Merge tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This adds a user for the new 'bytes-remaining' updates to
  memcpy_mcsafe() that you already received through Ingo via the
  x86-dax- for-linus pull.

  Not included here, but still targeting this cycle, is support for
  handling memory media errors (poison) consumed via userspace dax
  mappings.

  Summary:

   - DAX broke a fundamental assumption of truncate of file mapped
     pages. The truncate path assumed that it is safe to disconnect a
     pinned page from a file and let the filesystem reclaim the physical
     block. With DAX the page is equivalent to the filesystem block.
     Introduce dax_layout_busy_page() to enable filesystems to wait for
     pinned DAX pages to be released. Without this wait a filesystem
     could allocate blocks under active device-DMA to a new file.

   - DAX arranges for the block layer to be bypassed and uses
     dax_direct_access() + copy_to_iter() to satisfy read(2) calls.
     However, the memcpy_mcsafe() facility is available through the pmem
     block driver. In order to safely handle media errors, via the DAX
     block-layer bypass, introduce copy_to_iter_mcsafe().

   - Fix cache management policy relative to the ACPI NFIT Platform
     Capabilities Structure to properly elide cache flushes when they
     are not necessary. The table indicates whether CPU caches are
     power-fail protected. Clarify that a deep flush is always performed
     on REQ_{FUA,PREFLUSH} requests"

* tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits)
  dax: Use dax_write_cache* helpers
  libnvdimm, pmem: Do not flush power-fail protected CPU caches
  libnvdimm, pmem: Unconditionally deep flush on *sync
  libnvdimm, pmem: Complete REQ_FLUSH => REQ_PREFLUSH
  acpi, nfit: Remove ecc_unit_size
  dax: dax_insert_mapping_entry always succeeds
  libnvdimm, e820: Register all pmem resources
  libnvdimm: Debug probe times
  linvdimm, pmem: Preserve read-only setting for pmem devices
  x86, nfit_test: Add unit test for memcpy_mcsafe()
  pmem: Switch to copy_to_iter_mcsafe()
  dax: Report bytes remaining in dax_iomap_actor()
  dax: Introduce a ->copy_to_iter dax operation
  uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation
  xfs, dax: introduce xfs_break_dax_layouts()
  xfs: prepare xfs_break_layouts() for another layout type
  xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL
  mm, fs, dax: handle layout changes to pinned dax mappings
  mm: fix __gup_device_huge vs unmap
  mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS
  ...

Documentation/ABI/removed/sysfs-bus-nfit

@@ -0,0 +1,17 @@
+What:		/sys/bus/nd/devices/regionX/nfit/ecc_unit_size
+Date:		Aug, 2017
+KernelVersion:	v4.14 (Removed v4.18)
+Contact:	linux-nvdimm@lists.01.org
+Description:
+		(RO) Size of a write request to a DIMM that will not incur a
+		read-modify-write cycle at the memory controller.
+
+		When the nfit driver initializes it runs an ARS (Address Range
+		Scrub) operation across every pmem range. Part of that process
+		involves determining the ARS capabilities of a given address
+		range. One of the capabilities that is reported is the 'Clear
+		Uncorrectable Error Range Length Unit Size' (see: ACPI 6.2
+		section 9.20.7.4 Function Index 1 - Query ARS Capabilities).
+		This property indicates the boundary at which the NVDIMM may
+		need to perform read-modify-write cycles to maintain ECC (Error
+		Correcting Code) blocks.

Documentation/ABI/testing/sysfs-bus-nfit

@@ -212,22 +212,3 @@ Description:
 		range. Used by NVDIMM Region Mapping Structure to uniquely refer
 		to this structure. Value of 0 is reserved and not used as an
 		index.
-
-
-What:		/sys/bus/nd/devices/regionX/nfit/ecc_unit_size
-Date:		Aug, 2017
-KernelVersion:	v4.14
-Contact:	linux-nvdimm@lists.01.org
-Description:
-		(RO) Size of a write request to a DIMM that will not incur a
-		read-modify-write cycle at the memory controller.
-
-		When the nfit driver initializes it runs an ARS (Address Range
-		Scrub) operation across every pmem range. Part of that process
-		involves determining the ARS capabilities of a given address
-		range. One of the capabilities that is reported is the 'Clear
-		Uncorrectable Error Range Length Unit Size' (see: ACPI 6.2
-		section 9.20.7.4 Function Index 1 - Query ARS Capabilities).
-		This property indicates the boundary at which the NVDIMM may
-		need to perform read-modify-write cycles to maintain ECC (Error
-		Correcting Code) blocks.

arch/x86/Kconfig.debug

@@ -72,6 +72,9 @@ config EARLY_PRINTK_USB_XDBC
 	  You should normally say N here, unless you want to debug early
 	  crashes or need a very simple printk logging facility.
 
+config MCSAFE_TEST
+	def_bool n
+
 config X86_PTDUMP_CORE
 	def_bool n
 

arch/x86/include/asm/mcsafe_test.h

@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MCSAFE_TEST_H_
+#define _MCSAFE_TEST_H_
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_MCSAFE_TEST
+extern unsigned long mcsafe_test_src;
+extern unsigned long mcsafe_test_dst;
+
+static inline void mcsafe_inject_src(void *addr)
+{
+	if (addr)
+		mcsafe_test_src = (unsigned long) addr;
+	else
+		mcsafe_test_src = ~0UL;
+}
+
+static inline void mcsafe_inject_dst(void *addr)
+{
+	if (addr)
+		mcsafe_test_dst = (unsigned long) addr;
+	else
+		mcsafe_test_dst = ~0UL;
+}
+#else /* CONFIG_MCSAFE_TEST */
+static inline void mcsafe_inject_src(void *addr)
+{
+}
+
+static inline void mcsafe_inject_dst(void *addr)
+{
+}
+#endif /* CONFIG_MCSAFE_TEST */
+
+#else /* __ASSEMBLY__ */
+#include <asm/export.h>
+
+#ifdef CONFIG_MCSAFE_TEST
+.macro MCSAFE_TEST_CTL
+	.pushsection .data
+	.align 8
+	.globl mcsafe_test_src
+	mcsafe_test_src:
+		.quad 0
+	EXPORT_SYMBOL_GPL(mcsafe_test_src)
+	.globl mcsafe_test_dst
+	mcsafe_test_dst:
+		.quad 0
+	EXPORT_SYMBOL_GPL(mcsafe_test_dst)
+	.popsection
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+	leaq \count(\reg), %r9
+	cmp mcsafe_test_src, %r9
+	ja \target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+	leaq \count(\reg), %r9
+	cmp mcsafe_test_dst, %r9
+	ja \target
+.endm
+#else
+.macro MCSAFE_TEST_CTL
+.endm
+
+.macro MCSAFE_TEST_SRC reg count target
+.endm
+
+.macro MCSAFE_TEST_DST reg count target
+.endm
+#endif /* CONFIG_MCSAFE_TEST */
+#endif /* __ASSEMBLY__ */
+#endif /* _MCSAFE_TEST_H_ */

arch/x86/lib/memcpy_64.S

@@ -3,6 +3,7 @@
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
+#include <asm/mcsafe_test.h>
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
@@ -183,6 +184,9 @@ ENTRY(memcpy_orig)
 ENDPROC(memcpy_orig)
 
 #ifndef CONFIG_UML
+
+MCSAFE_TEST_CTL
+
 /*
  * __memcpy_mcsafe - memory copy with machine check exception handling
  * Note that we only catch machine checks when reading the source addresses.
@@ -206,6 +210,8 @@ ENTRY(__memcpy_mcsafe)
 	subl %ecx, %edx
 .L_read_leading_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_leading_bytes
 .L_write_leading_bytes:
 	movb %al, (%rdi)
 	incq %rsi
@@ -221,6 +227,8 @@ ENTRY(__memcpy_mcsafe)
 
 .L_read_words:
 	movq (%rsi), %r8
+	MCSAFE_TEST_SRC %rsi 8 .E_read_words
+	MCSAFE_TEST_DST %rdi 8 .E_write_words
 .L_write_words:
 	movq %r8, (%rdi)
 	addq $8, %rsi
@@ -237,6 +245,8 @@ ENTRY(__memcpy_mcsafe)
 	movl %edx, %ecx
 .L_read_trailing_bytes:
 	movb (%rsi), %al
+	MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes
+	MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes
 .L_write_trailing_bytes:
 	movb %al, (%rdi)
 	incq %rsi

drivers/acpi/nfit/core.c

@@ -1978,19 +1978,8 @@ static ssize_t range_index_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(range_index);
 
-static ssize_t ecc_unit_size_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct nd_region *nd_region = to_nd_region(dev);
-	struct nfit_spa *nfit_spa = nd_region_provider_data(nd_region);
-
-	return sprintf(buf, "%d\n", nfit_spa->clear_err_unit);
-}
-static DEVICE_ATTR_RO(ecc_unit_size);
-
 static struct attribute *acpi_nfit_region_attributes[] = {
 	&dev_attr_range_index.attr,
-	&dev_attr_ecc_unit_size.attr,
 	NULL,
 };
 

drivers/dax/super.c

@@ -85,6 +85,7 @@ EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 {
 	struct dax_device *dax_dev;
+	bool dax_enabled = false;
 	pgoff_t pgoff;
 	int err, id;
 	void *kaddr;
@@ -134,14 +135,21 @@ bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
 		 * on being able to do (page_address(pfn_to_page())).
 		 */
 		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
+		dax_enabled = true;
 	} else if (pfn_t_devmap(pfn)) {
-		/* pass */;
-	} else {
+		struct dev_pagemap *pgmap;
+
+		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
+		if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX)
+			dax_enabled = true;
+		put_dev_pagemap(pgmap);
+	}
+
+	if (!dax_enabled) {
 		pr_debug("%s: error: dax support not enabled\n",
 				bdevname(bdev, buf));
 		return false;
 	}
-
 	return true;
 }
 EXPORT_SYMBOL_GPL(__bdev_dax_supported);
@@ -182,8 +190,7 @@ static ssize_t write_cache_show(struct device *dev,
 	if (!dax_dev)
 		return -ENXIO;
 
-	rc = sprintf(buf, "%d\n", !!test_bit(DAXDEV_WRITE_CACHE,
-				&dax_dev->flags));
+	rc = sprintf(buf, "%d\n", !!dax_write_cache_enabled(dax_dev));
 	put_dax(dax_dev);
 	return rc;
 }
@@ -201,10 +208,8 @@ static ssize_t write_cache_store(struct device *dev,
 
 	if (rc)
 		len = rc;
-	else if (write_cache)
-		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
 	else
-		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+		dax_write_cache(dax_dev, write_cache);
 
 	put_dax(dax_dev);
 	return len;
@@ -282,11 +287,21 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 }
 EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 
+size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	if (!dax_alive(dax_dev))
+		return 0;
+
+	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_to_iter);
+
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
 {
-	if (unlikely(!test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags)))
+	if (unlikely(!dax_write_cache_enabled(dax_dev)))
 		return;
 
 	arch_wb_cache_pmem(addr, size);

drivers/md/dm-linear.c

@@ -185,9 +185,24 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct linear_c *lc = ti->private;
+	struct block_device *bdev = lc->dev->bdev;
+	struct dax_device *dax_dev = lc->dev->dax_dev;
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+
+	dev_sector = linear_map_sector(ti, sector);
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define linear_dax_direct_access NULL
 #define linear_dax_copy_from_iter NULL
+#define linear_dax_copy_to_iter NULL
 #endif
 
 static struct target_type linear_target = {
@@ -204,6 +219,7 @@ static struct target_type linear_target = {
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
 	.dax_copy_from_iter = linear_dax_copy_from_iter,
+	.dax_copy_to_iter = linear_dax_copy_to_iter,
 };
 
 int __init dm_linear_init(void)

drivers/md/dm-log-writes.c

@@ -962,9 +962,23 @@ static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
 dax_copy:
 	return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
+
+static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
+					  pgoff_t pgoff, void *addr, size_t bytes,
+					  struct iov_iter *i)
+{
+	struct log_writes_c *lc = ti->private;
+	sector_t sector = pgoff * PAGE_SECTORS;
+
+	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define log_writes_dax_direct_access NULL
 #define log_writes_dax_copy_from_iter NULL
+#define log_writes_dax_copy_to_iter NULL
 #endif
 
 static struct target_type log_writes_target = {
@@ -982,6 +996,7 @@ static struct target_type log_writes_target = {
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
 	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
+	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
 };
 
 static int __init dm_log_writes_init(void)

drivers/md/dm-stripe.c

@@ -354,9 +354,29 @@ static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
 	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
 }
 
+static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct stripe_c *sc = ti->private;
+	struct dax_device *dax_dev;
+	struct block_device *bdev;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, sector, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	dax_dev = sc->stripe[stripe].dev->dax_dev;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
+		return 0;
+	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+
 #else
 #define stripe_dax_direct_access NULL
 #define stripe_dax_copy_from_iter NULL
+#define stripe_dax_copy_to_iter NULL
 #endif
 
 /*
@@ -478,6 +498,7 @@ static struct target_type stripe_target = {
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
 	.dax_copy_from_iter = stripe_dax_copy_from_iter,
+	.dax_copy_to_iter = stripe_dax_copy_to_iter,
 };
 
 int __init dm_stripe_init(void)

drivers/md/dm.c

@@ -1089,6 +1089,30 @@ static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
+static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	struct mapped_device *md = dax_get_private(dax_dev);
+	sector_t sector = pgoff * PAGE_SECTORS;
+	struct dm_target *ti;
+	long ret = 0;
+	int srcu_idx;
+
+	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
+
+	if (!ti)
+		goto out;
+	if (!ti->type->dax_copy_to_iter) {
+		ret = copy_to_iter(addr, bytes, i);
+		goto out;
+	}
+	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
+ out:
+	dm_put_live_table(md, srcu_idx);
+
+	return ret;
+}
+
 /*
  * A target may call dm_accept_partial_bio only from the map routine.  It is
  * allowed for all bio types except REQ_PREFLUSH and REQ_OP_ZONE_RESET.
@@ -3137,6 +3161,7 @@ static const struct block_device_operations dm_blk_dops = {
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
 	.copy_from_iter = dm_dax_copy_from_iter,
+	.copy_to_iter = dm_dax_copy_to_iter,
 };
 
 /*

drivers/nvdimm/bus.c

@@ -100,6 +100,9 @@ static int nvdimm_bus_probe(struct device *dev)
 	if (!try_module_get(provider))
 		return -ENXIO;
 
+	dev_dbg(&nvdimm_bus->dev, "START: %s.probe(%s)\n",
+			dev->driver->name, dev_name(dev));
+
 	nvdimm_bus_probe_start(nvdimm_bus);
 	rc = nd_drv->probe(dev);
 	if (rc == 0)
@@ -108,7 +111,7 @@ static int nvdimm_bus_probe(struct device *dev)
 		nd_region_disable(nvdimm_bus, dev);
 	nvdimm_bus_probe_end(nvdimm_bus);
 
-	dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name,
+	dev_dbg(&nvdimm_bus->dev, "END: %s.probe(%s) = %d\n", dev->driver->name,
 			dev_name(dev), rc);
 
 	if (rc != 0)
@@ -566,14 +569,18 @@ int nvdimm_revalidate_disk(struct gendisk *disk)
 {
 	struct device *dev = disk_to_dev(disk)->parent;
 	struct nd_region *nd_region = to_nd_region(dev->parent);
-	const char *pol = nd_region->ro ? "only" : "write";
+	int disk_ro = get_disk_ro(disk);
 
-	if (nd_region->ro == get_disk_ro(disk))
+	/*
+	 * Upgrade to read-only if the region is read-only preserve as
+	 * read-only if the disk is already read-only.
+	 */
+	if (disk_ro || nd_region->ro == disk_ro)
 		return 0;
 
-	dev_info(dev, "%s read-%s, marking %s read-%s\n",
-			dev_name(&nd_region->dev), pol, disk->disk_name, pol);
-	set_disk_ro(disk, nd_region->ro);
+	dev_info(dev, "%s read-only, marking %s read-only\n",
+			dev_name(&nd_region->dev), disk->disk_name);
+	set_disk_ro(disk, 1);
 
 	return 0;
 

drivers/nvdimm/e820.c

@@ -38,12 +38,27 @@ static int e820_range_to_nid(resource_size_t addr)
 }
 #endif
 
+static int e820_register_one(struct resource *res, void *data)
+{
+	struct nd_region_desc ndr_desc;
+	struct nvdimm_bus *nvdimm_bus = data;
+
+	memset(&ndr_desc, 0, sizeof(ndr_desc));
+	ndr_desc.res = res;
+	ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+	ndr_desc.numa_node = e820_range_to_nid(res->start);
+	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
+	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+		return -ENXIO;
+	return 0;
+}
+
 static int e820_pmem_probe(struct platform_device *pdev)
 {
 	static struct nvdimm_bus_descriptor nd_desc;
 	struct device *dev = &pdev->dev;
 	struct nvdimm_bus *nvdimm_bus;
-	struct resource *p;
+	int rc = -ENXIO;
 
 	nd_desc.attr_groups = e820_pmem_attribute_groups;
 	nd_desc.provider_name = "e820";
@@ -53,27 +68,15 @@ static int e820_pmem_probe(struct platform_device *pdev)
 		goto err;
 	platform_set_drvdata(pdev, nvdimm_bus);
 
-	for (p = iomem_resource.child; p ; p = p->sibling) {
-		struct nd_region_desc ndr_desc;
-
-		if (p->desc != IORES_DESC_PERSISTENT_MEMORY_LEGACY)
-			continue;
-
-		memset(&ndr_desc, 0, sizeof(ndr_desc));
-		ndr_desc.res = p;
-		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
-		ndr_desc.numa_node = e820_range_to_nid(p->start);
-		set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
-		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
-			goto err;
-	}
-
+	rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+			IORESOURCE_MEM, 0, -1, nvdimm_bus, e820_register_one);
+	if (rc)
+		goto err;
 	return 0;
-
- err:
+err:
 	nvdimm_bus_unregister(nvdimm_bus);
 	dev_err(dev, "failed to register legacy persistent memory ranges\n");
-	return -ENXIO;
+	return rc;
 }
 
 static struct platform_driver e820_pmem_driver = {

drivers/nvdimm/pfn_devs.c

@@ -561,8 +561,6 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	res->start += start_pad;
 	res->end -= end_trunc;
 
-	pgmap->type = MEMORY_DEVICE_HOST;
-
 	if (nd_pfn->mode == PFN_MODE_RAM) {
 		if (offset < SZ_8K)
 			return -EINVAL;

drivers/nvdimm/pmem.c

@@ -164,11 +164,6 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	return rc;
 }
 
-/* account for REQ_FLUSH rename, replace with REQ_PREFLUSH after v4.8-rc1 */
-#ifndef REQ_FLUSH
-#define REQ_FLUSH REQ_PREFLUSH
-#endif
-
 static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 {
 	blk_status_t rc = 0;
@@ -179,7 +174,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	struct pmem_device *pmem = q->queuedata;
 	struct nd_region *nd_region = to_region(pmem);
 
-	if (bio->bi_opf & REQ_FLUSH)
+	if (bio->bi_opf & REQ_PREFLUSH)
 		nvdimm_flush(nd_region);
 
 	do_acct = nd_iostat_start(bio, &start);
@@ -264,9 +259,16 @@ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
 	return copy_from_iter_flushcache(addr, bytes, i);
 }
 
+static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter_mcsafe(addr, bytes, i);
+}
+
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
 	.copy_from_iter = pmem_copy_from_iter,
+	.copy_to_iter = pmem_copy_to_iter,
 };
 
 static const struct attribute_group *pmem_attribute_groups[] = {
@@ -294,12 +296,33 @@ static void pmem_release_disk(void *__pmem)
 	put_disk(pmem->disk);
 }
 
+static void pmem_release_pgmap_ops(void *__pgmap)
+{
+	dev_pagemap_put_ops();
+}
+
+static void fsdax_pagefree(struct page *page, void *data)
+{
+	wake_up_var(&page->_refcount);
+}
+
+static int setup_pagemap_fsdax(struct device *dev, struct dev_pagemap *pgmap)
+{
+	dev_pagemap_get_ops();
+	if (devm_add_action_or_reset(dev, pmem_release_pgmap_ops, pgmap))
+		return -ENOMEM;
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+	pgmap->page_free = fsdax_pagefree;
+
+	return 0;
+}
+
 static int pmem_attach_disk(struct device *dev,
 		struct nd_namespace_common *ndns)
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	struct nd_region *nd_region = to_nd_region(dev->parent);
-	int nid = dev_to_node(dev), fua, wbc;
+	int nid = dev_to_node(dev), fua;
 	struct resource *res = &nsio->res;
 	struct resource bb_res;
 	struct nd_pfn *nd_pfn = NULL;
@@ -335,7 +358,6 @@ static int pmem_attach_disk(struct device *dev,
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 		fua = 0;
 	}
-	wbc = nvdimm_has_cache(nd_region);
 
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
 				dev_name(&ndns->dev))) {
@@ -353,6 +375,8 @@ static int pmem_attach_disk(struct device *dev,
 	pmem->pfn_flags = PFN_DEV;
 	pmem->pgmap.ref = &q->q_usage_counter;
 	if (is_nd_pfn(dev)) {
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pfn_sb = nd_pfn->pfn_sb;
 		pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -364,6 +388,8 @@ static int pmem_attach_disk(struct device *dev,
 	} else if (pmem_should_map_pages(dev)) {
 		memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
 		pmem->pgmap.altmap_valid = false;
+		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
+			return -ENOMEM;
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
@@ -382,7 +408,7 @@ static int pmem_attach_disk(struct device *dev,
 		return PTR_ERR(addr);
 	pmem->virt_addr = addr;
 
-	blk_queue_write_cache(q, wbc, fua);
+	blk_queue_write_cache(q, true, fua);
 	blk_queue_make_request(q, pmem_make_request);
 	blk_queue_physical_block_size(q, PAGE_SIZE);
 	blk_queue_logical_block_size(q, pmem_sector_size(ndns));
@@ -413,7 +439,7 @@ static int pmem_attach_disk(struct device *dev,
 		put_disk(disk);
 		return -ENOMEM;
 	}
-	dax_write_cache(dax_dev, wbc);
+	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
 
 	gendev = disk_to_dev(disk);

drivers/nvdimm/region_devs.c

@@ -1132,7 +1132,8 @@ EXPORT_SYMBOL_GPL(nvdimm_has_flush);
 
 int nvdimm_has_cache(struct nd_region *nd_region)
 {
-	return is_nd_pmem(&nd_region->dev);
+	return is_nd_pmem(&nd_region->dev) &&
+		!test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags);
 }
 EXPORT_SYMBOL_GPL(nvdimm_has_cache);
 

drivers/s390/block/dcssblk.c

@@ -51,9 +51,16 @@ static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev,
 	return copy_from_iter(addr, bytes, i);
 }
 
+static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return copy_to_iter(addr, bytes, i);
+}
+
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
 	.copy_from_iter = dcssblk_dax_copy_from_iter,
+	.copy_to_iter = dcssblk_dax_copy_to_iter,
 };
 
 struct dcssblk_dev_info {

fs/Kconfig

@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED)
 	select FS_IOMAP
 	select DAX
 	help

fs/dax.c

@@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
 	}
 }
 
+static struct page *dax_busy_page(void *entry)
+{
+	unsigned long pfn;
+
+	for_each_mapped_pfn(entry, pfn) {
+		struct page *page = pfn_to_page(pfn);
+
+		if (page_ref_count(page) > 1)
+			return page;
+	}
+	return NULL;
+}
+
 /*
  * Find radix tree entry at given index. If it points to an exceptional entry,
  * return it with the radix tree entry locked. If the radix tree doesn't
@@ -492,6 +505,90 @@ restart:
 	return entry;
 }
 
+/**
+ * dax_layout_busy_page - find first pinned page in @mapping
+ * @mapping: address space to scan for a page with ref count > 1
+ *
+ * DAX requires ZONE_DEVICE mapped pages. These pages are never
+ * 'onlined' to the page allocator so they are considered idle when
+ * page->count == 1. A filesystem uses this interface to determine if
+ * any page in the mapping is busy, i.e. for DMA, or other
+ * get_user_pages() usages.
+ *
+ * It is expected that the filesystem is holding locks to block the
+ * establishment of new mappings in this address_space. I.e. it expects
+ * to be able to run unmap_mapping_range() and subsequently not race
+ * mapping_mapped() becoming true.
+ */
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	pgoff_t	indices[PAGEVEC_SIZE];
+	struct page *page = NULL;
+	struct pagevec pvec;
+	pgoff_t	index, end;
+	unsigned i;
+
+	/*
+	 * In the 'limited' case get_user_pages() for dax is disabled.
+	 */
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+		return NULL;
+
+	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+		return NULL;
+
+	pagevec_init(&pvec);
+	index = 0;
+	end = -1;
+
+	/*
+	 * If we race get_user_pages_fast() here either we'll see the
+	 * elevated page count in the pagevec_lookup and wait, or
+	 * get_user_pages_fast() will see that the page it took a reference
+	 * against is no longer mapped in the page tables and bail to the
+	 * get_user_pages() slow path.  The slow path is protected by
+	 * pte_lock() and pmd_lock(). New references are not taken without
+	 * holding those locks, and unmap_mapping_range() will not zero the
+	 * pte or pmd without holding the respective lock, so we are
+	 * guaranteed to either see new references or prevent new
+	 * references from being established.
+	 */
+	unmap_mapping_range(mapping, 0, 0, 1);
+
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE),
+				indices)) {
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *pvec_ent = pvec.pages[i];
+			void *entry;
+
+			index = indices[i];
+			if (index >= end)
+				break;
+
+			if (!radix_tree_exceptional_entry(pvec_ent))
+				continue;
+
+			xa_lock_irq(&mapping->i_pages);
+			entry = get_unlocked_mapping_entry(mapping, index, NULL);
+			if (entry)
+				page = dax_busy_page(entry);
+			put_unlocked_mapping_entry(mapping, index, entry);
+			xa_unlock_irq(&mapping->i_pages);
+			if (page)
+				break;
+		}
+		pagevec_remove_exceptionals(&pvec);
+		pagevec_release(&pvec);
+		index++;
+
+		if (page)
+			break;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page);
+
 static int __dax_invalidate_mapping_entry(struct address_space *mapping,
 					  pgoff_t index, bool trunc)
 {
@@ -912,7 +1009,6 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	unsigned long vaddr = vmf->address;
 	vm_fault_t ret = VM_FAULT_NOPAGE;
 	struct page *zero_page;
-	void *entry2;
 	pfn_t pfn;
 
 	zero_page = ZERO_PAGE(0);
@@ -922,13 +1018,8 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
 	}
 
 	pfn = page_to_pfn_t(zero_page);
-	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
-			RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(entry2)) {
-		ret = VM_FAULT_SIGBUS;
-		goto out;
-	}
-
+	dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
+			false);
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 out:
 	trace_dax_load_hole(inode, vmf, ret);
@@ -991,6 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	struct iov_iter *iter = data;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
+	size_t xfer;
 	int id;
 
 	if (iov_iter_rw(iter) == READ) {
@@ -1054,18 +1146,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		 * vfs_write(), depending on which operation we are doing.
 		 */
 		if (iov_iter_rw(iter) == WRITE)
-			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
+			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
-			map_len = copy_to_iter(kaddr, map_len, iter);
-		if (map_len <= 0) {
-			ret = map_len ? map_len : -EFAULT;
-			break;
-		}
+			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
+					map_len, iter);
 
-		pos += map_len;
-		length -= map_len;
-		done += map_len;
+		pos += xfer;
+		length -= xfer;
+		done += xfer;
+
+		if (xfer == 0)
+			ret = -EFAULT;
+		if (xfer < map_len)
+			break;
 	}
 	dax_read_unlock(id);
 
@@ -1240,10 +1334,6 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						 0, write && !sync);
-		if (IS_ERR(entry)) {
-			error = PTR_ERR(entry);
-			goto error_finish_iomap;
-		}
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
@@ -1324,8 +1414,6 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
 	pfn = page_to_pfn_t(zero_page);
 	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
-	if (IS_ERR(ret))
-		goto fallback;
 
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
@@ -1447,8 +1535,6 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
 						RADIX_DAX_PMD, write && !sync);
-		if (IS_ERR(entry))
-			goto finish_iomap;
 
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,

fs/xfs/xfs_file.c

@@ -312,7 +312,7 @@ restart:
 	if (error <= 0)
 		return error;
 
-	error = xfs_break_layouts(inode, iolock);
+	error = xfs_break_layouts(inode, iolock, BREAK_WRITE);
 	if (error)
 		return error;
 
@@ -731,6 +731,69 @@ xfs_file_write_iter(
 	return xfs_file_buffered_aio_write(iocb, from);
 }
 
+static void
+xfs_wait_dax_page(
+	struct inode		*inode,
+	bool			*did_unlock)
+{
+	struct xfs_inode        *ip = XFS_I(inode);
+
+	*did_unlock = true;
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+	schedule();
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+}
+
+static int
+xfs_break_dax_layouts(
+	struct inode		*inode,
+	uint			iolock,
+	bool			*did_unlock)
+{
+	struct page		*page;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL));
+
+	page = dax_layout_busy_page(inode->i_mapping);
+	if (!page)
+		return 0;
+
+	return ___wait_var_event(&page->_refcount,
+			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
+			0, 0, xfs_wait_dax_page(inode, did_unlock));
+}
+
+int
+xfs_break_layouts(
+	struct inode		*inode,
+	uint			*iolock,
+	enum layout_break_reason reason)
+{
+	bool			retry;
+	int			error;
+
+	ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
+
+	do {
+		retry = false;
+		switch (reason) {
+		case BREAK_UNMAP:
+			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			if (error || retry)
+				break;
+			/* fall through */
+		case BREAK_WRITE:
+			error = xfs_break_leased_layouts(inode, iolock, &retry);
+			break;
+		default:
+			WARN_ON_ONCE(1);
+			error = -EINVAL;
+		}
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 #define	XFS_FALLOC_FL_SUPPORTED						\
 		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
 		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
@@ -747,7 +810,7 @@ xfs_file_fallocate(
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	enum xfs_prealloc_flags	flags = 0;
-	uint			iolock = XFS_IOLOCK_EXCL;
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	loff_t			new_size = 0;
 	bool			do_file_insert = false;
 
@@ -757,13 +820,10 @@ xfs_file_fallocate(
 		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
 	if (error)
 		goto out_unlock;
 
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	iolock |= XFS_MMAPLOCK_EXCL;
-
 	if (mode & FALLOC_FL_PUNCH_HOLE) {
 		error = xfs_free_file_space(ip, offset, len);
 		if (error)

fs/xfs/xfs_inode.h

@@ -378,6 +378,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip)
 #define XFS_ILOCK_DEP(flags)	(((flags) & XFS_ILOCK_DEP_MASK) \
 					>> XFS_ILOCK_SHIFT)
 
+/*
+ * Layouts are broken in the BREAK_WRITE case to ensure that
+ * layout-holders do not collide with local writes. Additionally,
+ * layouts are broken in the BREAK_UNMAP case to make sure the
+ * layout-holder has a consistent view of the file's extent map. While
+ * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
+ * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
+ * go idle.
+ */
+enum layout_break_reason {
+        BREAK_WRITE,
+        BREAK_UNMAP,
+};
+
 /*
  * For multiple groups support: if S_ISGID bit is set in the parent
  * directory, group of new file is set to that of the parent, and
@@ -453,6 +467,8 @@ enum xfs_prealloc_flags {
 
 int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 				  enum xfs_prealloc_flags flags);
+int	xfs_break_layouts(struct inode *inode, uint *iolock,
+		enum layout_break_reason reason);
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);

fs/xfs/xfs_ioctl.c

@@ -39,7 +39,6 @@
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
 #include "xfs_trans.h"
-#include "xfs_pnfs.h"
 #include "xfs_acl.h"
 #include "xfs_btree.h"
 #include <linux/fsmap.h>
@@ -614,7 +613,7 @@ xfs_ioc_space(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct iattr		iattr;
 	enum xfs_prealloc_flags	flags = 0;
-	uint			iolock = XFS_IOLOCK_EXCL;
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	int			error;
 
 	/*
@@ -644,13 +643,10 @@ xfs_ioc_space(
 		return error;
 
 	xfs_ilock(ip, iolock);
-	error = xfs_break_layouts(inode, &iolock);
+	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
 	if (error)
 		goto out_unlock;
 
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	iolock |= XFS_MMAPLOCK_EXCL;
-
 	switch (bf->l_whence) {
 	case 0: /*SEEK_SET*/
 		break;

fs/xfs/xfs_iops.c

@@ -37,7 +37,6 @@
 #include "xfs_da_btree.h"
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
-#include "xfs_pnfs.h"
 #include "xfs_iomap.h"
 
 #include <linux/capability.h>
@@ -1030,14 +1029,19 @@ xfs_vn_setattr(
 	int			error;
 
 	if (iattr->ia_valid & ATTR_SIZE) {
-		struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-		uint			iolock = XFS_IOLOCK_EXCL;
+		struct inode		*inode = d_inode(dentry);
+		struct xfs_inode	*ip = XFS_I(inode);
+		uint			iolock;
 
-		error = xfs_break_layouts(d_inode(dentry), &iolock);
-		if (error)
+		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
+		iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+
+		error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
+		if (error) {
+			xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 			return error;
+		}
 
-		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 		error = xfs_vn_setattr_size(dentry, iattr);
 		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	} else {

fs/xfs/xfs_pnfs.c

@@ -31,19 +31,20 @@
  * rules in the page fault path we don't bother.
  */
 int
-xfs_break_layouts(
+xfs_break_leased_layouts(
 	struct inode		*inode,
-	uint			*iolock)
+	uint			*iolock,
+	bool			*did_unlock)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
-
 	while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
 		xfs_iunlock(ip, *iolock);
+		*did_unlock = true;
 		error = break_layout(inode, true);
-		*iolock = XFS_IOLOCK_EXCL;
+		*iolock &= ~XFS_IOLOCK_SHARED;
+		*iolock |= XFS_IOLOCK_EXCL;
 		xfs_ilock(ip, *iolock);
 	}
 
@@ -120,8 +121,8 @@ xfs_fs_map_blocks(
 	 * Lock out any other I/O before we flush and invalidate the pagecache,
 	 * and then hand out a layout to the remote system.  This is very
 	 * similar to direct I/O, except that the synchronization is much more
-	 * complicated.  See the comment near xfs_break_layouts for a detailed
-	 * explanation.
+	 * complicated.  See the comment near xfs_break_leased_layouts
+	 * for a detailed explanation.
 	 */
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 

fs/xfs/xfs_pnfs.h

@@ -9,10 +9,11 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length,
 int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps,
 		struct iattr *iattr);
 
-int xfs_break_layouts(struct inode *inode, uint *iolock);
+int xfs_break_leased_layouts(struct inode *inode, uint *iolock,
+		bool *did_unlock);
 #else
 static inline int
-xfs_break_layouts(struct inode *inode, uint *iolock)
+xfs_break_leased_layouts(struct inode *inode, uint *iolock, bool *did_unlock)
 {
 	return 0;
 }

include/linux/dax.h

@@ -20,6 +20,9 @@ struct dax_operations {
 	/* copy_from_iter: required operation for fs-dax direct-i/o */
 	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
 			struct iov_iter *);
+	/* copy_to_iter: required operation for fs-dax direct-i/o */
+	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
+			struct iov_iter *);
 };
 
 extern struct attribute_group dax_attribute_group;
@@ -83,6 +86,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev)
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc);
+
+struct page *dax_layout_busy_page(struct address_space *mapping);
 #else
 static inline bool bdev_dax_supported(struct block_device *bdev,
 		int blocksize)
@@ -104,6 +109,11 @@ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
 	return NULL;
 }
 
+static inline struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+	return NULL;
+}
+
 static inline int dax_writeback_mapping_range(struct address_space *mapping,
 		struct block_device *bdev, struct writeback_control *wbc)
 {
@@ -119,6 +129,8 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
+size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,

include/linux/device-mapper.h

@@ -133,7 +133,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
-typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
+typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
 #define PAGE_SECTORS (PAGE_SIZE / 512)
 
@@ -184,7 +184,8 @@ struct target_type {
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
-	dm_dax_copy_from_iter_fn dax_copy_from_iter;
+	dm_dax_copy_iter_fn dax_copy_from_iter;
+	dm_dax_copy_iter_fn dax_copy_to_iter;
 
 	/* For internal device-mapper use. */
 	struct list_head list;

include/linux/memremap.h

@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_MEMREMAP_H_
 #define _LINUX_MEMREMAP_H_
-#include <linux/mm.h>
 #include <linux/ioport.h>
 #include <linux/percpu-refcount.h>
 
@@ -30,13 +29,6 @@ struct vmem_altmap {
  * Specialize ZONE_DEVICE memory into multiple types each having differents
  * usage.
  *
- * MEMORY_DEVICE_HOST:
- * Persistent device memory (pmem): struct page might be allocated in different
- * memory and architecture might want to perform special actions. It is similar
- * to regular memory, in that the CPU can access it transparently. However,
- * it is likely to have different bandwidth and latency than regular memory.
- * See Documentation/nvdimm/nvdimm.txt for more information.
- *
  * MEMORY_DEVICE_PRIVATE:
  * Device memory that is not directly addressable by the CPU: CPU can neither
  * read nor write private memory. In this case, we do still have struct pages
@@ -53,11 +45,19 @@ struct vmem_altmap {
  * driver can hotplug the device memory using ZONE_DEVICE and with that memory
  * type. Any page of a process can be migrated to such memory. However no one
  * should be allow to pin such memory so that it can always be evicted.
+ *
+ * MEMORY_DEVICE_FS_DAX:
+ * Host memory that has similar access semantics as System RAM i.e. DMA
+ * coherent and supports page pinning. In support of coordinating page
+ * pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
+ * wakeup event whenever a page is unpinned and becomes idle. This
+ * wakeup is used to coordinate physical address space management (ex:
+ * fs truncate/hole punch) vs pinned pages (ex: device dma).
  */
 enum memory_type {
-	MEMORY_DEVICE_HOST = 0,
-	MEMORY_DEVICE_PRIVATE,
+	MEMORY_DEVICE_PRIVATE = 1,
 	MEMORY_DEVICE_PUBLIC,
+	MEMORY_DEVICE_FS_DAX,
 };
 
 /*
@@ -129,8 +129,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
-
-static inline bool is_zone_device_page(const struct page *page);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
@@ -161,20 +159,6 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 }
 #endif /* CONFIG_ZONE_DEVICE */
 
-#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
-static inline bool is_device_private_page(const struct page *page)
-{
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
-}
-
-static inline bool is_device_public_page(const struct page *page)
-{
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
-}
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)

include/linux/mm.h

@@ -830,27 +830,65 @@ static inline bool is_zone_device_page(const struct page *page)
 }
 #endif
 
-#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
-void put_zone_device_private_or_public_page(struct page *page);
-DECLARE_STATIC_KEY_FALSE(device_private_key);
-#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key)
-static inline bool is_device_private_page(const struct page *page);
-static inline bool is_device_public_page(const struct page *page);
-#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-static inline void put_zone_device_private_or_public_page(struct page *page)
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void dev_pagemap_get_ops(void);
+void dev_pagemap_put_ops(void);
+void __put_devmap_managed_page(struct page *page);
+DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
+static inline bool put_devmap_managed_page(struct page *page)
+{
+	if (!static_branch_unlikely(&devmap_managed_key))
+		return false;
+	if (!is_zone_device_page(page))
+		return false;
+	switch (page->pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+	case MEMORY_DEVICE_PUBLIC:
+	case MEMORY_DEVICE_FS_DAX:
+		__put_devmap_managed_page(page);
+		return true;
+	default:
+		break;
+	}
+	return false;
+}
+
+static inline bool is_device_private_page(const struct page *page)
 {
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
 }
-#define IS_HMM_ENABLED 0
+
+static inline bool is_device_public_page(const struct page *page)
+{
+	return is_zone_device_page(page) &&
+		page->pgmap->type == MEMORY_DEVICE_PUBLIC;
+}
+
+#else /* CONFIG_DEV_PAGEMAP_OPS */
+static inline void dev_pagemap_get_ops(void)
+{
+}
+
+static inline void dev_pagemap_put_ops(void)
+{
+}
+
+static inline bool put_devmap_managed_page(struct page *page)
+{
+	return false;
+}
+
 static inline bool is_device_private_page(const struct page *page)
 {
 	return false;
 }
+
 static inline bool is_device_public_page(const struct page *page)
 {
 	return false;
 }
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static inline void get_page(struct page *page)
 {
@@ -868,16 +906,13 @@ static inline void put_page(struct page *page)
 	page = compound_head(page);
 
 	/*
-	 * For private device pages we need to catch refcount transition from
-	 * 2 to 1, when refcount reach one it means the private device page is
-	 * free and we need to inform the device driver through callback. See
+	 * For devmap managed pages we need to catch refcount transition from
+	 * 2 to 1, when refcount reach one it means the page is free and we
+	 * need to inform the device driver through callback. See
 	 * include/linux/memremap.h and HMM for details.
 	 */
-	if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) ||
-	    unlikely(is_device_public_page(page)))) {
-		put_zone_device_private_or_public_page(page);
+	if (put_devmap_managed_page(page))
 		return;
-	}
 
 	if (put_page_testzero(page))
 		__put_page(page);

include/linux/uio.h

@@ -155,7 +155,7 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
 #endif
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_MCSAFE
-size_t _copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i);
+size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
 #else
 #define _copy_to_iter_mcsafe _copy_to_iter
 #endif

kernel/Makefile

@@ -112,7 +112,8 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o
 obj-$(CONFIG_TORTURE_TEST) += torture.o
 
-obj-$(CONFIG_HAS_IOMEM) += memremap.o
+obj-$(CONFIG_HAS_IOMEM) += iomem.o
+obj-$(CONFIG_ZONE_DEVICE) += memremap.o
 
 $(obj)/configs.o: $(obj)/config_data.h
 

kernel/iomem.c

@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#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
+
+#ifndef arch_memremap_wb
+static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
+{
+	return (__force void *)ioremap_cache(offset, size);
+}
+#endif
+
+#ifndef arch_memremap_can_ram_remap
+static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
+					unsigned long flags)
+{
+	return true;
+}
+#endif
+
+static void *try_ram_remap(resource_size_t offset, size_t size,
+			   unsigned long flags)
+{
+	unsigned long pfn = PHYS_PFN(offset);
+
+	/* In the simple case just return the existing linear address */
+	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) &&
+	    arch_memremap_can_ram_remap(offset, size, flags))
+		return __va(offset);
+
+	return NULL; /* fallback to arch_memremap_wb */
+}
+
+/**
+ * memremap() - remap an iomem_resource as cacheable memory
+ * @offset: iomem resource start address
+ * @size: size of remap
+ * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC,
+ *		  MEMREMAP_ENC, MEMREMAP_DEC
+ *
+ * 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. In the case of multiple flags, the different
+ * mapping types will be attempted in the order listed below until one of
+ * them succeeds.
+ *
+ * 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.
+ *
+ * MEMREMAP_WC - establish a writecombine mapping, whereby writes may
+ * be coalesced together (e.g. in the CPU's write buffers), but is otherwise
+ * uncached. 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,
+				       IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
+	void *addr = NULL;
+
+	if (!flags)
+		return 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) {
+		/*
+		 * 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 = try_ram_remap(offset, size, flags);
+		if (!addr)
+			addr = arch_memremap_wb(offset, size);
+	}
+
+	/*
+	 * If we don't have a mapping yet and other request flags are
+	 * present 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 != MEMREMAP_WB) {
+		WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
+				&offset, (unsigned long) size);
+		return NULL;
+	}
+
+	if (!addr && (flags & MEMREMAP_WT))
+		addr = ioremap_wt(offset, size);
+
+	if (!addr && (flags & MEMREMAP_WC))
+		addr = ioremap_wc(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(*(void **)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_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL,
+			dev_to_node(dev));
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	addr = memremap(offset, size, flags);
+	if (addr) {
+		*ptr = addr;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+		return ERR_PTR(-ENXIO);
+	}
+
+	return addr;
+}
+EXPORT_SYMBOL(devm_memremap);
+
+void devm_memunmap(struct device *dev, void *addr)
+{
+	WARN_ON(devres_release(dev, devm_memremap_release,
+				devm_memremap_match, addr));
+}
+EXPORT_SYMBOL(devm_memunmap);

kernel/memremap.c

@@ -1,15 +1,5 @@
-/*
- * 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.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
 #include <linux/radix-tree.h>
 #include <linux/device.h>
 #include <linux/types.h>
@@ -19,170 +9,8 @@
 #include <linux/memory_hotplug.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/wait_bit.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
-
-#ifndef arch_memremap_wb
-static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
-{
-	return (__force void *)ioremap_cache(offset, size);
-}
-#endif
-
-#ifndef arch_memremap_can_ram_remap
-static bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
-					unsigned long flags)
-{
-	return true;
-}
-#endif
-
-static void *try_ram_remap(resource_size_t offset, size_t size,
-			   unsigned long flags)
-{
-	unsigned long pfn = PHYS_PFN(offset);
-
-	/* In the simple case just return the existing linear address */
-	if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn)) &&
-	    arch_memremap_can_ram_remap(offset, size, flags))
-		return __va(offset);
-
-	return NULL; /* fallback to arch_memremap_wb */
-}
-
-/**
- * memremap() - remap an iomem_resource as cacheable memory
- * @offset: iomem resource start address
- * @size: size of remap
- * @flags: any of MEMREMAP_WB, MEMREMAP_WT, MEMREMAP_WC,
- *		  MEMREMAP_ENC, MEMREMAP_DEC
- *
- * 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. In the case of multiple flags, the different
- * mapping types will be attempted in the order listed below until one of
- * them succeeds.
- *
- * 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.
- *
- * MEMREMAP_WC - establish a writecombine mapping, whereby writes may
- * be coalesced together (e.g. in the CPU's write buffers), but is otherwise
- * uncached. 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,
-				       IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
-	void *addr = NULL;
-
-	if (!flags)
-		return 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) {
-		/*
-		 * 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 = try_ram_remap(offset, size, flags);
-		if (!addr)
-			addr = arch_memremap_wb(offset, size);
-	}
-
-	/*
-	 * If we don't have a mapping yet and other request flags are
-	 * present 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 != MEMREMAP_WB) {
-		WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n",
-				&offset, (unsigned long) size);
-		return NULL;
-	}
-
-	if (!addr && (flags & MEMREMAP_WT))
-		addr = ioremap_wt(offset, size);
-
-	if (!addr && (flags & MEMREMAP_WC))
-		addr = ioremap_wc(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(*(void **)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_node(devm_memremap_release, sizeof(*ptr), GFP_KERNEL,
-			dev_to_node(dev));
-	if (!ptr)
-		return ERR_PTR(-ENOMEM);
-
-	addr = memremap(offset, size, flags);
-	if (addr) {
-		*ptr = addr;
-		devres_add(dev, ptr);
-	} else {
-		devres_free(ptr);
-		return ERR_PTR(-ENXIO);
-	}
-
-	return addr;
-}
-EXPORT_SYMBOL(devm_memremap);
-
-void devm_memunmap(struct device *dev, void *addr)
-{
-	WARN_ON(devres_release(dev, devm_memremap_release,
-				devm_memremap_match, addr));
-}
-EXPORT_SYMBOL(devm_memunmap);
-
-#ifdef CONFIG_ZONE_DEVICE
 static DEFINE_MUTEX(pgmap_lock);
 static RADIX_TREE(pgmap_radix, GFP_KERNEL);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
@@ -473,10 +301,32 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 	return pgmap;
 }
-#endif /* CONFIG_ZONE_DEVICE */
+EXPORT_SYMBOL_GPL(get_dev_pagemap);
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
+EXPORT_SYMBOL_GPL(devmap_managed_key);
+static atomic_t devmap_enable;
+
+/*
+ * Toggle the static key for ->page_free() callbacks when dev_pagemap
+ * pages go idle.
+ */
+void dev_pagemap_get_ops(void)
+{
+	if (atomic_inc_return(&devmap_enable) == 1)
+		static_branch_enable(&devmap_managed_key);
+}
+EXPORT_SYMBOL_GPL(dev_pagemap_get_ops);
+
+void dev_pagemap_put_ops(void)
+{
+	if (atomic_dec_and_test(&devmap_enable))
+		static_branch_disable(&devmap_managed_key);
+}
+EXPORT_SYMBOL_GPL(dev_pagemap_put_ops);
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) ||  IS_ENABLED(CONFIG_DEVICE_PUBLIC)
-void put_zone_device_private_or_public_page(struct page *page)
+void __put_devmap_managed_page(struct page *page)
 {
 	int count = page_ref_dec_return(page);
 
@@ -496,5 +346,5 @@ void put_zone_device_private_or_public_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL(put_zone_device_private_or_public_page);
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
+EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+#endif /* CONFIG_DEV_PAGEMAP_OPS */

kernel/resource.c

@@ -415,6 +415,7 @@ int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
 
 	return __walk_iomem_res_desc(&res, desc, false, arg, func);
 }
+EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
 
 /*
  * This function calls the @func callback against all memory ranges of type

lib/Kconfig

@@ -621,6 +621,9 @@ config ARCH_HAS_PMEM_API
 config ARCH_HAS_UACCESS_FLUSHCACHE
 	bool
 
+config ARCH_HAS_UACCESS_MCSAFE
+	bool
+
 config STACKDEPOT
 	bool
 	select STACKTRACE

mm/Kconfig

@@ -694,6 +694,9 @@ config ARCH_HAS_HMM
 config MIGRATE_VMA_HELPER
 	bool
 
+config DEV_PAGEMAP_OPS
+	bool
+
 config HMM
 	bool
 	select MIGRATE_VMA_HELPER
@@ -714,6 +717,7 @@ config DEVICE_PRIVATE
 	bool "Unaddressable device memory (GPU memory, ...)"
 	depends on ARCH_HAS_HMM
 	select HMM
+	select DEV_PAGEMAP_OPS
 
 	help
 	  Allows creation of struct pages to represent unaddressable device
@@ -724,6 +728,7 @@ config DEVICE_PUBLIC
 	bool "Addressable device memory (like GPU memory)"
 	depends on ARCH_HAS_HMM
 	select HMM
+	select DEV_PAGEMAP_OPS
 
 	help
 	  Allows creation of struct pages to represent addressable device

mm/gup.c

@@ -1475,32 +1475,48 @@ static int __gup_device_huge(unsigned long pfn, unsigned long addr,
 	return 1;
 }
 
-static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
 	unsigned long fault_pfn;
+	int nr_start = *nr;
+
+	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+		return 0;
 
-	fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
+		undo_dev_pagemap(nr, nr_start, pages);
+		return 0;
+	}
+	return 1;
 }
 
-static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+static int __gup_device_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
 	unsigned long fault_pfn;
+	int nr_start = *nr;
+
+	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	if (!__gup_device_huge(fault_pfn, addr, end, pages, nr))
+		return 0;
 
-	fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	return __gup_device_huge(fault_pfn, addr, end, pages, nr);
+	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
+		undo_dev_pagemap(nr, nr_start, pages);
+		return 0;
+	}
+	return 1;
 }
 #else
-static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr,
+static int __gup_device_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
 	BUILD_BUG();
 	return 0;
 }
 
-static int __gup_device_huge_pud(pud_t pud, unsigned long addr,
+static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 		unsigned long end, struct page **pages, int *nr)
 {
 	BUILD_BUG();
@@ -1518,7 +1534,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return 0;
 
 	if (pmd_devmap(orig))
-		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
+		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 
 	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
@@ -1556,7 +1572,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return 0;
 
 	if (pud_devmap(orig))
-		return __gup_device_huge_pud(orig, addr, end, pages, nr);
+		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 
 	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);

mm/hmm.c

@@ -35,15 +35,6 @@
 
 #define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
-#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC)
-/*
- * Device private memory see HMM (Documentation/vm/hmm.rst) or hmm.h
- */
-DEFINE_STATIC_KEY_FALSE(device_private_key);
-EXPORT_SYMBOL(device_private_key);
-#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-
-
 #if IS_ENABLED(CONFIG_HMM_MIRROR)
 static const struct mmu_notifier_ops hmm_mmu_notifier_ops;
 
@@ -1167,7 +1158,7 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
 	resource_size_t addr;
 	int ret;
 
-	static_branch_enable(&device_private_key);
+	dev_pagemap_get_ops();
 
 	devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
 				   GFP_KERNEL, dev_to_node(device));
@@ -1261,7 +1252,7 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops,
 	if (res->desc != IORES_DESC_DEVICE_PUBLIC_MEMORY)
 		return ERR_PTR(-EINVAL);
 
-	static_branch_enable(&device_private_key);
+	dev_pagemap_get_ops();
 
 	devmem = devres_alloc_node(&hmm_devmem_release, sizeof(*devmem),
 				   GFP_KERNEL, dev_to_node(device));

mm/swap.c

@@ -29,6 +29,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/backing-dev.h>
+#include <linux/memremap.h>
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
 #include <linux/uio.h>
@@ -743,7 +744,7 @@ void release_pages(struct page **pages, int nr)
 						       flags);
 				locked_pgdat = NULL;
 			}
-			put_zone_device_private_or_public_page(page);
+			put_devmap_managed_page(page);
 			continue;
 		}
 

tools/testing/nvdimm/test/nfit.c

@@ -29,6 +29,8 @@
 #include "nfit_test.h"
 #include "../watermark.h"
 
+#include <asm/mcsafe_test.h>
+
 /*
  * Generate an NFIT table to describe the following topology:
  *
@@ -2681,6 +2683,107 @@ static struct platform_driver nfit_test_driver = {
 	.id_table = nfit_test_id,
 };
 
+static char mcsafe_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+
+enum INJECT {
+	INJECT_NONE,
+	INJECT_SRC,
+	INJECT_DST,
+};
+
+static void mcsafe_test_init(char *dst, char *src, size_t size)
+{
+	size_t i;
+
+	memset(dst, 0xff, size);
+	for (i = 0; i < size; i++)
+		src[i] = (char) i;
+}
+
+static bool mcsafe_test_validate(unsigned char *dst, unsigned char *src,
+		size_t size, unsigned long rem)
+{
+	size_t i;
+
+	for (i = 0; i < size - rem; i++)
+		if (dst[i] != (unsigned char) i) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n",
+					__func__, __LINE__, i, dst[i],
+					(unsigned char) i);
+			return false;
+		}
+	for (i = size - rem; i < size; i++)
+		if (dst[i] != 0xffU) {
+			pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n",
+					__func__, __LINE__, i, dst[i]);
+			return false;
+		}
+	return true;
+}
+
+void mcsafe_test(void)
+{
+	char *inject_desc[] = { "none", "source", "destination" };
+	enum INJECT inj;
+
+	if (IS_ENABLED(CONFIG_MCSAFE_TEST)) {
+		pr_info("%s: run...\n", __func__);
+	} else {
+		pr_info("%s: disabled, skip.\n", __func__);
+		return;
+	}
+
+	for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) {
+		int i;
+
+		pr_info("%s: inject: %s\n", __func__, inject_desc[inj]);
+		for (i = 0; i < 512; i++) {
+			unsigned long expect, rem;
+			void *src, *dst;
+			bool valid;
+
+			switch (inj) {
+			case INJECT_NONE:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 0;
+				break;
+			case INJECT_SRC:
+				mcsafe_inject_src(&mcsafe_buf[1024]);
+				mcsafe_inject_dst(NULL);
+				dst = &mcsafe_buf[2048];
+				src = &mcsafe_buf[1024 - i];
+				expect = 512 - i;
+				break;
+			case INJECT_DST:
+				mcsafe_inject_src(NULL);
+				mcsafe_inject_dst(&mcsafe_buf[2048]);
+				dst = &mcsafe_buf[2048 - i];
+				src = &mcsafe_buf[1024];
+				expect = 512 - i;
+				break;
+			}
+
+			mcsafe_test_init(dst, src, 512);
+			rem = __memcpy_mcsafe(dst, src, 512);
+			valid = mcsafe_test_validate(dst, src, 512, expect);
+			if (rem == expect && valid)
+				continue;
+			pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
+					__func__,
+					((unsigned long) dst) & ~PAGE_MASK,
+					((unsigned long ) src) & ~PAGE_MASK,
+					512, i, rem, valid ? "valid" : "bad",
+					expect);
+		}
+	}
+
+	mcsafe_inject_src(NULL);
+	mcsafe_inject_dst(NULL);
+}
+
 static __init int nfit_test_init(void)
 {
 	int rc, i;
@@ -2689,6 +2792,7 @@ static __init int nfit_test_init(void)
 	libnvdimm_test();
 	acpi_nfit_test();
 	device_dax_test();
+	mcsafe_test();
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);