drm/amdgpu/gfx9: add emit_reg_write_reg_wait ring callback (v2)

This adds support for writing and reading back in a single
oneshot packet.  This is needed to send a tlb invalidation
and wait for ack in a single operation.

v2: squash the gfx ring stall fix
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Emily Deng <Emily.Deng@amd.com>

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

@@ -4138,6 +4138,15 @@ static void gfx_v9_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 	gfx_v9_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
 }
 
+static void gfx_v9_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						  uint32_t reg0, uint32_t reg1,
+						  uint32_t ref, uint32_t mask)
+{
+	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+
+	gfx_v9_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1, ref, mask, 0x20);
+}
+
 static void gfx_v9_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 						 enum amdgpu_interrupt_state state)
 {
@@ -4459,6 +4468,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.emit_tmz = gfx_v9_0_ring_emit_tmz,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
@@ -4493,6 +4503,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
 	.set_priority = gfx_v9_0_ring_set_priority_compute,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
@@ -4523,6 +4534,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = {
 	.emit_rreg = gfx_v9_0_ring_emit_rreg,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v9_0_ring_emit_reg_write_reg_wait,
 };
 
 static void gfx_v9_0_set_ring_funcs(struct amdgpu_device *adev)