diff options
| author | Dave Airlie <airlied@redhat.com> | 2025-09-15 17:51:07 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2025-09-15 17:51:07 +1000 |
| commit | 0d9f0083f7a5a31d91d501467b499bb8c4b25bdf (patch) | |
| tree | 5670a6d87e7cb5c421809babf9dc9e72ff40f8ae /drivers/gpu | |
| parent | 2cda9a063dd6f21e5294092a679afdcd0fc58549 (diff) | |
| parent | f83ec76bf285bea5727f478a68b894f5543ca76e (diff) | |
Merge tag 'v6.17-rc6' into drm-next
This is a backmerge of Linux 6.17-rc6, needed for msm,
also requested by misc.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'drivers/gpu')
86 files changed, 772 insertions, 428 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index dfb6cfd83760..02138aa55793 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, - AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE | - AMDGPU_VM_PAGE_EXECUTABLE); + AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE | + AMDGPU_PTE_EXECUTABLE); if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 878b13efd154..8561ad7f6180 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -285,6 +285,36 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf, return ret; } +static int amdgpu_dma_buf_vmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + int ret; + + /* + * Pin to keep buffer in place while it's vmap'ed. The actual + * domain is not that important as long as it's mapable. Using + * GTT and VRAM should be compatible with most use cases. + */ + ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT | AMDGPU_GEM_DOMAIN_VRAM); + if (ret) + return ret; + ret = drm_gem_dmabuf_vmap(dma_buf, map); + if (ret) + amdgpu_bo_unpin(bo); + + return ret; +} + +static void amdgpu_dma_buf_vunmap(struct dma_buf *dma_buf, struct iosys_map *map) +{ + struct drm_gem_object *obj = dma_buf->priv; + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + + drm_gem_dmabuf_vunmap(dma_buf, map); + amdgpu_bo_unpin(bo); +} + const struct dma_buf_ops amdgpu_dmabuf_ops = { .attach = amdgpu_dma_buf_attach, .pin = amdgpu_dma_buf_pin, @@ -294,8 +324,8 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = { .release = drm_gem_dmabuf_release, .begin_cpu_access = amdgpu_dma_buf_begin_cpu_access, .mmap = drm_gem_dmabuf_mmap, - .vmap = drm_gem_dmabuf_vmap, - .vunmap = drm_gem_dmabuf_vunmap, + .vmap = amdgpu_dma_buf_vmap, + .vunmap = amdgpu_dma_buf_vunmap, }; /** @@ -526,7 +556,7 @@ bool amdgpu_dmabuf_is_xgmi_accessible(struct amdgpu_device *adev, return false; if (drm_gem_is_imported(obj)) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; if (dma_buf->ops != &amdgpu_dmabuf_ops) /* No XGMI with non AMD GPUs */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 630175746780..c049848a56b2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -317,7 +317,8 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj, */ if (!vm->is_compute_context || !vm->process_info) return 0; - if (!drm_gem_is_imported(obj) || !dma_buf_is_dynamic(obj->dma_buf)) + if (!drm_gem_is_imported(obj) || + !dma_buf_is_dynamic(obj->import_attach->dmabuf)) return 0; mutex_lock_nested(&vm->process_info->lock, 1); if (!WARN_ON(!vm->process_info->eviction_fence)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6379bb25bf5c..486c3646710c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -421,8 +421,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - ring->adev->rings[ring->idx] = NULL; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index cc74a9827ac9..dbda3a38a2b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1285,7 +1285,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *obj = &bo->tbo.base; if (drm_gem_is_imported(obj) && bo_va->is_xgmi) { - struct dma_buf *dma_buf = obj->dma_buf; + struct dma_buf *dma_buf = obj->import_attach->dmabuf; struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index a887df520414..4258d3e0b706 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -29,6 +29,8 @@ #include "amdgpu.h" #include "isp_v4_1_1.h" +MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin"); + #define ISP_PERFORMANCE_STATE_LOW 0 #define ISP_PERFORMANCE_STATE_HIGH 1 diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 95173156f956..f3085137ba08 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1886,15 +1886,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index d0d27790b73b..bc9dfe5ffea7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1804,15 +1804,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1903,22 +1907,16 @@ out: #define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1933,33 +1931,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index aa808675fead..954a2786fbe2 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1157,12 +1157,12 @@ struct dc_debug_options { bool enable_hblank_borrow; bool force_subvp_df_throttle; uint32_t acpi_transition_bitmasks[MAX_PIPES]; + bool enable_pg_cntl_debug_logs; unsigned int auxless_alpm_lfps_setup_ns; unsigned int auxless_alpm_lfps_period_ns; unsigned int auxless_alpm_lfps_silence_ns; unsigned int auxless_alpm_lfps_t1t2_us; short auxless_alpm_lfps_t1t2_offset_us; - bool enable_pg_cntl_debug_logs; }; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 7d24fa1517bf..cc377fcda6ff 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } - fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); + udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); params.vertical_total_min = stream->adjust.v_total_min; params.vertical_total_max = stream->adjust.v_total_max; diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h index 02a4a20e3560..e65747f7f12f 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -4258,18 +4258,6 @@ struct dmub_rb_cmd_replay_enable_data { * This does not support HDMI/DP2 for now. */ uint8_t phy_rate; - /** - * @hpo_stream_enc_inst: HPO stream encoder instance - */ - uint8_t hpo_stream_enc_inst; - /** - * @hpo_link_enc_inst: HPO link encoder instance - */ - uint8_t hpo_link_enc_inst; - /** - * @pad: Align structure to 4 byte boundary. - */ - uint8_t pad[2]; }; /** diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index ed35e567d117..efe534977d12 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1474,8 +1474,8 @@ analogix_dp_probe(struct device *dev, struct analogix_dp_plat_data *plat_data) dp = devm_drm_bridge_alloc(dev, struct analogix_dp_device, bridge, &analogix_dp_bridge_funcs); - if (!dp) - return ERR_PTR(-ENOMEM); + if (IS_ERR(dp)) + return ERR_CAST(dp); dp->dev = &pdev->dev; dp->dpms_mode = DRM_MODE_DPMS_OFF; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 464390372b34..ae0d08e5e960 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -393,6 +393,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev) gpiod_set_value_cansleep(pdata->enable_gpio, 1); /* + * After EN is deasserted and an external clock is detected, the bridge + * will sample GPIO3:1 to determine its frequency. The driver will + * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is + * racy. Thus we have to wait a couple of us. According to the datasheet + * the GPIO lines has to be stable at least 5 us (td5) but it seems that + * is not enough and the refclk frequency value is still lost or + * overwritten by the bridge itself. Waiting for 20us seems to work. + */ + usleep_range(20, 30); + + /* * If we have a reference clock we can enable communication w/ the * panel (including the aux channel) w/out any need for an input clock * so we can do it in resume which lets us read the EDID before diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c index 78a1a4f09509..a52e95555549 100644 --- a/drivers/gpu/drm/drm_gpuvm.c +++ b/drivers/gpu/drm/drm_gpuvm.c @@ -40,7 +40,7 @@ * mapping's backing &drm_gem_object buffers. * * &drm_gem_object buffers maintain a list of &drm_gpuva objects representing - * all existent GPU VA mappings using this &drm_gem_object as backing buffer. + * all existing GPU VA mappings using this &drm_gem_object as backing buffer. * * GPU VAs can be flagged as sparse, such that drivers may use GPU VAs to also * keep track of sparse PTEs in order to support Vulkan 'Sparse Resources'. @@ -72,7 +72,7 @@ * but it can also be a 'dummy' object, which can be allocated with * drm_gpuvm_resv_object_alloc(). * - * In order to connect a struct drm_gpuva its backing &drm_gem_object each + * In order to connect a struct drm_gpuva to its backing &drm_gem_object each * &drm_gem_object maintains a list of &drm_gpuvm_bo structures, and each * &drm_gpuvm_bo contains a list of &drm_gpuva structures. * @@ -81,7 +81,7 @@ * This is ensured by the API through drm_gpuvm_bo_obtain() and * drm_gpuvm_bo_obtain_prealloc() which first look into the corresponding * &drm_gem_object list of &drm_gpuvm_bos for an existing instance of this - * particular combination. If not existent a new instance is created and linked + * particular combination. If not present, a new instance is created and linked * to the &drm_gem_object. * * &drm_gpuvm_bo structures, since unique for a given &drm_gpuvm, are also used @@ -108,7 +108,7 @@ * sequence of operations to satisfy a given map or unmap request. * * Therefore the DRM GPU VA manager provides an algorithm implementing splitting - * and merging of existent GPU VA mappings with the ones that are requested to + * and merging of existing GPU VA mappings with the ones that are requested to * be mapped or unmapped. This feature is required by the Vulkan API to * implement Vulkan 'Sparse Memory Bindings' - drivers UAPIs often refer to this * as VM BIND. @@ -119,7 +119,7 @@ * execute in order to integrate the new mapping cleanly into the current state * of the GPU VA space. * - * Depending on how the new GPU VA mapping intersects with the existent mappings + * Depending on how the new GPU VA mapping intersects with the existing mappings * of the GPU VA space the &drm_gpuvm_ops callbacks contain an arbitrary amount * of unmap operations, a maximum of two remap operations and a single map * operation. The caller might receive no callback at all if no operation is @@ -139,16 +139,16 @@ * one unmap operation and one or two map operations, such that drivers can * derive the page table update delta accordingly. * - * Note that there can't be more than two existent mappings to split up, one at + * Note that there can't be more than two existing mappings to split up, one at * the beginning and one at the end of the new mapping, hence there is a * maximum of two remap operations. * * Analogous to drm_gpuvm_sm_map() drm_gpuvm_sm_unmap() uses &drm_gpuvm_ops to * call back into the driver in order to unmap a range of GPU VA space. The - * logic behind this function is way simpler though: For all existent mappings + * logic behind this function is way simpler though: For all existing mappings * enclosed by the given range unmap operations are created. For mappings which - * are only partically located within the given range, remap operations are - * created such that those mappings are split up and re-mapped partically. + * are only partially located within the given range, remap operations are + * created such that those mappings are split up and re-mapped partially. * * As an alternative to drm_gpuvm_sm_map() and drm_gpuvm_sm_unmap(), * drm_gpuvm_sm_map_ops_create() and drm_gpuvm_sm_unmap_ops_create() can be used @@ -168,7 +168,7 @@ * provided helper functions drm_gpuva_map(), drm_gpuva_remap() and * drm_gpuva_unmap() instead. * - * The following diagram depicts the basic relationships of existent GPU VA + * The following diagram depicts the basic relationships of existing GPU VA * mappings, a newly requested mapping and the resulting mappings as implemented * by drm_gpuvm_sm_map() - it doesn't cover any arbitrary combinations of these. * @@ -218,7 +218,7 @@ * * * 4) Existent mapping is a left aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -236,9 +236,9 @@ * and/or non-contiguous BO offset. * * - * 5) Requested mapping's range is a left aligned subset of the existent one, + * 5) Requested mapping's range is a left aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one adjusting its BO offset. + * the existing one adjusting its BO offset. * * :: * @@ -271,9 +271,9 @@ * new: |-----|-----| (a.bo_offset=n, a'.bo_offset=n+1) * * - * 7) Requested mapping's range is a right aligned subset of the existent one, + * 7) Requested mapping's range is a right aligned subset of the existing one, * but backed by a different BO. Hence, map the requested mapping and split - * the existent one, without adjusting the BO offset. + * the existing one, without adjusting the BO offset. * * :: * @@ -304,7 +304,7 @@ * * 9) Existent mapping is overlapped at the end by the requested mapping backed * by a different BO. Hence, map the requested mapping and split up the - * existent one, without adjusting the BO offset. + * existing one, without adjusting the BO offset. * * :: * @@ -334,9 +334,9 @@ * new: |-----|-----------| (a'.bo_offset=n, a.bo_offset=n+1) * * - * 11) Requested mapping's range is a centered subset of the existent one + * 11) Requested mapping's range is a centered subset of the existing one * having a different backing BO. Hence, map the requested mapping and split - * up the existent one in two mappings, adjusting the BO offset of the right + * up the existing one in two mappings, adjusting the BO offset of the right * one accordingly. * * :: @@ -351,7 +351,7 @@ * new: |-----|-----|-----| (a.bo_offset=n,b.bo_offset=m,a'.bo_offset=n+2) * * - * 12) Requested mapping is a contiguous subset of the existent one. Split it + * 12) Requested mapping is a contiguous subset of the existing one. Split it * up, but indicate that the backing PTEs could be kept. * * :: @@ -367,7 +367,7 @@ * * * 13) Existent mapping is a right aligned subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -386,7 +386,7 @@ * * * 14) Existent mapping is a centered subset of the requested one, hence - * replace the existent one. + * replace the existing one. * * :: * @@ -406,7 +406,7 @@ * * 15) Existent mappings is overlapped at the beginning by the requested mapping * backed by a different BO. Hence, map the requested mapping and split up - * the existent one, adjusting its BO offset accordingly. + * the existing one, adjusting its BO offset accordingly. * * :: * @@ -533,8 +533,8 @@ * make use of them. * * The below code is strictly limited to illustrate the generic usage pattern. - * To maintain simplicitly, it doesn't make use of any abstractions for common - * code, different (asyncronous) stages with fence signalling critical paths, + * To maintain simplicity, it doesn't make use of any abstractions for common + * code, different (asynchronous) stages with fence signalling critical paths, * any other helpers or error handling in terms of freeing memory and dropping * previously taken locks. * @@ -543,7 +543,7 @@ * // Allocates a new &drm_gpuva. * struct drm_gpuva * driver_gpuva_alloc(void); * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -651,7 +651,7 @@ * .sm_step_unmap = driver_gpuva_unmap, * }; * - * // Typically drivers would embedd the &drm_gpuvm and &drm_gpuva + * // Typically drivers would embed the &drm_gpuvm and &drm_gpuva * // structure in individual driver structures and lock the dma-resv with * // drm_exec or similar helpers. * int driver_mapping_create(struct drm_gpuvm *gpuvm, @@ -749,7 +749,7 @@ * * This helper is here to provide lockless list iteration. Lockless as in, the * iterator releases the lock immediately after picking the first element from - * the list, so list insertion deletion can happen concurrently. + * the list, so list insertion and deletion can happen concurrently. * * Elements popped from the original list are kept in a local list, so removal * and is_empty checks can still happen while we're iterating the list. @@ -1229,7 +1229,7 @@ drm_gpuvm_prepare_objects_locked(struct drm_gpuvm *gpuvm, } /** - * drm_gpuvm_prepare_objects() - prepare all assoiciated BOs + * drm_gpuvm_prepare_objects() - prepare all associated BOs * @gpuvm: the &drm_gpuvm * @exec: the &drm_exec locking context * @num_fences: the amount of &dma_fences to reserve @@ -1299,13 +1299,13 @@ drm_gpuvm_prepare_range(struct drm_gpuvm *gpuvm, struct drm_exec *exec, EXPORT_SYMBOL_GPL(drm_gpuvm_prepare_range); /** - * drm_gpuvm_exec_lock() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * * Acquires all dma-resv locks of all &drm_gem_objects the given * &drm_gpuvm contains mappings of. * - * Addionally, when calling this function with struct drm_gpuvm_exec::extra + * Additionally, when calling this function with struct drm_gpuvm_exec::extra * being set the driver receives the given @fn callback to lock additional * dma-resv in the context of the &drm_gpuvm_exec instance. Typically, drivers * would call drm_exec_prepare_obj() from within this callback. @@ -1362,7 +1362,7 @@ fn_lock_array(struct drm_gpuvm_exec *vm_exec) } /** - * drm_gpuvm_exec_lock_array() - lock all dma-resv of all assoiciated BOs + * drm_gpuvm_exec_lock_array() - lock all dma-resv of all associated BOs * @vm_exec: the &drm_gpuvm_exec wrapper * @objs: additional &drm_gem_objects to lock * @num_objs: the number of additional &drm_gem_objects to lock @@ -1658,7 +1658,7 @@ drm_gpuvm_bo_find(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_find); /** - * drm_gpuvm_bo_obtain() - obtains and instance of the &drm_gpuvm_bo for the + * drm_gpuvm_bo_obtain() - obtains an instance of the &drm_gpuvm_bo for the * given &drm_gpuvm and &drm_gem_object * @gpuvm: The &drm_gpuvm the @obj is mapped in. * @obj: The &drm_gem_object being mapped in the @gpuvm. @@ -1694,7 +1694,7 @@ drm_gpuvm_bo_obtain(struct drm_gpuvm *gpuvm, EXPORT_SYMBOL_GPL(drm_gpuvm_bo_obtain); /** - * drm_gpuvm_bo_obtain_prealloc() - obtains and instance of the &drm_gpuvm_bo + * drm_gpuvm_bo_obtain_prealloc() - obtains an instance of the &drm_gpuvm_bo * for the given &drm_gpuvm and &drm_gem_object * @__vm_bo: A pre-allocated struct drm_gpuvm_bo. * @@ -1758,7 +1758,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_bo_extobj_add); * @vm_bo: the &drm_gpuvm_bo to add or remove * @evict: indicates whether the object is evicted * - * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvms evicted list. + * Adds a &drm_gpuvm_bo to or removes it from the &drm_gpuvm's evicted list. */ void drm_gpuvm_bo_evict(struct drm_gpuvm_bo *vm_bo, bool evict) @@ -1860,7 +1860,7 @@ __drm_gpuva_remove(struct drm_gpuva *va) * drm_gpuva_remove() - remove a &drm_gpuva * @va: the &drm_gpuva to remove * - * This removes the given &va from the underlaying tree. + * This removes the given &va from the underlying tree. * * It is safe to use this function using the safe versions of iterating the GPU * VA space, such as drm_gpuvm_for_each_va_safe() and @@ -2462,7 +2462,7 @@ EXPORT_SYMBOL_GPL(drm_gpuvm_sm_map); * * This function iterates the given range of the GPU VA space. It utilizes the * &drm_gpuvm_ops to call back into the driver providing the operations to - * unmap and, if required, split existent mappings. + * unmap and, if required, split existing mappings. * * Drivers may use these callbacks to update the GPU VA space right away within * the callback. In case the driver decides to copy and store the operations for @@ -2531,7 +2531,9 @@ static const struct drm_gpuvm_ops lock_ops = { * remapped, and locks+prepares (drm_exec_prepare_object()) objects that * will be newly mapped. * - * The expected usage is: + * The expected usage is:: + * + * .. code-block:: c * * vm_bind { * struct drm_exec exec; @@ -2572,7 +2574,7 @@ static const struct drm_gpuvm_ops lock_ops = { * required without the earlier DRIVER_OP_MAP. This is safe because we've * already locked the GEM object in the earlier DRIVER_OP_MAP step. * - * Returns: 0 on success or a negative error codec + * Returns: 0 on success or a negative error code */ int drm_gpuvm_sm_map_exec_lock(struct drm_gpuvm *gpuvm, @@ -2744,12 +2746,12 @@ err_free_ops: * @req: map request arguments * * This function creates a list of operations to perform splitting and merging - * of existent mapping(s) with the newly requested one. + * of existing mapping(s) with the newly requested one. * * The list can be iterated with &drm_gpuva_for_each_op and must be processed * in the given order. It can contain map, unmap and remap operations, but it * also can be empty if no operation is required, e.g. if the requested mapping - * already exists is the exact same way. + * already exists in the exact same way. * * There can be an arbitrary amount of unmap operations, a maximum of two remap * operations and a single map operation. The latter one represents the original diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 09a9b452e8b7..50c286c5cee8 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -381,6 +381,26 @@ struct DecFifo { len: usize, } +// On arm32 architecture, dividing an `u64` by a constant will generate a call +// to `__aeabi_uldivmod` which is not present in the kernel. +// So use the multiply by inverse method for this architecture. +fn div10(val: u64) -> u64 { + if cfg!(target_arch = "arm") { + let val_h = val >> 32; + let val_l = val & 0xFFFFFFFF; + let b_h: u64 = 0x66666666; + let b_l: u64 = 0x66666667; + + let tmp1 = val_h * b_l + ((val_l * b_l) >> 32); + let tmp2 = val_l * b_h + (tmp1 & 0xffffffff); + let tmp3 = val_h * b_h + (tmp1 >> 32) + (tmp2 >> 32); + + tmp3 >> 2 + } else { + val / 10 + } +} + impl DecFifo { fn push(&mut self, data: u64, len: usize) { let mut chunk = data; @@ -389,7 +409,7 @@ impl DecFifo { } for i in 0..len { self.decimals[i] = (chunk % 10) as u8; - chunk /= 10; + chunk = div10(chunk); } self.len += len; } diff --git a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c index 74f7832ea53e..0726cb5b736e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c +++ b/drivers/gpu/drm/hisilicon/hibmc/dp/dp_link.c @@ -325,6 +325,17 @@ static int hibmc_dp_link_downgrade_training_eq(struct hibmc_dp_dev *dp) return hibmc_dp_link_reduce_rate(dp); } +static void hibmc_dp_update_caps(struct hibmc_dp_dev *dp) +{ + dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; + if (dp->link.cap.link_rate > DP_LINK_BW_8_1 || !dp->link.cap.link_rate) + dp->link.cap.link_rate = DP_LINK_BW_8_1; + + dp->link.cap.lanes = dp->dpcd[DP_MAX_LANE_COUNT] & DP_MAX_LANE_COUNT_MASK; + if (dp->link.cap.lanes > HIBMC_DP_LANE_NUM_MAX) + dp->link.cap.lanes = HIBMC_DP_LANE_NUM_MAX; +} + int hibmc_dp_link_training(struct hibmc_dp_dev *dp) { struct hibmc_dp_link *link = &dp->link; @@ -334,8 +345,7 @@ int hibmc_dp_link_training(struct hibmc_dp_dev *dp) if (ret) drm_err(dp->dev, "dp aux read dpcd failed, ret: %d\n", ret); - dp->link.cap.link_rate = dp->dpcd[DP_MAX_LINK_RATE]; - dp->link.cap.lanes = 0x2; + hibmc_dp_update_caps(dp); ret = hibmc_dp_get_serdes_rate_cfg(dp); if (ret < 0) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index 768b97f9e74a..289304500ab0 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -32,7 +32,7 @@ DEFINE_DRM_GEM_FOPS(hibmc_fops); -static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "vblank", "hpd" }; +static const char *g_irqs_names_map[HIBMC_MAX_VECTORS] = { "hibmc-vblank", "hibmc-hpd" }; static irqreturn_t hibmc_interrupt(int irq, void *arg) { @@ -115,6 +115,8 @@ static const struct drm_mode_config_funcs hibmc_mode_funcs = { static int hibmc_kms_init(struct hibmc_drm_private *priv) { struct drm_device *dev = &priv->dev; + struct drm_encoder *encoder; + u32 clone_mask = 0; int ret; ret = drmm_mode_config_init(dev); @@ -154,6 +156,12 @@ static int hibmc_kms_init(struct hibmc_drm_private *priv) return ret; } + drm_for_each_encoder(encoder, dev) + clone_mask |= drm_encoder_mask(encoder); + + drm_for_each_encoder(encoder, dev) + encoder->possible_clones = clone_mask; + return 0; } @@ -277,7 +285,6 @@ static void hibmc_unload(struct drm_device *dev) static int hibmc_msi_init(struct drm_device *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); - char name[32] = {0}; int valid_irq_num; int irq; int ret; @@ -292,9 +299,6 @@ static int hibmc_msi_init(struct drm_device *dev) valid_irq_num = ret; for (int i = 0; i < valid_irq_num; i++) { - snprintf(name, ARRAY_SIZE(name) - 1, "%s-%s-%s", - dev->driver->name, pci_name(pdev), g_irqs_names_map[i]); - irq = pci_irq_vector(pdev, i); if (i) @@ -302,10 +306,10 @@ static int hibmc_msi_init(struct drm_device *dev) ret = devm_request_threaded_irq(&pdev->dev, irq, hibmc_dp_interrupt, hibmc_dp_hpd_isr, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); else ret = devm_request_irq(&pdev->dev, irq, hibmc_interrupt, - IRQF_SHARED, name, dev); + IRQF_SHARED, g_irqs_names_map[i], dev); if (ret) { drm_err(dev, "install irq failed: %d\n", ret); return ret; @@ -323,13 +327,13 @@ static int hibmc_load(struct drm_device *dev) ret = hibmc_hw_init(priv); if (ret) - goto err; + return ret; ret = drmm_vram_helper_init(dev, pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); if (ret) { drm_err(dev, "Error initializing VRAM MM; %d\n", ret); - goto err; + return ret; } ret = hibmc_kms_init(priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h index 274feabe7df0..ca8502e2760c 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.h @@ -69,6 +69,7 @@ int hibmc_de_init(struct hibmc_drm_private *priv); int hibmc_vdac_init(struct hibmc_drm_private *priv); int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *connector); +void hibmc_ddc_del(struct hibmc_vdac *vdac); int hibmc_dp_init(struct hibmc_drm_private *priv); diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c index 99b3b77b5445..44860011855e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_i2c.c @@ -95,3 +95,8 @@ int hibmc_ddc_create(struct drm_device *drm_dev, struct hibmc_vdac *vdac) return i2c_bit_add_bus(&vdac->adapter); } + +void hibmc_ddc_del(struct hibmc_vdac *vdac) +{ + i2c_del_adapter(&vdac->adapter); +} diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c index e8a527ede854..841e81f47b68 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c @@ -53,7 +53,7 @@ static void hibmc_connector_destroy(struct drm_connector *connector) { struct hibmc_vdac *vdac = to_hibmc_vdac(connector); - i2c_del_adapter(&vdac->adapter); + hibmc_ddc_del(vdac); drm_connector_cleanup(connector); } @@ -110,7 +110,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) ret = drmm_encoder_init(dev, encoder, NULL, DRM_MODE_ENCODER_DAC, NULL); if (ret) { drm_err(dev, "failed to init encoder: %d\n", ret); - return ret; + goto err; } drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs); @@ -121,7 +121,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) &vdac->adapter); if (ret) { drm_err(dev, "failed to init connector: %d\n", ret); - return ret; + goto err; } drm_connector_helper_add(connector, &hibmc_connector_helper_funcs); @@ -131,4 +131,9 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv) connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; return 0; + +err: + hibmc_ddc_del(vdac); + + return ret; } diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 7f9a2d743bac..da4babfd6bcb 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1174,7 +1174,7 @@ static void icl_mbus_init(struct intel_display *display) if (DISPLAY_VER(display) == 12) abox_regs |= BIT(0); - for_each_set_bit(i, &abox_regs, sizeof(abox_regs)) + for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs)) intel_de_rmw(display, MBUS_ABOX_CTL(i), mask, val); } @@ -1639,11 +1639,11 @@ static void tgl_bw_buddy_init(struct intel_display *display) if (table[config].page_mask == 0) { drm_dbg_kms(display->drm, "Unknown memory configuration; disabling address buddy logic.\n"); - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) intel_de_write(display, BW_BUDDY_CTL(i), BW_BUDDY_DISABLE); } else { - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) { + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) { intel_de_write(display, BW_BUDDY_PAGE_MASK(i), table[config].page_mask); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index d5e6bab36414..eb5537f0ac90 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -394,10 +394,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) continue; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); + put_device(&pdev->dev); if (!drm_dev) continue; temp_drm_priv = dev_get_drvdata(drm_dev); + put_device(drm_dev); if (!temp_drm_priv) continue; diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index d7726091819c..0e2bcd5f67b7 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -1002,6 +1002,12 @@ static int mtk_dsi_host_attach(struct mipi_dsi_host *host, return PTR_ERR(dsi->next_bridge); } + /* + * set flag to request the DSI host bridge be pre-enabled before device bridge + * in the chain, so the DSI host is ready when the device bridge is pre-enabled + */ + dsi->next_bridge->pre_enable_prev_first = true; + drm_bridge_add(&dsi->bridge); ret = component_add(host->dev, &mtk_dsi_component_ops); diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 845fd8aa43c3..b766dd5e6c8d 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -182,8 +182,8 @@ static inline struct mtk_hdmi *hdmi_ctx_from_bridge(struct drm_bridge *b) static void mtk_hdmi_hw_vid_black(struct mtk_hdmi *hdmi, bool black) { - regmap_update_bits(hdmi->regs, VIDEO_SOURCE_SEL, - VIDEO_CFG_4, black ? GEN_RGB : NORMAL_PATH); + regmap_update_bits(hdmi->regs, VIDEO_CFG_4, + VIDEO_SOURCE_SEL, black ? GEN_RGB : NORMAL_PATH); } static void mtk_hdmi_hw_make_reg_writable(struct mtk_hdmi *hdmi, bool enable) @@ -310,8 +310,8 @@ static void mtk_hdmi_hw_send_info_frame(struct mtk_hdmi *hdmi, u8 *buffer, static void mtk_hdmi_hw_send_aud_packet(struct mtk_hdmi *hdmi, bool enable) { - regmap_update_bits(hdmi->regs, AUDIO_PACKET_OFF, - GRL_SHIFT_R2, enable ? 0 : AUDIO_PACKET_OFF); + regmap_update_bits(hdmi->regs, GRL_SHIFT_R2, + AUDIO_PACKET_OFF, enable ? 0 : AUDIO_PACKET_OFF); } static void mtk_hdmi_hw_config_sys(struct mtk_hdmi *hdmi) diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index cbc4f37da8ba..02349bd44001 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -292,7 +292,8 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane, wmb(); /* Make sure the above parameter is set before update */ mtk_plane_state->pending.dirty = true; - mtk_crtc_plane_disable(old_state->crtc, plane); + if (old_state && old_state->crtc) + mtk_crtc_plane_disable(old_state->crtc, plane); } static void mtk_plane_atomic_update(struct drm_plane *plane, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index faca2a0243ab..d5d1271fce61 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -11,7 +11,7 @@ static const unsigned int *gen7_0_0_external_core_regs[] __always_unused; static const unsigned int *gen7_2_0_external_core_regs[] __always_unused; static const unsigned int *gen7_9_0_external_core_regs[] __always_unused; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused; static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused; #include "adreno_gen7_0_0_snapshot.h" @@ -174,8 +174,15 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | - A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A7XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } else { + reg = A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_INDEX(offset) | + A6XX_DBGC_CFG_DBGBUS_SEL_D_PING_BLK_SEL(block); + } gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_A, reg); gpu_write(gpu, REG_A6XX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -198,11 +205,18 @@ static int debugbus_read(struct msm_gpu *gpu, u32 block, u32 offset, readl((ptr) + ((offset) << 2)) /* read a value from the CX debug bus */ -static int cx_debugbus_read(void __iomem *cxdbg, u32 block, u32 offset, +static int cx_debugbus_read(struct msm_gpu *gpu, void __iomem *cxdbg, u32 block, u32 offset, u32 *data) { - u32 reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | - A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + u32 reg; + + if (to_adreno_gpu(gpu)->info->family >= ADRENO_7XX_GEN1) { + reg = A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A7XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } else { + reg = A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_INDEX(offset) | + A6XX_CX_DBGC_CFG_DBGBUS_SEL_A_PING_BLK_SEL(block); + } cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_A, reg); cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_SEL_B, reg); @@ -315,7 +329,8 @@ static void a6xx_get_debugbus_block(struct msm_gpu *gpu, ptr += debugbus_read(gpu, block->id, i, ptr); } -static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, +static void a6xx_get_cx_debugbus_block(struct msm_gpu *gpu, + void __iomem *cxdbg, struct a6xx_gpu_state *a6xx_state, const struct a6xx_debugbus_block *block, struct a6xx_gpu_state_obj *obj) @@ -330,7 +345,7 @@ static void a6xx_get_cx_debugbus_block(void __iomem *cxdbg, obj->handle = block; for (ptr = obj->data, i = 0; i < block->count; i++) - ptr += cx_debugbus_read(cxdbg, block->id, i, ptr); + ptr += cx_debugbus_read(gpu, cxdbg, block->id, i, ptr); } static void a6xx_get_debugbus_blocks(struct msm_gpu *gpu, @@ -423,8 +438,9 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu, a6xx_state, &a7xx_debugbus_blocks[gbif_debugbus_blocks[i]], &a6xx_state->debugbus[i + debugbus_blocks_count]); } - } + a6xx_state->nr_debugbus = total_debugbus_blocks; + } } static void a6xx_get_debugbus(struct msm_gpu *gpu, @@ -526,7 +542,8 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu, int i; for (i = 0; i < nr_cx_debugbus_blocks; i++) - a6xx_get_cx_debugbus_block(cxdbg, + a6xx_get_cx_debugbus_block(gpu, + cxdbg, a6xx_state, &cx_debugbus_blocks[i], &a6xx_state->cx_debugbus[i]); @@ -759,15 +776,15 @@ static void a7xx_get_cluster(struct msm_gpu *gpu, size_t datasize; int i, regcount = 0; - /* Some clusters need a selector register to be programmed too */ - if (cluster->sel) - in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); - in += CRASHDUMP_WRITE(in, REG_A7XX_CP_APERTURE_CNTL_CD, A7XX_CP_APERTURE_CNTL_CD_PIPE(cluster->pipe_id) | A7XX_CP_APERTURE_CNTL_CD_CLUSTER(cluster->cluster_id) | A7XX_CP_APERTURE_CNTL_CD_CONTEXT(cluster->context_id)); + /* Some clusters need a selector register to be programmed too */ + if (cluster->sel) + in += CRASHDUMP_WRITE(in, cluster->sel->cd_reg, cluster->sel->val); + for (i = 0; cluster->regs[i] != UINT_MAX; i += 2) { int count = RANGE(cluster->regs, i); @@ -1796,6 +1813,7 @@ static void a7xx_show_shader(struct a6xx_gpu_state_obj *obj, print_name(p, " - type: ", a7xx_statetype_names[block->statetype]); print_name(p, " - pipe: ", a7xx_pipe_names[block->pipeid]); + drm_printf(p, " - location: %d\n", block->location); for (i = 0; i < block->num_sps; i++) { drm_printf(p, " - sp: %d\n", i); @@ -1873,6 +1891,7 @@ static void a7xx_show_dbgahb_cluster(struct a6xx_gpu_state_obj *obj, print_name(p, " - pipe: ", a7xx_pipe_names[dbgahb->pipe_id]); print_name(p, " - cluster-name: ", a7xx_cluster_names[dbgahb->cluster_id]); drm_printf(p, " - context: %d\n", dbgahb->context_id); + drm_printf(p, " - location: %d\n", dbgahb->location_id); a7xx_show_registers_indented(dbgahb->regs, obj->data, p, 4); } } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 95d93ac6812a..1c18499b60bb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -419,47 +419,47 @@ static const struct a6xx_indexed_registers a6xx_indexed_reglist[] = { REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a6xx_get_cp_roq_size}, }; static const struct a6xx_indexed_registers a7xx_indexed_reglist[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, - REG_A6XX_CP_SQE_STAT_DATA, 0x33, NULL }, + REG_A6XX_CP_SQE_STAT_DATA, 0x40, NULL }, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, - REG_A7XX_CP_BV_SQE_STAT_DATA, 0x33, NULL }, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, + REG_A7XX_CP_BV_SQE_STAT_DATA, 0x40, NULL }, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, - REG_A7XX_CP_SQE_AC_STAT_DATA, 0x33, NULL }, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, + REG_A7XX_CP_SQE_AC_STAT_DATA, 0x40, NULL }, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x100, NULL }, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x8000, NULL }, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x40, NULL }, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0, a7xx_get_cp_roq_size }, }; static const struct a6xx_indexed_registers a6xx_cp_mempool_indexed = { - "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2060, NULL, }; static const struct a6xx_indexed_registers a7xx_cp_bv_mempool_indexed[] = { - { "CP_MEMPOOL", REG_A6XX_CP_MEM_POOL_DBG_ADDR, - REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2100, NULL }, - { "CP_BV_MEMPOOL", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, - REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2100, NULL }, + { "CP_MEM_POOL_DBG", REG_A6XX_CP_MEM_POOL_DBG_ADDR, + REG_A6XX_CP_MEM_POOL_DBG_DATA, 0x2200, NULL }, + { "CP_BV_MEM_POOL_DBG", REG_A7XX_CP_BV_MEM_POOL_DBG_ADDR, + REG_A7XX_CP_BV_MEM_POOL_DBG_DATA, 0x2200, NULL }, }; #define DEBUGBUS(_id, _count) { .id = _id, .name = #_id, .count = _count } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h index cb66ece6606b..04b49d385f9d 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h @@ -81,7 +81,7 @@ static const u32 gen7_0_0_debugbus_blocks[] = { A7XX_DBGBUS_USPTP_7, }; -static struct gen7_shader_block gen7_0_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_0_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -668,12 +668,19 @@ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ -static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { 0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, 0x0b630, 0x0b633, UINT_MAX, UINT_MAX, }; +static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); + +/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ +static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { + 0x0b600, 0x0b600, + UINT_MAX, UINT_MAX, +}; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8)); /* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */ @@ -695,7 +702,7 @@ static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_0_0_clusters[] = { +static const struct gen7_cluster_registers gen7_0_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -764,7 +771,7 @@ static struct gen7_cluster_registers gen7_0_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -914,7 +921,7 @@ static const u32 gen7_0_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_0_0_reg_list[] = { +static const struct gen7_reg_list gen7_0_0_reg_list[] = { { gen7_0_0_gpu_registers, NULL }, { gen7_0_0_cx_misc_registers, NULL }, { gen7_0_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h index 6f8ad50f32ce..772652eb61f3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h @@ -95,7 +95,7 @@ static const u32 gen7_2_0_debugbus_blocks[] = { A7XX_DBGBUS_CCHE_2, }; -static struct gen7_shader_block gen7_2_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_2_0_shader_blocks[] = { {A7XX_TP0_TMO_DATA, 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_SMO_DATA, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, @@ -489,7 +489,7 @@ static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_2_0_clusters[] = { +static const struct gen7_cluster_registers gen7_2_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -558,7 +558,7 @@ static struct gen7_cluster_registers gen7_2_0_clusters[] = { gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -573,6 +573,8 @@ static struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, @@ -737,7 +739,7 @@ static const u32 gen7_2_0_dpm_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_2_0_dpm_registers), 8)); -static struct gen7_reg_list gen7_2_0_reg_list[] = { +static const struct gen7_reg_list gen7_2_0_reg_list[] = { { gen7_2_0_gpu_registers, NULL }, { gen7_2_0_cx_misc_registers, NULL }, { gen7_2_0_dpm_registers, NULL }, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h index e02cabb39f19..0956dfca1f05 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h @@ -117,7 +117,7 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { A7XX_DBGBUS_GBIF_CX, }; -static struct gen7_shader_block gen7_9_0_shader_blocks[] = { +static const struct gen7_shader_block gen7_9_0_shader_blocks[] = { { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, @@ -1116,7 +1116,7 @@ static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { .val = 0x9, }; -static struct gen7_cluster_registers gen7_9_0_clusters[] = { +static const struct gen7_cluster_registers gen7_9_0_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, @@ -1185,7 +1185,7 @@ static struct gen7_cluster_registers gen7_9_0_clusters[] = { gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; -static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { +static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00}, { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, @@ -1294,34 +1294,34 @@ static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; -static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { +static const struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { { "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR, REG_A6XX_CP_SQE_STAT_DATA, 0x00040}, { "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR, REG_A6XX_CP_DRAW_STATE_DATA, 0x00200}, - { "CP_ROQ", REG_A6XX_CP_ROQ_DBG_ADDR, + { "CP_ROQ_DBG", REG_A6XX_CP_ROQ_DBG_ADDR, REG_A6XX_CP_ROQ_DBG_DATA, 0x00800}, - { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, + { "CP_SQE_UCODE_DBG", REG_A6XX_CP_SQE_UCODE_DBG_ADDR, REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR, + { "CP_BV_DRAW_STATE", REG_A7XX_CP_BV_DRAW_STATE_ADDR, REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200}, - { "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR, + { "CP_BV_ROQ_DBG", REG_A7XX_CP_BV_ROQ_DBG_ADDR, REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800}, - { "CP_BV_SQE_UCODE_DBG_ADDR", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, + { "CP_BV_SQE_UCODE_DBG", REG_A7XX_CP_BV_SQE_UCODE_DBG_ADDR, REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000}, - { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, + { "CP_BV_SQE_STAT", REG_A7XX_CP_BV_SQE_STAT_ADDR, REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040}, - { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, + { "CP_RESOURCE_TABLE_DBG", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100}, - { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, + { "CP_LPAC_DRAW_STATE", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200}, - { "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, + { "CP_LPAC_ROQ_DBG", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, REG_A7XX_CP_LPAC_ROQ_DBG_DATA, 0x00200}, - { "CP_SQE_AC_UCODE_DBG_ADDR", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, + { "CP_SQE_AC_UCODE_DBG", REG_A7XX_CP_SQE_AC_UCODE_DBG_ADDR, REG_A7XX_CP_SQE_AC_UCODE_DBG_DATA, 0x08000}, - { "CP_SQE_AC_STAT_ADDR", REG_A7XX_CP_SQE_AC_STAT_ADDR, + { "CP_SQE_AC_STAT", REG_A7XX_CP_SQE_AC_STAT_ADDR, REG_A7XX_CP_SQE_AC_STAT_DATA, 0x00040}, - { "CP_LPAC_FIFO_DBG_ADDR", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, + { "CP_LPAC_FIFO_DBG", REG_A7XX_CP_LPAC_FIFO_DBG_ADDR, REG_A7XX_CP_LPAC_FIFO_DBG_DATA, 0x00040}, { "CP_AQE_ROQ_0", REG_A7XX_CP_AQE_ROQ_DBG_ADDR_0, REG_A7XX_CP_AQE_ROQ_DBG_DATA_0, 0x00100}, @@ -1337,7 +1337,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { REG_A7XX_CP_AQE_STAT_DATA_1, 0x00040}, }; -static struct gen7_reg_list gen7_9_0_reg_list[] = { +static const struct gen7_reg_list gen7_9_0_reg_list[] = { { gen7_9_0_gpu_registers, NULL}, { gen7_9_0_cx_misc_registers, NULL}, { gen7_9_0_cx_dbgc_registers, NULL}, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index d4b545448d74..94912b4708fb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -596,7 +596,7 @@ static void _dpu_crtc_complete_flip(struct drm_crtc *crtc) spin_lock_irqsave(&dev->event_lock, flags); if (dpu_crtc->event) { - DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name, + DRM_DEBUG_VBL("%s: send event: %p\n", dpu_crtc->name, dpu_crtc->event); trace_dpu_crtc_complete_flip(DRMID(crtc)); drm_crtc_send_vblank_event(crtc, dpu_crtc->event); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 05e5f3463e30..258edaa18fc0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -730,6 +730,8 @@ bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_st return false; conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return false; /** * These checks are duplicated from dpu_encoder_update_topology() since diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c index 11fb1bc54fa9..54b20faa0b69 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dspp.c @@ -31,14 +31,14 @@ static void dpu_setup_dspp_pcc(struct dpu_hw_dspp *ctx, u32 base; if (!ctx) { - DRM_ERROR("invalid ctx %pK\n", ctx); + DRM_ERROR("invalid ctx %p\n", ctx); return; } base = ctx->cap->sblk->pcc.base; if (!base) { - DRM_ERROR("invalid ctx %pK pcc base 0x%x\n", ctx, base); + DRM_ERROR("invalid ctx %p pcc base 0x%x\n", ctx, base); return; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 12dcb32b4724..a306077647c3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1345,7 +1345,7 @@ static int dpu_kms_mmap_mdp5(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap_mdss(mdss_dev, dpu_kms->pdev, @@ -1380,7 +1380,7 @@ static int dpu_kms_mmap_dpu(struct dpu_kms *dpu_kms) dpu_kms->mmio = NULL; return ret; } - DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio); + DRM_DEBUG("mapped dpu address space @%p\n", dpu_kms->mmio); dpu_kms->vbif[VBIF_RT] = msm_ioremap(pdev, "vbif"); if (IS_ERR(dpu_kms->vbif[VBIF_RT])) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 01171c535a27..6859e8ef6b05 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -1129,7 +1129,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, struct drm_plane_state *old_plane_state = drm_atomic_get_old_plane_state(state, plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); - struct drm_crtc_state *crtc_state; + struct drm_crtc_state *crtc_state = NULL; int ret; if (IS_ERR(plane_state)) @@ -1162,7 +1162,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, if (!old_plane_state || !old_plane_state->fb || old_plane_state->src_w != plane_state->src_w || old_plane_state->src_h != plane_state->src_h || - old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_w != plane_state->crtc_w || old_plane_state->crtc_h != plane_state->crtc_h || msm_framebuffer_format(old_plane_state->fb) != msm_framebuffer_format(plane_state->fb)) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index 221f12db5f8b..4ea681130dba 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -5,6 +5,8 @@ #include <linux/clk-provider.h> #include <linux/platform_device.h> +#include <linux/pm_clock.h> +#include <linux/pm_runtime.h> #include <dt-bindings/phy/phy.h> #include "dsi_phy.h" @@ -511,30 +513,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) -{ - struct device *dev = &phy->pdev->dev; - int ret; - - ret = pm_runtime_resume_and_get(dev); - if (ret) - return ret; - - ret = clk_prepare_enable(phy->ahb_clk); - if (ret) { - DRM_DEV_ERROR(dev, "%s: can't enable ahb clk, %d\n", __func__, ret); - pm_runtime_put_sync(dev); - } - - return ret; -} - -static void dsi_phy_disable_resource(struct msm_dsi_phy *phy) -{ - clk_disable_unprepare(phy->ahb_clk); - pm_runtime_put(&phy->pdev->dev); -} - static const struct of_device_id dsi_phy_dt_match[] = { #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY { .compatible = "qcom,dsi-phy-28nm-hpm", @@ -698,22 +676,20 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) if (ret) return ret; - phy->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(phy->ahb_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), - "Unable to get ahb clk\n"); + platform_set_drvdata(pdev, phy); - ret = devm_pm_runtime_enable(&pdev->dev); + ret = devm_pm_runtime_enable(dev); if (ret) return ret; - /* PLL init will call into clk_register which requires - * register access, so we need to enable power and ahb clock. - */ - ret = dsi_phy_enable_resource(phy); + ret = devm_pm_clk_create(dev); if (ret) return ret; + ret = pm_clk_add(dev, "iface"); + if (ret < 0) + return dev_err_probe(dev, ret, "Unable to get iface clk\n"); + if (phy->cfg->ops.pll_init) { ret = phy->cfg->ops.pll_init(phy); if (ret) @@ -727,18 +703,19 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "Failed to register clk provider\n"); - dsi_phy_disable_resource(phy); - - platform_set_drvdata(pdev, phy); - return 0; } +static const struct dev_pm_ops dsi_phy_pm_ops = { + SET_RUNTIME_PM_OPS(pm_clk_suspend, pm_clk_resume, NULL) +}; + static struct platform_driver dsi_phy_platform_driver = { .probe = dsi_phy_driver_probe, .driver = { .name = "msm_dsi_phy", .of_match_table = dsi_phy_dt_match, + .pm = &dsi_phy_pm_ops, }, }; @@ -764,9 +741,9 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, dev = &phy->pdev->dev; - ret = dsi_phy_enable_resource(phy); + ret = pm_runtime_resume_and_get(dev); if (ret) { - DRM_DEV_ERROR(dev, "%s: resource enable failed, %d\n", + DRM_DEV_ERROR(dev, "%s: resume failed, %d\n", __func__, ret); goto res_en_fail; } @@ -810,7 +787,7 @@ pll_restor_fail: phy_en_fail: regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); reg_en_fail: - dsi_phy_disable_resource(phy); + pm_runtime_put(dev); res_en_fail: return ret; } @@ -823,7 +800,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) phy->cfg->ops.disable(phy); regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); - dsi_phy_disable_resource(phy); + pm_runtime_put(&phy->pdev->dev); } void msm_dsi_phy_set_usecase(struct msm_dsi_phy *phy, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index c558f8df1684..3cbf08231492 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -104,7 +104,6 @@ struct msm_dsi_phy { phys_addr_t lane_size; int id; - struct clk *ahb_clk; struct regulator_bulk_data *supplies; struct msm_dsi_dphy_timing timing; diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index bbda865addae..97dc70876442 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -325,25 +325,28 @@ static struct drm_info_list msm_debugfs_list[] = { static int late_init_minor(struct drm_minor *minor) { - struct drm_device *dev = minor->dev; - struct msm_drm_private *priv = dev->dev_private; + struct drm_device *dev; + struct msm_drm_private *priv; int ret; if (!minor) return 0; + dev = minor->dev; + priv = dev->dev_private; + if (!priv->gpu_pdev) return 0; ret = msm_rd_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install rd debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install rd debugfs\n"); return ret; } ret = msm_perf_debugfs_init(minor); if (ret) { - DRM_DEV_ERROR(minor->dev->dev, "could not install perf debugfs\n"); + DRM_DEV_ERROR(dev->dev, "could not install perf debugfs\n"); return ret; } diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 7ff994d4f91a..e7631f4ef530 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -95,7 +95,6 @@ void msm_gem_vma_get(struct drm_gem_object *obj) void msm_gem_vma_put(struct drm_gem_object *obj) { struct msm_drm_private *priv = obj->dev->dev_private; - struct drm_exec exec; if (atomic_dec_return(&to_msm_bo(obj)->vma_ref)) return; @@ -103,9 +102,13 @@ void msm_gem_vma_put(struct drm_gem_object *obj) if (!priv->kms) return; +#ifdef CONFIG_DRM_MSM_KMS + struct drm_exec exec; + msm_gem_lock_vm_and_obj(&exec, obj, priv->kms->vm); put_iova_spaces(obj, priv->kms->vm, true, "vma_put"); drm_exec_fini(&exec); /* drop locks */ +#endif } /* @@ -663,9 +666,13 @@ int msm_gem_set_iova(struct drm_gem_object *obj, static bool is_kms_vm(struct drm_gpuvm *vm) { +#ifdef CONFIG_DRM_MSM_KMS struct msm_drm_private *priv = vm->drm->dev_private; return priv->kms && (priv->kms->vm == vm); +#else + return false; +#endif } /* @@ -1113,10 +1120,12 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (msm_obj->flags & MSM_BO_NO_SHARE) { + if (obj->resv != &obj->_resv) { struct drm_gem_object *r_obj = container_of(obj->resv, struct drm_gem_object, _resv); + WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE)); + /* Drop reference we hold to shared resv obj: */ drm_gem_object_put(r_obj); } diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 88239da1cd72..751c3b4965bc 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -100,7 +100,7 @@ struct msm_gem_vm { * * Only used for kernel managed VMs, unused for user managed VMs. * - * Protected by @mm_lock. + * Protected by vm lock. See msm_gem_lock_vm_and_obj(), for ex. */ struct drm_mm mm; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5f8e939a5906..3ab3b27134f9 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -271,32 +271,37 @@ out: return ret; } -/* This is where we make sure all the bo's are reserved and pin'd: */ -static int submit_lock_objects(struct msm_gem_submit *submit) +static int submit_lock_objects_vmbind(struct msm_gem_submit *submit) { - unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT | DRM_EXEC_IGNORE_DUPLICATES; struct drm_exec *exec = &submit->exec; - int ret; + int ret = 0; - if (msm_context_is_vmbind(submit->queue->ctx)) { - flags |= DRM_EXEC_IGNORE_DUPLICATES; + drm_exec_init(&submit->exec, flags, submit->nr_bos); - drm_exec_init(&submit->exec, flags, submit->nr_bos); + drm_exec_until_all_locked (&submit->exec) { + ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; - drm_exec_until_all_locked (&submit->exec) { - ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; + ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); + drm_exec_retry_on_contention(exec); + if (ret) + break; + } - ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1); - drm_exec_retry_on_contention(exec); - if (ret) - return ret; - } + return ret; +} - return 0; - } +/* This is where we make sure all the bo's are reserved and pin'd: */ +static int submit_lock_objects(struct msm_gem_submit *submit) +{ + unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT; + int ret = 0; + + if (msm_context_is_vmbind(submit->queue->ctx)) + return submit_lock_objects_vmbind(submit); drm_exec_init(&submit->exec, flags, submit->nr_bos); @@ -305,17 +310,17 @@ static int submit_lock_objects(struct msm_gem_submit *submit) drm_gpuvm_resv_obj(submit->vm)); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; for (unsigned i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = submit->bos[i].obj; ret = drm_exec_prepare_obj(&submit->exec, obj, 1); drm_exec_retry_on_contention(&submit->exec); if (ret) - return ret; + break; } } - return 0; + return ret; } static int submit_fence_sync(struct msm_gem_submit *submit) @@ -514,14 +519,15 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { + if (error) + submit_unpin_objects(submit); + if (submit->exec.objects) drm_exec_fini(&submit->exec); - if (error) { - submit_unpin_objects(submit); - /* job wasn't enqueued to scheduler, so early retirement: */ + /* if job wasn't enqueued to scheduler, early retirement: */ + if (error) msm_submit_retire(submit); - } } void msm_submit_retire(struct msm_gem_submit *submit) @@ -769,12 +775,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { sync_file = sync_file_create(submit->user_fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -812,10 +814,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(submit)) { diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index c632db9005e2..6df6b7c0984d 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -319,13 +319,10 @@ msm_gem_vma_map(struct drm_gpuva *vma, int prot, struct sg_table *sgt) mutex_lock(&vm->mmu_lock); /* - * NOTE: iommu/io-pgtable can allocate pages, so we cannot hold + * NOTE: if not using pgtable preallocation, we cannot hold * a lock across map/unmap which is also used in the job_run() * path, as this can cause deadlock in job_run() vs shrinker/ * reclaim. - * - * Revisit this if we can come up with a scheme to pre-alloc pages - * for the pgtable in map/unmap ops. */ ret = vm_map_op(vm, &(struct msm_vm_map_op){ .iova = vma->va.addr, @@ -461,6 +458,8 @@ msm_gem_vm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) struct op_arg { unsigned flags; struct msm_vm_bind_job *job; + const struct msm_vm_bind_op *op; + bool kept; }; static void @@ -482,14 +481,18 @@ vma_from_op(struct op_arg *arg, struct drm_gpuva_op_map *op) } static int -msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gem_object *obj = op->map.gem.obj; struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + if (arg->kept) + return 0; + vma = vma_from_op(arg, &op->map); if (WARN_ON(IS_ERR(vma))) return PTR_ERR(vma); @@ -609,15 +612,41 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) } static int -msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *arg) +msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) { - struct msm_vm_bind_job *job = ((struct op_arg *)arg)->job; + struct op_arg *arg = _arg; + struct msm_vm_bind_job *job = arg->job; struct drm_gpuva *vma = op->unmap.va; struct msm_gem_vma *msm_vma = to_msm_vma(vma); vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); + /* + * Detect in-place remap. Turnip does this to change the vma flags, + * in particular MSM_VMA_DUMP. In this case we want to avoid actually + * touching the page tables, as that would require synchronization + * against SUBMIT jobs running on the GPU. + */ + if (op->unmap.keep && + (arg->op->op == MSM_VM_BIND_OP_MAP) && + (vma->gem.obj == arg->op->obj) && + (vma->gem.offset == arg->op->obj_offset) && + (vma->va.addr == arg->op->iova) && + (vma->va.range == arg->op->range)) { + /* We are only expecting a single in-place unmap+map cb pair: */ + WARN_ON(arg->kept); + + /* Leave the existing VMA in place, but signal that to the map cb: */ + arg->kept = true; + + /* Only flags are changing, so update that in-place: */ + unsigned orig_flags = vma->flags & (DRM_GPUVA_USERBITS - 1); + vma->flags = orig_flags | arg->flags; + + return 0; + } + if (!msm_vma->mapped) goto out_close; @@ -1284,6 +1313,7 @@ vm_bind_job_prepare(struct msm_vm_bind_job *job) const struct msm_vm_bind_op *op = &job->ops[i]; struct op_arg arg = { .job = job, + .op = op, }; switch (op->op) { @@ -1480,12 +1510,8 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) if (args->flags & MSM_VM_BIND_FENCE_FD_OUT) { sync_file = sync_file_create(job->fence); - if (!sync_file) { + if (!sync_file) ret = -ENOMEM; - } else { - fd_install(out_fence_fd, sync_file->file); - args->fence_fd = out_fence_fd; - } } if (ret) @@ -1514,10 +1540,14 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) { - put_unused_fd(out_fence_fd); + if (ret) { + if (out_fence_fd >= 0) + put_unused_fd(out_fence_fd); if (sync_file) fput(sync_file->file); + } else if (sync_file) { + fd_install(out_fence_fd, sync_file->file); + args->fence_fd = out_fence_fd; } if (!IS_ERR_OR_NULL(job)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index c317b25a8162..26c5ce897cbb 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -465,6 +465,7 @@ static void recover_worker(struct kthread_work *work) struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; + struct task_struct *task; int i; mutex_lock(&gpu->lock); @@ -482,16 +483,20 @@ static void recover_worker(struct kthread_work *work) /* Increment the fault counts */ submit->queue->faults++; - if (submit->vm) { + + task = get_pid_task(submit->pid, PIDTYPE_PID); + if (!task) + gpu->global_faults++; + else { struct msm_gem_vm *vm = to_msm_vm(submit->vm); vm->faults++; /* * If userspace has opted-in to VM_BIND (and therefore userspace - * management of the VM), faults mark the VM as unusuable. This + * management of the VM), faults mark the VM as unusable. This * matches vulkan expectations (vulkan is the main target for - * VM_BIND) + * VM_BIND). */ if (!vm->managed) msm_gem_vm_unusable(submit->vm); @@ -553,8 +558,15 @@ static void recover_worker(struct kthread_work *work) unsigned long flags; spin_lock_irqsave(&ring->submit_lock, flags); - list_for_each_entry(submit, &ring->submits, node) + list_for_each_entry(submit, &ring->submits, node) { + /* + * If the submit uses an unusable vm make sure + * we don't actually run it + */ + if (to_msm_vm(submit->vm)->unusable) + submit->nr_cmds = 0; gpu->funcs->submit(gpu, submit); + } spin_unlock_irqrestore(&ring->submit_lock, flags); } } diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 55c29f49b788..76cdd5ea06a0 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -14,7 +14,9 @@ struct msm_iommu { struct msm_mmu base; struct iommu_domain *domain; - atomic_t pagetables; + + struct mutex init_lock; /* protects pagetables counter and prr_page */ + int pagetables; struct page *prr_page; struct kmem_cache *pt_cache; @@ -227,7 +229,8 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) * If this is the last attached pagetable for the parent, * disable TTBR0 in the arm-smmu driver */ - if (atomic_dec_return(&iommu->pagetables) == 0) { + mutex_lock(&iommu->init_lock); + if (--iommu->pagetables == 0) { adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, NULL); if (adreno_smmu->set_prr_bit) { @@ -236,6 +239,7 @@ static void msm_iommu_pagetable_destroy(struct msm_mmu *mmu) iommu->prr_page = NULL; } } + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); @@ -568,9 +572,12 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m * If this is the first pagetable that we've allocated, send it back to * the arm-smmu driver as a trigger to set up TTBR0 */ - if (atomic_inc_return(&iommu->pagetables) == 1) { + mutex_lock(&iommu->init_lock); + if (iommu->pagetables++ == 0) { ret = adreno_smmu->set_ttbr0_cfg(adreno_smmu->cookie, &ttbr0_cfg); if (ret) { + iommu->pagetables--; + mutex_unlock(&iommu->init_lock); free_io_pgtable_ops(pagetable->pgtbl_ops); kfree(pagetable); return ERR_PTR(ret); @@ -595,6 +602,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent, bool kernel_m adreno_smmu->set_prr_bit(adreno_smmu->cookie, true); } } + mutex_unlock(&iommu->init_lock); /* Needed later for TLB flush */ pagetable->parent = parent; @@ -730,7 +738,7 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) iommu->domain = domain; msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU); - atomic_set(&iommu->pagetables, 0); + mutex_init(&iommu->init_lock); ret = iommu_attach_device(iommu->domain, dev); if (ret) { diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 6889f1c1e721..56828d218e88 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -275,6 +275,12 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) if (ret) return ret; + ret = msm_disp_snapshot_init(ddev); + if (ret) { + DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); + return ret; + } + ret = priv->kms_init(ddev); if (ret) { DRM_DEV_ERROR(dev, "failed to load kms\n"); @@ -327,10 +333,6 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) goto err_msm_uninit; } - ret = msm_disp_snapshot_init(ddev); - if (ret) - DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret); - drm_mode_config_reset(ddev); return 0; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 1f5fe7811e01..39885b333910 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -423,7 +423,7 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5 if (IS_ERR(msm_mdss->mmio)) return ERR_CAST(msm_mdss->mmio); - dev_dbg(&pdev->dev, "mapped mdss address space @%pK\n", msm_mdss->mmio); + dev_dbg(&pdev->dev, "mapped mdss address space @%p\n", msm_mdss->mmio); ret = msm_mdss_parse_data_bus_icc_path(&pdev->dev, msm_mdss); if (ret) diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index d860fd94feae..86fab2750ba7 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -594,10 +594,14 @@ by a particular renderpass/blit. <reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/> <reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/> <reg32 offset="0x0602" name="DBGC_CFG_DBGBUS_SEL_C"/> - <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D"> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A6XX"> <bitfield high="7" low="0" name="PING_INDEX"/> <bitfield high="15" low="8" name="PING_BLK_SEL"/> </reg32> + <reg32 offset="0x0603" name="DBGC_CFG_DBGBUS_SEL_D" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> <reg32 offset="0x0604" name="DBGC_CFG_DBGBUS_CNTLT"> <bitfield high="5" low="0" name="TRACEEN"/> <bitfield high="14" low="12" name="GRANU"/> @@ -3796,6 +3800,14 @@ by a particular renderpass/blit. <reg32 offset="0x0030" name="CFG_DBGBUS_TRACE_BUF2"/> </domain> +<domain name="A7XX_CX_DBGC" width="32"> + <!-- Bitfields shifted, but otherwise the same: --> + <reg32 offset="0x0000" name="CFG_DBGBUS_SEL_A" variants="A7XX-"> + <bitfield high="7" low="0" name="PING_INDEX"/> + <bitfield high="24" low="16" name="PING_BLK_SEL"/> + </reg32> +</domain> + <domain name="A6XX_CX_MISC" width="32" prefix="variant" varset="chip"> <reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/> <reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/> diff --git a/drivers/gpu/drm/msm/registers/display/dsi.xml b/drivers/gpu/drm/msm/registers/display/dsi.xml index 501ffc585a9f..c7a7b633d747 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi.xml @@ -159,28 +159,28 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="RGB_SWAP" low="12" high="14" type="dsi_rgb_swap"/> </reg32> <reg32 offset="0x00020" name="ACTIVE_H"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00024" name="ACTIVE_V"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00028" name="TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0002c" name="ACTIVE_HSYNC"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00030" name="ACTIVE_VSYNC_HPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00034" name="ACTIVE_VSYNC_VPOS"> - <bitfield name="START" low="0" high="11" type="uint"/> - <bitfield name="END" low="16" high="27" type="uint"/> + <bitfield name="START" low="0" high="15" type="uint"/> + <bitfield name="END" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00038" name="CMD_DMA_CTRL"> @@ -209,8 +209,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="WORD_COUNT" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x00058" name="CMD_MDP_STREAM0_TOTAL"> - <bitfield name="H_TOTAL" low="0" high="11" type="uint"/> - <bitfield name="V_TOTAL" low="16" high="27" type="uint"/> + <bitfield name="H_TOTAL" low="0" high="15" type="uint"/> + <bitfield name="V_TOTAL" low="16" high="31" type="uint"/> </reg32> <reg32 offset="0x0005c" name="CMD_MDP_STREAM1_CTRL"> <bitfield name="DATA_TYPE" low="0" high="5" type="uint"/> diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 11d5b923d6e7..e2c55f4b9c5a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -795,6 +795,10 @@ static bool nv50_plane_format_mod_supported(struct drm_plane *plane, struct nouveau_drm *drm = nouveau_drm(plane->dev); uint8_t i; + /* All chipsets can display all formats in linear layout */ + if (modifier == DRM_FORMAT_MOD_LINEAR) + return true; + if (drm->client.device.info.chipset < 0xc0) { const struct drm_format_info *info = drm_format_info(format); const uint8_t kind = (modifier >> 12) & 0xff; diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c index cccdeca72002..317e516c4ec7 100644 --- a/drivers/gpu/drm/nouveau/gv100_fence.c +++ b/drivers/gpu/drm/nouveau/gv100_fence.c @@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) struct nvif_push *push = &chan->chan.push; int ret; - ret = PUSH_WAIT(push, 8); + ret = PUSH_WAIT(push, 13); if (ret) return ret; @@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) | NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS)); + PUSH_MTHD(push, NVC36F, MEM_OP_A, 0, + MEM_OP_B, 0, + MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR), + MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR)); + PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0); PUSH_KICK(push); diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h index 8735dda4c8a7..338f74b9f501 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h @@ -7,6 +7,91 @@ #define NVC36F_NON_STALL_INTERRUPT (0x00000020) #define NVC36F_NON_STALL_INTERRUPT_HANDLE 31:0 +// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for +// specifying the page address for a targeted TLB invalidate and the uTLB for +// a targeted REPLAY_CANCEL for UVM. +// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly +// rearranged fields. +#define NVC36F_MEM_OP_A (0x00000028) +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID 5:0 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE 5:0 // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID 10:6 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID 6:0 // only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR 11:11 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN 0x00000001 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS 0x00000000 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO 31:12 +#define NVC36F_MEM_OP_B (0x0000002c) +#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI 31:0 +#define NVC36F_MEM_OP_C (0x00000030) +#define NVC36F_MEM_OP_C_MEMBAR_TYPE 2:0 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR 0x00000000 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB 0:0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL 0x00000001 // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC 1:1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY 4:2 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE 6:5 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE 9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ 0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE 1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG 2 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD 3 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK 4 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL 5 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC 6 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL 7 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL 9:7 // Invalidate affects this level and all below +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL 0x00000000 // Invalidate tlb caches at all levels of the page table +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4 0x00000006 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5 0x00000007 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE 11:10 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO 31:12 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG 19:0 +// MEM_OP_D MUST be preceded by MEM_OPs A-C. +#define NVC36F_MEM_OP_D (0x00000034) +#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI 26:0 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_D_OPERATION 31:27 +#define NVC36F_MEM_OP_D_OPERATION_MEMBAR 0x00000005 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE 0x00000009 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED 0x0000000a +#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE 0x0000000d +#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE 0x0000000e +// CLEAN_LINES is an alias for Tegra/GPU IP usage +#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES 0x0000000e +#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS 0x0000000f +#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY 0x00000010 +#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS 0x00000015 +#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR 0x00000016 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE 1:0 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL 0x00000002 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED 0x00000003 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE 2:2 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK 6:3 #define NVC36F_SEM_ADDR_LO (0x0000005c) #define NVC36F_SEM_ADDR_LO_OFFSET 31:2 #define NVC36F_SEM_ADDR_HI (0x00000060) diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index edbbda78bac9..c4949e815eb3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -60,14 +60,14 @@ * virtual address in the GPU's VA space there is no guarantee that the actual * mappings are created in the GPU's MMU. If the given memory is swapped out * at the time the bind operation is executed the kernel will stash the mapping - * details into it's internal alloctor and create the actual MMU mappings once + * details into it's internal allocator and create the actual MMU mappings once * the memory is swapped back in. While this is transparent for userspace, it is * guaranteed that all the backing memory is swapped back in and all the memory * mappings, as requested by userspace previously, are actually mapped once the * DRM_NOUVEAU_EXEC ioctl is called to submit an exec job. * * A VM_BIND job can be executed either synchronously or asynchronously. If - * exectued asynchronously, userspace may provide a list of syncobjs this job + * executed asynchronously, userspace may provide a list of syncobjs this job * will wait for and/or a list of syncobj the kernel will signal once the * VM_BIND job finished execution. If executed synchronously the ioctl will * block until the bind job is finished. For synchronous jobs the kernel will @@ -82,7 +82,7 @@ * Since VM_BIND jobs update the GPU's VA space on job submit, EXEC jobs do have * an up to date view of the VA space. However, the actual mappings might still * be pending. Hence, EXEC jobs require to have the particular fences - of - * the corresponding VM_BIND jobs they depent on - attached to them. + * the corresponding VM_BIND jobs they depend on - attached to them. */ static int diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 9f345a008717..869d4335c0f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; } -void -nouveau_fence_cancel(struct nouveau_fence *fence) -{ - struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - unsigned long flags; - - spin_lock_irqsave(&fctx->lock, flags); - if (!dma_fence_is_signaled_locked(&fence->base)) { - dma_fence_set_error(&fence->base, -ECANCELED); - if (nouveau_fence_signal(fence)) - nvif_event_block(&fctx->event); - } - spin_unlock_irqrestore(&fctx->lock, flags); -} - bool nouveau_fence_done(struct nouveau_fence *fence) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 9957a919bd38..183dd43ecfff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); -void nouveau_fence_cancel(struct nouveau_fence *fence); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 0cc0bc9f9952..e60f7892f5ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -11,7 +11,6 @@ #include "nouveau_exec.h" #include "nouveau_abi16.h" #include "nouveau_sched.h" -#include "nouveau_chan.h" #define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 @@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job) { struct nouveau_sched *sched = job->sched; - spin_lock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); list_del(&job->entry); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); + + wake_up(&sched->job.wq); } void @@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job) } /* Submit was successful; add the job to the schedulers job list. */ - spin_lock(&sched->job_list.lock); - list_add(&job->entry, &sched->job_list.head); - spin_unlock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); + list_add(&job->entry, &sched->job.list.head); + spin_unlock(&sched->job.list.lock); drm_sched_job_arm(&job->base); job->done_fence = dma_fence_get(&job->base.s_fence->finished); @@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job) nouveau_job_fini(job); } -static void -nouveau_sched_cancel_job(struct drm_sched_job *sched_job) -{ - struct nouveau_fence *fence; - struct nouveau_job *job; - - job = to_nouveau_job(sched_job); - fence = to_nouveau_fence(job->done_fence); - - nouveau_fence_cancel(fence); -} - static const struct drm_sched_backend_ops nouveau_sched_ops = { .run_job = nouveau_sched_run_job, .timedout_job = nouveau_sched_timedout_job, .free_job = nouveau_sched_free_job, - .cancel_job = nouveau_sched_cancel_job, }; static int @@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, goto fail_sched; mutex_init(&sched->mutex); - spin_lock_init(&sched->job_list.lock); - INIT_LIST_HEAD(&sched->job_list.head); + spin_lock_init(&sched->job.list.lock); + INIT_LIST_HEAD(&sched->job.list.head); + init_waitqueue_head(&sched->job.wq); return 0; @@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } + static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; + rmb(); /* for list_empty to work without lock */ + wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index b98c3f0bef30..20cd1da8db73 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -103,9 +103,12 @@ struct nouveau_sched { struct mutex mutex; struct { - struct list_head head; - spinlock_t lock; - } job_list; + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; }; int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index d94a85509176..79eefdfd08a2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) u64 end = addr + range; again: - spin_lock(&sched->job_list.lock); - list_for_each_entry(__job, &sched->job_list.head, entry) { + spin_lock(&sched->job.list.lock); + list_for_each_entry(__job, &sched->job.list.head, entry) { struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job); list_for_each_op(op, &bind_job->ops) { @@ -1030,7 +1030,7 @@ again: if (!(end <= op_addr || addr >= op_end)) { nouveau_uvmm_bind_job_get(bind_job); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); wait_for_completion(&bind_job->complete); nouveau_uvmm_bind_job_put(bind_job); goto again; @@ -1038,7 +1038,7 @@ again: } } } - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); } static int diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c index 99296f03371a..07c1ebc2a941 100644 --- a/drivers/gpu/drm/nouveau/nvif/vmm.c +++ b/drivers/gpu/drm/nouveau/nvif/vmm.c @@ -219,7 +219,8 @@ nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, case RAW: args->type = NVIF_VMM_V0_TYPE_RAW; break; default: WARN_ON(1); - return -EINVAL; + ret = -EINVAL; + goto done; } memcpy(args->data, argv, argc); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c index fdffa0391b31..6fd4e60634fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c @@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine) nvkm_chid_unref(&fifo->chid); nvkm_event_fini(&fifo->nonstall.event); + if (fifo->func->nonstall_dtor) + fifo->func->nonstall_dtor(fifo); mutex_destroy(&fifo->mutex); if (fifo->func->dtor) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c index e74493a4569e..6848a56f20c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c @@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth) static void ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_block(&runl->nonstall.inth); } static void ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_allow(&runl->nonstall.inth); } const struct nvkm_event_func @@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo) if (ret) return ret; + nvkm_inth_allow(&runl->nonstall.inth); + nr = max(nr, runl->id + 1); } return nr; } +void +ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo) +{ + struct nvkm_runl *runl; + + nvkm_runl_foreach(runl, fifo) { + if (runl->nonstall.vector < 0) + continue; + nvkm_inth_block(&runl->nonstall.inth); + } +} + int ga100_fifo_runl_ctor(struct nvkm_fifo *fifo) { @@ -599,6 +605,7 @@ ga100_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c index 755235f55b3a..18a0b1f4eab7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c @@ -30,6 +30,7 @@ ga102_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h index 5e81ae195329..fff1428ef267 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h @@ -41,6 +41,7 @@ struct nvkm_fifo_func { void (*start)(struct nvkm_fifo *, unsigned long *); int (*nonstall_ctor)(struct nvkm_fifo *); + void (*nonstall_dtor)(struct nvkm_fifo *); const struct nvkm_event_func *nonstall; const struct nvkm_runl_func *runl; @@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *); int ga100_fifo_runl_ctor(struct nvkm_fifo *); int ga100_fifo_nonstall_ctor(struct nvkm_fifo *); +void ga100_fifo_nonstall_dtor(struct nvkm_fifo *); extern const struct nvkm_event_func ga100_fifo_nonstall; extern const struct nvkm_runl_func ga100_runl; extern const struct nvkm_runq_func ga100_runq; diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index b7da3ab44c27..7c43397c19e6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -103,7 +103,7 @@ gm200_flcn_pio_imem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 i static void gm200_flcn_pio_imem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int len, u16 tag) { - nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag++); + nvkm_falcon_wr32(falcon, 0x188 + (port * 0x10), tag); while (len >= 4) { nvkm_falcon_wr32(falcon, 0x184 + (port * 0x10), *(u32 *)img); img += 4; @@ -249,9 +249,11 @@ int gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) { struct nvkm_falcon *falcon = fw->falcon; - int target, ret; + int ret; if (fw->inst) { + int target; + nvkm_falcon_mask(falcon, 0x048, 0x00000001, 0x00000001); switch (nvkm_memory_target(fw->inst)) { @@ -285,15 +287,6 @@ gm200_flcn_fw_load(struct nvkm_falcon_fw *fw) } if (fw->boot) { - switch (nvkm_memory_target(&fw->fw.mem.memory)) { - case NVKM_MEM_TARGET_VRAM: target = 4; break; - case NVKM_MEM_TARGET_HOST: target = 5; break; - case NVKM_MEM_TARGET_NCOH: target = 6; break; - default: - WARN_ON(1); - return -EINVAL; - } - ret = nvkm_falcon_pio_wr(falcon, fw->boot, 0, 0, IMEM, falcon->code.limit - fw->boot_size, fw->boot_size, fw->boot_addr >> 8, false); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 52412965fac1..5b721bd9d799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -209,11 +209,12 @@ nvkm_gsp_fwsec_v2(struct nvkm_gsp *gsp, const char *name, fw->boot_addr = bld->start_tag << 8; fw->boot_size = bld->code_size; fw->boot = kmemdup(bl->data + hdr->data_offset + bld->code_off, fw->boot_size, GFP_KERNEL); - if (!fw->boot) - ret = -ENOMEM; nvkm_firmware_put(bl); + if (!fw->boot) + return -ENOMEM; + /* Patch in interface data. */ return nvkm_gsp_fwsec_patch(gsp, fw, desc->InterfaceOffset, init_cmd); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c index 1ac5628c5140..4ed54b386a60 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c @@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device, rm->chan.func = &r535_chan; rm->nonstall = &ga100_fifo_nonstall; rm->nonstall_ctor = ga100_fifo_nonstall_ctor; + rm->nonstall_dtor = ga100_fifo_nonstall_dtor; return nvkm_fifo_new_(rm, device, type, inst, pfifo); } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c index 9d06ff722fea..0dc4782df8c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c @@ -325,7 +325,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_peek(gsp, sizeof(*rpc), info.retries); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } @@ -334,7 +334,7 @@ r535_gsp_msgq_recv(struct nvkm_gsp *gsp, u32 gsp_rpc_len, int *retries) rpc = r535_gsp_msgq_recv_one_elem(gsp, &info); if (IS_ERR_OR_NULL(rpc)) { - kfree(buf); + kvfree(buf); return rpc; } diff --git a/drivers/gpu/drm/nova/file.rs b/drivers/gpu/drm/nova/file.rs index 7e7d4e2de2fb..90b9d2d0ec4a 100644 --- a/drivers/gpu/drm/nova/file.rs +++ b/drivers/gpu/drm/nova/file.rs @@ -36,7 +36,7 @@ impl File { _ => return Err(EINVAL), }; - getparam.value = value; + getparam.value = Into::<u64>::into(value); Ok(0) } diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 9256806eb662..4c202fc5ce05 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_panthor_queue_create *queue_args; int ret; - if (!args->queues.count) + if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG) return -EINVAL; ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues); diff --git a/drivers/gpu/drm/rockchip/Kconfig b/drivers/gpu/drm/rockchip/Kconfig index 616c0bc1ccee..b7b025814e72 100644 --- a/drivers/gpu/drm/rockchip/Kconfig +++ b/drivers/gpu/drm/rockchip/Kconfig @@ -54,6 +54,7 @@ config ROCKCHIP_CDN_DP bool "Rockchip cdn DP" depends on EXTCON=y || (EXTCON=m && DRM_ROCKCHIP=m) select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR select DRM_DISPLAY_DP_HELPER help This selects support for Rockchip SoC specific extensions diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 186f6452a7d3..b50927a824b4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -2579,12 +2579,13 @@ static int vop2_win_init(struct vop2 *vop2) } /* - * The window registers are only updated when config done is written. - * Until that they read back the old value. As we read-modify-write - * these registers mark them as non-volatile. This makes sure we read - * the new values from the regmap register cache. + * The window and video port registers are only updated when config + * done is written. Until that they read back the old value. As we + * read-modify-write these registers mark them as non-volatile. This + * makes sure we read the new values from the regmap register cache. */ static const struct regmap_range vop2_nonvolatile_range[] = { + regmap_reg_range(RK3568_VP0_CTRL_BASE, RK3588_VP3_CTRL_BASE + 255), regmap_reg_range(0x1000, 0x23ff), }; diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 41a285ec889f..8ede07fb7a21 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -526,7 +526,7 @@ void tegra_bo_free_object(struct drm_gem_object *gem) if (drm_gem_is_imported(gem)) { dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt, DMA_TO_DEVICE); - dma_buf_detach(gem->dma_buf, gem->import_attach); + dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach); } } diff --git a/drivers/gpu/drm/tests/drm_format_helper_test.c b/drivers/gpu/drm/tests/drm_format_helper_test.c index 7299fa8971ce..981dada8f3a8 100644 --- a/drivers/gpu/drm/tests/drm_format_helper_test.c +++ b/drivers/gpu/drm/tests/drm_format_helper_test.c @@ -1033,13 +1033,14 @@ static void drm_test_fb_xrgb8888_to_xrgb2101010(struct kunit *test) NULL : &result->dst_pitch; drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); - buf = le32buf_to_cpu(test, buf, dst_size / sizeof(u32)); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); buf = dst.vaddr; /* restore original value of buf */ memset(buf, 0, dst_size); drm_fb_xrgb8888_to_xrgb2101010(&dst, dst_pitch, &src, &fb, ¶ms->clip, &fmtcnv_state); + buf = le32buf_to_cpu(test, (__force const __le32 *)buf, dst_size / sizeof(u32)); KUNIT_EXPECT_MEMEQ(test, buf, result->expected, dst_size); } diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index bb469096d072..7b40cc8be1c9 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -236,7 +236,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc } xe_bo_lock(external, false); - err = xe_bo_pin_external(external); + err = xe_bo_pin_external(external, false); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c index 3c5ad8cc65a0..5baeab6b6fb7 100644 --- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c @@ -85,15 +85,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, return; } - /* - * If on different devices, the exporter is kept in system if - * possible, saving a migration step as the transfer is just - * likely as fast from system memory. - */ - if (params->mem_mask & XE_BO_FLAG_SYSTEM) - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT)); - else - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); + KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); if (params->force_different_devices) KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT)); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 4faf15d5fa6d..870f43347281 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -188,6 +188,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, + .flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ? + TTM_PL_FLAG_FALLBACK : 0, }; *c += 1; } @@ -2322,6 +2324,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) /** * xe_bo_pin_external - pin an external BO * @bo: buffer object to be pinned + * @in_place: Pin in current placement, don't attempt to migrate. * * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD) * BO. Unique call compared to xe_bo_pin as this function has it own set of @@ -2329,7 +2332,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) * * Returns 0 for success, negative error code otherwise. */ -int xe_bo_pin_external(struct xe_bo *bo) +int xe_bo_pin_external(struct xe_bo *bo, bool in_place) { struct xe_device *xe = xe_bo_device(bo); int err; @@ -2338,9 +2341,11 @@ int xe_bo_pin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_user(bo)); if (!xe_bo_is_pinned(bo)) { - err = xe_bo_validate(bo, NULL, false); - if (err) - return err; + if (!in_place) { + err = xe_bo_validate(bo, NULL, false); + if (err) + return err; + } spin_lock(&xe->pinned.lock); list_add_tail(&bo->pinned_link, &xe->pinned.late.external); @@ -2493,6 +2498,9 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) }; int ret; + if (xe_bo_is_pinned(bo)) + return 0; + if (vm) { lockdep_assert_held(&vm->lock); xe_vm_assert_held(vm); diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 8cce413b5235..cfb1ec266a6d 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -200,7 +200,7 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) } } -int xe_bo_pin_external(struct xe_bo *bo); +int xe_bo_pin_external(struct xe_bo *bo, bool in_place); int xe_bo_pin(struct xe_bo *bo); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 092004d14db2..1e780f8a2a8c 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -507,6 +507,12 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; + /** @rebind_resume_list: List of wq items to kick on resume. */ + struct list_head rebind_resume_list; + /** @rebind_resume_lock: Lock to protect the rebind_resume_list */ + struct mutex rebind_resume_lock; /** @pmt: Support the PMT driver callback interface */ struct { diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 71b70e17bddd..95d06bd65b0f 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -72,7 +72,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return ret; } - ret = xe_bo_pin_external(bo); + ret = xe_bo_pin_external(bo, true); xe_assert(xe, !ret); return 0; diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..374c831e691b 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -237,6 +237,15 @@ retry: goto err_unlock_list; } + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index d4b54cd34cff..6eea4190bbd2 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -25,6 +25,7 @@ #include "xe_pxp.h" #include "xe_sriov_vf_ccs.h" #include "xe_trace.h" +#include "xe_vm.h" #include "xe_wa.h" /** @@ -301,6 +302,19 @@ static u32 vram_threshold_value(struct xe_device *xe) return DEFAULT_VRAM_THRESHOLD; } +static void xe_pm_wake_rebind_workers(struct xe_device *xe) +{ + struct xe_vm *vm, *next; + + mutex_lock(&xe->rebind_resume_lock); + list_for_each_entry_safe(vm, next, &xe->rebind_resume_list, + preempt.pm_activate_link) { + list_del_init(&vm->preempt.pm_activate_link); + xe_vm_resume_rebind_worker(vm); + } + mutex_unlock(&xe->rebind_resume_lock); +} + static int xe_pm_notifier_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -310,30 +324,30 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err); - xe_pm_runtime_put(xe); - break; - } err = xe_bo_notifier_prepare_all_pinned(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err); - xe_pm_runtime_put(xe); - } + /* + * Keep the runtime pm reference until post hibernation / post suspend to + * avoid a runtime suspend interfering with evicted objects or backup + * allocations. + */ break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); + xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; } - if (err) - return NOTIFY_BAD; - return NOTIFY_DONE; } @@ -355,6 +369,14 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock); + if (err) + goto err_unregister; + + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); + INIT_LIST_HEAD(&xe->rebind_resume_list); + /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 53c5af4b810c..7999cc5262a5 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -44,6 +44,8 @@ * * # echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode * + * It is the responsibility of the user to clear the mode once firmware flash is complete. + * * Refer :ref:`xe_configfs` for more details on how to use configfs * * Survivability mode is indicated by the below admin-only readable sysfs which provides additional @@ -180,7 +182,6 @@ static void xe_survivability_mode_fini(void *arg) struct pci_dev *pdev = to_pci_dev(xe->drm.dev); struct device *dev = &pdev->dev; - xe_configfs_clear_survivability_mode(pdev); sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 3ff3c67aa79d..c00a5ff31817 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -394,6 +394,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); if (ret) return ret; @@ -480,6 +483,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } +static bool vm_suspend_rebind_worker(struct xe_vm *vm) +{ + struct xe_device *xe = vm->xe; + bool ret = false; + + mutex_lock(&xe->rebind_resume_lock); + if (!try_wait_for_completion(&vm->xe->pm_block)) { + ret = true; + list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list); + } + mutex_unlock(&xe->rebind_resume_lock); + + return ret; +} + +/** + * xe_vm_resume_rebind_worker() - Resume the rebind worker. + * @vm: The vm whose preempt worker to resume. + * + * Resume a preempt worker that was previously suspended by + * vm_suspend_rebind_worker(). + */ +void xe_vm_resume_rebind_worker(struct xe_vm *vm) +{ + queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work); +} + static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); @@ -503,6 +533,11 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) { + up_write(&vm->lock); + return; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) @@ -1741,6 +1776,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (flags & XE_VM_FLAG_LR_MODE) { INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); xe_pm_runtime_get_noresume(xe); + INIT_LIST_HEAD(&vm->preempt.pm_activate_link); } if (flags & XE_VM_FLAG_FAULT_MODE) { @@ -1922,8 +1958,12 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_assert(xe, !vm->preempt.num_exec_queues); xe_vm_close(vm); - if (xe_vm_in_preempt_fence_mode(vm)) + if (xe_vm_in_preempt_fence_mode(vm)) { + mutex_lock(&xe->rebind_resume_lock); + list_del_init(&vm->preempt.pm_activate_link); + mutex_unlock(&xe->rebind_resume_lock); flush_work(&vm->preempt.rebind_work); + } if (xe_vm_in_fault_mode(vm)) xe_svm_close(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index b3e5bec0fa58..d631c4b25c51 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -281,6 +281,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo, struct xe_exec_queue *q, u64 addr, enum xe_cache_level cache_lvl); +void xe_vm_resume_rebind_worker(struct xe_vm *vm); + /** * xe_vm_resv() - Return's the vm's reservation object * @vm: The vm diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index b5108d010786..e1a786db5f89 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -338,6 +338,11 @@ struct xe_vm { * BOs */ struct work_struct rebind_work; + /** + * @preempt.pm_activate_link: Link to list of rebind workers to be + * kicked on resume. + */ + struct list_head pm_activate_link; } preempt; /** @um: unified memory state */ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 0cf2b3c03532..338c344dcd7d 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -32,7 +32,8 @@ 16022287689 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) 13011645652 GRAPHICS_VERSION(2004) - GRAPHICS_VERSION(3001) + GRAPHICS_VERSION_RANGE(3000, 3001) + GRAPHICS_VERSION(3003) 14022293748 GRAPHICS_VERSION_RANGE(2001, 2002) GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 8726d80d6ba4..20d3e6d0d796 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -1,5 +1,6 @@ config NOVA_CORE tristate "Nova Core GPU driver" + depends on 64BIT depends on PCI depends on RUST depends on RUST_FW_LOADER_ABSTRACTIONS |