diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
43 files changed, 383 insertions, 125 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 6b74df446694..d148a1bd85e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -195,6 +195,7 @@ extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; extern int amdgpu_smu_pptable_id; extern uint amdgpu_dc_feature_mask; +extern uint amdgpu_freesync_vid_mode; extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dc_visual_confirm; extern uint amdgpu_dm_abm_level; @@ -242,6 +243,7 @@ extern int amdgpu_num_kcq; #define AMDGPU_VCNFW_LOG_SIZE (32 * 1024) extern int amdgpu_vcnfw_log; +extern int amdgpu_sg_display; #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index b15091d8310d..3b5c53712d31 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2099,7 +2099,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b } amdgpu_amdkfd_remove_eviction_fence( - bo, bo->kfd_bo->process_info->eviction_fence); + bo, bo->vm_bo->vm->process_info->eviction_fence); amdgpu_bo_unreserve(bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 8516c814bc9b..7af3041ccd0e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -61,6 +61,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, amdgpu_ctx_put(p->ctx); return -ECANCELED; } + + amdgpu_sync_create(&p->sync); return 0; } @@ -452,18 +454,6 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p, } r = amdgpu_sync_fence(&p->sync, fence); - if (r) - goto error; - - /* - * When we have an explicit dependency it might be necessary to insert a - * pipeline sync to make sure that all caches etc are flushed and the - * next job actually sees the results from the previous one. - */ - if (fence->context == p->gang_leader->base.entity->fence_context) - r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); - -error: dma_fence_put(fence); return r; } @@ -1188,10 +1178,19 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + struct drm_gpu_scheduler *sched; struct amdgpu_bo_list_entry *e; + struct dma_fence *fence; unsigned int i; int r; + r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]); + if (r) { + if (r != -ERESTARTSYS) + DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); + return r; + } + list_for_each_entry(e, &p->validated, tv.head) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); struct dma_resv *resv = bo->tbo.base.resv; @@ -1211,10 +1210,27 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) return r; } - r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]); - if (r && r != -ERESTARTSYS) - DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); - return r; + sched = p->gang_leader->base.entity->rq->sched; + while ((fence = amdgpu_sync_get_fence(&p->sync))) { + struct drm_sched_fence *s_fence = to_drm_sched_fence(fence); + + /* + * When we have an dependency it might be necessary to insert a + * pipeline sync to make sure that all caches etc are flushed and the + * next job actually sees the results from the previous one + * before we start executing on the same scheduler ring. + */ + if (!s_fence || s_fence->sched != sched) { + dma_fence_put(fence); + continue; + } + + r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); + dma_fence_put(fence); + if (r) + return r; + } + return 0; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1254,9 +1270,12 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, continue; fence = &p->jobs[i]->base.s_fence->scheduled; + dma_fence_get(fence); r = drm_sched_job_add_dependency(&leader->base, fence); - if (r) + if (r) { + dma_fence_put(fence); goto error_cleanup; + } } if (p->gang_size > 1) { @@ -1344,6 +1363,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) { unsigned i; + amdgpu_sync_free(&parser->sync); for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); kfree(parser->post_deps[i].chain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index afe6af9c0138..fbf2f24169eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -36,6 +36,7 @@ #include <generated/utsrelease.h> #include <linux/pci-p2pdma.h> +#include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> @@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); #define AMDGPU_MAX_RETRY_LIMIT 2 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL) +static const struct drm_driver amdgpu_kms_driver; + const char *amdgpu_asic_name[] = { "TAHITI", "PITCAIRN", @@ -3687,6 +3690,11 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (r) return r; + /* Get rid of things like offb */ + r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver); + if (r) + return r; + /* Enable TMZ based on IP_VERSION */ amdgpu_gmc_tmz_set(adev); @@ -4260,6 +4268,9 @@ exit: } adev->in_suspend = false; + if (adev->enable_mes) + amdgpu_mes_self_test(adev); + if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) DRM_WARN("smart shift update failed\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b4f2d61ea0d5..3fe277bc233f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -23,7 +23,6 @@ */ #include <drm/amdgpu_drm.h> -#include <drm/drm_aperture.h> #include <drm/drm_drv.h> #include <drm/drm_fbdev_generic.h> #include <drm/drm_gem.h> @@ -181,11 +180,13 @@ int amdgpu_mes_kiq; int amdgpu_noretry = -1; int amdgpu_force_asic_type = -1; int amdgpu_tmz = -1; /* auto */ +uint amdgpu_freesync_vid_mode; int amdgpu_reset_method = -1; /* auto */ int amdgpu_num_kcq = -1; int amdgpu_smartshift_bias; int amdgpu_use_xgmi_p2p = 1; int amdgpu_vcnfw_log; +int amdgpu_sg_display = -1; /* auto */ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -880,6 +881,32 @@ MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on) module_param_named(tmz, amdgpu_tmz, int, 0444); /** + * DOC: freesync_video (uint) + * Enable the optimization to adjust front porch timing to achieve seamless + * mode change experience when setting a freesync supported mode for which full + * modeset is not needed. + * + * The Display Core will add a set of modes derived from the base FreeSync + * video mode into the corresponding connector's mode list based on commonly + * used refresh rates and VRR range of the connected display, when users enable + * this feature. From the userspace perspective, they can see a seamless mode + * change experience when the change between different refresh rates under the + * same resolution. Additionally, userspace applications such as Video playback + * can read this modeset list and change the refresh rate based on the video + * frame rate. Finally, the userspace can also derive an appropriate mode for a + * particular refresh rate based on the FreeSync Mode and add it to the + * connector's mode list. + * + * Note: This is an experimental feature. + * + * The default value: 0 (off). + */ +MODULE_PARM_DESC( + freesync_video, + "Enable freesync modesetting optimization feature (0 = off (default), 1 = on)"); +module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444); + +/** * DOC: reset_method (int) * GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco) */ @@ -906,6 +933,16 @@ MODULE_PARM_DESC(vcnfw_log, "Enable vcnfw log(0 = disable (default value), 1 = e module_param_named(vcnfw_log, amdgpu_vcnfw_log, int, 0444); /** + * DOC: sg_display (int) + * Disable S/G (scatter/gather) display (i.e., display from system memory). + * This option is only relevant on APUs. Set this option to 0 to disable + * S/G display if you experience flickering or other issues under memory + * pressure and report the issue. + */ +MODULE_PARM_DESC(sg_display, "S/G Display (-1 = auto (default), 0 = disable)"); +module_param_named(sg_display, amdgpu_sg_display, int, 0444); + +/** * DOC: smu_pptable_id (int) * Used to override pptable id. id = 0 use VBIOS pptable. * id > 0 use the soft pptable with specicfied id. @@ -2095,11 +2132,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, } #endif - /* Get rid of things like offb */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver); - if (ret) - return ret; - adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev); if (IS_ERR(adev)) return PTR_ERR(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 00444203220d..faff4a3f96e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -618,7 +618,13 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev) if (!ring || !ring->fence_drv.initialized) continue; - if (!ring->no_scheduler) + /* + * Notice we check for sched.ops since there's some + * override on the meaning of sched.ready by amdgpu. + * The natural check would be sched.ready, which is + * set as drm_sched_init() finishes... + */ + if (ring->sched.ops) drm_sched_fini(&ring->sched); for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 23692e5d4d13..3380daf42da8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -156,6 +156,9 @@ static bool amdgpu_gfx_is_compute_multipipe_capable(struct amdgpu_device *adev) return amdgpu_compute_multipipe == 1; } + if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0)) + return true; + /* FIXME: spreading the queues across pipes causes perf regressions * on POLARIS11 compute workloads */ if (adev->asic_type == CHIP_POLARIS11) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index fcb711a11a5b..3f07b1a2ce47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -497,6 +497,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, !--id_mgr->reserved_use_count) { /* give the reserved ID back to normal round robin */ list_add(&id_mgr->reserved->list, &id_mgr->ids_lru); + id_mgr->reserved = NULL; } vm->reserved_vmid[vmhub] = false; mutex_unlock(&id_mgr->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 9e549923622b..c3d9d75143f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -161,8 +161,14 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) struct dma_fence *f; unsigned i; - /* use sched fence if available */ - f = job->base.s_fence ? &job->base.s_fence->finished : &job->hw_fence; + /* Check if any fences where initialized */ + if (job->base.s_fence && job->base.s_fence->finished.ops) + f = &job->base.s_fence->finished; + else if (job->hw_fence.ops) + f = &job->hw_fence; + else + f = NULL; + for (i = 0; i < job->num_ibs; ++i) amdgpu_ib_free(ring->adev, &job->ibs[i], f); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4e684c2afc70..25a68d8888e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev, return true; fail: - DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, - man->size); + if (man) + DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, + man->size); return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index f752c7ae7f60..3989e755a5b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -295,7 +295,7 @@ struct amdgpu_ring { #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib))) #define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib))) #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r)) -#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t)) +#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0) #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r)) #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r)) #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index bac7976975bd..dcd8c066bc1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -391,8 +391,10 @@ int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job) dma_fence_get(f); r = drm_sched_job_add_dependency(&job->base, f); - if (r) + if (r) { + dma_fence_put(f); return r; + } } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index b5f3bba851db..01e42bdd8e4e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -974,7 +974,7 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, min(nptes, 32u), dst, incr, upd_flags, - vm->task_info.pid, + vm->task_info.tgid, vm->immediate.fence_context); amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt), cursor.level, pe_start, dst, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index faa12146635c..9fa1d814508a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -882,7 +882,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) kfree(rsv); list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) { - drm_buddy_free_list(&mgr->mm, &rsv->blocks); + drm_buddy_free_list(&mgr->mm, &rsv->allocated); kfree(rsv); } drm_buddy_fini(&mgr->mm); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index a56c6e106d00..66eb102cd88f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -790,8 +790,8 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, * zero here */ WARN_ON(simd != 0); - /* type 2 wave data */ - dst[(*no_fields)++] = 2; + /* type 3 wave data */ + dst[(*no_fields)++] = 3; dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI); @@ -1287,10 +1287,8 @@ static int gfx_v11_0_sw_init(void *handle) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): - case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - case IP_VERSION(11, 0, 4): adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; @@ -1298,6 +1296,15 @@ static int gfx_v11_0_sw_init(void *handle) adev->gfx.mec.num_pipe_per_mec = 4; adev->gfx.mec.num_queue_per_pipe = 4; break; + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 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.mec.num_mec = 1; + adev->gfx.mec.num_pipe_per_mec = 4; + adev->gfx.mec.num_queue_per_pipe = 4; + break; default: adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index f202b45c413c..5dde6f82a1ca 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -6877,7 +6877,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = { .emit_gds_switch = gfx_v9_0_ring_emit_gds_switch, .emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush, .test_ring = gfx_v9_0_ring_test_ring, - .test_ib = gfx_v9_0_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, .emit_switch_buffer = gfx_v9_ring_emit_sb, diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 95548c512f4f..077c53c6cc08 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -35,6 +35,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 970b066b37bb..1c4787000a5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -40,6 +40,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin"); static int mes_v11_0_hw_fini(void *handle); static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev); @@ -196,7 +198,6 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; - mes_add_queue_pkt.trap_en = 1; /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; @@ -1343,7 +1344,7 @@ static int mes_v11_0_late_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* it's only intended for use in mes_self_test case, not for s0ix and reset */ - if (!amdgpu_in_reset(adev) && !adev->in_s0ix && + if (!amdgpu_in_reset(adev) && !adev->in_s0ix && !adev->in_suspend && (adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))) amdgpu_mes_self_test(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 15eb3658d70e..09fdcd20cb91 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -337,7 +337,13 @@ const struct nbio_hdp_flush_reg nbio_v4_3_hdp_flush_reg = { static void nbio_v4_3_init_registers(struct amdgpu_device *adev) { - return; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) { + uint32_t data; + + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2); + data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); + } } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 5562670b7b52..7050238c4c48 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -640,7 +640,10 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | - AMD_CG_SUPPORT_GFX_MGCG; + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_HDP_SD | + AMD_CG_SUPPORT_ATHUB_MGCG | + AMD_CG_SUPPORT_ATHUB_LS; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ecb4c3abc629..c06ada0844ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, queue_input.wptr_addr = (uint64_t)q->properties.write_ptr; if (q->wptr_bo) { - wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va; + wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 814f99888ab1..b94d2c1422ad 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -570,6 +570,15 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; } + if (clear) { + r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false); + if (r) { + pr_debug("failed %d to sync bo\n", r); + amdgpu_bo_unreserve(bo); + goto reserve_bo_failed; + } + } + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index bceb1a5b2518..3fdaba56be6f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -801,7 +801,7 @@ static int kfd_build_sysfs_node_entry(struct kfd_topology_device *dev, p2plink->attr.name = "properties"; p2plink->attr.mode = KFD_SYSFS_FILE_MODE; - sysfs_attr_init(&iolink->attr); + sysfs_attr_init(&p2plink->attr); ret = sysfs_create_file(p2plink->kobj, &p2plink->attr); if (ret < 0) return ret; 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 50c783e19f5a..9c7b69d377bd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1184,24 +1184,38 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_ memset(pa_config, 0, sizeof(*pa_config)); - logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; - pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); - - if (adev->apu_flags & AMD_APU_IS_RAVEN2) - /* - * Raven2 has a HW issue that it is unable to use the vram which - * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the - * workaround that increase system aperture high address (add 1) - * to get rid of the VM fault and hardware hang. - */ - logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18); - else - logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18; - agp_base = 0; agp_bot = adev->gmc.agp_start >> 24; agp_top = adev->gmc.agp_end >> 24; + /* AGP aperture is disabled */ + if (agp_bot == agp_top) { + logical_addr_low = adev->gmc.vram_start >> 18; + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + /* + * Raven2 has a HW issue that it is unable to use the vram which + * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the + * workaround that increase system aperture high address (add 1) + * to get rid of the VM fault and hardware hang. + */ + logical_addr_high = (adev->gmc.fb_end >> 18) + 0x1; + else + logical_addr_high = adev->gmc.vram_end >> 18; + } else { + logical_addr_low = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18; + if (adev->apu_flags & AMD_APU_IS_RAVEN2) + /* + * Raven2 has a HW issue that it is unable to use the vram which + * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the + * workaround that increase system aperture high address (add 1) + * to get rid of the VM fault and hardware hang. + */ + logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18); + else + logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18; + } + + pt_base = amdgpu_gmc_pd_addr(adev->gart.bo); page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF; page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12); @@ -1513,6 +1527,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) } break; } + if (init_data.flags.gpu_vm_support && + (amdgpu_sg_display == 0)) + init_data.flags.gpu_vm_support = false; if (init_data.flags.gpu_vm_support) adev->mode_info.gpu_vm_support = true; @@ -1730,10 +1747,6 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) adev->dm.vblank_control_workqueue = NULL; } - for (i = 0; i < adev->dm.display_indexes_num; i++) { - drm_encoder_cleanup(&adev->dm.mst_encoders[i].base); - } - amdgpu_dm_destroy_drm_device(&adev->dm); #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) @@ -4361,6 +4374,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) amdgpu_set_panel_orientation(&aconnector->base); } + /* If we didn't find a panel, notify the acpi video detection */ + if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0) + acpi_video_report_nolcd(); + /* Software is initialized. Now we can register interrupt handlers. */ switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) @@ -4503,6 +4520,17 @@ DEVICE_ATTR_WO(s3_debug); static int dm_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_mode_info *mode_info = &adev->mode_info; + struct atom_context *ctx = mode_info->atom_context; + int index = GetIndexIntoMasterTable(DATA, Object_Header); + u16 data_offset; + + /* if there is no object header, skip DM */ + if (!amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + dev_info(adev->dev, "No object header, skipping DM\n"); + return -ENOENT; + } switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) @@ -5307,8 +5335,6 @@ static void fill_stream_properties_from_drm_display_mode( timing_out->aspect_ratio = get_aspect_ratio(mode_in); - stream->output_color_space = get_output_color_space(timing_out); - stream->out_transfer_func->type = TF_TYPE_PREDEFINED; stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB; if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) { @@ -5319,6 +5345,8 @@ static void fill_stream_properties_from_drm_display_mode( adjust_colour_depth_from_display_info(timing_out, info); } } + + stream->output_color_space = get_output_color_space(timing_out); } static void fill_audio_info(struct audio_info *audio_info, @@ -5831,7 +5859,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, */ DRM_DEBUG_DRIVER("No preferred mode found\n"); } else { - recalculate_timing = is_freesync_video_mode(&mode, aconnector); + recalculate_timing = amdgpu_freesync_vid_mode && + is_freesync_video_mode(&mode, aconnector); if (recalculate_timing) { freesync_mode = get_highest_refresh_rate_mode(aconnector, false); drm_mode_copy(&saved_mode, &mode); @@ -6982,7 +7011,7 @@ static void amdgpu_dm_connector_add_freesync_modes(struct drm_connector *connect struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector); - if (!edid) + if (!(amdgpu_freesync_vid_mode && edid)) return; if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) @@ -8846,7 +8875,8 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, * TODO: Refactor this function to allow this check to work * in all conditions. */ - if (dm_new_crtc_state->stream && + if (amdgpu_freesync_vid_mode && + dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) goto skip_modeset; @@ -8881,7 +8911,14 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, if (!dm_old_crtc_state->stream) goto skip_modeset; - if (dm_new_crtc_state->stream && + /* Unset freesync video if it was active before */ + if (dm_old_crtc_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) { + dm_new_crtc_state->freesync_config.state = VRR_STATE_INACTIVE; + dm_new_crtc_state->freesync_config.fixed_refresh_in_uhz = 0; + } + + /* Now check if we should set freesync video mode */ + if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) { new_crtc_state->mode_changed = false; @@ -8893,7 +8930,7 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, set_freesync_fixed_config(dm_new_crtc_state); goto skip_modeset; - } else if (aconnector && + } else if (amdgpu_freesync_vid_mode && aconnector && is_freesync_video_mode(&new_crtc_state->mode, aconnector)) { struct drm_display_mode *high_mode; @@ -9497,6 +9534,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, bool lock_and_validation_needed = false; struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state; #if defined(CONFIG_DRM_AMD_DC_DCN) + struct drm_dp_mst_topology_mgr *mgr; + struct drm_dp_mst_topology_state *mst_state; struct dsc_mst_fairness_vars vars[MAX_PIPES]; #endif @@ -9524,8 +9563,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - if (dm_old_con_state->abm_level != - dm_new_con_state->abm_level) + if (dm_old_con_state->abm_level != dm_new_con_state->abm_level || + dm_old_con_state->scaling != dm_new_con_state->scaling) new_crtc_state->connectors_changed = true; } @@ -9619,7 +9658,11 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, * `dcn10_can_pipe_disable_cursor`). By now, all modified planes are in * atomic state, so call drm helper to normalize zpos. */ - drm_atomic_normalize_zpos(dev, state); + ret = drm_atomic_normalize_zpos(dev, state); + if (ret) { + drm_dbg(dev, "drm_atomic_normalize_zpos() failed\n"); + goto fail; + } /* Remove exiting planes if they are modified */ for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) { @@ -9745,6 +9788,28 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, lock_and_validation_needed = true; } +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* set the slot info for each mst_state based on the link encoding format */ + for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) { + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + u8 link_coding_cap; + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + if (connector->index == mst_state->mgr->conn_base_id) { + aconnector = to_amdgpu_dm_connector(connector); + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link); + drm_dp_mst_update_slots(mst_state, link_coding_cap); + + break; + } + } + drm_connector_list_iter_end(&iter); + } +#endif + /** * Streams and planes are reset when there are changes that affect * bandwidth. Anything that affects bandwidth needs to go through diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 6994c9a1ed85..5cff56bb8f56 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -120,23 +120,50 @@ enum dc_edid_status dm_helpers_parse_edid_caps( } static void -fill_dc_mst_payload_table_from_drm(struct drm_dp_mst_topology_state *mst_state, - struct amdgpu_dm_connector *aconnector, +fill_dc_mst_payload_table_from_drm(struct dc_link *link, + bool enable, + struct drm_dp_mst_atomic_payload *target_payload, struct dc_dp_mst_stream_allocation_table *table) { struct dc_dp_mst_stream_allocation_table new_table = { 0 }; struct dc_dp_mst_stream_allocation *sa; - struct drm_dp_mst_atomic_payload *payload; + struct link_mst_stream_allocation_table copy_of_link_table = + link->mst_stream_alloc_table; + + int i; + int current_hw_table_stream_cnt = copy_of_link_table.stream_count; + struct link_mst_stream_allocation *dc_alloc; + + /* TODO: refactor to set link->mst_stream_alloc_table directly if possible.*/ + if (enable) { + dc_alloc = + ©_of_link_table.stream_allocations[current_hw_table_stream_cnt]; + dc_alloc->vcp_id = target_payload->vcpi; + dc_alloc->slot_count = target_payload->time_slots; + } else { + for (i = 0; i < copy_of_link_table.stream_count; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == target_payload->vcpi) { + dc_alloc->vcp_id = 0; + dc_alloc->slot_count = 0; + break; + } + } + ASSERT(i != copy_of_link_table.stream_count); + } /* Fill payload info*/ - list_for_each_entry(payload, &mst_state->payloads, next) { - if (payload->delete) - continue; - - sa = &new_table.stream_allocations[new_table.stream_count]; - sa->slot_count = payload->time_slots; - sa->vcp_id = payload->vcpi; - new_table.stream_count++; + for (i = 0; i < MAX_CONTROLLER_NUM; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + if (dc_alloc->vcp_id > 0 && dc_alloc->slot_count > 0) { + sa = &new_table.stream_allocations[new_table.stream_count]; + sa->slot_count = dc_alloc->slot_count; + sa->vcp_id = dc_alloc->vcp_id; + new_table.stream_count++; + } } /* Overwrite the old table */ @@ -185,7 +212,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(mst_state, aconnector, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); return true; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 1edf7385f8d8..abdbd4352f6f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -468,7 +468,6 @@ static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder) { drm_encoder_cleanup(encoder); - kfree(encoder); } static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = { @@ -904,11 +903,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link); -#if defined(CONFIG_DRM_AMD_DC_DCN) - drm_dp_mst_update_slots(mst_state, dc_link_dp_mst_decide_link_encoding_format(dc_link)); -#endif - /* Set up params */ for (i = 0; i < dc_state->stream_count; i++) { struct dc_dsc_policy dsc_policy = {0}; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 471078fc3900..652270a0b498 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -90,8 +90,8 @@ static const struct out_csc_color_matrix_type output_csc_matrix[] = { { 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3, 0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} }, { COLOR_SPACE_YCBCR2020_TYPE, - { 0x1000, 0xF149, 0xFEB7, 0x0000, 0x0868, 0x15B2, - 0x01E6, 0x0000, 0xFB88, 0xF478, 0x1000, 0x0000} }, + { 0x1000, 0xF149, 0xFEB7, 0x1004, 0x0868, 0x15B2, + 0x01E6, 0x201, 0xFB88, 0xF478, 0x1000, 0x1004} }, { COLOR_SPACE_YCBCR709_BLACK_TYPE, { 0x0000, 0x0000, 0x0000, 0x1000, 0x0000, 0x0000, 0x0000, 0x0200, 0x0000, 0x0000, 0x0000, 0x1000} }, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 342e906ae26e..c88f044666fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3995,10 +3995,13 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0); int i; bool mst_mode = (link->type == dc_connection_mst_branch); + /* adjust for drm changes*/ + bool update_drm_mst_state = true; const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); const struct dc_link_settings empty_link_settings = {0}; DC_LOGGER_INIT(link->ctx->logger); + /* deallocate_mst_payload is called before disable link. When mode or * disable/enable monitor, new stream is created which is not in link * stream[] yet. For this, payload is not allocated yet, so de-alloc @@ -4014,7 +4017,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) &empty_link_settings, avg_time_slots_per_mtp); - if (mst_mode) { + if (mst_mode || update_drm_mst_state) { /* when link is in mst mode, reply on mst manager to remove * payload */ @@ -4077,11 +4080,18 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) stream->ctx, stream); + if (!update_drm_mst_state) + dm_helpers_dp_mst_send_payload_allocation( + stream->ctx, + stream, + false); + } + + if (update_drm_mst_state) dm_helpers_dp_mst_send_payload_allocation( stream->ctx, stream, false); - } return DC_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index fe2023f18b7d..8f894c1d1d1e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3626,7 +3626,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = temp_x + viewport_width; + pos_cpy.x = 2 * viewport_width - temp_x; } } } else { diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index f9ea1e86707f..79850a68f62a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -874,8 +874,9 @@ static const struct dc_plane_cap plane_cap = { }, // 6:1 downscaling ratio: 1000/6 = 166.666 + // 4:1 downscaling ratio for ARGB888 to prevent underflow during P010 playback: 1000/4 = 250 .max_downscale_factor = { - .argb8888 = 167, + .argb8888 = 250, .nv12 = 167, .fp16 = 167 }, @@ -1763,7 +1764,7 @@ static bool dcn314_resource_construct( pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE; pool->base.pipe_count = pool->base.res_cap->num_timing_generator; pool->base.mpcc_count = pool->base.res_cap->num_timing_generator; - dc->caps.max_downscale_ratio = 600; + dc->caps.max_downscale_ratio = 400; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; dc->caps.max_cursor_size = 256; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index dc4649458567..a4e9fd5307c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -94,7 +94,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, .apply_idle_power_optimizations = dcn32_apply_idle_power_optimizations, - .does_plane_fit_in_mall = dcn30_does_plane_fit_in_mall, + .does_plane_fit_in_mall = NULL, .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 950669f2c10d..cb7c0c878423 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -3183,7 +3183,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman } else { v->MIN_DST_Y_NEXT_START[k] = v->VTotal[k] - v->VFrontPorch[k] + v->VTotal[k] - v->VActive[k] - v->VStartup[k]; } - v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / (double)v->HTotal[k] / v->PixelClock[k], 1.0) / 4.0; + v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / ((double)v->HTotal[k] / v->PixelClock[k]), 1.0) / 4.0; if (((v->VUpdateOffsetPix[k] + v->VUpdateWidthPix[k] + v->VReadyOffsetPix[k]) / v->HTotal[k]) <= (isInterlaceTiming ? dml_floor((v->VTotal[k] - v->VActive[k] - v->VFrontPorch[k] - v->VStartup[k]) / 2.0, 1.0) : diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 5af601cff1a0..b53feeaf5cf1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -6257,12 +6257,12 @@ bool dml32_CalculateDETSwathFillLatencyHiding(unsigned int NumberOfActiveSurface double SwathSizePerSurfaceC[DC__NUM_DPP__MAX]; bool NotEnoughDETSwathFillLatencyHiding = false; - /* calculate sum of single swath size for all pipes in bytes*/ + /* calculate sum of single swath size for all pipes in bytes */ for (k = 0; k < NumberOfActiveSurfaces; k++) { - SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k]; + SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k]; if (SwathHeightC[k] != 0) - SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k]; + SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k]; else SwathSizePerSurfaceC[k] = 0; diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 4a122925c3ae..92c18bfb98b3 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -532,6 +532,9 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* reset the cache of the last wptr as well now that hw is reset */ + dmub->inbox1_last_wptr = 0; + cw0.offset.quad_part = inst_fb->gpu_addr; cw0.region.base = DMUB_CW0_BASE; cw0.region.top = cw0.region.base + inst_fb->size - 1; @@ -649,6 +652,15 @@ enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub) if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* mailboxes have been reset in hw, so reset the sw state as well */ + dmub->inbox1_last_wptr = 0; + dmub->inbox1_rb.wrpt = 0; + dmub->inbox1_rb.rptr = 0; + dmub->outbox0_rb.wrpt = 0; + dmub->outbox0_rb.rptr = 0; + dmub->outbox1_rb.wrpt = 0; + dmub->outbox1_rb.rptr = 0; + dmub->hw_init = false; return DMUB_STATUS_OK; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 236657eece47..2f3e239e623d 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -1991,6 +1991,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ case IP_VERSION(9, 4, 2): case IP_VERSION(10, 3, 0): case IP_VERSION(11, 0, 0): + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 2): *states = ATTR_STATE_SUPPORTED; break; default: @@ -2007,14 +2009,16 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_dclk)) { if (!(gc_ver == IP_VERSION(10, 3, 1) || gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_power_profile_mode)) { if (amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ca3beb5d8f27..6ab155023592 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1500,6 +1500,20 @@ static int smu_disable_dpms(struct smu_context *smu) } /* + * For SMU 13.0.4/11, PMFW will handle the features disablement properly + * for gpu reset case. Driver involvement is unnecessary. + */ + if (amdgpu_in_reset(adev)) { + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): + return 0; + default: + break; + } + } + + /* * For gpu reset, runpm and hibernation through BACO, * BACO feature has to be kept enabled. */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h index d6b964cf73bd..4bc7aee4d44f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h @@ -123,7 +123,8 @@ (1 << FEATURE_DS_FCLK_BIT) | \ (1 << FEATURE_DS_LCLK_BIT) | \ (1 << FEATURE_DS_DCFCLK_BIT) | \ - (1 << FEATURE_DS_UCLK_BIT)) + (1 << FEATURE_DS_UCLK_BIT) | \ + (1ULL << FEATURE_DS_VCN_BIT)) //For use with feature control messages typedef enum { @@ -522,9 +523,9 @@ typedef enum { TEMP_HOTSPOT_M, TEMP_MEM, TEMP_VR_GFX, - TEMP_VR_SOC, TEMP_VR_MEM0, TEMP_VR_MEM1, + TEMP_VR_SOC, TEMP_VR_U, TEMP_LIQUID0, TEMP_LIQUID1, diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h index d6b13933a98f..48a3a3952ceb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h @@ -113,20 +113,21 @@ #define NUM_FEATURES 64 #define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL -#define ALLOWED_FEATURE_CTRL_SCPM (1 << FEATURE_DPM_GFXCLK_BIT) | \ - (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \ - (1 << FEATURE_DPM_UCLK_BIT) | \ - (1 << FEATURE_DPM_FCLK_BIT) | \ - (1 << FEATURE_DPM_SOCCLK_BIT) | \ - (1 << FEATURE_DPM_MP0CLK_BIT) | \ - (1 << FEATURE_DPM_LINK_BIT) | \ - (1 << FEATURE_DPM_DCN_BIT) | \ - (1 << FEATURE_DS_GFXCLK_BIT) | \ - (1 << FEATURE_DS_SOCCLK_BIT) | \ - (1 << FEATURE_DS_FCLK_BIT) | \ - (1 << FEATURE_DS_LCLK_BIT) | \ - (1 << FEATURE_DS_DCFCLK_BIT) | \ - (1 << FEATURE_DS_UCLK_BIT) +#define ALLOWED_FEATURE_CTRL_SCPM ((1 << FEATURE_DPM_GFXCLK_BIT) | \ + (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \ + (1 << FEATURE_DPM_UCLK_BIT) | \ + (1 << FEATURE_DPM_FCLK_BIT) | \ + (1 << FEATURE_DPM_SOCCLK_BIT) | \ + (1 << FEATURE_DPM_MP0CLK_BIT) | \ + (1 << FEATURE_DPM_LINK_BIT) | \ + (1 << FEATURE_DPM_DCN_BIT) | \ + (1 << FEATURE_DS_GFXCLK_BIT) | \ + (1 << FEATURE_DS_SOCCLK_BIT) | \ + (1 << FEATURE_DS_FCLK_BIT) | \ + (1 << FEATURE_DS_LCLK_BIT) | \ + (1 << FEATURE_DS_DCFCLK_BIT) | \ + (1 << FEATURE_DS_UCLK_BIT) | \ + (1ULL << FEATURE_DS_VCN_BIT)) //For use with feature control messages typedef enum { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index e8c6febb8b64..992163e66f7b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -28,11 +28,11 @@ #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x34 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32 -#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35 +#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500 //500ms diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 85e22210963f..5cdc07165480 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1171,6 +1171,7 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, int ret = 0; uint32_t apu_percent = 0; uint32_t dgpu_percent = 0; + struct amdgpu_device *adev = smu->adev; ret = smu_cmn_get_metrics_table(smu, @@ -1196,7 +1197,11 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUvdActivity / 100; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; + if (((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) && (adev->pm.fw_version >= 0x40000f)) || + ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0)) && (adev->pm.fw_version >= 0x373200))) + *value = metrics->CurrentSocketPower << 8; + else + *value = (metrics->CurrentSocketPower << 8) / 1000; break; case METRICS_TEMPERATURE_EDGE: *value = (metrics->GfxTemperature / 100) * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index e54b760b875b..b4373b6568ae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1261,7 +1261,8 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed) { struct amdgpu_device *adev = smu->adev; - uint32_t tach_period, crystal_clock_freq; + uint32_t crystal_clock_freq = 2500; + uint32_t tach_period; int ret; if (!speed) @@ -1271,7 +1272,6 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, if (ret) return ret; - crystal_clock_freq = amdgpu_asic_get_xclk(adev); tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed); WREG32_SOC15(THM, 0, regCG_TACH_CTRL, REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL), @@ -2298,6 +2298,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu) !smu_baco->platform_support) return false; + /* return true if ASIC is in BACO state already */ + if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER) + return true; + if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) && !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) return false; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 9643b21c636a..508e392547d7 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -145,6 +145,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel, PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), + MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0), }; static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = { @@ -213,6 +214,7 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = { @@ -405,6 +407,9 @@ static int smu_v13_0_0_setup_pptable(struct smu_context *smu) struct amdgpu_device *adev = smu->adev; int ret = 0; + if (amdgpu_sriov_vf(smu->adev)) + return 0; + ret = smu_v13_0_0_get_pptable_from_pmfw(smu, &smu_table->power_play_table, &smu_table->power_play_table_size); @@ -1255,6 +1260,9 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu, table_context->power_play_table; PPTable_t *pptable = smu->smu_table.driver_pptable; + if (amdgpu_sriov_vf(smu->adev)) + return 0; + if (!range) return -EINVAL; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 5c6c6ad011ca..9e1967d8049e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -124,6 +124,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(DFCstateControl, PPSMC_MSG_SetExternalClientDfCstateAllow, 0), MSG_MAP(ArmD3, PPSMC_MSG_ArmD3, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), + MSG_MAP(GetPptLimit, PPSMC_MSG_GetPptLimit, 0), }; static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = { @@ -192,6 +193,7 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = { |