[PATCH v4] dax/bus: fix Device DAX range alignment validation

[PATCH v4] dax/bus: fix Device DAX range alignment validation

[Muchun Song]

Only range sizes are currently validated against dev_dax->align. A
dynamic device can therefore select a large-page alignment and allocate a
range whose start is not naturally aligned. The device binds successfully,
but a later write to a userspace mapping may trigger a kernel panic.

The automatic resize path can also split a size-aligned request across
arbitrary free gaps. When devices with different alignments fragment a
region, this can extend a range by less than the device alignment. A later
allocation then fails, leaving the failed resize partially applied.

Initialize the device alignment before its first allocation. Validate both
the start and size of allocated and adjusted ranges, account only for
aligned free space before changing ranges, skip unusable gaps, and
serialize size validation with alignment updates.

Static Device DAX already has a pre-populated pgmap whose full range was
validated against memremap_compat_align(). Its usable data range may begin
after namespace metadata, so require only dev_dax->align for static
devices. Dynamic Device DAX builds its pgmap from the allocated ranges and
must continue to satisfy both alignments.

Fixes: 6d82120f4156 ("device-dax: add an 'align' attribute")
Assisted-by: LLM
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
v4:
- Use dev_dax->align alone for static Device DAX ranges to preserve
  older 4K namespaces (reported by Alison Schofield)
- Condense the commit message to the failure scenarios and required fixes
  (suggested by Alison Schofield)

v3:
- Serialize size alignment validation with alignment updates to avoid a
  partial shrink after a concurrent alignment change (reported by Sashiko)
- Document the size validation serialization in the commit message

v2:
- Keep the alloc_is_aligned() name to avoid unrelated helper renaming
  (suggested by Dave Jiang)
- Move this patch after the mapping error reporting fix for independent
  backports (suggested by Dave Jiang)
---
 drivers/dax/bus.c | 152 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 117 insertions(+), 35 deletions(-)

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index b809e1a264af..b2c83a0e4ec5 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -848,6 +848,52 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
 	return 0;
 }
 
+static inline unsigned long dev_dax_min_align(struct dev_dax *dev_dax)
+{
+	/*
+	 * A static device has a pre-populated pgmap whose range already
+	 * satisfies memremap_compat_align(). Its data range may start after
+	 * metadata at dev_dax->align granularity.
+	 */
+	if (static_dev_dax(dev_dax))
+		return dev_dax->align;
+
+	/*
+	 * The minimum mapping granularity for a dynamic device instance is a
+	 * single subsection, unless the arch says otherwise.
+	 */
+	return max_t(unsigned long, dev_dax->align, memremap_compat_align());
+}
+
+static inline bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
+{
+	return IS_ALIGNED(size, dev_dax_min_align(dev_dax));
+}
+
+static inline bool range_is_aligned(struct dev_dax *dev_dax, u64 start,
+				    resource_size_t size)
+{
+	return IS_ALIGNED(start | size, dev_dax_min_align(dev_dax));
+}
+
+static resource_size_t
+aligned_gap_size(struct dev_dax *dev_dax, resource_size_t *start,
+		 resource_size_t end)
+{
+	resource_size_t aligned_start = ALIGN(*start, dev_dax_min_align(dev_dax));
+	resource_size_t size;
+
+	if (aligned_start < *start || aligned_start > end)
+		return 0;
+
+	size = ALIGN_DOWN(end - aligned_start + 1, dev_dax_min_align(dev_dax));
+	if (!size)
+		return 0;
+
+	*start = aligned_start;
+	return size;
+}
+
 static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
 		resource_size_t size)
 {
@@ -870,6 +916,9 @@ static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
 		return 0;
 	}
 
+	if (!range_is_aligned(dev_dax, start, size))
+		return -EINVAL;
+
 	alloc = __request_region(res, start, size, dev_name(dev), 0);
 	if (!alloc)
 		return -ENOMEM;
@@ -923,6 +972,9 @@ static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, r
 	if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n"))
 		return -EINVAL;
 
+	if (!range_is_aligned(dev_dax, range->start, size))
+		return -EINVAL;
+
 	rc = adjust_resource(res, range->start, size);
 	if (rc)
 		return rc;
@@ -955,15 +1007,6 @@ static ssize_t size_show(struct device *dev,
 	return sysfs_emit(buf, "%llu\n", 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, dev_dax->align, memremap_compat_align()));
-}
-
 static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
 {
 	resource_size_t to_shrink = dev_dax_size(dev_dax) - size;
@@ -1030,23 +1073,46 @@ static bool adjust_ok(struct dev_dax *dev_dax, struct resource *res)
 	return true;
 }
 
+static resource_size_t
+dax_region_aligned_avail_size(struct dax_region *dax_region,
+			      struct dev_dax *dev_dax)
+{
+	struct resource *region_res = &dax_region->res;
+	resource_size_t start = region_res->start;
+	resource_size_t avail = 0;
+	struct resource *res;
+
+	lockdep_assert_held_write(&dax_region_rwsem);
+
+	for_each_dax_region_resource(dax_region, res) {
+		if (res->start > start) {
+			resource_size_t gap_start = start;
+
+			avail += aligned_gap_size(dev_dax, &gap_start,
+					res->start - 1);
+		}
+		start = res->end + 1;
+	}
+	if (start <= region_res->end)
+		avail += aligned_gap_size(dev_dax, &start, region_res->end);
+
+	return avail;
+}
+
 static ssize_t dev_dax_resize(struct dax_region *dax_region,
 		struct dev_dax *dev_dax, resource_size_t size)
 {
-	resource_size_t avail = dax_region_avail_size(dax_region), to_alloc;
 	resource_size_t dev_size = dev_dax_size(dev_dax);
 	struct resource *region_res = &dax_region->res;
 	struct device *dev = &dev_dax->dev;
 	struct resource *res, *first;
-	resource_size_t alloc = 0;
+	resource_size_t alloc, to_alloc;
 	int rc;
 
 	if (dev->driver)
 		return -EBUSY;
 	if (size == dev_size)
 		return 0;
-	if (size > dev_size && size - dev_size > avail)
-		return -ENOSPC;
 	if (size < dev_size)
 		return dev_dax_shrink(dev_dax, size);
 
@@ -1054,6 +1120,8 @@ static ssize_t dev_dax_resize(struct dax_region *dax_region,
 	if (dev_WARN_ONCE(dev, !alloc_is_aligned(dev_dax, to_alloc),
 			"resize of %pa misaligned\n", &to_alloc))
 		return -ENXIO;
+	if (to_alloc > dax_region_aligned_avail_size(dax_region, dev_dax))
+		return -ENOSPC;
 
 	/*
 	 * Expand the device into the unused portion of the region. This
@@ -1062,37 +1130,51 @@ static ssize_t dev_dax_resize(struct dax_region *dax_region,
 	 */
 retry:
 	first = region_res->child;
-	if (!first)
-		return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
+	if (!first) {
+		resource_size_t start = region_res->start;
+
+		alloc = aligned_gap_size(dev_dax, &start, region_res->end);
+		return alloc_dev_dax_range(dev_dax, start, min(alloc, to_alloc));
+	}
 
 	rc = -ENOSPC;
 	for (res = first; res; res = res->sibling) {
 		struct resource *next = res->sibling;
+		resource_size_t start, end;
 
 		/* space at the beginning of the region */
 		if (res == first && res->start > dax_region->res.start) {
-			alloc = min(res->start - dax_region->res.start, to_alloc);
-			rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc);
-			break;
+			start = dax_region->res.start;
+			end = res->start - 1;
+			alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);
+			if (alloc) {
+				rc = alloc_dev_dax_range(dev_dax, start, alloc);
+				break;
+			}
 		}
 
-		alloc = 0;
 		/* space between allocations */
-		if (next && next->start > res->end + 1)
-			alloc = min(next->start - (res->end + 1), to_alloc);
-
-		/* space at the end of the region */
-		if (!alloc && !next && res->end < region_res->end)
-			alloc = min(region_res->end - res->end, to_alloc);
+		if (next) {
+			if (next->start <= res->end + 1)
+				continue;
+			end = next->start - 1;
+		} else {
+			/* space at the end of the region */
+			if (res->end >= region_res->end)
+				continue;
+			end = region_res->end;
+		}
 
+		start = res->end + 1;
+		alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);
 		if (!alloc)
 			continue;
 
-		if (adjust_ok(dev_dax, res)) {
+		if (start == res->end + 1 && adjust_ok(dev_dax, res)) {
 			rc = adjust_dev_dax_range(dev_dax, res, resource_size(res) + alloc);
 			break;
 		}
-		rc = alloc_dev_dax_range(dev_dax, res->end + 1, alloc);
+		rc = alloc_dev_dax_range(dev_dax, start, alloc);
 		break;
 	}
 	if (rc)
@@ -1115,11 +1197,6 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr,
 	if (rc)
 		return rc;
 
-	if (!alloc_is_aligned(dev_dax, val)) {
-		dev_dbg(dev, "%s: size: %lld misaligned\n", __func__, val);
-		return -EINVAL;
-	}
-
 	rc = down_write_killable(&dax_region_rwsem);
 	if (rc)
 		return rc;
@@ -1130,6 +1207,11 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr,
 	rc = down_write_killable(&dax_dev_rwsem);
 	if (rc)
 		goto err_dev;
+	if (!alloc_is_aligned(dev_dax, val)) {
+		dev_dbg(dev, "%s: size: %lld misaligned\n", __func__, val);
+		rc = -EINVAL;
+		goto err_dev;
+	}
 
 	rc = dev_dax_resize(dax_region, dev_dax, val);
 
@@ -1224,9 +1306,9 @@ static ssize_t dev_dax_validate_align(struct dev_dax *dev_dax)
 	int i;
 
 	for (i = 0; i < dev_dax->nr_range; i++) {
-		size_t len = range_len(&dev_dax->ranges[i].range);
+		struct range *range = &dev_dax->ranges[i].range;
 
-		if (!alloc_is_aligned(dev_dax, len)) {
+		if (!range_is_aligned(dev_dax, range->start, range_len(range))) {
 			dev_dbg(dev, "%s: align %u invalid for range %d\n",
 				__func__, dev_dax->align, i);
 			return -EINVAL;
@@ -1464,6 +1546,7 @@ static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data)
 		return ERR_PTR(-ENOMEM);
 
 	dev_dax->region = dax_region;
+	dev_dax->align = dax_region->align;
 	if (is_static(dax_region)) {
 		if (dev_WARN_ONCE(parent, data->id < 0,
 				"dynamic id specified to static region\n")) {
@@ -1522,7 +1605,6 @@ static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data)
 
 	dev_dax->dax_dev = dax_dev;
 	dev_dax->target_node = dax_region->target_node;
-	dev_dax->align = dax_region->align;
 	ida_init(&dev_dax->ida);
 
 	dev_dax->memmap_on_memory = data->memmap_on_memory;

base-commit: 93f51579e7df248780214094418f205253383cc5
-- 
2.54.0

Re: [PATCH v4] dax/bus: fix Device DAX range alignment validation

[Alison Schofield]

On Fri, Oct 16, 2026 at 01:39:44PM +0800, Muchun Song wrote:
> Only range sizes are currently validated against dev_dax->align. A
> dynamic device can therefore select a large-page alignment and allocate a
> range whose start is not naturally aligned. The device binds successfully,
> but a later write to a userspace mapping may trigger a kernel panic.
> 
> The automatic resize path can also split a size-aligned request across
> arbitrary free gaps. When devices with different alignments fragment a
> region, this can extend a range by less than the device alignment. A later
> allocation then fails, leaving the failed resize partially applied.
> 
> Initialize the device alignment before its first allocation. Validate both
> the start and size of allocated and adjusted ranges, account only for
> aligned free space before changing ranges, skip unusable gaps, and
> serialize size validation with alignment updates.
> 
> Static Device DAX already has a pre-populated pgmap whose full range was
> validated against memremap_compat_align(). Its usable data range may begin
> after namespace metadata, so require only dev_dax->align for static
> devices. Dynamic Device DAX builds its pgmap from the allocated ranges and
> must continue to satisfy both alignments.

Hi Muchun,

One commit message comment:

Now that this is a standalone patch, some useful context from the original
cover letter would be useful in this commit message. 

The cover letter explained that Sashiko identified a path where
`memmap_init_zone_device()` could initialize struct pages with a large-page
order for a physical range that wasn't naturally aligned. You also mentioned
that you reproduced the resulting kernel panic.

That gives us both the failure mechanism and confirmation that this is a
reproduced bug, rather than just a potential problem. Those details are worth
keeping in the commit message.

So I happened to hit this and the mapping_store() issue that was in the
original patch 1/2. Both these fixes solved my problems. 

Below I do have some style and simplification feedback, and am also wondering
about the gap handling logic.


> 
> Fixes: 6d82120f4156 ("device-dax: add an 'align' attribute")
> Assisted-by: LLM
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
> v4:
> - Use dev_dax->align alone for static Device DAX ranges to preserve
>   older 4K namespaces (reported by Alison Schofield)
> - Condense the commit message to the failure scenarios and required fixes
>   (suggested by Alison Schofield)
> 
> v3:
> - Serialize size alignment validation with alignment updates to avoid a
>   partial shrink after a concurrent alignment change (reported by Sashiko)
> - Document the size validation serialization in the commit message
> 
> v2:
> - Keep the alloc_is_aligned() name to avoid unrelated helper renaming
>   (suggested by Dave Jiang)
> - Move this patch after the mapping error reporting fix for independent
>   backports (suggested by Dave Jiang)
> ---
>  drivers/dax/bus.c | 152 +++++++++++++++++++++++++++++++++++-----------
>  1 file changed, 117 insertions(+), 35 deletions(-)
> 
> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
> index b809e1a264af..b2c83a0e4ec5 100644
> --- a/drivers/dax/bus.c
> +++ b/drivers/dax/bus.c
> @@ -848,6 +848,52 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
>  	return 0;
>  }
>  
> +static inline unsigned long dev_dax_min_align(struct dev_dax *dev_dax)

Why the static inline here and also why below do you change
alloc_is_aligned() to static inline?

coding-style.rst is against it in .c files and we don't do it in any
other drivers/dax/*.c code.


> +{
> +	/*
> +	 * A static device has a pre-populated pgmap whose range already
> +	 * satisfies memremap_compat_align(). Its data range may start after
> +	 * metadata at dev_dax->align granularity.
> +	 */
> +	if (static_dev_dax(dev_dax))
> +		return dev_dax->align;
> +
> +	/*
> +	 * The minimum mapping granularity for a dynamic device instance is a
> +	 * single subsection, unless the arch says otherwise.
> +	 */
> +	return max_t(unsigned long, dev_dax->align, memremap_compat_align());
> +}
> +
> +static inline bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
> +{
> +	return IS_ALIGNED(size, dev_dax_min_align(dev_dax));
> +}
> +
> +static inline bool range_is_aligned(struct dev_dax *dev_dax, u64 start,
> +				    resource_size_t size)
> +{
> +	return IS_ALIGNED(start | size, dev_dax_min_align(dev_dax));
> +}
> +
> +static resource_size_t
> +aligned_gap_size(struct dev_dax *dev_dax, resource_size_t *start,
> +		 resource_size_t end)


Please keep the return type on the same line as the function name, like
rest of this file.

Also a function comment like:
/* Return usable aligned gap size and update *aligned_start */

and a rename of *start to *aligned_start would make the contract clearer.


> +{
> +	resource_size_t aligned_start = ALIGN(*start, dev_dax_min_align(dev_dax));
> +	resource_size_t size;


How about calculating dev_dax_min_align() once and keep it in a local variable?
We use the same value again for ALIGN_DOWN().


> +
> +	if (aligned_start < *start || aligned_start > end)
> +		return 0;
> +
> +	size = ALIGN_DOWN(end - aligned_start + 1, dev_dax_min_align(dev_dax));
> +	if (!size)
> +		return 0;

The above early return looks needless given how callers use the result

> +
> +	*start = aligned_start;
> +	return size;
> +}
> +

snip

>  
> +static resource_size_t
> +dax_region_aligned_avail_size(struct dax_region *dax_region,
> +			      struct dev_dax *dev_dax)

Same as previous, keep return type on the same line here.

The dax_region argument looks needless as we can get it from
dev-dax->region.


snip


> @@ -1062,37 +1130,51 @@ static ssize_t dev_dax_resize(struct dax_region *dax_region,
>  	 */
>  retry:
>  	first = region_res->child;
> -	if (!first)
> -		return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
> +	if (!first) {
> +		resource_size_t start = region_res->start;
> +
> +		alloc = aligned_gap_size(dev_dax, &start, region_res->end);
> +		return alloc_dev_dax_range(dev_dax, start, min(alloc, to_alloc));
> +	}
>  
>  	rc = -ENOSPC;
>  	for (res = first; res; res = res->sibling) {
>  		struct resource *next = res->sibling;
> +		resource_size_t start, end;
>  
>  		/* space at the beginning of the region */
>  		if (res == first && res->start > dax_region->res.start) {
> -			alloc = min(res->start - dax_region->res.start, to_alloc);
> -			rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc);
> -			break;
> +			start = dax_region->res.start;
> +			end = res->start - 1;
> +			alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);
> +			if (alloc) {
> +				rc = alloc_dev_dax_range(dev_dax, start, alloc);
> +				break;
> +			}
>  		}
>  
> -		alloc = 0;
>  		/* space between allocations */
> -		if (next && next->start > res->end + 1)
> -			alloc = min(next->start - (res->end + 1), to_alloc);
> -
> -		/* space at the end of the region */
> -		if (!alloc && !next && res->end < region_res->end)
> -			alloc = min(region_res->end - res->end, to_alloc);
> +		if (next) {
> +			if (next->start <= res->end + 1)
> +				continue;
> +			end = next->start - 1;
> +		} else {
> +			/* space at the end of the region */
> +			if (res->end >= region_res->end)
> +				continue;
> +			end = region_res->end;
> +		}
>  
> +		start = res->end + 1;
> +		alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);

We're walking the free gaps twice now. Once in dax_region_aligned_avail_size()
and again here. It seems the 2 walks need to agree about which gaps
are usable so that the pre check doesn't succeed and then the allocation
loop cannot satify the request...which would get us right back to a
partially applied resize.

Please look at sharing the gap traversal.

-- Alison

snip

Re: [PATCH v4] dax/bus: fix Device DAX range alignment validation

[Muchun Song]

On 2026/10/23 08:05, Alison Schofield wrote:
> On Fri, Oct 16, 2026 at 01:39:44PM +0800, Muchun Song wrote:
>> Only range sizes are currently validated against dev_dax->align. A
>> dynamic device can therefore select a large-page alignment and allocate a
>> range whose start is not naturally aligned. The device binds successfully,
>> but a later write to a userspace mapping may trigger a kernel panic.
>>
>> The automatic resize path can also split a size-aligned request across
>> arbitrary free gaps. When devices with different alignments fragment a
>> region, this can extend a range by less than the device alignment. A later
>> allocation then fails, leaving the failed resize partially applied.
>>
>> Initialize the device alignment before its first allocation. Validate both
>> the start and size of allocated and adjusted ranges, account only for
>> aligned free space before changing ranges, skip unusable gaps, and
>> serialize size validation with alignment updates.
>>
>> Static Device DAX already has a pre-populated pgmap whose full range was
>> validated against memremap_compat_align(). Its usable data range may begin
>> after namespace metadata, so require only dev_dax->align for static
>> devices. Dynamic Device DAX builds its pgmap from the allocated ranges and
>> must continue to satisfy both alignments.
> Hi Muchun,

Hi,

>
> One commit message comment:
>
> Now that this is a standalone patch, some useful context from the original
> cover letter would be useful in this commit message.

OK, I'll add those info to commit message.

>
> The cover letter explained that Sashiko identified a path where
> `memmap_init_zone_device()` could initialize struct pages with a large-page
> order for a physical range that wasn't naturally aligned. You also mentioned
> that you reproduced the resulting kernel panic.
>
> That gives us both the failure mechanism and confirmation that this is a
> reproduced bug, rather than just a potential problem. Those details are worth
> keeping in the commit message.
>
> So I happened to hit this and the mapping_store() issue that was in the
> original patch 1/2. Both these fixes solved my problems.
>
> Below I do have some style and simplification feedback, and am also wondering
> about the gap handling logic.
>
>
>> Fixes: 6d82120f4156 ("device-dax: add an 'align' attribute")
>> Assisted-by: LLM
>> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
>> ---
>> v4:
>> - Use dev_dax->align alone for static Device DAX ranges to preserve
>>    older 4K namespaces (reported by Alison Schofield)
>> - Condense the commit message to the failure scenarios and required fixes
>>    (suggested by Alison Schofield)
>>
>> v3:
>> - Serialize size alignment validation with alignment updates to avoid a
>>    partial shrink after a concurrent alignment change (reported by Sashiko)
>> - Document the size validation serialization in the commit message
>>
>> v2:
>> - Keep the alloc_is_aligned() name to avoid unrelated helper renaming
>>    (suggested by Dave Jiang)
>> - Move this patch after the mapping error reporting fix for independent
>>    backports (suggested by Dave Jiang)
>> ---
>>   drivers/dax/bus.c | 152 +++++++++++++++++++++++++++++++++++-----------
>>   1 file changed, 117 insertions(+), 35 deletions(-)
>>
>> diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
>> index b809e1a264af..b2c83a0e4ec5 100644
>> --- a/drivers/dax/bus.c
>> +++ b/drivers/dax/bus.c
>> @@ -848,6 +848,52 @@ static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
>>   	return 0;
>>   }
>>   
>> +static inline unsigned long dev_dax_min_align(struct dev_dax *dev_dax)
> Why the static inline here and also why below do you change
> alloc_is_aligned() to static inline?

I thought it is a one-line code, inline is better, I usually do
this in MM area.

>
> coding-style.rst is against it in .c files and we don't do it in any
> other drivers/dax/*.c code.

Seems it is not a convention in DAX. I am not an expert in DAX.

>
>> +{
>> +	/*
>> +	 * A static device has a pre-populated pgmap whose range already
>> +	 * satisfies memremap_compat_align(). Its data range may start after
>> +	 * metadata at dev_dax->align granularity.
>> +	 */
>> +	if (static_dev_dax(dev_dax))
>> +		return dev_dax->align;
>> +
>> +	/*
>> +	 * The minimum mapping granularity for a dynamic device instance is a
>> +	 * single subsection, unless the arch says otherwise.
>> +	 */
>> +	return max_t(unsigned long, dev_dax->align, memremap_compat_align());
>> +}
>> +
>> +static inline bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
>> +{
>> +	return IS_ALIGNED(size, dev_dax_min_align(dev_dax));
>> +}
>> +
>> +static inline bool range_is_aligned(struct dev_dax *dev_dax, u64 start,
>> +				    resource_size_t size)
>> +{
>> +	return IS_ALIGNED(start | size, dev_dax_min_align(dev_dax));
>> +}
>> +
>> +static resource_size_t
>> +aligned_gap_size(struct dev_dax *dev_dax, resource_size_t *start,
>> +		 resource_size_t end)
>
> Please keep the return type on the same line as the function name, like
> rest of this file.
>
> Also a function comment like:
> /* Return usable aligned gap size and update *aligned_start */
>
> and a rename of *start to *aligned_start would make the contract clearer.

Will do.

>
>
>> +{
>> +	resource_size_t aligned_start = ALIGN(*start, dev_dax_min_align(dev_dax));
>> +	resource_size_t size;
>
> How about calculating dev_dax_min_align() once and keep it in a local variable?
> We use the same value again for ALIGN_DOWN().

Make sense.

>
>
>> +
>> +	if (aligned_start < *start || aligned_start > end)
>> +		return 0;
>> +
>> +	size = ALIGN_DOWN(end - aligned_start + 1, dev_dax_min_align(dev_dax));
>> +	if (!size)
>> +		return 0;
> The above early return looks needless given how callers use the result

Oh, yes.

>> +
>> +	*start = aligned_start;
>> +	return size;
>> +}
>> +
> snip
>
>>   
>> +static resource_size_t
>> +dax_region_aligned_avail_size(struct dax_region *dax_region,
>> +			      struct dev_dax *dev_dax)
> Same as previous, keep return type on the same line here.
>
> The dax_region argument looks needless as we can get it from
> dev-dax->region.

Right. My oversight.

>
>
> snip
>
>
>> @@ -1062,37 +1130,51 @@ static ssize_t dev_dax_resize(struct dax_region *dax_region,
>>   	 */
>>   retry:
>>   	first = region_res->child;
>> -	if (!first)
>> -		return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
>> +	if (!first) {
>> +		resource_size_t start = region_res->start;
>> +
>> +		alloc = aligned_gap_size(dev_dax, &start, region_res->end);
>> +		return alloc_dev_dax_range(dev_dax, start, min(alloc, to_alloc));
>> +	}
>>   
>>   	rc = -ENOSPC;
>>   	for (res = first; res; res = res->sibling) {
>>   		struct resource *next = res->sibling;
>> +		resource_size_t start, end;
>>   
>>   		/* space at the beginning of the region */
>>   		if (res == first && res->start > dax_region->res.start) {
>> -			alloc = min(res->start - dax_region->res.start, to_alloc);
>> -			rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc);
>> -			break;
>> +			start = dax_region->res.start;
>> +			end = res->start - 1;
>> +			alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);
>> +			if (alloc) {
>> +				rc = alloc_dev_dax_range(dev_dax, start, alloc);
>> +				break;
>> +			}
>>   		}
>>   
>> -		alloc = 0;
>>   		/* space between allocations */
>> -		if (next && next->start > res->end + 1)
>> -			alloc = min(next->start - (res->end + 1), to_alloc);
>> -
>> -		/* space at the end of the region */
>> -		if (!alloc && !next && res->end < region_res->end)
>> -			alloc = min(region_res->end - res->end, to_alloc);
>> +		if (next) {
>> +			if (next->start <= res->end + 1)
>> +				continue;
>> +			end = next->start - 1;
>> +		} else {
>> +			/* space at the end of the region */
>> +			if (res->end >= region_res->end)
>> +				continue;
>> +			end = region_res->end;
>> +		}
>>   
>> +		start = res->end + 1;
>> +		alloc = min(aligned_gap_size(dev_dax, &start, end), to_alloc);
> We're walking the free gaps twice now. Once in dax_region_aligned_avail_size()
> and again here. It seems the 2 walks need to agree about which gaps
> are usable so that the pre check doesn't succeed and then the allocation
> loop cannot satify the request...which would get us right back to a
> partially applied resize.
>
> Please look at sharing the gap traversal.

Good point. I will factor the gap traversal into a common iterator used
by both the pre-check and the allocation path, so they share the same
gap selection rules. I will include this in the next revision.

Thanks for your review.

Thanks,
Muchun

>
> -- Alison
>
> snip