* [PATCH V1] accel/amdxdna: Fix clflush buffer size
@ 2026-05-07 4:02 Lizhi Hou
2026-05-07 16:55 ` Mario Limonciello
0 siblings, 1 reply; 3+ messages in thread
From: Lizhi Hou @ 2026-05-07 4:02 UTC (permalink / raw)
To: ogabbay, quic_jhugo, dri-devel, mario.limonciello,
karol.wachowski
Cc: Lizhi Hou, linux-kernel, max.zhen, sonal.santan
The firmware is told the buffer is req.buf_size bytes. It may read/write
the entire region. If the CPU only flushes a subset, the remaining cache
lines could contain stale data, causing the device to see garbage.
Fixes: 6e87001fe19f ("accel/amdxdna: Adjust size for copy_to_user()")
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
---
drivers/accel/amdxdna/aie2_message.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
index 6e98af7b74db..a012e7e935ad 100644
--- a/drivers/accel/amdxdna/aie2_message.c
+++ b/drivers/accel/amdxdna/aie2_message.c
@@ -390,7 +390,7 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
req.num_cols = hweight32(aie_bitmap);
req.aie_bitmap = aie_bitmap;
- drm_clflush_virt_range(buff_addr, size); /* device can access */
+ drm_clflush_virt_range(buff_addr, req.dump_buff_size); /* device can access */
ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
if (ret) {
XDNA_ERR(xdna, "Error during NPU query, status %d", ret);
@@ -442,7 +442,7 @@ int aie2_query_telemetry(struct amdxdna_dev_hdl *ndev,
req.buf_size = buf_sz;
req.type = header->type;
- drm_clflush_virt_range(addr, size); /* device can access */
+ drm_clflush_virt_range(addr, req.buf_size); /* device can access */
ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
if (ret) {
XDNA_ERR(xdna, "Query telemetry failed, status %d", ret);
@@ -1186,7 +1186,7 @@ int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id,
req.context_id = context_id;
req.buf_size = buf_size;
- drm_clflush_virt_range(buf, sizeof(*report));
+ drm_clflush_virt_range(buf, req.buf_size);
ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
if (ret) {
XDNA_ERR(xdna, "Get app health failed, ret %d status 0x%x", ret, resp.status);
--
2.34.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [PATCH V1] accel/amdxdna: Fix clflush buffer size
2026-05-07 4:02 [PATCH V1] accel/amdxdna: Fix clflush buffer size Lizhi Hou
@ 2026-05-07 16:55 ` Mario Limonciello
2026-05-07 21:23 ` Lizhi Hou
0 siblings, 1 reply; 3+ messages in thread
From: Mario Limonciello @ 2026-05-07 16:55 UTC (permalink / raw)
To: Lizhi Hou, ogabbay, quic_jhugo, dri-devel, karol.wachowski
Cc: linux-kernel, max.zhen, sonal.santan
On 5/6/26 23:02, Lizhi Hou wrote:
> The firmware is told the buffer is req.buf_size bytes. It may read/write
> the entire region. If the CPU only flushes a subset, the remaining cache
> lines could contain stale data, causing the device to see garbage.
>
> Fixes: 6e87001fe19f ("accel/amdxdna: Adjust size for copy_to_user()")
> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
> ---
> drivers/accel/amdxdna/aie2_message.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c
> index 6e98af7b74db..a012e7e935ad 100644
> --- a/drivers/accel/amdxdna/aie2_message.c
> +++ b/drivers/accel/amdxdna/aie2_message.c
> @@ -390,7 +390,7 @@ int aie2_query_status(struct amdxdna_dev_hdl *ndev, char __user *buf,
> req.num_cols = hweight32(aie_bitmap);
> req.aie_bitmap = aie_bitmap;
>
> - drm_clflush_virt_range(buff_addr, size); /* device can access */
> + drm_clflush_virt_range(buff_addr, req.dump_buff_size); /* device can access */
> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
> if (ret) {
> XDNA_ERR(xdna, "Error during NPU query, status %d", ret);
> @@ -442,7 +442,7 @@ int aie2_query_telemetry(struct amdxdna_dev_hdl *ndev,
> req.buf_size = buf_sz;
> req.type = header->type;
>
> - drm_clflush_virt_range(addr, size); /* device can access */
> + drm_clflush_virt_range(addr, req.buf_size); /* device can access */
> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
> if (ret) {
> XDNA_ERR(xdna, "Query telemetry failed, status %d", ret);
> @@ -1186,7 +1186,7 @@ int aie2_query_app_health(struct amdxdna_dev_hdl *ndev, u32 context_id,
> req.context_id = context_id;
> req.buf_size = buf_size;
>
> - drm_clflush_virt_range(buf, sizeof(*report));
> + drm_clflush_virt_range(buf, req.buf_size);
> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
> if (ret) {
> XDNA_ERR(xdna, "Get app health failed, ret %d status 0x%x", ret, resp.status);
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [PATCH V1] accel/amdxdna: Fix clflush buffer size
2026-05-07 16:55 ` Mario Limonciello
@ 2026-05-07 21:23 ` Lizhi Hou
0 siblings, 0 replies; 3+ messages in thread
From: Lizhi Hou @ 2026-05-07 21:23 UTC (permalink / raw)
To: Mario Limonciello, ogabbay, quic_jhugo, dri-devel,
karol.wachowski
Cc: linux-kernel, max.zhen, sonal.santan
Applied to drm-misc-next
On 5/7/26 09:55, Mario Limonciello wrote:
>
>
> On 5/6/26 23:02, Lizhi Hou wrote:
>> The firmware is told the buffer is req.buf_size bytes. It may read/write
>> the entire region. If the CPU only flushes a subset, the remaining cache
>> lines could contain stale data, causing the device to see garbage.
>>
>> Fixes: 6e87001fe19f ("accel/amdxdna: Adjust size for copy_to_user()")
>> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
> Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
>> ---
>> drivers/accel/amdxdna/aie2_message.c | 6 +++---
>> 1 file changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/accel/amdxdna/aie2_message.c
>> b/drivers/accel/amdxdna/aie2_message.c
>> index 6e98af7b74db..a012e7e935ad 100644
>> --- a/drivers/accel/amdxdna/aie2_message.c
>> +++ b/drivers/accel/amdxdna/aie2_message.c
>> @@ -390,7 +390,7 @@ int aie2_query_status(struct amdxdna_dev_hdl
>> *ndev, char __user *buf,
>> req.num_cols = hweight32(aie_bitmap);
>> req.aie_bitmap = aie_bitmap;
>> - drm_clflush_virt_range(buff_addr, size); /* device can access */
>> + drm_clflush_virt_range(buff_addr, req.dump_buff_size); /* device
>> can access */
>> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
>> if (ret) {
>> XDNA_ERR(xdna, "Error during NPU query, status %d", ret);
>> @@ -442,7 +442,7 @@ int aie2_query_telemetry(struct amdxdna_dev_hdl
>> *ndev,
>> req.buf_size = buf_sz;
>> req.type = header->type;
>> - drm_clflush_virt_range(addr, size); /* device can access */
>> + drm_clflush_virt_range(addr, req.buf_size); /* device can access */
>> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
>> if (ret) {
>> XDNA_ERR(xdna, "Query telemetry failed, status %d", ret);
>> @@ -1186,7 +1186,7 @@ int aie2_query_app_health(struct
>> amdxdna_dev_hdl *ndev, u32 context_id,
>> req.context_id = context_id;
>> req.buf_size = buf_size;
>> - drm_clflush_virt_range(buf, sizeof(*report));
>> + drm_clflush_virt_range(buf, req.buf_size);
>> ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
>> if (ret) {
>> XDNA_ERR(xdna, "Get app health failed, ret %d status 0x%x",
>> ret, resp.status);
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2026-05-07 21:23 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-05-07 4:02 [PATCH V1] accel/amdxdna: Fix clflush buffer size Lizhi Hou
2026-05-07 16:55 ` Mario Limonciello
2026-05-07 21:23 ` Lizhi Hou
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox