drm/radeon: properly program gart on rv740, juniper, cypress, barts, hemlock

Need to program an additional VM register.  This doesn't not currently
cause any problems, but allows us to program the proper backend
map in a subsequent patch which should improve performance on these
asics.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/evergreen.c

@@ -1029,6 +1029,11 @@ int evergreen_pcie_gart_enable(struct radeon_device *rdev)
 		WREG32(MC_VM_MD_L1_TLB0_CNTL, tmp);
 		WREG32(MC_VM_MD_L1_TLB1_CNTL, tmp);
 		WREG32(MC_VM_MD_L1_TLB2_CNTL, tmp);
+		if ((rdev->family == CHIP_JUNIPER) ||
+		    (rdev->family == CHIP_CYPRESS) ||
+		    (rdev->family == CHIP_HEMLOCK) ||
+		    (rdev->family == CHIP_BARTS))
+			WREG32(MC_VM_MD_L1_TLB3_CNTL, tmp);
 	}
 	WREG32(MC_VM_MB_L1_TLB0_CNTL, tmp);
 	WREG32(MC_VM_MB_L1_TLB1_CNTL, tmp);

drivers/gpu/drm/radeon/evergreend.h

@@ -452,6 +452,7 @@
 #define	MC_VM_MD_L1_TLB0_CNTL				0x2654
 #define	MC_VM_MD_L1_TLB1_CNTL				0x2658
 #define	MC_VM_MD_L1_TLB2_CNTL				0x265C
+#define	MC_VM_MD_L1_TLB3_CNTL				0x2698
 
 #define	FUS_MC_VM_MD_L1_TLB0_CNTL			0x265C
 #define	FUS_MC_VM_MD_L1_TLB1_CNTL			0x2660

drivers/gpu/drm/radeon/rv770.c

@@ -151,6 +151,8 @@ int rv770_pcie_gart_enable(struct radeon_device *rdev)
 	WREG32(MC_VM_MD_L1_TLB0_CNTL, tmp);
 	WREG32(MC_VM_MD_L1_TLB1_CNTL, tmp);
 	WREG32(MC_VM_MD_L1_TLB2_CNTL, tmp);
+	if (rdev->family == CHIP_RV740)
+		WREG32(MC_VM_MD_L1_TLB3_CNTL, tmp);
 	WREG32(MC_VM_MB_L1_TLB0_CNTL, tmp);
 	WREG32(MC_VM_MB_L1_TLB1_CNTL, tmp);
 	WREG32(MC_VM_MB_L1_TLB2_CNTL, tmp);

drivers/gpu/drm/radeon/rv770d.h

@@ -174,6 +174,7 @@
 #define	MC_VM_MD_L1_TLB0_CNTL				0x2654
 #define	MC_VM_MD_L1_TLB1_CNTL				0x2658
 #define	MC_VM_MD_L1_TLB2_CNTL				0x265C
+#define	MC_VM_MD_L1_TLB3_CNTL				0x2698
 #define	MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR		0x203C
 #define	MC_VM_SYSTEM_APERTURE_HIGH_ADDR			0x2038
 #define	MC_VM_SYSTEM_APERTURE_LOW_ADDR			0x2034