device-dax: add dis-contiguous resource support

Break the requirement that device-dax instances are physically contiguous.
With this constraint removed it allows fragmented available capacity to
be fully allocated.

This capability is useful to mitigate the "noisy neighbor" problem with
memory-side-cache management for virtual machines, or any other scenario
where a platform address boundary also designates a performance boundary.
For example a direct mapped memory side cache might rotate cache colors at
1GB boundaries.  With dis-contiguous allocations a device-dax instance
could be configured to contain only 1 cache color.

It also satisfies Joao's use case (see link) for partitioning memory for
exclusive guest access.  It allows for a future potential mode where the
host kernel need not allocate 'struct page' capacity up-front.
Reported-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/lkml/20200110190313.17144-1-joao.m.martins@oracle.com/
Link: https://lkml.kernel.org/r/159643104304.4062302.16561669534797528660.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106116875.30709.11456649969327399771.stgit@dwillia2-desk3.amr.corp.intel.comSigned-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/dax/dax-private.h

@@ -49,7 +49,8 @@ struct dax_region {
  * @id: ida allocated id
  * @dev - device core
  * @pgmap - pgmap for memmap setup / lifetime (driver owned)
- * @range: resource range for the instance
+ * @nr_range: size of @ranges
+ * @ranges: resource-span + pgoff tuples for the instance
  */
 struct dev_dax {
 	struct dax_region *region;
@@ -58,7 +59,11 @@ struct dev_dax {
 	int id;
 	struct device dev;
 	struct dev_pagemap *pgmap;
-	struct range range;
+	int nr_range;
+	struct dev_dax_range {
+		unsigned long pgoff;
+		struct range range;
+	} *ranges;
 };
 
 static inline struct dev_dax *to_dev_dax(struct device *dev)

drivers/dax/device.c

@@ -55,15 +55,22 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
-	struct range *range = &dev_dax->range;
-	phys_addr_t phys;
-
-	phys = pgoff * PAGE_SIZE + range->start;
-	if (phys >= range->start && phys <= range->end) {
+	int i;
+
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+		struct range *range = &dax_range->range;
+		unsigned long long pgoff_end;
+		phys_addr_t phys;
+
+		pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
+		if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
+			continue;
+		phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
 		if (phys + size - 1 <= range->end)
 			return phys;
+		break;
 	}
-
 	return -1;
 }
 
@@ -395,30 +402,40 @@ static void dev_dax_kill(void *dev_dax)
 int dev_dax_probe(struct dev_dax *dev_dax)
 {
 	struct dax_device *dax_dev = dev_dax->dax_dev;
-	struct range *range = &dev_dax->range;
 	struct device *dev = &dev_dax->dev;
 	struct dev_pagemap *pgmap;
 	struct inode *inode;
 	struct cdev *cdev;
 	void *addr;
-	int rc;
-
-	/* 1:1 map region resource range to device-dax instance range */
-	if (!devm_request_mem_region(dev, range->start, range_len(range),
-				dev_name(dev))) {
-		dev_warn(dev, "could not reserve range: %#llx - %#llx\n",
-				range->start, range->end);
-		return -EBUSY;
-	}
+	int rc, i;
 
 	pgmap = dev_dax->pgmap;
+	if (dev_WARN_ONCE(dev, pgmap && dev_dax->nr_range > 1,
+			"static pgmap / multi-range device conflict\n"))
+		return -EINVAL;
+
 	if (!pgmap) {
-		pgmap = devm_kzalloc(dev, sizeof(*pgmap), GFP_KERNEL);
+		pgmap = devm_kzalloc(dev, sizeof(*pgmap) + sizeof(struct range)
+				* (dev_dax->nr_range - 1), GFP_KERNEL);
 		if (!pgmap)
 			return -ENOMEM;
-		pgmap->range = *range;
-		pgmap->nr_range = 1;
+		pgmap->nr_range = dev_dax->nr_range;
+	}
+
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct range *range = &dev_dax->ranges[i].range;
+
+		if (!devm_request_mem_region(dev, range->start,
+					range_len(range), dev_name(dev))) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve range\n",
+					i, range->start, range->end);
+			return -EBUSY;
+		}
+		/* don't update the range for static pgmap */
+		if (!dev_dax->pgmap)
+			pgmap->ranges[i] = *range;
 	}
+
 	pgmap->type = MEMORY_DEVICE_GENERIC;
 	addr = devm_memremap_pages(dev, pgmap);
 	if (IS_ERR(addr))

drivers/dax/kmem.c

@@ -19,24 +19,28 @@ static const char *kmem_name;
 /* Set if any memory will remain added when the driver will be unloaded. */
 static bool any_hotremove_failed;
 
-static struct range dax_kmem_range(struct dev_dax *dev_dax)
+static int dax_kmem_range(struct dev_dax *dev_dax, int i, struct range *r)
 {
-	struct range range;
+	struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+	struct range *range = &dax_range->range;
 
 	/* memory-block align the hotplug range */
-	range.start = ALIGN(dev_dax->range.start, memory_block_size_bytes());
-	range.end = ALIGN_DOWN(dev_dax->range.end + 1, memory_block_size_bytes()) - 1;
-	return range;
+	r->start = ALIGN(range->start, memory_block_size_bytes());
+	r->end = ALIGN_DOWN(range->end + 1, memory_block_size_bytes()) - 1;
+	if (r->start >= r->end) {
+		r->start = range->start;
+		r->end = range->end;
+		return -ENOSPC;
+	}
+	return 0;
 }
 
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
-	struct range range = dax_kmem_range(dev_dax);
 	struct device *dev = &dev_dax->dev;
-	struct resource *res;
+	int i, mapped = 0;
 	char *res_name;
 	int numa_node;
-	int rc;
 
 	/*
 	 * Ensure good NUMA information for the persistent memory.
@@ -55,31 +59,58 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 	if (!res_name)
 		return -ENOMEM;
 
-	/* Region is permanently reserved if hotremove fails. */
-	res = request_mem_region(range.start, range_len(&range), res_name);
-	if (!res) {
-		dev_warn(dev, "could not reserve region [%#llx-%#llx]\n", range.start, range.end);
-		kfree(res_name);
-		return -EBUSY;
-	}
-
-	/*
-	 * Set flags appropriate for System RAM.  Leave ..._BUSY clear
-	 * so that add_memory() can add a child resource.  Do not
-	 * inherit flags from the parent since it may set new flags
-	 * unknown to us that will break add_memory() below.
-	 */
-	res->flags = IORESOURCE_SYSTEM_RAM;
-
-	/*
-	 * Ensure that future kexec'd kernels will not treat this as RAM
-	 * automatically.
-	 */
-	rc = add_memory_driver_managed(numa_node, range.start, range_len(&range), kmem_name);
-	if (rc) {
-		release_mem_region(range.start, range_len(&range));
-		kfree(res_name);
-		return rc;
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct resource *res;
+		struct range range;
+		int rc;
+
+		rc = dax_kmem_range(dev_dax, i, &range);
+		if (rc) {
+			dev_info(dev, "mapping%d: %#llx-%#llx too small after alignment\n",
+					i, range.start, range.end);
+			continue;
+		}
+
+		/* Region is permanently reserved if hotremove fails. */
+		res = request_mem_region(range.start, range_len(&range), res_name);
+		if (!res) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve region\n",
+					i, range.start, range.end);
+			/*
+			 * Once some memory has been onlined we can't
+			 * assume that it can be un-onlined safely.
+			 */
+			if (mapped)
+				continue;
+			kfree(res_name);
+			return -EBUSY;
+		}
+
+		/*
+		 * Set flags appropriate for System RAM.  Leave ..._BUSY clear
+		 * so that add_memory() can add a child resource.  Do not
+		 * inherit flags from the parent since it may set new flags
+		 * unknown to us that will break add_memory() below.
+		 */
+		res->flags = IORESOURCE_SYSTEM_RAM;
+
+		/*
+		 * Ensure that future kexec'd kernels will not treat
+		 * this as RAM automatically.
+		 */
+		rc = add_memory_driver_managed(numa_node, range.start,
+				range_len(&range), kmem_name);
+
+		if (rc) {
+			dev_warn(dev, "mapping%d: %#llx-%#llx memory add failed\n",
+					i, range.start, range.end);
+			release_mem_region(range.start, range_len(&range));
+			if (mapped)
+				continue;
+			kfree(res_name);
+			return rc;
+		}
+		mapped++;
 	}
 
 	dev_set_drvdata(dev, res_name);
@@ -90,9 +121,8 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static int dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
-	int rc;
+	int i, success = 0;
 	struct device *dev = &dev_dax->dev;
-	struct range range = dax_kmem_range(dev_dax);
 	const char *res_name = dev_get_drvdata(dev);
 
 	/*
@@ -101,17 +131,31 @@ static int dev_dax_kmem_remove(struct dev_dax *dev_dax)
 	 * there is no way to hotremove this memory until reboot because device
 	 * unbind will succeed even if we return failure.
 	 */
-	rc = remove_memory(dev_dax->target_node, range.start, range_len(&range));
-	if (rc) {
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct range range;
+		int rc;
+
+		rc = dax_kmem_range(dev_dax, i, &range);
+		if (rc)
+			continue;
+
+		rc = remove_memory(dev_dax->target_node, range.start,
+				range_len(&range));
+		if (rc == 0) {
+			release_mem_region(range.start, range_len(&range));
+			success++;
+			continue;
+		}
 		any_hotremove_failed = true;
-		dev_err(dev, "%#llx-%#llx cannot be hotremoved until the next reboot\n",
-				range.start, range.end);
-		return rc;
+		dev_err(dev,
+			"mapping%d: %#llx-%#llx cannot be hotremoved until the next reboot\n",
+				i, range.start, range.end);
 	}
 
-	/* Release and free dax resources */
-	release_mem_region(range.start, range_len(&range));
-	kfree(res_name);
+	if (success >= dev_dax->nr_range) {
+		kfree(res_name);
+		dev_set_drvdata(dev, NULL);
+	}
 
 	return 0;
 }

tools/testing/nvdimm/dax-dev.c

@@ -9,11 +9,18 @@
 phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
-	struct range *range = &dev_dax->range;
-	phys_addr_t addr;
+	int i;
 
-	addr = pgoff * PAGE_SIZE + range->start;
-	if (addr >= range->start && addr <= range->end) {
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+		struct range *range = &dax_range->range;
+		unsigned long long pgoff_end;
+		phys_addr_t addr;
+
+		pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
+		if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
+			continue;
+		addr = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
 		if (addr + size - 1 <= range->end) {
 			if (get_nfit_res(addr)) {
 				struct page *page;
@@ -23,9 +30,10 @@ phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 
 				page = vmalloc_to_page((void *)addr);
 				return PFN_PHYS(page_to_pfn(page));
-			} else
-				return addr;
+			}
+			return addr;
 		}
+		break;
 	}
 	return -1;
 }