diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
31 files changed, 407 insertions, 188 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 108003bdf1e9..2e13c7c4b2b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -400,7 +400,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, mem_channel_number = vram_info->v30.channel_num; mem_channel_width = vram_info->v30.channel_width; if (vram_width) - *vram_width = mem_channel_number * (1 << mem_channel_width); + *vram_width = mem_channel_number * 16; break; default: return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 932dc93b2e63..33f791d92ddf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5220,11 +5220,14 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev) dev_info(adev->dev, "GPU mode1 reset\n"); + /* Cache the state before bus master disable. The saved config space + * values are used in other cases like restore after mode-2 reset. + */ + amdgpu_device_cache_pci_state(adev->pdev); + /* disable BM */ pci_clear_master(adev->pdev); - amdgpu_device_cache_pci_state(adev->pdev); - if (amdgpu_dpm_is_mode1_reset_supported(adev)) { dev_info(adev->dev, "GPU smu mode1 reset\n"); ret = amdgpu_dpm_mode1_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 055ba2ea4c12..662d0f28f358 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -41,8 +41,6 @@ #include <linux/dma-buf.h> #include <linux/dma-fence-array.h> #include <linux/pci-p2pdma.h> -#include <linux/pm_runtime.h> -#include "amdgpu_trace.h" /** * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation @@ -58,42 +56,11 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, struct drm_gem_object *obj = dmabuf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - int r; if (pci_p2pdma_distance(adev->pdev, attach->dev, false) < 0) attach->peer2peer = false; - r = pm_runtime_get_sync(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(1, __func__); - if (r < 0) - goto out; - return 0; - -out: - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); - return r; -} - -/** - * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation - * - * @dmabuf: DMA-buf where we remove the attachment from - * @attach: the attachment to remove - * - * Called when an attachment is removed from the DMA-buf. - */ -static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf, - struct dma_buf_attachment *attach) -{ - struct drm_gem_object *obj = dmabuf->priv; - struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - - pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); } /** @@ -267,7 +234,6 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, const struct dma_buf_ops amdgpu_dmabuf_ops = { .attach = amdgpu_dma_buf_attach, - .detach = amdgpu_dma_buf_detach, .pin = amdgpu_dma_buf_pin, .unpin = amdgpu_dma_buf_unpin, .map_dma_buf = amdgpu_dma_buf_map, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 10832b470448..bc3ac73b6b8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -181,7 +181,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr, seq, flags | AMDGPU_FENCE_FLAG_INT); pm_runtime_get_noresume(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(1, __func__); ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask]; if (unlikely(rcu_dereference_protected(*ptr, 1))) { struct dma_fence *old; @@ -309,7 +308,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) dma_fence_put(fence); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - trace_amdgpu_runpm_reference_dumps(0, __func__); } while (last_seq != seq); return true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 67c234bcf89f..3adaa4670103 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -108,6 +108,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, memset(&bp, 0, sizeof(bp)); *obj = NULL; + flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; bp.size = size; bp.byte_align = alignment; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index be4629cdac04..08b9dfb65335 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -684,12 +684,17 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring; struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst]; unsigned int ndw; - signed long r; + int r; uint32_t seq; - if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready || - !down_read_trylock(&adev->reset_domain->sem)) { + /* + * A GPU reset should flush all TLBs anyway, so no need to do + * this while one is ongoing. + */ + if (!down_read_trylock(&adev->reset_domain->sem)) + return 0; + if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) { if (adev->gmc.flush_tlb_needs_extra_type_2) adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, 2, all_hub, @@ -703,43 +708,40 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid, adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub, inst); - return 0; - } + r = 0; + } else { + /* 2 dwords flush + 8 dwords fence */ + ndw = kiq->pmf->invalidate_tlbs_size + 8; - /* 2 dwords flush + 8 dwords fence */ - ndw = kiq->pmf->invalidate_tlbs_size + 8; + if (adev->gmc.flush_tlb_needs_extra_type_2) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_2) - ndw += kiq->pmf->invalidate_tlbs_size; + if (adev->gmc.flush_tlb_needs_extra_type_0) + ndw += kiq->pmf->invalidate_tlbs_size; - if (adev->gmc.flush_tlb_needs_extra_type_0) - ndw += kiq->pmf->invalidate_tlbs_size; + spin_lock(&adev->gfx.kiq[inst].ring_lock); + amdgpu_ring_alloc(ring, ndw); + if (adev->gmc.flush_tlb_needs_extra_type_2) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); - spin_lock(&adev->gfx.kiq[inst].ring_lock); - amdgpu_ring_alloc(ring, ndw); - if (adev->gmc.flush_tlb_needs_extra_type_2) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub); + if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); - if (flush_type == 2 && adev->gmc.flush_tlb_needs_extra_type_0) - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 0, all_hub); + kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); + r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); + if (r) { + amdgpu_ring_undo(ring); + spin_unlock(&adev->gfx.kiq[inst].ring_lock); + goto error_unlock_reset; + } - kiq->pmf->kiq_invalidate_tlbs(ring, pasid, flush_type, all_hub); - r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); - if (r) { - amdgpu_ring_undo(ring); + amdgpu_ring_commit(ring); spin_unlock(&adev->gfx.kiq[inst].ring_lock); - goto error_unlock_reset; - } - - amdgpu_ring_commit(ring); - spin_unlock(&adev->gfx.kiq[inst].ring_lock); - r = amdgpu_fence_wait_polling(ring, seq, usec_timeout); - if (r < 1) { - dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r); - r = -ETIME; - goto error_unlock_reset; + if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) { + dev_err(adev->dev, "timeout waiting for kiq fence\n"); + r = -ETIME; + } } - r = 0; error_unlock_reset: up_read(&adev->reset_domain->sem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8d8c39be6129..c556c8b653fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -604,8 +604,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (!amdgpu_bo_support_uswc(bo->flags)) bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; - bo->tbo.bdev = &adev->mman.bdev; if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA | AMDGPU_GEM_DOMAIN_GDS)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 4bd4602d11b1..cef9dd0a012b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -640,6 +640,20 @@ static const char *psp_gfx_cmd_name(enum psp_gfx_cmd_id cmd_id) } } +static bool psp_err_warn(struct psp_context *psp) +{ + struct psp_gfx_cmd_resp *cmd = psp->cmd_buf_mem; + + /* This response indicates reg list is already loaded */ + if (amdgpu_ip_version(psp->adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 2) && + cmd->cmd_id == GFX_CMD_ID_LOAD_IP_FW && + cmd->cmd.cmd_load_ip_fw.fw_type == GFX_FW_TYPE_REG_LIST && + cmd->resp.status == TEE_ERROR_CANCEL) + return false; + + return true; +} + static int psp_cmd_submit_buf(struct psp_context *psp, struct amdgpu_firmware_info *ucode, @@ -699,10 +713,13 @@ psp_cmd_submit_buf(struct psp_context *psp, dev_warn(psp->adev->dev, "failed to load ucode %s(0x%X) ", amdgpu_ucode_name(ucode->ucode_id), ucode->ucode_id); - dev_warn(psp->adev->dev, - "psp gfx command %s(0x%X) failed and response status is (0x%X)\n", - psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id), psp->cmd_buf_mem->cmd_id, - psp->cmd_buf_mem->resp.status); + if (psp_err_warn(psp)) + dev_warn( + psp->adev->dev, + "psp gfx command %s(0x%X) failed and response status is (0x%X)\n", + psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id), + psp->cmd_buf_mem->cmd_id, + psp->cmd_buf_mem->resp.status); /* If any firmware (including CAP) load fails under SRIOV, it should * return failure to stop the VF from initializing. * Also return failure in case of timeout diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 7aafeb763e5d..383fce40d4dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -554,21 +554,6 @@ TRACE_EVENT(amdgpu_reset_reg_dumps, __entry->value) ); -TRACE_EVENT(amdgpu_runpm_reference_dumps, - TP_PROTO(uint32_t index, const char *func), - TP_ARGS(index, func), - TP_STRUCT__entry( - __field(uint32_t, index) - __string(func, func) - ), - TP_fast_assign( - __entry->index = index; - __assign_str(func); - ), - TP_printk("amdgpu runpm reference dump 0x%x: 0x%s\n", - __entry->index, - __get_str(func)) -); #undef AMDGPU_JOB_GET_TIMELINE_NAME #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index e30eecd02ae1..fde66225c481 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -3,6 +3,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_edid.h> #include <drm/drm_simple_kms_helper.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_vblank.h> #include "amdgpu.h" @@ -314,7 +315,13 @@ static int amdgpu_vkms_prepare_fb(struct drm_plane *plane, return 0; } afb = to_amdgpu_framebuffer(new_state->fb); - obj = new_state->fb->obj[0]; + + obj = drm_gem_fb_get_obj(new_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return -EINVAL; + } + rbo = gem_to_amdgpu_bo(obj); adev = amdgpu_ttm_adev(rbo->tbo.bdev); @@ -368,12 +375,19 @@ static void amdgpu_vkms_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state) { struct amdgpu_bo *rbo; + struct drm_gem_object *obj; int r; if (!old_state->fb) return; - rbo = gem_to_amdgpu_bo(old_state->fb->obj[0]); + obj = drm_gem_fb_get_obj(old_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return; + } + + rbo = gem_to_amdgpu_bo(obj); r = amdgpu_bo_reserve(rbo, false); if (unlikely(r)) { DRM_ERROR("failed to reserve rbo before unpin\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 7b16e8cca86a..f5b9f443cfdd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -4195,9 +4195,10 @@ static u32 gfx_v9_4_3_get_cu_active_bitmap(struct amdgpu_device *adev, int xcc_i static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, struct amdgpu_cu_info *cu_info) { - int i, j, k, counter, xcc_id, active_cu_number = 0; - u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; + int i, j, k, prev_counter, counter, xcc_id, active_cu_number = 0; + u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0, tmp; unsigned disable_masks[4 * 4]; + bool is_symmetric_cus; if (!adev || !cu_info) return -EINVAL; @@ -4215,6 +4216,7 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (xcc_id = 0; xcc_id < NUM_XCC(adev->gfx.xcc_mask); xcc_id++) { + is_symmetric_cus = true; for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; @@ -4242,6 +4244,15 @@ static int gfx_v9_4_3_get_cu_info(struct amdgpu_device *adev, ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8)); cu_info->ao_cu_bitmap[i][j] = ao_bitmap; } + if (i && is_symmetric_cus && prev_counter != counter) + is_symmetric_cus = false; + prev_counter = counter; + } + if (is_symmetric_cus) { + tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_RELAUNCH_DISABLE, 1); + tmp = REG_SET_FIELD(tmp, CP_CPC_DEBUG, CPC_HARVESTING_DISPATCH_DISABLE, 1); + WREG32_SOC15(GC, GET_INST(GC, xcc_id), regCP_CPC_DEBUG, tmp); } gfx_v9_4_3_xcc_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff, xcc_id); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 0d1407f25005..32d4519541c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -154,18 +154,18 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, void *pkt, int size, int api_status_off) { - int ndw = size / 4; - signed long r; - union MESAPI__MISC *x_pkt = pkt; - struct MES_API_STATUS *api_status; + union MESAPI__QUERY_MES_STATUS mes_status_pkt; + signed long timeout = 3000000; /* 3000 ms */ struct amdgpu_device *adev = mes->adev; struct amdgpu_ring *ring = &mes->ring; - unsigned long flags; - signed long timeout = 3000000; /* 3000 ms */ + struct MES_API_STATUS *api_status; + union MESAPI__MISC *x_pkt = pkt; const char *op_str, *misc_op_str; - u32 fence_offset; - u64 fence_gpu_addr; - u64 *fence_ptr; + unsigned long flags; + u64 status_gpu_addr; + u32 status_offset; + u64 *status_ptr; + signed long r; int ret; if (x_pkt->header.opcode >= MES_SCH_API_MAX) @@ -177,28 +177,38 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, /* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */ timeout = 15 * 600 * 1000; } - BUG_ON(size % 4 != 0); - ret = amdgpu_device_wb_get(adev, &fence_offset); + ret = amdgpu_device_wb_get(adev, &status_offset); if (ret) return ret; - fence_gpu_addr = - adev->wb.gpu_addr + (fence_offset * 4); - fence_ptr = (u64 *)&adev->wb.wb[fence_offset]; - *fence_ptr = 0; + + status_gpu_addr = adev->wb.gpu_addr + (status_offset * 4); + status_ptr = (u64 *)&adev->wb.wb[status_offset]; + *status_ptr = 0; spin_lock_irqsave(&mes->ring_lock, flags); - if (amdgpu_ring_alloc(ring, ndw)) { - spin_unlock_irqrestore(&mes->ring_lock, flags); - amdgpu_device_wb_free(adev, fence_offset); - return -ENOMEM; - } + r = amdgpu_ring_alloc(ring, (size + sizeof(mes_status_pkt)) / 4); + if (r) + goto error_unlock_free; api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off); - api_status->api_completion_fence_addr = fence_gpu_addr; + api_status->api_completion_fence_addr = status_gpu_addr; api_status->api_completion_fence_value = 1; - amdgpu_ring_write_multiple(ring, pkt, ndw); + amdgpu_ring_write_multiple(ring, pkt, size / 4); + + memset(&mes_status_pkt, 0, sizeof(mes_status_pkt)); + mes_status_pkt.header.type = MES_API_TYPE_SCHEDULER; + mes_status_pkt.header.opcode = MES_SCH_API_QUERY_SCHEDULER_STATUS; + mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; + mes_status_pkt.api_status.api_completion_fence_addr = + ring->fence_drv.gpu_addr; + mes_status_pkt.api_status.api_completion_fence_value = + ++ring->fence_drv.sync_seq; + + amdgpu_ring_write_multiple(ring, &mes_status_pkt, + sizeof(mes_status_pkt) / 4); + amdgpu_ring_commit(ring); spin_unlock_irqrestore(&mes->ring_lock, flags); @@ -206,15 +216,16 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, misc_op_str = mes_v11_0_get_misc_op_string(x_pkt); if (misc_op_str) - dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, misc_op_str); + dev_dbg(adev->dev, "MES msg=%s (%s) was emitted\n", op_str, + misc_op_str); else if (op_str) dev_dbg(adev->dev, "MES msg=%s was emitted\n", op_str); else - dev_dbg(adev->dev, "MES msg=%d was emitted\n", x_pkt->header.opcode); + dev_dbg(adev->dev, "MES msg=%d was emitted\n", + x_pkt->header.opcode); - r = amdgpu_mes_fence_wait_polling(fence_ptr, (u64)1, timeout); - amdgpu_device_wb_free(adev, fence_offset); - if (r < 1) { + r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout); + if (r < 1 || !*status_ptr) { if (misc_op_str) dev_err(adev->dev, "MES failed to respond to msg=%s (%s)\n", @@ -229,10 +240,19 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes, while (halt_if_hws_hang) schedule(); - return -ETIMEDOUT; + r = -ETIMEDOUT; + goto error_wb_free; } + amdgpu_device_wb_free(adev, status_offset); return 0; + +error_unlock_free: + spin_unlock_irqrestore(&mes->ring_lock, flags); + +error_wb_free: + amdgpu_device_wb_free(adev, status_offset); + return r; } static int convert_to_mes_queue_type(int queue_type) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index 7566973ed8f5..37b5ddd6f13b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -464,8 +464,9 @@ struct psp_gfx_rb_frame #define PSP_ERR_UNKNOWN_COMMAND 0x00000100 enum tee_error_code { - TEE_SUCCESS = 0x00000000, - TEE_ERROR_NOT_SUPPORTED = 0xFFFF000A, + TEE_SUCCESS = 0x00000000, + TEE_ERROR_CANCEL = 0xFFFF0002, + TEE_ERROR_NOT_SUPPORTED = 0xFFFF000A, }; #endif /* _PSP_TEE_GFX_IF_H_ */ diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c index f08a32c18694..40b28298af30 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v14_0.c @@ -32,7 +32,9 @@ #include "mp/mp_14_0_2_sh_mask.h" MODULE_FIRMWARE("amdgpu/psp_14_0_2_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_14_0_2_ta.bin"); MODULE_FIRMWARE("amdgpu/psp_14_0_3_sos.bin"); +MODULE_FIRMWARE("amdgpu/psp_14_0_3_ta.bin"); /* For large FW files the time to complete can be very long */ #define USBC_PD_POLLING_LIMIT_S 240 @@ -66,6 +68,9 @@ static int psp_v14_0_init_microcode(struct psp_context *psp) err = psp_init_sos_microcode(psp, ucode_prefix); if (err) return err; + err = psp_init_ta_microcode(psp, ucode_prefix); + if (err) + return err; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 5fcd4f778dc3..47b8b49da8a7 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -8,7 +8,7 @@ config DRM_AMD_DC depends on BROKEN || !CC_IS_CLANG || ARM64 || RISCV || SPARC64 || X86_64 select SND_HDA_COMPONENT if SND_HDA_CORE # !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752 - select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && (!ARM64 || !CC_IS_CLANG) + select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || RISCV)) help Choose this option if you want to use the new display engine support for AMDGPU. This adds required support for Vega and diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f1d67c6f4b98..e9ac20bed0f2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -9169,9 +9169,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) trace_amdgpu_dm_atomic_commit_tail_begin(state); - if (dm->dc->caps.ips_support && dm->dc->idle_optimizations_allowed) - dc_allow_idle_optimizations(dm->dc, false); - drm_atomic_helper_update_legacy_modeset_state(dev, state); drm_dp_mst_atomic_wait_for_dependencies(state); @@ -11440,6 +11437,12 @@ void amdgpu_dm_trigger_timing_sync(struct drm_device *dev) mutex_unlock(&adev->dm.dc_lock); } +static inline void amdgpu_dm_exit_ips_for_hw_access(struct dc *dc) +{ + if (dc->ctx->dmub_srv && !dc->ctx->dmub_srv->idle_exit_counter) + dc_exit_ips_for_hw_access(dc); +} + void dm_write_reg_func(const struct dc_context *ctx, uint32_t address, u32 value, const char *func_name) { @@ -11450,6 +11453,8 @@ void dm_write_reg_func(const struct dc_context *ctx, uint32_t address, return; } #endif + + amdgpu_dm_exit_ips_for_hw_access(ctx->dc); cgs_write_register(ctx->cgs_device, address, value); trace_amdgpu_dc_wreg(&ctx->perf_trace->write_count, address, value); } @@ -11473,6 +11478,8 @@ uint32_t dm_read_reg_func(const struct dc_context *ctx, uint32_t address, return 0; } + amdgpu_dm_exit_ips_for_hw_access(ctx->dc); + value = cgs_read_register(ctx->cgs_device, address); trace_amdgpu_dc_rreg(&ctx->perf_trace->read_count, address, value); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c index 60f251cf973b..beed7adbbd43 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c @@ -177,7 +177,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = { .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, .urgent_latency_vm_data_only_us = 4.0, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 34.0, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c index e4f333d4fb54..a201dbb743d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c @@ -215,7 +215,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_51_soc = { .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, .urgent_latency_vm_data_only_us = 4.0, - .dram_clock_change_latency_us = 11.72, + .dram_clock_change_latency_us = 34, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 5295f52e4fc8..dcced89c07b3 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -1439,3 +1439,75 @@ void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx, } } } + +static bool should_avoid_empty_tu(struct pipe_ctx *pipe_ctx) +{ + /* Calculate average pixel count per TU, return false if under ~2.00 to + * avoid empty TUs. This is only required for DPIA tunneling as empty TUs + * are legal to generate for native DP links. Assume TU size 64 as there + * is currently no scenario where it's reprogrammed from HW default. + * MTPs have no such limitation, so this does not affect MST use cases. + */ + unsigned int pix_clk_mhz; + unsigned int symclk_mhz; + unsigned int avg_pix_per_tu_x1000; + unsigned int tu_size_bytes = 64; + struct dc_crtc_timing *timing = &pipe_ctx->stream->timing; + struct dc_link_settings *link_settings = &pipe_ctx->link_config.dp_link_settings; + const struct dc *dc = pipe_ctx->stream->link->dc; + + if (pipe_ctx->stream->link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA) + return false; + + // Not necessary for MST configurations + if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) + return false; + + pix_clk_mhz = timing->pix_clk_100hz / 10000; + + // If this is true, can't block due to dynamic ODM + if (pix_clk_mhz > dc->clk_mgr->bw_params->clk_table.entries[0].dispclk_mhz) + return false; + + switch (link_settings->link_rate) { + case LINK_RATE_LOW: + symclk_mhz = 162; + break; + case LINK_RATE_HIGH: + symclk_mhz = 270; + break; + case LINK_RATE_HIGH2: + symclk_mhz = 540; + break; + case LINK_RATE_HIGH3: + symclk_mhz = 810; + break; + default: + // We shouldn't be tunneling any other rates, something is wrong + ASSERT(0); + return false; + } + + avg_pix_per_tu_x1000 = (1000 * pix_clk_mhz * tu_size_bytes) + / (symclk_mhz * link_settings->lane_count); + + // Add small empirically-decided margin to account for potential jitter + return (avg_pix_per_tu_x1000 < 2020); +} + +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx) +{ + struct dc *dc = pipe_ctx->stream->ctx->dc; + + if (!is_h_timing_divisible_by_2(pipe_ctx->stream)) + return false; + + if (should_avoid_empty_tu(pipe_ctx)) + return false; + + if (dc_is_dp_signal(pipe_ctx->stream->signal) && !dc->link_srv->dp_is_128b_132b_signal(pipe_ctx) && + dc->debug.enable_dp_dig_pixel_rate_div_policy) + return true; + + return false; +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h index a731c8880d60..f0ea7d1511ae 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.h @@ -95,4 +95,6 @@ void dcn35_set_static_screen_control(struct pipe_ctx **pipe_ctx, void dcn35_set_long_vblank(struct pipe_ctx **pipe_ctx, int num_pipes, uint32_t v_total_min, uint32_t v_total_max); +bool dcn35_is_dp_dig_pixel_rate_div_policy(struct pipe_ctx *pipe_ctx); + #endif /* __DC_HWSS_DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index df3bf77f3fb4..199781233fd5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -158,7 +158,7 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .set_pixels_per_cycle = dcn32_set_pixels_per_cycle, - .is_dp_dig_pixel_rate_div_policy = dcn32_is_dp_dig_pixel_rate_div_policy, + .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index a01d0842bf8e..d487dfcd219b 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1590,9 +1590,17 @@ static bool retrieve_link_cap(struct dc_link *link) return false; } - if (dp_is_lttpr_present(link)) + if (dp_is_lttpr_present(link)) { configure_lttpr_mode_transparent(link); + // Echo TOTAL_LTTPR_CNT back downstream + core_link_write_dpcd( + link, + DP_TOTAL_LTTPR_CNT, + &link->dpcd_caps.lttpr_caps.phy_repeater_cnt, + sizeof(link->dpcd_caps.lttpr_caps.phy_repeater_cnt)); + } + /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h index 914f28e9f224..aee5170f5fb2 100644 --- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h +++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h @@ -177,4 +177,9 @@ enum dpcd_psr_sink_states { #define DP_SINK_PR_PIXEL_DEVIATION_PER_LINE 0x379 #define DP_SINK_PR_MAX_NUMBER_OF_DEVIATION_LINE 0x37A +/* Remove once drm_dp_helper.h is updated upstream */ +#ifndef DP_TOTAL_LTTPR_CNT +#define DP_TOTAL_LTTPR_CNT 0xF000A /* 2.1 */ +#endif + #endif /* __DAL_DPCD_DEFS_H__ */ diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h index 2e8e6c9875f6..f83ace2d7ec3 100644 --- a/drivers/gpu/drm/amd/include/pptable.h +++ b/drivers/gpu/drm/amd/include/pptable.h @@ -477,31 +477,30 @@ typedef struct _ATOM_PPLIB_STATE_V2 } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ - //how many states we have - UCHAR ucNumEntries; - - ATOM_PPLIB_STATE_V2 states[1]; + //how many states we have + UCHAR ucNumEntries; + + ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */; }StateArray; typedef struct _ClockInfoArray{ - //how many clock levels we have - UCHAR ucNumEntries; - - //sizeof(ATOM_PPLIB_CLOCK_INFO) - UCHAR ucEntrySize; - - UCHAR clockInfo[]; + //how many clock levels we have + UCHAR ucNumEntries; + + //sizeof(ATOM_PPLIB_CLOCK_INFO) + UCHAR ucEntrySize; + + UCHAR clockInfo[]; }ClockInfoArray; typedef struct _NonClockInfoArray{ + //how many non-clock levels we have. normally should be same as number of states + UCHAR ucNumEntries; + //sizeof(ATOM_PPLIB_NONCLOCK_INFO) + UCHAR ucEntrySize; - //how many non-clock levels we have. normally should be same as number of states - UCHAR ucNumEntries; - //sizeof(ATOM_PPLIB_NONCLOCK_INFO) - UCHAR ucEntrySize; - - ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[]; + ATOM_PPLIB_NONCLOCK_INFO nonClockInfo[] __counted_by(ucNumEntries); }NonClockInfoArray; typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record @@ -513,8 +512,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Record typedef struct _ATOM_PPLIB_Clock_Voltage_Dependency_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_Clock_Voltage_Dependency_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_Clock_Voltage_Dependency_Table; typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record @@ -529,8 +530,10 @@ typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_Clock_Voltage_Limit_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_Clock_Voltage_Limit_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_Clock_Voltage_Limit_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_Clock_Voltage_Limit_Table; union _ATOM_PPLIB_CAC_Leakage_Record @@ -553,8 +556,10 @@ typedef union _ATOM_PPLIB_CAC_Leakage_Record ATOM_PPLIB_CAC_Leakage_Record; typedef struct _ATOM_PPLIB_CAC_Leakage_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_CAC_Leakage_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_CAC_Leakage_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_CAC_Leakage_Table; typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record @@ -568,8 +573,10 @@ typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Record typedef struct _ATOM_PPLIB_PhaseSheddingLimits_Table { - UCHAR ucNumEntries; // Number of entries. - ATOM_PPLIB_PhaseSheddingLimits_Record entries[1]; // Dynamically allocate entries. + // Number of entries. + UCHAR ucNumEntries; + // Dynamically allocate entries. + ATOM_PPLIB_PhaseSheddingLimits_Record entries[] __counted_by(ucNumEntries); }ATOM_PPLIB_PhaseSheddingLimits_Table; typedef struct _VCEClockInfo{ @@ -580,8 +587,8 @@ typedef struct _VCEClockInfo{ }VCEClockInfo; typedef struct _VCEClockInfoArray{ - UCHAR ucNumEntries; - VCEClockInfo entries[1]; + UCHAR ucNumEntries; + VCEClockInfo entries[] __counted_by(ucNumEntries); }VCEClockInfoArray; typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record @@ -592,8 +599,8 @@ typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table { - UCHAR numEntries; - ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_VCE_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_VCE_Clock_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_VCE_State_Record @@ -604,8 +611,8 @@ typedef struct _ATOM_PPLIB_VCE_State_Record typedef struct _ATOM_PPLIB_VCE_State_Table { - UCHAR numEntries; - ATOM_PPLIB_VCE_State_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_VCE_State_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_VCE_State_Table; @@ -626,8 +633,8 @@ typedef struct _UVDClockInfo{ }UVDClockInfo; typedef struct _UVDClockInfoArray{ - UCHAR ucNumEntries; - UVDClockInfo entries[1]; + UCHAR ucNumEntries; + UVDClockInfo entries[] __counted_by(ucNumEntries); }UVDClockInfoArray; typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record @@ -638,8 +645,8 @@ typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record typedef struct _ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table { - UCHAR numEntries; - ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_UVD_Clock_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_UVD_Clock_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_UVD_Table @@ -657,8 +664,8 @@ typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Record }ATOM_PPLIB_SAMClk_Voltage_Limit_Record; typedef struct _ATOM_PPLIB_SAMClk_Voltage_Limit_Table{ - UCHAR numEntries; - ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[]; + UCHAR numEntries; + ATOM_PPLIB_SAMClk_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_SAMClk_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_SAMU_Table @@ -675,8 +682,8 @@ typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Record }ATOM_PPLIB_ACPClk_Voltage_Limit_Record; typedef struct _ATOM_PPLIB_ACPClk_Voltage_Limit_Table{ - UCHAR numEntries; - ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[1]; + UCHAR numEntries; + ATOM_PPLIB_ACPClk_Voltage_Limit_Record entries[] __counted_by(numEntries); }ATOM_PPLIB_ACPClk_Voltage_Limit_Table; typedef struct _ATOM_PPLIB_ACP_Table @@ -743,9 +750,9 @@ typedef struct ATOM_PPLIB_VQ_Budgeting_Record{ } ATOM_PPLIB_VQ_Budgeting_Record; typedef struct ATOM_PPLIB_VQ_Budgeting_Table { - UCHAR revid; - UCHAR numEntries; - ATOM_PPLIB_VQ_Budgeting_Record entries[1]; + UCHAR revid; + UCHAR numEntries; + ATOM_PPLIB_VQ_Budgeting_Record entries[] __counted_by(numEntries); } ATOM_PPLIB_VQ_Budgeting_Table; #pragma pack() diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c index 6bb42d04b247..e8b6989a40f3 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c @@ -164,6 +164,8 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev, for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++) { if (table[i].ulSupportedSCLK != 0) { + if (table[i].usVoltageIndex >= SUMO_MAX_NUMBER_VOLTAGES) + continue; vid_mapping_table->entries[table[i].usVoltageIndex].vid_7bit = table[i].usVoltageID; vid_mapping_table->entries[table[i].usVoltageIndex].vid_2bit = diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 7789b313285c..e1796ecf9c05 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -324,6 +324,18 @@ static int smu_dpm_set_umsch_mm_enable(struct smu_context *smu, return ret; } +static int smu_set_mall_enable(struct smu_context *smu) +{ + int ret = 0; + + if (!smu->ppt_funcs->set_mall_enable) + return 0; + + ret = smu->ppt_funcs->set_mall_enable(smu); + + return ret; +} + /** * smu_dpm_set_power_gate - power gate/ungate the specific IP block * @@ -1791,6 +1803,7 @@ static int smu_hw_init(void *handle) smu_dpm_set_jpeg_enable(smu, true); smu_dpm_set_vpe_enable(smu, true); smu_dpm_set_umsch_mm_enable(smu, true); + smu_set_mall_enable(smu); smu_set_gfx_cgpg(smu, true); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 0917dec8efe3..64ccdb5f14ea 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -1395,6 +1395,11 @@ struct pptable_funcs { int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable); /** + * @set_mall_enable: Init MALL power gating control. + */ + int (*set_mall_enable)(struct smu_context *smu); + + /** * @notify_rlc_state: Notify RLC power state to SMU. */ int (*notify_rlc_state)(struct smu_context *smu, bool en); diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h index c4dc5881d8df..e7f5ef49049f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v14_0_0_ppsmc.h @@ -106,8 +106,8 @@ #define PPSMC_MSG_DisableLSdma 0x35 ///< Disable LSDMA #define PPSMC_MSG_SetSoftMaxVpe 0x36 ///< #define PPSMC_MSG_SetSoftMinVpe 0x37 ///< -#define PPSMC_MSG_AllocMALLCache 0x38 ///< Allocating MALL Cache -#define PPSMC_MSG_ReleaseMALLCache 0x39 ///< Releasing MALL Cache +#define PPSMC_MSG_MALLPowerController 0x38 ///< Set MALL control +#define PPSMC_MSG_MALLPowerState 0x39 ///< Enter/Exit MALL PG #define PPSMC_Message_Count 0x3A ///< Total number of PPSMC messages /** @}*/ diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h index c48214e3dc8e..2e32b085824a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_types.h @@ -272,7 +272,9 @@ __SMU_DUMMY_MAP(SetSoftMinVpe), \ __SMU_DUMMY_MAP(GetMetricsVersion), \ __SMU_DUMMY_MAP(EnableUCLKShadow), \ - __SMU_DUMMY_MAP(RmaDueToBadPageThreshold), + __SMU_DUMMY_MAP(RmaDueToBadPageThreshold), \ + __SMU_DUMMY_MAP(MALLPowerController), \ + __SMU_DUMMY_MAP(MALLPowerState), #undef __SMU_DUMMY_MAP #define __SMU_DUMMY_MAP(type) SMU_MSG_##type diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c index bc241b593db1..b6257f34a7c6 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c @@ -226,15 +226,17 @@ static int smu_v13_0_4_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && adev->in_s4) { - /* Adds a GFX reset as workaround just before sending the - * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering - * an invalid state. - */ - ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, - SMU_RESET_MODE_2, NULL); - if (ret) - return ret; + if (!en && !adev->in_s0ix) { + if (adev->in_s4) { + /* Adds a GFX reset as workaround just before sending the + * MP1_UNLOAD message to prevent GC/RLC/PMFW from entering + * an invalid state. + */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, + SMU_RESET_MODE_2, NULL); + if (ret) + return ret; + } ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index e4419e1561ef..18abfbd6d059 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -52,6 +52,19 @@ #define mmMP1_SMN_C2PMSG_90 0x029a #define mmMP1_SMN_C2PMSG_90_BASE_IDX 0 +/* MALLPowerController message arguments (Defines for the Cache mode control) */ +#define SMU_MALL_PMFW_CONTROL 0 +#define SMU_MALL_DRIVER_CONTROL 1 + +/* + * MALLPowerState message arguments + * (Defines for the Allocate/Release Cache mode if in driver mode) + */ +#define SMU_MALL_EXIT_PG 0 +#define SMU_MALL_ENTER_PG 1 + +#define SMU_MALL_PG_CONFIG_DEFAULT SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON + #define FEATURE_MASK(feature) (1ULL << feature) #define SMC_DPM_FEATURE ( \ FEATURE_MASK(FEATURE_CCLK_DPM_BIT) | \ @@ -66,6 +79,12 @@ FEATURE_MASK(FEATURE_GFX_DPM_BIT) | \ FEATURE_MASK(FEATURE_VPE_DPM_BIT)) +enum smu_mall_pg_config { + SMU_MALL_PG_CONFIG_PMFW_CONTROL = 0, + SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON = 1, + SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_OFF = 2, +}; + static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(TestMessage, PPSMC_MSG_TestMessage, 1), MSG_MAP(GetSmuVersion, PPSMC_MSG_GetPmfwVersion, 1), @@ -113,6 +132,8 @@ static struct cmn2asic_msg_mapping smu_v14_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(PowerDownUmsch, PPSMC_MSG_PowerDownUmsch, 1), MSG_MAP(SetSoftMaxVpe, PPSMC_MSG_SetSoftMaxVpe, 1), MSG_MAP(SetSoftMinVpe, PPSMC_MSG_SetSoftMinVpe, 1), + MSG_MAP(MALLPowerController, PPSMC_MSG_MALLPowerController, 1), + MSG_MAP(MALLPowerState, PPSMC_MSG_MALLPowerState, 1), }; static struct cmn2asic_mapping smu_v14_0_0_feature_mask_map[SMU_FEATURE_COUNT] = { @@ -1423,6 +1444,57 @@ static int smu_v14_0_common_get_dpm_table(struct smu_context *smu, struct dpm_cl return 0; } +static int smu_v14_0_1_init_mall_power_gating(struct smu_context *smu, enum smu_mall_pg_config pg_config) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + if (pg_config == SMU_MALL_PG_CONFIG_PMFW_CONTROL) { + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerController, + SMU_MALL_PMFW_CONTROL, NULL); + if (ret) { + dev_err(adev->dev, "Init MALL PMFW CONTROL Failure\n"); + return ret; + } + } else { + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerController, + SMU_MALL_DRIVER_CONTROL, NULL); + if (ret) { + dev_err(adev->dev, "Init MALL Driver CONTROL Failure\n"); + return ret; + } + + if (pg_config == SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_ON) { + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerState, + SMU_MALL_EXIT_PG, NULL); + if (ret) { + dev_err(adev->dev, "EXIT MALL PG Failure\n"); + return ret; + } + } else if (pg_config == SMU_MALL_PG_CONFIG_DRIVER_CONTROL_ALWAYS_OFF) { + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_MALLPowerState, + SMU_MALL_ENTER_PG, NULL); + if (ret) { + dev_err(adev->dev, "Enter MALL PG Failure\n"); + return ret; + } + } + } + + return ret; +} + +static int smu_v14_0_common_set_mall_enable(struct smu_context *smu) +{ + enum smu_mall_pg_config pg_config = SMU_MALL_PG_CONFIG_DEFAULT; + int ret = 0; + + if (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 1)) + ret = smu_v14_0_1_init_mall_power_gating(smu, pg_config); + + return ret; +} + static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .check_fw_version = smu_v14_0_check_fw_version, @@ -1454,6 +1526,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .dpm_set_vpe_enable = smu_v14_0_0_set_vpe_enable, .dpm_set_umsch_mm_enable = smu_v14_0_0_set_umsch_mm_enable, .get_dpm_clock_table = smu_v14_0_common_get_dpm_table, + .set_mall_enable = smu_v14_0_common_set_mall_enable, }; static void smu_v14_0_0_set_smu_mailbox_registers(struct smu_context *smu) |