct(ip, offset_fsb,
> -				end_fsb - offset_fsb, &imap);
> +				end_fsb - offset_fsb, 0, &imap);
>  		if (error)
>  			goto out_unlock;
>  
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 6d1b08d0ae930..5b9432f9f79eb 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h
> @@ -141,6 +141,11 @@ struct iomap_page_ops {
>  #define IOMAP_NOWAIT		(1 << 5) /* do not block */
>  #define IOMAP_OVERWRITE_ONLY	(1 << 6) /* only pure overwrites allowed */
>  #define IOMAP_UNSHARE		(1 << 7) /* unshare_file_range */
> +#ifdef CONFIG_FS_DAX
> +#define IOMAP_DAX		(1 << 8) /* DAX mapping */
> +#else
> +#define IOMAP_DAX		0
> +#endif /* CONFIG_FS_DAX */
>  
>  struct iomap_ops {
>  	/*
> -- 
> 2.30.2
> 

Re: [PATCH 25/29] dax: return the partition offset from fs_dax_get_by_bdev

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:21:59AM +0100, Christoph Hellwig wrote:
> 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>

--D

> ---
>  drivers/dax/super.c | 9 ++++++---
>  drivers/md/dm.c     | 4 ++--
>  fs/erofs/internal.h | 2 ++
>  fs/erofs/super.c    | 4 ++--
>  fs/ext2/ext2.h      | 1 +
>  fs/ext2/super.c     | 2 +-
>  fs/ext4/ext4.h      | 1 +
>  fs/ext4/super.c     | 2 +-
>  fs/xfs/xfs_buf.c    | 2 +-
>  fs/xfs/xfs_buf.h    | 1 +
>  include/linux/dax.h | 6 ++++--
>  11 files changed, 22 insertions(+), 12 deletions(-)
> 
> diff --git a/drivers/dax/super.c b/drivers/dax/super.c
> index 45d931aefd063..e7152a6c4cc40 100644
> --- 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 4eba27e75c230..4e997c02bb0a0 100644
> --- 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 3265688af7f9f..c1e65346e9f15 100644
> --- 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 0aed886473c8d..71efce16024d9 100644
> --- 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 3be9dd6412b78..d4f306aa5aceb 100644
> --- 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 7e23482862e69..94f1fbd7d3ac2 100644
> --- 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 404dd50856e5d..9cc55bcda6ba4 100644
> --- 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 8d7e3449c6472..56228e33e52a2 100644
> --- 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 4d4553ffa7050..bbb0fbd34e649 100644
> --- 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 bd7f709f0d232..edcb6254fa6a8 100644
> --- 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 b79036743e7fa..f6f353382cc90 100644
> --- 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;
>  }
> -- 
> 2.30.2
> 

Re: [PATCH 26/29] fsdax: shift partition offset handling into the file systems

[Darrick J. Wong]

On Mon, Nov 29, 2021 at 11:22:00AM +0100, Christoph Hellwig wrote:
> Remove the last user of ->bdev in dax.c by requiring the file system to
> pass in an address that already includes the DAX offset.  As part of the
> only set ->bdev or ->daxdev when actually required in the ->iomap_begin
> methods.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com> [erofs]

Looks like a straightfoward conversion.  In addition to reviewing the
xfs parts, I spot-checked the ext* bits and didn't see anything
obviously wrong there, but you might want to get an ack from Ted and
Jan.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> ---
>  fs/dax.c            |  6 +-----
>  fs/erofs/data.c     | 11 +++++++++--
>  fs/erofs/internal.h |  1 +
>  fs/ext2/inode.c     |  8 ++++++--
>  fs/ext4/inode.c     | 16 +++++++++++-----
>  fs/xfs/xfs_iomap.c  | 10 ++++++++--
>  6 files changed, 36 insertions(+), 16 deletions(-)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index 148e8b0967f35..e0eecd8e3a8f8 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -711,11 +711,7 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
>  
>  static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
>  {
> -	phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset;
> -
> -	if (iomap->bdev)
> -		paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT);
> -	return PHYS_PFN(paddr);
> +	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
>  }
>  
>  static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
> diff --git a/fs/erofs/data.c b/fs/erofs/data.c
> index 0e35ef3f9f3d7..9b1bb177ce303 100644
> --- a/fs/erofs/data.c
> +++ b/fs/erofs/data.c
> @@ -159,6 +159,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
>  	/* primary device by default */
>  	map->m_bdev = sb->s_bdev;
>  	map->m_daxdev = EROFS_SB(sb)->dax_dev;
> +	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
>  
>  	if (map->m_deviceid) {
>  		down_read(&devs->rwsem);
> @@ -169,6 +170,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
>  		}
>  		map->m_bdev = dif->bdev;
>  		map->m_daxdev = dif->dax_dev;
> +		map->m_dax_part_off = dif->dax_part_off;
>  		up_read(&devs->rwsem);
>  	} else if (devs->extra_devices) {
>  		down_read(&devs->rwsem);
> @@ -185,6 +187,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
>  				map->m_pa -= startoff;
>  				map->m_bdev = dif->bdev;
>  				map->m_daxdev = dif->dax_dev;
> +				map->m_dax_part_off = dif->dax_part_off;
>  				break;
>  			}
>  		}
> @@ -215,9 +218,13 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  	if (ret)
>  		return ret;
>  
> -	iomap->bdev = mdev.m_bdev;
> -	iomap->dax_dev = mdev.m_daxdev;
>  	iomap->offset = map.m_la;
> +	if (flags & IOMAP_DAX) {
> +		iomap->dax_dev = mdev.m_daxdev;
> +		iomap->offset += mdev.m_dax_part_off;
> +	} else {
> +		iomap->bdev = mdev.m_bdev;
> +	}
>  	iomap->length = map.m_llen;
>  	iomap->flags = 0;
>  	iomap->private = NULL;
> diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
> index c1e65346e9f15..5c2a83876220c 100644
> --- a/fs/erofs/internal.h
> +++ b/fs/erofs/internal.h
> @@ -438,6 +438,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
>  struct erofs_map_dev {
>  	struct block_device *m_bdev;
>  	struct dax_device *m_daxdev;
> +	u64 m_dax_part_off;
>  
>  	erofs_off_t m_pa;
>  	unsigned int m_deviceid;
> diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
> index 01d69618277de..602578b72d8c5 100644
> --- a/fs/ext2/inode.c
> +++ b/fs/ext2/inode.c
> @@ -817,9 +817,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  		return ret;
>  
>  	iomap->flags = 0;
> -	iomap->bdev = inode->i_sb->s_bdev;
>  	iomap->offset = (u64)first_block << blkbits;
> -	iomap->dax_dev = sbi->s_daxdev;
> +	if (flags & IOMAP_DAX)
> +		iomap->dax_dev = sbi->s_daxdev;
> +	else
> +		iomap->bdev = inode->i_sb->s_bdev;
>  
>  	if (ret == 0) {
>  		iomap->type = IOMAP_HOLE;
> @@ -828,6 +830,8 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  	} else {
>  		iomap->type = IOMAP_MAPPED;
>  		iomap->addr = (u64)bno << blkbits;
> +		if (flags & IOMAP_DAX)
> +			iomap->addr += sbi->s_dax_part_off;
>  		iomap->length = (u64)ret << blkbits;
>  		iomap->flags |= IOMAP_F_MERGED;
>  	}
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 89c4a174bd393..ccafcbc146d3e 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -3272,7 +3272,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
>  
>  static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
>  			   struct ext4_map_blocks *map, loff_t offset,
> -			   loff_t length)
> +			   loff_t length, unsigned int flags)
>  {
>  	u8 blkbits = inode->i_blkbits;
>  
> @@ -3289,8 +3289,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
>  	if (map->m_flags & EXT4_MAP_NEW)
>  		iomap->flags |= IOMAP_F_NEW;
>  
> -	iomap->bdev = inode->i_sb->s_bdev;
> -	iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
> +	if (flags & IOMAP_DAX)
> +		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
> +	else
> +		iomap->bdev = inode->i_sb->s_bdev;
>  	iomap->offset = (u64) map->m_lblk << blkbits;
>  	iomap->length = (u64) map->m_len << blkbits;
>  
> @@ -3310,9 +3312,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
>  	if (map->m_flags & EXT4_MAP_UNWRITTEN) {
>  		iomap->type = IOMAP_UNWRITTEN;
>  		iomap->addr = (u64) map->m_pblk << blkbits;
> +		if (flags & IOMAP_DAX)
> +			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
>  	} else if (map->m_flags & EXT4_MAP_MAPPED) {
>  		iomap->type = IOMAP_MAPPED;
>  		iomap->addr = (u64) map->m_pblk << blkbits;
> +		if (flags & IOMAP_DAX)
> +			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
>  	} else {
>  		iomap->type = IOMAP_HOLE;
>  		iomap->addr = IOMAP_NULL_ADDR;
> @@ -3421,7 +3427,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
>  	if (ret < 0)
>  		return ret;
>  out:
> -	ext4_set_iomap(inode, iomap, &map, offset, length);
> +	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
>  
>  	return 0;
>  }
> @@ -3541,7 +3547,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
>  		delalloc = ext4_iomap_is_delalloc(inode, &map);
>  
>  set_iomap:
> -	ext4_set_iomap(inode, iomap, &map, offset, length);
> +	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
>  	if (delalloc && iomap->type == IOMAP_HOLE)
>  		iomap->type = IOMAP_DELALLOC;
>  
> diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
> index 0ed3e7674353b..e552ce541ec2d 100644
> --- a/fs/xfs/xfs_iomap.c
> +++ b/fs/xfs/xfs_iomap.c
> @@ -71,15 +71,21 @@ xfs_bmbt_to_iomap(
>  		iomap->type = IOMAP_DELALLOC;
>  	} else {
>  		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
> +		if (mapping_flags & IOMAP_DAX)
> +			iomap->addr += target->bt_dax_part_off;
> +
>  		if (imap->br_state == XFS_EXT_UNWRITTEN)
>  			iomap->type = IOMAP_UNWRITTEN;
>  		else
>  			iomap->type = IOMAP_MAPPED;
> +
>  	}
>  	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
>  	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
> -	iomap->bdev = target->bt_bdev;
> -	iomap->dax_dev = target->bt_daxdev;
> +	if (mapping_flags & IOMAP_DAX)
> +		iomap->dax_dev = target->bt_daxdev;
> +	else
> +		iomap->bdev = target->bt_bdev;
>  	iomap->flags = iomap_flags;
>  
>  	if (xfs_ipincount(ip) &&
> -- 
> 2.30.2
> 

Re: [PATCH 17/29] fsdax: factor out a dax_memzero helper

[Christoph Hellwig]

On Tue, Nov 23, 2021 at 01:22:13PM -0800, Dan Williams wrote:
> On Tue, Nov 9, 2021 at 12:34 AM Christoph Hellwig <hch@lst.de> wrote:
> >
> > Factor out a helper for the "manual" zeroing of a DAX range to clean
> > up dax_iomap_zero a lot.
> >
> 
> Small / optional fixup below:

Incorporated.

Re: [PATCH 17/29] fsdax: factor out a dax_memzero helper

[Darrick J. Wong]

On Tue, Nov 23, 2021 at 01:22:13PM -0800, Dan Williams wrote:
> On Tue, Nov 9, 2021 at 12:34 AM Christoph Hellwig <hch@lst.de> wrote:
> >
> > Factor out a helper for the "manual" zeroing of a DAX range to clean
> > up dax_iomap_zero a lot.
> >
> 
> Small / optional fixup below:
> 
> Reviewed-by: Dan Williams <dan.j.williams@intel.com>
> 
> > Signed-off-by: Christoph Hellwig <hch@lst.de>
> > ---
> >  fs/dax.c | 36 +++++++++++++++++++-----------------
> >  1 file changed, 19 insertions(+), 17 deletions(-)
> >
> > diff --git a/fs/dax.c b/fs/dax.c
> > index d7a923d152240..dc9ebeff850ab 100644
> > --- a/fs/dax.c
> > +++ b/fs/dax.c
> > @@ -1121,34 +1121,36 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
> >  }
> >  #endif /* CONFIG_FS_DAX_PMD */
> >
> > +static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
> > +               unsigned int offset, size_t size)
> > +{
> > +       void *kaddr;
> > +       long rc;
> > +
> > +       rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
> > +       if (rc >= 0) {
> 
> Technically this should be "> 0" because dax_direct_access() returns
> nr_available_pages @pgoff, but this isn't broken because
> dax_direct_access() converts the "zero pages available" case into
> -ERANGE.

Agreed.  With that fixed,
Reviewed-by: Darrick J. Wong <djwong@kernel.org>

--D

> 
> > +               memset(kaddr + offset, 0, size);
> > +               dax_flush(dax_dev, kaddr + offset, size);
> > +       }
> > +       return rc;
> > +}
> > +
> >  s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
> >  {
> >         pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
> >         long rc, id;
> > -       void *kaddr;
> > -       bool page_aligned = false;
> >         unsigned offset = offset_in_page(pos);
> >         unsigned size = min_t(u64, PAGE_SIZE - offset, length);
> >
> > -       if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
> > -               page_aligned = true;
> > -
> >         id = dax_read_lock();
> > -
> > -       if (page_aligned)
> > +       if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
> >                 rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
> >         else
> > -               rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
> > -       if (rc < 0) {
> > -               dax_read_unlock(id);
> > -               return rc;
> > -       }
> > -
> > -       if (!page_aligned) {
> > -               memset(kaddr + offset, 0, size);
> > -               dax_flush(iomap->dax_dev, kaddr + offset, size);
> > -       }
> > +               rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
> >         dax_read_unlock(id);
> > +
> > +       if (rc < 0)
> > +               return rc;
> >         return size;
> >  }
> >
> > --
> > 2.30.2
> >

Re: [PATCH 17/29] fsdax: factor out a dax_memzero helper

[Dan Williams]

On Tue, Nov 9, 2021 at 12:34 AM Christoph Hellwig <hch@lst.de> wrote:
>
> Factor out a helper for the "manual" zeroing of a DAX range to clean
> up dax_iomap_zero a lot.
>

Small / optional fixup below:

Reviewed-by: Dan Williams <dan.j.williams@intel.com>

> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  fs/dax.c | 36 +++++++++++++++++++-----------------
>  1 file changed, 19 insertions(+), 17 deletions(-)
>
> diff --git a/fs/dax.c b/fs/dax.c
> index d7a923d152240..dc9ebeff850ab 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1121,34 +1121,36 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
>  }
>  #endif /* CONFIG_FS_DAX_PMD */
>
> +static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
> +               unsigned int offset, size_t size)
> +{
> +       void *kaddr;
> +       long rc;
> +
> +       rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
> +       if (rc >= 0) {

Technically this should be "> 0" because dax_direct_access() returns
nr_available_pages @pgoff, but this isn't broken because
dax_direct_access() converts the "zero pages available" case into
-ERANGE.

> +               memset(kaddr + offset, 0, size);
> +               dax_flush(dax_dev, kaddr + offset, size);
> +       }
> +       return rc;
> +}
> +
>  s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
>  {
>         pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
>         long rc, id;
> -       void *kaddr;
> -       bool page_aligned = false;
>         unsigned offset = offset_in_page(pos);
>         unsigned size = min_t(u64, PAGE_SIZE - offset, length);
>
> -       if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
> -               page_aligned = true;
> -
>         id = dax_read_lock();
> -
> -       if (page_aligned)
> +       if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
>                 rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
>         else
> -               rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
> -       if (rc < 0) {
> -               dax_read_unlock(id);
> -               return rc;
> -       }
> -
> -       if (!page_aligned) {
> -               memset(kaddr + offset, 0, size);
> -               dax_flush(iomap->dax_dev, kaddr + offset, size);
> -       }
> +               rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
>         dax_read_unlock(id);
> +
> +       if (rc < 0)
> +               return rc;
>         return size;
>  }
>
> --
> 2.30.2
>

[PATCH 17/29] fsdax: factor out a dax_memzero helper

[Christoph Hellwig]

Factor out a helper for the "manual" zeroing of a DAX range to clean
up dax_iomap_zero a lot.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/dax.c | 36 +++++++++++++++++++-----------------
 1 file changed, 19 insertions(+), 17 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d7a923d152240..dc9ebeff850ab 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1121,34 +1121,36 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 }
 #endif /* CONFIG_FS_DAX_PMD */
 
+static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
+		unsigned int offset, size_t size)
+{
+	void *kaddr;
+	long rc;
+
+	rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	if (rc >= 0) {
+		memset(kaddr + offset, 0, size);
+		dax_flush(dax_dev, kaddr + offset, size);
+	}
+	return rc;
+}
+
 s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 {
 	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	long rc, id;
-	void *kaddr;
-	bool page_aligned = false;
 	unsigned offset = offset_in_page(pos);
 	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
-	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
-		page_aligned = true;
-
 	id = dax_read_lock();
-
-	if (page_aligned)
+	if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
 		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
-		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
-	if (rc < 0) {
-		dax_read_unlock(id);
-		return rc;
-	}
-
-	if (!page_aligned) {
-		memset(kaddr + offset, 0, size);
-		dax_flush(iomap->dax_dev, kaddr + offset, size);
-	}
+		rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
 	dax_read_unlock(id);
+
+	if (rc < 0)
+		return rc;
 	return size;
 }
 
-- 
2.30.2