drm/amdgpu: Default disable GDS for compute+gfx

Units in the GDS block default to allowing all VMIDs access to all
entries. Disable shader access to the GDS, GWS, and OA blocks from all
compute and gfx VMIDs by default. For compute, HWS firmware will set
up the access bits for the appropriate VMID when a compute queue
requires access to these blocks.
The driver will handle enabling access on-demand for graphics VMIDs.

Leaving VMID0 with full access because otherwise HWS cannot save or
restore values during task switch.

v2: Fixed code and comment styling.
Signed-off-by: Joseph Greathouse <Joseph.Greathouse@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c

@@ -1516,17 +1516,27 @@ static void gfx_v10_0_init_compute_vmid(struct amdgpu_device *adev)
 	}
 	nv_grbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+}
 
-	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
-	   acccess. These should be enabled by FW for target VMIDs. */
-	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0);
+static void gfx_v10_0_init_gds_vmid(struct amdgpu_device *adev)
+{
+	int vmid;
+
+	/*
+	 * Initialize all compute and user-gfx VMIDs to have no GDS, GWS, or OA
+	 * access. Compute VMIDs should be enabled by FW for target VMIDs,
+	 * the driver can enable them for graphics. VMID0 should maintain
+	 * access so that HWS firmware can save/restore entries.
+	 */
+	for (vmid = 1; vmid < 16; vmid++) {
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, vmid, 0);
 	}
 }
 
+
 static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 {
 	int i, j, k;
@@ -1629,6 +1639,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	gfx_v10_0_init_compute_vmid(adev);
+	gfx_v10_0_init_gds_vmid(adev);
 
 }
 

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -1879,14 +1879,23 @@ static void gfx_v7_0_init_compute_vmid(struct amdgpu_device *adev)
 	}
 	cik_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+}
 
-	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
-	   acccess. These should be enabled by FW for target VMIDs. */
-	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
-		WREG32(amdgpu_gds_reg_offset[i].mem_base, 0);
-		WREG32(amdgpu_gds_reg_offset[i].mem_size, 0);
-		WREG32(amdgpu_gds_reg_offset[i].gws, 0);
-		WREG32(amdgpu_gds_reg_offset[i].oa, 0);
+static void gfx_v7_0_init_gds_vmid(struct amdgpu_device *adev)
+{
+	int vmid;
+
+	/*
+	 * Initialize all compute and user-gfx VMIDs to have no GDS, GWS, or OA
+	 * access. Compute VMIDs should be enabled by FW for target VMIDs,
+	 * the driver can enable them for graphics. VMID0 should maintain
+	 * access so that HWS firmware can save/restore entries.
+	 */
+	for (vmid = 1; vmid < 16; vmid++) {
+		WREG32(amdgpu_gds_reg_offset[vmid].mem_base, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].mem_size, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].gws, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].oa, 0);
 	}
 }
 
@@ -1968,6 +1977,7 @@ static void gfx_v7_0_constants_init(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	gfx_v7_0_init_compute_vmid(adev);
+	gfx_v7_0_init_gds_vmid(adev);
 
 	WREG32(mmSX_DEBUG_1, 0x20);
 

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -3706,14 +3706,23 @@ static void gfx_v8_0_init_compute_vmid(struct amdgpu_device *adev)
 	}
 	vi_srbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+}
 
-	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
-	   acccess. These should be enabled by FW for target VMIDs. */
-	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
-		WREG32(amdgpu_gds_reg_offset[i].mem_base, 0);
-		WREG32(amdgpu_gds_reg_offset[i].mem_size, 0);
-		WREG32(amdgpu_gds_reg_offset[i].gws, 0);
-		WREG32(amdgpu_gds_reg_offset[i].oa, 0);
+static void gfx_v8_0_init_gds_vmid(struct amdgpu_device *adev)
+{
+	int vmid;
+
+	/*
+	 * Initialize all compute and user-gfx VMIDs to have no GDS, GWS, or OA
+	 * access. Compute VMIDs should be enabled by FW for target VMIDs,
+	 * the driver can enable them for graphics. VMID0 should maintain
+	 * access so that HWS firmware can save/restore entries.
+	 */
+	for (vmid = 1; vmid < 16; vmid++) {
+		WREG32(amdgpu_gds_reg_offset[vmid].mem_base, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].mem_size, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].gws, 0);
+		WREG32(amdgpu_gds_reg_offset[vmid].oa, 0);
 	}
 }
 
@@ -3783,6 +3792,7 @@ static void gfx_v8_0_constants_init(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	gfx_v8_0_init_compute_vmid(adev);
+	gfx_v8_0_init_gds_vmid(adev);
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	/*

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -2029,14 +2029,23 @@ static void gfx_v9_0_init_compute_vmid(struct amdgpu_device *adev)
 	}
 	soc15_grbm_select(adev, 0, 0, 0, 0);
 	mutex_unlock(&adev->srbm_mutex);
+}
 
-	/* Initialize all compute VMIDs to have no GDS, GWS, or OA
-	   acccess. These should be enabled by FW for target VMIDs. */
-	for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0);
-		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0);
+static void gfx_v9_0_init_gds_vmid(struct amdgpu_device *adev)
+{
+	int vmid;
+
+	/*
+	 * Initialize all compute and user-gfx VMIDs to have no GDS, GWS, or OA
+	 * access. Compute VMIDs should be enabled by FW for target VMIDs,
+	 * the driver can enable them for graphics. VMID0 should maintain
+	 * access so that HWS firmware can save/restore entries.
+	 */
+	for (vmid = 1; vmid < 16; vmid++) {
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, vmid, 0);
+		WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, vmid, 0);
 	}
 }
 
@@ -2084,6 +2093,7 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
 	mutex_unlock(&adev->srbm_mutex);
 
 	gfx_v9_0_init_compute_vmid(adev);
+	gfx_v9_0_init_gds_vmid(adev);
 }
 
 static void gfx_v9_0_wait_for_rlc_serdes(struct amdgpu_device *adev)