mm, dax, pmem: introduce pfn_t

For the purpose of communicating the optional presence of a 'struct
page' for the pfn returned from ->direct_access(), introduce a type that
encapsulates a page-frame-number plus flags.  These flags contain the
historical "page_link" encoding for a scatterlist entry, but can also
denote "device memory".  Where "device memory" is a set of pfns that are
not part of the kernel's linear mapping by default, but are accessed via
the same memory controller as ram.

The motivation for this new type is large capacity persistent memory
that needs struct page entries in the 'memmap' to support 3rd party DMA
(i.e.  O_DIRECT I/O with a persistent memory source/target).  However,
we also need it in support of maintaining a list of mapped inodes which
need to be unmapped at driver teardown or freeze_bdev() time.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Hansen <dave@sr71.net>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 19 insertions, 12 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index a5880f4ab40e..cb27190e9f39 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -19,6 +19,9 @@
 #include <linux/radix-tree.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#ifdef CONFIG_BLK_DEV_RAM_DAX
+#include <linux/pfn_t.h>
+#endif
 
 #include <asm/uaccess.h>
 
@@ -378,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
-			void __pmem **kaddr, unsigned long *pfn)
+			void __pmem **kaddr, pfn_t *pfn)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -389,7 +392,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	if (!page)
 		return -ENOSPC;
 	*kaddr = (void __pmem *)page_address(page);
-	*pfn = page_to_pfn(page);
+	*pfn = page_to_pfn_t(page);
 
 	return PAGE_SIZE;
 }
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b493ff3fccb2..5def7f4ddbd2 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -25,6 +25,7 @@
 #include <linux/moduleparam.h>
 #include <linux/badblocks.h>
 #include <linux/vmalloc.h>
+#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
 #include <linux/nd.h>
@@ -40,6 +41,7 @@ struct pmem_device {
 	phys_addr_t		phys_addr;
 	/* when non-zero this device is hosting a 'pfn' instance */
 	phys_addr_t		data_offset;
+	unsigned long		pfn_flags;
 	void __pmem		*virt_addr;
 	size_t			size;
 	struct badblocks	bb;
@@ -135,13 +137,13 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, unsigned long *pfn)
+		      void __pmem **kaddr, pfn_t *pfn)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
 
 	*kaddr = pmem->virt_addr + offset;
-	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
+	*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
 
 	return pmem->size - offset;
 }
@@ -174,9 +176,11 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 		return ERR_PTR(-EBUSY);
 	}
 
-	if (pmem_should_map_pages(dev))
+	pmem->pfn_flags = PFN_DEV;
+	if (pmem_should_map_pages(dev)) {
 		pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, res);
-	else
+		pmem->pfn_flags |= PFN_MAP;
+	} else
 		pmem->virt_addr = (void __pmem *) devm_memremap(dev,
 				pmem->phys_addr, pmem->size,
 				ARCH_MEMREMAP_PMEM);
@@ -384,6 +388,7 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
 	pmem = dev_get_drvdata(dev);
 	devm_memunmap(dev, (void __force *) pmem->virt_addr);
 	pmem->virt_addr = (void __pmem *) devm_memremap_pages(dev, &nsio->res);
+	pmem->pfn_flags |= PFN_MAP;
 	if (IS_ERR(pmem->virt_addr)) {
 		rc = PTR_ERR(pmem->virt_addr);
 		goto err;
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 94a8f4ab57bc..ce7b70181740 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -17,6 +17,7 @@
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/pfn_t.h>
 #include <asm/extmem.h>
 #include <asm/io.h>
 
@@ -30,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static blk_qc_t dcssblk_make_request(struct request_queue *q,
 						struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-			 void __pmem **kaddr, unsigned long *pfn);
+			 void __pmem **kaddr, pfn_t *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -883,20 +884,18 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void __pmem **kaddr, unsigned long *pfn)
+			void __pmem **kaddr, pfn_t *pfn)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long offset, dev_sz;
-	void *addr;
 
 	dev_info = bdev->bd_disk->private_data;
 	if (!dev_info)
 		return -ENODEV;
 	dev_sz = dev_info->end - dev_info->start;
 	offset = secnum * 512;
-	addr = (void *) (dev_info->start + offset);
-	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
-	*kaddr = (void __pmem *) addr;
+	*kaddr = (void __pmem *) (dev_info->start + offset);
+	*pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), PFN_DEV);
 
 	return dev_sz - offset;
 }