dax: remove the copy_from_iter and copy_to_iter methods

These methods indirect the actual DAX read/write path. In the end pmem
uses magic flush and mc safe variants and fuse and dcssblk use plain ones
while device mapper picks redirects to the underlying device.

Add set_dax_nocache() and set_dax_nomc() APIs to control which copy
routines are used to remove indirect call from the read/write fast path
as well as a lot of boilerplate code.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Vivek Goyal <[e-mail]> [virtiofs]
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Dan Williams <[e-mail]>

drivers/dax/bus.c

···
 		goto err_alloc_dax;
 	}
 	set_dax_synchronous(dax_dev);
+	set_dax_nocache(dax_dev);
+	set_dax_nomc(dax_dev);
 
 	/* a device_dax instance is dead while the driver is not attached */
 	kill_dax(dax_dev);

drivers/dax/super.c

···
 	DAXDEV_WRITE_CACHE,
 	/* flag to check if device supports synchronous flush */
 	DAXDEV_SYNC,
+	/* do not leave the caches dirty after writes */
+	DAXDEV_NOCACHE,
+	/* handle CPU fetch exceptions during reads */
+	DAXDEV_NOMC,
 };
 
 /**
···
 	if (!dax_alive(dax_dev))
 		return 0;
 
-	return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+	/*
+	 * The userspace address for the memory copy has already been validated
+	 * via access_ok() in vfs_write, so use the 'no check' version to bypass
+	 * the HARDENED_USERCOPY overhead.
+	 */
+	if (test_bit(DAXDEV_NOCACHE, &dax_dev->flags))
+		return _copy_from_iter_flushcache(addr, bytes, i);
+	return _copy_from_iter(addr, bytes, i);
 }
-EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i)
···
 	if (!dax_alive(dax_dev))
 		return 0;
 
-	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+	/*
+	 * The userspace address for the memory copy has already been validated
+	 * via access_ok() in vfs_red, so use the 'no check' version to bypass
+	 * the HARDENED_USERCOPY overhead.
+	 */
+	if (test_bit(DAXDEV_NOMC, &dax_dev->flags))
+		return _copy_mc_to_iter(addr, bytes, i);
+	return _copy_to_iter(addr, bytes, i);
 }
-EXPORT_SYMBOL_GPL(dax_copy_to_iter);
 
 int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 			size_t nr_pages)
···
 	set_bit(DAXDEV_SYNC, &dax_dev->flags);
 }
 EXPORT_SYMBOL_GPL(set_dax_synchronous);
+
+void set_dax_nocache(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_NOCACHE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(set_dax_nocache);
+
+void set_dax_nomc(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_NOMC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(set_dax_nomc);
 
 bool dax_alive(struct dax_device *dax_dev)
 {

drivers/md/dm-linear.c

···
 	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 dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
-
-	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 dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
-
-	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)
 {
···
 
 #else
 #define linear_dax_direct_access NULL
-#define linear_dax_copy_from_iter NULL
-#define linear_dax_copy_to_iter NULL
 #define linear_dax_zero_page_range NULL
 #endif
 
···
 	.prepare_ioctl = linear_prepare_ioctl,
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
-	.dax_copy_from_iter = linear_dax_copy_from_iter,
-	.dax_copy_to_iter = linear_dax_copy_to_iter,
 	.dax_zero_page_range = linear_dax_zero_page_range,
 };
 

drivers/md/dm-log-writes.c

···
 }
 
 #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)
-{
-	struct pending_block *block;
-
-	if (!bytes)
-		return 0;
-
-	block = kzalloc(sizeof(struct pending_block), GFP_KERNEL);
-	if (!block) {
-		DMERR("Error allocating dax pending block");
-		return -ENOMEM;
-	}
-
-	block->data = kzalloc(bytes, GFP_KERNEL);
-	if (!block->data) {
-		DMERR("Error allocating dax data space");
-		kfree(block);
-		return -ENOMEM;
-	}
-
-	/* write data provided via the iterator */
-	if (!copy_from_iter(block->data, bytes, i)) {
-		DMERR("Error copying dax data");
-		kfree(block->data);
-		kfree(block);
-		return -EIO;
-	}
-
-	/* rewind the iterator so that the block driver can use it */
-	iov_iter_revert(i, bytes);
-
-	block->datalen = bytes;
-	block->sector = bio_to_dev_sectors(lc, sector);
-	block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift;
-
-	atomic_inc(&lc->pending_blocks);
-	spin_lock_irq(&lc->blocks_lock);
-	list_add_tail(&block->list, &lc->unflushed_blocks);
-	spin_unlock_irq(&lc->blocks_lock);
-	wake_up_process(lc->log_kthread);
-
-	return 0;
-}
-
 static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
 		pgoff_t *pgoff)
 {
···
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
-static size_t log_writes_dax_copy_from_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);
-	int err;
-
-	/* Don't bother doing anything if logging has been disabled */
-	if (!lc->logging_enabled)
-		goto dax_copy;
-
-	err = log_dax(lc, sector, bytes, i);
-	if (err) {
-		DMWARN("Error %d logging DAX write", err);
-		return 0;
-	}
-dax_copy:
-	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 dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
-
-	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)
 {
···
 
 #else
 #define log_writes_dax_direct_access NULL
-#define log_writes_dax_copy_from_iter NULL
-#define log_writes_dax_copy_to_iter NULL
 #define log_writes_dax_zero_page_range NULL
 #endif
 
···
 	.iterate_devices = log_writes_iterate_devices,
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
-	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
-	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
 	.dax_zero_page_range = log_writes_dax_zero_page_range,
 };
 

drivers/md/dm-stripe.c

···
 	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)
-{
-	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
-
-	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)
-{
-	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
-
-	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)
 {
···
 
 #else
 #define stripe_dax_direct_access NULL
-#define stripe_dax_copy_from_iter NULL
-#define stripe_dax_copy_to_iter NULL
 #define stripe_dax_zero_page_range NULL
 #endif
 
···
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
-	.dax_copy_from_iter = stripe_dax_copy_from_iter,
-	.dax_copy_to_iter = stripe_dax_copy_to_iter,
 	.dax_zero_page_range = stripe_dax_zero_page_range,
 };
 

drivers/md/dm.c

···
 	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)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	sector_t sector = pgoff * PAGE_SECTORS;
-	struct dm_target *ti;
-	long ret = 0;
-	int srcu_idx;
-
-	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
-
-	if (!ti)
-		goto out;
-	if (!ti->type->dax_copy_from_iter) {
-		ret = copy_from_iter(addr, bytes, i);
-		goto out;
-	}
-	ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
- out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
-static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	sector_t sector = pgoff * PAGE_SECTORS;
-	struct dm_target *ti;
-	long ret = 0;
-	int srcu_idx;
-
-	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
-
-	if (!ti)
-		goto out;
-	if (!ti->type->dax_copy_to_iter) {
-		ret = copy_to_iter(addr, bytes, i);
-		goto out;
-	}
-	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
- out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
 static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 				  size_t nr_pages)
 {
···
 			md->dax_dev = NULL;
 			goto bad;
 		}
+		set_dax_nocache(md->dax_dev);
+		set_dax_nomc(md->dax_dev);
 		if (dax_add_host(md->dax_dev, md->disk))
 			goto bad;
 	}
···
 
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
-	.copy_from_iter = dm_dax_copy_from_iter,
-	.copy_to_iter = dm_dax_copy_to_iter,
 	.zero_page_range = dm_dax_zero_page_range,
 };
 

drivers/nvdimm/pmem.c

···
 	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
 }
 
-/*
- * Bounds checking, both file offset and device offset, is handled by
- * dax_iomap_actor()
- */
-static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return _copy_from_iter_flushcache(addr, bytes, i);
-}
-
-static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return _copy_mc_to_iter(addr, bytes, i);
-}
-
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
-	.copy_from_iter = pmem_copy_from_iter,
-	.copy_to_iter = pmem_copy_to_iter,
 	.zero_page_range = pmem_dax_zero_page_range,
 };
 
···
 		rc = PTR_ERR(dax_dev);
 		goto out;
 	}
+	set_dax_nocache(dax_dev);
+	set_dax_nomc(dax_dev);
 	if (is_nvdimm_sync(nd_region))
 		set_dax_synchronous(dax_dev);
 	rc = dax_add_host(dax_dev, disk);

drivers/s390/block/dcssblk.c

···
 	.release 	= dcssblk_release,
 };
 
-static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev,
-		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
-		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_to_iter(addr, bytes, i);
-}
-
 static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 				       pgoff_t pgoff, size_t nr_pages)
 {
···
 
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
-	.copy_from_iter = dcssblk_dax_copy_from_iter,
-	.copy_to_iter = dcssblk_dax_copy_to_iter,
 	.zero_page_range = dcssblk_dax_zero_page_range,
 };
 

fs/dax.c

···
 		if (map_len > end - pos)
 			map_len = end - pos;
 
-		/*
-		 * The userspace address for the memory copy has already been
-		 * validated via access_ok() in either vfs_read() or
-		 * vfs_write(), depending on which operation we are doing.
-		 */
 		if (iov_iter_rw(iter) == WRITE)
 			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);

fs/fuse/virtio_fs.c

···
 	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
 }
 
-static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
-				       pgoff_t pgoff, void *addr,
-				       size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
-				       pgoff_t pgoff, void *addr,
-				       size_t bytes, struct iov_iter *i)
-{
-	return copy_to_iter(addr, bytes, i);
-}
-
 static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 				     pgoff_t pgoff, size_t nr_pages)
 {
···
 
 static const struct dax_operations virtio_fs_dax_ops = {
 	.direct_access = virtio_fs_direct_access,
-	.copy_from_iter = virtio_fs_copy_from_iter,
-	.copy_to_iter = virtio_fs_copy_to_iter,
 	.zero_page_range = virtio_fs_zero_page_range,
 };
 

include/linux/dax.h

···
 	 */
 	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
 			sector_t, sector_t);
-	/* copy_from_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
-	/* copy_to_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 };
···
 	return !(vma->vm_flags & VM_SYNC);
 }
 #endif
+
+void set_dax_nocache(struct dax_device *dax_dev);
+void set_dax_nomc(struct dax_device *dax_dev);
 
 struct writeback_control;
 #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)

include/linux/device-mapper.h

···
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
-typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
···
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
-	dm_dax_copy_iter_fn dax_copy_from_iter;
-	dm_dax_copy_iter_fn dax_copy_to_iter;
 	dm_dax_zero_page_range_fn dax_zero_page_range;
 
 	/* For internal device-mapper use. */