drm/radeon: use callbacks for ring pointer handling (v3)

Add callbacks to the radeon_asic struct to handle
rptr/wptr fetchs and wptr updates.
We currently use one version for all rings, but this
allows us to override with a ring specific versions.

Needed for compute rings on CIK.

v2: udpate as per Christian's comments
v3: fix some rebase cruft
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/radeon/radeon.h

@@ -1285,6 +1285,10 @@ struct radeon_asic {
 		int (*ib_test)(struct radeon_device *rdev, struct radeon_ring *cp);
 		bool (*is_lockup)(struct radeon_device *rdev, struct radeon_ring *cp);
 		void (*vm_flush)(struct radeon_device *rdev, int ridx, struct radeon_vm *vm);
+
+		u32 (*get_rptr)(struct radeon_device *rdev, struct radeon_ring *ring);
+		u32 (*get_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
+		void (*set_wptr)(struct radeon_device *rdev, struct radeon_ring *ring);
 	} ring[RADEON_NUM_RINGS];
 	/* irqs */
 	struct {
@@ -1962,6 +1966,9 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v);
 #define radeon_ring_ib_parse(rdev, r, ib) (rdev)->asic->ring[(r)].ib_parse((rdev), (ib))
 #define radeon_ring_is_lockup(rdev, r, cp) (rdev)->asic->ring[(r)].is_lockup((rdev), (cp))
 #define radeon_ring_vm_flush(rdev, r, vm) (rdev)->asic->ring[(r)].vm_flush((rdev), (r), (vm))
+#define radeon_ring_get_rptr(rdev, r) (rdev)->asic->ring[(r)->idx].get_rptr((rdev), (r))
+#define radeon_ring_get_wptr(rdev, r) (rdev)->asic->ring[(r)->idx].get_wptr((rdev), (r))
+#define radeon_ring_set_wptr(rdev, r) (rdev)->asic->ring[(r)->idx].set_wptr((rdev), (r))
 #define radeon_irq_set(rdev) (rdev)->asic->irq.set((rdev))
 #define radeon_irq_process(rdev) (rdev)->asic->irq.process((rdev))
 #define radeon_get_vblank_counter(rdev, crtc) (rdev)->asic->display.get_vblank_counter((rdev), (crtc))

drivers/gpu/drm/radeon/radeon_asic.h

@@ -47,6 +47,12 @@ u8 atombios_get_backlight_level(struct radeon_encoder *radeon_encoder);
 void radeon_legacy_set_backlight_level(struct radeon_encoder *radeon_encoder, u8 level);
 u8 radeon_legacy_get_backlight_level(struct radeon_encoder *radeon_encoder);
 
+u32 radeon_ring_generic_get_rptr(struct radeon_device *rdev,
+				 struct radeon_ring *ring);
+u32 radeon_ring_generic_get_wptr(struct radeon_device *rdev,
+				 struct radeon_ring *ring);
+void radeon_ring_generic_set_wptr(struct radeon_device *rdev,
+				  struct radeon_ring *ring);
 
 /*
  * r100,rv100,rs100,rv200,rs200

drivers/gpu/drm/radeon/radeon_ring.c

@@ -357,6 +357,38 @@ bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
 	}
 }
 
+u32 radeon_ring_generic_get_rptr(struct radeon_device *rdev,
+				 struct radeon_ring *ring)
+{
+	u32 rptr;
+
+	if (rdev->wb.enabled && ring != &rdev->ring[R600_RING_TYPE_UVD_INDEX])
+		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
+	else
+		rptr = RREG32(ring->rptr_reg);
+	rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+
+	return rptr;
+}
+
+u32 radeon_ring_generic_get_wptr(struct radeon_device *rdev,
+				 struct radeon_ring *ring)
+{
+	u32 wptr;
+
+	wptr = RREG32(ring->wptr_reg);
+	wptr = (wptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+
+	return wptr;
+}
+
+void radeon_ring_generic_set_wptr(struct radeon_device *rdev,
+				  struct radeon_ring *ring)
+{
+	WREG32(ring->wptr_reg, (ring->wptr << ring->ptr_reg_shift) & ring->ptr_reg_mask);
+	(void)RREG32(ring->wptr_reg);
+}
+
 /**
  * radeon_ring_free_size - update the free size
  *
@@ -367,13 +399,7 @@ bool radeon_ring_supports_scratch_reg(struct radeon_device *rdev,
  */
 void radeon_ring_free_size(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	u32 rptr;
-
-	if (rdev->wb.enabled && ring != &rdev->ring[R600_RING_TYPE_UVD_INDEX])
-		rptr = le32_to_cpu(rdev->wb.wb[ring->rptr_offs/4]);
-	else
-		rptr = RREG32(ring->rptr_reg);
-	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+	ring->rptr = radeon_ring_get_rptr(rdev, ring);
 	/* This works because ring_size is a power of 2 */
 	ring->ring_free_dw = (ring->rptr + (ring->ring_size / 4));
 	ring->ring_free_dw -= ring->wptr;
@@ -458,8 +484,7 @@ void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 		radeon_ring_write(ring, ring->nop);
 	}
 	DRM_MEMORYBARRIER();
-	WREG32(ring->wptr_reg, (ring->wptr << ring->ptr_reg_shift) & ring->ptr_reg_mask);
-	(void)RREG32(ring->wptr_reg);
+	radeon_ring_set_wptr(rdev, ring);
 }
 
 /**
@@ -561,7 +586,6 @@ void radeon_ring_lockup_update(struct radeon_ring *ring)
 bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	unsigned long cjiffies, elapsed;
-	uint32_t rptr;
 
 	cjiffies = jiffies;
 	if (!time_after(cjiffies, ring->last_activity)) {
@@ -569,8 +593,7 @@ bool radeon_ring_test_lockup(struct radeon_device *rdev, struct radeon_ring *rin
 		radeon_ring_lockup_update(ring);
 		return false;
 	}
-	rptr = RREG32(ring->rptr_reg);
-	ring->rptr = (rptr & ring->ptr_reg_mask) >> ring->ptr_reg_shift;
+	ring->rptr = radeon_ring_get_rptr(rdev, ring);
 	if (ring->rptr != ring->last_rptr) {
 		/* CP is still working no lockup */
 		radeon_ring_lockup_update(ring);
@@ -797,9 +820,9 @@ static int radeon_debugfs_ring_info(struct seq_file *m, void *data)
 
 	radeon_ring_free_size(rdev, ring);
 	count = (ring->ring_size / 4) - ring->ring_free_dw;
-	tmp = RREG32(ring->wptr_reg) >> ring->ptr_reg_shift;
+	tmp = radeon_ring_get_wptr(rdev, ring);
 	seq_printf(m, "wptr(0x%04x): 0x%08x [%5d]\n", ring->wptr_reg, tmp, tmp);
-	tmp = RREG32(ring->rptr_reg) >> ring->ptr_reg_shift;
+	tmp = radeon_ring_get_rptr(rdev, ring);
 	seq_printf(m, "rptr(0x%04x): 0x%08x [%5d]\n", ring->rptr_reg, tmp, tmp);
 	if (ring->rptr_save_reg) {
 		seq_printf(m, "rptr next(0x%04x): 0x%08x\n", ring->rptr_save_reg,