Merge branch 'for-5.7/libnvdimm' into libnvdimm-for-next

- Introduce 'zero_page_range' as a dax operation. This facilitates
  filesystem-dax operation without a block-device.

- Advertise a persistence-domain for of_pmem and papr_scm. The
  persistence domain indicates where cpu-store cycles need to reach in
  the platform-memory subsystem before the platform will consider them
  power-fail protected.

- Fixup some flexible-array declarations.

12 files changed, 211 insertions, 54 deletions

diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index b317f4043705..f5525f8bb770 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -145,32 +145,32 @@ struct nfit_spa {
 	unsigned long ars_state;
 	u32 clear_err_unit;
 	u32 max_ars;
-	struct acpi_nfit_system_address spa[0];
+	struct acpi_nfit_system_address spa[];
 };
 
 struct nfit_dcr {
 	struct list_head list;
-	struct acpi_nfit_control_region dcr[0];
+	struct acpi_nfit_control_region dcr[];
 };
 
 struct nfit_bdw {
 	struct list_head list;
-	struct acpi_nfit_data_region bdw[0];
+	struct acpi_nfit_data_region bdw[];
 };
 
 struct nfit_idt {
 	struct list_head list;
-	struct acpi_nfit_interleave idt[0];
+	struct acpi_nfit_interleave idt[];
 };
 
 struct nfit_flush {
 	struct list_head list;
-	struct acpi_nfit_flush_address flush[0];
+	struct acpi_nfit_flush_address flush[];
 };
 
 struct nfit_memdev {
 	struct list_head list;
-	struct acpi_nfit_memory_map memdev[0];
+	struct acpi_nfit_memory_map memdev[];
 };
 
 enum nfit_mem_flags {
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 46e46047a1f7..df238c8b6ef2 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -421,8 +421,10 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
 	 * device outside of mmap of the resulting character device.
 	 */
 	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
-	if (!dax_dev)
+	if (IS_ERR(dax_dev)) {
+		rc = PTR_ERR(dax_dev);
 		goto err;
+	}
 
 	/* a device_dax instance is dead while the driver is not attached */
 	kill_dax(dax_dev);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 0aa4b6bc5101..8e32345be0f7 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -344,6 +344,23 @@ 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;
+	/*
+	 * 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)
@@ -551,9 +568,16 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	dev_t devt;
 	int minor;
 
+	if (ops && !ops->zero_page_range) {
+		pr_debug("%s: error: device does not provide dax"
+			 " operation zero_page_range()\n",
+			 __host ? __host : "Unknown");
+		return ERR_PTR(-EINVAL);
+	}
+
 	host = kstrdup(__host, GFP_KERNEL);
 	if (__host && !host)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
 	if (minor < 0)
@@ -576,7 +600,7 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	ida_simple_remove(&dax_minor_ida, minor);
  err_minor:
 	kfree(host);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(alloc_dax);
 
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 8d07fdf63a47..e1db43446327 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -201,10 +201,27 @@ static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+				      size_t nr_pages)
+{
+	int ret;
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_copy_from_iter NULL
 #define linear_dax_copy_to_iter NULL
+#define linear_dax_zero_page_range NULL
 #endif
 
 static struct target_type linear_target = {
@@ -226,6 +243,7 @@ static struct target_type linear_target = {
 	.direct_access = linear_dax_direct_access,
 	.dax_copy_from_iter = linear_dax_copy_from_iter,
 	.dax_copy_to_iter = linear_dax_copy_to_iter,
+	.dax_zero_page_range = linear_dax_zero_page_range,
 };
 
 int __init dm_linear_init(void)
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index 99721c76225d..8ea20b56b4d6 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -994,10 +994,26 @@ static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
 	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
 
+static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+					  size_t nr_pages)
+{
+	int ret;
+	struct log_writes_c *lc = ti->private;
+	sector_t sector = pgoff * PAGE_SECTORS;
+
+	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT,
+			     &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(lc->dev->dax_dev, pgoff,
+				   nr_pages << PAGE_SHIFT);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_copy_from_iter NULL
 #define log_writes_dax_copy_to_iter NULL
+#define log_writes_dax_zero_page_range NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -1016,6 +1032,7 @@ static struct target_type log_writes_target = {
 	.direct_access = log_writes_dax_direct_access,
 	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
 	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
+	.dax_zero_page_range = log_writes_dax_zero_page_range,
 };
 
 static int __init dm_log_writes_init(void)
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 63bbcc20f49a..fa813c0f993d 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -360,10 +360,32 @@ static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
+				      size_t nr_pages)
+{
+	int ret;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
+	if (ret)
+		return ret;
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_copy_from_iter NULL
 #define stripe_dax_copy_to_iter NULL
+#define stripe_dax_zero_page_range NULL
 #endif
 
 /*
@@ -486,6 +508,7 @@ static struct target_type stripe_target = {
 	.direct_access = stripe_dax_direct_access,
 	.dax_copy_from_iter = stripe_dax_copy_from_iter,
 	.dax_copy_to_iter = stripe_dax_copy_to_iter,
+	.dax_zero_page_range = stripe_dax_zero_page_range,
 };
 
 int __init dm_stripe_init(void)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b89f07ee2eff..6504f0a358e5 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1198,6 +1198,35 @@ static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+				  size_t nr_pages)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	int ret = -EIO;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (WARN_ON(!ti->type->dax_zero_page_range)) {
+		/*
+		 * ->zero_page_range() is mandatory dax operation. If we are
+		 *  here, something is wrong.
+		 */
+		dm_put_live_table(md, srcu_idx);
+		goto out;
+	}
+	ret = ti->type->dax_zero_page_range(ti, pgoff, nr_pages);
+
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET,
@@ -1976,7 +2005,7 @@ static struct mapped_device *alloc_dev(int minor)
 	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
 		md->dax_dev = alloc_dax(md, md->disk->disk_name,
 					&dm_dax_ops, 0);
-		if (!md->dax_dev)
+		if (IS_ERR(md->dax_dev))
 			goto bad;
 	}
 
@@ -3199,6 +3228,7 @@ static const struct dax_operations dm_dax_ops = {
 	.dax_supported = dm_dax_supported,
 	.copy_from_iter = dm_dax_copy_from_iter,
 	.copy_to_iter = dm_dax_copy_to_iter,
+	.zero_page_range = dm_dax_zero_page_range,
 };
 
 /*
diff --git a/drivers/nvdimm/label.h b/drivers/nvdimm/label.h
index 4c7b775c2811..956b6d1bd8cc 100644
--- a/drivers/nvdimm/label.h
+++ b/drivers/nvdimm/label.h
@@ -62,7 +62,7 @@ struct nd_namespace_index {
 	__le16 major;
 	__le16 minor;
 	__le64 checksum;
-	u8 free[0];
+	u8 free[];
 };
 
 /**
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index c4d69c1cce55..85dbb2a322b9 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -39,7 +39,7 @@ struct nd_region_data {
 	int ns_count;
 	int ns_active;
 	unsigned int hints_shift;
-	void __iomem *flush_wpq[0];
+	void __iomem *flush_wpq[];
 };
 
 static inline void __iomem *ndrd_get_flush_wpq(struct nd_region_data *ndrd,
@@ -157,7 +157,7 @@ struct nd_region {
 	struct nd_interleave_set *nd_set;
 	struct nd_percpu_lane __percpu *lane;
 	int (*flush)(struct nd_region *nd_region, struct bio *bio);
-	struct nd_mapping mapping[0];
+	struct nd_mapping mapping[];
 };
 
 struct nd_blk_region {
diff --git a/drivers/nvdimm/of_pmem.c b/drivers/nvdimm/of_pmem.c
index 8224d1431ea9..6826a274a1f1 100644
--- a/drivers/nvdimm/of_pmem.c
+++ b/drivers/nvdimm/of_pmem.c
@@ -62,8 +62,10 @@ static int of_pmem_region_probe(struct platform_device *pdev)
 
 		if (is_volatile)
 			region = nvdimm_volatile_region_create(bus, &ndr_desc);
-		else
+		else {
+			set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
 			region = nvdimm_pmem_region_create(bus, &ndr_desc);
+		}
 
 		if (!region)
 			dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n",
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 4eae441f86c9..715cb0696525 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[] = {
@@ -462,9 +487,9 @@ 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;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 63502ca537eb..9b05cf1a25c4 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -57,11 +57,26 @@ static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
 	return copy_to_iter(addr, bytes, i);
 }
 
+static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
+				       pgoff_t pgoff, size_t nr_pages)
+{
+	long rc;
+	void *kaddr;
+
+	rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+	if (rc < 0)
+		return rc;
+	memset(kaddr, 0, nr_pages << PAGE_SHIFT);
+	dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT);
+	return 0;
+}
+
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
 	.dax_supported = generic_fsdax_supported,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
 	.copy_to_iter = dcssblk_dax_copy_to_iter,
+	.zero_page_range = dcssblk_dax_zero_page_range,
 };
 
 struct dcssblk_dev_info {
@@ -680,8 +695,9 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 
 	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
 			&dcssblk_dax_ops, DAXDEV_F_SYNC);
-	if (!dev_info->dax_dev) {
-		rc = -ENOMEM;
+	if (IS_ERR(dev_info->dax_dev)) {
+		rc = PTR_ERR(dev_info->dax_dev);
+		dev_info->dax_dev = NULL;
 		goto put_dev;
 	}