From f59902ffcc43ce7e1db5d0c4dfee37ec2a1bae0c Mon Sep 17 00:00:00 2001
From: Sunil Khatri <sunil.khatri@amd.com>
Date: Wed, 31 Jul 2024 18:27:28 +0530
Subject: drm/amdgpu: optimize the padding for gfx12
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
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_v12_0.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
(limited to 'drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c')
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index f932c7ff85e3..29b3bf1b29b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -5005,6 +5005,24 @@ static void gfx_v12_0_emit_mem_sync(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, gcr_cntl); /* GCR_CNTL */
}
+static void gfx_v12_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_v12_ip_print(void *handle, struct drm_printer *p)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -5186,7 +5204,7 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = {
.emit_hdp_flush = gfx_v12_0_ring_emit_hdp_flush,
.test_ring = gfx_v12_0_ring_test_ring,
.test_ib = gfx_v12_0_ring_test_ib,
- .insert_nop = amdgpu_ring_insert_nop,
+ .insert_nop = gfx_v12_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_cntxcntl = gfx_v12_0_ring_emit_cntxcntl,
.init_cond_exec = gfx_v12_0_ring_emit_init_cond_exec,
@@ -5224,7 +5242,7 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_compute = {
.emit_hdp_flush = gfx_v12_0_ring_emit_hdp_flush,
.test_ring = gfx_v12_0_ring_test_ring,
.test_ib = gfx_v12_0_ring_test_ib,
- .insert_nop = amdgpu_ring_insert_nop,
+ .insert_nop = gfx_v12_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_wreg = gfx_v12_0_ring_emit_wreg,
.emit_reg_wait = gfx_v12_0_ring_emit_reg_wait,
--
cgit v1.2.3-70-g09d2