diff options
Diffstat (limited to 'drivers/gpu/drm/vc4/vc4_crtc.c')
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_crtc.c | 210 |
1 files changed, 155 insertions, 55 deletions
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 783890e8d43a..9355213dc883 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -70,6 +70,7 @@ static const struct debugfs_reg32 crtc_regs[] = { static unsigned int vc4_crtc_get_cob_allocation(struct vc4_dev *vc4, unsigned int channel) { + struct vc4_hvs *hvs = vc4->hvs; u32 dispbase = HVS_READ(SCALER_DISPBASEX(channel)); /* Top/base are supposed to be 4-pixel aligned, but the * Raspberry Pi firmware fills the low bits (which are @@ -89,6 +90,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc, { struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state); unsigned int cob_size; @@ -123,7 +125,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc, *vpos /= 2; /* Use hpos to correct for field offset in interlaced mode. */ - if (VC4_GET_FIELD(val, SCALER_DISPSTATX_FRAME_COUNT) % 2) + if (vc4_hvs_get_fifo_frame_count(hvs, vc4_crtc_state->assigned_channel) % 2) *hpos += mode->crtc_htotal / 2; } @@ -254,7 +256,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) * Removing 1 from the FIFO full level however * seems to completely remove that issue. */ - if (!vc4->hvs->hvs5) + if (!vc4->is_vc5) return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1; return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX; @@ -387,7 +389,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_encoder *encode if (is_dsi) CRTC_WRITE(PV_HACT_ACT, mode->hdisplay * pixel_rep); - if (vc4->hvs->hvs5) + if (vc4->is_vc5) CRTC_WRITE(PV_MUX_CFG, VC4_SET_FIELD(PV_MUX_CFG_RGB_PIXEL_MUX_MODE_NO_SWAP, PV_MUX_CFG_RGB_PIXEL_MUX_MODE)); @@ -413,6 +415,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_encoder *encode static void require_hvs_enabled(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; WARN_ON_ONCE((HVS_READ(SCALER_DISPCTRL) & SCALER_DISPCTRL_ENABLE) != SCALER_DISPCTRL_ENABLE); @@ -426,6 +429,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc, struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); int ret; CRTC_WRITE(PV_V_CONTROL, @@ -455,7 +459,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc, vc4_encoder->post_crtc_disable(encoder, state); vc4_crtc_pixelvalve_reset(crtc); - vc4_hvs_stop_channel(dev, channel); + vc4_hvs_stop_channel(vc4->hvs, channel); if (vc4_encoder && vc4_encoder->post_crtc_powerdown) vc4_encoder->post_crtc_powerdown(encoder, state); @@ -481,6 +485,7 @@ static struct drm_encoder *vc4_crtc_get_encoder_by_type(struct drm_crtc *crtc, int vc4_crtc_disable_at_boot(struct drm_crtc *crtc) { struct drm_device *drm = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(drm); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); enum vc4_encoder_type encoder_type; const struct vc4_pv_data *pv_data; @@ -502,7 +507,7 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc) if (!(CRTC_READ(PV_V_CONTROL) & PV_VCONTROL_VIDEN)) return 0; - channel = vc4_hvs_get_fifo_from_output(drm, vc4_crtc->data->hvs_output); + channel = vc4_hvs_get_fifo_from_output(vc4->hvs, vc4_crtc->data->hvs_output); if (channel < 0) return 0; @@ -717,6 +722,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc) struct drm_crtc *crtc = &vc4_crtc->base; struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; u32 chan = vc4_crtc->current_hvs_channel; unsigned long flags; @@ -735,7 +741,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc) * the CRTC and encoder already reconfigured, leading to * underruns. This can be seen when reconfiguring the CRTC. */ - vc4_hvs_unmask_underrun(dev, chan); + vc4_hvs_unmask_underrun(hvs, chan); } spin_unlock(&vc4_crtc->irq_lock); spin_unlock_irqrestore(&dev->event_lock, flags); @@ -769,17 +775,18 @@ struct vc4_async_flip_state { struct drm_framebuffer *old_fb; struct drm_pending_vblank_event *event; - struct vc4_seqno_cb cb; + union { + struct dma_fence_cb fence; + struct vc4_seqno_cb seqno; + } cb; }; /* Called when the V3D execution for the BO being flipped to is done, so that * we can actually update the plane's address to point to it. */ static void -vc4_async_page_flip_complete(struct vc4_seqno_cb *cb) +vc4_async_page_flip_complete(struct vc4_async_flip_state *flip_state) { - struct vc4_async_flip_state *flip_state = - container_of(cb, struct vc4_async_flip_state, cb); struct drm_crtc *crtc = flip_state->crtc; struct drm_device *dev = crtc->dev; struct drm_plane *plane = crtc->primary; @@ -796,59 +803,96 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb) drm_crtc_vblank_put(crtc); drm_framebuffer_put(flip_state->fb); - /* Decrement the BO usecnt in order to keep the inc/dec calls balanced - * when the planes are updated through the async update path. - * FIXME: we should move to generic async-page-flip when it's - * available, so that we can get rid of this hand-made cleanup_fb() - * logic. - */ - if (flip_state->old_fb) { - struct drm_gem_cma_object *cma_bo; - struct vc4_bo *bo; + if (flip_state->old_fb) + drm_framebuffer_put(flip_state->old_fb); + + kfree(flip_state); +} + +static void vc4_async_page_flip_seqno_complete(struct vc4_seqno_cb *cb) +{ + struct vc4_async_flip_state *flip_state = + container_of(cb, struct vc4_async_flip_state, cb.seqno); + struct vc4_bo *bo = NULL; - cma_bo = drm_fb_cma_get_gem_obj(flip_state->old_fb, 0); + if (flip_state->old_fb) { + struct drm_gem_cma_object *cma_bo = + drm_fb_cma_get_gem_obj(flip_state->old_fb, 0); bo = to_vc4_bo(&cma_bo->base); - vc4_bo_dec_usecnt(bo); - drm_framebuffer_put(flip_state->old_fb); } - kfree(flip_state); + vc4_async_page_flip_complete(flip_state); + + /* + * Decrement the BO usecnt in order to keep the inc/dec + * calls balanced when the planes are updated through + * the async update path. + * + * FIXME: we should move to generic async-page-flip when + * it's available, so that we can get rid of this + * hand-made cleanup_fb() logic. + */ + if (bo) + vc4_bo_dec_usecnt(bo); } -/* Implements async (non-vblank-synced) page flips. - * - * The page flip ioctl needs to return immediately, so we grab the - * modeset semaphore on the pipe, and queue the address update for - * when V3D is done with the BO being flipped to. - */ -static int vc4_async_page_flip(struct drm_crtc *crtc, - struct drm_framebuffer *fb, - struct drm_pending_vblank_event *event, - uint32_t flags) +static void vc4_async_page_flip_fence_complete(struct dma_fence *fence, + struct dma_fence_cb *cb) { - struct drm_device *dev = crtc->dev; - struct drm_plane *plane = crtc->primary; - int ret = 0; - struct vc4_async_flip_state *flip_state; + struct vc4_async_flip_state *flip_state = + container_of(cb, struct vc4_async_flip_state, cb.fence); + + vc4_async_page_flip_complete(flip_state); + dma_fence_put(fence); +} + +static int vc4_async_set_fence_cb(struct drm_device *dev, + struct vc4_async_flip_state *flip_state) +{ + struct drm_framebuffer *fb = flip_state->fb; struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0); - struct vc4_bo *bo = to_vc4_bo(&cma_bo->base); + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct dma_fence *fence; + int ret; - /* Increment the BO usecnt here, so that we never end up with an - * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the - * plane is later updated through the non-async path. - * FIXME: we should move to generic async-page-flip when it's - * available, so that we can get rid of this hand-made prepare_fb() - * logic. - */ - ret = vc4_bo_inc_usecnt(bo); + if (!vc4->is_vc5) { + struct vc4_bo *bo = to_vc4_bo(&cma_bo->base); + + return vc4_queue_seqno_cb(dev, &flip_state->cb.seqno, bo->seqno, + vc4_async_page_flip_seqno_complete); + } + + ret = dma_resv_get_singleton(cma_bo->base.resv, DMA_RESV_USAGE_READ, &fence); if (ret) return ret; + /* If there's no fence, complete the page flip immediately */ + if (!fence) { + vc4_async_page_flip_fence_complete(fence, &flip_state->cb.fence); + return 0; + } + + /* If the fence has already been completed, complete the page flip */ + if (dma_fence_add_callback(fence, &flip_state->cb.fence, + vc4_async_page_flip_fence_complete)) + vc4_async_page_flip_fence_complete(fence, &flip_state->cb.fence); + + return 0; +} + +static int +vc4_async_page_flip_common(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t flags) +{ + struct drm_device *dev = crtc->dev; + struct drm_plane *plane = crtc->primary; + struct vc4_async_flip_state *flip_state; + flip_state = kzalloc(sizeof(*flip_state), GFP_KERNEL); - if (!flip_state) { - vc4_bo_dec_usecnt(bo); + if (!flip_state) return -ENOMEM; - } drm_framebuffer_get(fb); flip_state->fb = fb; @@ -875,23 +919,79 @@ static int vc4_async_page_flip(struct drm_crtc *crtc, */ drm_atomic_set_fb_for_plane(plane->state, fb); - vc4_queue_seqno_cb(dev, &flip_state->cb, bo->seqno, - vc4_async_page_flip_complete); + vc4_async_set_fence_cb(dev, flip_state); /* Driver takes ownership of state on successful async commit. */ return 0; } +/* Implements async (non-vblank-synced) page flips. + * + * The page flip ioctl needs to return immediately, so we grab the + * modeset semaphore on the pipe, and queue the address update for + * when V3D is done with the BO being flipped to. + */ +static int vc4_async_page_flip(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t flags) +{ + struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0); + struct vc4_bo *bo = to_vc4_bo(&cma_bo->base); + int ret; + + if (WARN_ON_ONCE(vc4->is_vc5)) + return -ENODEV; + + /* + * Increment the BO usecnt here, so that we never end up with an + * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the + * plane is later updated through the non-async path. + * + * FIXME: we should move to generic async-page-flip when + * it's available, so that we can get rid of this + * hand-made prepare_fb() logic. + */ + ret = vc4_bo_inc_usecnt(bo); + if (ret) + return ret; + + ret = vc4_async_page_flip_common(crtc, fb, event, flags); + if (ret) { + vc4_bo_dec_usecnt(bo); + return ret; + } + + return 0; +} + +static int vc5_async_page_flip(struct drm_crtc *crtc, + struct drm_framebuffer *fb, + struct drm_pending_vblank_event *event, + uint32_t flags) +{ + return vc4_async_page_flip_common(crtc, fb, event, flags); +} + int vc4_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event, uint32_t flags, struct drm_modeset_acquire_ctx *ctx) { - if (flags & DRM_MODE_PAGE_FLIP_ASYNC) - return vc4_async_page_flip(crtc, fb, event, flags); - else + if (flags & DRM_MODE_PAGE_FLIP_ASYNC) { + struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (vc4->is_vc5) + return vc5_async_page_flip(crtc, fb, event, flags); + else + return vc4_async_page_flip(crtc, fb, event, flags); + } else { return drm_atomic_helper_page_flip(crtc, fb, event, flags, ctx); + } } struct drm_crtc_state *vc4_crtc_duplicate_state(struct drm_crtc *crtc) @@ -1143,7 +1243,7 @@ int vc4_crtc_init(struct drm_device *drm, struct vc4_crtc *vc4_crtc, crtc_funcs, NULL); drm_crtc_helper_add(crtc, crtc_helper_funcs); - if (!vc4->hvs->hvs5) { + if (!vc4->is_vc5) { drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r)); drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size); |