[RFC PATCH v1] devres: align devres.data strictly only for devm_kmalloc()

[Marc Gonzalez]

Commit a66d972465d15 ("devres: Align data[] to ARCH_KMALLOC_MINALIGN")
increased the alignment of devres.data unconditionally.

Some platforms have very strict alignment requirements for DMA-safe
addresses, e.g. 128 bytes on arm64. There, struct devres amounts to:
	3 pointers + pad_to_128 + data + pad_to_256
i.e. ~220 bytes of padding.

Let's enforce the alignment only for devm_kmalloc().

Suggested-by: Robin Murphy <robin.murphy@xxxxxxx>
Signed-off-by: Marc Gonzalez <marc.w.gonzalez@xxxxxxx>
---
I had not been aware that dynamic allocation granularity on arm64 was
128 bytes. This means there's a lot of waste on small allocations.
I suppose there's no easy solution, though.
---
 drivers/base/devres.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 0bbb328bd17f..bf39188613d9 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -26,14 +26,7 @@ struct devres_node {
 
 struct devres {
 	struct devres_node		node;
-	/*
-	 * Some archs want to perform DMA into kmalloc caches
-	 * and need a guaranteed alignment larger than
-	 * the alignment of a 64-bit integer.
-	 * Thus we use ARCH_KMALLOC_MINALIGN here and get exactly the same
-	 * buffer alignment as if it was allocated by plain kmalloc().
-	 */
-	u8 __aligned(ARCH_KMALLOC_MINALIGN) data[];
+	u8				data[];
 };
 
 struct devres_group {
@@ -789,9 +782,16 @@ static void devm_kmalloc_release(struct device *dev, void *res)
 	/* noop */
 }
 
+#define DEVM_KMALLOC_PADDING_SIZE \
+	(ARCH_KMALLOC_MINALIGN - sizeof(struct devres) % ARCH_KMALLOC_MINALIGN)
+
 static int devm_kmalloc_match(struct device *dev, void *res, void *data)
 {
-	return res == data;
+	/*
+	 * 'res' is dr->data (not DMA-safe)
+	 * 'data' is the hand-aligned address from devm_kmalloc
+	 */
+	return res + DEVM_KMALLOC_PADDING_SIZE == data;
 }
 
 /**
@@ -811,6 +811,9 @@ void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 {
 	struct devres *dr;
 
+	/* Add enough padding to provide a DMA-safe address */
+	size += DEVM_KMALLOC_PADDING_SIZE;
+
 	/* use raw alloc_dr for kmalloc caller tracing */
 	dr = alloc_dr(devm_kmalloc_release, size, gfp, dev_to_node(dev));
 	if (unlikely(!dr))
@@ -822,7 +825,7 @@ void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 	 */
 	set_node_dbginfo(&dr->node, "devm_kzalloc_release", size);
 	devres_add(dev, dr->data);
-	return dr->data;
+	return dr->data + DEVM_KMALLOC_PADDING_SIZE;
 }
 EXPORT_SYMBOL_GPL(devm_kmalloc);
 
-- 
2.17.1