diff options
| author | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2022-05-03 16:35:26 +0200 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2022-05-03 16:35:26 +0200 |
| commit | b9c92fb4aabb8d93b657d028f7c530d6c42cb630 (patch) | |
| tree | 8fdb7274eee9e5a9b619979988171bce6725369b /drivers/gpu/drm/amd | |
| parent | c40b62216c1aecc0dc00faf33d71bd71cb440337 (diff) | |
| parent | 672c0c5173427e6b3e2a9bbb7be51ceeec78093a (diff) | |
Merge 5.18-rc5 into usb-next
We need the USB fixes in here, and this resolves a merge issue in
drivers/usb/dwc3/drd.c
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/gpu/drm/amd')
62 files changed, 679 insertions, 293 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..d0d0ea565e3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -128,6 +128,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; @@ -709,6 +711,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, dma_fence_put(parser->fence); if (parser->ctx) { + mutex_unlock(&parser->ctx->lock); amdgpu_ctx_put(parser->ctx); } if (parser->bo_list) @@ -1157,6 +1160,9 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, { int i, r; + /* TODO: Investigate why we still need the context lock */ + mutex_unlock(&p->ctx->lock); + for (i = 0; i < p->nchunks; ++i) { struct amdgpu_cs_chunk *chunk; @@ -1167,32 +1173,34 @@ static int amdgpu_cs_dependencies(struct amdgpu_device *adev, case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: r = amdgpu_cs_process_fence_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_IN: r = amdgpu_cs_process_syncobj_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: r = amdgpu_cs_process_syncobj_out_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: r = amdgpu_cs_process_syncobj_timeline_in_dep(p, chunk); if (r) - return r; + goto out; break; case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: r = amdgpu_cs_process_syncobj_timeline_out_dep(p, chunk); if (r) - return r; + goto out; break; } } - return 0; +out: + mutex_lock(&p->ctx->lock); + return r; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1368,6 +1376,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) goto out; r = amdgpu_cs_submit(&parser, cs); + out: amdgpu_cs_parser_fini(&parser, r, reserved_buffers); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 5981c7d9bd48..8f0e6d93bb9c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -237,6 +237,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev, kref_init(&ctx->refcount); spin_lock_init(&ctx->ring_lock); + mutex_init(&ctx->lock); ctx->reset_counter = atomic_read(&adev->gpu_reset_counter); ctx->reset_counter_query = ctx->reset_counter; @@ -357,6 +358,7 @@ static void amdgpu_ctx_fini(struct kref *ref) drm_dev_exit(idx); } + mutex_destroy(&ctx->lock); kfree(ctx); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h index d0cbfcea90f7..142f2f87d44c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h @@ -49,6 +49,7 @@ struct amdgpu_ctx { bool preamble_presented; int32_t init_priority; int32_t override_priority; + struct mutex lock; atomic_t guilty; unsigned long ras_counter_ce; unsigned long ras_counter_ue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..7fd0277b2805 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); @@ -2323,18 +2323,23 @@ static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; if (amdgpu_acpi_is_s0ix_active(adev)) adev->in_s0ix = true; else adev->in_s3 = true; - r = amdgpu_device_suspend(drm_dev, true); - if (r) - return r; + return amdgpu_device_suspend(drm_dev, true); +} + +static int amdgpu_pmops_suspend_noirq(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + if (!adev->in_s0ix) - r = amdgpu_asic_reset(adev); - return r; + return amdgpu_asic_reset(adev); + + return 0; } static int amdgpu_pmops_resume(struct device *dev) @@ -2390,6 +2395,71 @@ static int amdgpu_pmops_restore(struct device *dev) return amdgpu_device_resume(drm_dev, true); } +static int amdgpu_runtime_idle_check_display(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct drm_device *drm_dev = pci_get_drvdata(pdev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + + if (adev->mode_info.num_crtc) { + struct drm_connector *list_connector; + struct drm_connector_list_iter iter; + int ret = 0; + + /* XXX: Return busy if any displays are connected to avoid + * possible display wakeups after runtime resume due to + * hotplug events in case any displays were connected while + * the GPU was in suspend. Remove this once that is fixed. + */ + mutex_lock(&drm_dev->mode_config.mutex); + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->status == connector_status_connected) { + ret = -EBUSY; + break; + } + } + drm_connector_list_iter_end(&iter); + mutex_unlock(&drm_dev->mode_config.mutex); + + if (ret) + return ret; + + if (amdgpu_device_has_dc_support(adev)) { + struct drm_crtc *crtc; + + drm_for_each_crtc(crtc, drm_dev) { + drm_modeset_lock(&crtc->mutex, NULL); + if (crtc->state->active) + ret = -EBUSY; + drm_modeset_unlock(&crtc->mutex); + if (ret < 0) + break; + } + } else { + mutex_lock(&drm_dev->mode_config.mutex); + drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); + + drm_connector_list_iter_begin(drm_dev, &iter); + drm_for_each_connector_iter(list_connector, &iter) { + if (list_connector->dpms == DRM_MODE_DPMS_ON) { + ret = -EBUSY; + break; + } + } + + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); + mutex_unlock(&drm_dev->mode_config.mutex); + } + if (ret) + return ret; + } + + return 0; +} + static int amdgpu_pmops_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); @@ -2402,6 +2472,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) return -EBUSY; } + ret = amdgpu_runtime_idle_check_display(dev); + if (ret) + return ret; + /* wait for all rings to drain before suspending */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; @@ -2511,41 +2585,7 @@ static int amdgpu_pmops_runtime_idle(struct device *dev) return -EBUSY; } - if (amdgpu_device_has_dc_support(adev)) { - struct drm_crtc *crtc; - - drm_for_each_crtc(crtc, drm_dev) { - drm_modeset_lock(&crtc->mutex, NULL); - if (crtc->state->active) - ret = -EBUSY; - drm_modeset_unlock(&crtc->mutex); - if (ret < 0) - break; - } - - } else { - struct drm_connector *list_connector; - struct drm_connector_list_iter iter; - - mutex_lock(&drm_dev->mode_config.mutex); - drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL); - - drm_connector_list_iter_begin(drm_dev, &iter); - drm_for_each_connector_iter(list_connector, &iter) { - if (list_connector->dpms == DRM_MODE_DPMS_ON) { - ret = -EBUSY; - break; - } - } - - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock(&drm_dev->mode_config.connection_mutex); - mutex_unlock(&drm_dev->mode_config.mutex); - } - - if (ret == -EBUSY) - DRM_DEBUG_DRIVER("failing to power off - crtc active\n"); + ret = amdgpu_runtime_idle_check_display(dev); pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); @@ -2575,6 +2615,7 @@ static const struct dev_pm_ops amdgpu_pm_ops = { .prepare = amdgpu_pmops_prepare, .complete = amdgpu_pmops_complete, .suspend = amdgpu_pmops_suspend, + .suspend_noirq = amdgpu_pmops_suspend_noirq, .resume = amdgpu_pmops_resume, .freeze = amdgpu_pmops_freeze, .thaw = amdgpu_pmops_thaw, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..940752488330 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1284,6 +1284,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1304,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index f99093f2ebc7..a0ee828a4a97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -52,7 +52,7 @@ #define FIRMWARE_ALDEBARAN "amdgpu/aldebaran_vcn.bin" #define FIRMWARE_BEIGE_GOBY "amdgpu/beige_goby_vcn.bin" #define FIRMWARE_YELLOW_CARP "amdgpu/yellow_carp_vcn.bin" -#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2_vcn.bin" +#define FIRMWARE_VCN_3_1_2 "amdgpu/vcn_3_1_2.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN); MODULE_FIRMWARE(FIRMWARE_PICASSO); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 46d4bf27ebbb..b8cfcc6b1125 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1205,6 +1205,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, + /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ + { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..7c956cf21bc7 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } @@ -1151,6 +1151,16 @@ static int gmc_v10_0_set_clockgating_state(void *handle, int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + /* + * The issue mmhub can't disconnect from DF with MMHUB clock gating being disabled + * is a new problem observed at DF 3.0.3, however with the same suspend sequence not + * seen any issue on the DF 3.0.2 series platform. + */ + if (adev->in_s0ix && adev->ip_versions[DF_HWIP][0] > IP_VERSION(3, 0, 2)) { + dev_dbg(adev->dev, "keep mmhub clock gating being enabled for s0ix\n"); + return 0; + } + r = adev->mmhub.funcs->set_clockgating(adev, state); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; 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 acf4f7975850..198672264492 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -130,19 +130,33 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, } static void increment_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count++; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count++; + + if (q->properties.is_gws) { + dqm->gws_queue_count++; + qpd->mapped_gws_queue = true; + } } static void decrement_queue_count(struct device_queue_manager *dqm, - enum kfd_queue_type type) + struct qcm_process_device *qpd, + struct queue *q) { dqm->active_queue_count--; - if (type == KFD_QUEUE_TYPE_COMPUTE || type == KFD_QUEUE_TYPE_DIQ) + if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE || + q->properties.type == KFD_QUEUE_TYPE_DIQ) dqm->active_cp_queue_count--; + + if (q->properties.is_gws) { + dqm->gws_queue_count--; + qpd->mapped_gws_queue = false; + } } /* @@ -412,7 +426,7 @@ add_queue_to_list: list_add(&q->list, &qpd->queues_list); qpd->queue_count++; if (q->properties.is_active) - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); /* * Unconditionally increment this counter, regardless of the queue's @@ -601,13 +615,8 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, deallocate_vmid(dqm, qpd, q); } qpd->queue_count--; - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); return retval; } @@ -700,12 +709,11 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q, * dqm->active_queue_count to determine whether a new runlist must be * uploaded. */ - if (q->properties.is_active && !prev_active) - increment_queue_count(dqm, q->properties.type); - else if (!q->properties.is_active && prev_active) - decrement_queue_count(dqm, q->properties.type); - - if (q->gws && !q->properties.is_gws) { + if (q->properties.is_active && !prev_active) { + increment_queue_count(dqm, &pdd->qpd, q); + } else if (!q->properties.is_active && prev_active) { + decrement_queue_count(dqm, &pdd->qpd, q); + } else if (q->gws && !q->properties.is_gws) { if (q->properties.is_active) { dqm->gws_queue_count++; pdd->qpd.mapped_gws_queue = true; @@ -767,11 +775,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } + decrement_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n")) continue; @@ -817,7 +821,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = false; - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); } pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, @@ -888,11 +892,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count++; - qpd->mapped_gws_queue = true; - } + increment_queue_count(dqm, qpd, q); if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n")) continue; @@ -950,7 +950,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, continue; q->properties.is_active = true; - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, &pdd->qpd, q); } retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1378,7 +1378,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm, dqm->total_queue_count); list_add(&kq->list, &qpd->priv_queue_list); - increment_queue_count(dqm, kq->queue->properties.type); + increment_queue_count(dqm, qpd, kq->queue); qpd->is_debug = true; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); dqm_unlock(dqm); @@ -1392,7 +1392,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm, { dqm_lock(dqm); list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0); /* @@ -1467,7 +1467,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, qpd->queue_count++; if (q->properties.is_active) { - increment_queue_count(dqm, q->properties.type); + increment_queue_count(dqm, qpd, q); execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); @@ -1683,15 +1683,11 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm, list_del(&q->list); qpd->queue_count--; if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); + decrement_queue_count(dqm, qpd, q); retval = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); if (retval == -ETIME) qpd->reset_wavefronts = true; - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } } /* @@ -1932,7 +1928,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, /* Clean all kernel queues */ list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) { list_del(&kq->list); - decrement_queue_count(dqm, kq->queue->properties.type); + decrement_queue_count(dqm, qpd, kq->queue); qpd->is_debug = false; dqm->total_queue_count--; filter = KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES; @@ -1945,13 +1941,8 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, else if (q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI) deallocate_sdma_queue(dqm, q); - if (q->properties.is_active) { - decrement_queue_count(dqm, q->properties.type); - if (q->properties.is_gws) { - dqm->gws_queue_count--; - qpd->mapped_gws_queue = false; - } - } + if (q->properties.is_active) + decrement_queue_count(dqm, qpd, q); dqm->total_queue_count--; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 9967a73d5b0f..8f58fc491b28 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1103,7 +1103,7 @@ struct kfd_criu_queue_priv_data { uint32_t priority; uint32_t q_percent; uint32_t doorbell_id; - uint32_t is_gws; + uint32_t gws; uint32_t sdma_id; uint32_t eop_ring_buffer_size; uint32_t ctx_save_restore_area_size; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 6eca9509f2e3..4f58e671d39b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -636,6 +636,8 @@ static int criu_checkpoint_queue(struct kfd_process_device *pdd, q_data->ctx_save_restore_area_size = q->properties.ctx_save_restore_area_size; + q_data->gws = !!q->gws; + ret = pqm_checkpoint_mqd(&pdd->process->pqm, q->properties.queue_id, mqd, ctl_stack); if (ret) { pr_err("Failed checkpoint queue_mqd (%d)\n", ret); @@ -743,7 +745,6 @@ static void set_queue_properties_from_criu(struct queue_properties *qp, struct kfd_criu_queue_priv_data *q_data) { qp->is_interop = false; - qp->is_gws = q_data->is_gws; qp->queue_percent = q_data->q_percent; qp->priority = q_data->priority; qp->queue_address = q_data->q_address; @@ -826,12 +827,15 @@ int kfd_criu_restore_queue(struct kfd_process *p, NULL); if (ret) { pr_err("Failed to create new queue err:%d\n", ret); - ret = -EINVAL; + goto exit; } + if (q_data->gws) + ret = pqm_set_gws(&p->pqm, q_data->q_id, pdd->dev->gws); + exit: if (ret) - pr_err("Failed to create queue (%d)\n", ret); + pr_err("Failed to restore queue (%d)\n", ret); else pr_debug("Queue id %d was restored successfully\n", queue_id); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } 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 b30656959fd8..62139ff35476 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9947,7 +9949,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c index dfba6138f538..26feefbb8990 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c @@ -374,7 +374,7 @@ void dce_clock_read_ss_info(struct clk_mgr_internal *clk_mgr_dce) clk_mgr_dce->dprefclk_ss_percentage = info.spread_spectrum_percentage; } - if (clk_mgr_dce->base.ctx->dc->debug.ignore_dpref_ss) + if (clk_mgr_dce->base.ctx->dc->config.ignore_dpref_ss) clk_mgr_dce->dprefclk_ss_percentage = 0; } } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 702d00ce7da4..3121dd2d2a91 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -686,8 +686,8 @@ void dcn316_clk_mgr_construct( clk_mgr->base.base.dprefclk_khz = dcn316_smu_get_dpref_clk(&clk_mgr->base); clk_mgr->base.dccg->ref_dtbclk_khz = clk_mgr->base.base.dprefclk_khz; dce_clock_read_ss_info(&clk_mgr->base); - clk_mgr->base.dccg->ref_dtbclk_khz = - dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz); + /*clk_mgr->base.dccg->ref_dtbclk_khz = + dce_adjust_dp_ref_freq_for_ss(&clk_mgr->base, clk_mgr->base.base.dprefclk_khz);*/ clk_mgr->base.base.bw_params = &dcn316_bw_params; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} 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 cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..22dabe596dfc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..9e79f60e6129 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -339,6 +340,7 @@ struct dc_config { bool is_asymmetric_memory; bool is_single_rank_dimm; bool use_pipe_ctx_sync_logic; + bool ignore_dpref_ss; }; enum visual_confirm { @@ -525,6 +527,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,14 +721,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; - bool ignore_dpref_ss; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( 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 c3e141c19a77..83fbea2df410 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 @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } @@ -2522,14 +2522,18 @@ void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ab910deed481..b627c41713cc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); @@ -2332,14 +2344,18 @@ void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx) struct mpc *mpc = dc->res_pool->mpc; struct mpc_tree *mpc_tree_params = &(pipe_ctx->stream_res.opp->mpc_tree_params); - if (per_pixel_alpha) - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; - else - blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; - blnd_cfg.overlap_only = false; blnd_cfg.global_gain = 0xff; + if (per_pixel_alpha && pipe_ctx->plane_state->global_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA_COMBINED_GLOBAL_GAIN; + blnd_cfg.global_gain = pipe_ctx->plane_state->global_alpha_value; + } else if (per_pixel_alpha) { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA; + } else { + blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_GLOBAL_ALPHA; + } + if (pipe_ctx->plane_state->global_alpha) blnd_cfg.global_alpha = pipe_ctx->plane_state->global_alpha_value; else diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..faab59508d82 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, @@ -997,6 +997,7 @@ static struct clock_source *dcn21_clock_source_create( return &clk_src->base; } + kfree(clk_src); BREAK_TO_DEBUGGER(); return NULL; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..72e7b5d40af6 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -416,6 +427,7 @@ int amdgpu_dpm_read_sensor(struct amdgpu_device *adev, enum amd_pp_sensors senso void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + int i; if (!adev->pm.dpm_enabled) return; @@ -423,6 +435,15 @@ void amdgpu_dpm_compute_clocks(struct amdgpu_device *adev) if (!pp_funcs->pm_compute_clocks) return; + if (adev->mode_info.num_crtc) + amdgpu_display_bandwidth_update(adev); + + for (i = 0; i < AMDGPU_MAX_RINGS; i++) { + struct amdgpu_ring *ring = adev->rings[i]; + if (ring && ring->sched.ready) + amdgpu_fence_wait_empty(ring); + } + mutex_lock(&adev->pm.mutex); pp_funcs->pm_compute_clocks(adev->powerplay.pp_handle); mutex_unlock(&adev->pm.mutex); @@ -432,6 +453,20 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.uvd_active = true; + adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; + } else { + adev->pm.dpm.uvd_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable); if (ret) DRM_ERROR("Dpm %s uvd failed, ret = %d. \n", @@ -442,6 +477,21 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable) { int ret = 0; + if (adev->family == AMDGPU_FAMILY_SI) { + mutex_lock(&adev->pm.mutex); + if (enable) { + adev->pm.dpm.vce_active = true; + /* XXX select vce level based on ring/task */ + adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; + } else { + adev->pm.dpm.vce_active = false; + } + mutex_unlock(&adev->pm.mutex); + + amdgpu_dpm_compute_clocks(adev); + return; + } + ret = amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable); if (ret) DRM_ERROR("Dpm %s vce failed, ret = %d. \n", @@ -500,6 +550,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +565,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c index 9613c6181c17..d3fe149d8476 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c @@ -1028,16 +1028,6 @@ static int amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev) void amdgpu_legacy_dpm_compute_clocks(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index caae54487f9c..633dab14f51c 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3892,40 +3892,6 @@ static int si_set_boot_state(struct amdgpu_device *adev) } #endif -static int si_set_powergating_by_smu(void *handle, - uint32_t block_type, - bool gate) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - switch (block_type) { - case AMD_IP_BLOCK_TYPE_UVD: - if (!gate) { - adev->pm.dpm.uvd_active = true; - adev->pm.dpm.state = POWER_STATE_TYPE_INTERNAL_UVD; - } else { - adev->pm.dpm.uvd_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - case AMD_IP_BLOCK_TYPE_VCE: - if (!gate) { - adev->pm.dpm.vce_active = true; - /* XXX select vce level based on ring/task */ - adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; - } else { - adev->pm.dpm.vce_active = false; - } - - amdgpu_legacy_dpm_compute_clocks(handle); - break; - default: - break; - } - return 0; -} - static int si_set_sw_state(struct amdgpu_device *adev) { return (amdgpu_si_send_msg_to_smc(adev, PPSMC_MSG_SwitchToSwState) == PPSMC_Result_OK) ? @@ -8125,7 +8091,6 @@ static const struct amd_pm_funcs si_dpm_funcs = { .print_power_state = &si_dpm_print_power_state, .debugfs_print_current_performance_level = &si_dpm_debugfs_print_current_performance_level, .force_performance_level = &si_dpm_force_performance_level, - .set_powergating_by_smu = &si_set_powergating_by_smu, .vblank_too_short = &si_dpm_vblank_too_short, .set_fan_control_mode = &si_dpm_set_fan_control_mode, .get_fan_control_mode = &si_dpm_get_fan_control_mode, diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index a2da46bf3985..71e9c6ce6b1a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1487,16 +1487,6 @@ static void pp_pm_compute_clocks(void *handle) { struct pp_hwmgr *hwmgr = handle; struct amdgpu_device *adev = hwmgr->adev; - int i = 0; - - if (adev->mode_info.num_crtc) - amdgpu_display_bandwidth_update(adev); - - for (i = 0; i < AMDGPU_MAX_RINGS; i++) { - struct amdgpu_ring *ring = adev->rings[i]; - if (ring && ring->sched.ready) - amdgpu_fence_wait_empty(ring); - } if (!amdgpu_device_has_dc_support(adev)) { amdgpu_dpm_get_active_displays(adev); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, |