[051/181] device-dax: add a range mapping allocation attribute

Commit Message

Andrew Morton Oct. 13, 2020, 11:51 p.m. UTC

From: Joao Martins <[e-mail]>
Subject: device-dax: add a range mapping allocation attribute

Add a sysfs attribute which denotes a range from the dax region to be
allocated.  It's an write only @mapping sysfs attribute in the format of
'<start>-<end>' to allocate a range.  @start and @end use hexadecimal
values and the @pgoff is implicitly ordered wrt to previous writes to
@mapping sysfs e.g.  a write of a range of length 1G the pgoff is
0..1G(-4K), a second write will use @pgoff for 1G+4K..<size>.

This range mapping interface is useful for:

 1) Application which want to implement its own allocation logic, and
    thus pick the desired ranges from dax_region.

 2) For use cases like VMM fast restart[0] where after kexec we want
    to the same gpa<->phys mappings (as originally created before kexec).

[0] https://static.sched.com/hosted_files/kvmforum2019/66/VMM-fast-restart_kvmforum2019.pdf

Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lore.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Joao Martins <[e-mail]>
Signed-off-by: Dan Williams <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: Ard Biesheuvel <[e-mail]>
Cc: Ard Biesheuvel <[e-mail]>
Cc: Benjamin Herrenschmidt <[e-mail]>
Cc: Ben Skeggs <[e-mail]>
Cc: Bjorn Helgaas <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Boris Ostrovsky <[e-mail]>
Cc: Brice Goglin <[e-mail]>
Cc: Catalin Marinas <[e-mail]>
Cc: Daniel Vetter <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Cc: Dave Jiang <[e-mail]>
Cc: David Airlie <[e-mail]>
Cc: David Hildenbrand <[e-mail]>
Cc: Greg Kroah-Hartman <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: Hulk Robot <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Ira Weiny <[e-mail]>
Cc: Jason Gunthorpe <[e-mail]>
Cc: Jason Yan <[e-mail]>
Cc: Jeff Moyer <[e-mail]>
Cc: "Jérôme Glisse" <[e-mail]>
Cc: Jia He <[e-mail]>
Cc: Jonathan Cameron <[e-mail]>
Cc: Juergen Gross <[e-mail]>
Cc: kernel test robot <[e-mail]>
Cc: Michael Ellerman <[e-mail]>
Cc: Mike Rapoport <[e-mail]>
Cc: Paul Mackerras <[e-mail]>
Cc: Pavel Tatashin <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: "Rafael J. Wysocki" <[e-mail]>
Cc: Randy Dunlap <[e-mail]>
Cc: Stefano Stabellini <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Cc: Tom Lendacky <[e-mail]>
Cc: Vishal Verma <[e-mail]>
Cc: Vivek Goyal <[e-mail]>
Cc: Wei Yang <[e-mail]>
Cc: Will Deacon <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 drivers/dax/bus.c |   64 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

Patch

--- a/drivers/dax/bus.c~device-dax-add-a-range-mapping-allocation-attribute
+++ a/drivers/dax/bus.c
@@ -1043,6 +1043,67 @@  static ssize_t size_store(struct device
 }
 static DEVICE_ATTR_RW(size);
 
+static ssize_t range_parse(const char *opt, size_t len, struct range *range)
+{
+	unsigned long long addr = 0;
+	char *start, *end, *str;
+	ssize_t rc = EINVAL;
+
+	str = kstrdup(opt, GFP_KERNEL);
+	if (!str)
+		return rc;
+
+	end = str;
+	start = strsep(&end, "-");
+	if (!start || !end)
+		goto err;
+
+	rc = kstrtoull(start, 16, &addr);
+	if (rc)
+		goto err;
+	range->start = addr;
+
+	rc = kstrtoull(end, 16, &addr);
+	if (rc)
+		goto err;
+	range->end = addr;
+
+err:
+	kfree(str);
+	return rc;
+}
+
+static ssize_t mapping_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t len)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct dax_region *dax_region = dev_dax->region;
+	size_t to_alloc;
+	struct range r;
+	ssize_t rc;
+
+	rc = range_parse(buf, len, &r);
+	if (rc)
+		return rc;
+
+	rc = -ENXIO;
+	device_lock(dax_region->dev);
+	if (!dax_region->dev->driver) {
+		device_unlock(dax_region->dev);
+		return rc;
+	}
+	device_lock(dev);
+
+	to_alloc = range_len(&r);
+	if (alloc_is_aligned(dev_dax, to_alloc))
+		rc = alloc_dev_dax_range(dev_dax, r.start, to_alloc);
+	device_unlock(dev);
+	device_unlock(dax_region->dev);
+
+	return rc == 0 ? len : rc;
+}
+static DEVICE_ATTR_WO(mapping);
+
 static ssize_t align_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -1175,6 +1236,8 @@  static umode_t dev_dax_visible(struct ko
 		return 0;
 	if (a == &dev_attr_numa_node.attr && !IS_ENABLED(CONFIG_NUMA))
 		return 0;
+	if (a == &dev_attr_mapping.attr && is_static(dax_region))
+		return 0;
 	if ((a == &dev_attr_align.attr ||
 	     a == &dev_attr_size.attr) && is_static(dax_region))
 		return 0444;
@@ -1184,6 +1247,7 @@  static umode_t dev_dax_visible(struct ko
 static struct attribute *dev_dax_attributes[] = {
 	&dev_attr_modalias.attr,
 	&dev_attr_size.attr,
+	&dev_attr_mapping.attr,
 	&dev_attr_target_node.attr,
 	&dev_attr_align.attr,
 	&dev_attr_resource.attr,