[PATCH v2 08/17] libnvdimm, blk: add support for blk integrity

[Dan Williams <dan.j.williams@intel.com>]

From: Vishal Verma <vishal.l.verma@intel.com>

Support multiple block sizes (sector + metadata) for nd_blk in the
same way as done for the BTT. Add the idea of an 'internal' lbasize,
which is properly aligned and padded, and store metadata in this space.

Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/blk.c            |  174 ++++++++++++++++++++++++++++++++++-----
 drivers/nvdimm/btt.h            |    1 
 drivers/nvdimm/core.c           |    3 +
 drivers/nvdimm/namespace_devs.c |    3 -
 drivers/nvdimm/nd.h             |    1 
 5 files changed, 159 insertions(+), 23 deletions(-)

diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 9ac0c266c15c..5c44e067652f 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -27,10 +27,17 @@ struct nd_blk_device {
 	struct nd_namespace_blk *nsblk;
 	struct nd_blk_region *ndbr;
 	size_t disk_size;
+	u32 sector_size;
+	u32 internal_lbasize;
 };
 
 static int nd_blk_major;
 
+static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
+{
+	return blk_dev->nsblk->lbasize - blk_dev->sector_size;
+}
+
 static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
 				resource_size_t ns_offset, unsigned int len)
 {
@@ -52,41 +59,145 @@ static resource_size_t to_dev_offset(struct nd_namespace_blk *nsblk,
 	return SIZE_MAX;
 }
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
+				struct bio_integrity_payload *bip, u64 lba,
+				int rw)
+{
+	unsigned int len = nd_blk_meta_size(blk_dev);
+	resource_size_t	dev_offset, ns_offset;
+	struct nd_namespace_blk *nsblk;
+	struct nd_blk_region *ndbr;
+	int err = 0;
+
+	nsblk = blk_dev->nsblk;
+	ndbr = blk_dev->ndbr;
+	ns_offset = lba * blk_dev->internal_lbasize + blk_dev->sector_size;
+	dev_offset = to_dev_offset(nsblk, ns_offset, len);
+	if (dev_offset == SIZE_MAX)
+		return -EIO;
+
+	while (len) {
+		unsigned int cur_len;
+		struct bio_vec bv;
+		void *iobuf;
+
+		bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter);
+		/*
+		 * The 'bv' obtained from bvec_iter_bvec has its .bv_len and
+		 * .bv_offset already adjusted for iter->bi_bvec_done, and we
+		 * can use those directly
+		 */
+
+		cur_len = min(len, bv.bv_len);
+		iobuf = kmap_atomic(bv.bv_page);
+		err = ndbr->do_io(ndbr, dev_offset, iobuf + bv.bv_offset,
+				cur_len, rw);
+		kunmap_atomic(iobuf);
+		if (err)
+			return err;
+
+		len -= cur_len;
+		dev_offset += cur_len;
+		bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
+	}
+
+	return err;
+}
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static int nd_blk_rw_integrity(struct nd_blk_device *blk_dev,
+				struct bio_integrity_payload *bip, u64 lba,
+				int rw)
+{
+	return 0;
+}
+#endif
+
+static int nd_blk_do_bvec(struct nd_blk_device *blk_dev,
+			struct bio_integrity_payload *bip, struct page *page,
+			unsigned int len, unsigned int off, int rw,
+			sector_t sector)
+{
+	struct nd_blk_region *ndbr = blk_dev->ndbr;
+	resource_size_t	dev_offset, ns_offset;
+	int err = 0;
+	void *iobuf;
+	u64 lba;
+
+	while (len) {
+		unsigned int cur_len;
+
+		/*
+		 * If we don't have an integrity payload, we don't have to
+		 * split the bvec into sectors, as this would cause unnecessary
+		 * Block Window setup/move steps. the do_io routine is capable
+		 * of handling len <= PAGE_SIZE.
+		 */
+		cur_len = bip ? min(len, blk_dev->sector_size) : len;
+
+		lba = div_u64(sector << SECTOR_SHIFT, blk_dev->sector_size);
+		ns_offset = lba * blk_dev->internal_lbasize;
+		dev_offset = to_dev_offset(blk_dev->nsblk, ns_offset, cur_len);
+		if (dev_offset == SIZE_MAX)
+			return -EIO;
+
+		iobuf = kmap_atomic(page);
+		err = ndbr->do_io(ndbr, dev_offset, iobuf + off, cur_len, rw);
+		kunmap_atomic(iobuf);
+		if (err)
+			return err;
+
+		if (bip) {
+			err = nd_blk_rw_integrity(blk_dev, bip, lba, rw);
+			if (err)
+				return err;
+		}
+		len -= cur_len;
+		off += cur_len;
+		sector += blk_dev->sector_size >> SECTOR_SHIFT;
+	}
+
+	return err;
+}
+
 static void nd_blk_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 	struct gendisk *disk = bdev->bd_disk;
-	struct nd_namespace_blk *nsblk;
+	struct bio_integrity_payload *bip;
 	struct nd_blk_device *blk_dev;
-	struct nd_blk_region *ndbr;
 	struct bvec_iter iter;
 	struct bio_vec bvec;
 	int err = 0, rw;
 
+	/*
+	 * bio_integrity_enabled also checks if the bio already has an
+	 * integrity payload attached. If it does, we *don't* do a
+	 * bio_integrity_prep here - the payload has been generated by
+	 * another kernel subsystem, and we just pass it through.
+	 */
+	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
+		err = -EIO;
+		goto out;
+	}
+
+	bip = bio_integrity(bio);
 	blk_dev = disk->private_data;
-	nsblk = blk_dev->nsblk;
-	ndbr = blk_dev->ndbr;
 	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
-		resource_size_t	dev_offset;
-		void *iobuf;
 
 		BUG_ON(len > PAGE_SIZE);
-
-		dev_offset = to_dev_offset(nsblk,
-				iter.bi_sector << SECTOR_SHIFT, len);
-		if (dev_offset == SIZE_MAX) {
-			err = -EIO;
+		err = nd_blk_do_bvec(blk_dev, bip, bvec.bv_page, len,
+					bvec.bv_offset, rw, iter.bi_sector);
+		if (err) {
+			dev_info(&blk_dev->nsblk->common.dev,
+					"io error in %s sector %lld, len %d,\n",
+					(rw == READ) ? "READ" : "WRITE",
+					(unsigned long long) iter.bi_sector, len);
 			goto out;
 		}
-
-		iobuf = kmap_atomic(bvec.bv_page);
-		err = ndbr->do_io(ndbr, dev_offset, iobuf + bvec.bv_offset,
-				len, rw);
-		kunmap_atomic(iobuf);
-		if (err)
-			goto out;
 	}
 
  out:
@@ -121,8 +232,12 @@ static const struct block_device_operations nd_blk_fops = {
 static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
 		struct nd_blk_device *blk_dev)
 {
-	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(&ndns->dev);
+	resource_size_t available_disk_size;
 	struct gendisk *disk;
+	u64 internal_nlba;
+
+	internal_nlba = div_u64(blk_dev->disk_size, blk_dev->internal_lbasize);
+	available_disk_size = internal_nlba * blk_dev->sector_size;
 
 	blk_dev->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!blk_dev->queue)
@@ -131,7 +246,7 @@ static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
 	blk_queue_make_request(blk_dev->queue, nd_blk_make_request);
 	blk_queue_max_hw_sectors(blk_dev->queue, UINT_MAX);
 	blk_queue_bounce_limit(blk_dev->queue, BLK_BOUNCE_ANY);
-	blk_queue_logical_block_size(blk_dev->queue, nsblk->lbasize);
+	blk_queue_logical_block_size(blk_dev->queue, blk_dev->sector_size);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, blk_dev->queue);
 
 	disk = blk_dev->disk = alloc_disk(0);
@@ -148,15 +263,28 @@ static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
 	disk->queue		= blk_dev->queue;
 	disk->flags		= GENHD_FL_EXT_DEVT;
 	nvdimm_namespace_disk_name(ndns, disk->disk_name);
-	set_capacity(disk, blk_dev->disk_size >> SECTOR_SHIFT);
+	set_capacity(disk, 0);
 	add_disk(disk);
 
+	if (nd_blk_meta_size(blk_dev)) {
+		int rc = nd_integrity_init(disk, nd_blk_meta_size(blk_dev));
+
+		if (rc) {
+			del_gendisk(disk);
+			put_disk(disk);
+			blk_cleanup_queue(blk_dev->queue);
+			return rc;
+		}
+	}
+
+	set_capacity(disk, available_disk_size >> SECTOR_SHIFT);
 	return 0;
 }
 
 static int nd_blk_probe(struct device *dev)
 {
 	struct nd_namespace_common *ndns;
+	struct nd_namespace_blk *nsblk;
 	struct nd_blk_device *blk_dev;
 	int rc;
 
@@ -168,9 +296,13 @@ static int nd_blk_probe(struct device *dev)
 	if (!blk_dev)
 		return -ENOMEM;
 
+	nsblk = to_nd_namespace_blk(&ndns->dev);
 	blk_dev->disk_size = nvdimm_namespace_capacity(ndns);
 	blk_dev->ndbr = to_nd_blk_region(dev->parent);
 	blk_dev->nsblk = to_nd_namespace_blk(&ndns->dev);
+	blk_dev->internal_lbasize = roundup(nsblk->lbasize,
+						INT_LBASIZE_ALIGNMENT);
+	blk_dev->sector_size = ((nsblk->lbasize >= 4096) ? 4096 : 512);
 	dev_set_drvdata(dev, blk_dev);
 
 	ndns->rw_bytes = nd_blk_rw_bytes;
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index 2caa0ef7e67a..75b0d80a6bd9 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -31,7 +31,6 @@
 #define ARENA_MAX_SIZE (1ULL << 39)	/* 512 GB */
 #define RTT_VALID (1UL << 31)
 #define RTT_INVALID 0
-#define INT_LBASIZE_ALIGNMENT 64
 #define BTT_PG_SIZE 4096
 #define BTT_DEFAULT_NFREE ND_MAX_LANES
 #define LOG_SEQ_INIT 1
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 1d96b9a6e4cc..4288169432de 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -379,6 +379,9 @@ int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
 	};
 	int ret;
 
+	if (meta_size == 0)
+		return 0;
+
 	ret = blk_integrity_register(disk, &integrity);
 	if (ret)
 		return ret;
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 1ce1e70de44a..27d69bd3b4d6 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1059,7 +1059,8 @@ static ssize_t resource_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(resource);
 
-static const unsigned long ns_lbasize_supported[] = { 512, 0 };
+static const unsigned long ns_lbasize_supported[] = { 512, 520, 528,
+	4096, 4104, 4160, 4224, 0 };
 
 static ssize_t sector_size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 6a969a885d70..e73c34dcd935 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -27,6 +27,7 @@ enum {
 	 */
 	ND_MAX_LANES = 256,
 	SECTOR_SHIFT = 9,
+	INT_LBASIZE_ALIGNMENT = 64,
 };
 
 struct nvdimm_drvdata {