[PATCH 01/17] drm/amdgpu: clarify MEC_HPD_SIZE is specific to a gfx generation
Andres Rodriguez
andresx7 at gmail.com
Mon Apr 17 22:47:57 UTC 2017
Rename MEC_HPD_SIZE to GFXN_MEC_HPD_SIZE to clarify it is specific to a
gfx generation.
Signed-off-by: Andres Rodriguez <andresx7 at gmail.com>
---
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 11 +++++------
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 15 +++++++--------
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 17 ++++++++---------
3 files changed, 20 insertions(+), 23 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index c930bb8..3b98162 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -32,40 +32,41 @@
#include "clearstate_ci.h"
#include "dce/dce_8_0_d.h"
#include "dce/dce_8_0_sh_mask.h"
#include "bif/bif_4_1_d.h"
#include "bif/bif_4_1_sh_mask.h"
#include "gca/gfx_7_0_d.h"
#include "gca/gfx_7_2_enum.h"
#include "gca/gfx_7_2_sh_mask.h"
#include "gmc/gmc_7_0_d.h"
#include "gmc/gmc_7_0_sh_mask.h"
#include "oss/oss_2_0_d.h"
#include "oss/oss_2_0_sh_mask.h"
#define GFX7_NUM_GFX_RINGS 1
#define GFX7_NUM_COMPUTE_RINGS 8
+#define GFX7_MEC_HPD_SIZE 2048
static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
MODULE_FIRMWARE("radeon/bonaire_me.bin");
MODULE_FIRMWARE("radeon/bonaire_ce.bin");
MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
MODULE_FIRMWARE("radeon/bonaire_mec.bin");
MODULE_FIRMWARE("radeon/hawaii_pfp.bin");
MODULE_FIRMWARE("radeon/hawaii_me.bin");
MODULE_FIRMWARE("radeon/hawaii_ce.bin");
MODULE_FIRMWARE("radeon/hawaii_rlc.bin");
MODULE_FIRMWARE("radeon/hawaii_mec.bin");
MODULE_FIRMWARE("radeon/kaveri_pfp.bin");
MODULE_FIRMWARE("radeon/kaveri_me.bin");
MODULE_FIRMWARE("radeon/kaveri_ce.bin");
@@ -2804,90 +2805,88 @@ static void gfx_v7_0_cp_compute_fini(struct amdgpu_device *adev)
}
}
}
static void gfx_v7_0_mec_fini(struct amdgpu_device *adev)
{
int r;
if (adev->gfx.mec.hpd_eop_obj) {
r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);
if (unlikely(r != 0))
dev_warn(adev->dev, "(%d) reserve HPD EOP bo failed\n", r);
amdgpu_bo_unpin(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unref(&adev->gfx.mec.hpd_eop_obj);
adev->gfx.mec.hpd_eop_obj = NULL;
}
}
-#define MEC_HPD_SIZE 2048
-
static int gfx_v7_0_mec_init(struct amdgpu_device *adev)
{
int r;
u32 *hpd;
/*
* KV: 2 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 64 Queues total
* CI/KB: 1 MEC, 4 Pipes/MEC, 8 Queues/Pipe - 32 Queues total
* Nonetheless, we assign only 1 pipe because all other pipes will
* be handled by KFD
*/
adev->gfx.mec.num_mec = 1;
adev->gfx.mec.num_pipe = 1;
adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
if (adev->gfx.mec.hpd_eop_obj == NULL) {
r = amdgpu_bo_create(adev,
- adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2,
+ adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2,
PAGE_SIZE, true,
AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
&adev->gfx.mec.hpd_eop_obj);
if (r) {
dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
return r;
}
}
r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);
if (unlikely(r != 0)) {
gfx_v7_0_mec_fini(adev);
return r;
}
r = amdgpu_bo_pin(adev->gfx.mec.hpd_eop_obj, AMDGPU_GEM_DOMAIN_GTT,
&adev->gfx.mec.hpd_eop_gpu_addr);
if (r) {
dev_warn(adev->dev, "(%d) pin HDP EOP bo failed\n", r);
gfx_v7_0_mec_fini(adev);
return r;
}
r = amdgpu_bo_kmap(adev->gfx.mec.hpd_eop_obj, (void **)&hpd);
if (r) {
dev_warn(adev->dev, "(%d) map HDP EOP bo failed\n", r);
gfx_v7_0_mec_fini(adev);
return r;
}
/* clear memory. Not sure if this is required or not */
- memset(hpd, 0, adev->gfx.mec.num_mec *adev->gfx.mec.num_pipe * MEC_HPD_SIZE * 2);
+ memset(hpd, 0, adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * GFX7_MEC_HPD_SIZE * 2);
amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
return 0;
}
struct hqd_registers
{
u32 cp_mqd_base_addr;
u32 cp_mqd_base_addr_hi;
u32 cp_hqd_active;
u32 cp_hqd_vmid;
u32 cp_hqd_persistent_state;
u32 cp_hqd_pipe_priority;
u32 cp_hqd_queue_priority;
u32 cp_hqd_quantum;
u32 cp_hqd_pq_base;
u32 cp_hqd_pq_base_hi;
u32 cp_hqd_pq_rptr;
@@ -2961,55 +2960,55 @@ static int gfx_v7_0_cp_compute_resume(struct amdgpu_device *adev)
bool use_doorbell = true;
u64 hqd_gpu_addr;
u64 mqd_gpu_addr;
u64 eop_gpu_addr;
u64 wb_gpu_addr;
u32 *buf;
struct bonaire_mqd *mqd;
struct amdgpu_ring *ring;
/* fix up chicken bits */
tmp = RREG32(mmCP_CPF_DEBUG);
tmp |= (1 << 23);
WREG32(mmCP_CPF_DEBUG, tmp);
/* init the pipes */
mutex_lock(&adev->srbm_mutex);
for (i = 0; i < (adev->gfx.mec.num_pipe * adev->gfx.mec.num_mec); i++) {
int me = (i < 4) ? 1 : 2;
int pipe = (i < 4) ? i : (i - 4);
- eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE * 2);
+ eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX7_MEC_HPD_SIZE * 2);
cik_srbm_select(adev, me, pipe, 0, 0);
/* write the EOP addr */
WREG32(mmCP_HPD_EOP_BASE_ADDR, eop_gpu_addr >> 8);
WREG32(mmCP_HPD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr) >> 8);
/* set the VMID assigned */
WREG32(mmCP_HPD_EOP_VMID, 0);
/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
tmp = RREG32(mmCP_HPD_EOP_CONTROL);
tmp &= ~CP_HPD_EOP_CONTROL__EOP_SIZE_MASK;
- tmp |= order_base_2(MEC_HPD_SIZE / 8);
+ tmp |= order_base_2(GFX7_MEC_HPD_SIZE / 8);
WREG32(mmCP_HPD_EOP_CONTROL, tmp);
}
cik_srbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
/* init the queues. Just two for now. */
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
ring = &adev->gfx.compute_ring[i];
if (ring->mqd_obj == NULL) {
r = amdgpu_bo_create(adev,
sizeof(struct bonaire_mqd),
PAGE_SIZE, true,
AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
&ring->mqd_obj);
if (r) {
dev_warn(adev->dev, "(%d) create MQD bo failed\n", r);
return r;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index df50e34..fc94c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -36,40 +36,41 @@
#include "gmc/gmc_8_2_sh_mask.h"
#include "oss/oss_3_0_d.h"
#include "oss/oss_3_0_sh_mask.h"
#include "bif/bif_5_0_d.h"
#include "bif/bif_5_0_sh_mask.h"
#include "gca/gfx_8_0_d.h"
#include "gca/gfx_8_0_enum.h"
#include "gca/gfx_8_0_sh_mask.h"
#include "gca/gfx_8_0_enum.h"
#include "dce/dce_10_0_d.h"
#include "dce/dce_10_0_sh_mask.h"
#include "smu/smu_7_1_3_d.h"
#define GFX8_NUM_GFX_RINGS 1
#define GFX8_NUM_COMPUTE_RINGS 8
+#define GFX8_MEC_HPD_SIZE 2048
#define TOPAZ_GB_ADDR_CONFIG_GOLDEN 0x22010001
#define CARRIZO_GB_ADDR_CONFIG_GOLDEN 0x22010001
#define POLARIS11_GB_ADDR_CONFIG_GOLDEN 0x22011002
#define TONGA_GB_ADDR_CONFIG_GOLDEN 0x22011003
#define ARRAY_MODE(x) ((x) << GB_TILE_MODE0__ARRAY_MODE__SHIFT)
#define PIPE_CONFIG(x) ((x) << GB_TILE_MODE0__PIPE_CONFIG__SHIFT)
#define TILE_SPLIT(x) ((x) << GB_TILE_MODE0__TILE_SPLIT__SHIFT)
#define MICRO_TILE_MODE_NEW(x) ((x) << GB_TILE_MODE0__MICRO_TILE_MODE_NEW__SHIFT)
#define SAMPLE_SPLIT(x) ((x) << GB_TILE_MODE0__SAMPLE_SPLIT__SHIFT)
#define BANK_WIDTH(x) ((x) << GB_MACROTILE_MODE0__BANK_WIDTH__SHIFT)
#define BANK_HEIGHT(x) ((x) << GB_MACROTILE_MODE0__BANK_HEIGHT__SHIFT)
#define MACRO_TILE_ASPECT(x) ((x) << GB_MACROTILE_MODE0__MACRO_TILE_ASPECT__SHIFT)
#define NUM_BANKS(x) ((x) << GB_MACROTILE_MODE0__NUM_BANKS__SHIFT)
#define RLC_CGTT_MGCG_OVERRIDE__CPF_MASK 0x00000001L
#define RLC_CGTT_MGCG_OVERRIDE__RLC_MASK 0x00000002L
#define RLC_CGTT_MGCG_OVERRIDE__MGCG_MASK 0x00000004L
#define RLC_CGTT_MGCG_OVERRIDE__CGCG_MASK 0x00000008L
@@ -1396,116 +1397,114 @@ static int gfx_v8_0_kiq_init_ring(struct amdgpu_device *adev,
ring->pipe = 1;
}
ring->queue = 0;
ring->eop_gpu_addr = kiq->eop_gpu_addr;
sprintf(ring->name, "kiq %d.%d.%d", ring->me, ring->pipe, ring->queue);
r = amdgpu_ring_init(adev, ring, 1024,
irq, AMDGPU_CP_KIQ_IRQ_DRIVER0);
if (r)
dev_warn(adev->dev, "(%d) failed to init kiq ring\n", r);
return r;
}
static void gfx_v8_0_kiq_free_ring(struct amdgpu_ring *ring,
struct amdgpu_irq_src *irq)
{
amdgpu_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
amdgpu_ring_fini(ring);
}
-#define MEC_HPD_SIZE 2048
-
static int gfx_v8_0_mec_init(struct amdgpu_device *adev)
{
int r;
u32 *hpd;
/*
* we assign only 1 pipe because all other pipes will
* be handled by KFD
*/
adev->gfx.mec.num_mec = 1;
adev->gfx.mec.num_pipe = 1;
adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
if (adev->gfx.mec.hpd_eop_obj == NULL) {
r = amdgpu_bo_create(adev,
- adev->gfx.mec.num_queue * MEC_HPD_SIZE,
+ adev->gfx.mec.num_queue * GFX8_MEC_HPD_SIZE,
PAGE_SIZE, true,
AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
&adev->gfx.mec.hpd_eop_obj);
if (r) {
dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
return r;
}
}
r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);
if (unlikely(r != 0)) {
gfx_v8_0_mec_fini(adev);
return r;
}
r = amdgpu_bo_pin(adev->gfx.mec.hpd_eop_obj, AMDGPU_GEM_DOMAIN_GTT,
&adev->gfx.mec.hpd_eop_gpu_addr);
if (r) {
dev_warn(adev->dev, "(%d) pin HDP EOP bo failed\n", r);
gfx_v8_0_mec_fini(adev);
return r;
}
r = amdgpu_bo_kmap(adev->gfx.mec.hpd_eop_obj, (void **)&hpd);
if (r) {
dev_warn(adev->dev, "(%d) map HDP EOP bo failed\n", r);
gfx_v8_0_mec_fini(adev);
return r;
}
- memset(hpd, 0, adev->gfx.mec.num_queue * MEC_HPD_SIZE);
+ memset(hpd, 0, adev->gfx.mec.num_queue * GFX8_MEC_HPD_SIZE);
amdgpu_bo_kunmap(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
return 0;
}
static void gfx_v8_0_kiq_fini(struct amdgpu_device *adev)
{
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
}
static int gfx_v8_0_kiq_init(struct amdgpu_device *adev)
{
int r;
u32 *hpd;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
- r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+ r = amdgpu_bo_create_kernel(adev, GFX8_MEC_HPD_SIZE, PAGE_SIZE,
AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
&kiq->eop_gpu_addr, (void **)&hpd);
if (r) {
dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
return r;
}
- memset(hpd, 0, MEC_HPD_SIZE);
+ memset(hpd, 0, GFX8_MEC_HPD_SIZE);
r = amdgpu_bo_reserve(kiq->eop_obj, false);
if (unlikely(r != 0))
dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
amdgpu_bo_kunmap(kiq->eop_obj);
amdgpu_bo_unreserve(kiq->eop_obj);
return 0;
}
static const u32 vgpr_init_compute_shader[] =
{
0x7e000209, 0x7e020208,
0x7e040207, 0x7e060206,
0x7e080205, 0x7e0a0204,
0x7e0c0203, 0x7e0e0202,
0x7e100201, 0x7e120200,
0x7e140209, 0x7e160208,
0x7e180207, 0x7e1a0206,
0x7e1c0205, 0x7e1e0204,
@@ -2138,41 +2137,41 @@ static int gfx_v8_0_sw_init(void *handle)
if (r)
return r;
}
/* set up the compute queues */
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
unsigned irq_type;
/* max 32 queues per MEC */
if ((i >= 32) || (i >= AMDGPU_MAX_COMPUTE_RINGS)) {
DRM_ERROR("Too many (%d) compute rings!\n", i);
break;
}
ring = &adev->gfx.compute_ring[i];
ring->ring_obj = NULL;
ring->use_doorbell = true;
ring->doorbell_index = AMDGPU_DOORBELL_MEC_RING0 + i;
ring->me = 1; /* first MEC */
ring->pipe = i / 8;
ring->queue = i % 8;
- ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+ ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX8_MEC_HPD_SIZE);
sprintf(ring->name, "comp_%d.%d.%d", ring->me, ring->pipe, ring->queue);
irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
/* type-2 packets are deprecated on MEC, use type-3 instead */
r = amdgpu_ring_init(adev, ring, 1024, &adev->gfx.eop_irq,
irq_type);
if (r)
return r;
}
r = gfx_v8_0_kiq_init(adev);
if (r) {
DRM_ERROR("Failed to init KIQ BOs!\n");
return r;
}
kiq = &adev->gfx.kiq;
r = gfx_v8_0_kiq_init_ring(adev, &kiq->ring, &kiq->irq);
if (r)
return r;
@@ -4758,41 +4757,41 @@ static int gfx_v8_0_mqd_init(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
struct vi_mqd *mqd = ring->mqd_ptr;
uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
uint32_t tmp;
mqd->header = 0xC0310800;
mqd->compute_pipelinestat_enable = 0x00000001;
mqd->compute_static_thread_mgmt_se0 = 0xffffffff;
mqd->compute_static_thread_mgmt_se1 = 0xffffffff;
mqd->compute_static_thread_mgmt_se2 = 0xffffffff;
mqd->compute_static_thread_mgmt_se3 = 0xffffffff;
mqd->compute_misc_reserved = 0x00000003;
eop_base_addr = ring->eop_gpu_addr >> 8;
mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
tmp = RREG32(mmCP_HQD_EOP_CONTROL);
tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
- (order_base_2(MEC_HPD_SIZE / 4) - 1));
+ (order_base_2(GFX8_MEC_HPD_SIZE / 4) - 1));
mqd->cp_hqd_eop_control = tmp;
/* enable doorbell? */
tmp = REG_SET_FIELD(RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL),
CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_EN,
ring->use_doorbell ? 1 : 0);
mqd->cp_hqd_pq_doorbell_control = tmp;
/* disable the queue if it's active */
mqd->cp_hqd_dequeue_request = 0;
mqd->cp_hqd_pq_rptr = 0;
mqd->cp_hqd_pq_wptr = 0;
/* set the pointer to the MQD */
mqd->cp_mqd_base_addr_lo = ring->mqd_gpu_addr & 0xfffffffc;
mqd->cp_mqd_base_addr_hi = upper_32_bits(ring->mqd_gpu_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 87596e4..0de7ff4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -23,40 +23,41 @@
#include <linux/firmware.h>
#include "drmP.h"
#include "amdgpu.h"
#include "amdgpu_gfx.h"
#include "soc15.h"
#include "soc15d.h"
#include "vega10/soc15ip.h"
#include "vega10/GC/gc_9_0_offset.h"
#include "vega10/GC/gc_9_0_sh_mask.h"
#include "vega10/vega10_enum.h"
#include "vega10/HDP/hdp_4_0_offset.h"
#include "soc15_common.h"
#include "clearstate_gfx9.h"
#include "v9_structs.h"
#define GFX9_NUM_GFX_RINGS 1
#define GFX9_NUM_COMPUTE_RINGS 8
#define GFX9_NUM_SE 4
+#define GFX9_MEC_HPD_SIZE 2048
#define RLCG_UCODE_LOADING_START_ADDRESS 0x2000
MODULE_FIRMWARE("amdgpu/vega10_ce.bin");
MODULE_FIRMWARE("amdgpu/vega10_pfp.bin");
MODULE_FIRMWARE("amdgpu/vega10_me.bin");
MODULE_FIRMWARE("amdgpu/vega10_mec.bin");
MODULE_FIRMWARE("amdgpu/vega10_mec2.bin");
MODULE_FIRMWARE("amdgpu/vega10_rlc.bin");
static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
{
{SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_BASE), SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE),
SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID0), SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID0)},
{SOC15_REG_OFFSET(GC, 0, mmGDS_VMID1_BASE), SOC15_REG_OFFSET(GC, 0, mmGDS_VMID1_SIZE),
SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID1), SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID1)},
{SOC15_REG_OFFSET(GC, 0, mmGDS_VMID2_BASE), SOC15_REG_OFFSET(GC, 0, mmGDS_VMID2_SIZE),
SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID2), SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID2)},
{SOC15_REG_OFFSET(GC, 0, mmGDS_VMID3_BASE), SOC15_REG_OFFSET(GC, 0, mmGDS_VMID3_SIZE),
SOC15_REG_OFFSET(GC, 0, mmGDS_GWS_VMID3), SOC15_REG_OFFSET(GC, 0, mmGDS_OA_VMID3)},
{SOC15_REG_OFFSET(GC, 0, mmGDS_VMID4_BASE), SOC15_REG_OFFSET(GC, 0, mmGDS_VMID4_SIZE),
@@ -457,63 +458,61 @@ static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
if (unlikely(r != 0))
dev_warn(adev->dev, "(%d) reserve HPD EOP bo failed\n", r);
amdgpu_bo_unpin(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unreserve(adev->gfx.mec.hpd_eop_obj);
amdgpu_bo_unref(&adev->gfx.mec.hpd_eop_obj);
adev->gfx.mec.hpd_eop_obj = NULL;
}
if (adev->gfx.mec.mec_fw_obj) {
r = amdgpu_bo_reserve(adev->gfx.mec.mec_fw_obj, false);
if (unlikely(r != 0))
dev_warn(adev->dev, "(%d) reserve mec firmware bo failed\n", r);
amdgpu_bo_unpin(adev->gfx.mec.mec_fw_obj);
amdgpu_bo_unreserve(adev->gfx.mec.mec_fw_obj);
amdgpu_bo_unref(&adev->gfx.mec.mec_fw_obj);
adev->gfx.mec.mec_fw_obj = NULL;
}
}
-#define MEC_HPD_SIZE 2048
-
static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
{
int r;
u32 *hpd;
const __le32 *fw_data;
unsigned fw_size;
u32 *fw;
const struct gfx_firmware_header_v1_0 *mec_hdr;
/*
* we assign only 1 pipe because all other pipes will
* be handled by KFD
*/
adev->gfx.mec.num_mec = 1;
adev->gfx.mec.num_pipe = 1;
adev->gfx.mec.num_queue = adev->gfx.mec.num_mec * adev->gfx.mec.num_pipe * 8;
if (adev->gfx.mec.hpd_eop_obj == NULL) {
r = amdgpu_bo_create(adev,
- adev->gfx.mec.num_queue * MEC_HPD_SIZE,
+ adev->gfx.mec.num_queue * GFX9_MEC_HPD_SIZE,
PAGE_SIZE, true,
AMDGPU_GEM_DOMAIN_GTT, 0, NULL, NULL,
&adev->gfx.mec.hpd_eop_obj);
if (r) {
dev_warn(adev->dev, "(%d) create HDP EOP bo failed\n", r);
return r;
}
}
r = amdgpu_bo_reserve(adev->gfx.mec.hpd_eop_obj, false);
if (unlikely(r != 0)) {
gfx_v9_0_mec_fini(adev);
return r;
}
r = amdgpu_bo_pin(adev->gfx.mec.hpd_eop_obj, AMDGPU_GEM_DOMAIN_GTT,
&adev->gfx.mec.hpd_eop_gpu_addr);
if (r) {
dev_warn(adev->dev, "(%d) pin HDP EOP bo failed\n", r);
gfx_v9_0_mec_fini(adev);
return r;
@@ -572,49 +571,49 @@ static int gfx_v9_0_mec_init(struct amdgpu_device *adev)
amdgpu_bo_kunmap(adev->gfx.mec.mec_fw_obj);
amdgpu_bo_unreserve(adev->gfx.mec.mec_fw_obj);
return 0;
}
static void gfx_v9_0_kiq_fini(struct amdgpu_device *adev)
{
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
amdgpu_bo_free_kernel(&kiq->eop_obj, &kiq->eop_gpu_addr, NULL);
}
static int gfx_v9_0_kiq_init(struct amdgpu_device *adev)
{
int r;
u32 *hpd;
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
- r = amdgpu_bo_create_kernel(adev, MEC_HPD_SIZE, PAGE_SIZE,
+ r = amdgpu_bo_create_kernel(adev, GFX9_MEC_HPD_SIZE, PAGE_SIZE,
AMDGPU_GEM_DOMAIN_GTT, &kiq->eop_obj,
&kiq->eop_gpu_addr, (void **)&hpd);
if (r) {
dev_warn(adev->dev, "failed to create KIQ bo (%d).\n", r);
return r;
}
- memset(hpd, 0, MEC_HPD_SIZE);
+ memset(hpd, 0, GFX9_MEC_HPD_SIZE);
r = amdgpu_bo_reserve(kiq->eop_obj, false);
if (unlikely(r != 0))
dev_warn(adev->dev, "(%d) reserve kiq eop bo failed\n", r);
amdgpu_bo_kunmap(kiq->eop_obj);
amdgpu_bo_unreserve(kiq->eop_obj);
return 0;
}
static int gfx_v9_0_kiq_init_ring(struct amdgpu_device *adev,
struct amdgpu_ring *ring,
struct amdgpu_irq_src *irq)
{
struct amdgpu_kiq *kiq = &adev->gfx.kiq;
int r = 0;
r = amdgpu_wb_get(adev, &adev->virt.reg_val_offs);
if (r)
return r;
@@ -1078,41 +1077,41 @@ static int gfx_v9_0_sw_init(void *handle)
if (r)
return r;
}
/* set up the compute queues */
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
unsigned irq_type;
/* max 32 queues per MEC */
if ((i >= 32) || (i >= AMDGPU_MAX_COMPUTE_RINGS)) {
DRM_ERROR("Too many (%d) compute rings!\n", i);
break;
}
ring = &adev->gfx.compute_ring[i];
ring->ring_obj = NULL;
ring->use_doorbell = true;
ring->doorbell_index = (AMDGPU_DOORBELL64_MEC_RING0 + i) << 1;
ring->me = 1; /* first MEC */
ring->pipe = i / 8;
ring->queue = i % 8;
- ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * MEC_HPD_SIZE);
+ ring->eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (i * GFX9_MEC_HPD_SIZE);
sprintf(ring->name, "comp %d.%d.%d", ring->me, ring->pipe, ring->queue);
irq_type = AMDGPU_CP_IRQ_COMPUTE_MEC1_PIPE0_EOP + ring->pipe;
/* type-2 packets are deprecated on MEC, use type-3 instead */
r = amdgpu_ring_init(adev, ring, 1024,
&adev->gfx.eop_irq, irq_type);
if (r)
return r;
}
if (amdgpu_sriov_vf(adev)) {
r = gfx_v9_0_kiq_init(adev);
if (r) {
DRM_ERROR("Failed to init KIQ BOs!\n");
return r;
}
kiq = &adev->gfx.kiq;
r = gfx_v9_0_kiq_init_ring(adev, &kiq->ring, &kiq->irq);
if (r)
return r;
@@ -1883,41 +1882,41 @@ static int gfx_v9_0_mqd_init(struct amdgpu_ring *ring)
struct amdgpu_device *adev = ring->adev;
struct v9_mqd *mqd = ring->mqd_ptr;
uint64_t hqd_gpu_addr, wb_gpu_addr, eop_base_addr;
uint32_t tmp;
mqd->header = 0xC0310800;
mqd->compute_pipelinestat_enable = 0x00000001;
mqd->compute_static_thread_mgmt_se0 = 0xffffffff;
mqd->compute_static_thread_mgmt_se1 = 0xffffffff;
mqd->compute_static_thread_mgmt_se2 = 0xffffffff;
mqd->compute_static_thread_mgmt_se3 = 0xffffffff;
mqd->compute_misc_reserved = 0x00000003;
eop_base_addr = ring->eop_gpu_addr >> 8;
mqd->cp_hqd_eop_base_addr_lo = eop_base_addr;
mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_base_addr);
/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
tmp = RREG32_SOC15(GC, 0, mmCP_HQD_EOP_CONTROL);
tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
- (order_base_2(MEC_HPD_SIZE / 4) - 1));
+ (order_base_2(GFX9_MEC_HPD_SIZE / 4) - 1));
mqd->cp_hqd_eop_control = tmp;
/* enable doorbell? */
tmp = RREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL);
if (ring->use_doorbell) {
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_OFFSET, ring->doorbell_index);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_EN, 1);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_SOURCE, 0);
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_HIT, 0);
}
else
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
DOORBELL_EN, 0);
@@ -3740,52 +3739,52 @@ static int gfx_v9_0_init_queue(struct amdgpu_ring *ring)
/* init the mqd struct */
memset(buf, 0, sizeof(struct v9_mqd));
mqd = (struct v9_mqd *)buf;
mqd->header = 0xC0310800;
mqd->compute_pipelinestat_enable = 0x00000001;
mqd->compute_static_thread_mgmt_se0 = 0xffffffff;
mqd->compute_static_thread_mgmt_se1 = 0xffffffff;
mqd->compute_static_thread_mgmt_se2 = 0xffffffff;
mqd->compute_static_thread_mgmt_se3 = 0xffffffff;
mqd->compute_misc_reserved = 0x00000003;
mutex_lock(&adev->srbm_mutex);
soc15_grbm_select(adev, ring->me,
ring->pipe,
ring->queue, 0);
/* disable wptr polling */
WREG32_FIELD15(GC, 0, CP_PQ_WPTR_POLL_CNTL, EN, 0);
/* write the EOP addr */
BUG_ON(ring->me != 1 || ring->pipe != 0); /* can't handle other cases eop address */
- eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (ring->queue * MEC_HPD_SIZE);
+ eop_gpu_addr = adev->gfx.mec.hpd_eop_gpu_addr + (ring->queue * GFX9_MEC_HPD_SIZE);
eop_gpu_addr >>= 8;
WREG32_SOC15(GC, 0, mmCP_HQD_EOP_BASE_ADDR, lower_32_bits(eop_gpu_addr));
WREG32_SOC15(GC, 0, mmCP_HQD_EOP_BASE_ADDR_HI, upper_32_bits(eop_gpu_addr));
mqd->cp_hqd_eop_base_addr_lo = lower_32_bits(eop_gpu_addr);
mqd->cp_hqd_eop_base_addr_hi = upper_32_bits(eop_gpu_addr);
/* set the EOP size, register value is 2^(EOP_SIZE+1) dwords */
tmp = RREG32_SOC15(GC, 0, mmCP_HQD_EOP_CONTROL);
tmp = REG_SET_FIELD(tmp, CP_HQD_EOP_CONTROL, EOP_SIZE,
- (order_base_2(MEC_HPD_SIZE / 4) - 1));
+ (order_base_2(GFX9_MEC_HPD_SIZE / 4) - 1));
WREG32_SOC15(GC, 0, mmCP_HQD_EOP_CONTROL, tmp);
/* enable doorbell? */
tmp = RREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL);
if (use_doorbell)
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1);
else
tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 0);
WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, tmp);
mqd->cp_hqd_pq_doorbell_control = tmp;
/* disable the queue if it's active */
ring->wptr = 0;
mqd->cp_hqd_dequeue_request = 0;
mqd->cp_hqd_pq_rptr = 0;
mqd->cp_hqd_pq_wptr_lo = 0;
mqd->cp_hqd_pq_wptr_hi = 0;
if (RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE) & 1) {
WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 1);
--
2.9.3
More information about the amd-gfx
mailing list