diff options
Diffstat (limited to 'drivers/gpu/drm/vc4')
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_bo.c | 31 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_debugfs.c | 8 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_drv.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_drv.h | 14 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_gem.c | 11 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_hdmi.c | 8 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_irq.c | 20 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_plane.c | 15 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_txp.c | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_v3d.c | 72 |
10 files changed, 150 insertions, 42 deletions
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index d185a522da49..a75a2f98b82f 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -796,13 +796,36 @@ vc4_prime_import_sg_table(struct drm_device *dev, return obj; } +static int vc4_grab_bin_bo(struct vc4_dev *vc4, struct vc4_file *vc4file) +{ + int ret; + + if (!vc4->v3d) + return -ENODEV; + + if (vc4file->bin_bo_used) + return 0; + + ret = vc4_v3d_bin_bo_get(vc4, &vc4file->bin_bo_used); + if (ret) + return ret; + + return 0; +} + int vc4_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_vc4_create_bo *args = data; + struct vc4_file *vc4file = file_priv->driver_priv; + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_bo *bo = NULL; int ret; + ret = vc4_grab_bin_bo(vc4, vc4file); + if (ret) + return ret; + /* * We can't allocate from the BO cache, because the BOs don't * get zeroed, and that might leak data between users. @@ -843,6 +866,8 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_vc4_create_shader_bo *args = data; + struct vc4_file *vc4file = file_priv->driver_priv; + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_bo *bo = NULL; int ret; @@ -862,6 +887,10 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data, return -EINVAL; } + ret = vc4_grab_bin_bo(vc4, vc4file); + if (ret) + return ret; + bo = vc4_bo_create(dev, args->size, true, VC4_BO_TYPE_V3D_SHADER); if (IS_ERR(bo)) return PTR_ERR(bo); @@ -891,7 +920,7 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data, */ ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); - fail: +fail: drm_gem_object_put_unlocked(&bo->base.base); return ret; diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c index 273da7e58d44..4829a00c16b0 100644 --- a/drivers/gpu/drm/vc4/vc4_debugfs.c +++ b/drivers/gpu/drm/vc4/vc4_debugfs.c @@ -26,13 +26,9 @@ vc4_debugfs_init(struct drm_minor *minor) { struct vc4_dev *vc4 = to_vc4_dev(minor->dev); struct vc4_debugfs_info_entry *entry; - struct dentry *dentry; - dentry = debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR, - minor->debugfs_root, - &vc4->load_tracker_enabled); - if (!dentry) - return -ENOMEM; + debugfs_create_bool("hvs_load_tracker", S_IRUGO | S_IWUSR, + minor->debugfs_root, &vc4->load_tracker_enabled); list_for_each_entry(entry, &vc4->debugfs_list, link) { int ret = drm_debugfs_create_files(&entry->info, 1, diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index e88235eeed6c..bf11930e40e1 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -125,8 +125,12 @@ static int vc4_open(struct drm_device *dev, struct drm_file *file) static void vc4_close(struct drm_device *dev, struct drm_file *file) { + struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_file *vc4file = file->driver_priv; + if (vc4file->bin_bo_used) + vc4_v3d_bin_bo_put(vc4); + vc4_perfmon_close_file(vc4file); kfree(vc4file); } @@ -271,6 +275,8 @@ static int vc4_drm_bind(struct device *dev) drm->dev_private = vc4; INIT_LIST_HEAD(&vc4->debugfs_list); + mutex_init(&vc4->bin_bo_lock); + ret = vc4_bo_cache_init(drm); if (ret) goto dev_put; diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 24c45f2d9df1..616c011bcb82 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -213,6 +213,11 @@ struct vc4_dev { * the minor is available (after drm_dev_register()). */ struct list_head debugfs_list; + + /* Mutex for binner bo allocation. */ + struct mutex bin_bo_lock; + /* Reference count for our binner bo. */ + struct kref bin_bo_kref; }; static inline struct vc4_dev * @@ -581,6 +586,11 @@ struct vc4_exec_info { * NULL otherwise. */ struct vc4_perfmon *perfmon; + + /* Whether the exec has taken a reference to the binner BO, which should + * happen with a VC4_PACKET_TILE_BINNING_MODE_CONFIG packet. + */ + bool bin_bo_used; }; /* Per-open file private data. Any driver-specific resource that has to be @@ -591,6 +601,8 @@ struct vc4_file { struct idr idr; struct mutex lock; } perfmon; + + bool bin_bo_used; }; static inline struct vc4_exec_info * @@ -830,6 +842,8 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, extern struct platform_driver vc4_v3d_driver; extern const struct of_device_id vc4_v3d_dt_match[]; int vc4_v3d_get_bin_slot(struct vc4_dev *vc4); +int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used); +void vc4_v3d_bin_bo_put(struct vc4_dev *vc4); int vc4_v3d_pm_get(struct vc4_dev *vc4); void vc4_v3d_pm_put(struct vc4_dev *vc4); diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index d9311be32a4f..84795d928f20 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -820,6 +820,7 @@ static int vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) { struct drm_vc4_submit_cl *args = exec->args; + struct vc4_dev *vc4 = to_vc4_dev(dev); void *temp = NULL; void *bin; int ret = 0; @@ -918,6 +919,12 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) if (ret) goto fail; + if (exec->found_tile_binning_mode_config_packet) { + ret = vc4_v3d_bin_bo_get(vc4, &exec->bin_bo_used); + if (ret) + goto fail; + } + /* Block waiting on any previous rendering into the CS's VBO, * IB, or textures, so that pixels are actually written by the * time we try to read them. @@ -966,6 +973,10 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) vc4->bin_alloc_used &= ~exec->bin_slots; spin_unlock_irqrestore(&vc4->job_lock, irqflags); + /* Release the reference on the binner BO if needed. */ + if (exec->bin_bo_used) + vc4_v3d_bin_bo_put(vc4); + /* Release the reference we had on the perf monitor. */ vc4_perfmon_put(exec->perfmon); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 9f385979d1e6..ee7d4e7b0ee3 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -247,11 +247,17 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) return ret; } +static void vc4_hdmi_connector_reset(struct drm_connector *connector) +{ + drm_atomic_helper_connector_reset(connector); + drm_atomic_helper_connector_tv_reset(connector); +} + static const struct drm_connector_funcs vc4_hdmi_connector_funcs = { .detect = vc4_hdmi_connector_detect, .fill_modes = drm_helper_probe_single_connector_modes, .destroy = vc4_hdmi_connector_destroy, - .reset = drm_atomic_helper_connector_reset, + .reset = vc4_hdmi_connector_reset, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index ffd0a4388752..e226c24e543f 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -59,15 +59,22 @@ vc4_overflow_mem_work(struct work_struct *work) { struct vc4_dev *vc4 = container_of(work, struct vc4_dev, overflow_mem_work); - struct vc4_bo *bo = vc4->bin_bo; + struct vc4_bo *bo; int bin_bo_slot; struct vc4_exec_info *exec; unsigned long irqflags; + mutex_lock(&vc4->bin_bo_lock); + + if (!vc4->bin_bo) + goto complete; + + bo = vc4->bin_bo; + bin_bo_slot = vc4_v3d_get_bin_slot(vc4); if (bin_bo_slot < 0) { DRM_ERROR("Couldn't allocate binner overflow mem\n"); - return; + goto complete; } spin_lock_irqsave(&vc4->job_lock, irqflags); @@ -98,6 +105,9 @@ vc4_overflow_mem_work(struct work_struct *work) V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM); V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM); spin_unlock_irqrestore(&vc4->job_lock, irqflags); + +complete: + mutex_unlock(&vc4->bin_bo_lock); } static void @@ -249,8 +259,10 @@ vc4_irq_postinstall(struct drm_device *dev) if (!vc4->v3d) return 0; - /* Enable both the render done and out of memory interrupts. */ - V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS); + /* Enable the render done interrupts. The out-of-memory interrupt is + * enabled as soon as we have a binner BO allocated. + */ + V3D_WRITE(V3D_INTENA, V3D_INT_FLDONE | V3D_INT_FRDONE); return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 84fd0a31b701..0a0207c350a5 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -307,10 +307,10 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) struct drm_framebuffer *fb = state->fb; struct drm_gem_cma_object *bo = drm_fb_cma_get_gem_obj(fb, 0); u32 subpixel_src_mask = (1 << 16) - 1; - u32 format = fb->format->format; int num_planes = fb->format->num_planes; struct drm_crtc_state *crtc_state; - u32 h_subsample, v_subsample; + u32 h_subsample = fb->format->hsub; + u32 v_subsample = fb->format->vsub; int i, ret; crtc_state = drm_atomic_get_existing_crtc_state(state->state, @@ -325,9 +325,6 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) if (ret) return ret; - h_subsample = drm_format_horz_chroma_subsampling(format); - v_subsample = drm_format_vert_chroma_subsampling(format); - for (i = 0; i < num_planes; i++) vc4_state->offsets[i] = bo->paddr + fb->offsets[i]; @@ -589,8 +586,9 @@ static int vc4_plane_mode_set(struct drm_plane *plane, u32 ctl0_offset = vc4_state->dlist_count; const struct hvs_format *format = vc4_get_hvs_format(fb->format->format); u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier); - int num_planes = drm_format_num_planes(format->drm); - u32 h_subsample, v_subsample; + int num_planes = fb->format->num_planes; + u32 h_subsample = fb->format->hsub; + u32 v_subsample = fb->format->vsub; bool mix_plane_alpha; bool covers_screen; u32 scl0, scl1, pitch0; @@ -620,9 +618,6 @@ static int vc4_plane_mode_set(struct drm_plane *plane, scl1 = vc4_get_scl_field(state, 0); } - h_subsample = drm_format_horz_chroma_subsampling(format->drm); - v_subsample = drm_format_vert_chroma_subsampling(format->drm); - rotation = drm_rotation_simplify(state->rotation, DRM_MODE_ROTATE_0 | DRM_MODE_REFLECT_X | diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index c8b89a78f9f4..96f91c1b4b6e 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -221,17 +221,18 @@ static const u32 txp_fmts[] = { }; static int vc4_txp_connector_atomic_check(struct drm_connector *conn, - struct drm_connector_state *conn_state) + struct drm_atomic_state *state) { + struct drm_connector_state *conn_state; struct drm_crtc_state *crtc_state; struct drm_framebuffer *fb; int i; + conn_state = drm_atomic_get_new_connector_state(state, conn); if (!conn_state->writeback_job || !conn_state->writeback_job->fb) return 0; - crtc_state = drm_atomic_get_new_crtc_state(conn_state->state, - conn_state->crtc); + crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); fb = conn_state->writeback_job->fb; if (fb->width != crtc_state->mode.hdisplay || diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index c36315924b7d..fee4f90e71aa 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -202,7 +202,7 @@ try_again: } /** - * vc4_allocate_bin_bo() - allocates the memory that will be used for + * bin_bo_alloc() - allocates the memory that will be used for * tile binning. * * The binner has a limitation that the addresses in the tile state @@ -223,14 +223,16 @@ try_again: * overall CMA pool before they make scenes complicated enough to run * out of bin space. */ -static int vc4_allocate_bin_bo(struct drm_device *drm) +static int bin_bo_alloc(struct vc4_dev *vc4) { - struct vc4_dev *vc4 = to_vc4_dev(drm); struct vc4_v3d *v3d = vc4->v3d; uint32_t size = 16 * 1024 * 1024; int ret = 0; struct list_head list; + if (!v3d) + return -ENODEV; + /* We may need to try allocating more than once to get a BO * that doesn't cross 256MB. Track the ones we've allocated * that failed so far, so that we can free them when we've got @@ -240,7 +242,7 @@ static int vc4_allocate_bin_bo(struct drm_device *drm) INIT_LIST_HEAD(&list); while (true) { - struct vc4_bo *bo = vc4_bo_create(drm, size, true, + struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true, VC4_BO_TYPE_BIN); if (IS_ERR(bo)) { @@ -281,6 +283,14 @@ static int vc4_allocate_bin_bo(struct drm_device *drm) WARN_ON_ONCE(sizeof(vc4->bin_alloc_used) * 8 != bo->base.base.size / vc4->bin_alloc_size); + kref_init(&vc4->bin_bo_kref); + + /* Enable the out-of-memory interrupt to set our + * newly-allocated binner BO, potentially from an + * already-pending-but-masked interrupt. + */ + V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM); + break; } @@ -300,6 +310,47 @@ static int vc4_allocate_bin_bo(struct drm_device *drm) return ret; } +int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used) +{ + int ret = 0; + + mutex_lock(&vc4->bin_bo_lock); + + if (used && *used) + goto complete; + + if (vc4->bin_bo) + kref_get(&vc4->bin_bo_kref); + else + ret = bin_bo_alloc(vc4); + + if (ret == 0 && used) + *used = true; + +complete: + mutex_unlock(&vc4->bin_bo_lock); + + return ret; +} + +static void bin_bo_release(struct kref *ref) +{ + struct vc4_dev *vc4 = container_of(ref, struct vc4_dev, bin_bo_kref); + + if (WARN_ON_ONCE(!vc4->bin_bo)) + return; + + drm_gem_object_put_unlocked(&vc4->bin_bo->base.base); + vc4->bin_bo = NULL; +} + +void vc4_v3d_bin_bo_put(struct vc4_dev *vc4) +{ + mutex_lock(&vc4->bin_bo_lock); + kref_put(&vc4->bin_bo_kref, bin_bo_release); + mutex_unlock(&vc4->bin_bo_lock); +} + #ifdef CONFIG_PM static int vc4_v3d_runtime_suspend(struct device *dev) { @@ -308,9 +359,6 @@ static int vc4_v3d_runtime_suspend(struct device *dev) vc4_irq_uninstall(vc4->dev); - drm_gem_object_put_unlocked(&vc4->bin_bo->base.base); - vc4->bin_bo = NULL; - clk_disable_unprepare(v3d->clk); return 0; @@ -322,10 +370,6 @@ static int vc4_v3d_runtime_resume(struct device *dev) struct vc4_dev *vc4 = v3d->vc4; int ret; - ret = vc4_allocate_bin_bo(vc4->dev); - if (ret) - return ret; - ret = clk_prepare_enable(v3d->clk); if (ret != 0) return ret; @@ -392,12 +436,6 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) if (ret != 0) return ret; - ret = vc4_allocate_bin_bo(drm); - if (ret) { - clk_disable_unprepare(v3d->clk); - return ret; - } - /* Reset the binner overflow address/size at setup, to be sure * we don't reuse an old one. */ |