Merge branch 'pmem-api' into libnvdimm-for-next

56 files changed, 671 insertions, 315 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 6a34a0f4d37c..06d443450f21 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -397,7 +397,8 @@ prototypes:
 	int (*release) (struct gendisk *, fmode_t);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
+	int (*direct_access) (struct block_device *, sector_t, void __pmem **,
+				unsigned long *);
 	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
diff --git a/MAINTAINERS b/MAINTAINERS
index 9289ecb57b68..8fcde3717ab7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6161,6 +6161,7 @@ Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/pmem.c
 F:	include/linux/pmem.h
+F:	arch/*/include/asm/pmem.h
 
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
diff --git a/arch/arm/mach-clps711x/board-cdb89712.c b/arch/arm/mach-clps711x/board-cdb89712.c
index 1ec378c334e5..972abdb10028 100644
--- a/arch/arm/mach-clps711x/board-cdb89712.c
+++ b/arch/arm/mach-clps711x/board-cdb89712.c
@@ -95,7 +95,7 @@ static struct physmap_flash_data cdb89712_bootrom_pdata __initdata = {
 
 static struct resource cdb89712_bootrom_resources[] __initdata = {
 	DEFINE_RES_NAMED(CS7_PHYS_BASE, SZ_128, "BOOTROM", IORESOURCE_MEM |
-			 IORESOURCE_CACHEABLE | IORESOURCE_READONLY),
+			 IORESOURCE_READONLY),
 };
 
 static struct platform_device cdb89712_bootrom_pdev __initdata = {
diff --git a/arch/arm/mach-shmobile/pm-rcar.c b/arch/arm/mach-shmobile/pm-rcar.c
index 00022ee56f80..9d3dde00c2fe 100644
--- a/arch/arm/mach-shmobile/pm-rcar.c
+++ b/arch/arm/mach-shmobile/pm-rcar.c
@@ -12,7 +12,7 @@
 #include <linux/err.h>
 #include <linux/mm.h>
 #include <linux/spinlock.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include "pm-rcar.h"
 
 /* SYSC */
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 80a7e34be009..9041bbe2b7b4 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -435,6 +435,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 {
 	return ioremap(phys_addr, size);
 }
+#define ioremap_cache ioremap_cache
 
 
 /*
diff --git a/arch/ia64/kernel/cyclone.c b/arch/ia64/kernel/cyclone.c
index 4826ff957a3d..5fa3848ba224 100644
--- a/arch/ia64/kernel/cyclone.c
+++ b/arch/ia64/kernel/cyclone.c
@@ -4,7 +4,7 @@
 #include <linux/errno.h>
 #include <linux/timex.h>
 #include <linux/clocksource.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /* IBM Summit (EXA) Cyclone counter code*/
 #define CYCLONE_CBAR_ADDR 0xFEB00CD0
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 42e02a2d570b..d4726addff0b 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -102,7 +102,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
 		} else if (i == dev->rom_base_reg) {
 			res = &dev->resource[PCI_ROM_RESOURCE];
-			flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE;
+			flags |= IORESOURCE_READONLY;
 		} else {
 			printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
 			continue;
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index ee90db17b097..a2be2a66dab6 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -141,13 +141,14 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  */
 static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void **kaddr, unsigned long *pfn, long size)
+		       void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
 	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;
+	void *addr = (void *)(bank->ph_addr + offset);
 
-	*kaddr = (void *)(bank->ph_addr + offset);
-	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+	*kaddr = (void __pmem *)addr;
+	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
 
 	return bank->size - offset;
 }
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 728c4c571f40..6194e20fccca 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -342,6 +342,7 @@ ioremap_cache(phys_addr_t offset, unsigned long size)
 {
 	return __ioremap_mode(offset, size, PAGE_KERNEL);
 }
+#define ioremap_cache ioremap_cache
 
 #ifdef CONFIG_HAVE_IOREMAP_PROT
 static inline void __iomem *
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index c928bc64b4ba..04da147e0712 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -231,8 +231,7 @@ static void pci_parse_of_addrs(struct platform_device *op,
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
 		} else if (i == dev->rom_base_reg) {
 			res = &dev->resource[PCI_ROM_RESOURCE];
-			flags |= IORESOURCE_READONLY | IORESOURCE_CACHEABLE
-			      | IORESOURCE_SIZEALIGN;
+			flags |= IORESOURCE_READONLY | IORESOURCE_SIZEALIGN;
 		} else {
 			printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
 			continue;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 76c61154ed50..03ab6122325a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,6 +28,7 @@ config X86
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_PMEM_API
+	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 9bf3ea14b9f0..e63aa38e85fb 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -89,6 +89,8 @@ int set_pages_rw(struct page *page, int numpages);
 
 void clflush_cache_range(void *addr, unsigned int size);
 
+#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
+
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
@@ -109,75 +111,4 @@ static inline int rodata_test(void)
 }
 #endif
 
-#ifdef ARCH_HAS_NOCACHE_UACCESS
-
-/**
- * arch_memcpy_to_pmem - copy data to persistent memory
- * @dst: destination buffer for the copy
- * @src: source buffer for the copy
- * @n: length of the copy in bytes
- *
- * Copy data to persistent memory media via non-temporal stores so that
- * a subsequent arch_wmb_pmem() can flush cpu and memory controller
- * write buffers to guarantee durability.
- */
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
-{
-	int unwritten;
-
-	/*
-	 * We are copying between two kernel buffers, if
-	 * __copy_from_user_inatomic_nocache() returns an error (page
-	 * fault) we would have already reported a general protection fault
-	 * before the WARN+BUG.
-	 */
-	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
-			(void __user *) src, n);
-	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
-				__func__, dst, src, unwritten))
-		BUG();
-}
-
-/**
- * arch_wmb_pmem - synchronize writes to persistent memory
- *
- * After a series of arch_memcpy_to_pmem() operations this drains data
- * from cpu write buffers and any platform (memory controller) buffers
- * to ensure that written data is durable on persistent memory media.
- */
-static inline void arch_wmb_pmem(void)
-{
-	/*
-	 * wmb() to 'sfence' all previous writes such that they are
-	 * architecturally visible to 'pcommit'.  Note, that we've
-	 * already arranged for pmem writes to avoid the cache via
-	 * arch_memcpy_to_pmem().
-	 */
-	wmb();
-	pcommit_sfence();
-}
-
-static inline bool __arch_has_wmb_pmem(void)
-{
-#ifdef CONFIG_X86_64
-	/*
-	 * We require that wmb() be an 'sfence', that is only guaranteed on
-	 * 64-bit builds
-	 */
-	return static_cpu_has(X86_FEATURE_PCOMMIT);
-#else
-	return false;
-#endif
-}
-#else /* ARCH_HAS_NOCACHE_UACCESS i.e. ARCH=um */
-extern void arch_memcpy_to_pmem(void __pmem *dst, const void *src, size_t n);
-extern void arch_wmb_pmem(void);
-
-static inline bool __arch_has_wmb_pmem(void)
-{
-	return false;
-}
-#endif
-
 #endif /* _ASM_X86_CACHEFLUSH_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index cc9c61bc1abe..83ec9b1d77cc 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -248,12 +248,6 @@ static inline void flush_write_buffers(void)
 #endif
 }
 
-static inline void __pmem *arch_memremap_pmem(resource_size_t offset,
-	unsigned long size)
-{
-	return (void __force __pmem *) ioremap_cache(offset, size);
-}
-
 #endif /* __KERNEL__ */
 
 extern void native_io_delay(void);
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
new file mode 100644
index 000000000000..bb026c5adf8a
--- /dev/null
+++ b/arch/x86/include/asm/pmem.h
@@ -0,0 +1,160 @@
+/*
+ * Copyright(c) 2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef __ASM_X86_PMEM_H__
+#define __ASM_X86_PMEM_H__
+
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/special_insns.h>
+
+#define ARCH_MEMREMAP_PMEM MEMREMAP_WB
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+/**
+ * arch_memcpy_to_pmem - copy data to persistent memory
+ * @dst: destination buffer for the copy
+ * @src: source buffer for the copy
+ * @n: length of the copy in bytes
+ *
+ * Copy data to persistent memory media via non-temporal stores so that
+ * a subsequent arch_wmb_pmem() can flush cpu and memory controller
+ * write buffers to guarantee durability.
+ */
+static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
+		size_t n)
+{
+	int unwritten;
+
+	/*
+	 * We are copying between two kernel buffers, if
+	 * __copy_from_user_inatomic_nocache() returns an error (page
+	 * fault) we would have already reported a general protection fault
+	 * before the WARN+BUG.
+	 */
+	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
+			(void __user *) src, n);
+	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
+				__func__, dst, src, unwritten))
+		BUG();
+}
+
+/**
+ * arch_wmb_pmem - synchronize writes to persistent memory
+ *
+ * After a series of arch_memcpy_to_pmem() operations this drains data
+ * from cpu write buffers and any platform (memory controller) buffers
+ * to ensure that written data is durable on persistent memory media.
+ */
+static inline void arch_wmb_pmem(void)
+{
+	/*
+	 * wmb() to 'sfence' all previous writes such that they are
+	 * architecturally visible to 'pcommit'.  Note, that we've
+	 * already arranged for pmem writes to avoid the cache via
+	 * arch_memcpy_to_pmem().
+	 */
+	wmb();
+	pcommit_sfence();
+}
+
+/**
+ * __arch_wb_cache_pmem - write back a cache range with CLWB
+ * @vaddr:	virtual start address
+ * @size:	number of bytes to write back
+ *
+ * Write back a cache range using the CLWB (cache line write back)
+ * instruction.  This function requires explicit ordering with an
+ * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ */
+static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
+{
+	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+	unsigned long clflush_mask = x86_clflush_size - 1;
+	void *vend = vaddr + size;
+	void *p;
+
+	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	     p < vend; p += x86_clflush_size)
+		clwb(p);
+}
+
+/*
+ * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
+ * iterators, so for other types (bvec & kvec) we must do a cache write-back.
+ */
+static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
+{
+	return iter_is_iovec(i) == false;
+}
+
+/**
+ * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
+ * @addr:	PMEM destination address
+ * @bytes:	number of bytes to copy
+ * @i:		iterator with source data
+ *
+ * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
+ * This function requires explicit ordering with an arch_wmb_pmem() call.
+ */
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	void *vaddr = (void __force *)addr;
+	size_t len;
+
+	/* TODO: skip the write-back by always using non-temporal stores */
+	len = copy_from_iter_nocache(vaddr, bytes, i);
+
+	if (__iter_needs_pmem_wb(i))
+		__arch_wb_cache_pmem(vaddr, bytes);
+
+	return len;
+}
+
+/**
+ * arch_clear_pmem - zero a PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to zero
+ *
+ * Write zeros into the memory range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with an arch_wmb_pmem() call.
+ */
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+{
+	void *vaddr = (void __force *)addr;
+
+	/* TODO: implement the zeroing via non-temporal writes */
+	if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0)
+		clear_page(vaddr);
+	else
+		memset(vaddr, 0, size);
+
+	__arch_wb_cache_pmem(vaddr, size);
+}
+
+static inline bool arch_has_wmb_pmem(void)
+{
+#ifdef CONFIG_X86_64
+	/*
+	 * We require that wmb() be an 'sfence', that is only guaranteed on
+	 * 64-bit builds
+	 */
+	return static_cpu_has(X86_FEATURE_PCOMMIT);
+#else
+	return false;
+#endif
+}
+#endif /* CONFIG_ARCH_HAS_PMEM_API */
+
+#endif /* __ASM_X86_PMEM_H__ */
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index c39bb6e61911..867840f5400f 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -57,6 +57,7 @@ static inline void __iomem *ioremap_cache(unsigned long offset,
 	else
 		BUG();
 }
+#define ioremap_cache ioremap_cache
 
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 114cf48085ab..4baeb853e0c3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -410,6 +410,7 @@ config ACPI_NFIT
 	tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
+	depends on ARCH_HAS_MMIO_FLUSH
 	select LIBNVDIMM
 	help
 	  Infrastructure to probe ACPI 6 compliant platforms for
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 7c2638f914a9..56fff0141636 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -1017,7 +1017,7 @@ static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	return readq(mmio->base + offset);
+	return readq(mmio->addr.base + offset);
 }
 
 static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
@@ -1042,11 +1042,11 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 	if (mmio->num_lines)
 		offset = to_interleave_offset(offset, mmio);
 
-	writeq(cmd, mmio->base + offset);
+	writeq(cmd, mmio->addr.base + offset);
 	wmb_blk(nfit_blk);
 
 	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
-		readq(mmio->base + offset);
+		readq(mmio->addr.base + offset);
 }
 
 static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
@@ -1078,11 +1078,16 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 		}
 
 		if (rw)
-			memcpy_to_pmem(mmio->aperture + offset,
+			memcpy_to_pmem(mmio->addr.aperture + offset,
 					iobuf + copied, c);
-		else
+		else {
+			if (nfit_blk->dimm_flags & ND_BLK_READ_FLUSH)
+				mmio_flush_range((void __force *)
+					mmio->addr.aperture + offset, c);
+
 			memcpy_from_pmem(iobuf + copied,
-					mmio->aperture + offset, c);
+					mmio->addr.aperture + offset, c);
+		}
 
 		copied += c;
 		len -= c;
@@ -1129,7 +1134,10 @@ static void nfit_spa_mapping_release(struct kref *kref)
 
 	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
 	dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index);
-	iounmap(spa_map->iomem);
+	if (spa_map->type == SPA_MAP_APERTURE)
+		memunmap((void __force *)spa_map->addr.aperture);
+	else
+		iounmap(spa_map->addr.base);
 	release_mem_region(spa->address, spa->length);
 	list_del(&spa_map->list);
 	kfree(spa_map);
@@ -1175,7 +1183,7 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
 	spa_map = find_spa_mapping(acpi_desc, spa);
 	if (spa_map) {
 		kref_get(&spa_map->kref);
-		return spa_map->iomem;
+		return spa_map->addr.base;
 	}
 
 	spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL);
@@ -1191,20 +1199,19 @@ static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
 	if (!res)
 		goto err_mem;
 
-	if (type == SPA_MAP_APERTURE) {
-		/*
-		 * TODO: memremap_pmem() support, but that requires cache
-		 * flushing when the aperture is moved.
-		 */
-		spa_map->iomem = ioremap_wc(start, n);
-	} else
-		spa_map->iomem = ioremap_nocache(start, n);
+	spa_map->type = type;
+	if (type == SPA_MAP_APERTURE)
+		spa_map->addr.aperture = (void __pmem *)memremap(start, n,
+							ARCH_MEMREMAP_PMEM);
+	else
+		spa_map->addr.base = ioremap_nocache(start, n);
+
 
-	if (!spa_map->iomem)
+	if (!spa_map->addr.base)
 		goto err_map;
 
 	list_add_tail(&spa_map->list, &acpi_desc->spa_maps);
-	return spa_map->iomem;
+	return spa_map->addr.base;
 
  err_map:
 	release_mem_region(start, n);
@@ -1267,7 +1274,7 @@ static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
 		nfit_blk->dimm_flags = flags.flags;
 	else if (rc == -ENOTTY) {
 		/* fall back to a conservative default */
-		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH;
+		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH | ND_BLK_READ_FLUSH;
 		rc = 0;
 	} else
 		rc = -ENXIO;
@@ -1307,9 +1314,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
+	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
 			SPA_MAP_APERTURE);
-	if (!mmio->base) {
+	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
 		return -ENOMEM;
@@ -1330,9 +1337,9 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
+	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
 			SPA_MAP_CONTROL);
-	if (!mmio->base) {
+	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
 		return -ENOMEM;
@@ -1399,7 +1406,7 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
 	for (i = 0; i < 2; i++) {
 		struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i];
 
-		if (mmio->base)
+		if (mmio->addr.base)
 			nfit_spa_unmap(acpi_desc, mmio->spa);
 	}
 	nd_blk_region_set_provider_data(ndbr, NULL);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index f2c2bb751882..7e740156b9c2 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -41,6 +41,7 @@ enum nfit_uuids {
 };
 
 enum {
+	ND_BLK_READ_FLUSH = 1,
 	ND_BLK_DCR_LATCH = 2,
 };
 
@@ -117,12 +118,16 @@ enum nd_blk_mmio_selector {
 	DCR,
 };
 
+struct nd_blk_addr {
+	union {
+		void __iomem *base;
+		void __pmem  *aperture;
+	};
+};
+
 struct nfit_blk {
 	struct nfit_blk_mmio {
-		union {
-			void __iomem *base;
-			void __pmem  *aperture;
-		};
+		struct nd_blk_addr addr;
 		u64 size;
 		u64 base_offset;
 		u32 line_size;
@@ -149,7 +154,8 @@ struct nfit_spa_mapping {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
 	struct kref kref;
-	void __iomem *iomem;
+	enum spa_map_type type;
+	struct nd_blk_addr addr;
 };
 
 static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref)
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 64ab4951e9d6..c96402fd1560 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -371,7 +371,7 @@ 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 **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;
@@ -381,7 +381,7 @@ static long brd_direct_access(struct block_device *bdev, sector_t sector,
 	page = brd_insert_page(brd, sector);
 	if (!page)
 		return -ENOSPC;
-	*kaddr = page_address(page);
+	*kaddr = (void __pmem *)page_address(page);
 	*pfn = page_to_pfn(page);
 
 	/*
diff --git a/drivers/isdn/icn/icn.h b/drivers/isdn/icn/icn.h
index b713466997a0..f8f2e76d34bf 100644
--- a/drivers/isdn/icn/icn.h
+++ b/drivers/isdn/icn/icn.h
@@ -38,7 +38,7 @@ typedef struct icn_cdef {
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/major.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
index 2fc4957cbe7f..a70eb83e68f1 100644
--- a/drivers/mtd/devices/slram.c
+++ b/drivers/mtd/devices/slram.c
@@ -41,7 +41,7 @@
 #include <linux/fs.h>
 #include <linux/ioctl.h>
 #include <linux/init.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/mtd/mtd.h>
 
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index 7da266a53979..0802158a3f75 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -24,7 +24,7 @@
 #include <linux/rslib.h>
 #include <linux/moduleparam.h>
 #include <linux/slab.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c
index 32a216d31141..ab7bda0bb245 100644
--- a/drivers/mtd/onenand/generic.c
+++ b/drivers/mtd/onenand/generic.c
@@ -18,7 +18,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/onenand.h>
 #include <linux/mtd/partitions.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /*
  * Note: Driver name and platform data format have been updated!
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index bcf48f133443..f3b629779266 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,7 +92,7 @@ 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 **kaddr, unsigned long *pfn, long size)
+		      void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 	size_t offset = sector << 9;
@@ -101,7 +101,7 @@ static long pmem_direct_access(struct block_device *bdev, sector_t sector,
 		return -ENODEV;
 
 	/* FIXME convert DAX to comprehend that this mapping has a lifetime */
-	*kaddr = (void __force *) pmem->virt_addr + offset;
+	*kaddr = pmem->virt_addr + offset;
 	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
 
 	return pmem->size - offset;
@@ -119,7 +119,7 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 {
 	struct pmem_device *pmem;
 
-	pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
 	if (!pmem)
 		return ERR_PTR(-ENOMEM);
 
@@ -128,19 +128,16 @@ static struct pmem_device *pmem_alloc(struct device *dev,
 	if (!arch_has_pmem_api())
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
-	if (!request_mem_region(pmem->phys_addr, pmem->size, dev_name(dev))) {
+	if (!devm_request_mem_region(dev, pmem->phys_addr, pmem->size,
+			dev_name(dev))) {
 		dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
 				&pmem->phys_addr, pmem->size);
-		kfree(pmem);
 		return ERR_PTR(-EBUSY);
 	}
 
-	pmem->virt_addr = memremap_pmem(pmem->phys_addr, pmem->size);
-	if (!pmem->virt_addr) {
-		release_mem_region(pmem->phys_addr, pmem->size);
-		kfree(pmem);
+	pmem->virt_addr = memremap_pmem(dev, pmem->phys_addr, pmem->size);
+	if (!pmem->virt_addr)
 		return ERR_PTR(-ENXIO);
-	}
 
 	return pmem;
 }
@@ -210,20 +207,12 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
 	return 0;
 }
 
-static void pmem_free(struct pmem_device *pmem)
-{
-	memunmap_pmem(pmem->virt_addr);
-	release_mem_region(pmem->phys_addr, pmem->size);
-	kfree(pmem);
-}
-
 static int nd_pmem_probe(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
 	struct nd_namespace_common *ndns;
 	struct nd_namespace_io *nsio;
 	struct pmem_device *pmem;
-	int rc;
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
@@ -236,16 +225,14 @@ static int nd_pmem_probe(struct device *dev)
 
 	dev_set_drvdata(dev, pmem);
 	ndns->rw_bytes = pmem_rw_bytes;
+
 	if (is_nd_btt(dev))
-		rc = nvdimm_namespace_attach_btt(ndns);
-	else if (nd_btt_probe(ndns, pmem) == 0) {
+		return nvdimm_namespace_attach_btt(ndns);
+
+	if (nd_btt_probe(ndns, pmem) == 0)
 		/* we'll come back as btt-pmem */
-		rc = -ENXIO;
-	} else
-		rc = pmem_attach_disk(ndns, pmem);
-	if (rc)
-		pmem_free(pmem);
-	return rc;
+		return -ENXIO;
+	return pmem_attach_disk(ndns, pmem);
 }
 
 static int nd_pmem_remove(struct device *dev)
@@ -256,7 +243,6 @@ static int nd_pmem_remove(struct device *dev)
 		nvdimm_namespace_detach_btt(to_nd_btt(dev)->ndns);
 	else
 		pmem_detach_disk(pmem);
-	pmem_free(pmem);
 
 	return 0;
 }
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index cefd636681b6..8ed37dd04056 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -326,8 +326,7 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 		struct resource *res = &dev->resource[PCI_ROM_RESOURCE];
 		dev->rom_base_reg = rom;
 		res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH |
-				IORESOURCE_READONLY | IORESOURCE_CACHEABLE |
-				IORESOURCE_SIZEALIGN;
+				IORESOURCE_READONLY | IORESOURCE_SIZEALIGN;
 		__pci_read_base(dev, pci_bar_mem32, res, rom);
 	}
 }
diff --git a/drivers/pnp/manager.c b/drivers/pnp/manager.c
index 9357aa779048..7ad3295752ef 100644
--- a/drivers/pnp/manager.c
+++ b/drivers/pnp/manager.c
@@ -97,8 +97,6 @@ static int pnp_assign_mem(struct pnp_dev *dev, struct pnp_mem *rule, int idx)
 	/* ??? rule->flags restricted to 8 bits, all tests bogus ??? */
 	if (!(rule->flags & IORESOURCE_MEM_WRITEABLE))
 		res->flags |= IORESOURCE_READONLY;
-	if (rule->flags & IORESOURCE_MEM_CACHEABLE)
-		res->flags |= IORESOURCE_CACHEABLE;
 	if (rule->flags & IORESOURCE_MEM_RANGELENGTH)
 		res->flags |= IORESOURCE_RANGELENGTH;
 	if (rule->flags & IORESOURCE_MEM_SHADOWABLE)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index da212813f2d5..2c5a397b9f3e 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -29,7 +29,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static void dcssblk_make_request(struct request_queue *q, struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-				 void **kaddr, unsigned long *pfn, long size);
+			 void __pmem **kaddr, unsigned long *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -879,18 +879,20 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void **kaddr, unsigned long *pfn, long size)
+			void __pmem **kaddr, unsigned long *pfn, long size)
 {
 	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;
-	*kaddr = (void *) (dev_info->start + offset);
-	*pfn = virt_to_phys(*kaddr) >> PAGE_SHIFT;
+	addr = (void *) (dev_info->start + offset);
+	*pfn = virt_to_phys(addr) >> PAGE_SHIFT;
+	*kaddr = (void __pmem *) addr;
 
 	return dev_sz - offset;
 }
diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 4b135cca42a1..140cb8e6fea2 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -100,12 +100,7 @@ static int asd_map_memio(struct asd_ha_struct *asd_ha)
 				   pci_name(asd_ha->pcidev));
 			goto Err;
 		}
-		if (io_handle->flags & IORESOURCE_CACHEABLE)
-			io_handle->addr = ioremap(io_handle->start,
-						  io_handle->len);
-		else
-			io_handle->addr = ioremap_nocache(io_handle->start,
-							  io_handle->len);
+		io_handle->addr = ioremap(io_handle->start, io_handle->len);
 		if (!io_handle->addr) {
 			asd_printk("couldn't map MBAR%d of %s\n", i==0?0:1,
 				   pci_name(asd_ha->pcidev));
diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 914c39f9f388..e4f77cad9fd8 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -259,10 +259,7 @@ static bool arcmsr_remap_pciregion(struct AdapterControlBlock *acb)
 		addr = (unsigned long)pci_resource_start(pdev, 0);
 		range = pci_resource_len(pdev, 0);
 		flags = pci_resource_flags(pdev, 0);
-		if (flags & IORESOURCE_CACHEABLE)
-			mem_base0 = ioremap(addr, range);
-		else
-			mem_base0 = ioremap_nocache(addr, range);
+		mem_base0 = ioremap(addr, range);
 		if (!mem_base0) {
 			pr_notice("arcmsr%d: memory mapping region fail\n",
 				acb->host->host_no);
diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c
index d40d734aa53a..e654b5cec69e 100644
--- a/drivers/scsi/mvsas/mv_init.c
+++ b/drivers/scsi/mvsas/mv_init.c
@@ -324,13 +324,9 @@ int mvs_ioremap(struct mvs_info *mvi, int bar, int bar_ex)
 			goto err_out;
 
 		res_flag_ex = pci_resource_flags(pdev, bar_ex);
-		if (res_flag_ex & IORESOURCE_MEM) {
-			if (res_flag_ex & IORESOURCE_CACHEABLE)
-				mvi->regs_ex = ioremap(res_start, res_len);
-			else
-				mvi->regs_ex = ioremap_nocache(res_start,
-						res_len);
-		} else
+		if (res_flag_ex & IORESOURCE_MEM)
+			mvi->regs_ex = ioremap(res_start, res_len);
+		else
 			mvi->regs_ex = (void *)res_start;
 		if (!mvi->regs_ex)
 			goto err_out;
@@ -342,10 +338,7 @@ int mvs_ioremap(struct mvs_info *mvi, int bar, int bar_ex)
 		goto err_out;
 
 	res_flag = pci_resource_flags(pdev, bar);
-	if (res_flag & IORESOURCE_CACHEABLE)
-		mvi->regs = ioremap(res_start, res_len);
-	else
-		mvi->regs = ioremap_nocache(res_start, res_len);
+	mvi->regs = ioremap(res_start, res_len);
 
 	if (!mvi->regs) {
 		if (mvi->regs_ex && (res_flag_ex & IORESOURCE_MEM))
diff --git a/drivers/scsi/sun3x_esp.c b/drivers/scsi/sun3x_esp.c
index e26e81de7c45..d50c5ed8f428 100644
--- a/drivers/scsi/sun3x_esp.c
+++ b/drivers/scsi/sun3x_esp.c
@@ -12,9 +12,9 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 
 #include <asm/sun3x.h>
-#include <asm/io.h>
 #include <asm/dma.h>
 #include <asm/dvma.h>
 
diff --git a/drivers/staging/comedi/drivers/ii_pci20kc.c b/drivers/staging/comedi/drivers/ii_pci20kc.c
index 0768bc42a5db..14ef1f67dd42 100644
--- a/drivers/staging/comedi/drivers/ii_pci20kc.c
+++ b/drivers/staging/comedi/drivers/ii_pci20kc.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/io.h>
 #include "../comedidev.h"
 
 /*
diff --git a/drivers/staging/unisys/visorbus/visorchannel.c b/drivers/staging/unisys/visorbus/visorchannel.c
index 20b63496e9f2..19c4a78a3617 100644
--- a/drivers/staging/unisys/visorbus/visorchannel.c
+++ b/drivers/staging/unisys/visorbus/visorchannel.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/uuid.h>
+#include <linux/io.h>
 
 #include "version.h"
 #include "visorbus.h"
@@ -36,7 +37,7 @@ static const uuid_le spar_video_guid = SPAR_CONSOLEVIDEO_CHANNEL_PROTOCOL_GUID;
 struct visorchannel {
 	u64 physaddr;
 	ulong nbytes;
-	void __iomem *mapped;
+	void *mapped;
 	bool requested;
 	struct channel_header chan_hdr;
 	uuid_le guid;
@@ -93,7 +94,7 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 		}
 	}
 
-	channel->mapped = ioremap_cache(physaddr, size);
+	channel->mapped = memremap(physaddr, size, MEMREMAP_WB);
 	if (!channel->mapped) {
 		release_mem_region(physaddr, size);
 		goto cleanup;
@@ -113,7 +114,7 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 	if (uuid_le_cmp(guid, NULL_UUID_LE) == 0)
 		guid = channel->chan_hdr.chtype;
 
-	iounmap(channel->mapped);
+	memunmap(channel->mapped);
 	if (channel->requested)
 		release_mem_region(channel->physaddr, channel->nbytes);
 	channel->mapped = NULL;
@@ -126,7 +127,8 @@ visorchannel_create_guts(u64 physaddr, unsigned long channel_bytes,
 		}
 	}
 
-	channel->mapped = ioremap_cache(channel->physaddr, channel_bytes);
+	channel->mapped = memremap(channel->physaddr, channel_bytes,
+			MEMREMAP_WB);
 	if (!channel->mapped) {
 		release_mem_region(channel->physaddr, channel_bytes);
 		goto cleanup;
@@ -167,7 +169,7 @@ visorchannel_destroy(struct visorchannel *channel)
 	if (!channel)
 		return;
 	if (channel->mapped) {
-		iounmap(channel->mapped);
+		memunmap(channel->mapped);
 		if (channel->requested)
 			release_mem_region(channel->physaddr, channel->nbytes);
 	}
@@ -241,7 +243,7 @@ visorchannel_read(struct visorchannel *channel, ulong offset,
 	if (offset + nbytes > channel->nbytes)
 		return -EIO;
 
-	memcpy_fromio(local, channel->mapped + offset, nbytes);
+	memcpy(local, channel->mapped + offset, nbytes);
 
 	return 0;
 }
@@ -262,7 +264,7 @@ visorchannel_write(struct visorchannel *channel, ulong offset,
 		memcpy(&channel->chan_hdr + offset, local, copy_size);
 	}
 
-	memcpy_toio(channel->mapped + offset, local, nbytes);
+	memcpy(channel->mapped + offset, local, nbytes);
 
 	return 0;
 }
diff --git a/drivers/staging/unisys/visorbus/visorchipset.c b/drivers/staging/unisys/visorbus/visorchipset.c
index bb8087e70127..e3c55ccf929b 100644
--- a/drivers/staging/unisys/visorbus/visorchipset.c
+++ b/drivers/staging/unisys/visorbus/visorchipset.c
@@ -119,7 +119,7 @@ static struct visorchannel *controlvm_channel;
 
 /* Manages the request payload in the controlvm channel */
 struct visor_controlvm_payload_info {
-	u8 __iomem *ptr;	/* pointer to base address of payload pool */
+	u8 *ptr;		/* pointer to base address of payload pool */
 	u64 offset;		/* offset from beginning of controlvm
 				 * channel to beginning of payload * pool */
 	u32 bytes;		/* number of bytes in payload pool */
@@ -401,21 +401,22 @@ parser_init_byte_stream(u64 addr, u32 bytes, bool local, bool *retry)
 		p = __va((unsigned long) (addr));
 		memcpy(ctx->data, p, bytes);
 	} else {
-		void __iomem *mapping;
+		void *mapping;
 
 		if (!request_mem_region(addr, bytes, "visorchipset")) {
 			rc = NULL;
 			goto cleanup;
 		}
 
-		mapping = ioremap_cache(addr, bytes);
+		mapping = memremap(addr, bytes, MEMREMAP_WB);
 		if (!mapping) {
 			release_mem_region(addr, bytes);
 			rc = NULL;
 			goto cleanup;
 		}
-		memcpy_fromio(ctx->data, mapping, bytes);
+		memcpy(ctx->data, mapping, bytes);
 		release_mem_region(addr, bytes);
+		memunmap(mapping);
 	}
 
 	ctx->byte_stream = true;
@@ -1327,7 +1328,7 @@ static int
 initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 				  struct visor_controlvm_payload_info *info)
 {
-	u8 __iomem *payload = NULL;
+	u8 *payload = NULL;
 	int rc = CONTROLVM_RESP_SUCCESS;
 
 	if (!info) {
@@ -1339,7 +1340,7 @@ initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 		rc = -CONTROLVM_RESP_ERROR_PAYLOAD_INVALID;
 		goto cleanup;
 	}
-	payload = ioremap_cache(phys_addr + offset, bytes);
+	payload = memremap(phys_addr + offset, bytes, MEMREMAP_WB);
 	if (!payload) {
 		rc = -CONTROLVM_RESP_ERROR_IOREMAP_FAILED;
 		goto cleanup;
@@ -1352,7 +1353,7 @@ initialize_controlvm_payload_info(u64 phys_addr, u64 offset, u32 bytes,
 cleanup:
 	if (rc < 0) {
 		if (payload) {
-			iounmap(payload);
+			memunmap(payload);
 			payload = NULL;
 		}
 	}
@@ -1363,7 +1364,7 @@ static void
 destroy_controlvm_payload_info(struct visor_controlvm_payload_info *info)
 {
 	if (info->ptr) {
-		iounmap(info->ptr);
+		memunmap(info->ptr);
 		info->ptr = NULL;
 	}
 	memset(info, 0, sizeof(struct visor_controlvm_payload_info));
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 37fff12dd4d0..fe902ff52e58 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -38,11 +38,11 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
+#include <linux/io.h>
 #ifdef CONFIG_SPARC
 #include <linux/sunserialcore.h>
 #endif
 
-#include <asm/io.h>
 #include <asm/irq.h>
 
 #include "8250.h"
diff --git a/drivers/video/fbdev/ocfb.c b/drivers/video/fbdev/ocfb.c
index de9819660ca0..c9293aea8ec3 100644
--- a/drivers/video/fbdev/ocfb.c
+++ b/drivers/video/fbdev/ocfb.c
@@ -325,7 +325,6 @@ static int ocfb_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "I/O resource request failed\n");
 		return -ENXIO;
 	}
-	res->flags &= ~IORESOURCE_CACHEABLE;
 	fbdev->regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(fbdev->regs))
 		return PTR_ERR(fbdev->regs);
diff --git a/drivers/video/fbdev/s1d13xxxfb.c b/drivers/video/fbdev/s1d13xxxfb.c
index 83433cb0dfba..96aa46dc696c 100644
--- a/drivers/video/fbdev/s1d13xxxfb.c
+++ b/drivers/video/fbdev/s1d13xxxfb.c
@@ -32,8 +32,7 @@
 #include <linux/spinlock_types.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <video/s1d13xxxfb.h>
 
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 735355b0e023..7df4228e25f0 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -64,6 +64,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/io.h>
 
 #include <asm/grfioctl.h>	/* for HP-UX compatibility */
 #include <asm/uaccess.h>
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 198243717da5..2345a9870e2c 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -441,7 +441,7 @@ EXPORT_SYMBOL_GPL(bdev_write_page);
  * accessible at this address.
  */
 long bdev_direct_access(struct block_device *bdev, sector_t sector,
-			void **addr, unsigned long *pfn, long size)
+			void __pmem **addr, unsigned long *pfn, long size)
 {
 	long avail;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
diff --git a/fs/dax.c b/fs/dax.c
index c3e21ccfc358..7c634ac797b1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -23,6 +23,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/pmem.h>
 #include <linux/sched.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
@@ -34,7 +35,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 
 	might_sleep();
 	do {
-		void *addr;
+		void __pmem *addr;
 		unsigned long pfn;
 		long count;
 
@@ -46,10 +47,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
 			if (pgsz > count)
 				pgsz = count;
-			if (pgsz < PAGE_SIZE)
-				memset(addr, 0, pgsz);
-			else
-				clear_page(addr);
+			clear_pmem(addr, pgsz);
 			addr += pgsz;
 			size -= pgsz;
 			count -= pgsz;
@@ -59,26 +57,29 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 		}
 	} while (size);
 
+	wmb_pmem();
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dax_clear_blocks);
 
-static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
+static long dax_get_addr(struct buffer_head *bh, void __pmem **addr,
+		unsigned blkbits)
 {
 	unsigned long pfn;
 	sector_t sector = bh->b_blocknr << (blkbits - 9);
 	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
 }
 
-static void dax_new_buf(void *addr, unsigned size, unsigned first, loff_t pos,
-			loff_t end)
+/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
+static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
+		loff_t pos, loff_t end)
 {
 	loff_t final = end - pos + first; /* The final byte of the buffer */
 
 	if (first > 0)
-		memset(addr, 0, first);
+		clear_pmem(addr, first);
 	if (final < size)
-		memset(addr + final, 0, size - final);
+		clear_pmem(addr + final, size - final);
 }
 
 static bool buffer_written(struct buffer_head *bh)
@@ -106,14 +107,15 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 	loff_t pos = start;
 	loff_t max = start;
 	loff_t bh_max = start;
-	void *addr;
+	void __pmem *addr;
 	bool hole = false;
+	bool need_wmb = false;
 
 	if (iov_iter_rw(iter) != WRITE)
 		end = min(end, i_size_read(inode));
 
 	while (pos < end) {
-		unsigned len;
+		size_t len;
 		if (pos == max) {
 			unsigned blkbits = inode->i_blkbits;
 			sector_t block = pos >> blkbits;
@@ -145,19 +147,23 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 				retval = dax_get_addr(bh, &addr, blkbits);
 				if (retval < 0)
 					break;
-				if (buffer_unwritten(bh) || buffer_new(bh))
+				if (buffer_unwritten(bh) || buffer_new(bh)) {
 					dax_new_buf(addr, retval, first, pos,
 									end);
+					need_wmb = true;
+				}
 				addr += first;
 				size = retval - first;
 			}
 			max = min(pos + size, end);
 		}
 
-		if (iov_iter_rw(iter) == WRITE)
-			len = copy_from_iter_nocache(addr, max - pos, iter);
-		else if (!hole)
-			len = copy_to_iter(addr, max - pos, iter);
+		if (iov_iter_rw(iter) == WRITE) {
+			len = copy_from_iter_pmem(addr, max - pos, iter);
+			need_wmb = true;
+		} else if (!hole)
+			len = copy_to_iter((void __force *)addr, max - pos,
+					iter);
 		else
 			len = iov_iter_zero(max - pos, iter);
 
@@ -168,6 +174,9 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 		addr += len;
 	}
 
+	if (need_wmb)
+		wmb_pmem();
+
 	return (pos == start) ? retval : pos - start;
 }
 
@@ -260,11 +269,13 @@ static int dax_load_hole(struct address_space *mapping, struct page *page,
 static int copy_user_bh(struct page *to, struct buffer_head *bh,
 			unsigned blkbits, unsigned long vaddr)
 {
-	void *vfrom, *vto;
+	void __pmem *vfrom;
+	void *vto;
+
 	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
 		return -EIO;
 	vto = kmap_atomic(to);
-	copy_user_page(vto, vfrom, vaddr, to);
+	copy_user_page(vto, (void __force *)vfrom, vaddr, to);
 	kunmap_atomic(vto);
 	return 0;
 }
@@ -275,7 +286,7 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 	struct address_space *mapping = inode->i_mapping;
 	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
 	unsigned long vaddr = (unsigned long)vmf->virtual_address;
-	void *addr;
+	void __pmem *addr;
 	unsigned long pfn;
 	pgoff_t size;
 	int error;
@@ -303,8 +314,10 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 		goto out;
 	}
 
-	if (buffer_unwritten(bh) || buffer_new(bh))
-		clear_page(addr);
+	if (buffer_unwritten(bh) || buffer_new(bh)) {
+		clear_pmem(addr, PAGE_SIZE);
+		wmb_pmem();
+	}
 
 	error = vm_insert_mixed(vma, vaddr, pfn);
 
@@ -538,11 +551,12 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 	if (err < 0)
 		return err;
 	if (buffer_written(&bh)) {
-		void *addr;
+		void __pmem *addr;
 		err = dax_get_addr(&bh, &addr, inode->i_blkbits);
 		if (err < 0)
 			return err;
-		memset(addr + offset, 0, length);
+		clear_pmem(addr + offset, length);
+		wmb_pmem();
 	}
 
 	return 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d4068c17d0df..c401ecdff9cb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1555,8 +1555,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	long (*direct_access)(struct block_device *, sector_t,
-					void **, unsigned long *pfn, long size);
+	long (*direct_access)(struct block_device *, sector_t, void __pmem **,
+			unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1574,8 +1574,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
-extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
-						unsigned long *pfn, long size);
+extern long bdev_direct_access(struct block_device *, sector_t,
+		void __pmem **addr, unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index c27dde7215b5..e399029b68c5 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -21,7 +21,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/bug.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/page.h>
 
 /*
diff --git a/include/linux/io.h b/include/linux/io.h
index fb5a99800e77..d8d749abd665 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -80,6 +80,10 @@ int check_signature(const volatile void __iomem *io_addr,
 			const unsigned char *signature, int length);
 void devm_ioremap_release(struct device *dev, void *res);
 
+void *devm_memremap(struct device *dev, resource_size_t offset,
+		size_t size, unsigned long flags);
+void devm_memunmap(struct device *dev, void *addr);
+
 /*
  * Some systems do not have legacy ISA devices.
  * /dev/port is not a valid interface on these systems.
@@ -121,4 +125,13 @@ static inline int arch_phys_wc_index(int handle)
 #endif
 #endif
 
+enum {
+	/* See memremap() kernel-doc for usage description... */
+	MEMREMAP_WB = 1 << 0,
+	MEMREMAP_WT = 1 << 1,
+};
+
+void *memremap(resource_size_t offset, size_t size, unsigned long flags);
+void memunmap(void *addr);
+
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2e872f92dbac..84b05ebedb2d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -369,7 +369,14 @@ static inline int put_page_unless_one(struct page *page)
 }
 
 extern int page_is_ram(unsigned long pfn);
-extern int region_is_ram(resource_size_t phys_addr, unsigned long size);
+
+enum {
+	REGION_INTERSECTS,
+	REGION_DISJOINT,
+	REGION_MIXED,
+};
+
+int region_intersects(resource_size_t offset, size_t size, const char *type);
 
 /* Support for virtually mapped pages */
 struct page *vmalloc_to_page(const void *addr);
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 29975c73a953..366cf77953b5 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -27,9 +27,9 @@
 #include <linux/string.h>
 #include <linux/bug.h>
 #include <linux/kernel.h>
+#include <linux/io.h>
 
 #include <asm/unaligned.h>
-#include <asm/io.h>
 #include <asm/barrier.h>
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index d2114045a6c4..a9d84bf335ee 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -14,28 +14,35 @@
 #define __PMEM_H__
 
 #include <linux/io.h>
+#include <linux/uio.h>
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
-#include <asm/cacheflush.h>
+#include <asm/pmem.h>
 #else
 static inline void arch_wmb_pmem(void)
 {
 	BUG();
 }
 
-static inline bool __arch_has_wmb_pmem(void)
+static inline bool arch_has_wmb_pmem(void)
 {
 	return false;
 }
 
-static inline void __pmem *arch_memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
+		size_t n)
 {
-	return NULL;
+	BUG();
 }
 
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
+static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	BUG();
+	return 0;
+}
+
+static inline void arch_clear_pmem(void __pmem *addr, size_t size)
 {
 	BUG();
 }
@@ -43,8 +50,8 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
 
 /*
  * Architectures that define ARCH_HAS_PMEM_API must provide
- * implementations for arch_memremap_pmem(), arch_memcpy_to_pmem(),
- * arch_wmb_pmem(), and __arch_has_wmb_pmem().
+ * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(),
+ * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem().
  */
 
 static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size)
@@ -52,13 +59,13 @@ static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t si
 	memcpy(dst, (void __force const *) src, size);
 }
 
-static inline void memunmap_pmem(void __pmem *addr)
+static inline void memunmap_pmem(struct device *dev, void __pmem *addr)
 {
-	iounmap((void __force __iomem *) addr);
+	devm_memunmap(dev, (void __force *) addr);
 }
 
 /**
- * arch_has_wmb_pmem - true if wmb_pmem() ensures durability
+ * arch_has_pmem_api - true if wmb_pmem() ensures durability
  *
  * For a given cpu implementation within an architecture it is possible
  * that wmb_pmem() resolves to a nop.  In the case this returns
@@ -66,13 +73,6 @@ static inline void memunmap_pmem(void __pmem *addr)
  * fall back to a different data consistency model, or otherwise notify
  * the user.
  */
-static inline bool arch_has_wmb_pmem(void)
-{
-	if (IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
-		return __arch_has_wmb_pmem();
-	return false;
-}
-
 static inline bool arch_has_pmem_api(void)
 {
 	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && arch_has_wmb_pmem();
@@ -85,16 +85,24 @@ static inline bool arch_has_pmem_api(void)
  * default_memremap_pmem + default_memcpy_to_pmem is sufficient for
  * making data durable relative to i/o completion.
  */
-static void default_memcpy_to_pmem(void __pmem *dst, const void *src,
+static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src,
 		size_t size)
 {
 	memcpy((void __force *) dst, src, size);
 }
 
-static void __pmem *default_memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline size_t default_copy_from_iter_pmem(void __pmem *addr,
+		size_t bytes, struct iov_iter *i)
 {
-	return (void __pmem __force *)ioremap_wt(offset, size);
+	return copy_from_iter_nocache((void __force *)addr, bytes, i);
+}
+
+static inline void default_clear_pmem(void __pmem *addr, size_t size)
+{
+	if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0)
+		clear_page((void __force *)addr);
+	else
+		memset((void __force *)addr, 0, size);
 }
 
 /**
@@ -109,12 +117,16 @@ static void __pmem *default_memremap_pmem(resource_size_t offset,
  * wmb_pmem() arrange for the data to be written through the
  * cache to persistent media.
  */
-static inline void __pmem *memremap_pmem(resource_size_t offset,
-		unsigned long size)
+static inline void __pmem *memremap_pmem(struct device *dev,
+		resource_size_t offset, unsigned long size)
 {
-	if (arch_has_pmem_api())
-		return arch_memremap_pmem(offset, size);
-	return default_memremap_pmem(offset, size);
+#ifdef ARCH_MEMREMAP_PMEM
+	return (void __pmem *) devm_memremap(dev, offset, size,
+			ARCH_MEMREMAP_PMEM);
+#else
+	return (void __pmem *) devm_memremap(dev, offset, size,
+			MEMREMAP_WT);
+#endif
 }
 
 /**
@@ -149,4 +161,37 @@ static inline void wmb_pmem(void)
 	if (arch_has_pmem_api())
 		arch_wmb_pmem();
 }
+
+/**
+ * copy_from_iter_pmem - copy data from an iterator to PMEM
+ * @addr:	PMEM destination address
+ * @bytes:	number of bytes to copy
+ * @i:		iterator with source data
+ *
+ * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+		struct iov_iter *i)
+{
+	if (arch_has_pmem_api())
+		return arch_copy_from_iter_pmem(addr, bytes, i);
+	return default_copy_from_iter_pmem(addr, bytes, i);
+}
+
+/**
+ * clear_pmem - zero a PMEM memory range
+ * @addr:	virtual start address
+ * @size:	number of bytes to zero
+ *
+ * Write zeros into the memory range starting at 'addr' for 'size' bytes.
+ * This function requires explicit ordering with a wmb_pmem() call.
+ */
+static inline void clear_pmem(void __pmem *addr, size_t size)
+{
+	if (arch_has_pmem_api())
+		arch_clear_pmem(addr, size);
+	else
+		default_clear_pmem(addr, size);
+}
 #endif /* __PMEM_H__ */
diff --git a/include/video/vga.h b/include/video/vga.h
index cac567f22e62..d334e64c1c19 100644
--- a/include/video/vga.h
+++ b/include/video/vga.h
@@ -18,7 +18,7 @@
 #define __linux_video_vga_h__
 
 #include <linux/types.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/vga.h>
 #include <asm/byteorder.h>
 
diff --git a/kernel/Makefile b/kernel/Makefile
index 43c4c920f30a..92866d36e376 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -99,6 +99,8 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 obj-$(CONFIG_TORTURE_TEST) += torture.o
 
+obj-$(CONFIG_HAS_IOMEM) += memremap.o
+
 $(obj)/configs.o: $(obj)/config_data.h
 
 # config_data.h contains the same information as ikconfig.h but gzipped.
diff --git a/kernel/memremap.c b/kernel/memremap.c
new file mode 100644
index 000000000000..5c9b55eaf121
--- /dev/null
+++ b/kernel/memremap.c
@@ -0,0 +1,137 @@
+/*
+ * Copyright(c) 2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+
+#ifndef ioremap_cache
+/* temporary while we convert existing ioremap_cache users to memremap */
+__weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size)
+{
+	return ioremap(offset, size);
+}
+#endif
+
+/**
+ * memremap() - remap an iomem_resource as cacheable memory
+ * @offset: iomem resource start address
+ * @size: size of remap
+ * @flags: either MEMREMAP_WB or MEMREMAP_WT
+ *
+ * memremap() is "ioremap" for cases where it is known that the resource
+ * being mapped does not have i/o side effects and the __iomem
+ * annotation is not applicable.
+ *
+ * MEMREMAP_WB - matches the default mapping for "System RAM" on
+ * the architecture.  This is usually a read-allocate write-back cache.
+ * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
+ * memremap() will bypass establishing a new mapping and instead return
+ * a pointer into the direct map.
+ *
+ * MEMREMAP_WT - establish a mapping whereby writes either bypass the
+ * cache or are written through to memory and never exist in a
+ * cache-dirty state with respect to program visibility.  Attempts to
+ * map "System RAM" with this mapping type will fail.
+ */
+void *memremap(resource_size_t offset, size_t size, unsigned long flags)
+{
+	int is_ram = region_intersects(offset, size, "System RAM");
+	void *addr = NULL;
+
+	if (is_ram == REGION_MIXED) {
+		WARN_ONCE(1, "memremap attempted on mixed range %pa size: %#lx\n",
+				&offset, (unsigned long) size);
+		return NULL;
+	}
+
+	/* Try all mapping types requested until one returns non-NULL */
+	if (flags & MEMREMAP_WB) {
+		flags &= ~MEMREMAP_WB;
+		/*
+		 * MEMREMAP_WB is special in that it can be satisifed
+		 * from the direct map.  Some archs depend on the
+		 * capability of memremap() to autodetect cases where
+		 * the requested range is potentially in "System RAM"
+		 */
+		if (is_ram == REGION_INTERSECTS)
+			addr = __va(offset);
+		else
+			addr = ioremap_cache(offset, size);
+	}
+
+	/*
+	 * If we don't have a mapping yet and more request flags are
+	 * pending then we will be attempting to establish a new virtual
+	 * address mapping.  Enforce that this mapping is not aliasing
+	 * "System RAM"
+	 */
+	if (!addr && is_ram == REGION_INTERSECTS && flags) {
+		WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
+				&offset, (unsigned long) size);
+		return NULL;
+	}
+
+	if (!addr && (flags & MEMREMAP_WT)) {
+		flags &= ~MEMREMAP_WT;
+		addr = ioremap_wt(offset, size);
+	}
+
+	return addr;
+}
+EXPORT_SYMBOL(memremap);
+
+void memunmap(void *addr)
+{
+	if (is_vmalloc_addr(addr))
+		iounmap((void __iomem *) addr);
+}
+EXPORT_SYMBOL(memunmap);
+
+static void devm_memremap_release(struct device *dev, void *res)
+{
+	memunmap(res);
+}
+
+static int devm_memremap_match(struct device *dev, void *res, void *match_data)
+{
+	return *(void **)res == match_data;
+}
+
+void *devm_memremap(struct device *dev, resource_size_t offset,
+		size_t size, unsigned long flags)
+{
+	void **ptr, *addr;
+
+	ptr = devres_alloc(devm_memremap_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	addr = memremap(offset, size, flags);
+	if (addr) {
+		*ptr = addr;
+		devres_add(dev, ptr);
+	} else
+		devres_free(ptr);
+
+	return addr;
+}
+EXPORT_SYMBOL(devm_memremap);
+
+void devm_memunmap(struct device *dev, void *addr)
+{
+	WARN_ON(devres_destroy(dev, devm_memremap_release, devm_memremap_match,
+			       addr));
+	memunmap(addr);
+}
+EXPORT_SYMBOL(devm_memunmap);
diff --git a/kernel/resource.c b/kernel/resource.c
index fed052a1bc9f..f150dbbe6f62 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -492,40 +492,51 @@ int __weak page_is_ram(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(page_is_ram);
 
-/*
- * Search for a resouce entry that fully contains the specified region.
- * If found, return 1 if it is RAM, 0 if not.
- * If not found, or region is not fully contained, return -1
+/**
+ * region_intersects() - determine intersection of region with known resources
+ * @start: region start address
+ * @size: size of region
+ * @name: name of resource (in iomem_resource)
  *
- * Used by the ioremap functions to ensure the user is not remapping RAM and is
- * a vast speed up over walking through the resource table page by page.
+ * Check if the specified region partially overlaps or fully eclipses a
+ * resource identified by @name.  Return REGION_DISJOINT if the region
+ * does not overlap @name, return REGION_MIXED if the region overlaps
+ * @type and another resource, and return REGION_INTERSECTS if the
+ * region overlaps @type and no other defined resource. Note, that
+ * REGION_INTERSECTS is also returned in the case when the specified
+ * region overlaps RAM and undefined memory holes.
+ *
+ * region_intersect() is used by memory remapping functions to ensure
+ * the user is not remapping RAM and is a vast speed up over walking
+ * through the resource table page by page.
  */
-int region_is_ram(resource_size_t start, unsigned long size)
+int region_intersects(resource_size_t start, size_t size, const char *name)
 {
-	struct resource *p;
-	resource_size_t end = start + size - 1;
 	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-	const char *name = "System RAM";
-	int ret = -1;
+	resource_size_t end = start + size - 1;
+	int type = 0; int other = 0;
+	struct resource *p;
 
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
-		if (p->end < start)
-			continue;
-
-		if (p->start <= start && end <= p->end) {
-			/* resource fully contains region */
-			if ((p->flags != flags) || strcmp(p->name, name))
-				ret = 0;
-			else
-				ret = 1;
-			break;
-		}
-		if (end < p->start)
-			break;	/* not found */
+		bool is_type = strcmp(p->name, name) == 0 && p->flags == flags;
+
+		if (start >= p->start && start <= p->end)
+			is_type ? type++ : other++;
+		if (end >= p->start && end <= p->end)
+			is_type ? type++ : other++;
+		if (p->start >= start && p->end <= end)
+			is_type ? type++ : other++;
 	}
 	read_unlock(&resource_lock);
-	return ret;
+
+	if (other == 0)
+		return type ? REGION_INTERSECTS : REGION_DISJOINT;
+
+	if (type)
+		return REGION_MIXED;
+
+	return REGION_DISJOINT;
 }
 
 void __weak arch_remove_reservations(struct resource *avail)
diff --git a/lib/Kconfig b/lib/Kconfig
index 3a2ef67db6c7..a938a39191b3 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -531,4 +531,7 @@ config ARCH_HAS_SG_CHAIN
 config ARCH_HAS_PMEM_API
 	bool
 
+config ARCH_HAS_MMIO_FLUSH
+	bool
+
 endmenu
diff --git a/lib/devres.c b/lib/devres.c
index fbe2aac522e6..f13a2468ff39 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -119,10 +119,9 @@ EXPORT_SYMBOL(devm_iounmap);
  * @dev: generic device to handle the resource for
  * @res: resource to be handled
  *
- * Checks that a resource is a valid memory region, requests the memory region
- * and ioremaps it either as cacheable or as non-cacheable memory depending on
- * the resource's flags. All operations are managed and will be undone on
- * driver detach.
+ * Checks that a resource is a valid memory region, requests the memory
+ * region and ioremaps it. All operations are managed and will be undone
+ * on driver detach.
  *
  * Returns a pointer to the remapped memory or an ERR_PTR() encoded error code
  * on failure. Usage example:
@@ -153,11 +152,7 @@ void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res)
 		return IOMEM_ERR_PTR(-EBUSY);
 	}
 
-	if (res->flags & IORESOURCE_CACHEABLE)
-		dest_ptr = devm_ioremap(dev, res->start, size);
-	else
-		dest_ptr = devm_ioremap_nocache(dev, res->start, size);
-
+	dest_ptr = devm_ioremap(dev, res->start, size);
 	if (!dest_ptr) {
 		dev_err(dev, "ioremap failed for resource %pR\n", res);
 		devm_release_mem_region(dev, res->start, size);
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index bcce5f149310..e1930dbab2da 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -41,11 +41,8 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
 		len = maxlen;
 	if (flags & IORESOURCE_IO)
 		return __pci_ioport_map(dev, start, len);
-	if (flags & IORESOURCE_MEM) {
-		if (flags & IORESOURCE_CACHEABLE)
-			return ioremap(start, len);
-		return ioremap_nocache(start, len);
-	}
+	if (flags & IORESOURCE_MEM)
+		return ioremap(start, len);
 	/* What? */
 	return NULL;
 }
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index d7c136a96346..98f2881ba6a2 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -1,9 +1,11 @@
-ldflags-y += --wrap=ioremap_wt
 ldflags-y += --wrap=ioremap_wc
+ldflags-y += --wrap=memremap
 ldflags-y += --wrap=devm_ioremap_nocache
-ldflags-y += --wrap=ioremap_cache
+ldflags-y += --wrap=devm_memremap
 ldflags-y += --wrap=ioremap_nocache
 ldflags-y += --wrap=iounmap
+ldflags-y += --wrap=memunmap
+ldflags-y += --wrap=__devm_request_region
 ldflags-y += --wrap=__request_region
 ldflags-y += --wrap=__release_region
 
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 64bfaa50831c..179d2289f3a8 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -80,23 +80,39 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
 }
 EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
 
-void __iomem *__wrap_ioremap_cache(resource_size_t offset, unsigned long size)
+void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
+		size_t size, unsigned long flags)
 {
-	return __nfit_test_ioremap(offset, size, ioremap_cache);
+	struct nfit_test_resource *nfit_res;
+
+	rcu_read_lock();
+	nfit_res = get_nfit_res(offset);
+	rcu_read_unlock();
+	if (nfit_res)
+		return nfit_res->buf + offset - nfit_res->res->start;
+	return devm_memremap(dev, offset, size, flags);
 }
-EXPORT_SYMBOL(__wrap_ioremap_cache);
+EXPORT_SYMBOL(__wrap_devm_memremap);
 
-void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size)
+void *__wrap_memremap(resource_size_t offset, size_t size,
+		unsigned long flags)
 {
-	return __nfit_test_ioremap(offset, size, ioremap_nocache);
+	struct nfit_test_resource *nfit_res;
+
+	rcu_read_lock();
+	nfit_res = get_nfit_res(offset);
+	rcu_read_unlock();
+	if (nfit_res)
+		return nfit_res->buf + offset - nfit_res->res->start;
+	return memremap(offset, size, flags);
 }
-EXPORT_SYMBOL(__wrap_ioremap_nocache);
+EXPORT_SYMBOL(__wrap_memremap);
 
-void __iomem *__wrap_ioremap_wt(resource_size_t offset, unsigned long size)
+void __iomem *__wrap_ioremap_nocache(resource_size_t offset, unsigned long size)
 {
-	return __nfit_test_ioremap(offset, size, ioremap_wt);
+	return __nfit_test_ioremap(offset, size, ioremap_nocache);
 }
-EXPORT_SYMBOL(__wrap_ioremap_wt);
+EXPORT_SYMBOL(__wrap_ioremap_nocache);
 
 void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size)
 {
@@ -117,9 +133,22 @@ void __wrap_iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(__wrap_iounmap);
 
-struct resource *__wrap___request_region(struct resource *parent,
-		resource_size_t start, resource_size_t n, const char *name,
-		int flags)
+void __wrap_memunmap(void *addr)
+{
+	struct nfit_test_resource *nfit_res;
+
+	rcu_read_lock();
+	nfit_res = get_nfit_res((unsigned long) addr);
+	rcu_read_unlock();
+	if (nfit_res)
+		return;
+	return memunmap(addr);
+}
+EXPORT_SYMBOL(__wrap_memunmap);
+
+static struct resource *nfit_test_request_region(struct device *dev,
+		struct resource *parent, resource_size_t start,
+		resource_size_t n, const char *name, int flags)
 {
 	struct nfit_test_resource *nfit_res;
 
@@ -147,10 +176,29 @@ struct resource *__wrap___request_region(struct resource *parent,
 			return res;
 		}
 	}
+	if (dev)
+		return __devm_request_region(dev, parent, start, n, name);
 	return __request_region(parent, start, n, name, flags);
 }
+
+struct resource *__wrap___request_region(struct resource *parent,
+		resource_size_t start, resource_size_t n, const char *name,
+		int flags)
+{
+	return nfit_test_request_region(NULL, parent, start, n, name, flags);
+}
 EXPORT_SYMBOL(__wrap___request_region);
 
+struct resource *__wrap___devm_request_region(struct device *dev,
+		struct resource *parent, resource_size_t start,
+		resource_size_t n, const char *name)
+{
+	if (!dev)
+		return NULL;
+	return nfit_test_request_region(dev, parent, start, n, name, 0);
+}
+EXPORT_SYMBOL(__wrap___devm_request_region);
+
 void __wrap___release_region(struct resource *parent, resource_size_t start,
 				resource_size_t n)
 {
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 28dba918524e..021e6f97f33e 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1029,9 +1029,13 @@ static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
 
 	lane = nd_region_acquire_lane(nd_region);
 	if (rw)
-		memcpy(mmio->base + dpa, iobuf, len);
-	else
-		memcpy(iobuf, mmio->base + dpa, len);
+		memcpy(mmio->addr.base + dpa, iobuf, len);
+	else {
+		memcpy(iobuf, mmio->addr.base + dpa, len);
+
+		/* give us some some coverage of the mmio_flush_range() API */
+		mmio_flush_range(mmio->addr.base + dpa, len);
+	}
 	nd_region_release_lane(nd_region, lane);
 
 	return 0;