device-dax: add an 'align' attribute

Introduce a device align attribute. While doing so, rename the region
align attribute to be more explicitly named as so, but keep it named as
@align to retain the API for tools like daxctl.

Changes on align may not always be valid, when say certain mappings were
created with 2M and then we switch to 1G. So, we validate all ranges
against the new value being attempted, post resizing.

Signed-off-by: Joao Martins <[e-mail]>
Signed-off-by: Dan Williams <[e-mail]>
Signed-off-by: Andrew Morton <[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]>
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: Linus Torvalds <[e-mail]>

drivers/dax/bus.c

···
 static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,
 		region_size_show, NULL);
 
-static ssize_t align_show(struct device *dev,
+static ssize_t region_align_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct dax_region *dax_region = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", dax_region->align);
 }
-static DEVICE_ATTR_RO(align);
+static struct device_attribute dev_attr_region_align =
+		__ATTR(align, 0400, region_align_show, NULL);
 
 #define for_each_dax_region_resource(dax_region, res) \
 	for (res = (dax_region)->res.child; res; res = res->sibling)
···
 static struct attribute *dax_region_attributes[] = {
 	&dev_attr_available_size.attr,
 	&dev_attr_region_size.attr,
-	&dev_attr_align.attr,
+	&dev_attr_region_align.attr,
 	&dev_attr_create.attr,
 	&dev_attr_seed.attr,
 	&dev_attr_delete.attr,
···
 	return sprintf(buf, "%llu\n", size);
 }
 
-static bool alloc_is_aligned(struct dax_region *dax_region,
-		resource_size_t size)
+static bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
 {
 	/*
 	 * The minimum mapping granularity for a device instance is a
 	 * single subsection, unless the arch says otherwise.
 	 */
-	return IS_ALIGNED(size, max_t(unsigned long, dax_region->align,
-				memremap_compat_align()));
+	return IS_ALIGNED(size, max_t(unsigned long, dev_dax->align, memremap_compat_align()));
 }
 
 static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
···
 		return dev_dax_shrink(dev_dax, size);
 
 	to_alloc = size - dev_size;
-	if (dev_WARN_ONCE(dev, !alloc_is_aligned(dax_region, to_alloc),
+	if (dev_WARN_ONCE(dev, !alloc_is_aligned(dev_dax, to_alloc),
 			"resize of %pa misaligned\n", &to_alloc))
 		return -ENXIO;
 
···
 	if (rc)
 		return rc;
 
-	if (!alloc_is_aligned(dax_region, val)) {
+	if (!alloc_is_aligned(dev_dax, val)) {
 		dev_dbg(dev, "%s: size: %lld misaligned\n", __func__, val);
 		return -EINVAL;
 	}
···
 	return rc == 0 ? len : rc;
 }
 static DEVICE_ATTR_RW(size);
+
+static ssize_t align_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+
+	return sprintf(buf, "%d\n", dev_dax->align);
+}
+
+static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax)
+{
+	resource_size_t dev_size = dev_dax_size(dev_dax);
+	struct device *dev = &dev_dax->dev;
+	int i;
+
+	if (dev_size > 0 && !alloc_is_aligned(dev_dax, dev_size)) {
+		dev_dbg(dev, "%s: align %u invalid for size %pa\n",
+			__func__, dev_dax->align, &dev_size);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		size_t len = range_len(&dev_dax->ranges[i].range);
+
+		if (!alloc_is_aligned(dev_dax, len)) {
+			dev_dbg(dev, "%s: align %u invalid for range %d\n",
+				__func__, dev_dax->align, i);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static ssize_t align_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;
+	unsigned long val, align_save;
+	ssize_t rc;
+
+	rc = kstrtoul(buf, 0, &val);
+	if (rc)
+		return -ENXIO;
+
+	if (!dax_align_valid(val))
+		return -EINVAL;
+
+	device_lock(dax_region->dev);
+	if (!dax_region->dev->driver) {
+		device_unlock(dax_region->dev);
+		return -ENXIO;
+	}
+
+	device_lock(dev);
+	if (dev->driver) {
+		rc = -EBUSY;
+		goto out_unlock;
+	}
+
+	align_save = dev_dax->align;
+	dev_dax->align = val;
+	rc = dev_dax_validate_align(dev_dax);
+	if (rc)
+		dev_dax->align = align_save;
+out_unlock:
+	device_unlock(dev);
+	device_unlock(dax_region->dev);
+	return rc == 0 ? len : rc;
+}
+static DEVICE_ATTR_RW(align);
 
 static int dev_dax_target_node(struct dev_dax *dev_dax)
 {
···
 		return 0;
 	if (a == &dev_attr_numa_node.attr && !IS_ENABLED(CONFIG_NUMA))
 		return 0;
-	if (a == &dev_attr_size.attr && is_static(dax_region))
+	if ((a == &dev_attr_align.attr ||
+	     a == &dev_attr_size.attr) && is_static(dax_region))
 		return 0444;
 	return a->mode;
 }
···
 	&dev_attr_modalias.attr,
 	&dev_attr_size.attr,
 	&dev_attr_target_node.attr,
+	&dev_attr_align.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_numa_node.attr,
 	NULL,

drivers/dax/dax-private.h

···
 }
 
 phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, unsigned long size);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline bool dax_align_valid(unsigned long align)
+{
+	if (align == PUD_SIZE && IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+		return true;
+	if (align == PMD_SIZE && has_transparent_hugepage())
+		return true;
+	if (align == PAGE_SIZE)
+		return true;
+	return false;
+}
+#else
+static inline bool dax_align_valid(unsigned long align)
+{
+	return align == PAGE_SIZE;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif