- Aug 05, 2024
-
-
Alex Deucher authored
Protect the MMIO access with safe mode. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Protect the MMIO access with safe mode. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Protect the MMIO access with safe mode. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Protect the MMIO access with safe mode. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Protect the MMIO access with safe mode. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rather than open coding it for the queue reset. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rather than open coding it for the queue reset. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rather than open coding it for the queue reset. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rather than open coding it for the queue reset. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rather than open coding it for the queue reset. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callback for gfx. Untested. v2: fix operator precendence (kernel test robot) Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callback for gfx. Untested. v2: fix operator precendence (kernel test robot) Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callback for gfx. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
It's not supported under SR-IOV at the moment. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
It's not supported under SR-IOV at the moment. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
It's not supported under SR-IOV at the moment. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
It's not supported under SR-IOV at the moment. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Implement queue reset for graphic and compute queue. v2: use amdgpu_gfx_rlc funcs to enter/exit safe mode. v3: use gfx_v11_0_request_gfx_index_mutex() Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
It will be used by the queue reset code. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
This will be used in more places in the future so add a mutex. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Need to enter safe mode before touching GC MMIO. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
The reset_queue api could be used from kfd or kgd. v2: add use_mmio parameter for mes_reset_legacy_queue. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Add me/pipe/queue parameters for queue reset input. v2: fix build (Alex) Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Using mmio to do queue reset. Enter safe mode before writing mmio registers. v2: set register instance offset according to xcc id. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Using mmio to do queue reset. Enter safe mode when writing registers. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Add reset_hw_queue in kiq_pm4_funcs callbacks. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Since the MES FW resets kernel compute queue always failed, this may caused by the KIQ failed to process unmap KCQ. So, before MES FW work properly that will fallback to driver executes dequeue and resets SPI directly. Besides, rework the ring reset function and make the busy ring type reset in each function respectively. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callbacks for gfx and compute. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. v2: fix KIQ locking (Alex) v3: fix KIQ locking harder Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Kiq command unmap_queues only does the dequeueing action. We have to map the queue back with clean mqd. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callback for compute. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. v2: fix KIQ locking (Alex) v3: fix KIQ locking harder Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Kiq command unmap_queues only does the dequeueing action. We have to map the queue back with clean mqd. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callback for compute. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
To match other GFX IPs. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. v2: fix KIQ locking (Alex) v3: fix KIQ locking harder (Jessie) Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
Kiq command unmap_queues only does the dequeueing action. We have to map the queue back with clean mqd. v2: fix up error handling (Alex) Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Add ring reset callbacks for gfx and compute. v2: fix gfx handling v3: wait for KIQ to complete Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Jiadong Zhu authored
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. Signed-off-by:
Jiadong Zhu <Jiadong.Zhu@amd.com> Reviewed-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Alex Deucher authored
Rename to gfx_v11_0_kgq_init_queue() to better align with the other naming in the file. Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-