Merge branch 'for-5.1/libnvdimm-start-pad' into libnvdimm-for-next

Merge the initial lead-in cleanups and fixes that resulted from the
effort to resolve bugs in the section-alignment padding implementation
in the nvdimm core. The back half of this topic is abandoned in favor of
implementing sub-section hotplug support.

drivers/dax/super.c

@@ -86,12 +86,14 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
 	struct dax_device *dax_dev;
 	bool dax_enabled = false;
+	pgoff_t pgoff, pgoff_end;
 	struct request_queue *q;
-	pgoff_t pgoff;
-	int err, id;
-	pfn_t pfn;
-	long len;
 	char buf[BDEVNAME_SIZE];
+	void *kaddr, *end_kaddr;
+	pfn_t pfn, end_pfn;
+	sector_t last_page;
+	long len, len2;
+	int err, id;
 
 	if (blocksize != PAGE_SIZE) {
 		pr_debug("%s: error: unsupported blocksize for dax\n",
@@ -113,6 +115,14 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		return false;
 	}
 
+	last_page = PFN_DOWN(i_size_read(bdev->bd_inode) - 1) * 8;
+	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
+	if (err) {
+		pr_debug("%s: error: unaligned partition for dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
 	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
 	if (!dax_dev) {
 		pr_debug("%s: error: device does not support dax\n",
@@ -121,14 +131,15 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 	}
 
 	id = dax_read_lock();
-	len = dax_direct_access(dax_dev, pgoff, 1, NULL, &pfn);
+	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
+	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
 	dax_read_unlock(id);
 
 	put_dax(dax_dev);
 
-	if (len < 1) {
+	if (len < 1 || len2 < 1) {
 		pr_debug("%s: error: dax access failed (%ld)\n",
-				bdevname(bdev, buf), len);
+				bdevname(bdev, buf), len < 1 ? len : len2);
 		return false;
 	}
 
@@ -143,13 +154,20 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		 */
 		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
 		dax_enabled = true;
-	} else if (pfn_t_devmap(pfn)) {
-		struct dev_pagemap *pgmap;
+	} else if (pfn_t_devmap(pfn) && pfn_t_devmap(end_pfn)) {
+		struct dev_pagemap *pgmap, *end_pgmap;
 
 		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
-		if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX)
+		end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL);
+		if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX
+				&& pfn_t_to_page(pfn)->pgmap == pgmap
+				&& pfn_t_to_page(end_pfn)->pgmap == pgmap
+				&& pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr))
+				&& pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr)))
 			dax_enabled = true;
 		put_dev_pagemap(pgmap);
+		put_dev_pagemap(end_pgmap);
+
 	}
 
 	if (!dax_enabled) {

drivers/nvdimm/namespace_devs.c

@@ -138,6 +138,7 @@ bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
 bool pmem_should_map_pages(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
+	struct nd_namespace_common *ndns = to_ndns(dev);
 	struct nd_namespace_io *nsio;
 
 	if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
@@ -149,6 +150,9 @@ bool pmem_should_map_pages(struct device *dev)
 	if (is_nd_pfn(dev) || is_nd_btt(dev))
 		return false;
 
+	if (ndns->force_raw)
+		return false;
+
 	nsio = to_nd_namespace_io(dev);
 	if (region_intersects(nsio->res.start, resource_size(&nsio->res),
 				IORESOURCE_SYSTEM_RAM,

drivers/nvdimm/pfn_devs.c

@@ -580,6 +580,11 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
 }
 EXPORT_SYMBOL(nd_pfn_probe);
 
+static u32 info_block_reserve(void)
+{
+	return ALIGN(SZ_8K, PAGE_SIZE);
+}
+
 /*
  * We hotplug memory at section granularity, pad the reserved area from
  * the previous section base to the namespace base address.
@@ -593,7 +598,7 @@ static unsigned long init_altmap_base(resource_size_t base)
 
 static unsigned long init_altmap_reserve(resource_size_t base)
 {
-	unsigned long reserve = PHYS_PFN(SZ_8K);
+	unsigned long reserve = info_block_reserve() >> PAGE_SHIFT;
 	unsigned long base_pfn = PHYS_PFN(base);
 
 	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
@@ -608,6 +613,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	u64 offset = le64_to_cpu(pfn_sb->dataoff);
 	u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
 	u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+	u32 reserve = info_block_reserve();
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	resource_size_t base = nsio->res.start + start_pad;
@@ -621,7 +627,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	res->end -= end_trunc;
 
 	if (nd_pfn->mode == PFN_MODE_RAM) {
-		if (offset < SZ_8K)
+		if (offset < reserve)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 		pgmap->altmap_valid = false;
@@ -634,7 +640,7 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 					le64_to_cpu(nd_pfn->pfn_sb->npfns),
 					nd_pfn->npfns);
 		memcpy(altmap, &__altmap, sizeof(*altmap));
-		altmap->free = PHYS_PFN(offset - SZ_8K);
+		altmap->free = PHYS_PFN(offset - reserve);
 		altmap->alloc = 0;
 		pgmap->altmap_valid = true;
 	} else
@@ -678,18 +684,17 @@ static void trim_pfn_device(struct nd_pfn *nd_pfn, u32 *start_pad, u32 *end_trun
 	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
 				IORES_DESC_NONE) == REGION_MIXED
 			|| !IS_ALIGNED(end, nd_pfn->align)
-			|| nd_region_conflict(nd_region, start, size + adjust))
+			|| nd_region_conflict(nd_region, start, size))
 		*end_trunc = end - phys_pmem_align_down(nd_pfn, end);
 }
 
 static int nd_pfn_init(struct nd_pfn *nd_pfn)
 {
-	u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	u32 start_pad, end_trunc, reserve = info_block_reserve();
 	resource_size_t start, size;
 	struct nd_region *nd_region;
-	u32 start_pad, end_trunc;
 	struct nd_pfn_sb *pfn_sb;
 	unsigned long npfns;
 	phys_addr_t offset;
@@ -734,7 +739,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	 */
 	start = nsio->res.start + start_pad;
 	size = resource_size(&nsio->res);
-	npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - SZ_8K)
+	npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - reserve)
 			/ PAGE_SIZE);
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*
@@ -742,11 +747,10 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		 * when populating the vmemmap. This *should* be equal to
 		 * PMD_SIZE for most architectures.
 		 */
-		offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
+		offset = ALIGN(start + reserve + 64 * npfns,
 				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;
+		offset = ALIGN(start + reserve, nd_pfn->align) - start;
 	else
 		return -ENXIO;