[PATCH 10/16] drm/amdgpu: fix the VM fault while write at the top of the invisible vram

[Alex Deucher <alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>]

From: Huang Rui <ray.huang@amd.com>

Raven2 has a HW issue that it is unable to use the vram which is out of
MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the workaround that increase system
aperture high address to get rid of the VM fault and hardware hang.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 15 +++++++++++++--
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c  | 15 +++++++++++++--
 2 files changed, 26 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index ffd0ec9586d1..65f58ebcf835 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -73,8 +73,19 @@ static void gfxhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	/* Program the system aperture low logical page number. */
 	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 		     min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18);
-	WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-		     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
+
+	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
+		/*
+		 * Raven2 has a HW issue that it is unable to use the vram which
+		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+		 * workaround that increase system aperture high address (add 1)
+		 * to get rid of the VM fault and hardware hang.
+		 */
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			     (max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18) + 0x1);
+	else
+		WREG32_SOC15(GC, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
 
 	/* Set default page address. */
 	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index b121eb6a0ad4..2a126c6950c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -91,8 +91,19 @@ static void mmhub_v1_0_init_system_aperture_regs(struct amdgpu_device *adev)
 	/* Program the system aperture low logical page number. */
 	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_LOW_ADDR,
 		     min(adev->gmc.vram_start, adev->gmc.agp_start) >> 18);
-	WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
-		     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
+
+	if (adev->asic_type == CHIP_RAVEN && adev->rev_id >= 0x8)
+		/*
+		 * Raven2 has a HW issue that it is unable to use the vram which
+		 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+		 * workaround that increase system aperture high address (add 1)
+		 * to get rid of the VM fault and hardware hang.
+		 */
+		WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			     (max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18) + 0x1);
+	else
+		WREG32_SOC15(MMHUB, 0, mmMC_VM_SYSTEM_APERTURE_HIGH_ADDR,
+			     max(adev->gmc.vram_end, adev->gmc.agp_end) >> 18);
 
 	/* Set default page address. */
 	value = adev->vram_scratch.gpu_addr - adev->gmc.vram_start +
-- 
2.13.6

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx