[PATCH v5 03/10] drm/amdgpu: Modify GC register access from MMIO to RLCG in file kfd_v10*
Felix Kuehling
felix.kuehling at amd.com
Thu May 20 04:33:12 UTC 2021
Am 2021-05-17 um 10:39 a.m. schrieb Peng Ju Zhou:
> In SRIOV environment, KMD should access GC registers
> with RLCG if GC indirect access flag enabled.
>
> Signed-off-by: Peng Ju Zhou <PengJu.Zhou at amd.com>
This patch is
Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>
> ---
> .../drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c | 42 +++++++++----------
> 1 file changed, 21 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
> index 62aa1a6f64ed..491acdf92f73 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
> @@ -96,8 +96,8 @@ static void kgd_program_sh_mem_settings(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);
> @@ -161,7 +161,7 @@ static int kgd_init_interrupts(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);
>
> @@ -239,13 +239,13 @@ static int kgd_hqd_load(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
> @@ -274,27 +274,27 @@ static int kgd_hqd_load(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));
> }
>
> /* Start the EOP fetcher */
> - WREG32(SOC15_REG_OFFSET(GC, 0, mmCP_HQD_EOP_RPTR),
> + WREG32_SOC15(GC, 0, mmCP_HQD_EOP_RPTR,
> REG_SET_FIELD(m->cp_hqd_eop_rptr,
> 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);
>
> @@ -365,7 +365,7 @@ static int kgd_hqd_dump(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);
> @@ -497,13 +497,13 @@ static bool kgd_hqd_is_occupied(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);
> @@ -621,11 +621,11 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
> preempt_enable();
> #endif
>
> - 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)) {
> @@ -716,8 +716,8 @@ static int kgd_wave_control_execute(struct kgd_dev *kgd,
>
> mutex_lock(&adev->grbm_idx_mutex);
>
> - WREG32(SOC15_REG_OFFSET(GC, 0, mmGRBM_GFX_INDEX), gfx_index_val);
> - WREG32(SOC15_REG_OFFSET(GC, 0, mmSQ_CMD), sq_cmd);
> + WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX, gfx_index_val);
> + WREG32_SOC15(GC, 0, mmSQ_CMD, sq_cmd);
>
> data = REG_SET_FIELD(data, GRBM_GFX_INDEX,
> INSTANCE_BROADCAST_WRITES, 1);
> @@ -726,7 +726,7 @@ static int kgd_wave_control_execute(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;
More information about the amd-gfx
mailing list