[PATCH 4/4] drm/amdgpu: add reset_ras_error_count function for HDP

[Hawking Zhang]

HDP ras error counters are dirty ones after cold reboot
Read operation is needed to reset them to 0

Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   |  1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c |  1 -
 drivers/gpu/drm/amd/amdgpu/soc15.c    | 14 ++++++++++++++
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index a58b0cf9da51..b735e20888a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -595,6 +595,7 @@ struct amdgpu_asic_funcs {
 	/* invalidate hdp read cache */
 	void (*invalidate_hdp)(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring);
+	void (*reset_hdp_ras_error_count)(struct amdgpu_device *adev);
 	/* check if the asic needs a full reset of if soft reset will work */
 	bool (*need_full_reset)(struct amdgpu_device *adev);
 	/* initialize doorbell layout for specific asic*/
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index b746f26f933c..efd52bcf8785 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4149,7 +4149,6 @@ static const struct soc15_reg_entry gfx_v9_0_edc_counter_regs[] = {
    { SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0, 1, 16},
    { 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},
 };
 
 static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 4aa5b9c8e43b..6b717691d554 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -827,6 +827,15 @@ static bool soc15_need_full_reset(struct amdgpu_device *adev)
 	/* change this when we implement soft reset */
 	return true;
 }
+
+static void vega20_reset_hdp_ras_error_count(struct amdgpu_device *adev)
+{
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__HDP))
+		return;
+	/*read back hdp ras counter to reset it to 0 */
+	RREG32_SOC15(HDP, 0, mmHDP_EDC_CNT);
+}
+
 static void soc15_get_pcie_usage(struct amdgpu_device *adev, uint64_t *count0,
 				 uint64_t *count1)
 {
@@ -994,6 +1003,7 @@ static const struct amdgpu_asic_funcs vega20_asic_funcs =
 	.get_config_memsize = &soc15_get_config_memsize,
 	.flush_hdp = &soc15_flush_hdp,
 	.invalidate_hdp = &soc15_invalidate_hdp,
+	.reset_hdp_ras_error_count = &vega20_reset_hdp_ras_error_count,
 	.need_full_reset = &soc15_need_full_reset,
 	.init_doorbell_index = &vega20_doorbell_index_init,
 	.get_pcie_usage = &vega20_get_pcie_usage,
@@ -1239,6 +1249,10 @@ static int soc15_common_late_init(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_get_irq(adev);
 
+	if (adev->asic_funcs &&
+	    adev->asic_funcs->reset_hdp_ras_error_count)
+		adev->asic_funcs->reset_hdp_ras_error_count(adev);
+
 	if (adev->nbio.funcs->ras_late_init)
 		r = adev->nbio.funcs->ras_late_init(adev);
 
-- 
2.17.1