[v3,23/23] device-dax: Add a range mapping allocation attribute

Commit Message

Dan Williams Aug. 1, 2020, 3:27 a.m. UTC

From: Joao Martins <[e-mail]>

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

Signed-off-by: Joao Martins <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Dan Williams <[e-mail]>
---
 drivers/dax/bus.c |   64 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

Patch

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 7a9439132573..aa67555ba183 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1040,6 +1040,67 @@  static ssize_t size_store(struct device *dev, struct device_attribute *attr,
 }
 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)
 {
@@ -1181,6 +1242,8 @@  static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
 		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;
@@ -1190,6 +1253,7 @@  static umode_t dev_dax_visible(struct kobject *kobj, struct attribute *a, int n)
 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,