1 files changed, 63 insertions, 38 deletions

diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4ffc6f7ca131..2df6994acf83 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -136,9 +136,25 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 	return BLK_STS_OK;
 }
 
-static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, unsigned int op,
-			sector_t sector)
+static blk_status_t pmem_do_read(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
+{
+	blk_status_t rc;
+	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
+	void *pmem_addr = pmem->virt_addr + pmem_off;
+
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
+		return BLK_STS_IOERR;
+
+	rc = read_pmem(page, page_off, pmem_addr, len);
+	flush_dcache_page(page);
+	return rc;
+}
+
+static blk_status_t pmem_do_write(struct pmem_device *pmem,
+			struct page *page, unsigned int page_off,
+			sector_t sector, unsigned int len)
 {
 	blk_status_t rc = BLK_STS_OK;
 	bool bad_pmem = false;
@@ -148,34 +164,25 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!op_is_write(op)) {
-		if (unlikely(bad_pmem))
-			rc = BLK_STS_IOERR;
-		else {
-			rc = read_pmem(page, off, pmem_addr, len);
-			flush_dcache_page(page);
-		}
-	} else {
-		/*
-		 * Note that we write the data both before and after
-		 * clearing poison.  The write before clear poison
-		 * handles situations where the latest written data is
-		 * preserved and the clear poison operation simply marks
-		 * the address range as valid without changing the data.
-		 * In this case application software can assume that an
-		 * interrupted write will either return the new good
-		 * data or an error.
-		 *
-		 * However, if pmem_clear_poison() leaves the data in an
-		 * indeterminate state we need to perform the write
-		 * after clear poison.
-		 */
-		flush_dcache_page(page);
-		write_pmem(pmem_addr, page, off, len);
-		if (unlikely(bad_pmem)) {
-			rc = pmem_clear_poison(pmem, pmem_off, len);
-			write_pmem(pmem_addr, page, off, len);
-		}
+	/*
+	 * Note that we write the data both before and after
+	 * clearing poison.  The write before clear poison
+	 * handles situations where the latest written data is
+	 * preserved and the clear poison operation simply marks
+	 * the address range as valid without changing the data.
+	 * In this case application software can assume that an
+	 * interrupted write will either return the new good
+	 * data or an error.
+	 *
+	 * However, if pmem_clear_poison() leaves the data in an
+	 * indeterminate state we need to perform the write
+	 * after clear poison.
+	 */
+	flush_dcache_page(page);
+	write_pmem(pmem_addr, page, page_off, len);
+	if (unlikely(bad_pmem)) {
+		rc = pmem_clear_poison(pmem, pmem_off, len);
+		write_pmem(pmem_addr, page, page_off, len);
 	}
 
 	return rc;
@@ -197,8 +204,12 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
-		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, bio_op(bio), iter.bi_sector);
+		if (op_is_write(bio_op(bio)))
+			rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
+		else
+			rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
+				iter.bi_sector, bvec.bv_len);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -223,9 +234,12 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
-	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, op, sector);
-
+	if (op_is_write(op))
+		rc = pmem_do_write(pmem, page, 0, sector,
+				   hpage_nr_pages(page) * PAGE_SIZE);
+	else
+		rc = pmem_do_read(pmem, page, 0, sector,
+				   hpage_nr_pages(page) * PAGE_SIZE);
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
 	 * retries on any error, so we can only invoke page_endio() in
@@ -268,6 +282,16 @@ static const struct block_device_operations pmem_fops = {
 	.revalidate_disk =	nvdimm_revalidate_disk,
 };
 
+static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				    size_t nr_pages)
+{
+	struct pmem_device *pmem = dax_get_private(dax_dev);
+
+	return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
+				   PFN_PHYS(pgoff) >> SECTOR_SHIFT,
+				   PAGE_SIZE));
+}
+
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
 		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
 {
@@ -299,6 +323,7 @@ static const struct dax_operations pmem_dax_ops = {
 	.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,
 };
 
 static const struct attribute_group *pmem_attribute_groups[] = {
@@ -461,9 +486,9 @@ 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);
-	if (!dax_dev) {
+	if (IS_ERR(dax_dev)) {
 		put_disk(disk);
-		return -ENOMEM;
+		return PTR_ERR(dax_dev);
 	}
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;