dax, pmem: Add a dax operation zero_page_range

Add a dax operation zero_page_range, to zero a page. This will also clear any
known poison in the page being zeroed.

As of now, zeroing of one page is allowed in a single call. There
are no callers which are trying to zero more than a page in a single call.
Once we grow the callers which zero more than a page in single call, we
can add that support. Primary reason for not doing that yet is that this
will add little complexity in dm implementation where a range might be
spanning multiple underlying targets and one will have to split the range
into multiple sub ranges and call zero_page_range() on individual targets.

Suggested-by: Christoph Hellwig <[email protected]>
Signed-off-by: Vivek Goyal <[email protected]>
Reviewed-by: Pankaj Gupta <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Dan Williams <[email protected]>

Author: rhvgoyal

drivers/dax/super.c

@@ -344,6 +344,26 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_to_iter);
 
+int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+			size_t nr_pages)
+{
+	if (!dax_alive(dax_dev))
+		return -ENXIO;
+
+	if (!dax_dev->ops->zero_page_range)
+		return -EOPNOTSUPP;
+	/*
+	 * There are no callers that want to zero more than one page as of now.
+	 * Once users are there, this check can be removed after the
+	 * device mapper code has been updated to split ranges across targets.
+	 */
+	if (nr_pages != 1)
+		return -EIO;
+
+	return dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages);
+}
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)

drivers/nvdimm/pmem.c

@@ -282,6 +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)
 {
@@ -313,6 +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[] = {

include/linux/dax.h

@@ -34,6 +34,8 @@ struct dax_operations {
 	/* 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);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -199,6 +201,8 @@ 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,
 		size_t bytes, struct iov_iter *i);
+int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+			size_t nr_pages);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,