drm/amdgpu: bypass some cleanup work after err_event_athub (v2)

PSP lost connection when err_event_athub occurs. These cleanup work can be
skipped in BACO reset.

v2: squash in missing include (Alex)

Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

4 files changed, 30 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c03089503b0f..d36d2b093539 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2271,6 +2271,12 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		/* displays are handled in phase1 */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
 			continue;
+		/* PSP lost connection when err_event_athub occurs */
+		if (amdgpu_ras_intr_triggered() &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
+			adev->ip_blocks[i].status.hw = false;
+			continue;
+		}
 		/* XXX handle errors */
 		r = adev->ip_blocks[i].version->funcs->suspend(adev);
 		/* XXX handle errors */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index fd7a73f4fa70..bbe9ac7e843f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -34,6 +34,8 @@
 #include "psp_v11_0.h"
 #include "psp_v12_0.h"
 
+#include "amdgpu_ras.h"
+
 static void psp_set_funcs(struct amdgpu_device *adev);
 
 static int psp_early_init(void *handle)
@@ -167,6 +169,13 @@ psp_cmd_submit_buf(struct psp_context *psp,
 	while (*((unsigned int *)psp->fence_buf) != index) {
 		if (--timeout == 0)
 			break;
+		/*
+		 * Shouldn't wait for timeout when err_event_athub occurs,
+		 * because gpu reset thread triggered and lock resource should
+		 * be released for psp resume sequence.
+		 */
+		if (amdgpu_ras_intr_triggered())
+			break;
 		msleep(1);
 		amdgpu_asic_invalidate_hdp(psp->adev, NULL);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 796326b36e00..dab90c280476 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -558,15 +558,17 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!(!!enable ^ !!amdgpu_ras_is_feature_enabled(adev, head)))
 		return 0;
 
-	ret = psp_ras_enable_features(&adev->psp, &info, enable);
-	if (ret) {
-		DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
-				enable ? "enable":"disable",
-				ras_block_str(head->block),
-				ret);
-		if (ret == TA_RAS_STATUS__RESET_NEEDED)
-			return -EAGAIN;
-		return -EINVAL;
+	if (!amdgpu_ras_intr_triggered()) {
+		ret = psp_ras_enable_features(&adev->psp, &info, enable);
+		if (ret) {
+			DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
+					enable ? "enable":"disable",
+					ras_block_str(head->block),
+					ret);
+			if (ret == TA_RAS_STATUS__RESET_NEEDED)
+				return -EAGAIN;
+			return -EINVAL;
+		}
 	}
 
 	/* setup the obj */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 088c6a734a1a..d694be9a8c39 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3736,8 +3736,10 @@ static int gfx_v9_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
-	/* disable KCQ to avoid CPC touch memory not valid anymore */
-	gfx_v9_0_kcq_disable(adev);
+	/* DF freeze and kcq disable will fail */
+	if (!amdgpu_ras_intr_triggered())
+		/* disable KCQ to avoid CPC touch memory not valid anymore */
+		gfx_v9_0_kcq_disable(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v9_0_cp_gfx_enable(adev, false);