drm/amdgpu/gfx9: Fix Ring and IB test fail after mode2

For Renior APU with gfx9, in some test scenarios with disabling
ring_reset, like accessing an unmapped invalid address, it can
trigger a gpu job timeout event, then driver uses Mode2 reset
to reset GPU, but after Mode2 compute Ring test and IB test fail
randomly. It because the HQDs of MECs are always active before or
after Mode2, that causes MECs use stale HQDs when MECs are unhalted
before driver restore MQDs, and causes CPC and CPF are still stuck
after Mode2, then causes compute Ring and IB tests fail.

So, add sequences to deactivate HQDs of MECs in suspend IP function
of the resetting process.

v2: Move all sequences into a new function gfx_v9_0_cp_mode2_clear_state (Ray Huang)
    To check reset Mode2 method in the if condition (Ray Huang)
v3: Move all sequences before Mode2 instead of after Mode2 (Timur Kristóf)
v4: Call amdgpu_gfx_rlc_enter/exit_safe_mode int the begin and end of
    gfx_v9_0_deactivate_kcq_hqd (Alex Deucher)

Signed-off-by: Jiqian Chen <Jiqian.Chen@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c3988a7ad4799514447294f04f063b422e0551df)
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 47721d0c37812b3a9f4205dea09aaab3938eafbe..81a759a9872581d988709197205abf4afab26f97 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4071,6 +4071,41 @@ err_priv_inst:
        return r;
 }
 
+static void gfx_v9_0_deactivate_kcq_hqd(struct amdgpu_device *adev)
+{
+       amdgpu_gfx_rlc_enter_safe_mode(adev, 0);
+       for (int i = 0; i < adev->gfx.num_compute_rings; i++) {
+               u32 tmp;
+               struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
+
+               mutex_lock(&adev->srbm_mutex);
+               soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0, 0);
+               tmp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
+               /* disable the queue if it's active */
+               if (tmp & CP_HQD_ACTIVE__ACTIVE_MASK) {
+                       int j;
+
+                       WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 1);
+                       for (j = 0; j < adev->usec_timeout; j++) {
+                               tmp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE);
+                               if (!(tmp & CP_HQD_ACTIVE__ACTIVE_MASK))
+                                       break;
+                               udelay(1);
+                       }
+                       if (j == AMDGPU_MAX_USEC_TIMEOUT) {
+                               DRM_DEBUG("comp_%u_%u_%u dequeue request failed.\n",
+                                                       ring->me, ring->pipe, ring->queue);
+                               /* Manual disable if dequeue request times out */
+                               WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, 0);
+                       }
+                       WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 0);
+               }
+               soc15_grbm_select(adev, 0, 0, 0, 0, 0);
+               mutex_unlock(&adev->srbm_mutex);
+       }
+       amdgpu_gfx_rlc_exit_safe_mode(adev, 0);
+}
+
 static int gfx_v9_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
        struct amdgpu_device *adev = ip_block->adev;
@@ -4095,6 +4130,10 @@ static int gfx_v9_0_hw_fini(struct amdgpu_ip_block *ip_block)
                return 0;
        }
 
+       if ((adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev) &&
+               amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_MODE2)
+               gfx_v9_0_deactivate_kcq_hqd(adev);
+
        /* Use deinitialize sequence from CAIL when unbinding device from driver,
         * otherwise KIQ is hanging when binding back
         */