drm/amdgpu: Add Runtime Bad Page message definitions for VFs
Subsystems (2)
PATCH 1/4 drm/amdgpu: Add Runtime Bad Page message definitions for VFs
Currently VFs rely on poison consumption interrupt from HW to kick off the bad page retirement process. Part of this process includes a VF reset.
This patch adds the following:
1) Host Bad Pages notification message.
2) Guest request bad pages message.
When combined, VFs are able to reserve the pages early, and potentially avoid future poison consumption that will disrupt user services from consequent FLR.
--- drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +3 -0
@@ -331,6 +331,7 @@ enum amd_sriov_mailbox_request_message {MB_REQ_MSG_RAS_POISON =202 ,MB_REQ_RAS_ERROR_COUNT =203 ,MB_REQ_RAS_CPER_DUMP =204 , + MB_REQ_RAS_BAD_PAGES = 205, };/* mailbox message send from host to guest */
@@ -348,6 +349,8 @@ enum amd_sriov_mailbox_response_message {MB_RES_MSG_GPU_RMA =10 ,MB_RES_MSG_RAS_ERROR_COUNT_READY =11 ,MB_REQ_RAS_CPER_DUMP_READY =14 , +MB_RES_MSG_RAS_BAD_PAGES_READY =15 , +MB_RES_MSG_RAS_BAD_PAGES_NOTIFICATION =16 , MB_RES_MSG_TEXT_MESSAGE = 255 };
Signature · 1 line
2.34.1
[AMD Official Use Only - AMD Internal Distribution Only]
Looks good.
Thanks,
Shravan
-----Original Message-----
From: Pan, Ellen <[email protected]>
Sent: Tuesday, April 29, 2025 5:40 PM
To: [email protected]
Cc: Skvortsov, Victor <[email protected]>; Rehman, Ahmad <[email protected]>; Chan, Hing Pong <[email protected]>; Gande, Shravan kumar <[email protected]>; Luo, Zhigang <[email protected]>; Pan, Ellen <[email protected]>; Skvortsov, Victor <[email protected]>
Subject: [PATCH 1/4] drm/amdgpu: Add Runtime Bad Page message definitions for VFs
Currently VFs rely on poison consumption interrupt from HW to kick off the bad page retirement process. Part of this process includes a VF reset.
This patch adds the following:
1) Host Bad Pages notification message.
2) Guest request bad pages message.
When combined, VFs are able to reserve the pages early, and potentially avoid future poison consumption that will disrupt user services from consequent FLR.
--- drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +1 -0
@@ -331,6 +331,7 @@ enum amd_sriov_mailbox_request_message { MB_REQ_MSG_RAS_POISON = 202, MB_REQ_RAS_ERROR_COUNT = 203, MB_REQ_RAS_CPER_DUMP = 204, + MB_REQ_RAS_BAD_PAGES = 205, }; /* mailbox message send from host to guest */ @@ -348,6 +349,8 @@ enum amd_sriov_mailbox_response_message {
MB_RES_MSG_GPU_RMA = 10,
MB_RES_MSG_RAS_ERROR_COUNT_READY = 11,
MB_REQ_RAS_CPER_DUMP_READY = 14,
+ MB_RES_MSG_RAS_BAD_PAGES_READY = 15,
+ MB_RES_MSG_RAS_BAD_PAGES_NOTIFICATION = 16,
MB_RES_MSG_TEXT_MESSAGE = 255};
--
2.34.1