[PATCH v2 07/17] libnvdimm, btt: 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) using the blk integrity
framework. This registers a new integrity template that defines the
protection information tuple size based on the configured metadata size,
and simply acts as a passthrough for protection information generated by
another layer. The metadata is written to the storage as-is, and read back
with each sector.

Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/nvdimm/btt.c      |  129 +++++++++++++++++++++++++++++++++++++++------
 drivers/nvdimm/btt.h      |    2 -
 drivers/nvdimm/btt_devs.c |    3 +
 drivers/nvdimm/core.c     |   37 +++++++++++++
 drivers/nvdimm/nd.h       |    1 
 5 files changed, 154 insertions(+), 18 deletions(-)

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 7ae38aac2c25..18a2463c2300 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -837,6 +837,11 @@ static int btt_meta_init(struct btt *btt)
 	return ret;
 }
 
+static u32 btt_meta_size(struct btt *btt)
+{
+	return btt->lbasize - btt->sector_size;
+}
+
 /*
  * This function calculates the arena in which the given LBA lies
  * by doing a linear walk. This is acceptable since we expect only
@@ -921,8 +926,63 @@ static void zero_fill_data(struct page *page, unsigned int off, u32 len)
 	kunmap_atomic(mem);
 }
 
-static int btt_read_pg(struct btt *btt, struct page *page, unsigned int off,
-			sector_t sector, unsigned int len)
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
+			struct arena_info *arena, u32 postmap, int rw)
+{
+	unsigned int len = btt_meta_size(btt);
+	u64 meta_nsoff;
+	int ret = 0;
+
+	if (bip == NULL)
+		return 0;
+
+	meta_nsoff = to_namespace_offset(arena, postmap) + btt->sector_size;
+
+	while (len) {
+		unsigned int cur_len;
+		struct bio_vec bv;
+		void *mem;
+
+		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);
+		mem = kmap_atomic(bv.bv_page);
+		if (rw)
+			ret = arena_write_bytes(arena, meta_nsoff,
+					mem + bv.bv_offset, cur_len);
+		else
+			ret = arena_read_bytes(arena, meta_nsoff,
+					mem + bv.bv_offset, cur_len);
+
+		kunmap_atomic(mem);
+		if (ret)
+			return ret;
+
+		len -= cur_len;
+		meta_nsoff += cur_len;
+		bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len);
+	}
+
+	return ret;
+}
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
+			struct arena_info *arena, u32 postmap, int rw)
+{
+	return 0;
+}
+#endif
+
+static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
+			struct page *page, unsigned int off, sector_t sector,
+			unsigned int len)
 {
 	int ret = 0;
 	int t_flag, e_flag;
@@ -984,6 +1044,12 @@ static int btt_read_pg(struct btt *btt, struct page *page, unsigned int off,
 		if (ret)
 			goto out_rtt;
 
+		if (bip) {
+			ret = btt_rw_integrity(btt, bip, arena, postmap, READ);
+			if (ret)
+				goto out_rtt;
+		}
+
 		arena->rtt[lane] = RTT_INVALID;
 		nd_region_release_lane(btt->nd_region, lane);
 
@@ -1001,8 +1067,9 @@ static int btt_read_pg(struct btt *btt, struct page *page, unsigned int off,
 	return ret;
 }
 
-static int btt_write_pg(struct btt *btt, sector_t sector, struct page *page,
-		unsigned int off, unsigned int len)
+static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
+			sector_t sector, struct page *page, unsigned int off,
+			unsigned int len)
 {
 	int ret = 0;
 	struct arena_info *arena = NULL;
@@ -1036,12 +1103,19 @@ static int btt_write_pg(struct btt *btt, sector_t sector, struct page *page,
 		if (new_postmap >= arena->internal_nlba) {
 			ret = -EIO;
 			goto out_lane;
-		} else
-			ret = btt_data_write(arena, new_postmap, page,
-						off, cur_len);
+		}
+
+		ret = btt_data_write(arena, new_postmap, page, off, cur_len);
 		if (ret)
 			goto out_lane;
 
+		if (bip) {
+			ret = btt_rw_integrity(btt, bip, arena, new_postmap,
+						WRITE);
+			if (ret)
+				goto out_lane;
+		}
+
 		lock_map(arena, premap);
 		ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL);
 		if (ret)
@@ -1081,18 +1155,18 @@ static int btt_write_pg(struct btt *btt, sector_t sector, struct page *page,
 	return ret;
 }
 
-static int btt_do_bvec(struct btt *btt, struct page *page,
-			unsigned int len, unsigned int off, int rw,
-			sector_t sector)
+static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
+			struct page *page, unsigned int len, unsigned int off,
+			int rw, sector_t sector)
 {
 	int ret;
 
 	if (rw == READ) {
-		ret = btt_read_pg(btt, page, off, sector, len);
+		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
 		flush_dcache_page(page);
-		ret = btt_write_pg(btt, sector, page, off, len);
+		ret = btt_write_pg(btt, bip, sector, page, off, len);
 	}
 
 	return ret;
@@ -1100,11 +1174,23 @@ static int btt_do_bvec(struct btt *btt, struct page *page,
 
 static void btt_make_request(struct request_queue *q, struct bio *bio)
 {
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct btt *btt = q->queuedata;
 	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;
+	}
+
 	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
@@ -1115,7 +1201,7 @@ static void btt_make_request(struct request_queue *q, struct bio *bio)
 		BUG_ON(len < btt->sector_size);
 		BUG_ON(len % btt->sector_size);
 
-		err = btt_do_bvec(btt, bvec.bv_page, len, bvec.bv_offset,
+		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
 				rw, iter.bi_sector);
 		if (err) {
 			dev_info(&btt->nd_btt->dev,
@@ -1135,7 +1221,7 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector,
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 
-	btt_do_bvec(btt, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	btt_do_bvec(btt, NULL, page, PAGE_CACHE_SIZE, 0, rw, sector);
 	page_endio(page, rw & WRITE, 0);
 	return 0;
 }
@@ -1188,15 +1274,26 @@ static int btt_blk_init(struct btt *btt)
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, btt->btt_queue);
 	btt->btt_queue->queuedata = btt;
 
-	set_capacity(btt->btt_disk,
-			btt->nlba * btt->sector_size >> SECTOR_SHIFT);
+	set_capacity(btt->btt_disk, 0);
 	add_disk(btt->btt_disk);
+	if (btt_meta_size(btt)) {
+		int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt));
+
+		if (rc) {
+			del_gendisk(btt->btt_disk);
+			put_disk(btt->btt_disk);
+			blk_cleanup_queue(btt->btt_queue);
+			return rc;
+		}
+	}
+	set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
 
 	return 0;
 }
 
 static void btt_blk_cleanup(struct btt *btt)
 {
+	blk_integrity_unregister(btt->btt_disk);
 	del_gendisk(btt->btt_disk);
 	put_disk(btt->btt_disk);
 	blk_cleanup_queue(btt->btt_queue);
diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h
index 8c95a7792c3e..2caa0ef7e67a 100644
--- a/drivers/nvdimm/btt.h
+++ b/drivers/nvdimm/btt.h
@@ -31,7 +31,7 @@
 #define ARENA_MAX_SIZE (1ULL << 39)	/* 512 GB */
 #define RTT_VALID (1UL << 31)
 #define RTT_INVALID 0
-#define INT_LBASIZE_ALIGNMENT 256
+#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/btt_devs.c b/drivers/nvdimm/btt_devs.c
index cde9f075fcea..b6724cfbcfca 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -104,7 +104,8 @@ struct nd_btt *to_nd_btt(struct device *dev)
 }
 EXPORT_SYMBOL(to_nd_btt);
 
-static const unsigned long btt_lbasize_supported[] = { 512, 4096, 0 };
+static const unsigned long btt_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/core.c b/drivers/nvdimm/core.c
index dd824d7c2669..1d96b9a6e4cc 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -13,6 +13,7 @@
 #include <linux/libnvdimm.h>
 #include <linux/export.h>
 #include <linux/module.h>
+#include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/ctype.h>
 #include <linux/ndctl.h>
@@ -361,6 +362,42 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);
 
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+static int nd_pi_nop_generate_verify(struct blk_integrity_iter *iter)
+{
+	return 0;
+}
+
+int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
+{
+	struct blk_integrity integrity = {
+		.name = "ND-PI-NOP",
+		.generate_fn = nd_pi_nop_generate_verify,
+		.verify_fn = nd_pi_nop_generate_verify,
+		.tuple_size = meta_size,
+		.tag_size = meta_size,
+	};
+	int ret;
+
+	ret = blk_integrity_register(disk, &integrity);
+	if (ret)
+		return ret;
+
+	blk_queue_max_integrity_segments(disk->queue, 1);
+
+	return 0;
+}
+EXPORT_SYMBOL(nd_integrity_init);
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
+{
+	return 0;
+}
+EXPORT_SYMBOL(nd_integrity_init);
+
+#endif
+
 static __init int libnvdimm_init(void)
 {
 	int rc;
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index d7fc6ef4e4d8..6a969a885d70 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -135,6 +135,7 @@ enum nd_async_mode {
 	ND_ASYNC,
 };
 
+int nd_integrity_init(struct gendisk *disk, unsigned long meta_size);
 void wait_nvdimm_bus_probe_idle(struct device *dev);
 void nd_device_register(struct device *dev);
 void nd_device_unregister(struct device *dev, enum nd_async_mode mode);