- 24 May, 2017 40 commits
-
-
Xiangliang Yu authored
If psp version doesn't match asd version, asd loading will be failed. Add workaround to bypass it for sriov. Signed-off-by:
Daniel Wang <Daniel.Wang2@amd.com> Signed-off-by:
Xiangliang Yu <Xiangliang.Yu@amd.com> Reviewed-by:
Monk Liu <Monk.Liu@amd.com> Signed-off-by:
Alex Deucher <alexander.deucher@amd.com>
-
Trigger Huang authored
On vega10, some hw finish operations should not be applied in SR-IOV case. This works as workaround to fix multi-VFs reboot/shutdown issues. Signed-off-by:
Trigger Huang <trigger.huang@amd.com> Reviewed-by:
-
Monk Liu authored
1,this way we make those routines compatible with the sequence requirment for both Tonga and Vega10 2,ignore PSP hw init when doing TDR, because for SR-IOV device the ucode won't get lost after VF FLR, so no need to invoke PSP doing the ucode reloading again. v2: squash in ARRAY_SIZE fix Signed-off-by:
-
Monk Liu authored
if sriov gpu reset is invoked by job timeout, it is run in a global work-queue which is very slow and better not call msleep ortherwise it takes long time to get back CPU. so make below changes: 1: Change msleep 1 to mdelay 5 2: Ignore the ack fail from pf after time out, because VF FLR will clear ack, sometime VF FLR is done prior to the beginning of poll_ack so we can ignore this ack TODO: Put job_timedout (and the following gpu reset) in a driver thread, instead of the global work_struct. Signed-off-by:
-
Monk Liu authored
Signed-off-by:
-
Monk Liu authored
this is to prevent fence forever waiting if FLR occured during register accessing. v2: use define instead of hardcode for the timeout msec Signed-off-by:
Christian König <christian.koenig@amd.com> Signed-off-by:
-
Alex Deucher authored
We need to make sure the various init sequences submitted to KIQ complete before testing the rings. Reviewed-by:
-
Alex Deucher authored
Rather than magic numbers. Reviewed-by:
-
Alex Deucher authored
Will be used in subsequent commits rather rather than magic numbers. Reviewed-by:
-
Alex Deucher authored
To be consistent with gfx8. Reviewed-by:
-
Alex Deucher authored
And properly synchronize them with the master during queue init. Reviewed-by:
-
Shaoyun Liu authored
The usage of kiq should not depend on the virtualization. Signed-off-by:
Shaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by:
Andres Rodriquez <andresx7@gmail.com> Signed-off-by:
-
Chunming Zhou authored
Interface to reserve a vmid for a specific process to add in shader debugging that requries a fixed vmid. Signed-off-by:
Chunming Zhou <David1.Zhou@amd.com> Reviewed-by:
Junwei Zhang <Jerry.Zhang@amd.com> Reviewed-by:
-
Chunming Zhou authored
Implement the vmid reservation. v2: move sync waiting only when flush needs v3: fix racy v4: peek fence instead of get fence, and fix potential context starved. Signed-off-by:
-
Chunming Zhou authored
Limit reserved vmids to 1 to avoid taking too many out of commission and starving the system. v2: move #define to amdgpu_vm.h v3: move reserved vmid counter to id_manager, and increase counter before allocating vmid v4: rename to reserved_vmid_num Signed-off-by:
-
Chunming Zhou authored
add reserve/unreserve vmid funtions. Used to reserve vmids for certain shader debugging functionality that required a fixed vmid for the life of the debug. v3: only reserve vmid from gfxhub v4: fix racy condition Signed-off-by:
-
Chunming Zhou authored
v2: rename dedicated_vmid to reserved_vmid Signed-off-by:
-
Chunming Zhou authored
It will be used for reserving vmid for shader debugging that requires a fixed vmid. v2: fix warning (Alex) Signed-off-by:
-
Trigger Huang authored
Support for MCBP/Virtualization in combination with chained IBs is formal released on firmware feature version #46. So enable it according to firmware feature version, otherwise, world switch will hang. Signed-off-by:
-
Rex Zhu authored
Bug: SWDEV-117987: Always on CU mask broken for gfx7+ Signed-off-by:
Rex Zhu <Rex.Zhu@amd.com> Acked-by:
-
Rex Zhu authored
Signed-off-by:
-
Xiangliang Yu authored
Change place of virt_init_setting function so that can cover the cg and pg flags configuration. Signed-off-by:
-
Xiangliang Yu authored
GPU hypervisor cover all settings of CG and PG, so guest doesn't need to do anything. Bypass it. Signed-off-by:
Frank Min <Frank.Min@amd.com> Signed-off-by:
-
Christian König authored
Only per family registers are still used. Signed-off-by:
-
Christian König authored
I couldn't figure out what this was original good for, but we don't use it any more. Signed-off-by:
-
Rex Zhu authored
Signed-off-by:
-
Rex Zhu authored
Signed-off-by:
-
Xiaojie Yuan authored
Signed-off-by:
Xiaojie Yuan <Xiaojie.Yuan@amd.com> Reviewed-by:
Edward O'Callaghan <funfunctor@folklore1984.net> Reviewed-by:
-
Xiaojie Yuan authored
v2: refine dce_v6_0_audio_endpt_wreg() and unify inconsistent method names v3: fix num_pins for tahiti, pitcairn, verde and oland Signed-off-by:
-
Alex Deucher authored
I'm not sure if the order matters, but it seems like it makes more sense to set this after the range is programmed. v2: rebase (Alex) Signed-off-by: -
Rex Zhu authored
add set_doorbell functions for mec and cpg. Signed-off-by:
-
Alex Deucher authored
This could be used in Andres' priority scheduling patch as well. Reviewed-by:
-
Alex Deucher authored
Even if we disable clockgating, we still need to make sure the cp/rlc interrupts are enabled for powergating which might still be enabled. Acked-by:
-
Alex Deucher authored
Even if we disable clockgating, we still need to make sure the cp/rlc interrupts are enabled for powergating which might still be enabled. Acked-by:
-
Alex Deucher authored
It's global, not queue specific, so move it out of the kiq register init function. Tested-and-Reviewed-by:
-
Alex Deucher authored
No need to reset the wptr and clear the rings. The UNMAP_QUEUES packet writes the current MQD state back the MQD on suspend, so there is no need to reset it as well. Signed-off-by: -
Alex Deucher authored
Use the UNMAP_QUEUES packet to have the KIQ properly disable them. Reviewed-by:
-
Alex Deucher authored
Rather than open coding them. Reviewed-by:
-
Alex Deucher authored
As the KCQ setup. This way we only have to wait once for the entire MEC. Reviewed-by:
-
Alex Deucher authored
Rather than waiting for each queue. Reviewed-by:
-
