Merge tag 'libnvdimm-for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm from Dan Williams:
 "A rework of media error handling in the BTT driver and other updates.
  It has appeared in a few -next releases and collected some late-
  breaking build-error and warning fixups as a result.

  Summary:

   - Media error handling support in the Block Translation Table (BTT)
     driver is reworked to address sleeping-while-atomic locking and
     memory-allocation-context conflicts.

   - The dax_device lookup overhead for xfs and ext4 is moved out of the
     iomap hot-path to a mount-time lookup.

   - A new 'ecc_unit_size' sysfs attribute is added to advertise the
     read-modify-write boundary property of a persistent memory range.

   - Preparatory fix-ups for arm and powerpc pmem support are included
     along with other miscellaneous fixes"

* tag 'libnvdimm-for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (26 commits)
  libnvdimm, btt: fix format string warnings
  libnvdimm, btt: clean up warning and error messages
  ext4: fix null pointer dereference on sbi
  libnvdimm, nfit: move the check on nd_reserved2 to the endpoint
  dax: fix FS_DAX=n BLOCK=y compilation
  libnvdimm: fix integer overflow static analysis warning
  libnvdimm, nd_blk: remove mmio_flush_range()
  libnvdimm, btt: rework error clearing
  libnvdimm: fix potential deadlock while clearing errors
  libnvdimm, btt: cache sector_size in arena_info
  libnvdimm, btt: ensure that flags were also unchanged during a map_read
  libnvdimm, btt: refactor map entry operations with macros
  libnvdimm, btt: fix a missed NVDIMM_IO_ATOMIC case in the write path
  libnvdimm, nfit: export an 'ecc_unit_size' sysfs attribute
  ext4: perform dax_device lookup at mount
  ext2: perform dax_device lookup at mount
  xfs: perform dax_device lookup at mount
  dax: introduce a fs_dax_get_by_bdev() helper
  libnvdimm, btt: check memory allocation failure
  libnvdimm, label: fix index block size calculation
  ...

arch/x86/Kconfig

@@ -53,7 +53,6 @@ config X86
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV			if X86_64
-	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_PMEM_API		if X86_64
 	# Causing hangs/crashes, see the commit that added this change for details.
 	select ARCH_HAS_REFCOUNT		if BROKEN

arch/x86/include/asm/cacheflush.h

@@ -7,6 +7,4 @@
 
 void clflush_cache_range(void *addr, unsigned int size);
 
-#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
-
 #endif /* _ASM_X86_CACHEFLUSH_H */

drivers/acpi/nfit/Kconfig

@@ -2,7 +2,7 @@ config ACPI_NFIT
 	tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
-	depends on ARCH_HAS_MMIO_FLUSH
+	depends on ARCH_HAS_PMEM_API
 	select LIBNVDIMM
 	help
 	  Infrastructure to probe ACPI 6 compliant platforms for

drivers/acpi/nfit/core.c

@@ -228,6 +228,10 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	if (cmd == ND_CMD_CALL) {
 		call_pkg = buf;
 		func = call_pkg->nd_command;
+
+		for (i = 0; i < ARRAY_SIZE(call_pkg->nd_reserved2); i++)
+			if (call_pkg->nd_reserved2[i])
+				return -EINVAL;
 	}
 
 	if (nvdimm) {
@@ -1674,8 +1678,19 @@ static ssize_t range_index_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(range_index);
 
+static ssize_t ecc_unit_size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);
+
+	return sprintf(buf, "%d\n", nfit_spa->clear_err_unit);
+}
+static DEVICE_ATTR_RO(ecc_unit_size);
+
 static struct attribute *acpi_nfit_region_attributes[] = {
 	&dev_attr_range_index.attr,
+	&dev_attr_ecc_unit_size.attr,
 	NULL,
 };
 
@@ -1804,6 +1819,7 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
 				spa->range_index, i);
+		struct acpi_nfit_control_region *dcr = nfit_mem->dcr;
 
 		if (!memdev || !nfit_mem->dcr) {
 			dev_err(dev, "%s: failed to find DCR\n", __func__);
@@ -1811,13 +1827,13 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 		}
 
 		map->region_offset = memdev->region_offset;
-		map->serial_number = nfit_mem->dcr->serial_number;
+		map->serial_number = dcr->serial_number;
 
 		map2->region_offset = memdev->region_offset;
-		map2->serial_number = nfit_mem->dcr->serial_number;
-		map2->vendor_id = nfit_mem->dcr->vendor_id;
-		map2->manufacturing_date = nfit_mem->dcr->manufacturing_date;
-		map2->manufacturing_location = nfit_mem->dcr->manufacturing_location;
+		map2->serial_number = dcr->serial_number;
+		map2->vendor_id = dcr->vendor_id;
+		map2->manufacturing_date = dcr->manufacturing_date;
+		map2->manufacturing_location = dcr->manufacturing_location;
 	}
 
 	/* v1.1 namespaces */
@@ -1835,6 +1851,28 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 			cmp_map_compat, NULL);
 	nd_set->altcookie = nd_fletcher64(info, sizeof_nfit_set_info(nr), 0);
 
+	/* record the result of the sort for the mapping position */
+	for (i = 0; i < nr; i++) {
+		struct nfit_set_info_map2 *map2 = &info2->mapping[i];
+		int j;
+
+		for (j = 0; j < nr; j++) {
+			struct nd_mapping_desc *mapping = &ndr_desc->mapping[j];
+			struct nvdimm *nvdimm = mapping->nvdimm;
+			struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+			struct acpi_nfit_control_region *dcr = nfit_mem->dcr;
+
+			if (map2->serial_number == dcr->serial_number &&
+			    map2->vendor_id == dcr->vendor_id &&
+			    map2->manufacturing_date == dcr->manufacturing_date &&
+			    map2->manufacturing_location
+				    == dcr->manufacturing_location) {
+				mapping->position = i;
+				break;
+			}
+		}
+	}
+
 	ndr_desc->nd_set = nd_set;
 	devm_kfree(dev, info);
 	devm_kfree(dev, info2);
@@ -1930,7 +1968,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 			memcpy_flushcache(mmio->addr.aperture + offset, iobuf + copied, c);
 		else {
 			if (nfit_blk->dimm_flags & NFIT_BLK_READ_FLUSH)
-				mmio_flush_range((void __force *)
+				arch_invalidate_pmem((void __force *)
 					mmio->addr.aperture + offset, c);
 
 			memcpy(iobuf + copied, mmio->addr.aperture + offset, c);

drivers/dax/super.c

@@ -46,6 +46,8 @@ void dax_read_unlock(int id)
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
 #ifdef CONFIG_BLOCK
+#include <linux/blkdev.h>
+
 int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 		pgoff_t *pgoff)
 {
@@ -59,6 +61,16 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
 }
 EXPORT_SYMBOL(bdev_dax_pgoff);
 
+#if IS_ENABLED(CONFIG_FS_DAX)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+{
+	if (!blk_queue_dax(bdev->bd_queue))
+		return NULL;
+	return fs_dax_get_by_host(bdev->bd_disk->disk_name);
+}
+EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
+#endif
+
 /**
  * __bdev_dax_supported() - Check if the device supports dax for filesystem
  * @sb: The superblock of the device

drivers/nvdimm/btt.c

@@ -31,6 +31,16 @@ enum log_ent_request {
 	LOG_OLD_ENT
 };
 
+static struct device *to_dev(struct arena_info *arena)
+{
+	return &arena->nd_btt->dev;
+}
+
+static u64 adjust_initial_offset(struct nd_btt *nd_btt, u64 offset)
+{
+	return offset + nd_btt->initial_offset;
+}
+
 static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
 		void *buf, size_t n, unsigned long flags)
 {
@@ -38,7 +48,7 @@ static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
 	/* arena offsets may be shifted from the base of the device */
-	offset += arena->nd_btt->initial_offset;
+	offset = adjust_initial_offset(nd_btt, offset);
 	return nvdimm_read_bytes(ndns, offset, buf, n, flags);
 }
 
@@ -49,7 +59,7 @@ static int arena_write_bytes(struct arena_info *arena, resource_size_t offset,
 	struct nd_namespace_common *ndns = nd_btt->ndns;
 
 	/* arena offsets may be shifted from the base of the device */
-	offset += arena->nd_btt->initial_offset;
+	offset = adjust_initial_offset(nd_btt, offset);
 	return nvdimm_write_bytes(ndns, offset, buf, n, flags);
 }
 
@@ -62,8 +72,10 @@ static int btt_info_write(struct arena_info *arena, struct btt_sb *super)
 	 * We rely on that to make sure rw_bytes does error clearing
 	 * correctly, so make sure that is the case.
 	 */
-	WARN_ON_ONCE(!IS_ALIGNED(arena->infooff, 512));
-	WARN_ON_ONCE(!IS_ALIGNED(arena->info2off, 512));
+	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->infooff, 512),
+		"arena->infooff: %#llx is unaligned\n", arena->infooff);
+	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->info2off, 512),
+		"arena->info2off: %#llx is unaligned\n", arena->info2off);
 
 	ret = arena_write_bytes(arena, arena->info2off, super,
 			sizeof(struct btt_sb), 0);
@@ -76,7 +88,6 @@ static int btt_info_write(struct arena_info *arena, struct btt_sb *super)
 
 static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
 {
-	WARN_ON(!super);
 	return arena_read_bytes(arena, arena->infooff, super,
 			sizeof(struct btt_sb), 0);
 }
@@ -92,7 +103,10 @@ static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping,
 {
 	u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
 
-	WARN_ON(lba >= arena->external_nlba);
+	if (unlikely(lba >= arena->external_nlba))
+		dev_err_ratelimited(to_dev(arena),
+			"%s: lba %#x out of range (max: %#x)\n",
+			__func__, lba, arena->external_nlba);
 	return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE, flags);
 }
 
@@ -106,7 +120,7 @@ static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
 	 * This 'mapping' is supposed to be just the LBA mapping, without
 	 * any flags set, so strip the flag bits.
 	 */
-	mapping &= MAP_LBA_MASK;
+	mapping = ent_lba(mapping);
 
 	ze = (z_flag << 1) + e_flag;
 	switch (ze) {
@@ -131,7 +145,8 @@ static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
 		 * construed as a valid 'normal' case, but we decide not to,
 		 * to avoid confusion
 		 */
-		WARN_ONCE(1, "Invalid use of Z and E flags\n");
+		dev_err_ratelimited(to_dev(arena),
+			"Invalid use of Z and E flags\n");
 		return -EIO;
 	}
 
@@ -147,7 +162,10 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
 	u32 raw_mapping, postmap, ze, z_flag, e_flag;
 	u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);
 
-	WARN_ON(lba >= arena->external_nlba);
+	if (unlikely(lba >= arena->external_nlba))
+		dev_err_ratelimited(to_dev(arena),
+			"%s: lba %#x out of range (max: %#x)\n",
+			__func__, lba, arena->external_nlba);
 
 	ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE, rwb_flags);
 	if (ret)
@@ -155,10 +173,10 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
 
 	raw_mapping = le32_to_cpu(in);
 
-	z_flag = (raw_mapping & MAP_TRIM_MASK) >> MAP_TRIM_SHIFT;
-	e_flag = (raw_mapping & MAP_ERR_MASK) >> MAP_ERR_SHIFT;
+	z_flag = ent_z_flag(raw_mapping);
+	e_flag = ent_e_flag(raw_mapping);
 	ze = (z_flag << 1) + e_flag;
-	postmap = raw_mapping & MAP_LBA_MASK;
+	postmap = ent_lba(raw_mapping);
 
 	/* Reuse the {z,e}_flag variables for *trim and *error */
 	z_flag = 0;
@@ -195,7 +213,6 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
 static int btt_log_read_pair(struct arena_info *arena, u32 lane,
 			struct log_entry *ent)
 {
-	WARN_ON(!ent);
 	return arena_read_bytes(arena,
 			arena->logoff + (2 * lane * LOG_ENT_SIZE), ent,
 			2 * LOG_ENT_SIZE, 0);
@@ -299,11 +316,6 @@ static int btt_log_get_old(struct log_entry *ent)
 	return old;
 }
 
-static struct device *to_dev(struct arena_info *arena)
-{
-	return &arena->nd_btt->dev;
-}
-
 /*
  * This function copies the desired (old/new) log entry into ent if
  * it is not NULL. It returns the sub-slot number (0 or 1)
@@ -381,7 +393,9 @@ static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
 	arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
 	if (++(arena->freelist[lane].seq) == 4)
 		arena->freelist[lane].seq = 1;
-	arena->freelist[lane].block = le32_to_cpu(ent->old_map);
+	if (ent_e_flag(ent->old_map))
+		arena->freelist[lane].has_err = 1;
+	arena->freelist[lane].block = le32_to_cpu(ent_lba(ent->old_map));
 
 	return ret;
 }
@@ -407,12 +421,14 @@ static int btt_map_init(struct arena_info *arena)
 	 * make sure rw_bytes does error clearing correctly, so make sure that
 	 * is the case.
 	 */
-	WARN_ON_ONCE(!IS_ALIGNED(arena->mapoff, 512));
+	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->mapoff, 512),
+		"arena->mapoff: %#llx is unaligned\n", arena->mapoff);
 
 	while (mapsize) {
 		size_t size = min(mapsize, chunk_size);
 
-		WARN_ON_ONCE(size < 512);
+		dev_WARN_ONCE(to_dev(arena), size < 512,
+			"chunk size: %#zx is unaligned\n", size);
 		ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf,
 				size, 0);
 		if (ret)
@@ -449,12 +465,14 @@ static int btt_log_init(struct arena_info *arena)
 	 * make sure rw_bytes does error clearing correctly, so make sure that
 	 * is the case.
 	 */
-	WARN_ON_ONCE(!IS_ALIGNED(arena->logoff, 512));
+	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->logoff, 512),
+		"arena->logoff: %#llx is unaligned\n", arena->logoff);
 
 	while (logsize) {
 		size_t size = min(logsize, chunk_size);
 
-		WARN_ON_ONCE(size < 512);
+		dev_WARN_ONCE(to_dev(arena), size < 512,
+			"chunk size: %#zx is unaligned\n", size);
 		ret = arena_write_bytes(arena, arena->logoff + offset, zerobuf,
 				size, 0);
 		if (ret)
@@ -480,6 +498,40 @@ static int btt_log_init(struct arena_info *arena)
 	return ret;
 }
 
+static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
+{
+	return arena->dataoff + ((u64)lba * arena->internal_lbasize);
+}
+
+static int arena_clear_freelist_error(struct arena_info *arena, u32 lane)
+{
+	int ret = 0;
+
+	if (arena->freelist[lane].has_err) {
+		void *zero_page = page_address(ZERO_PAGE(0));
+		u32 lba = arena->freelist[lane].block;
+		u64 nsoff = to_namespace_offset(arena, lba);
+		unsigned long len = arena->sector_size;
+
+		mutex_lock(&arena->err_lock);
+
+		while (len) {
+			unsigned long chunk = min(len, PAGE_SIZE);
+
+			ret = arena_write_bytes(arena, nsoff, zero_page,
+				chunk, 0);
+			if (ret)
+				break;
+			len -= chunk;
+			nsoff += chunk;
+			if (len == 0)
+				arena->freelist[lane].has_err = 0;
+		}
+		mutex_unlock(&arena->err_lock);
+	}
+	return ret;
+}
+
 static int btt_freelist_init(struct arena_info *arena)
 {
 	int old, new, ret;
@@ -505,6 +557,17 @@ static int btt_freelist_init(struct arena_info *arena)
 		arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
 		arena->freelist[i].block = le32_to_cpu(log_new.old_map);
 
+		/*
+		 * FIXME: if error clearing fails during init, we want to make
+		 * the BTT read-only
+		 */
+		if (ent_e_flag(log_new.old_map)) {
+			ret = arena_clear_freelist_error(arena, i);
+			if (ret)
+				dev_err_ratelimited(to_dev(arena),
+					"Unable to clear known errors\n");
+		}
+
 		/* This implies a newly created or untouched flog entry */
 		if (log_new.old_map == log_new.new_map)
 			continue;
@@ -525,7 +588,6 @@ static int btt_freelist_init(struct arena_info *arena)
 			if (ret)
 				return ret;
 		}
-
 	}
 
 	return 0;
@@ -566,6 +628,7 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size,
 	if (!arena)
 		return NULL;
 	arena->nd_btt = btt->nd_btt;
+	arena->sector_size = btt->sector_size;
 
 	if (!size)
 		return arena;
@@ -694,6 +757,7 @@ static int discover_arenas(struct btt *btt)
 		arena->external_lba_start = cur_nlba;
 		parse_arena_meta(arena, super, cur_off);
 
+		mutex_init(&arena->err_lock);
 		ret = btt_freelist_init(arena);
 		if (ret)
 			goto out;
@@ -904,11 +968,6 @@ static void unlock_map(struct arena_info *arena, u32 premap)
 	spin_unlock(&arena->map_locks[idx].lock);
 }
 
-static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
-{
-	return arena->dataoff + ((u64)lba * arena->internal_lbasize);
-}
-
 static int btt_data_read(struct arena_info *arena, struct page *page,
 			unsigned int off, u32 lba, u32 len)
 {
@@ -1032,6 +1091,7 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
 		 */
 		while (1) {
 			u32 new_map;
+			int new_t, new_e;
 
 			if (t_flag) {
 				zero_fill_data(page, off, cur_len);
@@ -1050,20 +1110,29 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
 			 */
 			barrier();
 
-			ret = btt_map_read(arena, premap, &new_map, &t_flag,
-						&e_flag, NVDIMM_IO_ATOMIC);
+			ret = btt_map_read(arena, premap, &new_map, &new_t,
+						&new_e, NVDIMM_IO_ATOMIC);
 			if (ret)
 				goto out_rtt;
 
-			if (postmap == new_map)
+			if ((postmap == new_map) && (t_flag == new_t) &&
+					(e_flag == new_e))
 				break;
 
 			postmap = new_map;
+			t_flag = new_t;
+			e_flag = new_e;
 		}
 
 		ret = btt_data_read(arena, page, off, postmap, cur_len);
-		if (ret)
+		if (ret) {
+			int rc;
+
+			/* Media error - set the e_flag */
+			rc = btt_map_write(arena, premap, postmap, 0, 1,
+				NVDIMM_IO_ATOMIC);
 			goto out_rtt;
+		}
 
 		if (bip) {
 			ret = btt_rw_integrity(btt, bip, arena, postmap, READ);
@@ -1088,6 +1157,21 @@ static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
 	return ret;
 }
 
+/*
+ * Normally, arena_{read,write}_bytes will take care of the initial offset
+ * adjustment, but in the case of btt_is_badblock, where we query is_bad_pmem,
+ * we need the final, raw namespace offset here
+ */
+static bool btt_is_badblock(struct btt *btt, struct arena_info *arena,
+		u32 postmap)
+{
+	u64 nsoff = adjust_initial_offset(arena->nd_btt,
+			to_namespace_offset(arena, postmap));
+	sector_t phys_sector = nsoff >> 9;
+
+	return is_bad_pmem(btt->phys_bb, phys_sector, arena->internal_lbasize);
+}
+
 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)
@@ -1100,7 +1184,9 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 	while (len) {
 		u32 cur_len;
+		int e_flag;
 
+ retry:
 		lane = nd_region_acquire_lane(btt->nd_region);
 
 		ret = lba_to_arena(btt, sector, &premap, &arena);
@@ -1113,6 +1199,21 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 			goto out_lane;
 		}
 
+		if (btt_is_badblock(btt, arena, arena->freelist[lane].block))
+			arena->freelist[lane].has_err = 1;
+
+		if (mutex_is_locked(&arena->err_lock)
+				|| arena->freelist[lane].has_err) {
+			nd_region_release_lane(btt->nd_region, lane);
+
+			ret = arena_clear_freelist_error(arena, lane);
+			if (ret)
+				return ret;
+
+			/* OK to acquire a different lane/free block */
+			goto retry;
+		}
+
 		new_postmap = arena->freelist[lane].block;
 
 		/* Wait if the new block is being read from */
@@ -1138,7 +1239,7 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 		}
 
 		lock_map(arena, premap);
-		ret = btt_map_read(arena, premap, &old_postmap, NULL, NULL,
+		ret = btt_map_read(arena, premap, &old_postmap, NULL, &e_flag,
 				NVDIMM_IO_ATOMIC);
 		if (ret)
 			goto out_map;
@@ -1146,6 +1247,8 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 			ret = -EIO;
 			goto out_map;
 		}
+		if (e_flag)
+			set_e_flag(old_postmap);
 
 		log.lba = cpu_to_le32(premap);
 		log.old_map = cpu_to_le32(old_postmap);
@@ -1156,13 +1259,20 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 		if (ret)
 			goto out_map;
 
-		ret = btt_map_write(arena, premap, new_postmap, 0, 0, 0);
+		ret = btt_map_write(arena, premap, new_postmap, 0, 0,
+			NVDIMM_IO_ATOMIC);
 		if (ret)
 			goto out_map;
 
 		unlock_map(arena, premap);
 		nd_region_release_lane(btt->nd_region, lane);
 
+		if (e_flag) {
+			ret = arena_clear_freelist_error(arena, lane);
+			if (ret)
+				return ret;
+		}
+
 		len -= cur_len;
 		off += cur_len;
 		sector += btt->sector_size >> SECTOR_SHIFT;
@@ -1211,11 +1321,13 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 
-		BUG_ON(len > PAGE_SIZE);
-		/* Make sure len is in multiples of sector size. */
-		/* XXX is this right? */
-		BUG_ON(len < btt->sector_size);
-		BUG_ON(len % btt->sector_size);
+		if (len > PAGE_SIZE || len < btt->sector_size ||
+				len % btt->sector_size) {
+			dev_err_ratelimited(&btt->nd_btt->dev,
+				"unaligned bio segment (len: %d)\n", len);
+			bio->bi_status = BLK_STS_IOERR;
+			break;
+		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
 				  op_is_write(bio_op(bio)), iter.bi_sector);
@@ -1345,6 +1457,7 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 {
 	int ret;
 	struct btt *btt;
+	struct nd_namespace_io *nsio;
 	struct device *dev = &nd_btt->dev;
 
 	btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL);
@@ -1358,6 +1471,8 @@ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
 	INIT_LIST_HEAD(&btt->arena_list);
 	mutex_init(&btt->init_lock);
 	btt->nd_region = nd_region;
+	nsio = to_nd_namespace_io(&nd_btt->ndns->dev);
+	btt->phys_bb = &nsio->bb;
 
 	ret = discover_arenas(btt);
 	if (ret) {
@@ -1431,6 +1546,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
 	}
 
 	btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL);
+	if (!btt_sb)
+		return -ENOMEM;
 
 	/*
 	 * If this returns < 0, that is ok as it just means there wasn't

drivers/nvdimm/btt.h

@@ -15,6 +15,7 @@
 #ifndef _LINUX_BTT_H
 #define _LINUX_BTT_H
 
+#include <linux/badblocks.h>
 #include <linux/types.h>
 
 #define BTT_SIG_LEN 16
@@ -38,6 +39,11 @@
 #define IB_FLAG_ERROR 0x00000001
 #define IB_FLAG_ERROR_MASK 0x00000001
 
+#define ent_lba(ent) (ent & MAP_LBA_MASK)
+#define ent_e_flag(ent) (!!(ent & MAP_ERR_MASK))
+#define ent_z_flag(ent) (!!(ent & MAP_TRIM_MASK))
+#define set_e_flag(ent) (ent |= MAP_ERR_MASK)
+
 enum btt_init_state {
 	INIT_UNCHECKED = 0,
 	INIT_NOTFOUND,
@@ -78,6 +84,7 @@ struct free_entry {
 	u32 block;
 	u8 sub;
 	u8 seq;
+	u8 has_err;
 };
 
 struct aligned_lock {
@@ -104,6 +111,7 @@ struct aligned_lock {
  *			handle incoming writes.
  * @version_major:	Metadata layout version major.
  * @version_minor:	Metadata layout version minor.
+ * @sector_size:	The Linux sector size - 512 or 4096
  * @nextoff:		Offset in bytes to the start of the next arena.
  * @infooff:		Offset in bytes to the info block of this arena.
  * @dataoff:		Offset in bytes to the data area of this arena.
@@ -131,6 +139,7 @@ struct arena_info {
 	u32 nfree;
 	u16 version_major;
 	u16 version_minor;
+	u32 sector_size;
 	/* Byte offsets to the different on-media structures */
 	u64 nextoff;
 	u64 infooff;
@@ -147,6 +156,7 @@ struct arena_info {
 	struct dentry *debugfs_dir;
 	/* Arena flags */
 	u32 flags;
+	struct mutex err_lock;
 };
 
 /**
@@ -181,6 +191,7 @@ struct btt {
 	struct mutex init_lock;
 	int init_state;
 	int num_arenas;
+	struct badblocks *phys_bb;
 };
 
 bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super);

drivers/nvdimm/btt_devs.c

@@ -61,7 +61,7 @@ static ssize_t sector_size_show(struct device *dev,
 {
 	struct nd_btt *nd_btt = to_nd_btt(dev);
 
-	return nd_sector_size_show(nd_btt->lbasize, btt_lbasize_supported, buf);
+	return nd_size_select_show(nd_btt->lbasize, btt_lbasize_supported, buf);
 }
 
 static ssize_t sector_size_store(struct device *dev,
@@ -72,7 +72,7 @@ static ssize_t sector_size_store(struct device *dev,
 
 	device_lock(dev);
 	nvdimm_bus_lock(dev);
-	rc = nd_sector_size_store(dev, buf, &nd_btt->lbasize,
+	rc = nd_size_select_store(dev, buf, &nd_btt->lbasize,
 			btt_lbasize_supported);
 	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
 			rc, buf, buf[len - 1] == '\n' ? "" : "\n");

drivers/nvdimm/bus.c

@@ -11,6 +11,7 @@
  * General Public License for more details.
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/sched/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
@@ -234,6 +235,7 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 	struct nd_cmd_clear_error clear_err;
 	struct nd_cmd_ars_cap ars_cap;
 	u32 clear_err_unit, mask;
+	unsigned int noio_flag;
 	int cmd_rc, rc;
 
 	if (!nvdimm_bus)
@@ -250,8 +252,10 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 	memset(&ars_cap, 0, sizeof(ars_cap));
 	ars_cap.address = phys;
 	ars_cap.length = len;
+	noio_flag = memalloc_noio_save();
 	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, &ars_cap,
 			sizeof(ars_cap), &cmd_rc);
+	memalloc_noio_restore(noio_flag);
 	if (rc < 0)
 		return rc;
 	if (cmd_rc < 0)
@@ -266,8 +270,10 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 	memset(&clear_err, 0, sizeof(clear_err));
 	clear_err.address = phys;
 	clear_err.length = len;
+	noio_flag = memalloc_noio_save();
 	rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_CLEAR_ERROR, &clear_err,
 			sizeof(clear_err), &cmd_rc);
+	memalloc_noio_restore(noio_flag);
 	if (rc < 0)
 		return rc;
 	if (cmd_rc < 0)
@@ -905,19 +911,20 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		int read_only, unsigned int ioctl_cmd, unsigned long arg)
 {
 	struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
-	size_t buf_len = 0, in_len = 0, out_len = 0;
 	static char out_env[ND_CMD_MAX_ENVELOPE];
 	static char in_env[ND_CMD_MAX_ENVELOPE];
 	const struct nd_cmd_desc *desc = NULL;
 	unsigned int cmd = _IOC_NR(ioctl_cmd);
-	unsigned int func = cmd;
-	void __user *p = (void __user *) arg;
 	struct device *dev = &nvdimm_bus->dev;
-	struct nd_cmd_pkg pkg;
+	void __user *p = (void __user *) arg;
 	const char *cmd_name, *dimm_name;
+	u32 in_len = 0, out_len = 0;
+	unsigned int func = cmd;
 	unsigned long cmd_mask;
-	void *buf;
+	struct nd_cmd_pkg pkg;
 	int rc, i, cmd_rc;
+	u64 buf_len = 0;
+	void *buf;
 
 	if (nvdimm) {
 		desc = nd_cmd_dimm_desc(cmd);
@@ -977,13 +984,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 
 	if (cmd == ND_CMD_CALL) {
 		func = pkg.nd_command;
-		dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n",
+		dev_dbg(dev, "%s:%s, idx: %llu, in: %u, out: %u, len %llu\n",
 				__func__, dimm_name, pkg.nd_command,
 				in_len, out_len, buf_len);
-
-		for (i = 0; i < ARRAY_SIZE(pkg.nd_reserved2); i++)
-			if (pkg.nd_reserved2[i])
-				return -EINVAL;
 	}
 
 	/* process an output envelope */
@@ -1007,9 +1010,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm,
 		out_len += out_size;
 	}
 
-	buf_len = out_len + in_len;
+	buf_len = (u64) out_len + (u64) in_len;
 	if (buf_len > ND_IOCTL_MAX_BUFLEN) {
-		dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
+		dev_dbg(dev, "%s:%s cmd: %s buf_len: %llu > %d\n", __func__,
 				dimm_name, cmd_name, buf_len,
 				ND_IOCTL_MAX_BUFLEN);
 		return -EINVAL;

drivers/nvdimm/claim.c

@@ -280,18 +280,11 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
-		/*
-		 * FIXME: nsio_rw_bytes() may be called from atomic
-		 * context in the btt case and the ACPI DSM path for
-		 * clearing the error takes sleeping locks and allocates
-		 * memory. An explicit error clearing path, and support
-		 * for tracking badblocks in BTT metadata is needed to
-		 * work around this collision.
-		 */
 		if (IS_ALIGNED(offset, 512) && IS_ALIGNED(size, 512)
 				&& !(flags & NVDIMM_IO_ATOMIC)) {
 			long cleared;
 
+			might_sleep();
 			cleared = nvdimm_clear_poison(&ndns->dev,
 					nsio->res.start + offset, size);
 			if (cleared < size)

drivers/nvdimm/core.c

@@ -277,14 +277,14 @@ int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
 	return 0;
 }
 
-ssize_t nd_sector_size_show(unsigned long current_lbasize,
+ssize_t nd_size_select_show(unsigned long current_size,
 		const unsigned long *supported, char *buf)
 {
 	ssize_t len = 0;
 	int i;
 
 	for (i = 0; supported[i]; i++)
-		if (current_lbasize == supported[i])
+		if (current_size == supported[i])
 			len += sprintf(buf + len, "[%ld] ", supported[i]);
 		else
 			len += sprintf(buf + len, "%ld ", supported[i]);
@@ -292,8 +292,8 @@ ssize_t nd_sector_size_show(unsigned long current_lbasize,
 	return len;
 }
 
-ssize_t nd_sector_size_store(struct device *dev, const char *buf,
-		unsigned long *current_lbasize, const unsigned long *supported)
+ssize_t nd_size_select_store(struct device *dev, const char *buf,
+		unsigned long *current_size, const unsigned long *supported)
 {
 	unsigned long lbasize;
 	int rc, i;
@@ -310,7 +310,7 @@ ssize_t nd_sector_size_store(struct device *dev, const char *buf,
 			break;
 
 	if (supported[i]) {
-		*current_lbasize = lbasize;
+		*current_size = lbasize;
 		return 0;
 	} else {
 		return -EINVAL;

drivers/nvdimm/label.c

@@ -45,12 +45,14 @@ unsigned sizeof_namespace_label(struct nvdimm_drvdata *ndd)
 	return ndd->nslabel_size;
 }
 
-size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd)
+int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd)
 {
-	u32 index_span;
+	return ndd->nsarea.config_size / (sizeof_namespace_label(ndd) + 1);
+}
 
-	if (ndd->nsindex_size)
-		return ndd->nsindex_size;
+size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd)
+{
+	u32 nslot, space, size;
 
 	/*
 	 * The minimum index space is 512 bytes, with that amount of
@@ -60,16 +62,16 @@ size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd)
 	 * starts to waste space at larger config_sizes, but it's
 	 * unlikely we'll ever see anything but 128K.
 	 */
-	index_span = ndd->nsarea.config_size / (sizeof_namespace_label(ndd) + 1);
-	index_span /= NSINDEX_ALIGN * 2;
-	ndd->nsindex_size = index_span * NSINDEX_ALIGN;
-
-	return ndd->nsindex_size;
-}
-
-int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd)
-{
-	return ndd->nsarea.config_size / (sizeof_namespace_label(ndd) + 1);
+	nslot = nvdimm_num_label_slots(ndd);
+	space = ndd->nsarea.config_size - nslot * sizeof_namespace_label(ndd);
+	size = ALIGN(sizeof(struct nd_namespace_index) + DIV_ROUND_UP(nslot, 8),
+			NSINDEX_ALIGN) * 2;
+	if (size <= space)
+		return size / 2;
+
+	dev_err(ndd->dev, "label area (%d) too small to host (%d byte) labels\n",
+			ndd->nsarea.config_size, sizeof_namespace_label(ndd));
+	return 0;
 }
 
 static int __nd_label_validate(struct nvdimm_drvdata *ndd)

drivers/nvdimm/namespace_devs.c

@@ -1313,14 +1313,14 @@ static ssize_t sector_size_show(struct device *dev,
 	if (is_namespace_blk(dev)) {
 		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
 
-		return nd_sector_size_show(nsblk->lbasize,
+		return nd_size_select_show(nsblk->lbasize,
 				blk_lbasize_supported, buf);
 	}
 
 	if (is_namespace_pmem(dev)) {
 		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
 
-		return nd_sector_size_show(nspm->lbasize,
+		return nd_size_select_show(nspm->lbasize,
 				pmem_lbasize_supported, buf);
 	}
 	return -ENXIO;
@@ -1352,7 +1352,7 @@ static ssize_t sector_size_store(struct device *dev,
 	if (to_ndns(dev)->claim)
 		rc = -EBUSY;
 	if (rc >= 0)
-		rc = nd_sector_size_store(dev, buf, lbasize, supported);
+		rc = nd_size_select_store(dev, buf, lbasize, supported);
 	if (rc >= 0)
 		rc = nd_namespace_label_update(nd_region, dev);
 	dev_dbg(dev, "%s: result: %zd %s: %s%s", __func__,

drivers/nvdimm/nd.h

@@ -42,7 +42,7 @@ struct nd_poison {
 
 struct nvdimm_drvdata {
 	struct device *dev;
-	int nsindex_size, nslabel_size;
+	int nslabel_size;
 	struct nd_cmd_get_config_size nsarea;
 	void *data;
 	int ns_current, ns_next;
@@ -134,6 +134,7 @@ struct nd_mapping {
 	struct nvdimm *nvdimm;
 	u64 start;
 	u64 size;
+	int position;
 	struct list_head labels;
 	struct mutex lock;
 	/*
@@ -233,10 +234,10 @@ void nd_device_unregister(struct device *dev, enum nd_async_mode mode);
 void nd_device_notify(struct device *dev, enum nvdimm_event event);
 int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
 		size_t len);
-ssize_t nd_sector_size_show(unsigned long current_lbasize,
+ssize_t nd_size_select_show(unsigned long current_size,
 		const unsigned long *supported, char *buf);
-ssize_t nd_sector_size_store(struct device *dev, const char *buf,
-		unsigned long *current_lbasize, const unsigned long *supported);
+ssize_t nd_size_select_store(struct device *dev, const char *buf,
+		unsigned long *current_size, const unsigned long *supported);
 int __init nvdimm_init(void);
 int __init nd_region_init(void);
 int __init nd_label_init(void);
@@ -285,6 +286,13 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 
 struct nd_pfn *to_nd_pfn(struct device *dev);
 #if IS_ENABLED(CONFIG_NVDIMM_PFN)
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PFN_DEFAULT_ALIGNMENT HPAGE_PMD_SIZE
+#else
+#define PFN_DEFAULT_ALIGNMENT PAGE_SIZE
+#endif
+
 int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_pfn(struct device *dev);
 struct device *nd_pfn_create(struct nd_region *nd_region);

drivers/nvdimm/pfn_devs.c

@@ -111,24 +111,27 @@ static ssize_t align_show(struct device *dev,
 	return sprintf(buf, "%ld\n", nd_pfn->align);
 }
 
-static ssize_t __align_store(struct nd_pfn *nd_pfn, const char *buf)
+static const unsigned long *nd_pfn_supported_alignments(void)
 {
-	unsigned long val;
-	int rc;
-
-	rc = kstrtoul(buf, 0, &val);
-	if (rc)
-		return rc;
-
-	if (!is_power_of_2(val) || val < PAGE_SIZE || val > SZ_1G)
-		return -EINVAL;
+	/*
+	 * This needs to be a non-static variable because the *_SIZE
+	 * macros aren't always constants.
+	 */
+	const unsigned long supported_alignments[] = {
+		PAGE_SIZE,
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		HPAGE_PMD_SIZE,
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+		HPAGE_PUD_SIZE,
+#endif
+#endif
+		0,
+	};
+	static unsigned long data[ARRAY_SIZE(supported_alignments)];
 
-	if (nd_pfn->dev.driver)
-		return -EBUSY;
-	else
-		nd_pfn->align = val;
+	memcpy(data, supported_alignments, sizeof(data));
 
-	return 0;
+	return data;
 }
 
 static ssize_t align_store(struct device *dev,
@@ -139,7 +142,8 @@ static ssize_t align_store(struct device *dev,
 
 	device_lock(dev);
 	nvdimm_bus_lock(dev);
-	rc = __align_store(nd_pfn, buf);
+	rc = nd_size_select_store(dev, buf, &nd_pfn->align,
+			nd_pfn_supported_alignments());
 	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
 			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
 	nvdimm_bus_unlock(dev);
@@ -260,6 +264,13 @@ static ssize_t size_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(size);
 
+static ssize_t supported_alignments_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	return nd_size_select_show(0, nd_pfn_supported_alignments(), buf);
+}
+static DEVICE_ATTR_RO(supported_alignments);
+
 static struct attribute *nd_pfn_attributes[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_namespace.attr,
@@ -267,6 +278,7 @@ static struct attribute *nd_pfn_attributes[] = {
 	&dev_attr_align.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_size.attr,
+	&dev_attr_supported_alignments.attr,
 	NULL,
 };
 
@@ -290,7 +302,7 @@ struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
 		return NULL;
 
 	nd_pfn->mode = PFN_MODE_NONE;
-	nd_pfn->align = HPAGE_SIZE;
+	nd_pfn->align = PFN_DEFAULT_ALIGNMENT;
 	dev = &nd_pfn->dev;
 	device_initialize(&nd_pfn->dev);
 	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
@@ -638,11 +650,12 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 			/ PAGE_SIZE);
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*
-		 * vmemmap_populate_hugepages() allocates the memmap array in
-		 * HPAGE_SIZE chunks.
+		 * The altmap should be padded out to the block size used
+		 * when populating the vmemmap. This *should* be equal to
+		 * PMD_SIZE for most architectures.
 		 */
 		offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
-				max(nd_pfn->align, HPAGE_SIZE)) - start;
+				max(nd_pfn->align, PMD_SIZE)) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
 		offset = ALIGN(start + SZ_8K + dax_label_reserve,
 				nd_pfn->align) - start;

drivers/nvdimm/pmem.h

@@ -5,20 +5,6 @@
 #include <linux/pfn_t.h>
 #include <linux/fs.h>
 
-#ifdef CONFIG_ARCH_HAS_PMEM_API
-#define ARCH_MEMREMAP_PMEM MEMREMAP_WB
-void arch_wb_cache_pmem(void *addr, size_t size);
-void arch_invalidate_pmem(void *addr, size_t size);
-#else
-#define ARCH_MEMREMAP_PMEM MEMREMAP_WT
-static inline void arch_wb_cache_pmem(void *addr, size_t size)
-{
-}
-static inline void arch_invalidate_pmem(void *addr, size_t size)
-{
-}
-#endif
-
 /* this definition is in it's own header for tools/testing/nvdimm to consume */
 struct pmem_device {
 	/* One contiguous memory region per device */

drivers/nvdimm/region_devs.c

@@ -723,8 +723,9 @@ static ssize_t mappingN(struct device *dev, char *buf, int n)
 	nd_mapping = &nd_region->mapping[n];
 	nvdimm = nd_mapping->nvdimm;
 
-	return sprintf(buf, "%s,%llu,%llu\n", dev_name(&nvdimm->dev),
-			nd_mapping->start, nd_mapping->size);
+	return sprintf(buf, "%s,%llu,%llu,%d\n", dev_name(&nvdimm->dev),
+			nd_mapping->start, nd_mapping->size,
+			nd_mapping->position);
 }
 
 #define REGION_MAPPING(idx) \
@@ -965,6 +966,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 		nd_region->mapping[i].nvdimm = nvdimm;
 		nd_region->mapping[i].start = mapping->start;
 		nd_region->mapping[i].size = mapping->size;
+		nd_region->mapping[i].position = mapping->position;
 		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
 		mutex_init(&nd_region->mapping[i].lock);
 

fs/ext2/ext2.h

@@ -114,6 +114,7 @@ struct ext2_sb_info {
 	 */
 	spinlock_t s_lock;
 	struct mb_cache *s_ea_block_cache;
+	struct dax_device *s_daxdev;
 };
 
 static inline spinlock_t *

fs/ext2/inode.c

@@ -800,10 +800,10 @@ int ext2_get_block(struct inode *inode, sector_t iblock,
 static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		unsigned flags, struct iomap *iomap)
 {
-	struct block_device *bdev;
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;
 	unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
+	struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb);
 	bool new = false, boundary = false;
 	u32 bno;
 	int ret;
@@ -814,13 +814,9 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		return ret;
 
 	iomap->flags = 0;
-	bdev = inode->i_sb->s_bdev;
-	iomap->bdev = bdev;
+	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64)first_block << blkbits;
-	if (blk_queue_dax(bdev->bd_queue))
-		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
-	else
-		iomap->dax_dev = NULL;
+	iomap->dax_dev = sbi->s_daxdev;
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
@@ -842,7 +838,6 @@ static int
 ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 		ssize_t written, unsigned flags, struct iomap *iomap)
 {
-	fs_put_dax(iomap->dax_dev);
 	if (iomap->type == IOMAP_MAPPED &&
 	    written < length &&
 	    (flags & IOMAP_WRITE))

fs/ext2/super.c

@@ -171,6 +171,7 @@ static void ext2_put_super (struct super_block * sb)
 	brelse (sbi->s_sbh);
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
+	fs_put_dax(sbi->s_daxdev);
 	kfree(sbi);
 }
 
@@ -813,6 +814,7 @@ static unsigned long descriptor_loc(struct super_block *sb,
 
 static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 {
+	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	struct buffer_head * bh;
 	struct ext2_sb_info * sbi;
 	struct ext2_super_block * es;
@@ -842,6 +844,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
+	sbi->s_daxdev = dax_dev;
 
 	spin_lock_init(&sbi->s_lock);
 
@@ -1200,6 +1203,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
 failed:
+	fs_put_dax(dax_dev);
 	return ret;
 }
 

fs/ext4/ext4.h

@@ -1526,6 +1526,7 @@ struct ext4_sb_info {
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
+	struct dax_device *s_daxdev;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)

fs/ext4/inode.c

@@ -3397,7 +3397,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
-	struct block_device *bdev;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;
 	unsigned long last_block = (offset + length - 1) >> blkbits;
@@ -3466,12 +3466,8 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	}
 
 	iomap->flags = 0;
-	bdev = inode->i_sb->s_bdev;
-	iomap->bdev = bdev;
-	if (blk_queue_dax(bdev->bd_queue))
-		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
-	else
-		iomap->dax_dev = NULL;
+	iomap->bdev = inode->i_sb->s_bdev;
+	iomap->dax_dev = sbi->s_daxdev;
 	iomap->offset = first_block << blkbits;
 
 	if (ret == 0) {
@@ -3504,7 +3500,6 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 	int blkbits = inode->i_blkbits;
 	bool truncate = false;
 
-	fs_put_dax(iomap->dax_dev);
 	if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
 		return 0;
 

fs/ext4/super.c

@@ -951,6 +951,7 @@ static void ext4_put_super(struct super_block *sb)
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
+	fs_put_dax(sbi->s_daxdev);
 	kfree(sbi);
 }
 
@@ -3398,6 +3399,7 @@ static void ext4_set_resv_clusters(struct super_block *sb)
 
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 {
+	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
 	struct ext4_super_block *es = NULL;
@@ -3423,6 +3425,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	if ((data && !orig_data) || !sbi)
 		goto out_free_base;
 
+	sbi->s_daxdev = dax_dev;
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
 	if (!sbi->s_blockgroup_lock)
@@ -4399,6 +4402,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 out_free_base:
 	kfree(sbi);
 	kfree(orig_data);
+	fs_put_dax(dax_dev);
 	return err ? err : ret;
 }
 

fs/xfs/xfs_aops.c

@@ -80,6 +80,19 @@ xfs_find_bdev_for_inode(
 		return mp->m_ddev_targp->bt_bdev;
 }
 
+struct dax_device *
+xfs_find_daxdev_for_inode(
+	struct inode		*inode)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (XFS_IS_REALTIME_INODE(ip))
+		return mp->m_rtdev_targp->bt_daxdev;
+	else
+		return mp->m_ddev_targp->bt_daxdev;
+}
+
 /*
  * We're now finished for good with this page.  Update the page state via the
  * associated buffer_heads, paying attention to the start and end offsets that

fs/xfs/xfs_aops.h

@@ -59,5 +59,6 @@ int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
 extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
+extern struct dax_device *xfs_find_daxdev_for_inode(struct inode *);
 
 #endif /* __XFS_AOPS_H__ */

fs/xfs/xfs_buf.c

@@ -1802,7 +1802,8 @@ xfs_setsize_buftarg_early(
 xfs_buftarg_t *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct block_device	*bdev)
+	struct block_device	*bdev,
+	struct dax_device	*dax_dev)
 {
 	xfs_buftarg_t		*btp;
 
@@ -1811,6 +1812,7 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
+	btp->bt_daxdev = dax_dev;
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;

fs/xfs/xfs_buf.h

@@ -108,6 +108,7 @@ typedef unsigned int xfs_buf_flags_t;
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
+	struct dax_device	*bt_daxdev;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
@@ -385,7 +386,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
  *	Handling of buftargs.
  */
 extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
-			struct block_device *);
+			struct block_device *, struct dax_device *);
 extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
 extern void xfs_wait_buftarg(xfs_buftarg_t *);
 extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);

fs/xfs/xfs_iomap.c

@@ -69,6 +69,7 @@ xfs_bmbt_to_iomap(
 	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
 	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
+	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
 }
 
 xfs_extlen_t
@@ -975,7 +976,6 @@ xfs_file_iomap_begin(
 	int			nimaps = 1, error = 0;
 	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
-	struct block_device	*bdev;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -1085,13 +1085,6 @@ xfs_file_iomap_begin(
 
 	xfs_bmbt_to_iomap(ip, iomap, &imap);
 
-	/* optionally associate a dax device with the iomap bdev */
-	bdev = iomap->bdev;
-	if (blk_queue_dax(bdev->bd_queue))
-		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
-	else
-		iomap->dax_dev = NULL;
-
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
@@ -1169,7 +1162,6 @@ xfs_file_iomap_end(
 	unsigned		flags,
 	struct iomap		*iomap)
 {
-	fs_put_dax(iomap->dax_dev);
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
 				length, written, iomap);

fs/xfs/xfs_super.c

@@ -714,17 +714,26 @@ STATIC void
 xfs_close_devices(
 	struct xfs_mount	*mp)
 {
+	struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev;
+
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
 		struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
+		struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev;
+
 		xfs_free_buftarg(mp, mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
+		fs_put_dax(dax_logdev);
 	}
 	if (mp->m_rtdev_targp) {
 		struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
+		struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev;
+
 		xfs_free_buftarg(mp, mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
+		fs_put_dax(dax_rtdev);
 	}
 	xfs_free_buftarg(mp, mp->m_ddev_targp);
+	fs_put_dax(dax_ddev);
 }
 
 /*
@@ -742,6 +751,8 @@ xfs_open_devices(
 	struct xfs_mount	*mp)
 {
 	struct block_device	*ddev = mp->m_super->s_bdev;
+	struct dax_device	*dax_ddev = fs_dax_get_by_bdev(ddev);
+	struct dax_device	*dax_logdev = NULL, *dax_rtdev = NULL;
 	struct block_device	*logdev = NULL, *rtdev = NULL;
 	int			error;
 
@@ -752,6 +763,7 @@ xfs_open_devices(
 		error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
 		if (error)
 			goto out;
+		dax_logdev = fs_dax_get_by_bdev(logdev);
 	}
 
 	if (mp->m_rtname) {
@@ -765,24 +777,25 @@ xfs_open_devices(
 			error = -EINVAL;
 			goto out_close_rtdev;
 		}
+		dax_rtdev = fs_dax_get_by_bdev(rtdev);
 	}
 
 	/*
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = -ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -798,10 +811,14 @@ xfs_open_devices(
 	xfs_free_buftarg(mp, mp->m_ddev_targp);
  out_close_rtdev:
 	xfs_blkdev_put(rtdev);
+	fs_put_dax(dax_rtdev);
  out_close_logdev:
-	if (logdev && logdev != ddev)
+	if (logdev && logdev != ddev) {
 		xfs_blkdev_put(logdev);
+		fs_put_dax(dax_logdev);
+	}
  out:
+	fs_put_dax(dax_ddev);
 	return error;
 }
 

include/linux/dax.h

@@ -57,6 +57,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
 	put_dax(dax_dev);
 }
 
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 #else
 static inline int bdev_dax_supported(struct super_block *sb, int blocksize)
 {
@@ -71,6 +72,11 @@ static inline struct dax_device *fs_dax_get_by_host(const char *host)
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
 }
+
+static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+{
+	return NULL;
+}
 #endif
 
 int dax_read_lock(void);

include/linux/libnvdimm.h

@@ -87,6 +87,7 @@ struct nd_mapping_desc {
 	struct nvdimm *nvdimm;
 	u64 start;
 	u64 size;
+	int position;
 };
 
 struct nd_region_desc {
@@ -173,4 +174,19 @@ u64 nd_fletcher64(void *addr, size_t len, bool le);
 void nvdimm_flush(struct nd_region *nd_region);
 int nvdimm_has_flush(struct nd_region *nd_region);
 int nvdimm_has_cache(struct nd_region *nd_region);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+#define ARCH_MEMREMAP_PMEM MEMREMAP_WB
+void arch_wb_cache_pmem(void *addr, size_t size);
+void arch_invalidate_pmem(void *addr, size_t size);
+#else
+#define ARCH_MEMREMAP_PMEM MEMREMAP_WT
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
+{
+}
+static inline void arch_invalidate_pmem(void *addr, size_t size)
+{
+}
+#endif
+
 #endif /* __LIBNVDIMM_H__ */

lib/Kconfig

@@ -559,9 +559,6 @@ config ARCH_HAS_PMEM_API
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
-config ARCH_HAS_MMIO_FLUSH
-	bool
-
 config STACKDEPOT
 	bool
 	select STACKTRACE

tools/testing/nvdimm/test/nfit.c

@@ -1546,8 +1546,8 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
 	else {
 		memcpy(iobuf, mmio->addr.base + dpa, len);
 
-		/* give us some some coverage of the mmio_flush_range() API */
-		mmio_flush_range(mmio->addr.base + dpa, len);
+		/* give us some some coverage of the arch_invalidate_pmem() API */
+		arch_invalidate_pmem(mmio->addr.base + dpa, len);
 	}
 	nd_region_release_lane(nd_region, lane);