UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: simplify padding calculations (v2) 

Simplify padding calculations.

v2: Comment update and spacing.

Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Luben Tuikov 2019-10-24 19:30:13 -04:00 committed by Alex Deucher
parent f4feb9fa45
commit ce73516d42
5 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/drm/amd/amdgpu/cik_sdma.c
View File

@ -228,7 +228,7 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring,
u32 extra_bits = vmid & 0xf;
/* IB packet must end on a 8 DW boundary */
cik_sdma_ring_insert_nop(ring, (12 - (lower_32_bits(ring->wptr) & 7)) % 8);
cik_sdma_ring_insert_nop(ring, (4 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_INDIRECT_BUFFER, 0, extra_bits));
amdgpu_ring_write(ring, ib->gpu_addr & 0xffffffe0); /* base must be 32 byte aligned */
@ -811,7 +811,7 @@ static void cik_sdma_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
u32 pad_count;
int i;
pad_count = (8 - (ib->length_dw & 0x7)) % 8;
pad_count = (-ib->length_dw) & 7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =

4
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
View File

@ -255,7 +255,7 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
unsigned vmid = AMDGPU_JOB_GET_VMID(job);
/* IB packet must end on a 8 DW boundary */
sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@ -750,7 +750,7 @@ static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
u32 pad_count;
int i;
pad_count = (8 - (ib->length_dw & 0x7)) % 8;
pad_count = (-ib->length_dw) & 7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =

4
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
View File

@ -429,7 +429,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring,
unsigned vmid = AMDGPU_JOB_GET_VMID(job);
/* IB packet must end on a 8 DW boundary */
sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
sdma_v3_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@ -1021,7 +1021,7 @@ static void sdma_v3_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
u32 pad_count;
int i;
pad_count = (8 - (ib->length_dw & 0x7)) % 8;
pad_count = (-ib->length_dw) & 7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =

4
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
View File

@ -698,7 +698,7 @@ static void sdma_v4_0_ring_emit_ib(struct amdgpu_ring *ring,
unsigned vmid = AMDGPU_JOB_GET_VMID(job);
/* IB packet must end on a 8 DW boundary */
sdma_v4_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
sdma_v4_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@ -1579,7 +1579,7 @@ static void sdma_v4_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
u32 pad_count;
int i;
pad_count = (8 - (ib->length_dw & 0x7)) % 8;
pad_count = (-ib->length_dw) & 7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =

17
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
View File

@ -382,8 +382,15 @@ static void sdma_v5_0_ring_emit_ib(struct amdgpu_ring *ring,
unsigned vmid = AMDGPU_JOB_GET_VMID(job);
uint64_t csa_mc_addr = amdgpu_sdma_get_csa_mc_addr(ring, vmid);
/* IB packet must end on a 8 DW boundary */
sdma_v5_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
/* An IB packet must end on a 8 DW boundary--the next dword
* must be on a 8-dword boundary. Our IB packet below is 6
* dwords long, thus add x number of NOPs, such that, in
* modular arithmetic,
* wptr + 6 + x = 8k, k >= 0, which in C is,
* (wptr + 6 + x) % 8 = 0.
* The expression below, is a solution of x.
*/
sdma_v5_0_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@ -1076,10 +1083,10 @@ static void sdma_v5_0_vm_set_pte_pde(struct amdgpu_ib *ib,
}
/**
* sdma_v5_0_ring_pad_ib - pad the IB to the required number of dw
*
* sdma_v5_0_ring_pad_ib - pad the IB
* @ib: indirect buffer to fill with padding
*
* Pad the IB with NOPs to a boundary multiple of 8.
*/
static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
{
@ -1087,7 +1094,7 @@ static void sdma_v5_0_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib
u32 pad_count;
int i;
pad_count = (8 - (ib->length_dw & 0x7)) % 8;
pad_count = (-ib->length_dw) & 0x7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =