<html> <head> <meta http-equiv="Content-Type" content="text/html; charset=us-ascii"> <style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style> </head> <body dir="ltr"> [AMD Official Use Only] <div> <div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0); background-color: rgb(255, 255, 255);"> Reviewed-by: David Nieto <david.nieto@amd.com></div> <div id="appendonsend"></div> <hr style="display:inline-block;width:98%" tabindex="-1"> <div id="divRplyFwdMsg" dir="ltr">From: Skvortsov, Victor <Victor.Skvortsov@amd.com> Sent: Wednesday, December 15, 2021 10:55 AM To: amd-gfx@lists.freedesktop.org <amd-gfx@lists.freedesktop.org>; Deng, Emily <Emily.Deng@amd.com>; Liu, Monk <Monk.Liu@amd.com>; Ming, Davis <Davis.Ming@amd.com>; Liu, Shaoyun <Shaoyun.Liu@amd.com>; Zhou, Peng Ju <PengJu.Zhou@amd.com>; Chen, JingWen <JingWen.Chen2@amd.com>; Chen, Horace <Horace.Chen@amd.com>; Nieto, David M <David.Nieto@amd.com> Cc: Skvortsov, Victor <Victor.Skvortsov@amd.com> Subject: [PATCH 3/5] drm/amdgpu: Modify indirect register access for amdkfd_gfx_v9 sriov <div> </div> </div> <div class="BodyFragment"> <div class="PlainText">Modify GC register access from MMIO to RLCG if the indirect flag is set Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com> --- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 27 +++++++++---------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index ddfe7aff919d..1abf662a0e91 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -166,7 +166,7 @@ int kgd_gfx_v9_init_interrupts(struct amdgpu_device *adev, uint32_t pipe_id) lock_srbm(adev, mec, pipe, 0, 0); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCPC_INT_CNTL), + WREG32_SOC15(GC, 0, mmCPC_INT_CNTL, CP_INT_CNTL_RING0__TIME_STAMP_INT_ENABLE_MASK | CP_INT_CNTL_RING0__OPCODE_ERROR_INT_ENABLE_MASK); @@ -279,7 +279,7 @@ int kgd_gfx_v9_hqd_load(struct amdgpu_device *adev, void *mqd, lower_32_bits((uintptr_t)wptr)); WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI), upper_32_bits((uintptr_t)wptr)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1), + WREG32_SOC15(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1, (uint32_t)get_queue_mask(adev, pipe_id, queue_id)); } @@ -488,13 +488,13 @@ bool kgd_gfx_v9_hqd_is_occupied(struct amdgpu_device *adev, uint32_t low, high; acquire_queue(adev, pipe_id, queue_id); - act = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE)); + act = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE); if (act) { low = lower_32_bits(queue_address >> 8); high = upper_32_bits(queue_address >> 8); - if (low == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE)) && - high == RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_BASE_HI))) + if (low == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE) && + high == RREG32_SOC15(GC, 0, mmCP_HQD_PQ_BASE_HI)) retval = true; } release_queue(adev); @@ -556,7 +556,7 @@ int kgd_gfx_v9_hqd_destroy(struct amdgpu_device *adev, void *mqd, end_jiffies = (utimeout * HZ / 1000) + jiffies; while (true) { - temp = RREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE)); + temp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE); if (!(temp & CP_HQD_ACTIVE__ACTIVE_MASK)) break; if (time_after(jiffies, end_jiffies)) { @@ -645,7 +645,7 @@ int kgd_gfx_v9_wave_control_execute(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); WREG32_SOC15_RLC_SHADOW(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val); - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd); + WREG32_SOC15(GC, 0, mmSQ_CMD, sq_cmd); data = REG_SET_FIELD(data, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1); @@ -722,7 +722,7 @@ static void get_wave_count(struct amdgpu_device *adev, int queue_idx, pipe_idx = queue_idx / adev->gfx.mec.num_queue_per_pipe; queue_slot = queue_idx % adev->gfx.mec.num_queue_per_pipe; soc15_grbm_select(adev, 1, pipe_idx, queue_slot, 0); - reg_val = RREG32(SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) + + reg_val = RREG32_SOC15_IP(GC, SOC15_REG_OFFSET(GC, 0, mmSPI_CSQ_WF_ACTIVE_COUNT_0) + queue_slot); *wave_cnt = reg_val & SPI_CSQ_WF_ACTIVE_COUNT_0__COUNT_MASK; if (*wave_cnt != 0) @@ -809,8 +809,7 @@ void kgd_gfx_v9_get_cu_occupancy(struct amdgpu_device *adev, int pasid, for (sh_idx = 0; sh_idx < sh_cnt; sh_idx++) { gfx_v9_0_select_se_sh(adev, se_idx, sh_idx, 0xffffffff); - queue_map = RREG32(SOC15_REG_OFFSET(GC, 0, - mmSPI_CSQ_WF_ACTIVE_STATUS)); + queue_map = RREG32_SOC15(GC, 0, mmSPI_CSQ_WF_ACTIVE_STATUS); /* * Assumption: queue map encodes following schema: four @@ -860,17 +859,17 @@ void kgd_gfx_v9_program_trap_handler_settings(struct amdgpu_device *adev, /* * Program TBA registers */ - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_LO), + WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_LO, lower_32_bits(tba_addr >> 8)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TBA_HI), + WREG32_SOC15(GC, 0, mmSQ_SHADER_TBA_HI, upper_32_bits(tba_addr >> 8)); /* * Program TMA registers */ - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_LO), + WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_LO, lower_32_bits(tma_addr >> 8)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_SHADER_TMA_HI), + WREG32_SOC15(GC, 0, mmSQ_SHADER_TMA_HI, upper_32_bits(tma_addr >> 8)); unlock_srbm(adev); -- 2.25.1 </div> </div> </div> </body> </html>