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.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 36 insertions, 19 deletions

diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 5f808617672a..bf389712a20b 100644
--- a/drivers/dax/device.c
+++ b/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))