Skip to contentSkip to conversation

net: airoha: Fix DMA direction for NPU mailbox buffer

PATCH Applied Wayen Yan 3 participants 3 messages Jul 8 – Jul 21

Subsystems (4)
lore
Share & tools
lore

Wayen Yan

author
#0 lore raw

PATCH 1/1 net: airoha: Fix DMA direction for NPU mailbox buffer

airoha_npu_send_msg() always maps the mailbox buffer with DMA_TO_DEVICE, but some callers expect the NPU to write response data back into the same buffer:

- airoha_npu_wlan_msg_get() (NPU_OP_GET): NPU writes response into the buffer, then the caller reads it via memcpy()
- airoha_npu_ppe_stats_setup() (NPU_OP_SET): NPU writes back npu_stats_addr field in the response

On non-cache-coherent architectures like EN7581 (Cortex-A53 without hardware cache coherency for NPU DMA), DMA_TO_DEVICE unmap is a no-op — it does not invalidate the CPU cache. If the NPU-written cache line is still present in the CPU cache when the caller reads the buffer, the CPU observes stale data instead of the NPU response.

This is a timing-sensitive bug: small mailbox buffers (~24 bytes) typically fit in a single cache line and may survive in the cache until the caller reads them, producing silent data corruption rather than a crash. The bug is more likely to trigger when the caller reads the response immediately after dma_unmap_single() without intervening cache-evicting operations.

Fix by using DMA_BIDIRECTIONAL for both map and unmap, which ensures dma_unmap_single() invalidates the CPU cache on non-coherent systems. The mailbox buffers are small so there is no performance concern.

Fixes c52918744ee1e49cea86622a2633b9782446428f ("net: airoha: npu: Move memory allocation in airoha_npu_send_msg() caller")
---
 drivers/net/ethernet/airoha/airoha_npu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/airoha/airoha_npu.c +2 -2
index 870d61fdd9c6..b679bed952de 100644
@@ -168,7 +168,7 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 	dma_addr_t dma_addr;
 	int ret;
 
-	dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE);
+	dma_addr = dma_map_single(npu->dev, p, size, DMA_BIDIRECTIONAL);
 	ret = dma_mapping_error(npu->dev, dma_addr);
 	if (ret)
 		return ret;
@@ -191,7 +191,7 @@ 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_TO_DEVICE);
+	dma_unmap_single(npu->dev, dma_addr, size, DMA_BIDIRECTIONAL);
 
 	return ret;
 }
Signature · 1 line
2.51.0
maintainer Acked-by on v1 1/1
#1 lore raw
Quoted 22 lines

airoha_npu_send_msg() always maps the mailbox buffer with DMA_TO_DEVICE, but some callers expect the NPU to write response data back into the same buffer:

- airoha_npu_wlan_msg_get() (NPU_OP_GET): NPU writes response into the buffer, then the caller reads it via memcpy()
- airoha_npu_ppe_stats_setup() (NPU_OP_SET): NPU writes back npu_stats_addr field in the response

On non-cache-coherent architectures like EN7581 (Cortex-A53 without hardware cache coherency for NPU DMA), DMA_TO_DEVICE unmap is a no-op — it does not invalidate the CPU cache. If the NPU-written cache line is still present in the CPU cache when the caller reads the buffer, the CPU observes stale data instead of the NPU response.

This is a timing-sensitive bug: small mailbox buffers (~24 bytes) typically fit in a single cache line and may survive in the cache until the caller reads them, producing silent data corruption rather than a crash. The bug is more likely to trigger when the caller reads the response immediately after dma_unmap_single() without intervening cache-evicting operations.

Quoted 3 lines

Fix by using DMA_BIDIRECTIONAL for both map and unmap, which ensures dma_unmap_single() invalidates the CPU cache on non-coherent systems. The mailbox buffers are small so there is no performance concern.

Quoted 33 lines
Fixes c52918744ee1e49cea86622a2633b9782446428f ("net: airoha: npu: Move memory allocation in airoha_npu_send_msg() caller")
---
 drivers/net/ethernet/airoha/airoha_npu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/airoha/airoha_npu.c +2 -2
index 870d61fdd9c6..b679bed952de 100644
@@ -168,7 +168,7 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
 	dma_addr_t dma_addr;
 	int ret;
 
-	dma_addr = dma_map_single(npu->dev, p, size, DMA_TO_DEVICE);
+	dma_addr = dma_map_single(npu->dev, p, size, DMA_BIDIRECTIONAL);
 	ret = dma_mapping_error(npu->dev, dma_addr);
 	if (ret)
 		return ret;
@@ -191,7 +191,7 @@ 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_TO_DEVICE);
+	dma_unmap_single(npu->dev, dma_addr, size, DMA_BIDIRECTIONAL);
 
 	return ret;
 }
Signature · 1 line
2.51.0
#2 lore raw
In reply to Wayen Yan
This patch was applied to netdev/net.git (main) by Paolo Abeni <[email protected]>:

Hello:

This patch was applied to netdev/net.git (main)
by Paolo Abeni <[email protected]>:

Quoted 10 lines · On Wed, 8 Jul 2026 19:35:29 +0800 you wrote:

airoha_npu_send_msg() always maps the mailbox buffer with DMA_TO_DEVICE, but some callers expect the NPU to write response data back into the same buffer:

- airoha_npu_wlan_msg_get() (NPU_OP_GET): NPU writes response into the buffer, then the caller reads it via memcpy()
- airoha_npu_ppe_stats_setup() (NPU_OP_SET): NPU writes back npu_stats_addr field in the response

[...]

Here is the summary with links:
- [net] net: airoha: Fix DMA direction for NPU mailbox buffer

    https://git.kernel.org/netdev/net/c/6f884eb87a79

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html