drm/amdgpu: optimize the padding for gfx9

Adding NOP packets one by one in the ring
does not use the CP efficiently.

Solution:
Use CP optimization while adding NOP packet's so PFP
can discard NOP packets based on information of count
from the Header instead of fetching all NOP packets
one by one.
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Cc: Tvrtko Ursulin <tursulin@igalia.com>
Cc: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -7100,6 +7100,24 @@ static void gfx_v9_0_emit_wave_limit(struct amdgpu_ring *ring, bool enable)
 	}
 }
 
+static void gfx_v9_ring_insert_nop(struct amdgpu_ring *ring, uint32_t num_nop)
+{
+	int i;
+
+	/* Header itself is a NOP packet */
+	if (num_nop == 1) {
+		amdgpu_ring_write(ring, ring->funcs->nop);
+		return;
+	}
+
+	/* Max HW optimization till 0x3ffe, followed by remaining one NOP at a time*/
+	amdgpu_ring_write(ring, PACKET3(PACKET3_NOP, min(num_nop - 2, 0x3ffe)));
+
+	/* Header is at index 0, followed by num_nops - 1 NOP packet's */
+	for (i = 1; i < num_nop; i++)
+		amdgpu_ring_write(ring, ring->funcs->nop);
+}
+
 static void gfx_v9_ip_print(void *handle, struct drm_printer *p)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -7240,7 +7258,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.emit_gds_switch = gfx_v9_0_ring_emit_gds_switch,
 	.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v9_0_ring_test_ring,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = gfx_v9_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_switch_buffer = gfx_v9_ring_emit_sb,
 	.emit_cntxcntl = gfx_v9_ring_emit_cntxcntl,
@@ -7294,7 +7312,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_sw_ring_funcs_gfx = {
 	.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v9_0_ring_test_ring,
 	.test_ib = gfx_v9_0_ring_test_ib,
-	.insert_nop = amdgpu_sw_ring_insert_nop,
+	.insert_nop = gfx_v9_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_switch_buffer = gfx_v9_ring_emit_sb,
 	.emit_cntxcntl = gfx_v9_ring_emit_cntxcntl,
@@ -7338,7 +7356,7 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = {
 	.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v9_0_ring_test_ring,
 	.test_ib = gfx_v9_0_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = gfx_v9_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_wreg = gfx_v9_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v9_0_ring_emit_reg_wait,