drm/radeon: Writeback endian fixes

The writeback ring pointer and IH ring pointer are read using le32_to_cpu
so we do not want the chip to byteswap them on big-endian.

We still want to byteswap the ring itself and the IBs, so we don't touch
that but we remove setting of the byteswap bits in CP_RB_RPTR_ADDR and
IH_CNTL.

In general, for things like that where we control all the accessors easily,
we are better off doing the swap in SW rather than HW. Paradoxally, it does
keep the code closer to x86 and avoid using poorly tested HW features.

I also changed the use of RADEON_ to R600_ in a couple of cases to be more
consistent with the surrounding code.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Michel Dänzer <michel@daenzer.net>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/evergreen.c

@@ -1382,9 +1382,6 @@ int evergreen_cp_resume(struct radeon_device *rdev)
 
 	/* set the wb address wether it's enabled or not */
 	WREG32(CP_RB_RPTR_ADDR,
-#ifdef __BIG_ENDIAN
-	       RB_RPTR_SWAP(2) |
-#endif
 	       ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
 	WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
 	WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);

drivers/gpu/drm/radeon/r600.c

@@ -2213,9 +2213,6 @@ int r600_cp_resume(struct radeon_device *rdev)
 
 	/* set the wb address whether it's enabled or not */
 	WREG32(CP_RB_RPTR_ADDR,
-#ifdef __BIG_ENDIAN
-	       RB_RPTR_SWAP(2) |
-#endif
 	       ((rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC));
 	WREG32(CP_RB_RPTR_ADDR_HI, upper_32_bits(rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFF);
 	WREG32(SCRATCH_ADDR, ((rdev->wb.gpu_addr + RADEON_WB_SCRATCH_OFFSET) >> 8) & 0xFFFFFFFF);
@@ -2995,10 +2992,6 @@ int r600_irq_init(struct radeon_device *rdev)
 	/* RPTR_REARM only works if msi's are enabled */
 	if (rdev->msi_enabled)
 		ih_cntl |= RPTR_REARM;
-
-#ifdef __BIG_ENDIAN
-	ih_cntl |= IH_MC_SWAP(IH_MC_SWAP_32BIT);
-#endif
 	WREG32(IH_CNTL, ih_cntl);
 
 	/* force the active interrupt state to all disabled */

drivers/gpu/drm/radeon/r600_cp.c

@@ -1802,8 +1802,8 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 	/* Set ring buffer size */
 #ifdef __BIG_ENDIAN
 	RADEON_WRITE(R600_CP_RB_CNTL,
-		     RADEON_BUF_SWAP_32BIT |
-		     RADEON_RB_NO_UPDATE |
+		     R600_BUF_SWAP_32BIT |
+		     R600_RB_NO_UPDATE |
 		     (dev_priv->ring.rptr_update_l2qw << 8) |
 		     dev_priv->ring.size_l2qw);
 #else
@@ -1820,15 +1820,15 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 
 #ifdef __BIG_ENDIAN
 	RADEON_WRITE(R600_CP_RB_CNTL,
-		     RADEON_BUF_SWAP_32BIT |
-		     RADEON_RB_NO_UPDATE |
-		     RADEON_RB_RPTR_WR_ENA |
+		     R600_BUF_SWAP_32BIT |
+		     R600_RB_NO_UPDATE |
+		     R600_RB_RPTR_WR_ENA |
 		     (dev_priv->ring.rptr_update_l2qw << 8) |
 		     dev_priv->ring.size_l2qw);
 #else
 	RADEON_WRITE(R600_CP_RB_CNTL,
-		     RADEON_RB_NO_UPDATE |
-		     RADEON_RB_RPTR_WR_ENA |
+		     R600_RB_NO_UPDATE |
+		     R600_RB_RPTR_WR_ENA |
 		     (dev_priv->ring.rptr_update_l2qw << 8) |
 		     dev_priv->ring.size_l2qw);
 #endif
@@ -1851,13 +1851,8 @@ static void r600_cp_init_ring_buffer(struct drm_device *dev,
 			- ((unsigned long) dev->sg->virtual)
 			+ dev_priv->gart_vm_start;
 	}
-	RADEON_WRITE(R600_CP_RB_RPTR_ADDR,
-#ifdef __BIG_ENDIAN
-		     (2 << 0) |
-#endif
-		     (rptr_addr & 0xfffffffc));
-	RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI,
-		     upper_32_bits(rptr_addr));
+	RADEON_WRITE(R600_CP_RB_RPTR_ADDR, (rptr_addr & 0xfffffffc));
+	RADEON_WRITE(R600_CP_RB_RPTR_ADDR_HI, upper_32_bits(rptr_addr));
 
 #ifdef __BIG_ENDIAN
 	RADEON_WRITE(R600_CP_RB_CNTL,