[PATCH 2/6] dax: prepare dax_direct_access() API with DAXDEV_F_RECOVERY flag

From: Jane Chu <jane.chu@oracle.com>
To: david@fromorbit.com, djwong@kernel.org, dan.j.williams@intel.com,
	hch@infradead.org, vishal.l.verma@intel.com,
	dave.jiang@intel.com, agk@redhat.com, snitzer@redhat.com,
	dm-devel@redhat.com, ira.weiny@intel.com, willy@infradead.org,
	vgoyal@redhat.com, linux-fsdevel@vger.kernel.org,
	nvdimm@lists.linux.dev, linux-kernel@vger.kernel.org,
	linux-xfs@vger.kernel.org
Subject: [PATCH 2/6] dax: prepare dax_direct_access() API with DAXDEV_F_RECOVERY flag
Date: Wed, 20 Oct 2021 18:10:55 -0600	[thread overview]
Message-ID: <20211021001059.438843-3-jane.chu@oracle.com> (raw)
In-Reply-To: <20211021001059.438843-1-jane.chu@oracle.com>

Prepare dax_direct_access() API with DAXDEV_F_RECOVERY flag
such that the API may perform device address translation
in spite of the presence of poison(s) in a given range.

Signed-off-by: Jane Chu <jane.chu@oracle.com>
---
 drivers/dax/super.c             |  9 +++++----
 drivers/md/dm-linear.c          |  4 ++--
 drivers/md/dm-log-writes.c      |  5 +++--
 drivers/md/dm-stripe.c          |  4 ++--
 drivers/md/dm-target.c          |  2 +-
 drivers/md/dm-writecache.c      |  4 ++--
 drivers/md/dm.c                 |  4 ++--
 drivers/nvdimm/pmem.c           |  7 ++++---
 drivers/nvdimm/pmem.h           |  2 +-
 drivers/s390/block/dcssblk.c    |  7 ++++---
 fs/dax.c                        | 12 ++++++++----
 fs/fuse/dax.c                   |  2 +-
 fs/fuse/virtio_fs.c             |  4 ++--
 include/linux/dax.h             |  7 +++++--
 include/linux/device-mapper.h   |  2 +-
 tools/testing/nvdimm/pmem-dax.c |  2 +-
 16 files changed, 44 insertions(+), 33 deletions(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index fc89e91beea7..67093f1c3341 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -156,8 +156,8 @@ bool generic_fsdax_supported(struct dax_device *dax_dev,
 	}
 
 	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);
+	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn, 0);
+	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn, 0);
 
 	if (len < 1 || len2 < 1) {
 		pr_info("%pg: error: dax access failed (%ld)\n",
@@ -302,12 +302,13 @@ EXPORT_SYMBOL_GPL(dax_attribute_group);
  * @nr_pages: number of consecutive pages caller can handle relative to @pfn
  * @kaddr: output parameter that returns a virtual address mapping of pfn
  * @pfn: output parameter that returns an absolute pfn translation of @pgoff
+ * @flags: indication whether on dax data recovery code path or not
  *
  * Return: negative errno if an error occurs, otherwise the number of
  * pages accessible at the device relative @pgoff.
  */
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn)
+		void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	long avail;
 
@@ -321,7 +322,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		return -EINVAL;
 
 	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
-			kaddr, pfn);
+			kaddr, pfn, flags);
 	if (!avail)
 		return -ERANGE;
 	return min(avail, nr_pages);
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 679b4c0a2eea..cb7c8518f02d 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -165,7 +165,7 @@ static int linear_iterate_devices(struct dm_target *ti,
 
 #if IS_ENABLED(CONFIG_DAX_DRIVER)
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	long ret;
 	struct linear_c *lc = ti->private;
@@ -177,7 +177,7 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
 	if (ret)
 		return ret;
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn, flags);
 }
 
 static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index d93a4db23512..6d8b88dcce6c 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -950,7 +950,7 @@ static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes,
 }
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-					 long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	struct log_writes_c *lc = ti->private;
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -959,7 +959,8 @@ static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t 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(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn,
+				 flags);
 }
 
 static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 6660b6b53d5b..0a97d0472a0b 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -302,7 +302,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 
 #if IS_ENABLED(CONFIG_DAX_DRIVER)
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
 	struct stripe_c *sc = ti->private;
@@ -319,7 +319,7 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
 	if (ret)
 		return ret;
-	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn, flags);
 }
 
 static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 64dd0b34fcf4..431764b77528 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -142,7 +142,7 @@ static void io_err_release_clone_rq(struct request *clone,
 }
 
 static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	return -EIO;
 }
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 18320444fb0a..c523cb911eca 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -286,7 +286,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 
 	id = dax_read_lock();
 
-	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn);
+	da = dax_direct_access(wc->ssd_dev->dax_dev, offset, p, &wc->memory_map, &pfn, 0);
 	if (da < 0) {
 		wc->memory_map = NULL;
 		r = da;
@@ -309,7 +309,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		do {
 			long daa;
 			daa = dax_direct_access(wc->ssd_dev->dax_dev, offset + i, p - i,
-						NULL, &pfn);
+						NULL, &pfn, 0);
 			if (daa <= 0) {
 				r = daa ? daa : -EINVAL;
 				goto err3;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a011d09cb0fa..e5a14abd45f9 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -998,7 +998,7 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
 }
 
 static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				 long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
@@ -1016,7 +1016,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (len < 1)
 		goto out;
 	nr_pages = min(len, nr_pages);
-	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn);
+	ret = ti->type->direct_access(ti, pgoff, nr_pages, kaddr, pfn, flags);
 
  out:
 	dm_put_live_table(md, srcu_idx);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 72de88ff0d30..b0b7fd40560e 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -256,7 +256,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
@@ -295,11 +295,12 @@ static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 }
 
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
-		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
+		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn,
+		unsigned long flags)
 {
 	struct pmem_device *pmem = dax_get_private(dax_dev);
 
-	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
+	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn, flags);
 }
 
 /*
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 59cfe13ea8a8..fb769b22777a 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -27,7 +27,7 @@ struct pmem_device {
 };
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags);
 
 #ifdef CONFIG_MEMORY_FAILURE
 static inline bool test_and_clear_pmem_poison(struct page *page)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 5be3d1c39a78..6ab2f9badc8d 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -32,7 +32,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static blk_qc_t dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -62,7 +62,7 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL, 0);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
@@ -932,7 +932,8 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 
 static long
 dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, void **kaddr, pfn_t *pfn,
+		unsigned long flags)
 {
 	struct dcssblk_dev_info *dev_info = dax_get_private(dax_dev);
 
diff --git a/fs/dax.c b/fs/dax.c
index 01118de00011..f603a9ce7f20 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -722,7 +722,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
 		return rc;
 
 	id = dax_read_lock();
-	rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL, 0);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -1023,7 +1023,7 @@ static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 		return rc;
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
-				   NULL, pfnp);
+				   NULL, pfnp, 0);
 	if (length < 0) {
 		rc = length;
 		goto out;
@@ -1149,7 +1149,7 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
 	if (page_aligned)
 		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 	else
-		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
+		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL, 0);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
@@ -1172,6 +1172,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	struct block_device *bdev = iomap->bdev;
 	struct dax_device *dax_dev = iomap->dax_dev;
 	loff_t end = pos + length, done = 0;
+	unsigned long dax_flag = 0;
 	ssize_t ret = 0;
 	size_t xfer;
 	int id;
@@ -1199,6 +1200,9 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 					      (end - 1) >> PAGE_SHIFT);
 	}
 
+	if (iomi->flags & IOMAP_RECOVERY)
+		dax_flag |= DAXDEV_F_RECOVERY;
+
 	id = dax_read_lock();
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
@@ -1218,7 +1222,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 			break;
 
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
-				&kaddr, NULL);
+				&kaddr, NULL, dax_flag);
 		if (map_len < 0) {
 			ret = map_len;
 			break;
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 281d79f8b3d3..2c45b94647f1 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -1245,7 +1245,7 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
 
 	id = dax_read_lock();
 	nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL,
-				     NULL);
+				     NULL, 0);
 	dax_read_unlock(id);
 	if (nr_pages < 0) {
 		pr_debug("dax_direct_access() returned %ld\n", nr_pages);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 0ad89c6629d7..d201b6e8a190 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -739,7 +739,7 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
  * offset.
  */
 static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
-				    long nr_pages, void **kaddr, pfn_t *pfn)
+	    long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	struct virtio_fs *fs = dax_get_private(dax_dev);
 	phys_addr_t offset = PFN_PHYS(pgoff);
@@ -773,7 +773,7 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 	long rc;
 	void *kaddr;
 
-	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL, 0);
 	if (rc < 0)
 		return rc;
 	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 2619d94c308d..0044a5d87e5d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -9,6 +9,9 @@
 /* Flag for synchronous flush */
 #define DAXDEV_F_SYNC (1UL << 0)
 
+/* Flag for DAX data recovery */
+#define DAXDEV_F_RECOVERY	(1UL << 1)
+
 typedef unsigned long dax_entry_t;
 
 struct iomap_ops;
@@ -21,7 +24,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			void **, pfn_t *);
+			void **, pfn_t *, unsigned long);
 	/*
 	 * Validate whether this device is usable as an fsdax backing
 	 * device.
@@ -192,7 +195,7 @@ static inline void dax_read_unlock(int id)
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn);
+		void **kaddr, pfn_t *pfn, unsigned long);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 114553b487ef..307c29789332 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -146,7 +146,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  * >= 0 : the number of bytes accessible at the address
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn);
+		long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags);
 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,
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index af19c85558e7..45dcfffe5575 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -8,7 +8,7 @@
 #include <nd.h>
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+	long nr_pages, void **kaddr, pfn_t *pfn, unsigned long flags)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
-- 
2.18.4

