Use generic PCI reset for GPU reset if the user specifies
PCI reset as the reset mechanism. This should in general
only be used for validation.
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use generic PCI reset for GPU reset if the user specifies
PCI reset as the reset mechanism. This should in general
only be used for validation.
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This allows us to use generic PCI reset mechanisms (FLR, SBR) as
a reset mechanism to verify that the generic PCI reset mechanisms
are working properly.
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To achieve the best QoS for high priority compute jobs it is
required to limit waves on other compute pipes as well.
This patch will set min value in non high priority
mmSPI_WCL_PIPE_PERCENT_CS[0-3] registers to minimize the
impact of normal/low priority compute jobs over high priority
compute jobs.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why & How]
In order to get appropriate timing for registers which
read/write is vertical line sensitive, add new IRQ source variable.
This interrupt is triggered by specific vertical line,
Signed-off-by: Wayne Lin <Wayne.Lin@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Switch to smuio callbacks: use smuio v11_0_6 callbacks for
Sienna_cichlid and forward ASIC, use smuio v11_0 callbacks for the
other NV family ASIC.
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Enable DCS
V1: Enable Async DCS.
V2: Add the ppfeaturemask bit to enable from the modprobe parameter.
V3:
1. add the flag to skip APU support.
2. remove the hunk for workload selection since
it doesn't impact the function.
Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Enable gfx wave limiting for gfx jobs before pushing high priority
compute jobs so that high priority compute jobs gets more resources
to finish early.
v2: use ring priority instead of job priority.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Wave limiting can be use to load balance high priority
compute jobs along with gfx jobs. When enabled, this will reserve
~75% of waves for compute jobs.
We do not need this from gfx10 onwards because >=gfx10 has
asynchronous compute tunneling to replace wave limit requirement.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For high priority compute to work properly we need to enable
wave limiting on gfx pipe. Wave limiting is done through writing
into mmSPI_WCL_PIPE_PERCENT_GFX register. Enable only one high
priority compute queue to avoid race condition between multiple
high priority compute queues writing that register simultaneously.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch consist of below related changes:
1 Rename ring->priority to ring->hw_prio.
2 Assign correct hardware ring priority.
3 Remove ring->priority_mutex as ring priority remains unchanged
after initialization.
4 Remove unused ring->num_jobs.
v3: remove ring->num_jobs.
v2: remove ring->priority_mutex.
Fixes: 33abcb1f5a ("drm/amdgpu: set compute queue priority at mqd_init")
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Some newer APUs can scanout directly from GTT, that saves us from
allocating another bounce buffer in VRAM and enables freesync in such
configurations.
Without this patch creating a framebuffer from the imported BO will
fail and userspace will fall back to a copy.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Shashank Sharma <shashank.sharma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For Vangogh:
The offset of the CGTS_TCC_DISABLE is 0x5006 by calculation.
The offset of the CGTS_USER_TCC_DISABLE is 0x5007 by calculation.
Signed-off-by: chen gong <curry.gong@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Some newer APUs can scanout directly from GTT, that saves us from
allocating another bounce buffer in VRAM and enables freesync in such
configurations.
Without this patch creating a framebuffer from the imported BO will
fail and userspace will fall back to a copy.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Shashank Sharma <shashank.sharma@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For Vangogh:
The offset of the CGTS_TCC_DISABLE is 0x5006 by calculation.
The offset of the CGTS_USER_TCC_DISABLE is 0x5007 by calculation.
Signed-off-by: chen gong <curry.gong@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Enable 1:1 mapping between VRAM of a DRM node and a scatterlist node
[How]
Ensure construction of DRM node to not exceed specified limit
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Ramesh Errabolu <Ramesh.Errabolu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We cannot modify initial_domain every time while the retry starts. That
will cause the busy waiting that unable to switch to GTT while the vram
is not enough.
Fixes: f8aab60422 ("drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs")
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The purpose of this patch is to add a missing device ID for Sienna Cichlid.
The missing ID "0x73A1" is now added to the "amdgpu_drv.c" file.
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently the ! operator is incorrectly being used to flip bits on
mask values. Fix this by using the bit-wise ~ operator instead.
Addresses-Coverity: ("Logical vs. bitwise operator")
Fixes: 3c9a7b7d6e ("drm/amdgpu: update mmhub mgcg&ls for mmhub_v2_3")
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
when vram lost happened in guest, try to write vram can lead to
kernel stuck.
[How]
When the readback data is invalid, don't do write work, directly
reschedule a new work.
Signed-off-by: Jingwen Chen <Jingwen.Chen2@amd.com>
Reviewed-by: Monk Liu<monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix a racing issue when jobs on 2 rings timeout simultaneously.
If 2 rings timed out at the same time, the
amdgpu_device_gpu_recover will be reentered. Then the
adev->gmc.xgmi.head will be grabbed by 2 local linked list,
which may cause wild pointer issue in iterating.
lock the device earily to prevent the node be added to 2
different lists.
also increase karma for the skipped job since the job is also
timed out and should be guilty.
Signed-off-by: Horace Chen <horace.chen@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Starting from vangogh, the ATCL2 and DAGB0 registers relative
to mgcg/ls has changed.
For MGCG:
Replace mmMM_ATC_L2_MISC_CG with mmMM_ATC_L2_CGTT_CLK_CTRL.
For MGLS:
Replace mmMM_ATC_L2_MISC_CG with mmMM_ATC_L2_CGTT_CLK_CTRL.
Add DAGB0_(WR/RD)_CGTT_CLK_CTRL registers.
Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
GCR_GENERAL_CNTL is defined differently in gc_10_1_0_offset.h and
gc_10_3_0_offset.h. Update GCR_GENERAL_CNTL for Vangogh.
Signed-off-by: Jinzhou Su <Jinzhou.Su@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Starting from vangogh, the ATCL2 and DAGB0 registers relative
to mgcg/ls has changed.
For MGCG:
Replace mmMM_ATC_L2_MISC_CG with mmMM_ATC_L2_CGTT_CLK_CTRL.
For MGLS:
Replace mmMM_ATC_L2_MISC_CG with mmMM_ATC_L2_CGTT_CLK_CTRL.
Add DAGB0_(WR/RD)_CGTT_CLK_CTRL registers.
Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Driver should enable the CGPG feature for RLC in safe mode to
prevent any misalignment or conflict in middle of any power
feature entry/exit sequence.
Achieved by setting RLC_PG_CNTL.GFX_POWER_GATING_ENABLE = 0x1,
and RLC_PG_DELAY_3.CGCG_ACTIVE_BEFORE_CGPG to the desired CGPG
hysteresis value in refclk count.
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Jinzhou Su <Jinzhou.Su@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
GCR_GENERAL_CNTL is defined differently in gc_10_1_0_offset.h and
gc_10_3_0_offset.h. Update GCR_GENERAL_CNTL for Vangogh.
Signed-off-by: Jinzhou Su <Jinzhou.Su@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
