libnvdimm, pmem, pfn: move pfn setup to the core

Now that pmem internals have been disentangled from pfn setup, that code
can move to the core.  This is in preparation for adding another user of
the pfn-device capabilities.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 181 insertions, 0 deletions

diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 9df081ae96e3..e8693fe65e49 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -10,6 +10,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * General Public License for more details.
  */
+#include <linux/memremap.h>
 #include <linux/blkdev.h>
 #include <linux/device.h>
 #include <linux/genhd.h>
@@ -441,3 +442,183 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns)
 	return rc;
 }
 EXPORT_SYMBOL(nd_pfn_probe);
+
+/*
+ * We hotplug memory at 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);
+}
+
+static unsigned long init_altmap_reserve(resource_size_t base)
+{
+	unsigned long reserve = PHYS_PFN(SZ_8K);
+	unsigned long base_pfn = PHYS_PFN(base);
+
+	reserve += base_pfn - PFN_SECTION_ALIGN_DOWN(base_pfn);
+	return reserve;
+}
+
+static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+	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);
+	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;
+	struct vmem_altmap __altmap = {
+		.base_pfn = init_altmap_base(base),
+		.reserve = init_altmap_reserve(base),
+	};
+
+	memcpy(res, &nsio->res, sizeof(*res));
+	res->start += start_pad;
+	res->end -= end_trunc;
+
+	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
+	if (nd_pfn->mode == PFN_MODE_RAM) {
+		if (offset < SZ_8K)
+			return ERR_PTR(-EINVAL);
+		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
+		altmap = NULL;
+	} else if (nd_pfn->mode == PFN_MODE_PMEM) {
+		nd_pfn->npfns = (resource_size(res) - offset) / PAGE_SIZE;
+		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",
+					le64_to_cpu(nd_pfn->pfn_sb->npfns),
+					nd_pfn->npfns);
+		memcpy(altmap, &__altmap, sizeof(*altmap));
+		altmap->free = PHYS_PFN(offset - SZ_8K);
+		altmap->alloc = 0;
+	} else
+		return ERR_PTR(-ENXIO);
+
+	return altmap;
+}
+
+static int nd_pfn_init(struct nd_pfn *nd_pfn)
+{
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	u32 start_pad = 0, end_trunc = 0;
+	resource_size_t start, size;
+	struct nd_namespace_io *nsio;
+	struct nd_region *nd_region;
+	struct nd_pfn_sb *pfn_sb;
+	unsigned long npfns;
+	phys_addr_t offset;
+	u64 checksum;
+	int rc;
+
+	pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
+	if (!pfn_sb)
+		return -ENOMEM;
+
+	nd_pfn->pfn_sb = pfn_sb;
+	rc = nd_pfn_validate(nd_pfn);
+	if (rc != -ENODEV)
+		return rc;
+
+	/* no info block, do init */;
+	nd_region = to_nd_region(nd_pfn->dev.parent);
+	if (nd_region->ro) {
+		dev_info(&nd_pfn->dev,
+				"%s is read-only, unable to init metadata\n",
+				dev_name(&nd_region->dev));
+		return -ENXIO;
+	}
+
+	memset(pfn_sb, 0, sizeof(*pfn_sb));
+
+	/*
+	 * Check if pmem collides with 'System RAM' when section aligned and
+	 * trim it accordingly
+	 */
+	nsio = to_nd_namespace_io(&ndns->dev);
+	start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
+	size = resource_size(&nsio->res);
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+		start = nsio->res.start;
+		start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
+	}
+
+	start = nsio->res.start;
+	size = PHYS_SECTION_ALIGN_UP(start + size) - start;
+	if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
+				IORES_DESC_NONE) == REGION_MIXED) {
+		size = resource_size(&nsio->res);
+		end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
+	}
+
+	if (start_pad + end_trunc)
+		dev_info(&nd_pfn->dev, "%s section 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 += start_pad;
+	size = resource_size(&nsio->res);
+	npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
+	if (nd_pfn->mode == PFN_MODE_PMEM)
+		offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align)
+			- start;
+	else if (nd_pfn->mode == PFN_MODE_RAM)
+		offset = ALIGN(start + SZ_8K, nd_pfn->align) - start;
+	else
+		return -ENXIO;
+
+	if (offset + start_pad + end_trunc >= 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;
+	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
+	pfn_sb->dataoff = cpu_to_le64(offset);
+	pfn_sb->npfns = cpu_to_le64(npfns);
+	memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
+	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(1);
+	pfn_sb->start_pad = cpu_to_le32(start_pad);
+	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
+	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
+	pfn_sb->checksum = cpu_to_le64(checksum);
+
+	return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
+}
+
+/*
+ * Determine the effective resource range and vmem_altmap from an nd_pfn
+ * instance.
+ */
+struct vmem_altmap *nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
+		struct resource *res, struct vmem_altmap *altmap)
+{
+	int rc;
+
+	if (!nd_pfn->uuid || !nd_pfn->ndns)
+		return ERR_PTR(-ENODEV);
+
+	rc = nd_pfn_init(nd_pfn);
+	if (rc)
+		return ERR_PTR(rc);
+
+	/* we need a valid pfn_sb before we can init a vmem_altmap */
+	return __nvdimm_setup_pfn(nd_pfn, res, altmap);
+}
+EXPORT_SYMBOL_GPL(nvdimm_setup_pfn);