Merge tag 'libnvdimm-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "Primarily just the virtio_pmem driver:

   - virtio_pmem

     The new virtio_pmem facility introduces a paravirtualized
     persistent memory device that allows a guest VM to use DAX
     mechanisms to access a host-file with host-page-cache. It arranges
     for MAP_SYNC to be disabled and instead triggers a host fsync()
     when a 'write-cache flush' command is sent to the virtual disk
     device.

   - Miscellaneous small fixups"

* tag 'libnvdimm-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  virtio_pmem: fix sparse warning
  xfs: disable map_sync for async flush
  ext4: disable map_sync for async flush
  dax: check synchronous mapping is supported
  dm: enable synchronous dax
  libnvdimm: add dax_dev sync flag
  virtio-pmem: Add virtio pmem driver
  libnvdimm: nd_region flush callback support
  libnvdimm, namespace: Drop uuid_t implementation detail

Author: torvalds

drivers/acpi/nfit/core.c

@@ -2426,7 +2426,7 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->addr.base + offset);
-	nvdimm_flush(nfit_blk->nd_region);
+	nvdimm_flush(nfit_blk->nd_region, NULL);
 
 	if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH)
 		readq(mmio->addr.base + offset);
@@ -2475,7 +2475,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 	}
 
 	if (rw)
-		nvdimm_flush(nfit_blk->nd_region);
+		nvdimm_flush(nfit_blk->nd_region, NULL);
 
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;

drivers/dax/bus.c

@@ -388,7 +388,7 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
 	 * No 'host' or dax_operations since there is no access to this
 	 * device outside of mmap of the resulting character device.
 	 */
-	dax_dev = alloc_dax(dev_dax, NULL, NULL);
+	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
 	if (!dax_dev)
 		goto err;
 

drivers/dax/super.c

@@ -195,6 +195,8 @@ enum dax_device_flags {
 	DAXDEV_ALIVE,
 	/* gate whether dax_flush() calls the low level flush routine */
 	DAXDEV_WRITE_CACHE,
+	/* flag to check if device supports synchronous flush */
+	DAXDEV_SYNC,
 };
 
 /**
@@ -372,6 +374,18 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
 
+bool __dax_synchronous(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(__dax_synchronous);
+
+void __set_dax_synchronous(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(__set_dax_synchronous);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
@@ -526,7 +540,7 @@ static void dax_add_host(struct dax_device *dax_dev, const char *host)
 }
 
 struct dax_device *alloc_dax(void *private, const char *__host,
-		const struct dax_operations *ops)
+		const struct dax_operations *ops, unsigned long flags)
 {
 	struct dax_device *dax_dev;
 	const char *host;
@@ -549,6 +563,9 @@ struct dax_device *alloc_dax(void *private, const char *__host,
 	dax_add_host(dax_dev, host);
 	dax_dev->ops = ops;
 	dax_dev->private = private;
+	if (flags & DAXDEV_F_SYNC)
+		set_dax_synchronous(dax_dev);
+
 	return dax_dev;
 
  err_dev:

drivers/md/dm-table.c

@@ -881,7 +881,7 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
 EXPORT_SYMBOL_GPL(dm_table_set_type);
 
 /* validate the dax capability of the target device span */
-static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 				       sector_t start, sector_t len, void *data)
 {
 	int blocksize = *(int *) data;
@@ -890,7 +890,15 @@ static int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
 			start, len);
 }
 
-bool dm_table_supports_dax(struct dm_table *t, int blocksize)
+/* Check devices support synchronous DAX */
+static int device_synchronous(struct dm_target *ti, struct dm_dev *dev,
+				       sector_t start, sector_t len, void *data)
+{
+	return dax_synchronous(dev->dax_dev);
+}
+
+bool dm_table_supports_dax(struct dm_table *t,
+			  iterate_devices_callout_fn iterate_fn, int *blocksize)
 {
 	struct dm_target *ti;
 	unsigned i;
@@ -903,8 +911,7 @@ bool dm_table_supports_dax(struct dm_table *t, int blocksize)
 			return false;
 
 		if (!ti->type->iterate_devices ||
-		    !ti->type->iterate_devices(ti, device_supports_dax,
-			    &blocksize))
+			!ti->type->iterate_devices(ti, iterate_fn, blocksize))
 			return false;
 	}
 
@@ -940,6 +947,7 @@ static int dm_table_determine_type(struct dm_table *t)
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
+	int page_size = PAGE_SIZE;
 
 	if (t->type != DM_TYPE_NONE) {
 		/* target already set the table's type */
@@ -984,7 +992,7 @@ static int dm_table_determine_type(struct dm_table *t)
 verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
-		if (dm_table_supports_dax(t, PAGE_SIZE) ||
+		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
 		} else {
@@ -1883,6 +1891,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
 	bool wc = false, fua = false;
+	int page_size = PAGE_SIZE;
 
 	/*
 	 * Copy table's limits to the DM device's request_queue
@@ -1910,8 +1919,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (dm_table_supports_dax(t, PAGE_SIZE))
+	if (dm_table_supports_dax(t, device_supports_dax, &page_size)) {
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
+		if (dm_table_supports_dax(t, device_synchronous, NULL))
+			set_dax_synchronous(t->md->dax_dev);
+	}
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_DAX, q);
 

drivers/md/dm.c

@@ -1117,7 +1117,7 @@ static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bd
 	if (!map)
 		return false;
 
-	ret = dm_table_supports_dax(map, blocksize);
+	ret = dm_table_supports_dax(map, device_supports_dax, &blocksize);
 
 	dm_put_live_table(md, srcu_idx);
 
@@ -1989,7 +1989,8 @@ static struct mapped_device *alloc_dev(int minor)
 	sprintf(md->disk->disk_name, "dm-%d", minor);
 
 	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
-		md->dax_dev = alloc_dax(md, md->disk->disk_name, &dm_dax_ops);
+		md->dax_dev = alloc_dax(md, md->disk->disk_name,
+					&dm_dax_ops, 0);
 		if (!md->dax_dev)
 			goto bad;
 	}

drivers/md/dm.h

@@ -72,7 +72,10 @@ bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
-bool dm_table_supports_dax(struct dm_table *t, int blocksize);
+bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn,
+			   int *blocksize);
+int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
+			   sector_t start, sector_t len, void *data);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);

drivers/nvdimm/Makefile

@@ -5,6 +5,7 @@ obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
 obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_OF_PMEM) += of_pmem.o
+obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o
 
 nd_pmem-y := pmem.o
 

drivers/nvdimm/claim.c

@@ -255,7 +255,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
 	sector_t sector = offset >> 9;
-	int rc = 0;
+	int rc = 0, ret = 0;
 
 	if (unlikely(!size))
 		return 0;
@@ -293,7 +293,9 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	}
 
 	memcpy_flushcache(nsio->addr + offset, buf, size);
-	nvdimm_flush(to_nd_region(ndns->dev.parent));
+	ret = nvdimm_flush(to_nd_region(ndns->dev.parent), NULL);
+	if (ret)
+		rc = ret;
 
 	return rc;
 }

drivers/nvdimm/namespace_devs.c

@@ -1822,8 +1822,8 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid,
 					&& !guid_equal(&nd_set->type_guid,
 						&nd_label->type_guid)) {
 				dev_dbg(ndd->dev, "expect type_guid %pUb got %pUb\n",
-						nd_set->type_guid.b,
-						nd_label->type_guid.b);
+						&nd_set->type_guid,
+						&nd_label->type_guid);
 				continue;
 			}
 
@@ -2227,8 +2227,8 @@ static struct device *create_namespace_blk(struct nd_region *nd_region,
 	if (namespace_label_has(ndd, type_guid)) {
 		if (!guid_equal(&nd_set->type_guid, &nd_label->type_guid)) {
 			dev_dbg(ndd->dev, "expect type_guid %pUb got %pUb\n",
-					nd_set->type_guid.b,
-					nd_label->type_guid.b);
+					&nd_set->type_guid,
+					&nd_label->type_guid);
 			return ERR_PTR(-EAGAIN);
 		}
 

drivers/nvdimm/nd.h

@@ -155,6 +155,7 @@ struct nd_region {
 	struct badblocks bb;
 	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];
 };