Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 06:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: optimize the padding for gfx10

Browse Source 
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.

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>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Sunil Khatri 2024-07-30 00:24:44 +05:30 committed by Alex Deucher
parent 4a4c815b08
commit e89d2fec4c
1 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
View File

@ -9397,6 +9397,24 @@ static void gfx_v10_0_emit_mem_sync(struct amdgpu_ring *ring)
amdgpu_ring_write(ring, gcr_cntl); /* GCR_CNTL */
}
static void gfx_v10_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_v10_ip_print(void *handle, struct drm_printer *p)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@ -9588,7 +9606,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
.emit_hdp_flush = gfx_v10_0_ring_emit_hdp_flush,
.test_ring = gfx_v10_0_ring_test_ring,
.test_ib = gfx_v10_0_ring_test_ib,
.insert_nop = amdgpu_ring_insert_nop,
.insert_nop = gfx_v10_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_switch_buffer = gfx_v10_0_ring_emit_sb,
.emit_cntxcntl = gfx_v10_0_ring_emit_cntxcntl,
@ -9629,7 +9647,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
.emit_hdp_flush = gfx_v10_0_ring_emit_hdp_flush,
.test_ring = gfx_v10_0_ring_test_ring,
.test_ib = gfx_v10_0_ring_test_ib,
.insert_nop = amdgpu_ring_insert_nop,
.insert_nop = gfx_v10_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.emit_wreg = gfx_v10_0_ring_emit_wreg,
.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,