diff options
Diffstat (limited to 'drivers/gpu')
75 files changed, 528 insertions, 387 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 1f5a296f5ed2..7dd55ed57c1d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -172,8 +172,8 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, &buffer); obj = (union acpi_object *)buffer.pointer; - /* Fail if calling the method fails and ATIF is supported */ - if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { + /* Fail if calling the method fails */ + if (ACPI_FAILURE(status)) { DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n", acpi_format_exception(status)); kfree(obj); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index cbef720de779..9da4414de617 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -402,7 +402,7 @@ static ssize_t amdgpu_debugfs_gprwave_read(struct file *f, char __user *buf, siz int r; uint32_t *data, x; - if (size & 0x3 || *pos & 0x3) + if (size > 4096 || size & 0x3 || *pos & 0x3) return -EINVAL; r = pm_runtime_get_sync(adev_to_drm(adev)->dev); @@ -1648,7 +1648,7 @@ int amdgpu_debugfs_regs_init(struct amdgpu_device *adev) for (i = 0; i < ARRAY_SIZE(debugfs_regs); i++) { ent = debugfs_create_file(debugfs_regs_names[i], - S_IFREG | 0444, root, + S_IFREG | 0400, root, adev, debugfs_regs[i]); if (!i && !IS_ERR_OR_NULL(ent)) i_size_write(ent->d_inode, adev->rmmio_size); @@ -2100,11 +2100,11 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) amdgpu_securedisplay_debugfs_init(adev); amdgpu_fw_attestation_debugfs_init(adev); - debugfs_create_file("amdgpu_evict_vram", 0444, root, adev, + debugfs_create_file("amdgpu_evict_vram", 0400, root, adev, &amdgpu_evict_vram_fops); - debugfs_create_file("amdgpu_evict_gtt", 0444, root, adev, + debugfs_create_file("amdgpu_evict_gtt", 0400, root, adev, &amdgpu_evict_gtt_fops); - debugfs_create_file("amdgpu_test_ib", 0444, root, adev, + debugfs_create_file("amdgpu_test_ib", 0400, root, adev, &amdgpu_debugfs_test_ib_fops); debugfs_create_file("amdgpu_vm_info", 0444, root, adev, &amdgpu_debugfs_vm_info_fops); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 44819cdba7fb..971419e3a9bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -161,7 +161,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) * When GTT is just an alternative to VRAM make sure that we * only use it as fallback and still try to fill up VRAM first. */ - if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) + if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM && + !(adev->flags & AMD_IS_APU)) places[c].flags |= TTM_PL_FLAG_FALLBACK; c++; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index b0a8abc7a8ec..341beec59537 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -35,21 +35,19 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, int fd, int32_t priority) { - struct fd f = fdget(fd); + CLASS(fd, f)(fd); struct amdgpu_fpriv *fpriv; struct amdgpu_ctx_mgr *mgr; struct amdgpu_ctx *ctx; uint32_t id; int r; - if (!fd_file(f)) + if (fd_empty(f)) return -EINVAL; r = amdgpu_file_to_fpriv(fd_file(f), &fpriv); - if (r) { - fdput(f); + if (r) return r; - } mgr = &fpriv->ctx_mgr; mutex_lock(&mgr->lock); @@ -57,7 +55,6 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, amdgpu_ctx_priority_override(ctx, priority); mutex_unlock(&mgr->lock); - fdput(f); return 0; } @@ -66,31 +63,25 @@ static int amdgpu_sched_context_priority_override(struct amdgpu_device *adev, unsigned ctx_id, int32_t priority) { - struct fd f = fdget(fd); + CLASS(fd, f)(fd); struct amdgpu_fpriv *fpriv; struct amdgpu_ctx *ctx; int r; - if (!fd_file(f)) + if (fd_empty(f)) return -EINVAL; r = amdgpu_file_to_fpriv(fd_file(f), &fpriv); - if (r) { - fdput(f); + if (r) return r; - } ctx = amdgpu_ctx_get(fpriv, ctx_id); - if (!ctx) { - fdput(f); + if (!ctx) return -EINVAL; - } amdgpu_ctx_priority_override(ctx, priority); amdgpu_ctx_put(ctx); - fdput(f); - return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c index 5e8833e4fed2..ccfd2a4b4acc 100644 --- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c +++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c @@ -482,7 +482,7 @@ static bool __aqua_vanjaram_is_valid_mode(struct amdgpu_xcp_mgr *xcp_mgr, case AMDGPU_SPX_PARTITION_MODE: return adev->gmc.num_mem_partitions == 1 && num_xcc > 0; case AMDGPU_DPX_PARTITION_MODE: - return adev->gmc.num_mem_partitions != 8 && (num_xcc % 4) == 0; + return adev->gmc.num_mem_partitions <= 2 && (num_xcc % 4) == 0; case AMDGPU_TPX_PARTITION_MODE: return (adev->gmc.num_mem_partitions == 1 || adev->gmc.num_mem_partitions == 3) && diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index c76ac0dfe572..7a45f3fdc734 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1124,8 +1124,10 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, uint64_t *flags) { struct amdgpu_device *bo_adev = amdgpu_ttm_adev(bo->tbo.bdev); - bool is_vram = bo->tbo.resource->mem_type == TTM_PL_VRAM; - bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | AMDGPU_GEM_CREATE_EXT_COHERENT); + bool is_vram = bo->tbo.resource && + bo->tbo.resource->mem_type == TTM_PL_VRAM; + bool coherent = bo->flags & (AMDGPU_GEM_CREATE_COHERENT | + AMDGPU_GEM_CREATE_EXT_COHERENT); bool ext_coherent = bo->flags & AMDGPU_GEM_CREATE_EXT_COHERENT; bool uncached = bo->flags & AMDGPU_GEM_CREATE_UNCACHED; struct amdgpu_vm *vm = mapping->bo_va->base.vm; @@ -1133,6 +1135,8 @@ static void gmc_v9_0_get_coherence_flags(struct amdgpu_device *adev, bool snoop = false; bool is_local; + dma_resv_assert_held(bo->tbo.base.resv); + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): @@ -1251,9 +1255,8 @@ static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev, *flags &= ~AMDGPU_PTE_VALID; } - if (bo && bo->tbo.resource) - gmc_v9_0_get_coherence_flags(adev, mapping->bo_va->base.bo, - mapping, flags); + if ((*flags & AMDGPU_PTE_VALID) && bo) + gmc_v9_0_get_coherence_flags(adev, bo, mapping, flags); } static void gmc_v9_0_override_vm_pte_flags(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index a37a6801c9ea..b3175ff676f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -550,7 +550,7 @@ static int mes_v12_0_set_hw_resources_1(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_1_pkt.header.type = MES_API_TYPE_SCHEDULER; mes_set_hw_res_1_pkt.header.opcode = MES_SCH_API_SET_HW_RSRC_1; mes_set_hw_res_1_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS; - mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 100; + mes_set_hw_res_1_pkt.mes_kiq_unmap_timeout = 0xa; return mes_v12_0_submit_pkt_and_poll_completion(mes, pipe, &mes_set_hw_res_1_pkt, sizeof(mes_set_hw_res_1_pkt), diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index fb37e354a9d5..1ac730328516 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -247,6 +247,12 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data); + switch (adev->ip_versions[NBIO_HWIP][0]) { + case IP_VERSION(7, 7, 0): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23); + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data); + break; + } } static void nbio_v7_7_update_medium_grain_clock_gating(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 4938e6b340e9..73065a85e0d2 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -67,8 +67,8 @@ static const struct amd_ip_funcs nv_common_ip_funcs; /* Navi */ static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)}, }; static const struct amdgpu_video_codecs nv_video_codecs_encode = { @@ -94,8 +94,8 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode = { /* Sienna Cichlid */ static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; static const struct amdgpu_video_codecs sc_video_codecs_encode = { @@ -136,8 +136,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 = { /* SRIOV Sienna Cichlid, not const since data is controlled by host */ static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] = { diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 8d16dacdc172..307185c0e1b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -90,8 +90,8 @@ static const struct amd_ip_funcs soc15_common_ip_funcs; /* Vega, Raven, Arcturus */ static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 0)}, }; static const struct amdgpu_video_codecs vega_video_codecs_encode = diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index d30ad7d56def..bba35880badb 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -49,13 +49,13 @@ static const struct amd_ip_funcs soc21_common_ip_funcs; /* SOC21 */ static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn0[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static const struct amdgpu_video_codec_info vcn_4_0_0_video_codecs_encode_array_vcn1[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; @@ -96,14 +96,14 @@ static const struct amdgpu_video_codecs vcn_4_0_0_video_codecs_decode_vcn1 = { /* SRIOV SOC21, not const since data is controlled by host */ static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn0[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; static struct amdgpu_video_codec_info sriov_vcn_4_0_0_video_codecs_encode_array_vcn1[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, }; static struct amdgpu_video_codecs sriov_vcn_4_0_0_video_codecs_encode_vcn0 = { diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index fd4c3d4f8387..29a848f2466b 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -48,7 +48,7 @@ static const struct amd_ip_funcs soc24_common_ip_funcs; static const struct amdgpu_video_codec_info vcn_5_0_0_video_codecs_encode_array_vcn0[] = { - {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4096, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 0)}, {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)}, }; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index d39c670f6220..792b2eb6bbac 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -136,15 +136,15 @@ static const struct amdgpu_video_codec_info polaris_video_codecs_encode_array[] { .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, + .max_height = 4096, + .max_pixels_per_frame = 4096 * 4096, .max_level = 0, }, { .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, .max_width = 4096, - .max_height = 2304, - .max_pixels_per_frame = 4096 * 2304, + .max_height = 4096, + .max_pixels_per_frame = 4096 * 4096, .max_level = 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 13421a58210d..8d97f17ffe66 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -6762,7 +6762,7 @@ create_stream_for_sink(struct drm_connector *connector, if (stream->out_transfer_func.tf == TRANSFER_FUNCTION_GAMMA22) tf = TRANSFER_FUNC_GAMMA_22; mod_build_vsc_infopacket(stream, &stream->vsc_infopacket, stream->output_color_space, tf); - aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; + aconnector->sr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; } finish: @@ -8875,6 +8875,56 @@ static void amdgpu_dm_update_cursor(struct drm_plane *plane, } } +static void amdgpu_dm_enable_self_refresh(struct amdgpu_crtc *acrtc_attach, + const struct dm_crtc_state *acrtc_state, + const u64 current_ts) +{ + struct psr_settings *psr = &acrtc_state->stream->link->psr_settings; + struct replay_settings *pr = &acrtc_state->stream->link->replay_settings; + struct amdgpu_dm_connector *aconn = + (struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context; + + if (acrtc_state->update_type > UPDATE_TYPE_FAST) { + if (pr->config.replay_supported && !pr->replay_feature_enabled) + amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn); + else if (psr->psr_version != DC_PSR_VERSION_UNSUPPORTED && + !psr->psr_feature_enabled) + if (!aconn->disallow_edp_enter_psr) + amdgpu_dm_link_setup_psr(acrtc_state->stream); + } + + /* Decrement skip count when SR is enabled and we're doing fast updates. */ + if (acrtc_state->update_type == UPDATE_TYPE_FAST && + (psr->psr_feature_enabled || pr->config.replay_supported)) { + if (aconn->sr_skip_count > 0) + aconn->sr_skip_count--; + + /* Allow SR when skip count is 0. */ + acrtc_attach->dm_irq_params.allow_sr_entry = !aconn->sr_skip_count; + + /* + * If sink supports PSR SU/Panel Replay, there is no need to rely on + * a vblank event disable request to enable PSR/RP. PSR SU/RP + * can be enabled immediately once OS demonstrates an + * adequate number of fast atomic commits to notify KMD + * of update events. See `vblank_control_worker()`. + */ + if (acrtc_attach->dm_irq_params.allow_sr_entry && +#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY + !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) && +#endif + (current_ts - psr->psr_dirty_rects_change_timestamp_ns) > 500000000) { + if (pr->replay_feature_enabled && !pr->replay_allow_active) + amdgpu_dm_replay_enable(acrtc_state->stream, true); + if (psr->psr_version >= DC_PSR_VERSION_SU_1 && + !psr->psr_allow_active && !aconn->disallow_edp_enter_psr) + amdgpu_dm_psr_enable(acrtc_state->stream); + } + } else { + acrtc_attach->dm_irq_params.allow_sr_entry = false; + } +} + static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct drm_device *dev, struct amdgpu_display_manager *dm, @@ -9028,7 +9078,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * during the PSR-SU was disabled. */ if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && - acrtc_attach->dm_irq_params.allow_psr_entry && + acrtc_attach->dm_irq_params.allow_sr_entry && #ifdef CONFIG_DRM_AMD_SECURE_DISPLAY !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) && #endif @@ -9203,9 +9253,12 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->stream_update.abm_level = &acrtc_state->abm_level; mutex_lock(&dm->dc_lock); - if ((acrtc_state->update_type > UPDATE_TYPE_FAST) && - acrtc_state->stream->link->psr_settings.psr_allow_active) - amdgpu_dm_psr_disable(acrtc_state->stream); + if (acrtc_state->update_type > UPDATE_TYPE_FAST) { + if (acrtc_state->stream->link->replay_settings.replay_allow_active) + amdgpu_dm_replay_disable(acrtc_state->stream); + if (acrtc_state->stream->link->psr_settings.psr_allow_active) + amdgpu_dm_psr_disable(acrtc_state->stream); + } mutex_unlock(&dm->dc_lock); /* @@ -9246,57 +9299,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, dm_update_pflip_irq_state(drm_to_adev(dev), acrtc_attach); - if (acrtc_state->update_type > UPDATE_TYPE_FAST) { - if (acrtc_state->stream->link->replay_settings.config.replay_supported && - !acrtc_state->stream->link->replay_settings.replay_feature_enabled) { - struct amdgpu_dm_connector *aconn = - (struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context; - amdgpu_dm_link_setup_replay(acrtc_state->stream->link, aconn); - } else if (acrtc_state->stream->link->psr_settings.psr_version != DC_PSR_VERSION_UNSUPPORTED && - !acrtc_state->stream->link->psr_settings.psr_feature_enabled) { - - struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *) - acrtc_state->stream->dm_stream_context; - - if (!aconn->disallow_edp_enter_psr) - amdgpu_dm_link_setup_psr(acrtc_state->stream); - } - } - - /* Decrement skip count when PSR is enabled and we're doing fast updates. */ - if (acrtc_state->update_type == UPDATE_TYPE_FAST && - acrtc_state->stream->link->psr_settings.psr_feature_enabled) { - struct amdgpu_dm_connector *aconn = - (struct amdgpu_dm_connector *)acrtc_state->stream->dm_stream_context; - - if (aconn->psr_skip_count > 0) - aconn->psr_skip_count--; - - /* Allow PSR when skip count is 0. */ - acrtc_attach->dm_irq_params.allow_psr_entry = !aconn->psr_skip_count; - - /* - * If sink supports PSR SU, there is no need to rely on - * a vblank event disable request to enable PSR. PSR SU - * can be enabled immediately once OS demonstrates an - * adequate number of fast atomic commits to notify KMD - * of update events. See `vblank_control_worker()`. - */ - if (acrtc_state->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && - acrtc_attach->dm_irq_params.allow_psr_entry && -#ifdef CONFIG_DRM_AMD_SECURE_DISPLAY - !amdgpu_dm_crc_window_is_activated(acrtc_state->base.crtc) && -#endif - !acrtc_state->stream->link->psr_settings.psr_allow_active && - !aconn->disallow_edp_enter_psr && - (timestamp_ns - - acrtc_state->stream->link->psr_settings.psr_dirty_rects_change_timestamp_ns) > - 500000000) - amdgpu_dm_psr_enable(acrtc_state->stream); - } else { - acrtc_attach->dm_irq_params.allow_psr_entry = false; - } - + amdgpu_dm_enable_self_refresh(acrtc_attach, acrtc_state, timestamp_ns); mutex_unlock(&dm->dc_lock); } @@ -9429,6 +9432,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, bool mode_set_reset_required = false; u32 i; struct dc_commit_streams_params params = {dc_state->streams, dc_state->stream_count}; + bool set_backlight_level = false; /* Disable writeback */ for_each_old_connector_in_state(state, connector, old_con_state, i) { @@ -9548,6 +9552,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, acrtc->hw_mode = new_crtc_state->mode; crtc->hwmode = new_crtc_state->mode; mode_set_reset_required = true; + set_backlight_level = true; } else if (modereset_required(new_crtc_state)) { drm_dbg_atomic(dev, "Atomic commit: RESET. crtc id %d:[%p]\n", @@ -9599,6 +9604,19 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state, acrtc->otg_inst = status->primary_otg_inst; } } + + /* During boot up and resume the DC layer will reset the panel brightness + * to fix a flicker issue. + * It will cause the dm->actual_brightness is not the current panel brightness + * level. (the dm->brightness is the correct panel level) + * So we set the backlight level with dm->brightness value after set mode + */ + if (set_backlight_level) { + for (i = 0; i < dm->num_of_edps; i++) { + if (dm->backlight_dev[i]) + amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); + } + } } static void dm_set_writeback(struct amdgpu_display_manager *dm, @@ -12065,7 +12083,7 @@ static int parse_amd_vsdb(struct amdgpu_dm_connector *aconnector, break; } - while (j < EDID_LENGTH) { + while (j < EDID_LENGTH - sizeof(struct amd_vsdb_block)) { struct amd_vsdb_block *amd_vsdb = (struct amd_vsdb_block *)&edid_ext[j]; unsigned int ieeeId = (amd_vsdb->ieee_id[2] << 16) | (amd_vsdb->ieee_id[1] << 8) | (amd_vsdb->ieee_id[0]); 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 15d4690c74d6..90dfffec33cf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -727,7 +727,7 @@ struct amdgpu_dm_connector { /* Cached display modes */ struct drm_display_mode freesync_vid_base; - int psr_skip_count; + int sr_skip_count; bool disallow_edp_enter_psr; /* Record progress status of mst*/ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index a2cf2c066a76..288be19db7c1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -266,11 +266,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work) * where the SU region is the full hactive*vactive region. See * fill_dc_dirty_rects(). */ - if (vblank_work->stream && vblank_work->stream->link) { + if (vblank_work->stream && vblank_work->stream->link && vblank_work->acrtc) { amdgpu_dm_crtc_set_panel_sr_feature( vblank_work, vblank_work->enable, - vblank_work->acrtc->dm_irq_params.allow_psr_entry || - vblank_work->stream->link->replay_settings.replay_feature_enabled); + vblank_work->acrtc->dm_irq_params.allow_sr_entry); } if (dm->active_vblank_irq_count == 0) { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h index 5c9303241aeb..6a7ecc1e4602 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq_params.h @@ -33,7 +33,7 @@ struct dm_irq_params { struct mod_vrr_params vrr_params; struct dc_stream_state *stream; int active_planes; - bool allow_psr_entry; + bool allow_sr_entry; struct mod_freesync_config freesync_config; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 0d8498ab9b23..c9a6de110b74 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -3122,7 +3122,7 @@ static enum bp_result bios_parser_get_vram_info( struct dc_vram_info *info) { struct bios_parser *bp = BP_FROM_DCB(dcb); - static enum bp_result result = BP_RESULT_BADBIOSTABLE; + enum bp_result result = BP_RESULT_BADBIOSTABLE; struct atom_common_table_header *header; struct atom_data_revision revision; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index 2597e3fd562b..e006f816ff2f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -265,6 +265,9 @@ struct dc_state *dc_state_create_copy(struct dc_state *src_state) dc_state_copy_internal(new_state, src_state); #ifdef CONFIG_DRM_AMD_DC_FP + new_state->bw_ctx.dml2 = NULL; + new_state->bw_ctx.dml2_dc_power_source = NULL; + if (src_state->bw_ctx.dml2 && !dml2_create_copy(&new_state->bw_ctx.dml2, src_state->bw_ctx.dml2)) { dc_state_release(new_state); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c index 1cf9015e854a..dd9971867f74 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c @@ -8,6 +8,7 @@ #include "dml2_pmo_dcn4_fams2.h" static const double MIN_VACTIVE_MARGIN_PCT = 0.25; // We need more than non-zero margin because DET buffer granularity can alter vactive latency hiding +static const double MIN_BLANK_STUTTER_FACTOR = 3.0; static const struct dml2_pmo_pstate_strategy base_strategy_list_1_display[] = { // VActive Preferred @@ -2139,6 +2140,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in struct dml2_pmo_instance *pmo = in_out->instance; bool stutter_period_meets_z8_eco = true; bool z8_stutter_optimization_too_expensive = false; + bool stutter_optimization_too_expensive = false; double line_time_us, vblank_nom_time_us; unsigned int i; @@ -2160,10 +2162,15 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in line_time_us = (double)in_out->base_display_config->display_config.stream_descriptors[i].timing.h_total / (in_out->base_display_config->display_config.stream_descriptors[i].timing.pixel_clock_khz * 1000) * 1000000; vblank_nom_time_us = line_time_us * in_out->base_display_config->display_config.stream_descriptors[i].timing.vblank_nom; - if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us) { + if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.z8_stutter_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) { z8_stutter_optimization_too_expensive = true; break; } + + if (vblank_nom_time_us < pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us * MIN_BLANK_STUTTER_FACTOR) { + stutter_optimization_too_expensive = true; + break; + } } pmo->scratch.pmo_dcn4.num_stutter_candidates = 0; @@ -2179,7 +2186,7 @@ bool pmo_dcn4_fams2_init_for_stutter(struct dml2_pmo_init_for_stutter_in_out *in pmo->scratch.pmo_dcn4.z8_vblank_optimizable = false; } - if (pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) { + if (!stutter_optimization_too_expensive && pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us > 0) { pmo->scratch.pmo_dcn4.optimal_vblank_reserved_time_for_stutter_us[pmo->scratch.pmo_dcn4.num_stutter_candidates] = (unsigned int)pmo->soc_bb->power_management_parameters.stutter_enter_plus_exit_latency_us; pmo->scratch.pmo_dcn4.num_stutter_candidates++; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index 8798ebfcea83..84f9b007b59f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -1132,7 +1132,7 @@ static int smu_v14_0_common_get_dpm_level_count(struct smu_context *smu, static int smu_v14_0_0_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf) { - int i, size = 0, ret = 0; + int i, idx, ret = 0, size = 0; uint32_t cur_value = 0, value = 0, count = 0; uint32_t min, max; @@ -1168,7 +1168,8 @@ static int smu_v14_0_0_print_clk_levels(struct smu_context *smu, break; for (i = 0; i < count; i++) { - ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, i, &value); + idx = (clk_type == SMU_MCLK) ? (count - i - 1) : i; + ret = smu_v14_0_common_get_dpm_freq_by_index(smu, clk_type, idx, &value); if (ret) break; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index e83ea2bc7f9c..1e16a281f2dc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -367,54 +367,6 @@ static int smu_v14_0_2_store_powerplay_table(struct smu_context *smu) return 0; } -#ifndef atom_smc_dpm_info_table_14_0_0 -struct atom_smc_dpm_info_table_14_0_0 { - struct atom_common_table_header table_header; - BoardTable_t BoardTable; -}; -#endif - -static int smu_v14_0_2_append_powerplay_table(struct smu_context *smu) -{ - struct smu_table_context *table_context = &smu->smu_table; - PPTable_t *smc_pptable = table_context->driver_pptable; - struct atom_smc_dpm_info_table_14_0_0 *smc_dpm_table; - BoardTable_t *BoardTable = &smc_pptable->BoardTable; - int index, ret; - - index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, - smc_dpm_info); - - ret = amdgpu_atombios_get_data_table(smu->adev, index, NULL, NULL, NULL, - (uint8_t **)&smc_dpm_table); - if (ret) - return ret; - - memcpy(BoardTable, &smc_dpm_table->BoardTable, sizeof(BoardTable_t)); - - return 0; -} - -#if 0 -static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu, - void **table, - uint32_t *size) -{ - struct smu_table_context *smu_table = &smu->smu_table; - void *combo_pptable = smu_table->combo_pptable; - int ret = 0; - - ret = smu_cmn_get_combo_pptable(smu); - if (ret) - return ret; - - *table = combo_pptable; - *size = sizeof(struct smu_14_0_powerplay_table); - - return 0; -} -#endif - static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu, void **table, uint32_t *size) @@ -436,16 +388,12 @@ static int smu_v14_0_2_get_pptable_from_pmfw(struct smu_context *smu, static int smu_v14_0_2_setup_pptable(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; - struct amdgpu_device *adev = smu->adev; int ret = 0; if (amdgpu_sriov_vf(smu->adev)) return 0; - if (!adev->scpm_enabled) - ret = smu_v14_0_setup_pptable(smu); - else - ret = smu_v14_0_2_get_pptable_from_pmfw(smu, + ret = smu_v14_0_2_get_pptable_from_pmfw(smu, &smu_table->power_play_table, &smu_table->power_play_table_size); if (ret) @@ -455,16 +403,6 @@ static int smu_v14_0_2_setup_pptable(struct smu_context *smu) if (ret) return ret; - /* - * With SCPM enabled, the operation below will be handled - * by PSP. Driver involvment is unnecessary and useless. - */ - if (!adev->scpm_enabled) { - ret = smu_v14_0_2_append_powerplay_table(smu); - if (ret) - return ret; - } - ret = smu_v14_0_2_check_powerplay_table(smu); if (ret) return ret; @@ -2799,7 +2737,6 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = { .check_fw_status = smu_v14_0_check_fw_status, .setup_pptable = smu_v14_0_2_setup_pptable, .check_fw_version = smu_v14_0_check_fw_version, - .write_pptable = smu_cmn_write_pptable, .set_driver_table_location = smu_v14_0_set_driver_table_location, .system_features_control = smu_v14_0_system_features_control, .set_allowed_mask = smu_v14_0_set_allowed_mask, diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 0e8813278a2f..bb1750a3dab0 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -125,6 +125,9 @@ #define TC358768_DSI_CONFW_MODE_CLR (6 << 29) #define TC358768_DSI_CONFW_ADDR_DSI_CONTROL (0x3 << 24) +/* TC358768_DSICMD_TX (0x0600) register */ +#define TC358768_DSI_CMDTX_DC_START BIT(0) + static const char * const tc358768_supplies[] = { "vddc", "vddmipi", "vddio" }; @@ -229,6 +232,21 @@ static void tc358768_update_bits(struct tc358768_priv *priv, u32 reg, u32 mask, tc358768_write(priv, reg, tmp); } +static void tc358768_dsicmd_tx(struct tc358768_priv *priv) +{ + u32 val; + + /* start transfer */ + tc358768_write(priv, TC358768_DSICMD_TX, TC358768_DSI_CMDTX_DC_START); + if (priv->error) + return; + + /* wait transfer completion */ + priv->error = regmap_read_poll_timeout(priv->regmap, TC358768_DSICMD_TX, val, + (val & TC358768_DSI_CMDTX_DC_START) == 0, + 100, 100000); +} + static int tc358768_sw_reset(struct tc358768_priv *priv) { /* Assert Reset */ @@ -516,8 +534,7 @@ static ssize_t tc358768_dsi_host_transfer(struct mipi_dsi_host *host, } } - /* start transfer */ - tc358768_write(priv, TC358768_DSICMD_TX, 1); + tc358768_dsicmd_tx(priv); ret = tc358768_clear_error(priv); if (ret) diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 0830cae9a4d0..2d84d7ea1ab7 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -403,7 +403,6 @@ static const struct dmi_system_id orientation_data[] = { }, { /* Lenovo Yoga Tab 3 X90F */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), - DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"), }, .driver_data = (void *)&lcd1600x2560_rightside_up, diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 8e3d2d7060f8..4f2ab8a7b50f 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -712,16 +712,14 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private, int fd, u32 *handle) { struct drm_syncobj *syncobj; - struct fd f = fdget(fd); + CLASS(fd, f)(fd); int ret; - if (!fd_file(f)) + if (fd_empty(f)) return -EINVAL; - if (fd_file(f)->f_op != &drm_syncobj_file_fops) { - fdput(f); + if (fd_file(f)->f_op != &drm_syncobj_file_fops) return -EINVAL; - } /* take a reference to put in the idr */ syncobj = fd_file(f)->private_data; @@ -739,7 +737,6 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private, } else drm_syncobj_put(syncobj); - fdput(f); return ret; } diff --git a/drivers/gpu/drm/gma500/Kconfig b/drivers/gpu/drm/gma500/Kconfig index efb4a2dd2f80..23b7c14de5e2 100644 --- a/drivers/gpu/drm/gma500/Kconfig +++ b/drivers/gpu/drm/gma500/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_GMA500 tristate "Intel GMA500/600/3600/3650 KMS Framebuffer" - depends on DRM && PCI && X86 && MMU + depends on DRM && PCI && X86 && MMU && HAS_IOPORT select DRM_KMS_HELPER select FB_IOMEM_HELPERS if DRM_FBDEV_EMULATION select I2C diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 581844d1db9a..5fee4be64592 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -928,7 +928,7 @@ intel_enable_tv(struct intel_atomic_state *state, const struct intel_crtc_state *pipe_config, const struct drm_connector_state *conn_state) { - struct intel_display *display = to_intel_display(state); + struct intel_display *display = to_intel_display(encoder); /* Prevents vblank waits from timing out in intel_tv_detect_type() */ intel_crtc_wait_for_next_vblank(to_intel_crtc(pipe_config->uapi.crtc)); @@ -942,7 +942,7 @@ intel_disable_tv(struct intel_atomic_state *state, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { - struct intel_display *display = to_intel_display(state); + struct intel_display *display = to_intel_display(encoder); intel_de_rmw(display, TV_CTL, TV_ENC_ENABLE, 0); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index a6c69a706fd7..bb29f361110e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -302,7 +302,7 @@ static void gen6_check_faults(struct intel_gt *gt) { struct intel_engine_cs *engine; enum intel_engine_id id; - u32 fault; + unsigned long fault; for_each_engine(engine, gt, id) { fault = GEN6_RING_FAULT_REG_READ(engine); @@ -310,8 +310,8 @@ static void gen6_check_faults(struct intel_gt *gt) gt_dbg(gt, "Unexpected fault\n" "\tAddr: 0x%08lx\n" "\tAddress space: %s\n" - "\tSource ID: %d\n" - "\tType: %d\n", + "\tSource ID: %ld\n" + "\tType: %ld\n", fault & PAGE_MASK, fault & RING_FAULT_GTTSEL_MASK ? "GGTT" : "PPGTT", diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 1fb6ff77fd89..bb696b29ee2c 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -40,7 +40,7 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) if (i915_gem_object_is_shmem(obj)) { file = obj->base.filp; - atomic_long_inc(&file->f_count); + get_file(file); return file; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c index 551b0d7974ff..5dc0ccd07636 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c @@ -80,6 +80,7 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s const struct intel_gsc_cpd_header_v2 *cpd_header = NULL; const struct intel_gsc_cpd_entry *cpd_entry = NULL; const struct intel_gsc_manifest_header *manifest; + struct intel_uc_fw_ver min_ver = { 0 }; size_t min_size = sizeof(*layout); int i; @@ -212,33 +213,46 @@ int intel_gsc_fw_get_binary_info(struct intel_uc_fw *gsc_fw, const void *data, s } } - if (IS_ARROWLAKE(gt->i915)) { + /* + * ARL SKUs require newer firmwares, but the blob is actually common + * across all MTL and ARL SKUs, so we need to do an explicit version check + * here rather than using a separate table entry. If a too old version + * is found, then just don't use GSC rather than aborting the driver load. + * Note that the major number in the GSC FW version is used to indicate + * the platform, so we expect it to always be 102 for MTL/ARL binaries. + */ + if (IS_ARROWLAKE_S(gt->i915)) + min_ver = (struct intel_uc_fw_ver){ 102, 0, 10, 1878 }; + else if (IS_ARROWLAKE_H(gt->i915) || IS_ARROWLAKE_U(gt->i915)) + min_ver = (struct intel_uc_fw_ver){ 102, 1, 15, 1926 }; + + if (IS_METEORLAKE(gt->i915) && gsc->release.major != 102) { + gt_info(gt, "Invalid GSC firmware for MTL/ARL, got %d.%d.%d.%d but need 102.x.x.x", + gsc->release.major, gsc->release.minor, + gsc->release.patch, gsc->release.build); + return -EINVAL; + } + + if (min_ver.major) { bool too_old = false; - /* - * ARL requires a newer firmware than MTL did (102.0.10.1878) but the - * firmware is actually common. So, need to do an explicit version check - * here rather than using a separate table entry. And if the older - * MTL-only version is found, then just don't use GSC rather than aborting - * the driver load. - */ - if (gsc->release.major < 102) { + if (gsc->release.minor < min_ver.minor) { too_old = true; - } else if (gsc->release.major == 102) { - if (gsc->release.minor == 0) { - if (gsc->release.patch < 10) { + } else if (gsc->release.minor == min_ver.minor) { + if (gsc->release.patch < min_ver.patch) { + too_old = true; + } else if (gsc->release.patch == min_ver.patch) { + if (gsc->release.build < min_ver.build) too_old = true; - } else if (gsc->release.patch == 10) { - if (gsc->release.build < 1878) - too_old = true; - } } } if (too_old) { - gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least 102.0.10.1878", + gt_info(gt, "GSC firmware too old for ARL, got %d.%d.%d.%d but need at least %d.%d.%d.%d", gsc->release.major, gsc->release.minor, - gsc->release.patch, gsc->release.build); + gsc->release.patch, gsc->release.build, + min_ver.major, min_ver.minor, + min_ver.patch, min_ver.build); return -EINVAL; } } diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 39f6614a0a99..aa0b1bfb38e0 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -540,8 +540,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_LUNARLAKE(i915) (0 && i915) #define IS_BATTLEMAGE(i915) (0 && i915) -#define IS_ARROWLAKE(i915) \ - IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL) +#define IS_ARROWLAKE_H(i915) \ + IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_H) +#define IS_ARROWLAKE_U(i915) \ + IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_U) +#define IS_ARROWLAKE_S(i915) \ + IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_ARL_S) #define IS_DG2_G10(i915) \ IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10) #define IS_DG2_G11(i915) \ diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 519e096c607c..8f62cfa23fb7 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -273,11 +273,6 @@ i915_request_active_engine(struct i915_request *rq, return ret; } -static void __rq_init_watchdog(struct i915_request *rq) -{ - rq->watchdog.timer.function = NULL; -} - static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer) { struct i915_request *rq = @@ -294,6 +289,14 @@ static enum hrtimer_restart __rq_watchdog_expired(struct hrtimer *hrtimer) return HRTIMER_NORESTART; } +static void __rq_init_watchdog(struct i915_request *rq) +{ + struct i915_request_watchdog *wdg = &rq->watchdog; + + hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + wdg->timer.function = __rq_watchdog_expired; +} + static void __rq_arm_watchdog(struct i915_request *rq) { struct i915_request_watchdog *wdg = &rq->watchdog; @@ -304,8 +307,6 @@ static void __rq_arm_watchdog(struct i915_request *rq) i915_request_get(rq); - hrtimer_init(&wdg->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - wdg->timer.function = __rq_watchdog_expired; hrtimer_start_range_ns(&wdg->timer, ns_to_ktime(ce->watchdog.timeout_us * NSEC_PER_USEC), @@ -317,7 +318,7 @@ static void __rq_cancel_watchdog(struct i915_request *rq) { struct i915_request_watchdog *wdg = &rq->watchdog; - if (wdg->timer.function && hrtimer_try_to_cancel(&wdg->timer) > 0) + if (hrtimer_try_to_cancel(&wdg->timer) > 0) i915_request_put(rq); } diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index 3c47c625993e..467999249b9a 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -200,8 +200,16 @@ static const u16 subplatform_g12_ids[] = { INTEL_DG2_G12_IDS(ID), }; -static const u16 subplatform_arl_ids[] = { - INTEL_ARL_IDS(ID), +static const u16 subplatform_arl_h_ids[] = { + INTEL_ARL_H_IDS(ID), +}; + +static const u16 subplatform_arl_u_ids[] = { + INTEL_ARL_U_IDS(ID), +}; + +static const u16 subplatform_arl_s_ids[] = { + INTEL_ARL_S_IDS(ID), }; static bool find_devid(u16 id, const u16 *p, unsigned int num) @@ -261,9 +269,15 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915) } else if (find_devid(devid, subplatform_g12_ids, ARRAY_SIZE(subplatform_g12_ids))) { mask = BIT(INTEL_SUBPLATFORM_G12); - } else if (find_devid(devid, subplatform_arl_ids, - ARRAY_SIZE(subplatform_arl_ids))) { - mask = BIT(INTEL_SUBPLATFORM_ARL); + } else if (find_devid(devid, subplatform_arl_h_ids, + ARRAY_SIZE(subplatform_arl_h_ids))) { + mask = BIT(INTEL_SUBPLATFORM_ARL_H); + } else if (find_devid(devid, subplatform_arl_u_ids, + ARRAY_SIZE(subplatform_arl_u_ids))) { + mask = BIT(INTEL_SUBPLATFORM_ARL_U); + } else if (find_devid(devid, subplatform_arl_s_ids, + ARRAY_SIZE(subplatform_arl_s_ids))) { + mask = BIT(INTEL_SUBPLATFORM_ARL_S); } GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK); diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 643ff1bf74ee..a9fcaf33df9e 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -128,7 +128,9 @@ enum intel_platform { #define INTEL_SUBPLATFORM_RPLU 2 /* MTL */ -#define INTEL_SUBPLATFORM_ARL 0 +#define INTEL_SUBPLATFORM_ARL_H 0 +#define INTEL_SUBPLATFORM_ARL_U 1 +#define INTEL_SUBPLATFORM_ARL_S 2 enum intel_ppgtt_type { INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE, diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index 61da4ed9d521..0727492576be 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -4,7 +4,7 @@ * Copyright © 2018 Intel Corporation */ -#include <linux/random.h> +#include <linux/prandom.h> #include "gem/i915_gem_internal.h" #include "gem/i915_gem_pm.h" diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h index 05364eca20f7..70330a2e80f2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_random.h +++ b/drivers/gpu/drm/i915/selftests/i915_random.h @@ -26,7 +26,7 @@ #define __I915_SELFTESTS_RANDOM_H__ #include <linux/math64.h> -#include <linux/random.h> +#include <linux/prandom.h> #include "../i915_selftest.h" diff --git a/drivers/gpu/drm/i915/selftests/scatterlist.c b/drivers/gpu/drm/i915/selftests/scatterlist.c index 805c4bfb85fe..7e59591bbed6 100644 --- a/drivers/gpu/drm/i915/selftests/scatterlist.c +++ b/drivers/gpu/drm/i915/selftests/scatterlist.c @@ -22,7 +22,7 @@ */ #include <linux/prime_numbers.h> -#include <linux/random.h> +#include <linux/prandom.h> #include "i915_selftest.h" #include "i915_utils.h" diff --git a/drivers/gpu/drm/imagination/pvr_context.c b/drivers/gpu/drm/imagination/pvr_context.c index eded5e955cc0..4cb3494c0bb2 100644 --- a/drivers/gpu/drm/imagination/pvr_context.c +++ b/drivers/gpu/drm/imagination/pvr_context.c @@ -17,10 +17,14 @@ #include <drm/drm_auth.h> #include <drm/drm_managed.h> + +#include <linux/bug.h> #include <linux/errno.h> #include <linux/kernel.h> +#include <linux/list.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/xarray.h> @@ -354,6 +358,10 @@ int pvr_context_create(struct pvr_file *pvr_file, struct drm_pvr_ioctl_create_co return err; } + spin_lock(&pvr_dev->ctx_list_lock); + list_add_tail(&ctx->file_link, &pvr_file->contexts); + spin_unlock(&pvr_dev->ctx_list_lock); + return 0; err_destroy_fw_obj: @@ -380,6 +388,11 @@ pvr_context_release(struct kref *ref_count) container_of(ref_count, struct pvr_context, ref_count); struct pvr_device *pvr_dev = ctx->pvr_dev; + WARN_ON(in_interrupt()); + spin_lock(&pvr_dev->ctx_list_lock); + list_del(&ctx->file_link); + spin_unlock(&pvr_dev->ctx_list_lock); + xa_erase(&pvr_dev->ctx_ids, ctx->ctx_id); pvr_context_destroy_queues(ctx); pvr_fw_object_destroy(ctx->fw_obj); @@ -437,11 +450,30 @@ pvr_context_destroy(struct pvr_file *pvr_file, u32 handle) */ void pvr_destroy_contexts_for_file(struct pvr_file *pvr_file) { + struct pvr_device *pvr_dev = pvr_file->pvr_dev; struct pvr_context *ctx; unsigned long handle; xa_for_each(&pvr_file->ctx_handles, handle, ctx) pvr_context_destroy(pvr_file, handle); + + spin_lock(&pvr_dev->ctx_list_lock); + ctx = list_first_entry(&pvr_file->contexts, struct pvr_context, file_link); + + while (!list_entry_is_head(ctx, &pvr_file->contexts, file_link)) { + list_del_init(&ctx->file_link); + + if (pvr_context_get_if_referenced(ctx)) { + spin_unlock(&pvr_dev->ctx_list_lock); + + pvr_vm_unmap_all(ctx->vm_ctx); + + pvr_context_put(ctx); + spin_lock(&pvr_dev->ctx_list_lock); + } + ctx = list_first_entry(&pvr_file->contexts, struct pvr_context, file_link); + } + spin_unlock(&pvr_dev->ctx_list_lock); } /** @@ -451,6 +483,7 @@ void pvr_destroy_contexts_for_file(struct pvr_file *pvr_file) void pvr_context_device_init(struct pvr_device *pvr_dev) { xa_init_flags(&pvr_dev->ctx_ids, XA_FLAGS_ALLOC1); + spin_lock_init(&pvr_dev->ctx_list_lock); } /** diff --git a/drivers/gpu/drm/imagination/pvr_context.h b/drivers/gpu/drm/imagination/pvr_context.h index 0c7b97dfa6ba..07afa179cdf4 100644 --- a/drivers/gpu/drm/imagination/pvr_context.h +++ b/drivers/gpu/drm/imagination/pvr_context.h @@ -85,6 +85,9 @@ struct pvr_context { /** @compute: Transfer queue. */ struct pvr_queue *transfer; } queues; + + /** @file_link: pvr_file PVR context list link. */ + struct list_head file_link; }; static __always_inline struct pvr_queue * @@ -124,6 +127,24 @@ pvr_context_get(struct pvr_context *ctx) } /** + * pvr_context_get_if_referenced() - Take an additional reference on a still + * referenced context. + * @ctx: Context pointer. + * + * Call pvr_context_put() to release. + * + * Returns: + * * True on success, or + * * false if no context pointer passed, or the context wasn't still + * * referenced. + */ +static __always_inline bool +pvr_context_get_if_referenced(struct pvr_context *ctx) +{ + return ctx != NULL && kref_get_unless_zero(&ctx->ref_count) != 0; +} + +/** * pvr_context_lookup() - Lookup context pointer from handle and file. * @pvr_file: Pointer to pvr_file structure. * @handle: Context handle. diff --git a/drivers/gpu/drm/imagination/pvr_device.h b/drivers/gpu/drm/imagination/pvr_device.h index b574e23d484b..6d0dfacb677b 100644 --- a/drivers/gpu/drm/imagination/pvr_device.h +++ b/drivers/gpu/drm/imagination/pvr_device.h @@ -23,6 +23,7 @@ #include <linux/kernel.h> #include <linux/math.h> #include <linux/mutex.h> +#include <linux/spinlock_types.h> #include <linux/timer.h> #include <linux/types.h> #include <linux/wait.h> @@ -293,6 +294,12 @@ struct pvr_device { /** @sched_wq: Workqueue for schedulers. */ struct workqueue_struct *sched_wq; + + /** + * @ctx_list_lock: Lock to be held when accessing the context list in + * struct pvr_file. + */ + spinlock_t ctx_list_lock; }; /** @@ -344,6 +351,9 @@ struct pvr_file { * This array is used to allocate handles returned to userspace. */ struct xarray vm_ctx_handles; + + /** @contexts: PVR context list. */ + struct list_head contexts; }; /** diff --git a/drivers/gpu/drm/imagination/pvr_drv.c b/drivers/gpu/drm/imagination/pvr_drv.c index 1a0cb7aa9cea..fb17196e05f4 100644 --- a/drivers/gpu/drm/imagination/pvr_drv.c +++ b/drivers/gpu/drm/imagination/pvr_drv.c @@ -28,6 +28,7 @@ #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> +#include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -1326,6 +1327,8 @@ pvr_drm_driver_open(struct drm_device *drm_dev, struct drm_file *file) */ pvr_file->pvr_dev = pvr_dev; + INIT_LIST_HEAD(&pvr_file->contexts); + xa_init_flags(&pvr_file->ctx_handles, XA_FLAGS_ALLOC1); xa_init_flags(&pvr_file->free_list_handles, XA_FLAGS_ALLOC1); xa_init_flags(&pvr_file->hwrt_handles, XA_FLAGS_ALLOC1); diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c index 97c0f772ed65..7bd6ba4c6e8a 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.c +++ b/drivers/gpu/drm/imagination/pvr_vm.c @@ -14,6 +14,7 @@ #include <drm/drm_gem.h> #include <drm/drm_gpuvm.h> +#include <linux/bug.h> #include <linux/container_of.h> #include <linux/err.h> #include <linux/errno.h> @@ -597,12 +598,26 @@ err_free: } /** - * pvr_vm_context_release() - Teardown a VM context. - * @ref_count: Pointer to reference counter of the VM context. + * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context. + * @vm_ctx: Target VM context. * * This function ensures that no mappings are left dangling by unmapping them * all in order of ascending device-virtual address. */ +void +pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx) +{ + WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start, + vm_ctx->gpuvm_mgr.mm_range)); +} + +/** + * pvr_vm_context_release() - Teardown a VM context. + * @ref_count: Pointer to reference counter of the VM context. + * + * This function also ensures that no mappings are left dangling by calling + * pvr_vm_unmap_all. + */ static void pvr_vm_context_release(struct kref *ref_count) { @@ -612,8 +627,7 @@ pvr_vm_context_release(struct kref *ref_count) if (vm_ctx->fw_mem_ctx_obj) pvr_fw_object_destroy(vm_ctx->fw_mem_ctx_obj); - WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start, - vm_ctx->gpuvm_mgr.mm_range)); + pvr_vm_unmap_all(vm_ctx); pvr_mmu_context_destroy(vm_ctx->mmu_ctx); drm_gem_private_object_fini(&vm_ctx->dummy_gem); diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h index f2a6463f2b05..79406243617c 100644 --- a/drivers/gpu/drm/imagination/pvr_vm.h +++ b/drivers/gpu/drm/imagination/pvr_vm.h @@ -39,6 +39,7 @@ int pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset, u64 device_addr, u64 size); int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size); +void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx); dma_addr_t pvr_vm_get_page_table_root_addr(struct pvr_vm_context *vm_ctx); struct dma_resv *pvr_vm_get_dma_resv(struct pvr_vm_context *vm_ctx); diff --git a/drivers/gpu/drm/lib/drm_random.h b/drivers/gpu/drm/lib/drm_random.h index 5543bf0474bc..9f827260a89d 100644 --- a/drivers/gpu/drm/lib/drm_random.h +++ b/drivers/gpu/drm/lib/drm_random.h @@ -6,7 +6,7 @@ * be transposed to lib/ at the earliest convenience. */ -#include <linux/random.h> +#include <linux/prandom.h> #define DRM_RND_STATE_INITIALIZER(seed__) ({ \ struct rnd_state state__; \ diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 465a4cd14a43..3a40b38f2467 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -572,8 +572,19 @@ struct drm_gem_object *adreno_fw_create_bo(struct msm_gpu *gpu, int adreno_hw_init(struct msm_gpu *gpu) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + int ret; + VERB("%s", gpu->name); + if (adreno_gpu->info->family >= ADRENO_6XX_GEN1 && + qcom_scm_set_gpu_smmu_aperture_is_available()) { + /* We currently always use context bank 0, so hard code this */ + ret = qcom_scm_set_gpu_smmu_aperture(0); + if (ret) + DRM_DEV_ERROR(gpu->dev->dev, "unable to set SMMU aperture: %d\n", ret); + } + for (int i = 0; i < gpu->nr_rings; i++) { struct msm_ringbuffer *ring = gpu->rb[i]; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c index 027867c2a8c5..99110ab2f44d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c @@ -992,7 +992,7 @@ r535_dp_train_target(struct nvkm_outp *outp, u8 target, bool mst, u8 link_nr, u8 ctrl->data = data; ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); - if (ret == -EAGAIN && ctrl->retryTimeMs) { + if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) { /* * Device (likely an eDP panel) isn't ready yet, wait for the time specified * by GSP before retrying again @@ -1060,33 +1060,44 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize) NV0073_CTRL_DP_AUXCH_CTRL_PARAMS *ctrl; u8 size = *psize; int ret; + int retries; - ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl)); - if (IS_ERR(ctrl)) - return PTR_ERR(ctrl); + for (retries = 0; retries < 3; ++retries) { + ctrl = nvkm_gsp_rm_ctrl_get(&disp->rm.objcom, NV0073_CTRL_CMD_DP_AUXCH_CTRL, sizeof(*ctrl)); + if (IS_ERR(ctrl)) + return PTR_ERR(ctrl); - ctrl->subDeviceInstance = 0; - ctrl->displayId = BIT(outp->index); - ctrl->bAddrOnly = !size; - ctrl->cmd = type; - if (ctrl->bAddrOnly) { - ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE); - ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, I2C_MOT, FALSE); - } - ctrl->addr = addr; - ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0; - memcpy(ctrl->data, data, size); + ctrl->subDeviceInstance = 0; + ctrl->displayId = BIT(outp->index); + ctrl->bAddrOnly = !size; + ctrl->cmd = type; + if (ctrl->bAddrOnly) { + ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, REQ_TYPE, WRITE); + ctrl->cmd = NVDEF_SET(ctrl->cmd, NV0073_CTRL, DP_AUXCH_CMD, I2C_MOT, FALSE); + } + ctrl->addr = addr; + ctrl->size = !ctrl->bAddrOnly ? (size - 1) : 0; + memcpy(ctrl->data, data, size); - ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); - if (ret) { - nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); - return ret; + ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); + if ((ret == -EAGAIN || ret == -EBUSY) && ctrl->retryTimeMs) { + /* + * Device (likely an eDP panel) isn't ready yet, wait for the time specified + * by GSP before retrying again + */ + nvkm_debug(&disp->engine.subdev, + "Waiting %dms for GSP LT panel delay before retrying in AUX\n", + ctrl->retryTimeMs); + msleep(ctrl->retryTimeMs); + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + } else { + memcpy(data, ctrl->data, size); + *psize = ctrl->size; + ret = ctrl->replyType; + nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); + break; + } } - - memcpy(data, ctrl->data, size); - *psize = ctrl->size; - ret = ctrl->replyType; - nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c index a1c8545f1249..cac6d64ab67d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c @@ -89,11 +89,6 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, nvkm_falcon_fw_dtor_sigs(fw); } - /* after last write to the img, sync dma mappings */ - dma_sync_single_for_device(fw->fw.device->dev, - fw->fw.phys, - sg_dma_len(&fw->fw.mem.sgl), - DMA_TO_DEVICE); FLCNFW_DBG(fw, "resetting"); fw->func->reset(fw); @@ -105,6 +100,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user, goto done; } + /* after last write to the img, sync dma mappings */ + dma_sync_single_for_device(fw->fw.device->dev, + fw->fw.phys, + sg_dma_len(&fw->fw.mem.sgl), + DMA_TO_DEVICE); + ret = fw->func->load(fw); if (ret) goto done; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index cf58f9da9139..d586aea30898 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -78,7 +78,7 @@ r535_rpc_status_to_errno(uint32_t rpc_status) switch (rpc_status) { case 0x55: /* NV_ERR_NOT_READY */ case 0x66: /* NV_ERR_TIMEOUT_RETRY */ - return -EAGAIN; + return -EBUSY; case 0x51: /* NV_ERR_NO_MEMORY */ return -ENOMEM; default: @@ -601,7 +601,7 @@ r535_gsp_rpc_rm_alloc_push(struct nvkm_gsp_object *object, void *argv, u32 repc) if (rpc->status) { ret = ERR_PTR(r535_rpc_status_to_errno(rpc->status)); - if (PTR_ERR(ret) != -EAGAIN) + if (PTR_ERR(ret) != -EAGAIN && PTR_ERR(ret) != -EBUSY) nvkm_error(&gsp->subdev, "RM_ALLOC: 0x%x\n", rpc->status); } else { ret = repc ? rpc->params : NULL; @@ -660,7 +660,7 @@ r535_gsp_rpc_rm_ctrl_push(struct nvkm_gsp_object *object, void **argv, u32 repc) if (rpc->status) { ret = r535_rpc_status_to_errno(rpc->status); - if (ret != -EAGAIN) + if (ret != -EAGAIN && ret != -EBUSY) nvkm_error(&gsp->subdev, "cli:0x%08x obj:0x%08x ctrl cmd:0x%08x failed: 0x%08x\n", object->client->object.handle, object->handle, rpc->cmd, rpc->status); } diff --git a/drivers/gpu/drm/omapdrm/dss/dpi.c b/drivers/gpu/drm/omapdrm/dss/dpi.c index 030f997eccd0..b17e77f700dd 100644 --- a/drivers/gpu/drm/omapdrm/dss/dpi.c +++ b/drivers/gpu/drm/omapdrm/dss/dpi.c @@ -16,6 +16,7 @@ #include <linux/export.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/of_graph.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> #include <linux/string.h> @@ -709,7 +710,7 @@ int dpi_init_port(struct dss_device *dss, struct platform_device *pdev, if (!dpi) return -ENOMEM; - ep = of_get_next_child(port, NULL); + ep = of_graph_get_next_port_endpoint(port, NULL); if (!ep) return 0; diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c index 91eaae3b9481..f9ae358e8e52 100644 --- a/drivers/gpu/drm/omapdrm/dss/sdi.c +++ b/drivers/gpu/drm/omapdrm/dss/sdi.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/of_graph.h> #include <linux/platform_device.h> #include <linux/regulator/consumer.h> #include <linux/string.h> @@ -346,7 +347,7 @@ int sdi_init_port(struct dss_device *dss, struct platform_device *pdev, if (!sdi) return -ENOMEM; - ep = of_get_next_child(port, NULL); + ep = of_graph_get_next_port_endpoint(port, NULL); if (!ep) { r = 0; goto err_free; diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c index 4082c8f2951d..6fbff516c1c1 100644 --- a/drivers/gpu/drm/panthor/panthor_device.c +++ b/drivers/gpu/drm/panthor/panthor_device.c @@ -390,11 +390,15 @@ int panthor_device_mmap_io(struct panthor_device *ptdev, struct vm_area_struct * { u64 offset = (u64)vma->vm_pgoff << PAGE_SHIFT; + if ((vma->vm_flags & VM_SHARED) == 0) + return -EINVAL; + switch (offset) { case DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET: if (vma->vm_end - vma->vm_start != PAGE_SIZE || (vma->vm_flags & (VM_WRITE | VM_EXEC))) return -EINVAL; + vm_flags_clear(vma, VM_MAYWRITE); break; diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c index 5d5e25b1be95..0e6f94df690d 100644 --- a/drivers/gpu/drm/panthor/panthor_mmu.c +++ b/drivers/gpu/drm/panthor/panthor_mmu.c @@ -990,6 +990,8 @@ panthor_vm_map_pages(struct panthor_vm *vm, u64 iova, int prot, if (!size) break; + + offset = 0; } return panthor_vm_flush_range(vm, start_iova, iova - start_iova); @@ -1580,7 +1582,9 @@ panthor_vm_pool_get_vm(struct panthor_vm_pool *pool, u32 handle) { struct panthor_vm *vm; + xa_lock(&pool->xa); vm = panthor_vm_get(xa_load(&pool->xa, handle)); + xa_unlock(&pool->xa); return vm; } diff --git a/drivers/gpu/drm/qxl/Kconfig b/drivers/gpu/drm/qxl/Kconfig index ca3f51c2a8fe..17d6927e5e23 100644 --- a/drivers/gpu/drm/qxl/Kconfig +++ b/drivers/gpu/drm/qxl/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_QXL tristate "QXL virtual GPU" - depends on DRM && PCI && MMU + depends on DRM && PCI && MMU && HAS_IOPORT select DRM_KMS_HELPER select DRM_TTM select DRM_TTM_HELPER diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index f161f40d8ce4..69900138295b 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1093,10 +1093,10 @@ static int vop_plane_atomic_async_check(struct drm_plane *plane, if (!plane->state->fb) return -EINVAL; - if (state) - crtc_state = drm_atomic_get_existing_crtc_state(state, - new_plane_state->crtc); - else /* Special case for asynchronous cursor updates. */ + crtc_state = drm_atomic_get_existing_crtc_state(state, new_plane_state->crtc); + + /* Special case for asynchronous cursor updates. */ + if (!crtc_state) crtc_state = plane->crtc->state; return drm_atomic_helper_check_plane_state(plane->state, crtc_state, diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index 00c8564520e7..caee824832b3 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -46,6 +46,7 @@ struct gr3d { unsigned int nclocks; struct reset_control_bulk_data resets[RST_GR3D_MAX]; unsigned int nresets; + struct dev_pm_domain_list *pd_list; DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS); }; @@ -369,18 +370,13 @@ static int gr3d_power_up_legacy_domain(struct device *dev, const char *name, return 0; } -static void gr3d_del_link(void *link) -{ - device_link_del(link); -} - static int gr3d_init_power(struct device *dev, struct gr3d *gr3d) { - static const char * const opp_genpd_names[] = { "3d0", "3d1", NULL }; - const u32 link_flags = DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME; - struct device **opp_virt_devs, *pd_dev; - struct device_link *link; - unsigned int i; + struct dev_pm_domain_attach_data pd_data = { + .pd_names = (const char *[]) { "3d0", "3d1" }, + .num_pd_names = 2, + .pd_flags = PD_FLAG_REQUIRED_OPP, + }; int err; err = of_count_phandle_with_args(dev->of_node, "power-domains", @@ -414,29 +410,10 @@ static int gr3d_init_power(struct device *dev, struct gr3d *gr3d) if (dev->pm_domain) return 0; - err = devm_pm_opp_attach_genpd(dev, opp_genpd_names, &opp_virt_devs); - if (err) + err = devm_pm_domain_attach_list(dev, &pd_data, &gr3d->pd_list); + if (err < 0) return err; - for (i = 0; opp_genpd_names[i]; i++) { - pd_dev = opp_virt_devs[i]; - if (!pd_dev) { - dev_err(dev, "failed to get %s power domain\n", - opp_genpd_names[i]); - return -EINVAL; - } - - link = device_link_add(dev, pd_dev, link_flags); - if (!link) { - dev_err(dev, "failed to link to %s\n", dev_name(pd_dev)); - return -EINVAL; - } - - err = devm_add_action_or_reset(dev, gr3d_del_link, link); - if (err) - return err; - } - return 0; } diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 31fc5d839e10..e738bb858316 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/bug.h> #include <linux/module.h> #include <linux/pci.h> @@ -95,12 +96,17 @@ struct bochs_device { /* ---------------------------------------------------------------------- */ +static __always_inline bool bochs_uses_mmio(struct bochs_device *bochs) +{ + return !IS_ENABLED(CONFIG_HAS_IOPORT) || bochs->mmio; +} + static void bochs_vga_writeb(struct bochs_device *bochs, u16 ioport, u8 val) { if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) return; - if (bochs->mmio) { + if (bochs_uses_mmio(bochs)) { int offset = ioport - 0x3c0 + 0x400; writeb(val, bochs->mmio + offset); @@ -114,7 +120,7 @@ static u8 bochs_vga_readb(struct bochs_device *bochs, u16 ioport) if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) return 0xff; - if (bochs->mmio) { + if (bochs_uses_mmio(bochs)) { int offset = ioport - 0x3c0 + 0x400; return readb(bochs->mmio + offset); @@ -127,7 +133,7 @@ static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg) { u16 ret = 0; - if (bochs->mmio) { + if (bochs_uses_mmio(bochs)) { int offset = 0x500 + (reg << 1); ret = readw(bochs->mmio + offset); @@ -140,7 +146,7 @@ static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg) static void bochs_dispi_write(struct bochs_device *bochs, u16 reg, u16 val) { - if (bochs->mmio) { + if (bochs_uses_mmio(bochs)) { int offset = 0x500 + (reg << 1); writew(val, bochs->mmio + offset); @@ -228,7 +234,7 @@ static int bochs_hw_init(struct drm_device *dev) DRM_ERROR("Cannot map mmio region\n"); return -ENOMEM; } - } else { + } else if (IS_ENABLED(CONFIG_HAS_IOPORT)) { ioaddr = VBE_DISPI_IOPORT_INDEX; iosize = 2; if (!request_region(ioaddr, iosize, "bochs-drm")) { @@ -236,6 +242,9 @@ static int bochs_hw_init(struct drm_device *dev) return -EBUSY; } bochs->ioports = 1; + } else { + dev_err(dev->dev, "I/O ports are not supported\n"); + return -EIO; } id = bochs_dispi_read(bochs, VBE_DISPI_INDEX_ID); diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c index 751326e3d9c3..e31e1df029ab 100644 --- a/drivers/gpu/drm/tiny/cirrus.c +++ b/drivers/gpu/drm/tiny/cirrus.c @@ -509,8 +509,10 @@ static void cirrus_crtc_helper_atomic_enable(struct drm_crtc *crtc, cirrus_mode_set(cirrus, &crtc_state->mode); +#ifdef CONFIG_HAS_IOPORT /* Unblank (needed on S3 resume, vgabios doesn't do it then) */ outb(VGA_AR_ENABLE_DISPLAY, VGA_ATT_W); +#endif drm_dev_exit(idx); } diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 3353e97687d1..a17e62867f3b 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -471,7 +471,7 @@ void ttm_object_device_release(struct ttm_object_device **p_tdev) */ static bool __must_check get_dma_buf_unless_doomed(struct dma_buf *dmabuf) { - return atomic_long_inc_not_zero(&dmabuf->file->f_count) != 0L; + return file_ref_get(&dmabuf->file->f_ref); } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 63b8d7591253..10d596cb4b40 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1265,6 +1265,8 @@ static int vmw_framebuffer_surface_create_handle(struct drm_framebuffer *fb, struct vmw_framebuffer_surface *vfbs = vmw_framebuffer_to_vfbs(fb); struct vmw_bo *bo = vmw_user_object_buffer(&vfbs->uo); + if (WARN_ON(!bo)) + return -EINVAL; return drm_gem_handle_create(file_priv, &bo->tbo.base, handle); } diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig index 7bbe46a98ff1..116f58774135 100644 --- a/drivers/gpu/drm/xe/Kconfig +++ b/drivers/gpu/drm/xe/Kconfig @@ -49,7 +49,7 @@ config DRM_XE config DRM_XE_DISPLAY bool "Enable display support" - depends on DRM_XE && DRM_XE=m + depends on DRM_XE && DRM_XE=m && HAS_IOPORT select FB_IOMEM_HELPERS select I2C select I2C_ALGOBIT diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h index 00ad34ed73a5..bd604b9f08e4 100644 --- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h @@ -517,7 +517,7 @@ * [4-6] RSVD * [7] Disabled */ -#define CCS_MODE XE_REG(0x14804) +#define CCS_MODE XE_REG(0x14804, XE_REG_OPTION_MASKED) #define CCS_MODE_CSLICE_0_3_MASK REG_GENMASK(11, 0) /* 3 bits per cslice */ #define CCS_MODE_CSLICE_MASK 0x7 /* CCS0-3 + rsvd */ #define CCS_MODE_CSLICE_WIDTH ilog2(CCS_MODE_CSLICE_MASK + 1) diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index e5f51fd23c65..2a093540354e 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -886,8 +886,8 @@ int xe_bo_evict_pinned(struct xe_bo *bo) if (WARN_ON(!xe_bo_is_pinned(bo))) return -EINVAL; - if (WARN_ON(!xe_bo_is_vram(bo))) - return -EINVAL; + if (!xe_bo_is_vram(bo)) + return 0; ret = ttm_bo_mem_space(&bo->ttm, &placement, &new_mem, &ctx); if (ret) @@ -937,6 +937,7 @@ int xe_bo_restore_pinned(struct xe_bo *bo) .interruptible = false, }; struct ttm_resource *new_mem; + struct ttm_place *place = &bo->placements[0]; int ret; xe_bo_assert_held(bo); @@ -947,9 +948,15 @@ int xe_bo_restore_pinned(struct xe_bo *bo) if (WARN_ON(!xe_bo_is_pinned(bo))) return -EINVAL; - if (WARN_ON(xe_bo_is_vram(bo) || !bo->ttm.ttm)) + if (WARN_ON(xe_bo_is_vram(bo))) + return -EINVAL; + + if (WARN_ON(!bo->ttm.ttm && !xe_bo_is_stolen(bo))) return -EINVAL; + if (!mem_type_is_vram(place->mem_type)) + return 0; + ret = ttm_bo_mem_space(&bo->ttm, &bo->placement, &new_mem, &ctx); if (ret) return ret; @@ -1719,6 +1726,7 @@ int xe_bo_pin_external(struct xe_bo *bo) int xe_bo_pin(struct xe_bo *bo) { + struct ttm_place *place = &bo->placements[0]; struct xe_device *xe = xe_bo_device(bo); int err; @@ -1749,21 +1757,21 @@ int xe_bo_pin(struct xe_bo *bo) */ if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) && bo->flags & XE_BO_FLAG_INTERNAL_TEST)) { - struct ttm_place *place = &(bo->placements[0]); - if (mem_type_is_vram(place->mem_type)) { xe_assert(xe, place->flags & TTM_PL_FLAG_CONTIGUOUS); place->fpfn = (xe_bo_addr(bo, 0, PAGE_SIZE) - vram_region_gpu_offset(bo->ttm.resource)) >> PAGE_SHIFT; place->lpfn = place->fpfn + (bo->size >> PAGE_SHIFT); - - spin_lock(&xe->pinned.lock); - list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present); - spin_unlock(&xe->pinned.lock); } } + if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) { + spin_lock(&xe->pinned.lock); + list_add_tail(&bo->pinned_link, &xe->pinned.kernel_bo_present); + spin_unlock(&xe->pinned.lock); + } + ttm_bo_pin(&bo->ttm); /* @@ -1809,23 +1817,18 @@ void xe_bo_unpin_external(struct xe_bo *bo) void xe_bo_unpin(struct xe_bo *bo) { + struct ttm_place *place = &bo->placements[0]; struct xe_device *xe = xe_bo_device(bo); xe_assert(xe, !bo->ttm.base.import_attach); xe_assert(xe, xe_bo_is_pinned(bo)); - if (IS_DGFX(xe) && !(IS_ENABLED(CONFIG_DRM_XE_DEBUG) && - bo->flags & XE_BO_FLAG_INTERNAL_TEST)) { - struct ttm_place *place = &(bo->placements[0]); - - if (mem_type_is_vram(place->mem_type)) { - spin_lock(&xe->pinned.lock); - xe_assert(xe, !list_empty(&bo->pinned_link)); - list_del_init(&bo->pinned_link); - spin_unlock(&xe->pinned.lock); - } + if (mem_type_is_vram(place->mem_type) || bo->flags & XE_BO_FLAG_GGTT) { + spin_lock(&xe->pinned.lock); + xe_assert(xe, !list_empty(&bo->pinned_link)); + list_del_init(&bo->pinned_link); + spin_unlock(&xe->pinned.lock); } - ttm_bo_unpin(&bo->ttm); } diff --git a/drivers/gpu/drm/xe/xe_bo_evict.c b/drivers/gpu/drm/xe/xe_bo_evict.c index 541b49007d73..8fb2be061003 100644 --- a/drivers/gpu/drm/xe/xe_bo_evict.c +++ b/drivers/gpu/drm/xe/xe_bo_evict.c @@ -34,14 +34,22 @@ int xe_bo_evict_all(struct xe_device *xe) u8 id; int ret; - if (!IS_DGFX(xe)) - return 0; - /* User memory */ - for (mem_type = XE_PL_VRAM0; mem_type <= XE_PL_VRAM1; ++mem_type) { + for (mem_type = XE_PL_TT; mem_type <= XE_PL_VRAM1; ++mem_type) { struct ttm_resource_manager *man = ttm_manager_type(bdev, mem_type); + /* + * On igpu platforms with flat CCS we need to ensure we save and restore any CCS + * state since this state lives inside graphics stolen memory which doesn't survive + * hibernation. + * + * This can be further improved by only evicting objects that we know have actually + * used a compression enabled PAT index. + */ + if (mem_type == XE_PL_TT && (IS_DGFX(xe) || !xe_device_has_flat_ccs(xe))) + continue; + if (man) { ret = ttm_resource_manager_evict_all(bdev, man); if (ret) @@ -125,9 +133,6 @@ int xe_bo_restore_kernel(struct xe_device *xe) struct xe_bo *bo; int ret; - if (!IS_DGFX(xe)) - return 0; - spin_lock(&xe->pinned.lock); for (;;) { bo = list_first_entry_or_null(&xe->pinned.evicted, @@ -159,7 +164,6 @@ int xe_bo_restore_kernel(struct xe_device *xe) * should setup the iosys map. */ xe_assert(xe, !iosys_map_is_null(&bo->vmap)); - xe_assert(xe, xe_bo_is_vram(bo)); xe_bo_put(bo); diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 10fd4601b9f2..a1987b554a8d 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -87,10 +87,6 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) mutex_init(&xef->exec_queue.lock); xa_init_flags(&xef->exec_queue.xa, XA_FLAGS_ALLOC1); - spin_lock(&xe->clients.lock); - xe->clients.count++; - spin_unlock(&xe->clients.lock); - file->driver_priv = xef; kref_init(&xef->refcount); @@ -107,17 +103,12 @@ static int xe_file_open(struct drm_device *dev, struct drm_file *file) static void xe_file_destroy(struct kref *ref) { struct xe_file *xef = container_of(ref, struct xe_file, refcount); - struct xe_device *xe = xef->xe; xa_destroy(&xef->exec_queue.xa); mutex_destroy(&xef->exec_queue.lock); xa_destroy(&xef->vm.xa); mutex_destroy(&xef->vm.lock); - spin_lock(&xe->clients.lock); - xe->clients.count--; - spin_unlock(&xe->clients.lock); - xe_drm_client_put(xef->client); kfree(xef->process_name); kfree(xef); @@ -333,7 +324,6 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xe->info.force_execlist = xe_modparam.force_execlist; spin_lock_init(&xe->irq.lock); - spin_lock_init(&xe->clients.lock); init_waitqueue_head(&xe->ufence_wq); diff --git a/drivers/gpu/drm/xe/xe_device.h b/drivers/gpu/drm/xe/xe_device.h index 894f04770454..34620ef855c0 100644 --- a/drivers/gpu/drm/xe/xe_device.h +++ b/drivers/gpu/drm/xe/xe_device.h @@ -178,4 +178,18 @@ void xe_device_declare_wedged(struct xe_device *xe); struct xe_file *xe_file_get(struct xe_file *xef); void xe_file_put(struct xe_file *xef); +/* + * Occasionally it is seen that the G2H worker starts running after a delay of more than + * a second even after being queued and activated by the Linux workqueue subsystem. This + * leads to G2H timeout error. The root cause of issue lies with scheduling latency of + * Lunarlake Hybrid CPU. Issue disappears if we disable Lunarlake atom cores from BIOS + * and this is beyond xe kmd. + * + * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU. + */ +#define LNL_FLUSH_WORKQUEUE(wq__) \ + flush_workqueue(wq__) +#define LNL_FLUSH_WORK(wrk__) \ + flush_work(wrk__) + #endif diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 09d731a9125c..687f3a9039bb 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -353,15 +353,6 @@ struct xe_device { struct workqueue_struct *wq; } sriov; - /** @clients: drm clients info */ - struct { - /** @clients.lock: Protects drm clients info */ - spinlock_t lock; - - /** @clients.count: number of drm clients */ - u64 count; - } clients; - /** @usm: unified memory state */ struct { /** @usm.asid: convert a ASID to VM */ diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index f23ac1e2ed88..31cca938956f 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -132,12 +132,16 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file) if (XE_IOCTL_DBG(xe, !q)) return -ENOENT; - if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM)) - return -EINVAL; + if (XE_IOCTL_DBG(xe, q->flags & EXEC_QUEUE_FLAG_VM)) { + err = -EINVAL; + goto err_exec_queue; + } if (XE_IOCTL_DBG(xe, args->num_batch_buffer && - q->width != args->num_batch_buffer)) - return -EINVAL; + q->width != args->num_batch_buffer)) { + err = -EINVAL; + goto err_exec_queue; + } if (XE_IOCTL_DBG(xe, q->ops->reset_status(q))) { err = -ECANCELED; @@ -199,14 +203,14 @@ retry: write_locked = false; } if (err) - goto err_syncs; + goto err_hw_exec_mode; if (write_locked) { err = xe_vm_userptr_pin(vm); downgrade_write(&vm->lock); write_locked = false; if (err) - goto err_hw_exec_mode; + goto err_unlock_list; } if (!args->num_batch_buffer) { @@ -220,6 +224,7 @@ retry: fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm); if (IS_ERR(fence)) { err = PTR_ERR(fence); + xe_vm_unlock(vm); goto err_unlock_list; } for (i = 0; i < num_syncs; i++) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index d098d2dd1b2d..fd0f3b3c9101 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -260,8 +260,14 @@ void xe_exec_queue_fini(struct xe_exec_queue *q) { int i; + /* + * Before releasing our ref to lrc and xef, accumulate our run ticks + */ + xe_exec_queue_update_run_ticks(q); + for (i = 0; i < q->width; ++i) xe_lrc_put(q->lrc[i]); + __xe_exec_queue_free(q); } diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c index d2e4dc3aaf61..ffcbd05671fc 100644 --- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c +++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c @@ -68,6 +68,12 @@ static void __xe_gt_apply_ccs_mode(struct xe_gt *gt, u32 num_engines) } } + /* + * Mask bits need to be set for the register. Though only Xe2+ + * platforms require setting of mask bits, it won't harm for older + * platforms as these bits are unused there. + */ + mode |= CCS_MODE_CSLICE_0_3_MASK << 16; xe_mmio_write32(gt, CCS_MODE, mode); xe_gt_dbg(gt, "CCS_MODE=%x config:%08x, num_engines:%d, num_slices:%d\n", @@ -133,9 +139,10 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr, } /* CCS mode can only be updated when there are no drm clients */ - spin_lock(&xe->clients.lock); - if (xe->clients.count) { - spin_unlock(&xe->clients.lock); + mutex_lock(&xe->drm.filelist_mutex); + if (!list_empty(&xe->drm.filelist)) { + mutex_unlock(&xe->drm.filelist_mutex); + xe_gt_dbg(gt, "Rejecting compute mode change as there are active drm clients\n"); return -EBUSY; } @@ -146,7 +153,7 @@ ccs_mode_store(struct device *kdev, struct device_attribute *attr, xe_gt_reset_async(gt); } - spin_unlock(&xe->clients.lock); + mutex_unlock(&xe->drm.filelist_mutex); return count; } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 8250ef71e685..afdb477ecf83 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -387,6 +387,8 @@ static void pf_release_ggtt(struct xe_tile *tile, struct xe_ggtt_node *node) * the xe_ggtt_clear() called by below xe_ggtt_remove_node(). */ xe_ggtt_node_remove(node, false); + } else { + xe_ggtt_node_fini(node); } } @@ -442,7 +444,7 @@ static int pf_provision_vf_ggtt(struct xe_gt *gt, unsigned int vfid, u64 size) config->ggtt_region = node; return 0; err: - xe_ggtt_node_fini(node); + pf_release_ggtt(tile, node); return err; } diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index bbb9e411d21f..9d82ea30f4df 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -72,6 +72,8 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) struct xe_device *xe = gt_to_xe(gt); struct xe_gt_tlb_invalidation_fence *fence, *next; + LNL_FLUSH_WORK(>->uc.guc.ct.g2h_worker); + spin_lock_irq(>->tlb_invalidation.pending_lock); list_for_each_entry_safe(fence, next, >->tlb_invalidation.pending_fences, link) { diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 17986bfd8818..9c505d3517cd 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -897,17 +897,8 @@ retry_same_fence: ret = wait_event_timeout(ct->g2h_fence_wq, g2h_fence.done, HZ); - /* - * Occasionally it is seen that the G2H worker starts running after a delay of more than - * a second even after being queued and activated by the Linux workqueue subsystem. This - * leads to G2H timeout error. The root cause of issue lies with scheduling latency of - * Lunarlake Hybrid CPU. Issue dissappears if we disable Lunarlake atom cores from BIOS - * and this is beyond xe kmd. - * - * TODO: Drop this change once workqueue scheduling delay issue is fixed on LNL Hybrid CPU. - */ if (!ret) { - flush_work(&ct->g2h_worker); + LNL_FLUSH_WORK(&ct->g2h_worker); if (g2h_fence.done) { xe_gt_warn(gt, "G2H fence %u, action %04x, done\n", g2h_fence.seqno, action[0]); diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index f903b0772722..4f5d00aea716 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -745,8 +745,6 @@ static void guc_exec_queue_free_job(struct drm_sched_job *drm_job) { struct xe_sched_job *job = to_xe_sched_job(drm_job); - xe_exec_queue_update_run_ticks(job->q); - trace_xe_sched_job_free(job); xe_sched_job_put(job); } diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index 2804f14f8f29..78823f53d290 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -1206,9 +1206,11 @@ static int xe_oa_release(struct inode *inode, struct file *file) struct xe_oa_stream *stream = file->private_data; struct xe_gt *gt = stream->gt; + xe_pm_runtime_get(gt_to_xe(gt)); mutex_lock(>->oa.gt_lock); xe_oa_destroy_locked(stream); mutex_unlock(>->oa.gt_lock); + xe_pm_runtime_put(gt_to_xe(gt)); /* Release the reference the OA stream kept on the driver */ drm_dev_put(>_to_xe(gt)->drm); diff --git a/drivers/gpu/drm/xe/xe_wait_user_fence.c b/drivers/gpu/drm/xe/xe_wait_user_fence.c index f5deb81eba01..5b4264ea38bd 100644 --- a/drivers/gpu/drm/xe/xe_wait_user_fence.c +++ b/drivers/gpu/drm/xe/xe_wait_user_fence.c @@ -155,6 +155,13 @@ int xe_wait_user_fence_ioctl(struct drm_device *dev, void *data, } if (!timeout) { + LNL_FLUSH_WORKQUEUE(xe->ordered_wq); + err = do_compare(addr, args->value, args->mask, + args->op); + if (err <= 0) { + drm_dbg(&xe->drm, "LNL_FLUSH_WORKQUEUE resolved ufence timeout\n"); + break; + } err = -ETIME; break; } |