<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"> [Public] <div> <div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);"> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> </div> <div id="appendonsend"></div> <hr style="display:inline-block;width:98%" tabindex="-1"> <div id="divRplyFwdMsg" dir="ltr">From: Khaire, Rohit <Rohit.Khaire@amd.com> Sent: Friday, June 4, 2021 12:38 PM To: amd-gfx@lists.freedesktop.org <amd-gfx@lists.freedesktop.org>; Deucher, Alexander <Alexander.Deucher@amd.com>; Zhang, Hawking <Hawking.Zhang@amd.com>; Deng, Emily <Emily.Deng@amd.com>; Liu, Monk <Monk.Liu@amd.com>; Zhou, Peng Ju <PengJu.Zhou@amd.com>; Chen, Horace <Horace.Chen@amd.com> Cc: Ming, Davis <Davis.Ming@amd.com>; Khaire, Rohit <Rohit.Khaire@amd.com>; Koenig, Christian <Christian.Koenig@amd.com>; Khaire, Rohit <Rohit.Khaire@amd.com> Subject: [PATCH] drm/amdgpu: Modify GC register access to use _SOC15 macros <div> </div> </div> <div class="BodyFragment"> <div class="PlainText">In SRIOV environment, KMD should access GC registers with RLCG if GC indirect access flag enabled. Using _SOC15 read/write macros ensures that they go through RLC when flag is enabled. Signed-off-by: Rohit Khaire <rohit.khaire@amd.com> --- .../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c | 42 +++++++++---------- 1 file changed, 21 insertions(+), 21 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c index d39cff4a1fe3..1f5620cc3570 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c @@ -95,8 +95,8 @@ static void program_sh_mem_settings_v10_3(struct kgd_dev *kgd, uint32_t vmid, lock_srbm(kgd, 0, 0, 0, vmid); - WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_CONFIG), sh_mem_config); - WREG32(SOC15_REG_OFFSET(GC, 0, mmSH_MEM_BASES), sh_mem_bases); + WREG32_SOC15(GC, 0, mmSH_MEM_CONFIG, sh_mem_config); + WREG32_SOC15(GC, 0, mmSH_MEM_BASES, sh_mem_bases); /* APE1 no longer exists on GFX9 */ unlock_srbm(kgd); @@ -129,7 +129,7 @@ static int init_interrupts_v10_3(struct kgd_dev *kgd, uint32_t pipe_id) lock_srbm(kgd, 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); @@ -212,10 +212,10 @@ static int hqd_load_v10_3(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, pr_debug("kfd: set HIQ, mec:%d, pipe:%d, queue:%d.\n", mec, pipe, queue_id); - value = RREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS)); + value = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS); value = REG_SET_FIELD(value, RLC_CP_SCHEDULERS, scheduler1, ((mec << 5) | (pipe << 3) | queue_id | 0x80)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmRLC_CP_SCHEDULERS), value); + WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, value); } /* HQD registers extend from CP_MQD_BASE_ADDR to CP_HQD_EOP_WPTR_MEM. */ @@ -224,13 +224,13 @@ static int hqd_load_v10_3(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, for (reg = hqd_base; reg <= SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI); reg++) - WREG32(reg, mqd_hqd[reg - hqd_base]); + WREG32_SOC15_IP(GC, reg, mqd_hqd[reg - hqd_base]); /* Activate doorbell logic before triggering WPTR poll. */ data = REG_SET_FIELD(m->cp_hqd_pq_doorbell_control, CP_HQD_PQ_DOORBELL_CONTROL, DOORBELL_EN, 1); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL), data); + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_DOORBELL_CONTROL, data); if (wptr) { /* Don't read wptr with get_user because the user @@ -259,17 +259,17 @@ static int hqd_load_v10_3(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, guessed_wptr += m->cp_hqd_pq_wptr_lo & ~(queue_size - 1); guessed_wptr += (uint64_t)m->cp_hqd_pq_wptr_hi << 32; - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_LO), + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_LO, lower_32_bits(guessed_wptr)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_HI), + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_HI, upper_32_bits(guessed_wptr)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR), + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR, lower_32_bits((uint64_t)wptr)); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI), + WREG32_SOC15(GC, 0, mmCP_HQD_PQ_WPTR_POLL_ADDR_HI, upper_32_bits((uint64_t)wptr)); pr_debug("%s setting CP_PQ_WPTR_POLL_CNTL1 to %x\n", __func__, (uint32_t)get_queue_mask(adev, pipe_id, queue_id)); - 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)); } @@ -279,7 +279,7 @@ static int hqd_load_v10_3(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, CP_HQD_EOP_RPTR, INIT_FETCHER, 1)); data = REG_SET_FIELD(m->cp_hqd_active, CP_HQD_ACTIVE, ACTIVE, 1); - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_ACTIVE), data); + WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, data); release_queue(kgd); @@ -350,7 +350,7 @@ static int hqd_dump_v10_3(struct kgd_dev *kgd, if (WARN_ON_ONCE(i >= HQD_N_REGS)) \ break; \ (*dump)[i][0] = (addr) << 2; \ - (*dump)[i++][1] = RREG32(addr); \ + (*dump)[i++][1] = RREG32_SOC15_IP(GC, addr); \ } while (0) *dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL); @@ -482,13 +482,13 @@ static bool hqd_is_occupied_v10_3(struct kgd_dev *kgd, uint64_t queue_address, uint32_t low, high; acquire_queue(kgd, 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(kgd); @@ -542,11 +542,11 @@ static int hqd_destroy_v10_3(struct kgd_dev *kgd, void *mqd, break; } - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_DEQUEUE_REQUEST), type); + WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, type); 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)) { @@ -626,7 +626,7 @@ static int wave_control_execute_v10_3(struct kgd_dev *kgd, mutex_lock(&adev->grbm_idx_mutex); - WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), gfx_index_val); + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val); WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd); data = REG_SET_FIELD(data, GRBM_GFX_INDEX, @@ -636,7 +636,7 @@ static int wave_control_execute_v10_3(struct kgd_dev *kgd, data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SE_BROADCAST_WRITES, 1); - WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), data); + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, data); mutex_unlock(&adev->grbm_idx_mutex); return 0; -- 2.17.1 </div> </div> </div> </body> </html>