Merge tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This update has successfully completed a 0day-kbuild run and has
  appeared in a linux-next release.  The changes outside of the typical
  drivers/nvdimm/ and drivers/acpi/nfit.[ch] paths are related to the
  removal of IORESOURCE_CACHEABLE, the introduction of memremap(), and
  the introduction of ZONE_DEVICE + devm_memremap_pages().

  Summary:

   - Introduce ZONE_DEVICE and devm_memremap_pages() as a generic
     mechanism for adding device-driver-discovered memory regions to the
     kernel's direct map.

     This facility is used by the pmem driver to enable pfn_to_page()
     operations on the page frames returned by DAX ('direct_access' in
     'struct block_device_operations').

     For now, the 'memmap' allocation for these "device" pages comes
     from "System RAM".  Support for allocating the memmap from device
     memory will arrive in a later kernel.

   - Introduce memremap() to replace usages of ioremap_cache() and
     ioremap_wt().  memremap() drops the __iomem annotation for these
     mappings to memory that do not have i/o side effects.  The
     replacement of ioremap_cache() with memremap() is limited to the
     pmem driver to ease merging the api change in v4.3.

     Completion of the conversion is targeted for v4.4.

   - Similar to the usage of memcpy_to_pmem() + wmb_pmem() in the pmem
     driver, update the VFS DAX implementation and PMEM api to provide
     persistence guarantees for kernel operations on a DAX mapping.

   - Convert the ACPI NFIT 'BLK' driver to map the block apertures as
     cacheable to improve performance.

   - Miscellaneous updates and fixes to libnvdimm including support for
     issuing "address range scrub" commands, clarifying the optimal
     'sector size' of pmem devices, a clarification of the usage of the
     ACPI '_STA' (status) property for DIMM devices, and other minor
     fixes"

* tag 'libnvdimm-for-4.3' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (34 commits)
  libnvdimm, pmem: direct map legacy pmem by default
  libnvdimm, pmem: 'struct page' for pmem
  libnvdimm, pfn: 'struct page' provider infrastructure
  x86, pmem: clarify that ARCH_HAS_PMEM_API implies PMEM mapped WB
  add devm_memremap_pages
  mm: ZONE_DEVICE for "device memory"
  mm: move __phys_to_pfn and __pfn_to_phys to asm/generic/memory_model.h
  dax: drop size parameter to ->direct_access()
  nd_blk: change aperture mapping from WC to WB
  nvdimm: change to use generic kvfree()
  pmem, dax: have direct_access use __pmem annotation
  dax: update I/O path to do proper PMEM flushing
  pmem: add copy_from_iter_pmem() and clear_pmem()
  pmem, x86: clean up conditional pmem includes
  pmem: remove layer when calling arch_has_wmb_pmem()
  pmem, x86: move x86 PMEM API to new pmem.h header
  libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option
  pmem: switch to devm_ allocations
  devres: add devm_memremap
  libnvdimm, btt: write and validate parent_uuid
  ...

3 files changed, 228 insertions, 25 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index d25ebea0453a..e0d7587e7684 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..72b0c66628b6
--- /dev/null
+++ b/kernel/memremap.c
@@ -0,0 +1,190 @@
+/*
+ * 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>
+#include <linux/memory_hotplug.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);
+
+#ifdef CONFIG_ZONE_DEVICE
+struct page_map {
+	struct resource res;
+};
+
+static void devm_memremap_pages_release(struct device *dev, void *res)
+{
+	struct page_map *page_map = res;
+
+	/* pages are dead and unused, undo the arch mapping */
+	arch_remove_memory(page_map->res.start, resource_size(&page_map->res));
+}
+
+void *devm_memremap_pages(struct device *dev, struct resource *res)
+{
+	int is_ram = region_intersects(res->start, resource_size(res),
+			"System RAM");
+	struct page_map *page_map;
+	int error, nid;
+
+	if (is_ram == REGION_MIXED) {
+		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
+				__func__, res);
+		return ERR_PTR(-ENXIO);
+	}
+
+	if (is_ram == REGION_INTERSECTS)
+		return __va(res->start);
+
+	page_map = devres_alloc(devm_memremap_pages_release,
+			sizeof(*page_map), GFP_KERNEL);
+	if (!page_map)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&page_map->res, res, sizeof(*res));
+
+	nid = dev_to_node(dev);
+	if (nid < 0)
+		nid = 0;
+
+	error = arch_add_memory(nid, res->start, resource_size(res), true);
+	if (error) {
+		devres_free(page_map);
+		return ERR_PTR(error);
+	}
+
+	devres_add(dev, page_map);
+	return __va(res->start);
+}
+EXPORT_SYMBOL(devm_memremap_pages);
+#endif /* CONFIG_ZONE_DEVICE */
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)