summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c139
1 files changed, 91 insertions, 48 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 23e6a05359c2..75ea071744eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -368,11 +368,6 @@ static const struct amdgpu_hwip_reg_entry gc_reg_list_10_1[] = {
SOC15_REG_ENTRY_STR(GC, 0, mmRLC_GPM_DEBUG_INST_ADDR),
SOC15_REG_ENTRY_STR(GC, 0, mmRLC_LX6_CORE_PDEBUG_INST),
/* cp header registers */
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME2_HEADER_DUMP),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
SOC15_REG_ENTRY_STR(GC, 0, mmCP_MES_HEADER_DUMP),
/* SE status registers */
SOC15_REG_ENTRY_STR(GC, 0, mmGRBM_STATUS_SE0),
@@ -421,7 +416,16 @@ static const struct amdgpu_hwip_reg_entry gc_cp_reg_list_10[] = {
SOC15_REG_ENTRY_STR(GC, 0, mmCP_HQD_SUSPEND_CNTL_STACK_OFFSET),
SOC15_REG_ENTRY_STR(GC, 0, mmCP_HQD_SUSPEND_CNTL_STACK_DW_CNT),
SOC15_REG_ENTRY_STR(GC, 0, mmCP_HQD_SUSPEND_WG_STATE_OFFSET),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_HQD_DEQUEUE_STATUS)
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_HQD_DEQUEUE_STATUS),
+ /* cp header registers */
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_MEC_ME1_HEADER_DUMP),
};
static const struct amdgpu_hwip_reg_entry gc_gfx_queue_reg_list_10[] = {
@@ -448,7 +452,32 @@ static const struct amdgpu_hwip_reg_entry gc_gfx_queue_reg_list_10[] = {
SOC15_REG_ENTRY_STR(GC, 0, mmCP_GFX_MQD_BASE_ADDR),
SOC15_REG_ENTRY_STR(GC, 0, mmCP_GFX_MQD_BASE_ADDR_HI),
SOC15_REG_ENTRY_STR(GC, 0, mmCP_RB_WPTR_POLL_ADDR_LO),
- SOC15_REG_ENTRY_STR(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI)
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_RB_WPTR_POLL_ADDR_HI),
+ /* gfx header registers */
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_CE_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_PFP_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
+ SOC15_REG_ENTRY_STR(GC, 0, mmCP_ME_HEADER_DUMP),
};
static const struct soc15_reg_golden golden_settings_gc_10_1[] = {
@@ -4296,9 +4325,7 @@ static u32 gfx_v10_0_get_csb_size(struct amdgpu_device *adev)
static void gfx_v10_0_get_csb_buffer(struct amdgpu_device *adev,
volatile u32 *buffer)
{
- u32 count = 0, i;
- const struct cs_section_def *sect = NULL;
- const struct cs_extent_def *ext = NULL;
+ u32 count = 0;
int ctx_reg_offset;
if (adev->gfx.rlc.cs_data == NULL)
@@ -4306,39 +4333,15 @@ static void gfx_v10_0_get_csb_buffer(struct amdgpu_device *adev,
if (buffer == NULL)
return;
- buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
- buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_BEGIN_CLEAR_STATE);
+ count = amdgpu_gfx_csb_preamble_start(buffer);
+ count = amdgpu_gfx_csb_data_parser(adev, buffer, count);
- buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CONTEXT_CONTROL, 1));
- buffer[count++] = cpu_to_le32(0x80000000);
- buffer[count++] = cpu_to_le32(0x80000000);
-
- for (sect = adev->gfx.rlc.cs_data; sect->section != NULL; ++sect) {
- for (ext = sect->section; ext->extent != NULL; ++ext) {
- if (sect->id == SECT_CONTEXT) {
- buffer[count++] =
- cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, ext->reg_count));
- buffer[count++] = cpu_to_le32(ext->reg_index -
- PACKET3_SET_CONTEXT_REG_START);
- for (i = 0; i < ext->reg_count; i++)
- buffer[count++] = cpu_to_le32(ext->extent[i]);
- } else {
- return;
- }
- }
- }
-
- ctx_reg_offset =
- SOC15_REG_OFFSET(GC, 0, mmPA_SC_TILE_STEERING_OVERRIDE) - PACKET3_SET_CONTEXT_REG_START;
+ ctx_reg_offset = SOC15_REG_OFFSET(GC, 0, mmPA_SC_TILE_STEERING_OVERRIDE) - PACKET3_SET_CONTEXT_REG_START;
buffer[count++] = cpu_to_le32(PACKET3(PACKET3_SET_CONTEXT_REG, 1));
buffer[count++] = cpu_to_le32(ctx_reg_offset);
buffer[count++] = cpu_to_le32(adev->gfx.config.pa_sc_tile_steering_override);
- buffer[count++] = cpu_to_le32(PACKET3(PACKET3_PREAMBLE_CNTL, 0));
- buffer[count++] = cpu_to_le32(PACKET3_PREAMBLE_END_CLEAR_STATE);
-
- buffer[count++] = cpu_to_le32(PACKET3(PACKET3_CLEAR_STATE, 0));
- buffer[count++] = cpu_to_le32(0);
+ amdgpu_gfx_csb_preamble_end(buffer, count);
}
static void gfx_v10_0_rlc_fini(struct amdgpu_device *adev)
@@ -4752,6 +4755,7 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
int i, j, k, r, ring_id = 0;
int xcc_id = 0;
struct amdgpu_device *adev = ip_block->adev;
+ int num_queue_per_pipe = 1; /* we only enable 1 KGQ per pipe */
INIT_DELAYED_WORK(&adev->gfx.idle_work, amdgpu_gfx_profile_idle_work_handler);
@@ -4763,7 +4767,7 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
case IP_VERSION(10, 1, 4):
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 1;
- adev->gfx.me.num_queue_per_pipe = 1;
+ adev->gfx.me.num_queue_per_pipe = 8;
adev->gfx.mec.num_mec = 2;
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 8;
@@ -4778,7 +4782,7 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
case IP_VERSION(10, 3, 7):
adev->gfx.me.num_me = 1;
adev->gfx.me.num_pipe_per_me = 2;
- adev->gfx.me.num_queue_per_pipe = 1;
+ adev->gfx.me.num_queue_per_pipe = 2;
adev->gfx.mec.num_mec = 2;
adev->gfx.mec.num_pipe_per_mec = 4;
adev->gfx.mec.num_queue_per_pipe = 4;
@@ -4800,7 +4804,7 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
adev->gfx.cleaner_shader_size = sizeof(gfx_10_1_10_cleaner_shader_hex);
if (adev->gfx.me_fw_version >= 101 &&
adev->gfx.pfp_fw_version >= 158 &&
- adev->gfx.mec_fw_version >= 152) {
+ adev->gfx.mec_fw_version >= 151) {
adev->gfx.enable_cleaner_shader = true;
r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
if (r) {
@@ -4810,7 +4814,9 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
}
break;
case IP_VERSION(10, 3, 0):
+ case IP_VERSION(10, 3, 1):
case IP_VERSION(10, 3, 2):
+ case IP_VERSION(10, 3, 3):
case IP_VERSION(10, 3, 4):
case IP_VERSION(10, 3, 5):
adev->gfx.cleaner_shader_ptr = gfx_10_3_0_cleaner_shader_hex;
@@ -4826,6 +4832,34 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
}
}
break;
+ case IP_VERSION(10, 3, 6):
+ adev->gfx.cleaner_shader_ptr = gfx_10_3_0_cleaner_shader_hex;
+ adev->gfx.cleaner_shader_size = sizeof(gfx_10_3_0_cleaner_shader_hex);
+ if (adev->gfx.me_fw_version >= 14 &&
+ adev->gfx.pfp_fw_version >= 17 &&
+ adev->gfx.mec_fw_version >= 24) {
+ adev->gfx.enable_cleaner_shader = true;
+ r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+ if (r) {
+ adev->gfx.enable_cleaner_shader = false;
+ dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+ }
+ }
+ break;
+ case IP_VERSION(10, 3, 7):
+ adev->gfx.cleaner_shader_ptr = gfx_10_3_0_cleaner_shader_hex;
+ adev->gfx.cleaner_shader_size = sizeof(gfx_10_3_0_cleaner_shader_hex);
+ if (adev->gfx.me_fw_version >= 4 &&
+ adev->gfx.pfp_fw_version >= 9 &&
+ adev->gfx.mec_fw_version >= 12) {
+ adev->gfx.enable_cleaner_shader = true;
+ r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+ if (r) {
+ adev->gfx.enable_cleaner_shader = false;
+ dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+ }
+ }
+ break;
default:
adev->gfx.enable_cleaner_shader = false;
break;
@@ -4886,7 +4920,7 @@ static int gfx_v10_0_sw_init(struct amdgpu_ip_block *ip_block)
/* set up the gfx ring */
for (i = 0; i < adev->gfx.me.num_me; i++) {
- for (j = 0; j < adev->gfx.me.num_queue_per_pipe; j++) {
+ for (j = 0; j < num_queue_per_pipe; j++) {
for (k = 0; k < adev->gfx.me.num_pipe_per_me; k++) {
if (!amdgpu_gfx_is_me_queue_enabled(adev, i, k, j))
continue;
@@ -9645,9 +9679,14 @@ static void gfx_v10_ip_print(struct amdgpu_ip_block *ip_block, struct drm_printe
for (k = 0; k < adev->gfx.mec.num_queue_per_pipe; k++) {
drm_printf(p, "\nmec %d, pipe %d, queue %d\n", i, j, k);
for (reg = 0; reg < reg_count; reg++) {
- drm_printf(p, "%-50s \t 0x%08x\n",
- gc_cp_reg_list_10[reg].reg_name,
- adev->gfx.ip_dump_compute_queues[index + reg]);
+ if (i && gc_cp_reg_list_10[reg].reg_offset == mmCP_MEC_ME1_HEADER_DUMP)
+ drm_printf(p, "%-50s \t 0x%08x\n",
+ "mmCP_MEC_ME2_HEADER_DUMP",
+ adev->gfx.ip_dump_compute_queues[index + reg]);
+ else
+ drm_printf(p, "%-50s \t 0x%08x\n",
+ gc_cp_reg_list_10[reg].reg_name,
+ adev->gfx.ip_dump_compute_queues[index + reg]);
}
index += reg_count;
}
@@ -9708,9 +9747,13 @@ static void gfx_v10_ip_dump(struct amdgpu_ip_block *ip_block)
nv_grbm_select(adev, adev->gfx.me.num_me + i, j, k, 0);
for (reg = 0; reg < reg_count; reg++) {
- adev->gfx.ip_dump_compute_queues[index + reg] =
- RREG32(SOC15_REG_ENTRY_OFFSET(
- gc_cp_reg_list_10[reg]));
+ if (i && gc_cp_reg_list_10[reg].reg_offset == mmCP_MEC_ME1_HEADER_DUMP)
+ adev->gfx.ip_dump_compute_queues[index + reg] =
+ RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_MEC_ME2_HEADER_DUMP));
+ else
+ adev->gfx.ip_dump_compute_queues[index + reg] =
+ RREG32(SOC15_REG_ENTRY_OFFSET(
+ gc_cp_reg_list_10[reg]));
}
index += reg_count;
}
generated by cgit v1.2.3 (git 2.39.0) at 2025-05-31 15:27:24 +0300