drm/amdgpu: read sdma edc counter to clear the counters

SDMA edc counter registers were added in gfx edc counters
array. When querying gfx error counter in that array, there
is no way to differentiate sdma instance number for different
asic and then results to NULL pointer access when trying to
read sdma register base address for instances greater
than 2 on Vega20.
In addition, this also results to wrong gfx error counters
since it actually added sdma edc counters.
Therefore, sdma edc counter registers should be separated
from gfx edc counter regsiter array and only get initialized
when driver tries to enable sdma ras.

Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index a5492e375f29ee7874aa31a3b2e8a45aad4f2cb2..89c04cfcfe127b2eb866824e6d966ff3faf95976 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4021,14 +4021,6 @@ static const struct soc15_reg_entry sec_ded_counter_registers[] = {
    { SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT), 0, 1, 2},
    { SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 0, 4, 6},
    { SOC15_REG_ENTRY(HDP, 0, mmHDP_EDC_CNT), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA0, 0, mmSDMA0_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA1, 0, mmSDMA1_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA2, 0, mmSDMA2_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA3, 0, mmSDMA3_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA4, 0, mmSDMA4_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA5, 0, mmSDMA5_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA6, 0, mmSDMA6_EDC_COUNTER), 0, 1, 1},
-   { SOC15_REG_ENTRY(SDMA7, 0, mmSDMA7_EDC_COUNTER), 0, 1, 1},
 };
 
 static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)
@@ -4092,7 +4084,6 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
                                                adev->gfx.config.max_sh_per_se;
        int sgpr_work_group_size = 5;
        int gpr_reg_size = compute_dim_x / 16 + 6;
-       int sec_ded_counter_reg_size = adev->sdma.num_instances + 34;
 
        /* only support when RAS is enabled */
        if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
@@ -4232,7 +4223,7 @@ static int gfx_v9_0_do_edc_gpr_workarounds(struct amdgpu_device *adev)
 
        /* read back registers to clear the counters */
        mutex_lock(&adev->grbm_idx_mutex);
-       for (i = 0; i < sec_ded_counter_reg_size; i++) {
+       for (i = 0; i < ARRAY_SIZE(sec_ded_counter_registers); i++) {
                for (j = 0; j < sec_ded_counter_registers[i].se_num; j++) {
                        for (k = 0; k < sec_ded_counter_registers[i].instance; k++) {
                                gfx_v9_0_select_se_sh(adev, j, 0x0, k);

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 1e0767e88d196b93d37a7694ec6c7bd8e342ad3f..ec9d7873ed42198c3fdd807f59b400032c553498 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1801,6 +1801,13 @@ static int sdma_v4_0_late_init(void *handle)
        struct ras_ih_if ih_info = {
                .cb = sdma_v4_0_process_ras_data_cb,
        };
+       int i;
+
+       /* read back edc counter registers to clear the counters */
+       if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
+               for (i = 0; i < adev->sdma.num_instances; i++)
+                       RREG32_SDMA(i, mmSDMA0_EDC_COUNTER);
+       }
 
        return adev->sdma.funcs->ras_late_init(adev, &ih_info);
 }