[PATCH v10 2/2] net: airoha: npu: use cacheline-sized buffers for mailbox DMA

On non-coherent ARM64 (EN7581), the kernel's dma_direct_map_page()
forces swiotlb bounce buffering when:

  !IS_ALIGNED(phys | size, dma_get_cache_alignment())

The NPU mailbox buffers are 12-24 bytes, well below the 64-byte cache
line size, so this check always fails regardless of physical address
alignment. The swiotlb sync path itself works correctly, but the
EN7581 NPU cannot DMA-write to the swiotlb bounce buffer address
range — it reads commands fine (mbox_status=0x7 success) but never
writes responses back, leaving response fields as zeros.

This was confirmed through five boot traces on a Gemtek W1700K:

  - Boots 1-4: all streaming DMA through swiotlb (is_swiotlb=1),
    bounce buffer byte-identical to pre-map after NPU completion,
    even after explicit CPU cache invalidation (dcache_inval_poc).
    NPU version reads 0.0.

  - Boot 5: kmalloc'd cache-line-aligned buffer bypasses swiotlb
    (is_swiotlb=0 on all 169 mappings), NPU writes response data
    directly, version reads 0.1111, WiFi fully functional.

Fix by rounding mailbox buffer allocations up to
dma_get_cache_alignment() and mapping the rounded length. The original
payload size is still programmed into the mailbox length register.
kmalloc returns cache-line-aligned pointers on ARM64 for allocations
>= ARCH_KMALLOC_MINALIGN, so the IS_ALIGNED check passes and swiotlb
is not triggered.

Fixes: 6f884eb87a79 ("net: airoha: Fix DMA direction for NPU mailbox buffer")
Link: https://patchwork.kernel.org/project/linux-mediatek/patch/[email protected]/
Link: https://patchwork.kernel.org/project/linux-mediatek/patch/[email protected]/
Link: https://patchwork.kernel.org/project/linux-mediatek/patch/[email protected]/
Assisted-by: Claude:claude-opus-4-6
Signed-off-by: Daniel Pawlik <[email protected]>
---
 drivers/net/ethernet/airoha/airoha_npu.c | 25 +++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
index 4045d1eb93ea..3416f921f961 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.c
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/devcoredump.h>
+#include <linux/dma-mapping.h>
 #include <linux/firmware.h>
 #include <linux/platform_device.h>
 #include <linux/of_net.h>
@@ -160,15 +161,21 @@ struct wlan_mbox_data {
 	DECLARE_FLEX_ARRAY(u8, d);
 };
 
+static size_t airoha_npu_mbox_size(size_t len)
+{
+	return ALIGN(len, dma_get_cache_alignment());
+}
+
 static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 			       void *p, int size)
 {
 	u16 core = 0; /* FIXME */
 	u32 val, offset = core << 4;
 	dma_addr_t dma_addr;
+	size_t map_len = airoha_npu_mbox_size(size);
 	int ret;
 
-	dma_addr = dma_map_single(npu->dev, p, size, DMA_BIDIRECTIONAL);
+	dma_addr = dma_map_single(npu->dev, p, map_len, DMA_BIDIRECTIONAL);
 	ret = dma_mapping_error(npu->dev, dma_addr);
 	if (ret)
 		return ret;
@@ -191,7 +198,7 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 
 	spin_unlock_bh(&npu->cores[core].lock);
 
-	dma_unmap_single(npu->dev, dma_addr, size, DMA_BIDIRECTIONAL);
+	dma_unmap_single(npu->dev, dma_addr, map_len, DMA_BIDIRECTIONAL);
 
 	return ret;
 }
@@ -333,7 +340,7 @@ static int airoha_npu_ppe_init(struct airoha_npu *npu)
 	struct ppe_mbox_data *ppe_data;
 	int err;
 
-	ppe_data = kzalloc_obj(*ppe_data);
+	ppe_data = kzalloc(airoha_npu_mbox_size(sizeof(*ppe_data)), GFP_KERNEL);
 	if (!ppe_data)
 		return -ENOMEM;
 
@@ -354,7 +361,7 @@ static int airoha_npu_ppe_deinit(struct airoha_npu *npu)
 	struct ppe_mbox_data *ppe_data;
 	int err;
 
-	ppe_data = kzalloc_obj(*ppe_data);
+	ppe_data = kzalloc(airoha_npu_mbox_size(sizeof(*ppe_data)), GFP_KERNEL);
 	if (!ppe_data)
 		return -ENOMEM;
 
@@ -375,7 +382,7 @@ static int airoha_npu_ppe_flush_sram_entries(struct airoha_npu *npu,
 	struct ppe_mbox_data *ppe_data;
 	int err;
 
-	ppe_data = kzalloc_obj(*ppe_data);
+	ppe_data = kzalloc(airoha_npu_mbox_size(sizeof(*ppe_data)), GFP_KERNEL);
 	if (!ppe_data)
 		return -ENOMEM;
 
@@ -399,7 +406,7 @@ static int airoha_npu_foe_commit_entry(struct airoha_npu *npu,
 	struct ppe_mbox_data *ppe_data;
 	int err;
 
-	ppe_data = kzalloc_obj(*ppe_data, GFP_ATOMIC);
+	ppe_data = kzalloc(airoha_npu_mbox_size(sizeof(*ppe_data)), GFP_ATOMIC);
 	if (!ppe_data)
 		return -ENOMEM;
 
@@ -434,7 +441,7 @@ static int airoha_npu_ppe_stats_setup(struct airoha_npu *npu,
 	int err, size = num_stats_entries * sizeof(*npu->stats);
 	struct ppe_mbox_data *ppe_data;
 
-	ppe_data = kzalloc_obj(*ppe_data, GFP_ATOMIC);
+	ppe_data = kzalloc(airoha_npu_mbox_size(sizeof(*ppe_data)), GFP_ATOMIC);
 	if (!ppe_data)
 		return -ENOMEM;
 
@@ -466,7 +473,7 @@ static int airoha_npu_wlan_msg_send(struct airoha_npu *npu, int ifindex,
 	int err, len;
 
 	len = sizeof(*wlan_data) + data_len;
-	wlan_data = kzalloc(len, gfp);
+	wlan_data = kzalloc(airoha_npu_mbox_size(len), gfp);
 	if (!wlan_data)
 		return -ENOMEM;
 
@@ -489,7 +496,7 @@ static int airoha_npu_wlan_msg_get(struct airoha_npu *npu, int ifindex,
 	int err, len;
 
 	len = sizeof(*wlan_data) + data_len;
-	wlan_data = kzalloc(len, gfp);
+	wlan_data = kzalloc(airoha_npu_mbox_size(len), gfp);
 	if (!wlan_data)
 		return -ENOMEM;
 
-- 
2.55.0