1 files changed, 41 insertions, 81 deletions

diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 0f81fc56bbfd..3e7b11cf1aae 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -67,7 +67,7 @@ static ssize_t mode_store(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc = 0;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	nvdimm_bus_lock(dev);
 	if (dev->driver)
 		rc = -EBUSY;
@@ -89,7 +89,7 @@ static ssize_t mode_store(struct device *dev,
 	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
 			buf[len - 1] == '\n' ? "" : "\n");
 	nvdimm_bus_unlock(dev);
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc ? rc : len;
 }
@@ -132,14 +132,14 @@ static ssize_t align_store(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	nvdimm_bus_lock(dev);
 	rc = nd_size_select_store(dev, buf, &nd_pfn->align,
 			nd_pfn_supported_alignments());
 	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
 			buf[len - 1] == '\n' ? "" : "\n");
 	nvdimm_bus_unlock(dev);
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc ? rc : len;
 }
@@ -161,11 +161,11 @@ static ssize_t uuid_store(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
 	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
 			buf[len - 1] == '\n' ? "" : "\n");
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc ? rc : len;
 }
@@ -190,13 +190,13 @@ static ssize_t namespace_store(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	nvdimm_bus_lock(dev);
 	rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
 	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
 			buf[len - 1] == '\n' ? "" : "\n");
 	nvdimm_bus_unlock(dev);
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc;
 }
@@ -208,7 +208,7 @@ static ssize_t resource_show(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	if (dev->driver) {
 		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
@@ -222,7 +222,7 @@ static ssize_t resource_show(struct device *dev,
 		/* no address to convey if the pfn instance is disabled */
 		rc = -ENXIO;
 	}
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc;
 }
@@ -234,7 +234,7 @@ static ssize_t size_show(struct device *dev,
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 	ssize_t rc;
 
-	device_lock(dev);
+	nd_device_lock(dev);
 	if (dev->driver) {
 		struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
 		u64 offset = __le64_to_cpu(pfn_sb->dataoff);
@@ -250,7 +250,7 @@ static ssize_t size_show(struct device *dev,
 		/* no size to convey if the pfn instance is disabled */
 		rc = -ENXIO;
 	}
-	device_unlock(dev);
+	nd_device_unlock(dev);
 
 	return rc;
 }
@@ -412,6 +412,15 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
 	return 0;
 }
 
+/**
+ * nd_pfn_validate - read and validate info-block
+ * @nd_pfn: fsdax namespace runtime state / properties
+ * @sig: 'devdax' or 'fsdax' signature
+ *
+ * Upon return the info-block buffer contents (->pfn_sb) are
+ * indeterminate when validation fails, and a coherent info-block
+ * otherwise.
+ */
 int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
@@ -557,7 +566,7 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
 	nvdimm_bus_unlock(&ndns->dev);
 	if (!pfn_dev)
 		return -ENOMEM;
-	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
+	pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
 	nd_pfn = to_nd_pfn(pfn_dev);
 	nd_pfn->pfn_sb = pfn_sb;
 	rc = nd_pfn_validate(nd_pfn, PFN_SIG);
@@ -578,14 +587,14 @@ static u32 info_block_reserve(void)
 }
 
 /*
- * We hotplug memory at section granularity, pad the reserved area from
- * the previous section base to the namespace base address.
+ * We hotplug memory at sub-section granularity, pad the reserved area
+ * from the previous section base to the namespace base address.
  */
 static unsigned long init_altmap_base(resource_size_t base)
 {
 	unsigned long base_pfn = PHYS_PFN(base);
 
-	return PFN_SECTION_ALIGN_DOWN(base_pfn);
+	return SUBSECTION_ALIGN_DOWN(base_pfn);
 }
 
 static unsigned long init_altmap_reserve(resource_size_t base)
@@ -593,7 +602,7 @@ static unsigned long init_altmap_reserve(resource_size_t base)
 	unsigned long reserve = info_block_reserve() >> PAGE_SHIFT;
 	unsigned long base_pfn = PHYS_PFN(base);
 
-	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
+	reserve += base_pfn - SUBSECTION_ALIGN_DOWN(base_pfn);
 	return reserve;
 }
 
@@ -622,10 +631,8 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		if (offset < reserve)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
-		pgmap->altmap_valid = false;
 	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
-		nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
-					- offset) / PAGE_SIZE);
+		nd_pfn->npfns = PHYS_PFN((resource_size(res) - offset));
 		if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
 			dev_info(&nd_pfn->dev,
 					"number of pfns truncated from %lld to %ld\n",
@@ -634,67 +641,27 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 		memcpy(altmap, &__altmap, sizeof(*altmap));
 		altmap->free = PHYS_PFN(offset - reserve);
 		altmap->alloc = 0;
-		pgmap->altmap_valid = true;
+		pgmap->flags |= PGMAP_ALTMAP_VALID;
 	} else
 		return -ENXIO;
 
 	return 0;
 }
 
-static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys)
-{
-	return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys),
-			ALIGN_DOWN(phys, nd_pfn->align));
-}
-
-/*
- * Check if pmem collides with 'System RAM', or other regions when
- * section aligned.  Trim it accordingly.
- */
-static void trim_pfn_device(struct nd_pfn *nd_pfn, u32 *start_pad, u32 *end_trunc)
-{
-	struct nd_namespace_common *ndns = nd_pfn->ndns;
-	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-	struct nd_region *nd_region = to_nd_region(nd_pfn->dev.parent);
-	const resource_size_t start = nsio->res.start;
-	const resource_size_t end = start + resource_size(&nsio->res);
-	resource_size_t adjust, size;
-
-	*start_pad = 0;
-	*end_trunc = 0;
-
-	adjust = start - PHYS_SECTION_ALIGN_DOWN(start);
-	size = resource_size(&nsio->res) + adjust;
-	if (region_intersects(start - adjust, size, IORESOURCE_SYSTEM_RAM,
-				IORES_DESC_NONE) == REGION_MIXED
-			|| nd_region_conflict(nd_region, start - adjust, size))
-		*start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
-
-	/* Now check that end of the range does not collide. */
-	adjust = PHYS_SECTION_ALIGN_UP(end) - end;
-	size = resource_size(&nsio->res) + adjust;
-	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))
-		*end_trunc = end - phys_pmem_align_down(nd_pfn, end);
-}
-
 static int nd_pfn_init(struct nd_pfn *nd_pfn)
 {
 	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;
+	unsigned long npfns, align;
 	struct nd_pfn_sb *pfn_sb;
-	unsigned long npfns;
 	phys_addr_t offset;
 	const char *sig;
 	u64 checksum;
 	int rc;
 
-	pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
+	pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
 	if (!pfn_sb)
 		return -ENOMEM;
 
@@ -703,11 +670,14 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		sig = DAX_SIG;
 	else
 		sig = PFN_SIG;
+
 	rc = nd_pfn_validate(nd_pfn, sig);
 	if (rc != -ENODEV)
 		return rc;
 
 	/* no info block, do init */;
+	memset(pfn_sb, 0, sizeof(*pfn_sb));
+
 	nd_region = to_nd_region(nd_pfn->dev.parent);
 	if (nd_region->ro) {
 		dev_info(&nd_pfn->dev,
@@ -716,43 +686,35 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		return -ENXIO;
 	}
 
-	memset(pfn_sb, 0, sizeof(*pfn_sb));
-
-	trim_pfn_device(nd_pfn, &start_pad, &end_trunc);
-	if (start_pad + end_trunc)
-		dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n",
-				dev_name(&ndns->dev), start_pad + end_trunc);
-
 	/*
 	 * Note, we use 64 here for the standard size of struct page,
 	 * debugging options may cause it to be larger in which case the
 	 * implementation will limit the pfns advertised through
 	 * ->direct_access() to those that are included in the memmap.
 	 */
-	start = nsio->res.start + start_pad;
+	start = nsio->res.start;
 	size = resource_size(&nsio->res);
-	npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - reserve)
-			/ PAGE_SIZE);
+	npfns = PHYS_PFN(size - SZ_8K);
+	align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*
 		 * 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 + reserve + 64 * npfns,
-				max(nd_pfn->align, PMD_SIZE)) - start;
+		offset = ALIGN(start + SZ_8K + 64 * npfns, align) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
-		offset = ALIGN(start + reserve, nd_pfn->align) - start;
+		offset = ALIGN(start + SZ_8K, align) - start;
 	else
 		return -ENXIO;
 
-	if (offset + start_pad + end_trunc >= size) {
+	if (offset >= size) {
 		dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
 				dev_name(&ndns->dev));
 		return -ENXIO;
 	}
 
-	npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
+	npfns = PHYS_PFN(size - offset);
 	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
 	pfn_sb->dataoff = cpu_to_le64(offset);
 	pfn_sb->npfns = cpu_to_le64(npfns);
@@ -760,9 +722,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
 	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);
-	pfn_sb->version_minor = cpu_to_le16(2);
-	pfn_sb->start_pad = cpu_to_le32(start_pad);
-	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
+	pfn_sb->version_minor = cpu_to_le16(3);
 	pfn_sb->align = cpu_to_le32(nd_pfn->align);
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);