Merge branch 'for-4.6/pfn' into libnvdimm-for-next

7 files changed, 205 insertions, 89 deletions

diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c
index 91a336ea8c4f..e9ff9229d942 100644
--- a/drivers/nvdimm/blk.c
+++ b/drivers/nvdimm/blk.c
@@ -31,8 +31,6 @@ struct nd_blk_device {
         u32 internal_lbasize;
 };
 
-static int nd_blk_major;
-
 static u32 nd_blk_meta_size(struct nd_blk_device *blk_dev)
 {
         return blk_dev->nsblk->lbasize - blk_dev->sector_size;
@@ -264,7 +262,6 @@ static int nd_blk_attach_disk(struct nd_namespace_common *ndns,
         }
 
         disk->driverfs_dev      = &ndns->dev;
-        disk->major             = nd_blk_major;
         disk->first_minor       = 0;
         disk->fops              = &nd_blk_fops;
         disk->private_data      = blk_dev;
@@ -358,25 +355,12 @@ static struct nd_device_driver nd_blk_driver = {
 
 static int __init nd_blk_init(void)
 {
-        int rc;
-
-        rc = register_blkdev(0, "nd_blk");
-        if (rc < 0)
-                return rc;
-
-        nd_blk_major = rc;
-        rc = nd_driver_register(&nd_blk_driver);
-
-        if (rc < 0)
-                unregister_blkdev(nd_blk_major, "nd_blk");
-
-        return rc;
+        return nd_driver_register(&nd_blk_driver);
 }
 
 static void __exit nd_blk_exit(void)
 {
         driver_unregister(&nd_blk_driver.drv);
-        unregister_blkdev(nd_blk_major, "nd_blk");
 }
 
 MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index efb2c1ceef98..c32cbb593600 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -31,8 +31,6 @@ enum log_ent_request {
         LOG_OLD_ENT
 };
 
-static int btt_major;
-
 static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
                 void *buf, size_t n)
 {
@@ -1246,7 +1244,6 @@ static int btt_blk_init(struct btt *btt)
 
         nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
         btt->btt_disk->driverfs_dev = &btt->nd_btt->dev;
-        btt->btt_disk->major = btt_major;
         btt->btt_disk->first_minor = 0;
         btt->btt_disk->fops = &btt_fops;
         btt->btt_disk->private_data = btt;
@@ -1423,22 +1420,11 @@ EXPORT_SYMBOL(nvdimm_namespace_detach_btt);
 
 static int __init nd_btt_init(void)
 {
-        int rc;
-
-        btt_major = register_blkdev(0, "btt");
-        if (btt_major < 0)
-                return btt_major;
+        int rc = 0;
 
         debugfs_root = debugfs_create_dir("btt", NULL);
-        if (IS_ERR_OR_NULL(debugfs_root)) {
+        if (IS_ERR_OR_NULL(debugfs_root))
                 rc = -ENXIO;
-                goto err_debugfs;
-        }
-
-        return 0;
-
- err_debugfs:
-        unregister_blkdev(btt_major, "btt");
 
         return rc;
 }
@@ -1446,7 +1432,6 @@ static int __init nd_btt_init(void)
 static void __exit nd_btt_exit(void)
 {
         debugfs_remove_recursive(debugfs_root);
-        unregister_blkdev(btt_major, "btt");
 }
 
 MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT);
diff --git a/drivers/nvdimm/e820.c b/drivers/nvdimm/e820.c
index b0045a505dc8..95825b38559a 100644
--- a/drivers/nvdimm/e820.c
+++ b/drivers/nvdimm/e820.c
@@ -55,7 +55,7 @@ static int e820_pmem_probe(struct platform_device *pdev)
         for (p = iomem_resource.child; p ; p = p->sibling) {
                 struct nd_region_desc ndr_desc;
 
-                if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0)
+                if (p->desc != IORES_DESC_PERSISTENT_MEMORY_LEGACY)
                         continue;
 
                 memset(&ndr_desc, 0, sizeof(ndr_desc));
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 9edf7eb7d17c..f5cb88601359 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -133,6 +133,7 @@ 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_io *nsio;
 
         if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
                 return false;
@@ -143,6 +144,12 @@ bool pmem_should_map_pages(struct device *dev)
         if (is_nd_pfn(dev) || is_nd_btt(dev))
                 return false;
 
+        nsio = to_nd_namespace_io(dev);
+        if (region_intersects(nsio->res.start, resource_size(&nsio->res),
+                                IORESOURCE_SYSTEM_RAM,
+                                IORES_DESC_NONE) == REGION_MIXED)
+                return false;
+
 #ifdef ARCH_MEMREMAP_PMEM
         return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
 #else
diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index cc243754acef..8e343a3ca873 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -15,6 +15,7 @@
 #define __NVDIMM_PFN_H
 
 #include <linux/types.h>
+#include <linux/mmzone.h>
 
 #define PFN_SIG_LEN 16
 #define PFN_SIG "NVDIMM_PFN_INFO\0"
@@ -26,10 +27,28 @@ struct nd_pfn_sb {
         __le32 flags;
         __le16 version_major;
         __le16 version_minor;
-        __le64 dataoff;
+        __le64 dataoff; /* relative to namespace_base + start_pad */
         __le64 npfns;
         __le32 mode;
-        u8 padding[4012];
+        /* minor-version-1 additions for section alignment */
+        __le32 start_pad;
+        __le32 end_trunc;
+        u8 padding[4004];
         __le64 checksum;
 };
+
+#ifdef CONFIG_SPARSEMEM
+#define PFN_SECTION_ALIGN_DOWN(x) SECTION_ALIGN_DOWN(x)
+#define PFN_SECTION_ALIGN_UP(x) SECTION_ALIGN_UP(x)
+#else
+/*
+ * In this case ZONE_DEVICE=n and we will disable 'pfn' device support,
+ * but we still want pmem to compile.
+ */
+#define PFN_SECTION_ALIGN_DOWN(x) (x)
+#define PFN_SECTION_ALIGN_UP(x) (x)
+#endif
+
+#define PHYS_SECTION_ALIGN_DOWN(x) PFN_PHYS(PFN_SECTION_ALIGN_DOWN(PHYS_PFN(x)))
+#define PHYS_SECTION_ALIGN_UP(x) PFN_PHYS(PFN_SECTION_ALIGN_UP(PHYS_PFN(x)))
 #endif /* __NVDIMM_PFN_H */
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index ae81a2f1da50..254d3bc13f70 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -205,11 +205,67 @@ static ssize_t namespace_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(namespace);
 
+static ssize_t resource_show(struct device *dev,
+                struct device_attribute *attr, char *buf)
+{
+        struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+        ssize_t rc;
+
+        device_lock(dev);
+        if (dev->driver) {
+                struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+                u64 offset = __le64_to_cpu(pfn_sb->dataoff);
+                struct nd_namespace_common *ndns = nd_pfn->ndns;
+                u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+                struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+                rc = sprintf(buf, "%#llx\n", (unsigned long long) nsio->res.start
+                                + start_pad + offset);
+        } else {
+                /* no address to convey if the pfn instance is disabled */
+                rc = -ENXIO;
+        }
+        device_unlock(dev);
+
+        return rc;
+}
+static DEVICE_ATTR_RO(resource);
+
+static ssize_t size_show(struct device *dev,
+                struct device_attribute *attr, char *buf)
+{
+        struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+        ssize_t rc;
+
+        device_lock(dev);
+        if (dev->driver) {
+                struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+                u64 offset = __le64_to_cpu(pfn_sb->dataoff);
+                struct nd_namespace_common *ndns = nd_pfn->ndns;
+                u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+                u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+                struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+
+                rc = sprintf(buf, "%llu\n", (unsigned long long)
+                                resource_size(&nsio->res) - start_pad
+                                - end_trunc - offset);
+        } else {
+                /* no size to convey if the pfn instance is disabled */
+                rc = -ENXIO;
+        }
+        device_unlock(dev);
+
+        return rc;
+}
+static DEVICE_ATTR_RO(size);
+
 static struct attribute *nd_pfn_attributes[] = {
         &dev_attr_mode.attr,
         &dev_attr_namespace.attr,
         &dev_attr_uuid.attr,
         &dev_attr_align.attr,
+        &dev_attr_resource.attr,
+        &dev_attr_size.attr,
         NULL,
 };
 
@@ -299,6 +355,11 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
         if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
                 return -ENODEV;
 
+        if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
+                pfn_sb->start_pad = 0;
+                pfn_sb->end_trunc = 0;
+        }
+
         switch (le32_to_cpu(pfn_sb->mode)) {
         case PFN_MODE_RAM:
         case PFN_MODE_PMEM:
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index adc387236fe7..ca5721c306bb 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -43,12 +43,13 @@ struct pmem_device {
         phys_addr_t             data_offset;
         u64                     pfn_flags;
         void __pmem             *virt_addr;
+        /* immutable base size of the namespace */
         size_t                  size;
+        /* trim size when namespace capacity has been section aligned */
+        u32                     pfn_pad;
         struct badblocks        bb;
 };
 
-static int pmem_major;
-
 static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
 {
         if (bb->count) {
@@ -175,7 +176,7 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
         *kaddr = pmem->virt_addr + offset;
         *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
 
-        return pmem->size - offset;
+        return pmem->size - pmem->pfn_pad - offset;
 }
 
 static const struct block_device_operations pmem_fops = {
@@ -258,15 +259,14 @@ static int pmem_attach_disk(struct device *dev,
                 return -ENOMEM;
         }
 
-        disk->major             = pmem_major;
-        disk->first_minor       = 0;
         disk->fops              = &pmem_fops;
         disk->private_data      = pmem;
         disk->queue             = pmem->pmem_queue;
         disk->flags             = GENHD_FL_EXT_DEVT;
         nvdimm_namespace_disk_name(ndns, disk->disk_name);
         disk->driverfs_dev = dev;
-        set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
+        set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
+                        / 512);
         pmem->pmem_disk = disk;
         devm_exit_badblocks(dev, &pmem->bb);
         if (devm_init_badblocks(dev, &pmem->bb))
@@ -309,6 +309,9 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
         struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
         struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
         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;
         unsigned long npfns;
         phys_addr_t offset;
@@ -334,21 +337,56 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
         }
 
         memset(pfn_sb, 0, sizeof(*pfn_sb));
-        npfns = (pmem->size - SZ_8K) / SZ_4K;
+
+        /*
+         * 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;
+        npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K;
         if (nd_pfn->mode == PFN_MODE_PMEM)
-                offset = ALIGN(SZ_8K + 64 * npfns, nd_pfn->align);
+                offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align)
+                        - start;
         else if (nd_pfn->mode == PFN_MODE_RAM)
-                offset = ALIGN(SZ_8K, nd_pfn->align);
+                offset = ALIGN(start + SZ_8K, nd_pfn->align) - start;
         else
                 goto err;
 
-        npfns = (pmem->size - offset) / SZ_4K;
+        if (offset + start_pad + end_trunc >= pmem->size) {
+                dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
+                                dev_name(&ndns->dev));
+                goto err;
+        }
+
+        npfns = (pmem->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);
@@ -356,6 +394,9 @@ 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(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);
 
@@ -386,41 +427,56 @@ static int nvdimm_namespace_detach_pfn(struct nd_namespace_common *ndns)
         return 0;
 }
 
-static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
+/*
+ * 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 int __nvdimm_namespace_attach_pfn(struct nd_pfn *nd_pfn)
 {
-        struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
-        struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
-        struct device *dev = &nd_pfn->dev;
-        struct nd_region *nd_region;
-        struct vmem_altmap *altmap;
-        struct nd_pfn_sb *pfn_sb;
-        struct pmem_device *pmem;
-        struct request_queue *q;
-        phys_addr_t offset;
         int rc;
+        struct resource res;
+        struct request_queue *q;
+        struct pmem_device *pmem;
+        struct vmem_altmap *altmap;
+        struct device *dev = &nd_pfn->dev;
+        struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+        struct nd_namespace_common *ndns = nd_pfn->ndns;
+        u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
+        u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
+        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 = __phys_to_pfn(nsio->res.start),
-                .reserve = __phys_to_pfn(SZ_8K),
+                .base_pfn = init_altmap_base(base),
+                .reserve = init_altmap_reserve(base),
         };
 
-        if (!nd_pfn->uuid || !nd_pfn->ndns)
-                return -ENODEV;
-
-        nd_region = to_nd_region(dev->parent);
-        rc = nd_pfn_init(nd_pfn);
-        if (rc)
-                return rc;
-
-        pfn_sb = nd_pfn->pfn_sb;
-        offset = le64_to_cpu(pfn_sb->dataoff);
+        pmem = dev_get_drvdata(dev);
+        pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
+        pmem->pfn_pad = start_pad + end_trunc;
         nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
         if (nd_pfn->mode == PFN_MODE_RAM) {
-                if (offset < SZ_8K)
+                if (pmem->data_offset < SZ_8K)
                         return -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(&nsio->res) - offset)
+                nd_pfn->npfns = (pmem->size - pmem->pfn_pad - pmem->data_offset)
                         / PAGE_SIZE;
                 if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
                         dev_info(&nd_pfn->dev,
@@ -428,7 +484,7 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
                                         le64_to_cpu(nd_pfn->pfn_sb->npfns),
                                         nd_pfn->npfns);
                 altmap = & __altmap;
-                altmap->free = __phys_to_pfn(offset - SZ_8K);
+                altmap->free = PHYS_PFN(pmem->data_offset - SZ_8K);
                 altmap->alloc = 0;
         } else {
                 rc = -ENXIO;
@@ -436,10 +492,12 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
         }
 
         /* establish pfn range for lookup, and switch to direct map */
-        pmem = dev_get_drvdata(dev);
         q = pmem->pmem_queue;
+        memcpy(&res, &nsio->res, sizeof(res));
+        res.start += start_pad;
+        res.end -= end_trunc;
         devm_memunmap(dev, (void __force *) pmem->virt_addr);
-        pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res,
+        pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &res,
                         &q->q_usage_counter, altmap);
         pmem->pfn_flags |= PFN_MAP;
         if (IS_ERR(pmem->virt_addr)) {
@@ -448,7 +506,6 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
         }
 
         /* attach pmem disk in "pfn-mode" */
-        pmem->data_offset = offset;
         rc = pmem_attach_disk(dev, ndns, pmem);
         if (rc)
                 goto err;
@@ -457,6 +514,22 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
  err:
         nvdimm_namespace_detach_pfn(ndns);
         return rc;
+
+}
+
+static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
+{
+        struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
+        int rc;
+
+        if (!nd_pfn->uuid || !nd_pfn->ndns)
+                return -ENODEV;
+
+        rc = nd_pfn_init(nd_pfn);
+        if (rc)
+                return rc;
+        /* we need a valid pfn_sb before we can init a vmem_altmap */
+        return __nvdimm_namespace_attach_pfn(nd_pfn);
 }
 
 static int nd_pmem_probe(struct device *dev)
@@ -547,26 +620,13 @@ static struct nd_device_driver nd_pmem_driver = {
 
 static int __init pmem_init(void)
 {
-        int error;
-
-        pmem_major = register_blkdev(0, "pmem");
-        if (pmem_major < 0)
-                return pmem_major;
-
-        error = nd_driver_register(&nd_pmem_driver);
-        if (error) {
-                unregister_blkdev(pmem_major, "pmem");
-                return error;
-        }
-
-        return 0;
+        return nd_driver_register(&nd_pmem_driver);
 }
 module_init(pmem_init);
 
 static void pmem_exit(void)
 {
         driver_unregister(&nd_pmem_driver.drv);
-        unregister_blkdev(pmem_major, "pmem");
 }
 module_exit(pmem_exit);