diff options
Diffstat (limited to 'drivers/gpu/drm/vc4/vc4_plane.c')
| -rw-r--r-- | drivers/gpu/drm/vc4/vc4_plane.c | 92 |
1 files changed, 71 insertions, 21 deletions
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index d098337c10e9..4934127f0d76 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015 Broadcom - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /** @@ -20,11 +17,14 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_atomic_uapi.h> #include <drm/drm_fb_cma_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_plane_helper.h> -#include <drm/drm_atomic_uapi.h> #include "uapi/drm/vc4_drm.h" + #include "vc4_drv.h" #include "vc4_regs.h" @@ -178,7 +178,7 @@ static void vc4_plane_destroy_state(struct drm_plane *plane, struct vc4_dev *vc4 = to_vc4_dev(plane->dev); struct vc4_plane_state *vc4_state = to_vc4_plane_state(state); - if (vc4_state->lbm.allocated) { + if (drm_mm_node_allocated(&vc4_state->lbm)) { unsigned long irqflags; spin_lock_irqsave(&vc4->hvs->mm_lock, irqflags); @@ -310,10 +310,10 @@ 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, @@ -328,9 +328,6 @@ 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]; @@ -488,6 +485,61 @@ static void vc4_write_scaling_parameters(struct drm_plane_state *state, } } +static void vc4_plane_calc_load(struct drm_plane_state *state) +{ + unsigned int hvs_load_shift, vrefresh, i; + struct drm_framebuffer *fb = state->fb; + struct vc4_plane_state *vc4_state; + struct drm_crtc_state *crtc_state; + unsigned int vscale_factor; + + vc4_state = to_vc4_plane_state(state); + crtc_state = drm_atomic_get_existing_crtc_state(state->state, + state->crtc); + vrefresh = drm_mode_vrefresh(&crtc_state->adjusted_mode); + + /* The HVS is able to process 2 pixels/cycle when scaling the source, + * 4 pixels/cycle otherwise. + * Alpha blending step seems to be pipelined and it's always operating + * at 4 pixels/cycle, so the limiting aspect here seems to be the + * scaler block. + * HVS load is expressed in clk-cycles/sec (AKA Hz). + */ + if (vc4_state->x_scaling[0] != VC4_SCALING_NONE || + vc4_state->x_scaling[1] != VC4_SCALING_NONE || + vc4_state->y_scaling[0] != VC4_SCALING_NONE || + vc4_state->y_scaling[1] != VC4_SCALING_NONE) + hvs_load_shift = 1; + else + hvs_load_shift = 2; + + vc4_state->membus_load = 0; + vc4_state->hvs_load = 0; + for (i = 0; i < fb->format->num_planes; i++) { + /* Even if the bandwidth/plane required for a single frame is + * + * vc4_state->src_w[i] * vc4_state->src_h[i] * cpp * vrefresh + * + * when downscaling, we have to read more pixels per line in + * the time frame reserved for a single line, so the bandwidth + * demand can be punctually higher. To account for that, we + * calculate the down-scaling factor and multiply the plane + * load by this number. We're likely over-estimating the read + * demand, but that's better than under-estimating it. + */ + vscale_factor = DIV_ROUND_UP(vc4_state->src_h[i], + vc4_state->crtc_h); + vc4_state->membus_load += vc4_state->src_w[i] * + vc4_state->src_h[i] * vscale_factor * + fb->format->cpp[i]; + vc4_state->hvs_load += vc4_state->crtc_h * vc4_state->crtc_w; + } + + vc4_state->hvs_load *= vrefresh; + vc4_state->hvs_load >>= hvs_load_shift; + vc4_state->membus_load *= vrefresh; +} + static int vc4_plane_allocate_lbm(struct drm_plane_state *state) { struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev); @@ -505,7 +557,7 @@ static int vc4_plane_allocate_lbm(struct drm_plane_state *state) /* Allocate the LBM memory that the HVS will use for temporary * storage due to our scaling/format conversion. */ - if (!vc4_state->lbm.allocated) { + if (!drm_mm_node_allocated(&vc4_state->lbm)) { int ret; spin_lock_irqsave(&vc4->hvs->mm_lock, irqflags); @@ -537,8 +589,9 @@ 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; @@ -568,9 +621,6 @@ 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 | @@ -875,6 +925,8 @@ static int vc4_plane_mode_set(struct drm_plane *plane, */ vc4_state->dlist_initialized = 1; + vc4_plane_calc_load(state); + return 0; } @@ -968,7 +1020,7 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane, { struct vc4_plane_state *vc4_state, *new_vc4_state; - drm_atomic_set_fb_for_plane(plane->state, state->fb); + swap(plane->state->fb, state->fb); plane->state->crtc_x = state->crtc_x; plane->state->crtc_y = state->crtc_y; plane->state->crtc_w = state->crtc_w; @@ -1074,7 +1126,6 @@ static int vc4_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) { struct vc4_bo *bo; - struct dma_fence *fence; int ret; if (!state->fb) @@ -1082,8 +1133,7 @@ static int vc4_prepare_fb(struct drm_plane *plane, bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base); - fence = reservation_object_get_excl_rcu(bo->resv); - drm_atomic_set_fence_for_plane(state, fence); + drm_gem_fb_prepare_fb(plane, state); if (plane->state->fb == state->fb) return 0; |