drm/amdgpu: Add check to prevent IH overflow

[ Upstream commit e4180c4253f3f2da09047f5139959227f5cf1173 ]

Similar to commit <b82175750131>("drm/amdgpu: fix IH overflow on Vega10 v2").
When an ring buffer overflow happens the appropriate bit is set in the WPTR
register which is also written back to memory. But clearing the bit in the
WPTR doesn't trigger another memory writeback.

So what can happen is that we end up processing the buffer overflow over and
over again because the bit is never cleared. Resulting in a random system
lockup because of an infinite loop in an interrupt handler.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Defang Bo <bodefang@126.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

3 files changed, 71 insertions, 39 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/cz_ih.c b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
index 1dca0cabc326..13520d173296 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_ih.c
@@ -193,19 +193,30 @@ static u32 cz_ih_get_wptr(struct amdgpu_device *adev,
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+
+out:
 	return (wptr & ih->ptr_mask);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
index a13dd9a51149..7d165f024f07 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_ih.c
@@ -193,19 +193,29 @@ static u32 iceland_ih_get_wptr(struct amdgpu_device *adev,
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			 wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+
+out:
 	return (wptr & ih->ptr_mask);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
index e40140bf6699..db0a3bda13fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_ih.c
@@ -195,19 +195,30 @@ static u32 tonga_ih_get_wptr(struct amdgpu_device *adev,
 
 	wptr = le32_to_cpu(*ih->wptr_cpu);
 
-	if (REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW)) {
-		wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
-		/* When a ring buffer overflow happen start parsing interrupt
-		 * from the last not overwritten vector (wptr + 16). Hopefully
-		 * this should allow us to catchup.
-		 */
-		dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
-			 wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
-		ih->rptr = (wptr + 16) & ih->ptr_mask;
-		tmp = RREG32(mmIH_RB_CNTL);
-		tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
-		WREG32(mmIH_RB_CNTL, tmp);
-	}
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	/* Double check that the overflow wasn't already cleared. */
+	wptr = RREG32(mmIH_RB_WPTR);
+
+	if (!REG_GET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW))
+		goto out;
+
+	wptr = REG_SET_FIELD(wptr, IH_RB_WPTR, RB_OVERFLOW, 0);
+
+	/* When a ring buffer overflow happen start parsing interrupt
+	 * from the last not overwritten vector (wptr + 16). Hopefully
+	 * this should allow us to catchup.
+	 */
+
+	dev_warn(adev->dev, "IH ring buffer overflow (0x%08X, 0x%08X, 0x%08X)\n",
+		wptr, ih->rptr, (wptr + 16) & ih->ptr_mask);
+	ih->rptr = (wptr + 16) & ih->ptr_mask;
+	tmp = RREG32(mmIH_RB_CNTL);
+	tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
+	WREG32(mmIH_RB_CNTL, tmp);
+
+out:
 	return (wptr & ih->ptr_mask);
 }