diff options
Diffstat (limited to 'drivers/gpu/drm/tegra')
36 files changed, 4974 insertions, 1138 deletions
diff --git a/drivers/gpu/drm/tegra/Kconfig b/drivers/gpu/drm/tegra/Kconfig index 5043dcaf1cf9..8a3b16aac5d6 100644 --- a/drivers/gpu/drm/tegra/Kconfig +++ b/drivers/gpu/drm/tegra/Kconfig @@ -1,16 +1,27 @@ # SPDX-License-Identifier: GPL-2.0-only config DRM_TEGRA tristate "NVIDIA Tegra DRM" - depends on ARCH_TEGRA || (ARM && COMPILE_TEST) + depends on ARCH_TEGRA || COMPILE_TEST depends on COMMON_CLK depends on DRM depends on OF + select DRM_CLIENT_SELECTION + select DRM_DISPLAY_DP_HELPER + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HELPER + select DRM_BRIDGE_CONNECTOR + select DRM_DISPLAY_DP_AUX_BUS select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL + select FB_DMAMEM_HELPERS if DRM_FBDEV_EMULATION select TEGRA_HOST1X + select INTERCONNECT select IOMMU_IOVA select CEC_CORE if CEC_NOTIFIER + select SND_SIMPLE_CARD if SND_SOC_TEGRA20_SPDIF + select SND_SOC_HDMI_CODEC if SND_SOC_TEGRA20_SPDIF + select SND_AUDIO_GRAPH_CARD if SND_SOC_TEGRA20_SPDIF help Choose this option if you have an NVIDIA Tegra SoC. diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile index d6cf202414f0..e399b40d64a1 100644 --- a/drivers/gpu/drm/tegra/Makefile +++ b/drivers/gpu/drm/tegra/Makefile @@ -3,6 +3,9 @@ ccflags-$(CONFIG_DRM_TEGRA_DEBUG) += -DDEBUG tegra-drm-y := \ drm.o \ + uapi.o \ + submit.o \ + firewall.o \ gem.o \ fb.o \ dp.o \ @@ -20,8 +23,13 @@ tegra-drm-y := \ gr2d.o \ gr3d.o \ falcon.o \ - vic.o + vic.o \ + nvdec.o \ + nvjpg.o \ + riscv.o tegra-drm-y += trace.o +tegra-drm-$(CONFIG_DRM_FBDEV_EMULATION) += fbdev.o + obj-$(CONFIG_DRM_TEGRA) += tegra-drm.o diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 51bbbc42a144..01e9d5011dd8 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -7,19 +7,27 @@ #include <linux/clk.h> #include <linux/debugfs.h> #include <linux/delay.h> +#include <linux/dma-mapping.h> #include <linux/iommu.h> +#include <linux/interconnect.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_opp.h> #include <linux/pm_runtime.h> #include <linux/reset.h> +#include <soc/tegra/common.h> #include <soc/tegra/pmc.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_blend.h> #include <drm/drm_debugfs.h> #include <drm/drm_fourcc.h> -#include <drm/drm_plane_helper.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_print.h> #include <drm/drm_vblank.h> #include "dc.h" @@ -341,18 +349,19 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, { unsigned h_offset, v_offset, h_size, v_size, h_dda, v_dda, bpp; struct tegra_dc *dc = plane->dc; - bool yuv, planar; + unsigned int planes; u32 value; + bool yuv; /* * For YUV planar modes, the number of bytes per pixel takes into * account only the luma component and therefore is 1. */ - yuv = tegra_plane_format_is_yuv(window->format, &planar, NULL); + yuv = tegra_plane_format_is_yuv(window->format, &planes, NULL); if (!yuv) bpp = window->bits_per_pixel / 8; else - bpp = planar ? 1 : 2; + bpp = (planes > 1) ? 1 : 2; tegra_plane_writel(plane, window->format, DC_WIN_COLOR_DEPTH); tegra_plane_writel(plane, window->swap, DC_WIN_BYTE_SWAP); @@ -381,7 +390,7 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, * For DDA computations the number of bytes per pixel for YUV planar * modes needs to take into account all Y, U and V components. */ - if (yuv && planar) + if (yuv && planes > 1) bpp = 2; h_dda = compute_dda_inc(window->src.w, window->dst.w, false, bpp); @@ -401,9 +410,12 @@ static void tegra_dc_setup_window(struct tegra_plane *plane, tegra_plane_writel(plane, window->base[0], DC_WINBUF_START_ADDR); - if (yuv && planar) { + if (yuv && planes > 1) { tegra_plane_writel(plane, window->base[1], DC_WINBUF_START_ADDR_U); - tegra_plane_writel(plane, window->base[2], DC_WINBUF_START_ADDR_V); + + if (planes > 2) + tegra_plane_writel(plane, window->base[2], DC_WINBUF_START_ADDR_V); + value = window->stride[1] << 16 | window->stride[0]; tegra_plane_writel(plane, value, DC_WIN_LINE_STRIDE); } else { @@ -618,9 +630,14 @@ static int tegra_plane_atomic_check(struct drm_plane *plane, struct tegra_dc *dc = to_tegra_dc(new_plane_state->crtc); int err; + plane_state->peak_memory_bandwidth = 0; + plane_state->avg_memory_bandwidth = 0; + /* no need for further checks if the plane is being disabled */ - if (!new_plane_state->crtc) + if (!new_plane_state->crtc) { + plane_state->total_peak_memory_bandwidth = 0; return 0; + } err = tegra_plane_format(new_plane_state->fb->format->format, &plane_state->format, @@ -808,6 +825,12 @@ static struct drm_plane *tegra_primary_plane_create(struct drm_device *drm, formats = dc->soc->primary_formats; modifiers = dc->soc->modifiers; + err = tegra_plane_interconnect_init(plane); + if (err) { + kfree(plane); + return ERR_PTR(err); + } + err = drm_universal_plane_init(drm, &plane->base, possible_crtcs, &tegra_plane_funcs, formats, num_formats, modifiers, type, NULL); @@ -845,12 +868,18 @@ static int tegra_cursor_atomic_check(struct drm_plane *plane, { struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); + struct tegra_plane_state *plane_state = to_tegra_plane_state(new_plane_state); struct tegra_plane *tegra = to_tegra_plane(plane); int err; + plane_state->peak_memory_bandwidth = 0; + plane_state->avg_memory_bandwidth = 0; + /* no need for further checks if the plane is being disabled */ - if (!new_plane_state->crtc) + if (!new_plane_state->crtc) { + plane_state->total_peak_memory_bandwidth = 0; return 0; + } /* scaling not supported for cursor */ if ((new_plane_state->src_w >> 16 != new_plane_state->crtc_w) || @@ -872,11 +901,9 @@ static int tegra_cursor_atomic_check(struct drm_plane *plane, return 0; } -static void tegra_cursor_atomic_update(struct drm_plane *plane, - struct drm_atomic_state *state) +static void __tegra_cursor_atomic_update(struct drm_plane *plane, + struct drm_plane_state *new_state) { - struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, - plane); struct tegra_plane_state *tegra_plane_state = to_tegra_plane_state(new_state); struct tegra_dc *dc = to_tegra_dc(new_state->crtc); struct tegra_drm *tegra = plane->dev->dev_private; @@ -972,6 +999,14 @@ static void tegra_cursor_atomic_update(struct drm_plane *plane, tegra_dc_writel(dc, value, DC_DISP_CURSOR_POSITION); } +static void tegra_cursor_atomic_update(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); + + __tegra_cursor_atomic_update(plane, new_state); +} + static void tegra_cursor_atomic_disable(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -991,12 +1026,79 @@ static void tegra_cursor_atomic_disable(struct drm_plane *plane, tegra_dc_writel(dc, value, DC_DISP_DISP_WIN_OPTIONS); } +static int tegra_cursor_atomic_async_check(struct drm_plane *plane, struct drm_atomic_state *state, + bool flip) +{ + struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); + struct drm_crtc_state *crtc_state; + int min_scale, max_scale; + int err; + + crtc_state = drm_atomic_get_new_crtc_state(state, new_state->crtc); + if (WARN_ON(!crtc_state)) + return -EINVAL; + + if (!crtc_state->active) + return -EINVAL; + + if (plane->state->crtc != new_state->crtc || + plane->state->src_w != new_state->src_w || + plane->state->src_h != new_state->src_h || + plane->state->crtc_w != new_state->crtc_w || + plane->state->crtc_h != new_state->crtc_h || + plane->state->fb != new_state->fb || + plane->state->fb == NULL) + return -EINVAL; + + min_scale = (1 << 16) / 8; + max_scale = (8 << 16) / 1; + + err = drm_atomic_helper_check_plane_state(new_state, crtc_state, min_scale, max_scale, + true, true); + if (err < 0) + return err; + + if (new_state->visible != plane->state->visible) + return -EINVAL; + + return 0; +} + +static void tegra_cursor_atomic_async_update(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); + struct tegra_dc *dc = to_tegra_dc(new_state->crtc); + + plane->state->src_x = new_state->src_x; + plane->state->src_y = new_state->src_y; + plane->state->crtc_x = new_state->crtc_x; + plane->state->crtc_y = new_state->crtc_y; + + if (new_state->visible) { + struct tegra_plane *p = to_tegra_plane(plane); + u32 value; + + __tegra_cursor_atomic_update(plane, new_state); + + value = (WIN_A_ACT_REQ << p->index) << 8 | GENERAL_UPDATE; + tegra_dc_writel(dc, value, DC_CMD_STATE_CONTROL); + (void)tegra_dc_readl(dc, DC_CMD_STATE_CONTROL); + + value = (WIN_A_ACT_REQ << p->index) | GENERAL_ACT_REQ; + tegra_dc_writel(dc, value, DC_CMD_STATE_CONTROL); + (void)tegra_dc_readl(dc, DC_CMD_STATE_CONTROL); + } +} + static const struct drm_plane_helper_funcs tegra_cursor_plane_helper_funcs = { .prepare_fb = tegra_plane_prepare_fb, .cleanup_fb = tegra_plane_cleanup_fb, .atomic_check = tegra_cursor_atomic_check, .atomic_update = tegra_cursor_atomic_update, .atomic_disable = tegra_cursor_atomic_disable, + .atomic_async_check = tegra_cursor_atomic_async_check, + .atomic_async_update = tegra_cursor_atomic_async_update, }; static const uint64_t linear_modifiers[] = { @@ -1030,6 +1132,12 @@ static struct drm_plane *tegra_dc_cursor_plane_create(struct drm_device *drm, if (!dc->soc->has_nvdisplay) { num_formats = ARRAY_SIZE(tegra_legacy_cursor_plane_formats); formats = tegra_legacy_cursor_plane_formats; + + err = tegra_plane_interconnect_init(plane); + if (err) { + kfree(plane); + return ERR_PTR(err); + } } else { num_formats = ARRAY_SIZE(tegra_cursor_plane_formats); formats = tegra_cursor_plane_formats; @@ -1094,6 +1202,13 @@ static const u32 tegra114_overlay_formats[] = { DRM_FORMAT_YUYV, DRM_FORMAT_YUV420, DRM_FORMAT_YUV422, + /* semi-planar formats */ + DRM_FORMAT_NV12, + DRM_FORMAT_NV21, + DRM_FORMAT_NV16, + DRM_FORMAT_NV61, + DRM_FORMAT_NV24, + DRM_FORMAT_NV42, }; static const u32 tegra124_overlay_formats[] = { @@ -1122,8 +1237,18 @@ static const u32 tegra124_overlay_formats[] = { /* planar formats */ DRM_FORMAT_UYVY, DRM_FORMAT_YUYV, - DRM_FORMAT_YUV420, - DRM_FORMAT_YUV422, + DRM_FORMAT_YVYU, + DRM_FORMAT_VYUY, + DRM_FORMAT_YUV420, /* YU12 */ + DRM_FORMAT_YUV422, /* YU16 */ + DRM_FORMAT_YUV444, /* YU24 */ + /* semi-planar formats */ + DRM_FORMAT_NV12, + DRM_FORMAT_NV21, + DRM_FORMAT_NV16, + DRM_FORMAT_NV61, + DRM_FORMAT_NV24, + DRM_FORMAT_NV42, }; static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, @@ -1149,6 +1274,12 @@ static struct drm_plane *tegra_dc_overlay_plane_create(struct drm_device *drm, num_formats = dc->soc->num_overlay_formats; formats = dc->soc->overlay_formats; + err = tegra_plane_interconnect_init(plane); + if (err) { + kfree(plane); + return ERR_PTR(err); + } + if (!cursor) type = DRM_PLANE_TYPE_OVERLAY; else @@ -1191,10 +1322,16 @@ static struct drm_plane *tegra_dc_add_shared_planes(struct drm_device *drm, if (wgrp->dc == dc->pipe) { for (j = 0; j < wgrp->num_windows; j++) { unsigned int index = wgrp->windows[j]; + enum drm_plane_type type; + + if (primary) + type = DRM_PLANE_TYPE_OVERLAY; + else + type = DRM_PLANE_TYPE_PRIMARY; plane = tegra_shared_plane_create(drm, dc, wgrp->index, - index); + index, type); if (IS_ERR(plane)) return plane; @@ -1202,10 +1339,8 @@ static struct drm_plane *tegra_dc_add_shared_planes(struct drm_device *drm, * Choose the first shared plane owned by this * head as the primary plane. */ - if (!primary) { - plane->type = DRM_PLANE_TYPE_PRIMARY; + if (!primary) primary = plane; - } } } } @@ -1237,9 +1372,9 @@ static struct drm_plane *tegra_dc_add_planes(struct drm_device *drm, err = PTR_ERR(planes[i]); while (i--) - tegra_plane_funcs.destroy(planes[i]); + planes[i]->funcs->destroy(planes[i]); - tegra_plane_funcs.destroy(primary); + primary->funcs->destroy(primary); return ERR_PTR(err); } } @@ -1259,7 +1394,10 @@ static void tegra_crtc_reset(struct drm_crtc *crtc) if (crtc->state) tegra_crtc_atomic_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &state->base); + if (state) + __drm_atomic_helper_crtc_reset(crtc, &state->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } static struct drm_crtc_state * @@ -1572,6 +1710,11 @@ static int tegra_dc_show_stats(struct seq_file *s, void *data) seq_printf(s, "underflow: %lu\n", dc->stats.underflow); seq_printf(s, "overflow: %lu\n", dc->stats.overflow); + seq_printf(s, "frames total: %lu\n", dc->stats.frames_total); + seq_printf(s, "vblank total: %lu\n", dc->stats.vblank_total); + seq_printf(s, "underflow total: %lu\n", dc->stats.underflow_total); + seq_printf(s, "overflow total: %lu\n", dc->stats.overflow_total); + return 0; } @@ -1612,8 +1755,15 @@ static void tegra_dc_early_unregister(struct drm_crtc *crtc) unsigned int count = ARRAY_SIZE(debugfs_files); struct drm_minor *minor = crtc->dev->primary; struct tegra_dc *dc = to_tegra_dc(crtc); + struct dentry *root; - drm_debugfs_remove_files(dc->debugfs_files, count, minor); +#ifdef CONFIG_DEBUG_FS + root = crtc->debugfs_entry; +#else + root = NULL; +#endif + + drm_debugfs_remove_files(dc->debugfs_files, count, root, minor); kfree(dc->debugfs_files); dc->debugfs_files = NULL; } @@ -1727,10 +1877,55 @@ int tegra_dc_state_setup_clock(struct tegra_dc *dc, return 0; } -static void tegra_dc_commit_state(struct tegra_dc *dc, - struct tegra_dc_state *state) +static void tegra_dc_update_voltage_state(struct tegra_dc *dc, + struct tegra_dc_state *state) +{ + unsigned long rate, pstate; + struct dev_pm_opp *opp; + int err; + + if (!dc->has_opp_table) + return; + + /* calculate actual pixel clock rate which depends on internal divider */ + rate = DIV_ROUND_UP(clk_get_rate(dc->clk) * 2, state->div + 2); + + /* find suitable OPP for the rate */ + opp = dev_pm_opp_find_freq_ceil(dc->dev, &rate); + + /* + * Very high resolution modes may results in a clock rate that is + * above the characterized maximum. In this case it's okay to fall + * back to the characterized maximum. + */ + if (opp == ERR_PTR(-ERANGE)) + opp = dev_pm_opp_find_freq_floor(dc->dev, &rate); + + if (IS_ERR(opp)) { + dev_err(dc->dev, "failed to find OPP for %luHz: %pe\n", + rate, opp); + return; + } + + pstate = dev_pm_opp_get_required_pstate(opp, 0); + dev_pm_opp_put(opp); + + /* + * The minimum core voltage depends on the pixel clock rate (which + * depends on internal clock divider of the CRTC) and not on the + * rate of the display controller clock. This is why we're not using + * dev_pm_opp_set_rate() API and instead controlling the power domain + * directly. + */ + err = dev_pm_genpd_set_performance_state(dc->dev, pstate); + if (err) + dev_err(dc->dev, "failed to set power domain state to %lu: %d\n", + pstate, err); +} + +static void tegra_dc_set_clock_rate(struct tegra_dc *dc, + struct tegra_dc_state *state) { - u32 value; int err; err = clk_set_parent(dc->clk, state->clk); @@ -1762,10 +1957,7 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, state->div); DRM_DEBUG_KMS("pclk: %lu\n", state->pclk); - if (!dc->soc->has_nvdisplay) { - value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1; - tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL); - } + tegra_dc_update_voltage_state(dc, state); } static void tegra_dc_stop(struct tegra_dc *dc) @@ -1804,6 +1996,103 @@ static int tegra_dc_wait_idle(struct tegra_dc *dc, unsigned long timeout) return -ETIMEDOUT; } +static void +tegra_crtc_update_memory_bandwidth(struct drm_crtc *crtc, + struct drm_atomic_state *state, + bool prepare_bandwidth_transition) +{ + const struct tegra_plane_state *old_tegra_state, *new_tegra_state; + u32 i, new_avg_bw, old_avg_bw, new_peak_bw, old_peak_bw; + const struct drm_plane_state *old_plane_state; + const struct drm_crtc_state *old_crtc_state; + struct tegra_dc_window window, old_window; + struct tegra_dc *dc = to_tegra_dc(crtc); + struct tegra_plane *tegra; + struct drm_plane *plane; + + if (dc->soc->has_nvdisplay) + return; + + old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); + + if (!crtc->state->active) { + if (!old_crtc_state->active) + return; + + /* + * When CRTC is disabled on DPMS, the state of attached planes + * is kept unchanged. Hence we need to enforce removal of the + * bandwidths from the ICC paths. + */ + drm_atomic_crtc_for_each_plane(plane, crtc) { + tegra = to_tegra_plane(plane); + + icc_set_bw(tegra->icc_mem, 0, 0); + icc_set_bw(tegra->icc_mem_vfilter, 0, 0); + } + + return; + } + + for_each_old_plane_in_state(old_crtc_state->state, plane, + old_plane_state, i) { + old_tegra_state = to_const_tegra_plane_state(old_plane_state); + new_tegra_state = to_const_tegra_plane_state(plane->state); + tegra = to_tegra_plane(plane); + + /* + * We're iterating over the global atomic state and it contains + * planes from another CRTC, hence we need to filter out the + * planes unrelated to this CRTC. + */ + if (tegra->dc != dc) + continue; + + new_avg_bw = new_tegra_state->avg_memory_bandwidth; + old_avg_bw = old_tegra_state->avg_memory_bandwidth; + + new_peak_bw = new_tegra_state->total_peak_memory_bandwidth; + old_peak_bw = old_tegra_state->total_peak_memory_bandwidth; + + /* + * See the comment related to !crtc->state->active above, + * which explains why bandwidths need to be updated when + * CRTC is turning ON. + */ + if (new_avg_bw == old_avg_bw && new_peak_bw == old_peak_bw && + old_crtc_state->active) + continue; + + window.src.h = drm_rect_height(&plane->state->src) >> 16; + window.dst.h = drm_rect_height(&plane->state->dst); + + old_window.src.h = drm_rect_height(&old_plane_state->src) >> 16; + old_window.dst.h = drm_rect_height(&old_plane_state->dst); + + /* + * During the preparation phase (atomic_begin), the memory + * freq should go high before the DC changes are committed + * if bandwidth requirement goes up, otherwise memory freq + * should to stay high if BW requirement goes down. The + * opposite applies to the completion phase (post_commit). + */ + if (prepare_bandwidth_transition) { + new_avg_bw = max(old_avg_bw, new_avg_bw); + new_peak_bw = max(old_peak_bw, new_peak_bw); + + if (tegra_plane_use_vertical_filtering(tegra, &old_window)) + window = old_window; + } + + icc_set_bw(tegra->icc_mem, new_avg_bw, new_peak_bw); + + if (tegra_plane_use_vertical_filtering(tegra, &window)) + icc_set_bw(tegra->icc_mem_vfilter, new_avg_bw, new_peak_bw); + else + icc_set_bw(tegra->icc_mem_vfilter, 0, 0); + } +} + static void tegra_crtc_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1859,6 +2148,13 @@ static void tegra_crtc_atomic_disable(struct drm_crtc *crtc, err = host1x_client_suspend(&dc->client); if (err < 0) dev_err(dc->dev, "failed to suspend: %d\n", err); + + if (dc->has_opp_table) { + err = dev_pm_genpd_set_performance_state(dc->dev, 0); + if (err) + dev_err(dc->dev, + "failed to clear power domain state: %d\n", err); + } } static void tegra_crtc_atomic_enable(struct drm_crtc *crtc, @@ -1870,6 +2166,9 @@ static void tegra_crtc_atomic_enable(struct drm_crtc *crtc, u32 value; int err; + /* apply PLL changes */ + tegra_dc_set_clock_rate(dc, crtc_state); + err = host1x_client_resume(&dc->client); if (err < 0) { dev_err(dc->dev, "failed to resume: %d\n", err); @@ -1944,8 +2243,11 @@ static void tegra_crtc_atomic_enable(struct drm_crtc *crtc, else tegra_dc_writel(dc, 0, DC_DISP_BORDER_COLOR); - /* apply PLL and pixel clock changes */ - tegra_dc_commit_state(dc, crtc_state); + /* apply pixel clock changes */ + if (!dc->soc->has_nvdisplay) { + value = SHIFT_CLK_DIVIDER(crtc_state->div) | PIXEL_CLK_DIVIDER_PCD1; + tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL); + } /* program display mode */ tegra_dc_set_timings(dc, mode); @@ -1975,6 +2277,12 @@ static void tegra_crtc_atomic_enable(struct drm_crtc *crtc, tegra_dc_writel(dc, value, DC_COM_RG_UNDERFLOW); } + if (dc->rgb) { + /* XXX: parameterize? */ + value = SC0_H_QUALIFIER_NONE | SC1_H_QUALIFIER_NONE; + tegra_dc_writel(dc, value, DC_DISP_SHIFT_CLOCK_OPTIONS); + } + tegra_dc_commit(dc); drm_crtc_vblank_on(crtc); @@ -1985,6 +2293,8 @@ static void tegra_crtc_atomic_begin(struct drm_crtc *crtc, { unsigned long flags; + tegra_crtc_update_memory_bandwidth(crtc, state, true); + if (crtc->state->event) { spin_lock_irqsave(&crtc->dev->event_lock, flags); @@ -2017,7 +2327,205 @@ static void tegra_crtc_atomic_flush(struct drm_crtc *crtc, value = tegra_dc_readl(dc, DC_CMD_STATE_CONTROL); } +static bool tegra_plane_is_cursor(const struct drm_plane_state *state) +{ + const struct tegra_dc_soc_info *soc = to_tegra_dc(state->crtc)->soc; + const struct drm_format_info *fmt = state->fb->format; + unsigned int src_w = drm_rect_width(&state->src) >> 16; + unsigned int dst_w = drm_rect_width(&state->dst); + + if (state->plane->type != DRM_PLANE_TYPE_CURSOR) + return false; + + if (soc->supports_cursor) + return true; + + if (src_w != dst_w || fmt->num_planes != 1 || src_w * fmt->cpp[0] > 256) + return false; + + return true; +} + +static unsigned long +tegra_plane_overlap_mask(struct drm_crtc_state *state, + const struct drm_plane_state *plane_state) +{ + const struct drm_plane_state *other_state; + const struct tegra_plane *tegra; + unsigned long overlap_mask = 0; + struct drm_plane *plane; + struct drm_rect rect; + + if (!plane_state->visible || !plane_state->fb) + return 0; + + /* + * Data-prefetch FIFO will easily help to overcome temporal memory + * pressure if other plane overlaps with the cursor plane. + */ + if (tegra_plane_is_cursor(plane_state)) + return 0; + + drm_atomic_crtc_state_for_each_plane_state(plane, other_state, state) { + rect = plane_state->dst; + + tegra = to_tegra_plane(other_state->plane); + + if (!other_state->visible || !other_state->fb) + continue; + + /* + * Ignore cursor plane overlaps because it's not practical to + * assume that it contributes to the bandwidth in overlapping + * area if window width is small. + */ + if (tegra_plane_is_cursor(other_state)) + continue; + + if (drm_rect_intersect(&rect, &other_state->dst)) + overlap_mask |= BIT(tegra->index); + } + + return overlap_mask; +} + +static int tegra_crtc_calculate_memory_bandwidth(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + ulong overlap_mask[TEGRA_DC_LEGACY_PLANES_NUM] = {}, mask; + u32 plane_peak_bw[TEGRA_DC_LEGACY_PLANES_NUM] = {}; + bool all_planes_overlap_simultaneously = true; + const struct tegra_plane_state *tegra_state; + const struct drm_plane_state *plane_state; + struct tegra_dc *dc = to_tegra_dc(crtc); + struct drm_crtc_state *new_state; + struct tegra_plane *tegra; + struct drm_plane *plane; + + /* + * The nv-display uses shared planes. The algorithm below assumes + * maximum 3 planes per-CRTC, this assumption isn't applicable to + * the nv-display. Note that T124 support has additional windows, + * but currently they aren't supported by the driver. + */ + if (dc->soc->has_nvdisplay) + return 0; + + new_state = drm_atomic_get_new_crtc_state(state, crtc); + + /* + * For overlapping planes pixel's data is fetched for each plane at + * the same time, hence bandwidths are accumulated in this case. + * This needs to be taken into account for calculating total bandwidth + * consumed by all planes. + * + * Here we get the overlapping state of each plane, which is a + * bitmask of plane indices telling with what planes there is an + * overlap. Note that bitmask[plane] includes BIT(plane) in order + * to make further code nicer and simpler. + */ + drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, new_state) { + tegra_state = to_const_tegra_plane_state(plane_state); + tegra = to_tegra_plane(plane); + + if (WARN_ON_ONCE(tegra->index >= TEGRA_DC_LEGACY_PLANES_NUM)) + return -EINVAL; + + plane_peak_bw[tegra->index] = tegra_state->peak_memory_bandwidth; + mask = tegra_plane_overlap_mask(new_state, plane_state); + overlap_mask[tegra->index] = mask; + + if (hweight_long(mask) != 3) + all_planes_overlap_simultaneously = false; + } + + /* + * Then we calculate maximum bandwidth of each plane state. + * The bandwidth includes the plane BW + BW of the "simultaneously" + * overlapping planes, where "simultaneously" means areas where DC + * fetches from the planes simultaneously during of scan-out process. + * + * For example, if plane A overlaps with planes B and C, but B and C + * don't overlap, then the peak bandwidth will be either in area where + * A-and-B or A-and-C planes overlap. + * + * The plane_peak_bw[] contains peak memory bandwidth values of + * each plane, this information is needed by interconnect provider + * in order to set up latency allowance based on the peak BW, see + * tegra_crtc_update_memory_bandwidth(). + */ + drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, new_state) { + u32 i, old_peak_bw, new_peak_bw, overlap_bw = 0; + + /* + * Note that plane's atomic check doesn't touch the + * total_peak_memory_bandwidth of enabled plane, hence the + * current state contains the old bandwidth state from the + * previous CRTC commit. + */ + tegra_state = to_const_tegra_plane_state(plane_state); + tegra = to_tegra_plane(plane); + + for_each_set_bit(i, &overlap_mask[tegra->index], 3) { + if (i == tegra->index) + continue; + + if (all_planes_overlap_simultaneously) + overlap_bw += plane_peak_bw[i]; + else + overlap_bw = max(overlap_bw, plane_peak_bw[i]); + } + + new_peak_bw = plane_peak_bw[tegra->index] + overlap_bw; + old_peak_bw = tegra_state->total_peak_memory_bandwidth; + + /* + * If plane's peak bandwidth changed (for example plane isn't + * overlapped anymore) and plane isn't in the atomic state, + * then add plane to the state in order to have the bandwidth + * updated. + */ + if (old_peak_bw != new_peak_bw) { + struct tegra_plane_state *new_tegra_state; + struct drm_plane_state *new_plane_state; + + new_plane_state = drm_atomic_get_plane_state(state, plane); + if (IS_ERR(new_plane_state)) + return PTR_ERR(new_plane_state); + + new_tegra_state = to_tegra_plane_state(new_plane_state); + new_tegra_state->total_peak_memory_bandwidth = new_peak_bw; + } + } + + return 0; +} + +static int tegra_crtc_atomic_check(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + int err; + + err = tegra_crtc_calculate_memory_bandwidth(crtc, state); + if (err) + return err; + + return 0; +} + +void tegra_crtc_atomic_post_commit(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + /* + * Display bandwidth is allowed to go down only once hardware state + * is known to be armed, i.e. state was committed and VBLANK event + * received. + */ + tegra_crtc_update_memory_bandwidth(crtc, state, false); +} + static const struct drm_crtc_helper_funcs tegra_crtc_helper_funcs = { + .atomic_check = tegra_crtc_atomic_check, .atomic_begin = tegra_crtc_atomic_begin, .atomic_flush = tegra_crtc_atomic_flush, .atomic_enable = tegra_crtc_atomic_enable, @@ -2036,6 +2544,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data) /* dev_dbg(dc->dev, "%s(): frame end\n", __func__); */ + dc->stats.frames_total++; dc->stats.frames++; } @@ -2044,6 +2553,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data) dev_dbg(dc->dev, "%s(): vertical blank\n", __func__); */ drm_crtc_handle_vblank(&dc->base); + dc->stats.vblank_total++; dc->stats.vblank++; } @@ -2051,6 +2561,7 @@ static irqreturn_t tegra_dc_irq(int irq, void *data) /* dev_dbg(dc->dev, "%s(): underflow\n", __func__); */ + dc->stats.underflow_total++; dc->stats.underflow++; } @@ -2058,11 +2569,13 @@ static irqreturn_t tegra_dc_irq(int irq, void *data) /* dev_dbg(dc->dev, "%s(): overflow\n", __func__); */ + dc->stats.overflow_total++; dc->stats.overflow++; } if (status & HEAD_UF_INT) { dev_dbg_ratelimited(dc->dev, "%s(): head underflow\n", __func__); + dc->stats.underflow_total++; dc->stats.underflow++; } @@ -2343,7 +2856,10 @@ static const struct tegra_dc_soc_info tegra20_dc_soc_info = { .overlay_formats = tegra20_overlay_formats, .modifiers = tegra20_modifiers, .has_win_a_without_filters = true, + .has_win_b_vfilter_mem_client = true, .has_win_c_without_vert_filter = true, + .plane_tiled_memory_bandwidth_x2 = false, + .has_pll_d2_out0 = false, }; static const struct tegra_dc_soc_info tegra30_dc_soc_info = { @@ -2363,7 +2879,10 @@ static const struct tegra_dc_soc_info tegra30_dc_soc_info = { .overlay_formats = tegra20_overlay_formats, .modifiers = tegra20_modifiers, .has_win_a_without_filters = false, + .has_win_b_vfilter_mem_client = true, .has_win_c_without_vert_filter = false, + .plane_tiled_memory_bandwidth_x2 = true, + .has_pll_d2_out0 = true, }; static const struct tegra_dc_soc_info tegra114_dc_soc_info = { @@ -2383,7 +2902,10 @@ static const struct tegra_dc_soc_info tegra114_dc_soc_info = { .overlay_formats = tegra114_overlay_formats, .modifiers = tegra20_modifiers, .has_win_a_without_filters = false, + .has_win_b_vfilter_mem_client = false, .has_win_c_without_vert_filter = false, + .plane_tiled_memory_bandwidth_x2 = true, + .has_pll_d2_out0 = true, }; static const struct tegra_dc_soc_info tegra124_dc_soc_info = { @@ -2403,7 +2925,10 @@ static const struct tegra_dc_soc_info tegra124_dc_soc_info = { .overlay_formats = tegra124_overlay_formats, .modifiers = tegra124_modifiers, .has_win_a_without_filters = false, + .has_win_b_vfilter_mem_client = false, .has_win_c_without_vert_filter = false, + .plane_tiled_memory_bandwidth_x2 = false, + .has_pll_d2_out0 = true, }; static const struct tegra_dc_soc_info tegra210_dc_soc_info = { @@ -2423,7 +2948,10 @@ static const struct tegra_dc_soc_info tegra210_dc_soc_info = { .overlay_formats = tegra114_overlay_formats, .modifiers = tegra124_modifiers, .has_win_a_without_filters = false, + .has_win_b_vfilter_mem_client = false, .has_win_c_without_vert_filter = false, + .plane_tiled_memory_bandwidth_x2 = false, + .has_pll_d2_out0 = true, }; static const struct tegra_windowgroup_soc tegra186_dc_wgrps[] = { @@ -2473,6 +3001,8 @@ static const struct tegra_dc_soc_info tegra186_dc_soc_info = { .has_nvdisplay = true, .wgrps = tegra186_dc_wgrps, .num_wgrps = ARRAY_SIZE(tegra186_dc_wgrps), + .plane_tiled_memory_bandwidth_x2 = false, + .has_pll_d2_out0 = false, }; static const struct tegra_windowgroup_soc tegra194_dc_wgrps[] = { @@ -2522,6 +3052,8 @@ static const struct tegra_dc_soc_info tegra194_dc_soc_info = { .has_nvdisplay = true, .wgrps = tegra194_dc_wgrps, .num_wgrps = ARRAY_SIZE(tegra194_dc_wgrps), + .plane_tiled_memory_bandwidth_x2 = false, + .has_pll_d2_out0 = false, }; static const struct of_device_id tegra_dc_of_match[] = { @@ -2617,11 +3149,29 @@ static int tegra_dc_couple(struct tegra_dc *dc) dc->client.parent = &parent->client; dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); + put_device(companion); } return 0; } +static int tegra_dc_init_opp_table(struct tegra_dc *dc) +{ + struct tegra_core_opp_params opp_params = {}; + int err; + + err = devm_tegra_core_dev_init_opp_table(dc->dev, &opp_params); + if (err && err != -ENODEV) + return err; + + if (err) + dc->has_opp_table = false; + else + dc->has_opp_table = true; + + return 0; +} + static int tegra_dc_probe(struct platform_device *pdev) { u64 dma_mask = dma_get_mask(pdev->dev.parent); @@ -2671,8 +3221,10 @@ static int tegra_dc_probe(struct platform_device *pdev) usleep_range(2000, 4000); err = reset_control_assert(dc->rst); - if (err < 0) + if (err < 0) { + clk_disable_unprepare(dc->clk); return err; + } usleep_range(2000, 4000); @@ -2687,6 +3239,10 @@ static int tegra_dc_probe(struct platform_device *pdev) tegra_powergate_power_off(dc->powergate); } + err = tegra_dc_init_opp_table(dc); + if (err < 0) + return err; + dc->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dc->regs)) return PTR_ERR(dc->regs); @@ -2696,16 +3252,9 @@ static int tegra_dc_probe(struct platform_device *pdev) return -ENXIO; err = tegra_dc_rgb_probe(dc); - if (err < 0 && err != -ENODEV) { - const char *level = KERN_ERR; - - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, dc->dev, "failed to probe RGB output: %d\n", - err); - return err; - } + if (err < 0 && err != -ENODEV) + return dev_err_probe(&pdev->dev, err, + "failed to probe RGB output\n"); platform_set_drvdata(pdev, dc); pm_runtime_enable(&pdev->dev); @@ -2730,27 +3279,15 @@ disable_pm: return err; } -static int tegra_dc_remove(struct platform_device *pdev) +static void tegra_dc_remove(struct platform_device *pdev) { struct tegra_dc *dc = platform_get_drvdata(pdev); - int err; - err = host1x_client_unregister(&dc->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; - } + host1x_client_unregister(&dc->client); - err = tegra_dc_rgb_remove(dc); - if (err < 0) { - dev_err(&pdev->dev, "failed to remove RGB output: %d\n", err); - return err; - } + tegra_dc_rgb_remove(dc); pm_runtime_disable(&pdev->dev); - - return 0; } struct platform_driver tegra_dc_driver = { diff --git a/drivers/gpu/drm/tegra/dc.h b/drivers/gpu/drm/tegra/dc.h index 5e13f1cfd749..0559fa6b1bf7 100644 --- a/drivers/gpu/drm/tegra/dc.h +++ b/drivers/gpu/drm/tegra/dc.h @@ -15,6 +15,8 @@ struct tegra_output; +#define TEGRA_DC_LEGACY_PLANES_NUM 7 + struct tegra_dc_state { struct drm_crtc_state base; @@ -38,6 +40,11 @@ struct tegra_dc_stats { unsigned long vblank; unsigned long underflow; unsigned long overflow; + + unsigned long frames_total; + unsigned long vblank_total; + unsigned long underflow_total; + unsigned long overflow_total; }; struct tegra_windowgroup_soc { @@ -66,7 +73,10 @@ struct tegra_dc_soc_info { unsigned int num_overlay_formats; const u64 *modifiers; bool has_win_a_without_filters; + bool has_win_b_vfilter_mem_client; bool has_win_c_without_vert_filter; + bool plane_tiled_memory_bandwidth_x2; + bool has_pll_d2_out0; }; struct tegra_dc { @@ -91,6 +101,8 @@ struct tegra_dc { struct drm_info_list *debugfs_files; const struct tegra_dc_soc_info *soc; + + bool has_opp_table; }; static inline struct tegra_dc * @@ -152,10 +164,12 @@ int tegra_dc_state_setup_clock(struct tegra_dc *dc, struct drm_crtc_state *crtc_state, struct clk *clk, unsigned long pclk, unsigned int div); +void tegra_crtc_atomic_post_commit(struct drm_crtc *crtc, + struct drm_atomic_state *state); /* from rgb.c */ int tegra_dc_rgb_probe(struct tegra_dc *dc); -int tegra_dc_rgb_remove(struct tegra_dc *dc); +void tegra_dc_rgb_remove(struct tegra_dc *dc); int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc); int tegra_dc_rgb_exit(struct tegra_dc *dc); @@ -623,6 +637,13 @@ int tegra_dc_rgb_exit(struct tegra_dc *dc); #define WIN_COLOR_DEPTH_A8B8G8R8 36 #define WIN_COLOR_DEPTH_B8G8R8X8 37 #define WIN_COLOR_DEPTH_R8G8B8X8 38 +#define WIN_COLOR_DEPTH_YCbCr444P 41 +#define WIN_COLOR_DEPTH_YCrCb420SP 42 +#define WIN_COLOR_DEPTH_YCbCr420SP 43 +#define WIN_COLOR_DEPTH_YCrCb422SP 44 +#define WIN_COLOR_DEPTH_YCbCr422SP 45 +#define WIN_COLOR_DEPTH_YCrCb444SP 48 +#define WIN_COLOR_DEPTH_YCbCr444SP 49 #define WIN_COLOR_DEPTH_X8B8G8R8 65 #define WIN_COLOR_DEPTH_X8R8G8B8 66 diff --git a/drivers/gpu/drm/tegra/dp.c b/drivers/gpu/drm/tegra/dp.c index 70dfb7d1dec5..990e744b0923 100644 --- a/drivers/gpu/drm/tegra/dp.c +++ b/drivers/gpu/drm/tegra/dp.c @@ -4,8 +4,8 @@ * Copyright (C) 2015 Rob Clark */ +#include <drm/display/drm_dp_helper.h> #include <drm/drm_crtc.h> -#include <drm/drm_dp_helper.h> #include <drm/drm_print.h> #include "dp.h" @@ -256,73 +256,6 @@ int drm_dp_link_probe(struct drm_dp_aux *aux, struct drm_dp_link *link) } /** - * drm_dp_link_power_up() - power up a DisplayPort link - * @aux: DisplayPort AUX channel - * @link: pointer to a structure containing the link configuration - * - * Returns 0 on success or a negative error code on failure. - */ -int drm_dp_link_power_up(struct drm_dp_aux *aux, struct drm_dp_link *link) -{ - u8 value; - int err; - - /* DP_SET_POWER register is only available on DPCD v1.1 and later */ - if (link->revision < 0x11) - return 0; - - err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); - if (err < 0) - return err; - - value &= ~DP_SET_POWER_MASK; - value |= DP_SET_POWER_D0; - - err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); - if (err < 0) - return err; - - /* - * According to the DP 1.1 specification, a "Sink Device must exit the - * power saving state within 1 ms" (Section 2.5.3.1, Table 5-52, "Sink - * Control Field" (register 0x600). - */ - usleep_range(1000, 2000); - - return 0; -} - -/** - * drm_dp_link_power_down() - power down a DisplayPort link - * @aux: DisplayPort AUX channel - * @link: pointer to a structure containing the link configuration - * - * Returns 0 on success or a negative error code on failure. - */ -int drm_dp_link_power_down(struct drm_dp_aux *aux, struct drm_dp_link *link) -{ - u8 value; - int err; - - /* DP_SET_POWER register is only available on DPCD v1.1 and later */ - if (link->revision < 0x11) - return 0; - - err = drm_dp_dpcd_readb(aux, DP_SET_POWER, &value); - if (err < 0) - return err; - - value &= ~DP_SET_POWER_MASK; - value |= DP_SET_POWER_D3; - - err = drm_dp_dpcd_writeb(aux, DP_SET_POWER, value); - if (err < 0) - return err; - - return 0; -} - -/** * drm_dp_link_configure() - configure a DisplayPort link * @aux: DisplayPort AUX channel * @link: pointer to a structure containing the link configuration @@ -549,6 +482,15 @@ static void drm_dp_link_get_adjustments(struct drm_dp_link *link, { struct drm_dp_link_train_set *adjust = &link->train.adjust; unsigned int i; + u8 post_cursor; + int err; + + err = drm_dp_dpcd_read(link->aux, DP_ADJUST_REQUEST_POST_CURSOR2, + &post_cursor, sizeof(post_cursor)); + if (err < 0) { + DRM_ERROR("failed to read post_cursor2: %d\n", err); + post_cursor = 0; + } for (i = 0; i < link->lanes; i++) { adjust->voltage_swing[i] = @@ -560,7 +502,7 @@ static void drm_dp_link_get_adjustments(struct drm_dp_link *link, DP_TRAIN_PRE_EMPHASIS_SHIFT; adjust->post_cursor[i] = - drm_dp_get_adjust_request_post_cursor(status, i); + (post_cursor >> (i << 1)) & 0x3; } } diff --git a/drivers/gpu/drm/tegra/dp.h b/drivers/gpu/drm/tegra/dp.h index cb12ed0c54e7..695060cafac0 100644 --- a/drivers/gpu/drm/tegra/dp.h +++ b/drivers/gpu/drm/tegra/dp.h @@ -164,8 +164,6 @@ int drm_dp_link_remove_rate(struct drm_dp_link *link, unsigned long rate); void drm_dp_link_update_rates(struct drm_dp_link *link); int drm_dp_link_probe(struct drm_dp_aux *aux, struct drm_dp_link *link); -int drm_dp_link_power_up(struct drm_dp_aux *aux, struct drm_dp_link *link); -int drm_dp_link_power_down(struct drm_dp_aux *aux, struct drm_dp_link *link); int drm_dp_link_configure(struct drm_dp_aux *aux, struct drm_dp_link *link); int drm_dp_link_choose(struct drm_dp_link *link, const struct drm_display_mode *mode, diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index 1f96e416fa08..e5297ac5c0fc 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -8,7 +8,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/pinctrl.h> #include <linux/pinctrl/pinmux.h> @@ -18,7 +18,8 @@ #include <linux/reset.h> #include <linux/workqueue.h> -#include <drm/drm_dp_helper.h> +#include <drm/display/drm_dp_helper.h> +#include <drm/display/drm_dp_aux_bus.h> #include <drm/drm_panel.h> #include "dp.h" @@ -279,7 +280,6 @@ static void tegra_dpaux_hotplug(struct work_struct *work) static irqreturn_t tegra_dpaux_irq(int irq, void *data) { struct tegra_dpaux *dpaux = data; - irqreturn_t ret = IRQ_HANDLED; u32 value; /* clear interrupts */ @@ -296,7 +296,7 @@ static irqreturn_t tegra_dpaux_irq(int irq, void *data) if (value & DPAUX_INTR_AUX_DONE) complete(&dpaux->complete); - return ret; + return IRQ_HANDLED; } enum tegra_dpaux_functions { @@ -447,7 +447,6 @@ static const struct pinmux_ops tegra_dpaux_pinmux_ops = { static int tegra_dpaux_probe(struct platform_device *pdev) { struct tegra_dpaux *dpaux; - struct resource *regs; u32 value; int err; @@ -461,14 +460,13 @@ static int tegra_dpaux_probe(struct platform_device *pdev) INIT_LIST_HEAD(&dpaux->list); dpaux->dev = &pdev->dev; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dpaux->regs = devm_ioremap_resource(&pdev->dev, regs); + dpaux->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(dpaux->regs)) return PTR_ERR(dpaux->regs); dpaux->irq = platform_get_irq(pdev, 0); if (dpaux->irq < 0) - return -ENXIO; + return dpaux->irq; if (!pdev->dev.pm_domain) { dpaux->rst = devm_reset_control_get(&pdev->dev, "dpaux"); @@ -503,14 +501,9 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->vdd = devm_regulator_get_optional(&pdev->dev, "vdd"); if (IS_ERR(dpaux->vdd)) { - if (PTR_ERR(dpaux->vdd) != -ENODEV) { - if (PTR_ERR(dpaux->vdd) != -EPROBE_DEFER) - dev_err(&pdev->dev, - "failed to get VDD supply: %ld\n", - PTR_ERR(dpaux->vdd)); - - return PTR_ERR(dpaux->vdd); - } + if (PTR_ERR(dpaux->vdd) != -ENODEV) + return dev_err_probe(&pdev->dev, PTR_ERR(dpaux->vdd), + "failed to get VDD supply\n"); dpaux->vdd = NULL; } @@ -524,7 +517,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) if (err < 0) { dev_err(dpaux->dev, "failed to request IRQ#%u: %d\n", dpaux->irq, err); - return err; + goto err_pm_disable; } disable_irq(dpaux->irq); @@ -544,7 +537,7 @@ static int tegra_dpaux_probe(struct platform_device *pdev) */ err = tegra_dpaux_pad_config(dpaux, DPAUX_PADCTL_FUNC_I2C); if (err < 0) - return err; + goto err_pm_disable; #ifdef CONFIG_GENERIC_PINCONF dpaux->desc.name = dev_name(&pdev->dev); @@ -557,7 +550,8 @@ static int tegra_dpaux_probe(struct platform_device *pdev) dpaux->pinctrl = devm_pinctrl_register(&pdev->dev, &dpaux->desc, dpaux); if (IS_ERR(dpaux->pinctrl)) { dev_err(&pdev->dev, "failed to register pincontrol\n"); - return PTR_ERR(dpaux->pinctrl); + err = PTR_ERR(dpaux->pinctrl); + goto err_pm_disable; } #endif /* enable and clear all interrupts */ @@ -570,10 +564,21 @@ static int tegra_dpaux_probe(struct platform_device *pdev) list_add_tail(&dpaux->list, &dpaux_list); mutex_unlock(&dpaux_lock); + err = devm_of_dp_aux_populate_ep_devices(&dpaux->aux); + if (err < 0) { + dev_err(dpaux->dev, "failed to populate AUX bus: %d\n", err); + goto err_pm_disable; + } + return 0; + +err_pm_disable: + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return err; } -static int tegra_dpaux_remove(struct platform_device *pdev) +static void tegra_dpaux_remove(struct platform_device *pdev) { struct tegra_dpaux *dpaux = platform_get_drvdata(pdev); @@ -588,11 +593,8 @@ static int tegra_dpaux_remove(struct platform_device *pdev) mutex_lock(&dpaux_lock); list_del(&dpaux->list); mutex_unlock(&dpaux_lock); - - return 0; } -#ifdef CONFIG_PM static int tegra_dpaux_suspend(struct device *dev) { struct tegra_dpaux *dpaux = dev_get_drvdata(dev); @@ -651,10 +653,9 @@ disable_clk: clk_disable_unprepare(dpaux->clk); return err; } -#endif static const struct dev_pm_ops tegra_dpaux_pm_ops = { - SET_RUNTIME_PM_OPS(tegra_dpaux_suspend, tegra_dpaux_resume, NULL) + RUNTIME_PM_OPS(tegra_dpaux_suspend, tegra_dpaux_resume, NULL) }; static const struct tegra_dpaux_soc tegra124_dpaux_soc = { @@ -688,7 +689,7 @@ struct platform_driver tegra_dpaux_driver = { .driver = { .name = "tegra-dpaux", .of_match_table = tegra_dpaux_of_match, - .pm = &tegra_dpaux_pm_ops, + .pm = pm_ptr(&tegra_dpaux_pm_ops), }, .probe = tegra_dpaux_probe, .remove = tegra_dpaux_remove, diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index f96c237b2242..1d18d43292dc 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -4,41 +4,45 @@ * Copyright (C) 2012-2016 NVIDIA CORPORATION. All rights reserved. */ +#include <linux/aperture.h> #include <linux/bitops.h> #include <linux/host1x.h> #include <linux/idr.h> #include <linux/iommu.h> #include <linux/module.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> -#include <drm/drm_aperture.h> +#include <drm/clients/drm_client_setup.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_debugfs.h> #include <drm/drm_drv.h> #include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> #include <drm/drm_ioctl.h> #include <drm/drm_prime.h> +#include <drm/drm_print.h> #include <drm/drm_vblank.h> +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) +#include <asm/dma-iommu.h> +#endif + +#include "dc.h" #include "drm.h" #include "gem.h" +#include "uapi.h" #define DRIVER_NAME "tegra" #define DRIVER_DESC "NVIDIA Tegra graphics" -#define DRIVER_DATE "20120330" -#define DRIVER_MAJOR 0 +#define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 #define DRIVER_PATCHLEVEL 0 #define CARVEOUT_SZ SZ_64M #define CDMA_GATHER_FETCHES_MAX_NB 16383 -struct tegra_drm_file { - struct idr contexts; - struct mutex lock; -}; - static int tegra_atomic_check(struct drm_device *drm, struct drm_atomic_state *state) { @@ -53,13 +57,21 @@ static int tegra_atomic_check(struct drm_device *drm, static const struct drm_mode_config_funcs tegra_drm_mode_config_funcs = { .fb_create = tegra_fb_create, -#ifdef CONFIG_DRM_FBDEV_EMULATION - .output_poll_changed = drm_fb_helper_output_poll_changed, -#endif .atomic_check = tegra_atomic_check, .atomic_commit = drm_atomic_helper_commit, }; +static void tegra_atomic_post_commit(struct drm_device *drm, + struct drm_atomic_state *old_state) +{ + struct drm_crtc_state *old_crtc_state __maybe_unused; + struct drm_crtc *crtc; + unsigned int i; + + for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i) + tegra_crtc_atomic_post_commit(crtc, old_state); +} + static void tegra_atomic_commit_tail(struct drm_atomic_state *old_state) { struct drm_device *drm = old_state->dev; @@ -79,6 +91,8 @@ static void tegra_atomic_commit_tail(struct drm_atomic_state *old_state) } else { drm_atomic_helper_commit_tail_rpm(old_state); } + + tegra_atomic_post_commit(drm, old_state); } static const struct drm_mode_config_helper_funcs @@ -94,7 +108,9 @@ static int tegra_drm_open(struct drm_device *drm, struct drm_file *filp) if (!fpriv) return -ENOMEM; - idr_init_base(&fpriv->contexts, 1); + idr_init_base(&fpriv->legacy_contexts, 1); + xa_init_flags(&fpriv->contexts, XA_FLAGS_ALLOC1); + xa_init(&fpriv->syncpoints); mutex_init(&fpriv->lock); filp->driver_priv = fpriv; @@ -104,23 +120,10 @@ static int tegra_drm_open(struct drm_device *drm, struct drm_file *filp) static void tegra_drm_context_free(struct tegra_drm_context *context) { context->client->ops->close_channel(context); + pm_runtime_put(context->client->base.dev); kfree(context); } -static struct host1x_bo * -host1x_bo_lookup(struct drm_file *file, u32 handle) -{ - struct drm_gem_object *gem; - struct tegra_bo *bo; - - gem = drm_gem_object_lookup(file, handle); - if (!gem) - return NULL; - - bo = to_tegra_bo(gem); - return &bo->base; -} - static int host1x_reloc_copy_from_user(struct host1x_reloc *dest, struct drm_tegra_reloc __user *src, struct drm_device *drm, @@ -151,11 +154,11 @@ static int host1x_reloc_copy_from_user(struct host1x_reloc *dest, dest->flags = HOST1X_RELOC_READ | HOST1X_RELOC_WRITE; - dest->cmdbuf.bo = host1x_bo_lookup(file, cmdbuf); + dest->cmdbuf.bo = tegra_gem_lookup(file, cmdbuf); if (!dest->cmdbuf.bo) return -ENOENT; - dest->target.bo = host1x_bo_lookup(file, target); + dest->target.bo = tegra_gem_lookup(file, target); if (!dest->target.bo) return -ENOENT; @@ -193,7 +196,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, return -EINVAL; job = host1x_job_alloc(context->channel, args->num_cmdbufs, - args->num_relocs); + args->num_relocs, false); if (!job) return -ENOMEM; @@ -201,6 +204,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, job->client = client; job->class = client->class; job->serialize = true; + job->syncpt_recovery = true; /* * Track referenced BOs so that they can be unreferenced after the @@ -237,7 +241,7 @@ int tegra_drm_submit(struct tegra_drm_context *context, goto fail; } - bo = host1x_bo_lookup(file, cmdbuf.handle); + bo = tegra_gem_lookup(file, cmdbuf.handle); if (!bo) { err = -ENOENT; goto fail; @@ -428,13 +432,20 @@ static int tegra_client_open(struct tegra_drm_file *fpriv, { int err; + err = pm_runtime_resume_and_get(client->base.dev); + if (err) + return err; + err = client->ops->open_channel(client, context); - if (err < 0) + if (err < 0) { + pm_runtime_put(client->base.dev); return err; + } - err = idr_alloc(&fpriv->contexts, context, 1, 0, GFP_KERNEL); + err = idr_alloc(&fpriv->legacy_contexts, context, 1, 0, GFP_KERNEL); if (err < 0) { client->ops->close_channel(context); + pm_runtime_put(client->base.dev); return err; } @@ -487,13 +498,13 @@ static int tegra_close_channel(struct drm_device *drm, void *data, mutex_lock(&fpriv->lock); - context = idr_find(&fpriv->contexts, args->context); + context = idr_find(&fpriv->legacy_contexts, args->context); if (!context) { err = -EINVAL; goto unlock; } - idr_remove(&fpriv->contexts, context->id); + idr_remove(&fpriv->legacy_contexts, context->id); tegra_drm_context_free(context); unlock: @@ -512,7 +523,7 @@ static int tegra_get_syncpt(struct drm_device *drm, void *data, mutex_lock(&fpriv->lock); - context = idr_find(&fpriv->contexts, args->context); + context = idr_find(&fpriv->legacy_contexts, args->context); if (!context) { err = -ENODEV; goto unlock; @@ -541,7 +552,7 @@ static int tegra_submit(struct drm_device *drm, void *data, mutex_lock(&fpriv->lock); - context = idr_find(&fpriv->contexts, args->context); + context = idr_find(&fpriv->legacy_contexts, args->context); if (!context) { err = -ENODEV; goto unlock; @@ -566,7 +577,7 @@ static int tegra_get_syncpt_base(struct drm_device *drm, void *data, mutex_lock(&fpriv->lock); - context = idr_find(&fpriv->contexts, args->context); + context = idr_find(&fpriv->legacy_contexts, args->context); if (!context) { err = -ENODEV; goto unlock; @@ -735,10 +746,25 @@ static int tegra_gem_get_flags(struct drm_device *drm, void *data, static const struct drm_ioctl_desc tegra_drm_ioctls[] = { #ifdef CONFIG_DRM_TEGRA_STAGING - DRM_IOCTL_DEF_DRV(TEGRA_GEM_CREATE, tegra_gem_create, + DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_OPEN, tegra_drm_ioctl_channel_open, DRM_RENDER_ALLOW), - DRM_IOCTL_DEF_DRV(TEGRA_GEM_MMAP, tegra_gem_mmap, + DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_CLOSE, tegra_drm_ioctl_channel_close, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_MAP, tegra_drm_ioctl_channel_map, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_UNMAP, tegra_drm_ioctl_channel_unmap, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_CHANNEL_SUBMIT, tegra_drm_ioctl_channel_submit, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_ALLOCATE, tegra_drm_ioctl_syncpoint_allocate, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_FREE, tegra_drm_ioctl_syncpoint_free, + DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_SYNCPOINT_WAIT, tegra_drm_ioctl_syncpoint_wait, + DRM_RENDER_ALLOW), + + DRM_IOCTL_DEF_DRV(TEGRA_GEM_CREATE, tegra_gem_create, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(TEGRA_GEM_MMAP, tegra_gem_mmap, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(TEGRA_SYNCPT_READ, tegra_syncpt_read, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(TEGRA_SYNCPT_INCR, tegra_syncpt_incr, @@ -776,6 +802,7 @@ static const struct file_operations tegra_drm_fops = { .read = drm_read, .compat_ioctl = drm_compat_ioctl, .llseek = noop_llseek, + .fop_flags = FOP_UNSIGNED_OFFSET, }; static int tegra_drm_context_cleanup(int id, void *p, void *data) @@ -792,10 +819,11 @@ static void tegra_drm_postclose(struct drm_device *drm, struct drm_file *file) struct tegra_drm_file *fpriv = file->driver_priv; mutex_lock(&fpriv->lock); - idr_for_each(&fpriv->contexts, tegra_drm_context_cleanup, NULL); + idr_for_each(&fpriv->legacy_contexts, tegra_drm_context_cleanup, NULL); + tegra_drm_uapi_close_file(fpriv); mutex_unlock(&fpriv->lock); - idr_destroy(&fpriv->contexts); + idr_destroy(&fpriv->legacy_contexts); mutex_destroy(&fpriv->lock); kfree(fpriv); } @@ -853,28 +881,26 @@ static void tegra_debugfs_init(struct drm_minor *minor) static const struct drm_driver tegra_drm_driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | - DRIVER_ATOMIC | DRIVER_RENDER, + DRIVER_ATOMIC | DRIVER_RENDER | DRIVER_SYNCOBJ, .open = tegra_drm_open, .postclose = tegra_drm_postclose, - .lastclose = drm_fb_helper_lastclose, #if defined(CONFIG_DEBUG_FS) .debugfs_init = tegra_debugfs_init, #endif - .prime_handle_to_fd = drm_gem_prime_handle_to_fd, - .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_import = tegra_gem_prime_import, .dumb_create = tegra_bo_dumb_create, + TEGRA_FBDEV_DRIVER_OPS, + .ioctls = tegra_drm_ioctls, .num_ioctls = ARRAY_SIZE(tegra_drm_ioctls), .fops = &tegra_drm_fops, .name = DRIVER_NAME, .desc = DRIVER_DESC, - .date = DRIVER_DATE, .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, @@ -883,6 +909,14 @@ static const struct drm_driver tegra_drm_driver = { int tegra_drm_register_client(struct tegra_drm *tegra, struct tegra_drm_client *client) { + /* + * When MLOCKs are implemented, change to allocate a shared channel + * only when MLOCKs are disabled. + */ + client->shared_channel = host1x_channel_request(&client->base); + if (!client->shared_channel) + return -EBUSY; + mutex_lock(&tegra->clients_lock); list_add_tail(&client->list, &tegra->clients); client->drm = tegra; @@ -899,6 +933,9 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra, client->drm = NULL; mutex_unlock(&tegra->clients_lock); + if (client->shared_channel) + host1x_channel_put(client->shared_channel); + return 0; } @@ -910,12 +947,24 @@ int host1x_client_iommu_attach(struct host1x_client *client) struct iommu_group *group = NULL; int err; +#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) + if (client->dev->archdata.mapping) { + struct dma_iommu_mapping *mapping = + to_dma_iommu_mapping(client->dev); + arm_iommu_detach_device(client->dev); + arm_iommu_release_mapping(mapping); + + domain = iommu_get_domain_for_dev(client->dev); + } +#endif + /* * If the host1x client is already attached to an IOMMU domain that is * not the shared IOMMU domain, don't try to attach it to a different * domain. This allows using the IOMMU-backed DMA API. */ - if (domain && domain != tegra->domain) + if (domain && domain->type != IOMMU_DOMAIN_IDENTITY && + domain != tegra->domain) return 0; if (tegra->domain) { @@ -1006,7 +1055,7 @@ void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *dma) *dma = iova_dma_addr(&tegra->carveout.domain, alloc); err = iommu_map(tegra->domain, *dma, virt_to_phys(virt), - size, IOMMU_READ | IOMMU_WRITE); + size, IOMMU_READ | IOMMU_WRITE, GFP_KERNEL); if (err < 0) goto free_iova; @@ -1042,6 +1091,10 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; + /* Our IOMMU usage policy doesn't currently play well with GART */ + if (of_machine_is_compatible("nvidia,tegra20")) + return false; + /* * If the Tegra DRM clients are backed by an IOMMU, push buffers are * likely to be allocated beyond the 32-bit boundary if sufficient @@ -1085,6 +1138,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) static int host1x_drm_probe(struct host1x_device *dev) { + struct device *dma_dev = dev->dev.parent; struct tegra_drm *tegra; struct drm_device *drm; int err; @@ -1099,10 +1153,10 @@ static int host1x_drm_probe(struct host1x_device *dev) goto put; } - if (host1x_drm_wants_iommu(dev) && iommu_present(&platform_bus_type)) { - tegra->domain = iommu_domain_alloc(&platform_bus_type); - if (!tegra->domain) { - err = -ENOMEM; + if (host1x_drm_wants_iommu(dev) && device_iommu_mapped(dma_dev)) { + tegra->domain = iommu_paging_domain_alloc(dma_dev); + if (IS_ERR(tegra->domain)) { + err = PTR_ERR(tegra->domain); goto free; } @@ -1130,15 +1184,11 @@ static int host1x_drm_probe(struct host1x_device *dev) drm->mode_config.funcs = &tegra_drm_mode_config_funcs; drm->mode_config.helper_private = &tegra_drm_mode_config_helpers; - err = tegra_drm_fb_prepare(drm); - if (err < 0) - goto config; - drm_kms_helper_poll_init(drm); err = host1x_device_init(dev); if (err < 0) - goto fbdev; + goto poll; /* * Now that all display controller have been initialized, the maximum @@ -1188,13 +1238,6 @@ static int host1x_drm_probe(struct host1x_device *dev) goto device; } - /* - * We don't use the drm_irq_install() helpers provided by the DRM - * core, so we need to set this manually in order to allow the - * DRM_IOCTL_WAIT_VBLANK to operate correctly. - */ - drm->irq_enabled = true; - /* syncpoints are used for full 32-bit hardware VBLANK counters */ drm->max_vblank_count = 0xffffffff; @@ -1204,22 +1247,35 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(false, "tegradrmfb"); - if (err < 0) - goto hub; + /* + * Only take over from a potential firmware framebuffer if any CRTCs + * have been registered. This must not be a fatal error because there + * are other accelerators that are exposed via this driver. + * + * Another case where this happens is on Tegra234 where the display + * hardware is no longer part of the host1x complex, so this driver + * will not expose any modesetting features. + */ + if (drm->mode_config.num_crtc > 0) { + err = aperture_remove_all_conflicting_devices(tegra_drm_driver.name); + if (err < 0) + goto hub; + } else { + /* + * Indicate to userspace that this doesn't expose any display + * capabilities. + */ + drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); + } - err = tegra_drm_fb_init(drm); + err = drm_dev_register(drm, 0); if (err < 0) goto hub; - err = drm_dev_register(drm, 0); - if (err < 0) - goto fb; + drm_client_setup(drm, NULL); return 0; -fb: - tegra_drm_fb_exit(drm); hub: if (tegra->hub) tegra_display_hub_cleanup(tegra->hub); @@ -1232,10 +1288,8 @@ device: } host1x_device_exit(dev); -fbdev: +poll: drm_kms_helper_poll_fini(drm); - tegra_drm_fb_free(drm); -config: drm_mode_config_cleanup(drm); domain: if (tegra->domain) @@ -1256,7 +1310,6 @@ static int host1x_drm_remove(struct host1x_device *dev) drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); - tegra_drm_fb_exit(drm); drm_atomic_helper_shutdown(drm); drm_mode_config_cleanup(drm); @@ -1281,6 +1334,11 @@ static int host1x_drm_remove(struct host1x_device *dev) return 0; } +static void host1x_drm_shutdown(struct host1x_device *dev) +{ + drm_atomic_helper_shutdown(dev_get_drvdata(&dev->dev)); +} + #ifdef CONFIG_PM_SLEEP static int host1x_drm_suspend(struct device *dev) { @@ -1325,15 +1383,21 @@ static const struct of_device_id host1x_drm_subdevs[] = { { .compatible = "nvidia,tegra210-sor", }, { .compatible = "nvidia,tegra210-sor1", }, { .compatible = "nvidia,tegra210-vic", }, + { .compatible = "nvidia,tegra210-nvdec", }, + { .compatible = "nvidia,tegra210-nvjpg", }, { .compatible = "nvidia,tegra186-display", }, { .compatible = "nvidia,tegra186-dc", }, { .compatible = "nvidia,tegra186-sor", }, { .compatible = "nvidia,tegra186-sor1", }, { .compatible = "nvidia,tegra186-vic", }, + { .compatible = "nvidia,tegra186-nvdec", }, { .compatible = "nvidia,tegra194-display", }, { .compatible = "nvidia,tegra194-dc", }, { .compatible = "nvidia,tegra194-sor", }, { .compatible = "nvidia,tegra194-vic", }, + { .compatible = "nvidia,tegra194-nvdec", }, + { .compatible = "nvidia,tegra234-vic", }, + { .compatible = "nvidia,tegra234-nvdec", }, { /* sentinel */ } }; @@ -1344,6 +1408,7 @@ static struct host1x_driver host1x_drm_driver = { }, .probe = host1x_drm_probe, .remove = host1x_drm_remove, + .shutdown = host1x_drm_shutdown, .subdevs = host1x_drm_subdevs, }; @@ -1357,12 +1422,17 @@ static struct platform_driver * const drivers[] = { &tegra_gr2d_driver, &tegra_gr3d_driver, &tegra_vic_driver, + &tegra_nvdec_driver, + &tegra_nvjpg_driver, }; static int __init host1x_drm_init(void) { int err; + if (drm_firmware_drivers_only()) + return -ENODEV; + err = host1x_driver_register(&host1x_drm_driver); if (err < 0) return err; diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index 0cb868065348..ae68b03d8483 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -13,9 +13,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_bridge.h> -#include <drm/drm_edid.h> #include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_fixed.h> #include <drm/drm_probe_helper.h> #include <uapi/drm/tegra_drm.h> @@ -27,14 +25,11 @@ /* XXX move to include/uapi/drm/drm_fourcc.h? */ #define DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT BIT_ULL(22) -struct reset_control; +struct drm_fb_helper; +struct drm_fb_helper_surface_size; -#ifdef CONFIG_DRM_FBDEV_EMULATION -struct tegra_fbdev { - struct drm_fb_helper base; - struct drm_framebuffer *fb; -}; -#endif +struct edid; +struct reset_control; struct tegra_drm { struct drm_device *drm; @@ -53,10 +48,6 @@ struct tegra_drm { struct mutex clients_lock; struct list_head clients; -#ifdef CONFIG_DRM_FBDEV_EMULATION - struct tegra_fbdev *fbdev; -#endif - unsigned int hmask, vmask; unsigned int pitch_align; unsigned int num_crtcs; @@ -64,12 +55,23 @@ struct tegra_drm { struct tegra_display_hub *hub; }; +static inline struct host1x *tegra_drm_to_host1x(struct tegra_drm *tegra) +{ + return dev_get_drvdata(tegra->drm->dev->parent); +} + struct tegra_drm_client; struct tegra_drm_context { struct tegra_drm_client *client; struct host1x_channel *channel; + + /* Only used by legacy UAPI. */ unsigned int id; + + /* Only used by new UAPI. */ + struct xarray mappings; + struct host1x_memory_context *memory_context; }; struct tegra_drm_client_ops { @@ -81,17 +83,29 @@ struct tegra_drm_client_ops { int (*submit)(struct tegra_drm_context *context, struct drm_tegra_submit *args, struct drm_device *drm, struct drm_file *file); + int (*get_streamid_offset)(struct tegra_drm_client *client, u32 *offset); + int (*can_use_memory_ctx)(struct tegra_drm_client *client, bool *supported); }; int tegra_drm_submit(struct tegra_drm_context *context, struct drm_tegra_submit *args, struct drm_device *drm, struct drm_file *file); +static inline int +tegra_drm_get_streamid_offset_thi(struct tegra_drm_client *client, u32 *offset) +{ + *offset = 0x30; + + return 0; +} + struct tegra_drm_client { struct host1x_client base; struct list_head list; struct tegra_drm *drm; + struct host1x_channel *shared_channel; + /* Set by driver */ unsigned int version; const struct tegra_drm_client_ops *ops; }; @@ -109,9 +123,6 @@ int tegra_drm_unregister_client(struct tegra_drm *tegra, int host1x_client_iommu_attach(struct host1x_client *client); void host1x_client_iommu_detach(struct host1x_client *client); -int tegra_drm_init(struct tegra_drm *tegra, struct drm_device *drm); -int tegra_drm_exit(struct tegra_drm *tegra); - void *tegra_drm_alloc(struct tegra_drm *tegra, size_t size, dma_addr_t *iova); void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt, dma_addr_t iova); @@ -125,7 +136,7 @@ struct tegra_output { struct drm_bridge *bridge; struct drm_panel *panel; struct i2c_adapter *ddc; - const struct edid *edid; + const struct drm_edid *drm_edid; struct cec_notifier *cec; unsigned int hpd_irq; struct gpio_desc *hpd_gpio; @@ -173,13 +184,25 @@ struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer, bool tegra_fb_is_bottom_up(struct drm_framebuffer *framebuffer); int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer, struct tegra_bo_tiling *tiling); +struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm, + const struct drm_format_info *info, + const struct drm_mode_fb_cmd2 *mode_cmd, + struct tegra_bo **planes, + unsigned int num_planes); struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, struct drm_file *file, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *cmd); -int tegra_drm_fb_prepare(struct drm_device *drm); -void tegra_drm_fb_free(struct drm_device *drm); -int tegra_drm_fb_init(struct drm_device *drm); -void tegra_drm_fb_exit(struct drm_device *drm); + +#ifdef CONFIG_DRM_FBDEV_EMULATION +int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes); +#define TEGRA_FBDEV_DRIVER_OPS \ + .fbdev_probe = tegra_fbdev_driver_fbdev_probe +#else +#define TEGRA_FBDEV_DRIVER_OPS \ + .fbdev_probe = NULL +#endif extern struct platform_driver tegra_display_hub_driver; extern struct platform_driver tegra_dc_driver; @@ -190,5 +213,7 @@ extern struct platform_driver tegra_sor_driver; extern struct platform_driver tegra_gr2d_driver; extern struct platform_driver tegra_gr3d_driver; extern struct platform_driver tegra_vic_driver; +extern struct platform_driver tegra_nvdec_driver; +extern struct platform_driver tegra_nvjpg_driver; #endif /* HOST1X_DRM_H */ diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index f46d377f0c30..175f5f9937b0 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -22,6 +22,7 @@ #include <drm/drm_file.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_panel.h> +#include <drm/drm_print.h> #include <drm/drm_simple_kms_helper.h> #include "dc.h" @@ -256,6 +257,7 @@ static void tegra_dsi_early_unregister(struct drm_connector *connector) struct tegra_dsi *dsi = to_dsi(output); drm_debugfs_remove_files(dsi->debugfs_files, count, + connector->debugfs_entry, connector->dev->primary); kfree(dsi->debugfs_files); dsi->debugfs_files = NULL; @@ -544,12 +546,19 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe, /* horizontal back porch */ hbp = (mode->htotal - mode->hsync_end) * mul / div; - if ((dsi->flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) == 0) - hbp += hsw; - /* horizontal front porch */ hfp = (mode->hsync_start - mode->hdisplay) * mul / div; + if (dsi->master || dsi->slave) { + hact /= 2; + hsw /= 2; + hbp /= 2; + hfp /= 2; + } + + if ((dsi->flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) == 0) + hbp += hsw; + /* subtract packet overhead */ hsw -= 10; hbp -= 14; @@ -559,11 +568,6 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe, tegra_dsi_writel(dsi, hact << 16 | hbp, DSI_PKT_LEN_2_3); tegra_dsi_writel(dsi, hfp, DSI_PKT_LEN_4_5); tegra_dsi_writel(dsi, 0x0f0f << 16, DSI_PKT_LEN_6_7); - - /* set SOL delay (for non-burst mode only) */ - tegra_dsi_writel(dsi, 8 * mul / div, DSI_SOL_DELAY); - - /* TODO: implement ganged mode */ } else { u16 bytes; @@ -585,29 +589,28 @@ static void tegra_dsi_configure(struct tegra_dsi *dsi, unsigned int pipe, value = MIPI_DCS_WRITE_MEMORY_START << 8 | MIPI_DCS_WRITE_MEMORY_CONTINUE; tegra_dsi_writel(dsi, value, DSI_DCS_CMDS); + } - /* set SOL delay */ - if (dsi->master || dsi->slave) { - unsigned long delay, bclk, bclk_ganged; - unsigned int lanes = state->lanes; - - /* SOL to valid, valid to FIFO and FIFO write delay */ - delay = 4 + 4 + 2; - delay = DIV_ROUND_UP(delay * mul, div * lanes); - /* FIFO read delay */ - delay = delay + 6; - - bclk = DIV_ROUND_UP(mode->htotal * mul, div * lanes); - bclk_ganged = DIV_ROUND_UP(bclk * lanes / 2, lanes); - value = bclk - bclk_ganged + delay + 20; - } else { - /* TODO: revisit for non-ganged mode */ - value = 8 * mul / div; - } + /* set SOL delay */ + if (dsi->master || dsi->slave) { + unsigned long delay, bclk, bclk_ganged; + unsigned int lanes = state->lanes; + + /* SOL to valid, valid to FIFO and FIFO write delay */ + delay = 4 + 4 + 2; + delay = DIV_ROUND_UP(delay * mul, div * lanes); + /* FIFO read delay */ + delay = delay + 6; - tegra_dsi_writel(dsi, value, DSI_SOL_DELAY); + bclk = DIV_ROUND_UP(mode->htotal * mul, div * lanes); + bclk_ganged = DIV_ROUND_UP(bclk * lanes / 2, lanes); + value = bclk - bclk_ganged + delay + 20; + } else { + value = 8 * mul / div; } + tegra_dsi_writel(dsi, value, DSI_SOL_DELAY); + if (dsi->slave) { tegra_dsi_configure(dsi->slave, pipe, mode); @@ -811,7 +814,7 @@ static const struct drm_connector_funcs tegra_dsi_connector_funcs = { static enum drm_mode_status tegra_dsi_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) + const struct drm_display_mode *mode) { return MODE_OK; } @@ -1534,12 +1537,16 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) np = of_parse_phandle(dsi->dev->of_node, "nvidia,ganged-mode", 0); if (np) { struct platform_device *gangster = of_find_device_by_node(np); + of_node_put(np); + if (!gangster) + return -EPROBE_DEFER; dsi->slave = platform_get_drvdata(gangster); - of_node_put(np); - if (!dsi->slave) + if (!dsi->slave) { + put_device(&gangster->dev); return -EPROBE_DEFER; + } dsi->slave->master = dsi; } @@ -1550,7 +1557,6 @@ static int tegra_dsi_ganged_probe(struct tegra_dsi *dsi) static int tegra_dsi_probe(struct platform_device *pdev) { struct tegra_dsi *dsi; - struct resource *regs; int err; dsi = devm_kzalloc(&pdev->dev, sizeof(*dsi), GFP_KERNEL); @@ -1582,48 +1588,57 @@ static int tegra_dsi_probe(struct platform_device *pdev) if (!pdev->dev.pm_domain) { dsi->rst = devm_reset_control_get(&pdev->dev, "dsi"); - if (IS_ERR(dsi->rst)) - return PTR_ERR(dsi->rst); + if (IS_ERR(dsi->rst)) { + err = PTR_ERR(dsi->rst); + goto remove; + } } dsi->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(dsi->clk)) { - dev_err(&pdev->dev, "cannot get DSI clock\n"); - return PTR_ERR(dsi->clk); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk), + "cannot get DSI clock\n"); + goto remove; } dsi->clk_lp = devm_clk_get(&pdev->dev, "lp"); if (IS_ERR(dsi->clk_lp)) { - dev_err(&pdev->dev, "cannot get low-power clock\n"); - return PTR_ERR(dsi->clk_lp); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_lp), + "cannot get low-power clock\n"); + goto remove; } dsi->clk_parent = devm_clk_get(&pdev->dev, "parent"); if (IS_ERR(dsi->clk_parent)) { - dev_err(&pdev->dev, "cannot get parent clock\n"); - return PTR_ERR(dsi->clk_parent); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->clk_parent), + "cannot get parent clock\n"); + goto remove; } dsi->vdd = devm_regulator_get(&pdev->dev, "avdd-dsi-csi"); if (IS_ERR(dsi->vdd)) { - dev_err(&pdev->dev, "cannot get VDD supply\n"); - return PTR_ERR(dsi->vdd); + err = dev_err_probe(&pdev->dev, PTR_ERR(dsi->vdd), + "cannot get VDD supply\n"); + goto remove; } err = tegra_dsi_setup_clocks(dsi); if (err < 0) { dev_err(&pdev->dev, "cannot setup clocks\n"); - return err; + goto remove; } - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - dsi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(dsi->regs)) - return PTR_ERR(dsi->regs); + dsi->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(dsi->regs)) { + err = PTR_ERR(dsi->regs); + goto remove; + } dsi->mipi = tegra_mipi_request(&pdev->dev, pdev->dev.of_node); - if (IS_ERR(dsi->mipi)) - return PTR_ERR(dsi->mipi); + if (IS_ERR(dsi->mipi)) { + err = PTR_ERR(dsi->mipi); + goto remove; + } dsi->host.ops = &tegra_dsi_host_ops; dsi->host.dev = &pdev->dev; @@ -1651,32 +1666,27 @@ static int tegra_dsi_probe(struct platform_device *pdev) return 0; unregister: + pm_runtime_disable(&pdev->dev); mipi_dsi_host_unregister(&dsi->host); mipi_free: tegra_mipi_free(dsi->mipi); +remove: + tegra_output_remove(&dsi->output); return err; } -static int tegra_dsi_remove(struct platform_device *pdev) +static void tegra_dsi_remove(struct platform_device *pdev) { struct tegra_dsi *dsi = platform_get_drvdata(pdev); - int err; pm_runtime_disable(&pdev->dev); - err = host1x_client_unregister(&dsi->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; - } + host1x_client_unregister(&dsi->client); tegra_output_remove(&dsi->output); mipi_dsi_host_unregister(&dsi->host); tegra_mipi_free(dsi->mipi); - - return 0; } static const struct of_device_id tegra_dsi_of_match[] = { diff --git a/drivers/gpu/drm/tegra/falcon.c b/drivers/gpu/drm/tegra/falcon.c index 223ab2ceb7e6..17f616bbcb45 100644 --- a/drivers/gpu/drm/tegra/falcon.c +++ b/drivers/gpu/drm/tegra/falcon.c @@ -30,6 +30,14 @@ int falcon_wait_idle(struct falcon *falcon) (value == 0), 10, 100000); } +static int falcon_dma_wait_not_full(struct falcon *falcon) +{ + u32 value; + + return readl_poll_timeout(falcon->regs + FALCON_DMATRFCMD, value, + !(value & FALCON_DMATRFCMD_FULL), 10, 100000); +} + static int falcon_dma_wait_idle(struct falcon *falcon) { u32 value; @@ -44,15 +52,28 @@ static int falcon_copy_chunk(struct falcon *falcon, enum falcon_memory target) { u32 cmd = FALCON_DMATRFCMD_SIZE_256B; + int err; if (target == FALCON_MEMORY_IMEM) cmd |= FALCON_DMATRFCMD_IMEM; + /* + * Use second DMA context (i.e. the one for firmware). Strictly + * speaking, at this point both DMA contexts point to the firmware + * stream ID, but this register's value will be reused by the firmware + * for later DMA transactions, so we need to use the correct value. + */ + cmd |= FALCON_DMATRFCMD_DMACTX(1); + + err = falcon_dma_wait_not_full(falcon); + if (err < 0) + return err; + falcon_writel(falcon, offset, FALCON_DMATRFMOFFS); falcon_writel(falcon, base, FALCON_DMATRFFBOFFS); falcon_writel(falcon, cmd, FALCON_DMATRFCMD); - return falcon_dma_wait_idle(falcon); + return 0; } static void falcon_copy_firmware_image(struct falcon *falcon, @@ -63,7 +84,7 @@ static void falcon_copy_firmware_image(struct falcon *falcon, /* copy the whole thing taking into account endianness */ for (i = 0; i < firmware->size / sizeof(u32); i++) - virt[i] = le32_to_cpu(((u32 *)firmware->data)[i]); + virt[i] = le32_to_cpu(((__le32 *)firmware->data)[i]); } static int falcon_parse_firmware_image(struct falcon *falcon) @@ -183,6 +204,11 @@ int falcon_boot(struct falcon *falcon) falcon_copy_chunk(falcon, falcon->firmware.code.offset + offset, offset, FALCON_MEMORY_IMEM); + /* wait for DMA to complete */ + err = falcon_dma_wait_idle(falcon); + if (err < 0) + return err; + /* setup falcon interrupts */ falcon_writel(falcon, FALCON_IRQMSET_EXT(0xff) | FALCON_IRQMSET_SWGEN1 | diff --git a/drivers/gpu/drm/tegra/falcon.h b/drivers/gpu/drm/tegra/falcon.h index c56ee32d92ee..902bb7e4fd0f 100644 --- a/drivers/gpu/drm/tegra/falcon.h +++ b/drivers/gpu/drm/tegra/falcon.h @@ -47,9 +47,11 @@ #define FALCON_DMATRFMOFFS 0x00001114 #define FALCON_DMATRFCMD 0x00001118 +#define FALCON_DMATRFCMD_FULL (1 << 0) #define FALCON_DMATRFCMD_IDLE (1 << 1) #define FALCON_DMATRFCMD_IMEM (1 << 4) #define FALCON_DMATRFCMD_SIZE_256B (6 << 8) +#define FALCON_DMATRFCMD_DMACTX(v) (((v) & 0x7) << 12) #define FALCON_DMATRFFBOFFS 0x0000111c diff --git a/drivers/gpu/drm/tegra/fb.c b/drivers/gpu/drm/tegra/fb.c index cae8b8cbe9dd..1cef8c5cac50 100644 --- a/drivers/gpu/drm/tegra/fb.c +++ b/drivers/gpu/drm/tegra/fb.c @@ -3,26 +3,21 @@ * Copyright (C) 2012-2013 Avionic Design GmbH * Copyright (C) 2012 NVIDIA CORPORATION. All rights reserved. * - * Based on the KMS/FB CMA helpers + * Based on the KMS/FB DMA helpers * Copyright (C) 2012 Analog Devices Inc. */ #include <linux/console.h> #include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_modeset_helper.h> +#include <drm/drm_print.h> #include "drm.h" #include "gem.h" -#ifdef CONFIG_DRM_FBDEV_EMULATION -static inline struct tegra_fbdev *to_tegra_fbdev(struct drm_fb_helper *helper) -{ - return container_of(helper, struct tegra_fbdev, base); -} -#endif - struct tegra_bo *tegra_fb_get_plane(struct drm_framebuffer *framebuffer, unsigned int index) { @@ -44,7 +39,7 @@ int tegra_fb_get_tiling(struct drm_framebuffer *framebuffer, { uint64_t modifier = framebuffer->modifier; - if ((modifier >> 56) == DRM_FORMAT_MOD_VENDOR_NVIDIA) { + if (fourcc_mod_is_vendor(modifier, NVIDIA)) { if ((modifier & DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT) == 0) tiling->sector_layout = TEGRA_BO_SECTOR_LAYOUT_TEGRA; else @@ -107,10 +102,11 @@ static const struct drm_framebuffer_funcs tegra_fb_funcs = { .create_handle = drm_gem_fb_create_handle, }; -static struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm, - const struct drm_mode_fb_cmd2 *mode_cmd, - struct tegra_bo **planes, - unsigned int num_planes) +struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm, + const struct drm_format_info *info, + const struct drm_mode_fb_cmd2 *mode_cmd, + struct tegra_bo **planes, + unsigned int num_planes) { struct drm_framebuffer *fb; unsigned int i; @@ -120,7 +116,7 @@ static struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm, if (!fb) return ERR_PTR(-ENOMEM); - drm_helper_mode_fill_fb_struct(drm, fb, mode_cmd); + drm_helper_mode_fill_fb_struct(drm, fb, info, mode_cmd); for (i = 0; i < fb->format->num_planes; i++) fb->obj[i] = &planes[i]->gem; @@ -138,9 +134,9 @@ static struct drm_framebuffer *tegra_fb_alloc(struct drm_device *drm, struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, struct drm_file *file, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *cmd) { - const struct drm_format_info *info = drm_get_format_info(drm, cmd); struct tegra_bo *planes[4]; struct drm_gem_object *gem; struct drm_framebuffer *fb; @@ -165,13 +161,14 @@ struct drm_framebuffer *tegra_fb_create(struct drm_device *drm, if (gem->size < size) { err = -EINVAL; + drm_gem_object_put(gem); goto unreference; } planes[i] = to_tegra_bo(gem); } - fb = tegra_fb_alloc(drm, cmd, planes, i); + fb = tegra_fb_alloc(drm, info, cmd, planes, i); if (IS_ERR(fb)) { err = PTR_ERR(fb); goto unreference; @@ -185,229 +182,3 @@ unreference: return ERR_PTR(err); } - -#ifdef CONFIG_DRM_FBDEV_EMULATION -static int tegra_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) -{ - struct drm_fb_helper *helper = info->par; - struct tegra_bo *bo; - int err; - - bo = tegra_fb_get_plane(helper->fb, 0); - - err = drm_gem_mmap_obj(&bo->gem, bo->gem.size, vma); - if (err < 0) - return err; - - return __tegra_gem_mmap(&bo->gem, vma); -} - -static const struct fb_ops tegra_fb_ops = { - .owner = THIS_MODULE, - DRM_FB_HELPER_DEFAULT_OPS, - .fb_fillrect = drm_fb_helper_sys_fillrect, - .fb_copyarea = drm_fb_helper_sys_copyarea, - .fb_imageblit = drm_fb_helper_sys_imageblit, - .fb_mmap = tegra_fb_mmap, -}; - -static int tegra_fbdev_probe(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) -{ - struct tegra_fbdev *fbdev = to_tegra_fbdev(helper); - struct tegra_drm *tegra = helper->dev->dev_private; - struct drm_device *drm = helper->dev; - struct drm_mode_fb_cmd2 cmd = { 0 }; - unsigned int bytes_per_pixel; - struct drm_framebuffer *fb; - unsigned long offset; - struct fb_info *info; - struct tegra_bo *bo; - size_t size; - int err; - - bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8); - - cmd.width = sizes->surface_width; - cmd.height = sizes->surface_height; - cmd.pitches[0] = round_up(sizes->surface_width * bytes_per_pixel, - tegra->pitch_align); - - cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, - sizes->surface_depth); - - size = cmd.pitches[0] * cmd.height; - - bo = tegra_bo_create(drm, size, 0); - if (IS_ERR(bo)) - return PTR_ERR(bo); - - info = drm_fb_helper_alloc_fbi(helper); - if (IS_ERR(info)) { - dev_err(drm->dev, "failed to allocate framebuffer info\n"); - drm_gem_object_put(&bo->gem); - return PTR_ERR(info); - } - - fbdev->fb = tegra_fb_alloc(drm, &cmd, &bo, 1); - if (IS_ERR(fbdev->fb)) { - err = PTR_ERR(fbdev->fb); - dev_err(drm->dev, "failed to allocate DRM framebuffer: %d\n", - err); - drm_gem_object_put(&bo->gem); - return PTR_ERR(fbdev->fb); - } - - fb = fbdev->fb; - helper->fb = fb; - helper->fbdev = info; - - info->fbops = &tegra_fb_ops; - - drm_fb_helper_fill_info(info, helper, sizes); - - offset = info->var.xoffset * bytes_per_pixel + - info->var.yoffset * fb->pitches[0]; - - if (bo->pages) { - bo->vaddr = vmap(bo->pages, bo->num_pages, VM_MAP, - pgprot_writecombine(PAGE_KERNEL)); - if (!bo->vaddr) { - dev_err(drm->dev, "failed to vmap() framebuffer\n"); - err = -ENOMEM; - goto destroy; - } - } - - drm->mode_config.fb_base = (resource_size_t)bo->iova; - info->screen_base = (void __iomem *)bo->vaddr + offset; - info->screen_size = size; - info->fix.smem_start = (unsigned long)(bo->iova + offset); - info->fix.smem_len = size; - - return 0; - -destroy: - drm_framebuffer_remove(fb); - return err; -} - -static const struct drm_fb_helper_funcs tegra_fb_helper_funcs = { - .fb_probe = tegra_fbdev_probe, -}; - -static struct tegra_fbdev *tegra_fbdev_create(struct drm_device *drm) -{ - struct tegra_fbdev *fbdev; - - fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL); - if (!fbdev) { - dev_err(drm->dev, "failed to allocate DRM fbdev\n"); - return ERR_PTR(-ENOMEM); - } - - drm_fb_helper_prepare(drm, &fbdev->base, &tegra_fb_helper_funcs); - - return fbdev; -} - -static void tegra_fbdev_free(struct tegra_fbdev *fbdev) -{ - kfree(fbdev); -} - -static int tegra_fbdev_init(struct tegra_fbdev *fbdev, - unsigned int preferred_bpp, - unsigned int num_crtc, - unsigned int max_connectors) -{ - struct drm_device *drm = fbdev->base.dev; - int err; - - err = drm_fb_helper_init(drm, &fbdev->base); - if (err < 0) { - dev_err(drm->dev, "failed to initialize DRM FB helper: %d\n", - err); - return err; - } - - err = drm_fb_helper_initial_config(&fbdev->base, preferred_bpp); - if (err < 0) { - dev_err(drm->dev, "failed to set initial configuration: %d\n", - err); - goto fini; - } - - return 0; - -fini: - drm_fb_helper_fini(&fbdev->base); - return err; -} - -static void tegra_fbdev_exit(struct tegra_fbdev *fbdev) -{ - drm_fb_helper_unregister_fbi(&fbdev->base); - - if (fbdev->fb) { - struct tegra_bo *bo = tegra_fb_get_plane(fbdev->fb, 0); - - /* Undo the special mapping we made in fbdev probe. */ - if (bo && bo->pages) { - vunmap(bo->vaddr); - bo->vaddr = NULL; - } - - drm_framebuffer_remove(fbdev->fb); - } - - drm_fb_helper_fini(&fbdev->base); - tegra_fbdev_free(fbdev); -} -#endif - -int tegra_drm_fb_prepare(struct drm_device *drm) -{ -#ifdef CONFIG_DRM_FBDEV_EMULATION - struct tegra_drm *tegra = drm->dev_private; - - tegra->fbdev = tegra_fbdev_create(drm); - if (IS_ERR(tegra->fbdev)) - return PTR_ERR(tegra->fbdev); -#endif - - return 0; -} - -void tegra_drm_fb_free(struct drm_device *drm) -{ -#ifdef CONFIG_DRM_FBDEV_EMULATION - struct tegra_drm *tegra = drm->dev_private; - - tegra_fbdev_free(tegra->fbdev); -#endif -} - -int tegra_drm_fb_init(struct drm_device *drm) -{ -#ifdef CONFIG_DRM_FBDEV_EMULATION - struct tegra_drm *tegra = drm->dev_private; - int err; - - err = tegra_fbdev_init(tegra->fbdev, 32, drm->mode_config.num_crtc, - drm->mode_config.num_connector); - if (err < 0) - return err; -#endif - - return 0; -} - -void tegra_drm_fb_exit(struct drm_device *drm) -{ -#ifdef CONFIG_DRM_FBDEV_EMULATION - struct tegra_drm *tegra = drm->dev_private; - - tegra_fbdev_exit(tegra->fbdev); -#endif -} diff --git a/drivers/gpu/drm/tegra/fbdev.c b/drivers/gpu/drm/tegra/fbdev.c new file mode 100644 index 000000000000..8f40882aa76e --- /dev/null +++ b/drivers/gpu/drm/tegra/fbdev.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2013 Avionic Design GmbH + * Copyright (C) 2012 NVIDIA CORPORATION. All rights reserved. + * + * Based on the KMS/FB DMA helpers + * Copyright (C) 2012 Analog Devices Inc. + */ + +#include <linux/console.h> +#include <linux/fb.h> +#include <linux/vmalloc.h> + +#include <drm/drm_drv.h> +#include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_modeset_helper.h> + +#include "drm.h" +#include "gem.h" + +static int tegra_fb_mmap(struct fb_info *info, struct vm_area_struct *vma) +{ + struct drm_fb_helper *helper = info->par; + struct tegra_bo *bo; + int err; + + bo = tegra_fb_get_plane(helper->fb, 0); + + err = drm_gem_mmap_obj(&bo->gem, bo->gem.size, vma); + if (err < 0) + return err; + + return __tegra_gem_mmap(&bo->gem, vma); +} + +static void tegra_fbdev_fb_destroy(struct fb_info *info) +{ + struct drm_fb_helper *helper = info->par; + struct drm_framebuffer *fb = helper->fb; + struct tegra_bo *bo = tegra_fb_get_plane(fb, 0); + + drm_fb_helper_fini(helper); + + /* Undo the special mapping we made in fbdev probe. */ + if (bo->pages) { + vunmap(bo->vaddr); + bo->vaddr = NULL; + } + drm_framebuffer_remove(fb); + + drm_client_release(&helper->client); +} + +static const struct fb_ops tegra_fb_ops = { + .owner = THIS_MODULE, + __FB_DEFAULT_DMAMEM_OPS_RDWR, + DRM_FB_HELPER_DEFAULT_OPS, + __FB_DEFAULT_DMAMEM_OPS_DRAW, + .fb_mmap = tegra_fb_mmap, + .fb_destroy = tegra_fbdev_fb_destroy, +}; + +static const struct drm_fb_helper_funcs tegra_fbdev_helper_funcs = { +}; + +int tegra_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, + struct drm_fb_helper_surface_size *sizes) +{ + struct tegra_drm *tegra = helper->dev->dev_private; + struct drm_device *drm = helper->dev; + struct drm_mode_fb_cmd2 cmd = { 0 }; + struct fb_info *info = helper->info; + unsigned int bytes_per_pixel; + struct drm_framebuffer *fb; + unsigned long offset; + struct tegra_bo *bo; + size_t size; + int err; + + bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8); + + cmd.width = sizes->surface_width; + cmd.height = sizes->surface_height; + cmd.pitches[0] = round_up(sizes->surface_width * bytes_per_pixel, + tegra->pitch_align); + + cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, + sizes->surface_depth); + + size = cmd.pitches[0] * cmd.height; + + bo = tegra_bo_create(drm, size, 0); + if (IS_ERR(bo)) + return PTR_ERR(bo); + + fb = tegra_fb_alloc(drm, + drm_get_format_info(drm, cmd.pixel_format, cmd.modifier[0]), + &cmd, &bo, 1); + if (IS_ERR(fb)) { + err = PTR_ERR(fb); + dev_err(drm->dev, "failed to allocate DRM framebuffer: %d\n", + err); + drm_gem_object_put(&bo->gem); + return PTR_ERR(fb); + } + + helper->funcs = &tegra_fbdev_helper_funcs; + helper->fb = fb; + helper->info = info; + + info->fbops = &tegra_fb_ops; + + drm_fb_helper_fill_info(info, helper, sizes); + + offset = info->var.xoffset * bytes_per_pixel + + info->var.yoffset * fb->pitches[0]; + + if (bo->pages) { + bo->vaddr = vmap(bo->pages, bo->num_pages, VM_MAP, + pgprot_writecombine(PAGE_KERNEL)); + if (!bo->vaddr) { + dev_err(drm->dev, "failed to vmap() framebuffer\n"); + err = -ENOMEM; + goto destroy; + } + } + + info->flags |= FBINFO_VIRTFB; + info->screen_buffer = bo->vaddr + offset; + info->screen_size = size; + info->fix.smem_start = (unsigned long)(bo->iova + offset); + info->fix.smem_len = size; + + return 0; + +destroy: + drm_framebuffer_remove(fb); + return err; +} diff --git a/drivers/gpu/drm/tegra/firewall.c b/drivers/gpu/drm/tegra/firewall.c new file mode 100644 index 000000000000..d53f890fa689 --- /dev/null +++ b/drivers/gpu/drm/tegra/firewall.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2010-2020 NVIDIA Corporation */ + +#include "drm.h" +#include "submit.h" +#include "uapi.h" + +struct tegra_drm_firewall { + struct tegra_drm_submit_data *submit; + struct tegra_drm_client *client; + u32 *data; + u32 pos; + u32 end; + u32 class; +}; + +static int fw_next(struct tegra_drm_firewall *fw, u32 *word) +{ + if (fw->pos == fw->end) + return -EINVAL; + + *word = fw->data[fw->pos++]; + + return 0; +} + +static bool fw_check_addr_valid(struct tegra_drm_firewall *fw, u32 offset) +{ + u32 i; + + for (i = 0; i < fw->submit->num_used_mappings; i++) { + struct tegra_drm_mapping *m = fw->submit->used_mappings[i].mapping; + + if (offset >= m->iova && offset <= m->iova_end) + return true; + } + + return false; +} + +static int fw_check_reg(struct tegra_drm_firewall *fw, u32 offset) +{ + bool is_addr; + u32 word; + int err; + + err = fw_next(fw, &word); + if (err) + return err; + + if (!fw->client->ops->is_addr_reg) + return 0; + + is_addr = fw->client->ops->is_addr_reg(fw->client->base.dev, fw->class, + offset); + + if (!is_addr) + return 0; + + if (!fw_check_addr_valid(fw, word)) + return -EINVAL; + + return 0; +} + +static int fw_check_regs_seq(struct tegra_drm_firewall *fw, u32 offset, + u32 count, bool incr) +{ + u32 i; + + for (i = 0; i < count; i++) { + if (fw_check_reg(fw, offset)) + return -EINVAL; + + if (incr) + offset++; + } + + return 0; +} + +static int fw_check_regs_mask(struct tegra_drm_firewall *fw, u32 offset, + u16 mask) +{ + unsigned long bmask = mask; + unsigned int bit; + + for_each_set_bit(bit, &bmask, 16) { + if (fw_check_reg(fw, offset+bit)) + return -EINVAL; + } + + return 0; +} + +static int fw_check_regs_imm(struct tegra_drm_firewall *fw, u32 offset) +{ + bool is_addr; + + if (!fw->client->ops->is_addr_reg) + return 0; + + is_addr = fw->client->ops->is_addr_reg(fw->client->base.dev, fw->class, + offset); + if (is_addr) + return -EINVAL; + + return 0; +} + +static int fw_check_class(struct tegra_drm_firewall *fw, u32 class) +{ + if (!fw->client->ops->is_valid_class) { + if (class == fw->client->base.class) + return 0; + else + return -EINVAL; + } + + if (!fw->client->ops->is_valid_class(class)) + return -EINVAL; + + return 0; +} + +enum { + HOST1X_OPCODE_SETCLASS = 0x00, + HOST1X_OPCODE_INCR = 0x01, + HOST1X_OPCODE_NONINCR = 0x02, + HOST1X_OPCODE_MASK = 0x03, + HOST1X_OPCODE_IMM = 0x04, + HOST1X_OPCODE_RESTART = 0x05, + HOST1X_OPCODE_GATHER = 0x06, + HOST1X_OPCODE_SETSTRMID = 0x07, + HOST1X_OPCODE_SETAPPID = 0x08, + HOST1X_OPCODE_SETPYLD = 0x09, + HOST1X_OPCODE_INCR_W = 0x0a, + HOST1X_OPCODE_NONINCR_W = 0x0b, + HOST1X_OPCODE_GATHER_W = 0x0c, + HOST1X_OPCODE_RESTART_W = 0x0d, + HOST1X_OPCODE_EXTEND = 0x0e, +}; + +int tegra_drm_fw_validate(struct tegra_drm_client *client, u32 *data, u32 start, + u32 words, struct tegra_drm_submit_data *submit, + u32 *job_class) +{ + struct tegra_drm_firewall fw = { + .submit = submit, + .client = client, + .data = data, + .pos = start, + .end = start+words, + .class = *job_class, + }; + bool payload_valid = false; + u32 payload; + int err; + + while (fw.pos != fw.end) { + u32 word, opcode, offset, count, mask, class; + + err = fw_next(&fw, &word); + if (err) + return err; + + opcode = (word & 0xf0000000) >> 28; + + switch (opcode) { + case HOST1X_OPCODE_SETCLASS: + offset = word >> 16 & 0xfff; + mask = word & 0x3f; + class = (word >> 6) & 0x3ff; + err = fw_check_class(&fw, class); + fw.class = class; + *job_class = class; + if (!err) + err = fw_check_regs_mask(&fw, offset, mask); + if (err) + dev_warn(client->base.dev, + "illegal SETCLASS(offset=0x%x, mask=0x%x, class=0x%x) at word %u", + offset, mask, class, fw.pos-1); + break; + case HOST1X_OPCODE_INCR: + offset = (word >> 16) & 0xfff; + count = word & 0xffff; + err = fw_check_regs_seq(&fw, offset, count, true); + if (err) + dev_warn(client->base.dev, + "illegal INCR(offset=0x%x, count=%u) in class 0x%x at word %u", + offset, count, fw.class, fw.pos-1); + break; + case HOST1X_OPCODE_NONINCR: + offset = (word >> 16) & 0xfff; + count = word & 0xffff; + err = fw_check_regs_seq(&fw, offset, count, false); + if (err) + dev_warn(client->base.dev, + "illegal NONINCR(offset=0x%x, count=%u) in class 0x%x at word %u", + offset, count, fw.class, fw.pos-1); + break; + case HOST1X_OPCODE_MASK: + offset = (word >> 16) & 0xfff; + mask = word & 0xffff; + err = fw_check_regs_mask(&fw, offset, mask); + if (err) + dev_warn(client->base.dev, + "illegal MASK(offset=0x%x, mask=0x%x) in class 0x%x at word %u", + offset, mask, fw.class, fw.pos-1); + break; + case HOST1X_OPCODE_IMM: + /* IMM cannot reasonably be used to write a pointer */ + offset = (word >> 16) & 0xfff; + err = fw_check_regs_imm(&fw, offset); + if (err) + dev_warn(client->base.dev, + "illegal IMM(offset=0x%x) in class 0x%x at word %u", + offset, fw.class, fw.pos-1); + break; + case HOST1X_OPCODE_SETPYLD: + payload = word & 0xffff; + payload_valid = true; + break; + case HOST1X_OPCODE_INCR_W: + if (!payload_valid) + return -EINVAL; + + offset = word & 0x3fffff; + err = fw_check_regs_seq(&fw, offset, payload, true); + if (err) + dev_warn(client->base.dev, + "illegal INCR_W(offset=0x%x) in class 0x%x at word %u", + offset, fw.class, fw.pos-1); + break; + case HOST1X_OPCODE_NONINCR_W: + if (!payload_valid) + return -EINVAL; + + offset = word & 0x3fffff; + err = fw_check_regs_seq(&fw, offset, payload, false); + if (err) + dev_warn(client->base.dev, + "illegal NONINCR(offset=0x%x) in class 0x%x at word %u", + offset, fw.class, fw.pos-1); + break; + default: + dev_warn(client->base.dev, "illegal opcode at word %u", + fw.pos-1); + return -EINVAL; + } + + if (err) + return err; + } + + return 0; +} diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index 26af8daa9a16..6b14f1e919eb 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -12,94 +12,110 @@ #include <linux/dma-buf.h> #include <linux/iommu.h> +#include <linux/module.h> +#include <linux/vmalloc.h> #include <drm/drm_drv.h> +#include <drm/drm_dumb_buffers.h> #include <drm/drm_prime.h> -#include <drm/tegra_drm.h> #include "drm.h" #include "gem.h" -static void tegra_bo_put(struct host1x_bo *bo) +MODULE_IMPORT_NS("DMA_BUF"); + +static unsigned int sg_dma_count_chunks(struct scatterlist *sgl, unsigned int nents) { - struct tegra_bo *obj = host1x_to_tegra_bo(bo); + dma_addr_t next = ~(dma_addr_t)0; + unsigned int count = 0, i; + struct scatterlist *s; + + for_each_sg(sgl, s, nents, i) { + /* sg_dma_address(s) is only valid for entries that have sg_dma_len(s) != 0. */ + if (!sg_dma_len(s)) + continue; + + if (sg_dma_address(s) != next) { + next = sg_dma_address(s) + sg_dma_len(s); + count++; + } + } - drm_gem_object_put(&obj->gem); + return count; } -/* XXX move this into lib/scatterlist.c? */ -static int sg_alloc_table_from_sg(struct sg_table *sgt, struct scatterlist *sg, - unsigned int nents, gfp_t gfp_mask) +static inline unsigned int sgt_dma_count_chunks(struct sg_table *sgt) { - struct scatterlist *dst; - unsigned int i; - int err; - - err = sg_alloc_table(sgt, nents, gfp_mask); - if (err < 0) - return err; - - dst = sgt->sgl; + return sg_dma_count_chunks(sgt->sgl, sgt->nents); +} - for (i = 0; i < nents; i++) { - sg_set_page(dst, sg_page(sg), sg->length, 0); - dst = sg_next(dst); - sg = sg_next(sg); - } +static void tegra_bo_put(struct host1x_bo *bo) +{ + struct tegra_bo *obj = host1x_to_tegra_bo(bo); - return 0; + drm_gem_object_put(&obj->gem); } -static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, - dma_addr_t *phys) +static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction direction) { struct tegra_bo *obj = host1x_to_tegra_bo(bo); - struct sg_table *sgt; + struct drm_gem_object *gem = &obj->gem; + struct host1x_bo_mapping *map; int err; + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return ERR_PTR(-ENOMEM); + + kref_init(&map->ref); + map->bo = host1x_bo_get(bo); + map->direction = direction; + map->dev = dev; + /* - * If we've manually mapped the buffer object through the IOMMU, make - * sure to return the IOVA address of our mapping. - * - * Similarly, for buffers that have been allocated by the DMA API the - * physical address can be used for devices that are not attached to - * an IOMMU. For these devices, callers must pass a valid pointer via - * the @phys argument. - * - * Imported buffers were also already mapped at import time, so the - * existing mapping can be reused. + * Imported buffers need special treatment to satisfy the semantics of DMA-BUF. */ - if (phys) { - *phys = obj->iova; - return NULL; + if (obj->dma_buf) { + struct dma_buf *buf = obj->dma_buf; + + map->attach = dma_buf_attach(buf, dev); + if (IS_ERR(map->attach)) { + err = PTR_ERR(map->attach); + goto free; + } + + map->sgt = dma_buf_map_attachment_unlocked(map->attach, direction); + if (IS_ERR(map->sgt)) { + dma_buf_detach(buf, map->attach); + err = PTR_ERR(map->sgt); + map->sgt = NULL; + goto free; + } + + err = sgt_dma_count_chunks(map->sgt); + map->size = gem->size; + + goto out; } /* * If we don't have a mapping for this buffer yet, return an SG table * so that host1x can do the mapping for us via the DMA API. */ - sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); - if (!sgt) - return ERR_PTR(-ENOMEM); + map->sgt = kzalloc(sizeof(*map->sgt), GFP_KERNEL); + if (!map->sgt) { + err = -ENOMEM; + goto free; + } if (obj->pages) { /* * If the buffer object was allocated from the explicit IOMMU * API code paths, construct an SG table from the pages. */ - err = sg_alloc_table_from_pages(sgt, obj->pages, obj->num_pages, - 0, obj->gem.size, GFP_KERNEL); - if (err < 0) - goto free; - } else if (obj->sgt) { - /* - * If the buffer object already has an SG table but no pages - * were allocated for it, it means the buffer was imported and - * the SG table needs to be copied to avoid overwriting any - * other potential users of the original SG table. - */ - err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, - obj->sgt->orig_nents, GFP_KERNEL); + err = sg_alloc_table_from_pages(map->sgt, obj->pages, obj->num_pages, 0, gem->size, + GFP_KERNEL); if (err < 0) goto free; } else { @@ -108,55 +124,94 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, * not imported, it had to be allocated with the DMA API, so * the DMA API helper can be used. */ - err = dma_get_sgtable(dev, sgt, obj->vaddr, obj->iova, - obj->gem.size); + err = dma_get_sgtable(dev, map->sgt, obj->vaddr, obj->iova, gem->size); if (err < 0) goto free; } - return sgt; + err = dma_map_sgtable(dev, map->sgt, direction, 0); + if (err) + goto free_sgt; + +out: + /* + * If we've manually mapped the buffer object through the IOMMU, make sure to return the + * existing IOVA address of our mapping. + */ + if (!obj->mm) { + map->phys = sg_dma_address(map->sgt->sgl); + map->chunks = err; + } else { + map->phys = obj->iova; + map->chunks = 1; + } + + map->size = gem->size; + + return map; +free_sgt: + sg_free_table(map->sgt); free: - kfree(sgt); + kfree(map->sgt); + kfree(map); return ERR_PTR(err); } -static void tegra_bo_unpin(struct device *dev, struct sg_table *sgt) +static void tegra_bo_unpin(struct host1x_bo_mapping *map) { - if (sgt) { - sg_free_table(sgt); - kfree(sgt); + if (map->attach) { + dma_buf_unmap_attachment_unlocked(map->attach, map->sgt, + map->direction); + dma_buf_detach(map->attach->dmabuf, map->attach); + } else { + dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0); + sg_free_table(map->sgt); + kfree(map->sgt); } + + host1x_bo_put(map->bo); + kfree(map); } static void *tegra_bo_mmap(struct host1x_bo *bo) { struct tegra_bo *obj = host1x_to_tegra_bo(bo); - struct dma_buf_map map; + struct iosys_map map = { 0 }; + void *vaddr; int ret; - if (obj->vaddr) { + if (obj->vaddr) return obj->vaddr; - } else if (obj->gem.import_attach) { - ret = dma_buf_vmap(obj->gem.import_attach->dmabuf, &map); - return ret ? NULL : map.vaddr; - } else { - return vmap(obj->pages, obj->num_pages, VM_MAP, - pgprot_writecombine(PAGE_KERNEL)); + + if (obj->dma_buf) { + ret = dma_buf_vmap_unlocked(obj->dma_buf, &map); + if (ret < 0) + return ERR_PTR(ret); + + return map.vaddr; } + + vaddr = vmap(obj->pages, obj->num_pages, VM_MAP, + pgprot_writecombine(PAGE_KERNEL)); + if (!vaddr) + return ERR_PTR(-ENOMEM); + + return vaddr; } static void tegra_bo_munmap(struct host1x_bo *bo, void *addr) { struct tegra_bo *obj = host1x_to_tegra_bo(bo); - struct dma_buf_map map = DMA_BUF_MAP_INIT_VADDR(addr); + struct iosys_map map = IOSYS_MAP_INIT_VADDR(addr); if (obj->vaddr) return; - else if (obj->gem.import_attach) - dma_buf_vunmap(obj->gem.import_attach->dmabuf, &map); - else - vunmap(addr); + + if (obj->dma_buf) + return dma_buf_vunmap_unlocked(obj->dma_buf, &map); + + vunmap(addr); } static struct host1x_bo *tegra_bo_get(struct host1x_bo *bo) @@ -410,33 +465,38 @@ static struct tegra_bo *tegra_bo_import(struct drm_device *drm, if (IS_ERR(bo)) return bo; - attach = dma_buf_attach(buf, drm->dev); - if (IS_ERR(attach)) { - err = PTR_ERR(attach); - goto free; - } - - get_dma_buf(buf); + /* + * If we need to use IOMMU API to map the dma-buf into the internally managed + * domain, map it first to the DRM device to get an sgt. + */ + if (tegra->domain) { + attach = dma_buf_attach(buf, drm->dev); + if (IS_ERR(attach)) { + err = PTR_ERR(attach); + goto free; + } - bo->sgt = dma_buf_map_attachment(attach, DMA_TO_DEVICE); - if (IS_ERR(bo->sgt)) { - err = PTR_ERR(bo->sgt); - goto detach; - } + bo->sgt = dma_buf_map_attachment_unlocked(attach, DMA_TO_DEVICE); + if (IS_ERR(bo->sgt)) { + err = PTR_ERR(bo->sgt); + goto detach; + } - if (tegra->domain) { err = tegra_bo_iommu_map(tegra, bo); if (err < 0) goto detach; + + bo->gem.import_attach = attach; } - bo->gem.import_attach = attach; + get_dma_buf(buf); + bo->dma_buf = buf; return bo; detach: if (!IS_ERR_OR_NULL(bo->sgt)) - dma_buf_unmap_attachment(attach, bo->sgt, DMA_TO_DEVICE); + dma_buf_unmap_attachment_unlocked(attach, bo->sgt, DMA_TO_DEVICE); dma_buf_detach(buf, attach); dma_buf_put(buf); @@ -449,19 +509,33 @@ free: void tegra_bo_free_object(struct drm_gem_object *gem) { struct tegra_drm *tegra = gem->dev->dev_private; + struct host1x_bo_mapping *mapping, *tmp; struct tegra_bo *bo = to_tegra_bo(gem); - if (tegra->domain) + /* remove all mappings of this buffer object from any caches */ + list_for_each_entry_safe(mapping, tmp, &bo->base.mappings, list) { + if (mapping->cache) + host1x_bo_unpin(mapping); + else + dev_err(gem->dev->dev, "mapping %p stale for device %s\n", mapping, + dev_name(mapping->dev)); + } + + if (tegra->domain) { tegra_bo_iommu_unmap(tegra, bo); - if (gem->import_attach) { - dma_buf_unmap_attachment(gem->import_attach, bo->sgt, - DMA_TO_DEVICE); - drm_prime_gem_destroy(gem, NULL); - } else { - tegra_bo_free(gem->dev, bo); + if (drm_gem_is_imported(gem)) { + dma_buf_unmap_attachment_unlocked(gem->import_attach, bo->sgt, + DMA_TO_DEVICE); + dma_buf_detach(gem->import_attach->dmabuf, gem->import_attach); + } } + tegra_bo_free(gem->dev, bo); + + if (bo->dma_buf) + dma_buf_put(bo->dma_buf); + drm_gem_object_release(gem); kfree(bo); } @@ -469,12 +543,13 @@ void tegra_bo_free_object(struct drm_gem_object *gem) int tegra_bo_dumb_create(struct drm_file *file, struct drm_device *drm, struct drm_mode_create_dumb *args) { - unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8); struct tegra_drm *tegra = drm->dev_private; struct tegra_bo *bo; + int ret; - args->pitch = round_up(min_pitch, tegra->pitch_align); - args->size = args->pitch * args->height; + ret = drm_mode_size_dumb(drm, args, tegra->pitch_align, 0); + if (ret) + return ret; bo = tegra_bo_create_with_handle(file, drm, args->size, 0, &args->handle); @@ -520,7 +595,7 @@ int __tegra_gem_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma) * and set the vm_pgoff (used as a fake buffer offset by DRM) * to 0 as we want to map the whole buffer. */ - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_clear(vma, VM_PFNMAP); vma->vm_pgoff = 0; err = dma_mmap_wc(gem->dev->dev, vma, bo->vaddr, bo->iova, @@ -534,8 +609,7 @@ int __tegra_gem_mmap(struct drm_gem_object *gem, struct vm_area_struct *vma) } else { pgprot_t prot = vm_get_page_prot(vma->vm_flags); - vma->vm_flags |= VM_MIXEDMAP; - vma->vm_flags &= ~VM_PFNMAP; + vm_flags_mod(vma, VM_MIXEDMAP, VM_PFNMAP); vma->vm_page_prot = pgprot_writecombine(prot); } @@ -647,18 +721,27 @@ static int tegra_gem_prime_mmap(struct dma_buf *buf, struct vm_area_struct *vma) return __tegra_gem_mmap(gem, vma); } -static int tegra_gem_prime_vmap(struct dma_buf *buf, struct dma_buf_map *map) +static int tegra_gem_prime_vmap(struct dma_buf *buf, struct iosys_map *map) { struct drm_gem_object *gem = buf->priv; struct tegra_bo *bo = to_tegra_bo(gem); + void *vaddr; - dma_buf_map_set_vaddr(map, bo->vaddr); + vaddr = tegra_bo_mmap(&bo->base); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + iosys_map_set_vaddr(map, vaddr); return 0; } -static void tegra_gem_prime_vunmap(struct dma_buf *buf, struct dma_buf_map *map) +static void tegra_gem_prime_vunmap(struct dma_buf *buf, struct iosys_map *map) { + struct drm_gem_object *gem = buf->priv; + struct tegra_bo *bo = to_tegra_bo(gem); + + tegra_bo_munmap(&bo->base, map->vaddr); } static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = { @@ -707,3 +790,16 @@ struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm, return &bo->gem; } + +struct host1x_bo *tegra_gem_lookup(struct drm_file *file, u32 handle) +{ + struct drm_gem_object *gem; + struct tegra_bo *bo; + + gem = drm_gem_object_lookup(file, handle); + if (!gem) + return NULL; + + bo = to_tegra_bo(gem); + return &bo->base; +} diff --git a/drivers/gpu/drm/tegra/gem.h b/drivers/gpu/drm/tegra/gem.h index c15fd99d6cb2..bf2cbd48eb3f 100644 --- a/drivers/gpu/drm/tegra/gem.h +++ b/drivers/gpu/drm/tegra/gem.h @@ -32,6 +32,26 @@ struct tegra_bo_tiling { enum tegra_bo_sector_layout sector_layout; }; +/* + * How memory is referenced within a tegra_bo: + * + * Buffer source | Mapping API(*) | Fields + * ---------------+-----------------+--------------- + * Allocated here | DMA API | iova (IOVA mapped to drm->dev), vaddr (CPU VA) + * + * Allocated here | IOMMU API | pages/num_pages (Phys. memory), sgt (Mapped to drm->dev), + * | iova/size (Mapped to domain) + * + * Imported | DMA API | dma_buf (Imported dma_buf) + * + * Imported | IOMMU API | dma_buf (Imported dma_buf), + * | gem->import_attach (Attachment on drm->dev), + * | sgt (Mapped to drm->dev) + * | iova/size (Mapped to domain) + * + * (*) If tegra->domain is set, i.e. TegraDRM IOMMU domain is directly managed through IOMMU API, + * this is IOMMU API. Otherwise DMA API. + */ struct tegra_bo { struct drm_gem_object gem; struct host1x_bo base; @@ -39,6 +59,7 @@ struct tegra_bo { struct sg_table *sgt; dma_addr_t iova; void *vaddr; + struct dma_buf *dma_buf; struct drm_mm_node *mm; unsigned long num_pages; @@ -80,4 +101,6 @@ struct dma_buf *tegra_gem_prime_export(struct drm_gem_object *gem, struct drm_gem_object *tegra_gem_prime_import(struct drm_device *drm, struct dma_buf *buf); +struct host1x_bo *tegra_gem_lookup(struct drm_file *file, u32 handle); + #endif diff --git a/drivers/gpu/drm/tegra/gr2d.c b/drivers/gpu/drm/tegra/gr2d.c index de288cba3905..21f4dd0fa6af 100644 --- a/drivers/gpu/drm/tegra/gr2d.c +++ b/drivers/gpu/drm/tegra/gr2d.c @@ -4,14 +4,26 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/iommu.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> + +#include <soc/tegra/common.h> #include "drm.h" #include "gem.h" #include "gr2d.h" +enum { + RST_MC, + RST_GR2D, + RST_GR2D_MAX, +}; + struct gr2d_soc { unsigned int version; }; @@ -21,6 +33,9 @@ struct gr2d { struct host1x_channel *channel; struct clk *clk; + struct reset_control_bulk_data resets[RST_GR2D_MAX]; + unsigned int nresets; + const struct gr2d_soc *soc; DECLARE_BITMAP(addr_regs, GR2D_NUM_REGS); @@ -59,12 +74,12 @@ static int gr2d_init(struct host1x_client *client) err = tegra_drm_register_client(dev->dev_private, drm); if (err < 0) { dev_err(client->dev, "failed to register client: %d\n", err); - goto detach; + goto detach_iommu; } return 0; -detach: +detach_iommu: host1x_client_iommu_detach(client); free: host1x_syncpt_put(client->syncpts[0]); @@ -85,10 +100,15 @@ static int gr2d_exit(struct host1x_client *client) if (err < 0) return err; + pm_runtime_dont_use_autosuspend(client->dev); + pm_runtime_force_suspend(client->dev); + host1x_client_iommu_detach(client); host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(gr2d->channel); + gr2d->channel = NULL; + return 0; } @@ -190,6 +210,27 @@ static const u32 gr2d_addr_regs[] = { GR2D_VA_BASE_ADDR_SB, }; +static int gr2d_get_resets(struct device *dev, struct gr2d *gr2d) +{ + int err; + + gr2d->resets[RST_MC].id = "mc"; + gr2d->resets[RST_GR2D].id = "2d"; + gr2d->nresets = RST_GR2D_MAX; + + err = devm_reset_control_bulk_get_optional_exclusive_released( + dev, gr2d->nresets, gr2d->resets); + if (err) { + dev_err(dev, "failed to get reset: %d\n", err); + return err; + } + + if (WARN_ON(!gr2d->resets[RST_GR2D].rstc)) + return -ENOENT; + + return 0; +} + static int gr2d_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -202,6 +243,8 @@ static int gr2d_probe(struct platform_device *pdev) if (!gr2d) return -ENOMEM; + platform_set_drvdata(pdev, gr2d); + gr2d->soc = of_device_get_match_data(dev); syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL); @@ -214,11 +257,9 @@ static int gr2d_probe(struct platform_device *pdev) return PTR_ERR(gr2d->clk); } - err = clk_prepare_enable(gr2d->clk); - if (err) { - dev_err(dev, "cannot turn on clock\n"); + err = gr2d_get_resets(dev, gr2d); + if (err) return err; - } INIT_LIST_HEAD(&gr2d->client.base.list); gr2d->client.base.ops = &gr2d_client_ops; @@ -231,10 +272,13 @@ static int gr2d_probe(struct platform_device *pdev) gr2d->client.version = gr2d->soc->version; gr2d->client.ops = &gr2d_ops; + err = devm_tegra_core_dev_init_opp_table_common(dev); + if (err) + return err; + err = host1x_client_register(&gr2d->client.base); if (err < 0) { dev_err(dev, "failed to register host1x client: %d\n", err); - clk_disable_unprepare(gr2d->clk); return err; } @@ -242,32 +286,112 @@ static int gr2d_probe(struct platform_device *pdev) for (i = 0; i < ARRAY_SIZE(gr2d_addr_regs); i++) set_bit(gr2d_addr_regs[i], gr2d->addr_regs); - platform_set_drvdata(pdev, gr2d); - return 0; } -static int gr2d_remove(struct platform_device *pdev) +static void gr2d_remove(struct platform_device *pdev) { struct gr2d *gr2d = platform_get_drvdata(pdev); + + pm_runtime_disable(&pdev->dev); + host1x_client_unregister(&gr2d->client.base); +} + +static int __maybe_unused gr2d_runtime_suspend(struct device *dev) +{ + struct gr2d *gr2d = dev_get_drvdata(dev); int err; - err = host1x_client_unregister(&gr2d->client.base); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; + host1x_channel_stop(gr2d->channel); + reset_control_bulk_release(gr2d->nresets, gr2d->resets); + + /* + * GR2D module shouldn't be reset while hardware is idling, otherwise + * host1x's cmdproc will stuck on trying to access any G2 register + * after reset. GR2D module could be either hot-reset or reset after + * power-gating of the HEG partition. Hence we will put in reset only + * the memory client part of the module, the HEG GENPD will take care + * of resetting GR2D module across power-gating. + * + * On Tegra20 there is no HEG partition, but it's okay to have + * undetermined h/w state since userspace is expected to reprogram + * the state on each job submission anyways. + */ + err = reset_control_acquire(gr2d->resets[RST_MC].rstc); + if (err) { + dev_err(dev, "failed to acquire MC reset: %d\n", err); + goto acquire_reset; + } + + err = reset_control_assert(gr2d->resets[RST_MC].rstc); + reset_control_release(gr2d->resets[RST_MC].rstc); + if (err) { + dev_err(dev, "failed to assert MC reset: %d\n", err); + goto acquire_reset; } clk_disable_unprepare(gr2d->clk); return 0; + +acquire_reset: + reset_control_bulk_acquire(gr2d->nresets, gr2d->resets); + reset_control_bulk_deassert(gr2d->nresets, gr2d->resets); + + return err; } +static int __maybe_unused gr2d_runtime_resume(struct device *dev) +{ + struct gr2d *gr2d = dev_get_drvdata(dev); + int err; + + err = reset_control_bulk_acquire(gr2d->nresets, gr2d->resets); + if (err) { + dev_err(dev, "failed to acquire reset: %d\n", err); + return err; + } + + err = clk_prepare_enable(gr2d->clk); + if (err) { + dev_err(dev, "failed to enable clock: %d\n", err); + goto release_reset; + } + + usleep_range(2000, 4000); + + /* this is a reset array which deasserts both 2D MC and 2D itself */ + err = reset_control_bulk_deassert(gr2d->nresets, gr2d->resets); + if (err) { + dev_err(dev, "failed to deassert reset: %d\n", err); + goto disable_clk; + } + + pm_runtime_enable(dev); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_autosuspend_delay(dev, 500); + + return 0; + +disable_clk: + clk_disable_unprepare(gr2d->clk); +release_reset: + reset_control_bulk_release(gr2d->nresets, gr2d->resets); + + return err; +} + +static const struct dev_pm_ops tegra_gr2d_pm = { + SET_RUNTIME_PM_OPS(gr2d_runtime_suspend, gr2d_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) +}; + struct platform_driver tegra_gr2d_driver = { .driver = { .name = "tegra-gr2d", .of_match_table = gr2d_match, + .pm = &tegra_gr2d_pm, }, .probe = gr2d_probe, .remove = gr2d_remove, diff --git a/drivers/gpu/drm/tegra/gr3d.c b/drivers/gpu/drm/tegra/gr3d.c index 24442ade0da3..42e9656ab80c 100644 --- a/drivers/gpu/drm/tegra/gr3d.c +++ b/drivers/gpu/drm/tegra/gr3d.c @@ -5,32 +5,48 @@ */ #include <linux/clk.h> +#include <linux/delay.h> #include <linux/host1x.h> #include <linux/iommu.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_opp.h> +#include <linux/pm_runtime.h> #include <linux/reset.h> +#include <soc/tegra/common.h> #include <soc/tegra/pmc.h> #include "drm.h" #include "gem.h" #include "gr3d.h" +enum { + RST_MC, + RST_GR3D, + RST_MC2, + RST_GR3D2, + RST_GR3D_MAX, +}; + struct gr3d_soc { unsigned int version; + unsigned int num_clocks; + unsigned int num_resets; }; struct gr3d { struct tegra_drm_client client; struct host1x_channel *channel; - struct clk *clk_secondary; - struct clk *clk; - struct reset_control *rst_secondary; - struct reset_control *rst; const struct gr3d_soc *soc; + struct clk_bulk_data *clocks; + unsigned int nclocks; + struct reset_control_bulk_data resets[RST_GR3D_MAX]; + unsigned int nresets; + struct dev_pm_domain_list *pd_list; DECLARE_BITMAP(addr_regs, GR3D_NUM_REGS); }; @@ -68,12 +84,12 @@ static int gr3d_init(struct host1x_client *client) err = tegra_drm_register_client(dev->dev_private, drm); if (err < 0) { dev_err(client->dev, "failed to register client: %d\n", err); - goto detach; + goto detach_iommu; } return 0; -detach: +detach_iommu: host1x_client_iommu_detach(client); free: host1x_syncpt_put(client->syncpts[0]); @@ -93,10 +109,15 @@ static int gr3d_exit(struct host1x_client *client) if (err < 0) return err; + pm_runtime_dont_use_autosuspend(client->dev); + pm_runtime_force_suspend(client->dev); + host1x_client_iommu_detach(client); host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(gr3d->channel); + gr3d->channel = NULL; + return 0; } @@ -155,14 +176,20 @@ static const struct tegra_drm_client_ops gr3d_ops = { static const struct gr3d_soc tegra20_gr3d_soc = { .version = 0x20, + .num_clocks = 1, + .num_resets = 2, }; static const struct gr3d_soc tegra30_gr3d_soc = { .version = 0x30, + .num_clocks = 2, + .num_resets = 4, }; static const struct gr3d_soc tegra114_gr3d_soc = { .version = 0x35, + .num_clocks = 1, + .num_resets = 2, }; static const struct of_device_id tegra_gr3d_match[] = { @@ -278,9 +305,163 @@ static const u32 gr3d_addr_regs[] = { GR3D_GLOBAL_SAMP23SURFADDR(15), }; +static int gr3d_power_up_legacy_domain(struct device *dev, const char *name, + unsigned int id) +{ + struct gr3d *gr3d = dev_get_drvdata(dev); + struct reset_control *reset; + struct clk *clk; + unsigned int i; + int err; + + /* + * Tegra20 device-tree doesn't specify 3d clock name and there is only + * one clock for Tegra20. Tegra30+ device-trees always specified names + * for the clocks. + */ + if (gr3d->nclocks == 1) { + if (id == TEGRA_POWERGATE_3D1) + return 0; + + clk = gr3d->clocks[0].clk; + } else { + for (i = 0; i < gr3d->nclocks; i++) { + if (WARN_ON(!gr3d->clocks[i].id)) + continue; + + if (!strcmp(gr3d->clocks[i].id, name)) { + clk = gr3d->clocks[i].clk; + break; + } + } + + if (WARN_ON(i == gr3d->nclocks)) + return -EINVAL; + } + + /* + * We use array of resets, which includes MC resets, and MC + * reset shouldn't be asserted while hardware is gated because + * MC flushing will fail for gated hardware. Hence for legacy + * PD we request the individual reset separately. + */ + reset = reset_control_get_exclusive_released(dev, name); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + err = reset_control_acquire(reset); + if (err) { + dev_err(dev, "failed to acquire %s reset: %d\n", name, err); + } else { + err = tegra_powergate_sequence_power_up(id, clk, reset); + reset_control_release(reset); + } + + reset_control_put(reset); + if (err) + return err; + + /* + * tegra_powergate_sequence_power_up() leaves clocks enabled, + * while GENPD not. Hence keep clock-enable balanced. + */ + clk_disable_unprepare(clk); + + return 0; +} + +static int gr3d_init_power(struct device *dev, struct gr3d *gr3d) +{ + struct dev_pm_domain_attach_data pd_data = { + .pd_names = (const char *[]) { "3d0", "3d1" }, + .num_pd_names = 2, + .pd_flags = PD_FLAG_REQUIRED_OPP, + }; + int err; + + err = of_count_phandle_with_args(dev->of_node, "power-domains", + "#power-domain-cells"); + if (err < 0) { + if (err != -ENOENT) + return err; + + /* + * Older device-trees don't use GENPD. In this case we should + * toggle power domain manually. + */ + err = gr3d_power_up_legacy_domain(dev, "3d", + TEGRA_POWERGATE_3D); + if (err) + return err; + + err = gr3d_power_up_legacy_domain(dev, "3d2", + TEGRA_POWERGATE_3D1); + if (err) + return err; + + return 0; + } + + /* + * The PM domain core automatically attaches a single power domain, + * otherwise it skips attaching completely. We have a single domain + * on Tegra20 and two domains on Tegra30+. + */ + if (dev->pm_domain) + return 0; + + err = devm_pm_domain_attach_list(dev, &pd_data, &gr3d->pd_list); + if (err < 0) + return err; + + return 0; +} + +static int gr3d_get_clocks(struct device *dev, struct gr3d *gr3d) +{ + int err; + + err = devm_clk_bulk_get_all(dev, &gr3d->clocks); + if (err < 0) { + dev_err(dev, "failed to get clock: %d\n", err); + return err; + } + gr3d->nclocks = err; + + if (gr3d->nclocks != gr3d->soc->num_clocks) { + dev_err(dev, "invalid number of clocks: %u\n", gr3d->nclocks); + return -ENOENT; + } + + return 0; +} + +static int gr3d_get_resets(struct device *dev, struct gr3d *gr3d) +{ + int err; + + gr3d->resets[RST_MC].id = "mc"; + gr3d->resets[RST_MC2].id = "mc2"; + gr3d->resets[RST_GR3D].id = "3d"; + gr3d->resets[RST_GR3D2].id = "3d2"; + gr3d->nresets = gr3d->soc->num_resets; + + err = devm_reset_control_bulk_get_optional_exclusive_released( + dev, gr3d->nresets, gr3d->resets); + if (err) { + dev_err(dev, "failed to get reset: %d\n", err); + return err; + } + + if (WARN_ON(!gr3d->resets[RST_GR3D].rstc) || + WARN_ON(!gr3d->resets[RST_GR3D2].rstc && gr3d->nresets == 4)) + return -ENOENT; + + return 0; +} + static int gr3d_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; struct host1x_syncpt **syncpts; struct gr3d *gr3d; unsigned int i; @@ -290,56 +471,25 @@ static int gr3d_probe(struct platform_device *pdev) if (!gr3d) return -ENOMEM; + platform_set_drvdata(pdev, gr3d); + gr3d->soc = of_device_get_match_data(&pdev->dev); syncpts = devm_kzalloc(&pdev->dev, sizeof(*syncpts), GFP_KERNEL); if (!syncpts) return -ENOMEM; - gr3d->clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(gr3d->clk)) { - dev_err(&pdev->dev, "cannot get clock\n"); - return PTR_ERR(gr3d->clk); - } - - gr3d->rst = devm_reset_control_get(&pdev->dev, "3d"); - if (IS_ERR(gr3d->rst)) { - dev_err(&pdev->dev, "cannot get reset\n"); - return PTR_ERR(gr3d->rst); - } - - if (of_device_is_compatible(np, "nvidia,tegra30-gr3d")) { - gr3d->clk_secondary = devm_clk_get(&pdev->dev, "3d2"); - if (IS_ERR(gr3d->clk_secondary)) { - dev_err(&pdev->dev, "cannot get secondary clock\n"); - return PTR_ERR(gr3d->clk_secondary); - } - - gr3d->rst_secondary = devm_reset_control_get(&pdev->dev, - "3d2"); - if (IS_ERR(gr3d->rst_secondary)) { - dev_err(&pdev->dev, "cannot get secondary reset\n"); - return PTR_ERR(gr3d->rst_secondary); - } - } + err = gr3d_get_clocks(&pdev->dev, gr3d); + if (err) + return err; - err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D, gr3d->clk, - gr3d->rst); - if (err < 0) { - dev_err(&pdev->dev, "failed to power up 3D unit\n"); + err = gr3d_get_resets(&pdev->dev, gr3d); + if (err) return err; - } - if (gr3d->clk_secondary) { - err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_3D1, - gr3d->clk_secondary, - gr3d->rst_secondary); - if (err < 0) { - dev_err(&pdev->dev, - "failed to power up secondary 3D unit\n"); - return err; - } - } + err = gr3d_init_power(&pdev->dev, gr3d); + if (err) + return err; INIT_LIST_HEAD(&gr3d->client.base.list); gr3d->client.base.ops = &gr3d_client_ops; @@ -352,6 +502,10 @@ static int gr3d_probe(struct platform_device *pdev) gr3d->client.version = gr3d->soc->version; gr3d->client.ops = &gr3d_ops; + err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); + if (err) + return err; + err = host1x_client_register(&gr3d->client.base); if (err < 0) { dev_err(&pdev->dev, "failed to register host1x client: %d\n", @@ -363,40 +517,92 @@ static int gr3d_probe(struct platform_device *pdev) for (i = 0; i < ARRAY_SIZE(gr3d_addr_regs); i++) set_bit(gr3d_addr_regs[i], gr3d->addr_regs); - platform_set_drvdata(pdev, gr3d); - return 0; } -static int gr3d_remove(struct platform_device *pdev) +static void gr3d_remove(struct platform_device *pdev) { struct gr3d *gr3d = platform_get_drvdata(pdev); + + pm_runtime_disable(&pdev->dev); + host1x_client_unregister(&gr3d->client.base); +} + +static int __maybe_unused gr3d_runtime_suspend(struct device *dev) +{ + struct gr3d *gr3d = dev_get_drvdata(dev); int err; - err = host1x_client_unregister(&gr3d->client.base); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); + host1x_channel_stop(gr3d->channel); + + err = reset_control_bulk_assert(gr3d->nresets, gr3d->resets); + if (err) { + dev_err(dev, "failed to assert reset: %d\n", err); + return err; + } + + usleep_range(10, 20); + + /* + * Older device-trees don't specify MC resets and power-gating can't + * be done safely in that case. Hence we will keep the power ungated + * for older DTBs. For newer DTBs, GENPD will perform the power-gating. + */ + + clk_bulk_disable_unprepare(gr3d->nclocks, gr3d->clocks); + reset_control_bulk_release(gr3d->nresets, gr3d->resets); + + return 0; +} + +static int __maybe_unused gr3d_runtime_resume(struct device *dev) +{ + struct gr3d *gr3d = dev_get_drvdata(dev); + int err; + + err = reset_control_bulk_acquire(gr3d->nresets, gr3d->resets); + if (err) { + dev_err(dev, "failed to acquire reset: %d\n", err); return err; } - if (gr3d->clk_secondary) { - reset_control_assert(gr3d->rst_secondary); - tegra_powergate_power_off(TEGRA_POWERGATE_3D1); - clk_disable_unprepare(gr3d->clk_secondary); + err = clk_bulk_prepare_enable(gr3d->nclocks, gr3d->clocks); + if (err) { + dev_err(dev, "failed to enable clock: %d\n", err); + goto release_reset; } - reset_control_assert(gr3d->rst); - tegra_powergate_power_off(TEGRA_POWERGATE_3D); - clk_disable_unprepare(gr3d->clk); + err = reset_control_bulk_deassert(gr3d->nresets, gr3d->resets); + if (err) { + dev_err(dev, "failed to deassert reset: %d\n", err); + goto disable_clk; + } + + pm_runtime_enable(dev); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_autosuspend_delay(dev, 500); return 0; + +disable_clk: + clk_bulk_disable_unprepare(gr3d->nclocks, gr3d->clocks); +release_reset: + reset_control_bulk_release(gr3d->nresets, gr3d->resets); + + return err; } +static const struct dev_pm_ops tegra_gr3d_pm = { + SET_RUNTIME_PM_OPS(gr3d_runtime_suspend, gr3d_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) +}; + struct platform_driver tegra_gr3d_driver = { .driver = { .name = "tegra-gr3d", .of_match_table = tegra_gr3d_match, + .pm = &tegra_gr3d_pm, }, .probe = gr3d_probe, .remove = gr3d_remove, diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c index e5d2a4026028..0adcd4244a42 100644 --- a/drivers/gpu/drm/tegra/hdmi.c +++ b/drivers/gpu/drm/tegra/hdmi.c @@ -10,16 +10,25 @@ #include <linux/hdmi.h> #include <linux/math64.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_opp.h> #include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> #include <linux/reset.h> +#include <soc/tegra/common.h> +#include <sound/hdmi-codec.h> + +#include <drm/drm_bridge_connector.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_crtc.h> #include <drm/drm_debugfs.h> +#include <drm/drm_edid.h> +#include <drm/drm_eld.h> #include <drm/drm_file.h> #include <drm/drm_fourcc.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <drm/drm_simple_kms_helper.h> @@ -78,6 +87,9 @@ struct tegra_hdmi { bool dvi; struct drm_info_list *debugfs_files; + + struct platform_device *audio_pdev; + struct mutex audio_lock; }; static inline struct tegra_hdmi * @@ -360,6 +372,18 @@ static const struct tmds_config tegra124_tmds_config[] = { }, }; +static void tegra_hdmi_audio_lock(struct tegra_hdmi *hdmi) +{ + mutex_lock(&hdmi->audio_lock); + disable_irq(hdmi->irq); +} + +static void tegra_hdmi_audio_unlock(struct tegra_hdmi *hdmi) +{ + enable_irq(hdmi->irq); + mutex_unlock(&hdmi->audio_lock); +} + static int tegra_hdmi_get_audio_config(unsigned int audio_freq, unsigned int pix_clock, struct tegra_hdmi_audio_config *config) @@ -411,7 +435,7 @@ tegra_hdmi_get_audio_config(unsigned int audio_freq, unsigned int pix_clock, static void tegra_hdmi_setup_audio_fs_tables(struct tegra_hdmi *hdmi) { - const unsigned int freqs[] = { + static const unsigned int freqs[] = { 32000, 44100, 48000, 88200, 96000, 176400, 192000 }; unsigned int i; @@ -635,7 +659,7 @@ static void tegra_hdmi_write_infopack(struct tegra_hdmi *hdmi, const void *data, { const u8 *ptr = data; unsigned long offset; - size_t i, j; + size_t i; u32 value; switch (ptr[0]) { @@ -668,7 +692,7 @@ static void tegra_hdmi_write_infopack(struct tegra_hdmi *hdmi, const void *data, * - subpack_low: bytes 0 - 3 * - subpack_high: bytes 4 - 6 (with byte 7 padded to 0x00) */ - for (i = 3, j = 0; i < size; i += 7, j += 8) { + for (i = 3; i < size; i += 7) { size_t rem = size - i, num = min_t(size_t, rem, 4); value = tegra_hdmi_subpack(&ptr[i], num); @@ -829,16 +853,26 @@ static void tegra_hdmi_setup_tmds(struct tegra_hdmi *hdmi, HDMI_NV_PDISP_SOR_IO_PEAK_CURRENT); } -static bool tegra_output_is_hdmi(struct tegra_output *output) +static int tegra_hdmi_reconfigure_audio(struct tegra_hdmi *hdmi) { - struct edid *edid; + int err; - if (!output->connector.edid_blob_ptr) - return false; + err = tegra_hdmi_setup_audio(hdmi); + if (err < 0) { + tegra_hdmi_disable_audio_infoframe(hdmi); + tegra_hdmi_disable_audio(hdmi); + } else { + tegra_hdmi_setup_audio_infoframe(hdmi); + tegra_hdmi_enable_audio_infoframe(hdmi); + tegra_hdmi_enable_audio(hdmi); + } - edid = (struct edid *)output->connector.edid_blob_ptr->data; + return err; +} - return drm_detect_hdmi_monitor(edid); +static bool tegra_output_is_hdmi(struct tegra_output *output) +{ + return output->connector.display_info.is_hdmi; } static enum drm_connector_status @@ -1085,7 +1119,8 @@ static void tegra_hdmi_early_unregister(struct drm_connector *connector) unsigned int count = ARRAY_SIZE(debugfs_files); struct tegra_hdmi *hdmi = to_hdmi(output); - drm_debugfs_remove_files(hdmi->debugfs_files, count, minor); + drm_debugfs_remove_files(hdmi->debugfs_files, count, + connector->debugfs_entry, minor); kfree(hdmi->debugfs_files); hdmi->debugfs_files = NULL; } @@ -1103,7 +1138,7 @@ static const struct drm_connector_funcs tegra_hdmi_connector_funcs = { static enum drm_mode_status tegra_hdmi_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) + const struct drm_display_mode *mode) { struct tegra_output *output = connector_to_output(connector); struct tegra_hdmi *hdmi = to_hdmi(output); @@ -1135,6 +1170,8 @@ static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder) u32 value; int err; + tegra_hdmi_audio_lock(hdmi); + /* * The following accesses registers of the display controller, so make * sure it's only executed when the output is attached to one. @@ -1159,6 +1196,10 @@ static void tegra_hdmi_encoder_disable(struct drm_encoder *encoder) tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_ENABLE); tegra_hdmi_writel(hdmi, 0, HDMI_NV_PDISP_INT_MASK); + hdmi->pixel_clock = 0; + + tegra_hdmi_audio_unlock(hdmi); + err = host1x_client_suspend(&hdmi->client); if (err < 0) dev_err(hdmi->dev, "failed to suspend: %d\n", err); @@ -1182,6 +1223,8 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder) return; } + tegra_hdmi_audio_lock(hdmi); + /* * Enable and unmask the HDA codec SCRATCH0 register interrupt. This * is used for interoperability between the HDA codec driver and the @@ -1195,7 +1238,7 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder) h_back_porch = mode->htotal - mode->hsync_end; h_front_porch = mode->hsync_start - mode->hdisplay; - err = clk_set_rate(hdmi->clk, hdmi->pixel_clock); + err = dev_pm_opp_set_rate(hdmi->dev, hdmi->pixel_clock); if (err < 0) { dev_err(hdmi->dev, "failed to set HDMI clock frequency: %d\n", err); @@ -1387,6 +1430,8 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder) } /* TODO: add HDCP support */ + + tegra_hdmi_audio_unlock(hdmi); } static int @@ -1416,30 +1461,136 @@ static const struct drm_encoder_helper_funcs tegra_hdmi_encoder_helper_funcs = { .atomic_check = tegra_hdmi_encoder_atomic_check, }; +static int tegra_hdmi_hw_params(struct device *dev, void *data, + struct hdmi_codec_daifmt *fmt, + struct hdmi_codec_params *hparms) +{ + struct tegra_hdmi *hdmi = data; + int ret = 0; + + tegra_hdmi_audio_lock(hdmi); + + hdmi->format.sample_rate = hparms->sample_rate; + hdmi->format.channels = hparms->channels; + + if (hdmi->pixel_clock && !hdmi->dvi) + ret = tegra_hdmi_reconfigure_audio(hdmi); + + tegra_hdmi_audio_unlock(hdmi); + + return ret; +} + +static int tegra_hdmi_audio_startup(struct device *dev, void *data) +{ + struct tegra_hdmi *hdmi = data; + int ret; + + ret = host1x_client_resume(&hdmi->client); + if (ret < 0) + dev_err(hdmi->dev, "failed to resume: %d\n", ret); + + return ret; +} + +static void tegra_hdmi_audio_shutdown(struct device *dev, void *data) +{ + struct tegra_hdmi *hdmi = data; + int ret; + + tegra_hdmi_audio_lock(hdmi); + + hdmi->format.sample_rate = 0; + hdmi->format.channels = 0; + + tegra_hdmi_audio_unlock(hdmi); + + ret = host1x_client_suspend(&hdmi->client); + if (ret < 0) + dev_err(hdmi->dev, "failed to suspend: %d\n", ret); +} + +static const struct hdmi_codec_ops tegra_hdmi_codec_ops = { + .hw_params = tegra_hdmi_hw_params, + .audio_startup = tegra_hdmi_audio_startup, + .audio_shutdown = tegra_hdmi_audio_shutdown, +}; + +static int tegra_hdmi_codec_register(struct tegra_hdmi *hdmi) +{ + struct hdmi_codec_pdata codec_data = {}; + + if (hdmi->config->has_hda) + return 0; + + codec_data.ops = &tegra_hdmi_codec_ops; + codec_data.data = hdmi; + codec_data.spdif = 1; + + hdmi->audio_pdev = platform_device_register_data(hdmi->dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_data, + sizeof(codec_data)); + if (IS_ERR(hdmi->audio_pdev)) + return PTR_ERR(hdmi->audio_pdev); + + hdmi->format.channels = 2; + + return 0; +} + +static void tegra_hdmi_codec_unregister(struct tegra_hdmi *hdmi) +{ + if (hdmi->audio_pdev) + platform_device_unregister(hdmi->audio_pdev); +} + static int tegra_hdmi_init(struct host1x_client *client) { struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client); struct drm_device *drm = dev_get_drvdata(client->host); + struct drm_connector *connector; int err; hdmi->output.dev = client->dev; - drm_connector_init_with_ddc(drm, &hdmi->output.connector, - &tegra_hdmi_connector_funcs, - DRM_MODE_CONNECTOR_HDMIA, - hdmi->output.ddc); - drm_connector_helper_add(&hdmi->output.connector, - &tegra_hdmi_connector_helper_funcs); - hdmi->output.connector.dpms = DRM_MODE_DPMS_OFF; - drm_simple_encoder_init(drm, &hdmi->output.encoder, DRM_MODE_ENCODER_TMDS); drm_encoder_helper_add(&hdmi->output.encoder, &tegra_hdmi_encoder_helper_funcs); - drm_connector_attach_encoder(&hdmi->output.connector, - &hdmi->output.encoder); - drm_connector_register(&hdmi->output.connector); + if (hdmi->output.bridge) { + err = drm_bridge_attach(&hdmi->output.encoder, hdmi->output.bridge, + NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (err) { + dev_err(client->dev, "failed to attach bridge: %d\n", + err); + return err; + } + + connector = drm_bridge_connector_init(drm, &hdmi->output.encoder); + if (IS_ERR(connector)) { + dev_err(client->dev, + "failed to initialize bridge connector: %pe\n", + connector); + return PTR_ERR(connector); + } + + drm_connector_attach_encoder(connector, &hdmi->output.encoder); + } else { + drm_connector_init_with_ddc(drm, &hdmi->output.connector, + &tegra_hdmi_connector_funcs, + DRM_MODE_CONNECTOR_HDMIA, + hdmi->output.ddc); + drm_connector_helper_add(&hdmi->output.connector, + &tegra_hdmi_connector_helper_funcs); + hdmi->output.connector.dpms = DRM_MODE_DPMS_OFF; + + drm_connector_attach_encoder(&hdmi->output.connector, + &hdmi->output.encoder); + drm_connector_register(&hdmi->output.connector); + } err = tegra_output_init(drm, &hdmi->output); if (err < 0) { @@ -1453,28 +1604,47 @@ static int tegra_hdmi_init(struct host1x_client *client) if (err < 0) { dev_err(client->dev, "failed to enable HDMI regulator: %d\n", err); - return err; + goto output_exit; } err = regulator_enable(hdmi->pll); if (err < 0) { dev_err(hdmi->dev, "failed to enable PLL regulator: %d\n", err); - return err; + goto disable_hdmi; } err = regulator_enable(hdmi->vdd); if (err < 0) { dev_err(hdmi->dev, "failed to enable VDD regulator: %d\n", err); - return err; + goto disable_pll; + } + + err = tegra_hdmi_codec_register(hdmi); + if (err < 0) { + dev_err(hdmi->dev, "failed to register audio codec: %d\n", err); + goto disable_vdd; } return 0; + +disable_vdd: + regulator_disable(hdmi->vdd); +disable_pll: + regulator_disable(hdmi->pll); +disable_hdmi: + regulator_disable(hdmi->hdmi); +output_exit: + tegra_output_exit(&hdmi->output); + + return err; } static int tegra_hdmi_exit(struct host1x_client *client) { struct tegra_hdmi *hdmi = host1x_client_to_hdmi(client); + tegra_hdmi_codec_unregister(hdmi); + tegra_output_exit(&hdmi->output); regulator_disable(hdmi->vdd); @@ -1599,7 +1769,6 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data) { struct tegra_hdmi *hdmi = data; u32 value; - int err; value = tegra_hdmi_readl(hdmi, HDMI_NV_PDISP_INT_STATUS); tegra_hdmi_writel(hdmi, value, HDMI_NV_PDISP_INT_STATUS); @@ -1614,16 +1783,7 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data) format = value & SOR_AUDIO_HDA_CODEC_SCRATCH0_FMT_MASK; tegra_hda_parse_format(format, &hdmi->format); - - err = tegra_hdmi_setup_audio(hdmi); - if (err < 0) { - tegra_hdmi_disable_audio_infoframe(hdmi); - tegra_hdmi_disable_audio(hdmi); - } else { - tegra_hdmi_setup_audio_infoframe(hdmi); - tegra_hdmi_enable_audio_infoframe(hdmi); - tegra_hdmi_enable_audio(hdmi); - } + tegra_hdmi_reconfigure_audio(hdmi); } else { tegra_hdmi_disable_audio_infoframe(hdmi); tegra_hdmi_disable_audio(hdmi); @@ -1635,9 +1795,7 @@ static irqreturn_t tegra_hdmi_irq(int irq, void *data) static int tegra_hdmi_probe(struct platform_device *pdev) { - const char *level = KERN_ERR; struct tegra_hdmi *hdmi; - struct resource *regs; int err; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); @@ -1651,6 +1809,8 @@ static int tegra_hdmi_probe(struct platform_device *pdev) hdmi->stereo = false; hdmi->dvi = false; + mutex_init(&hdmi->audio_lock); + hdmi->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(hdmi->clk)) { dev_err(&pdev->dev, "failed to get clock\n"); @@ -1675,36 +1835,21 @@ static int tegra_hdmi_probe(struct platform_device *pdev) hdmi->hdmi = devm_regulator_get(&pdev->dev, "hdmi"); err = PTR_ERR_OR_ZERO(hdmi->hdmi); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get HDMI regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get HDMI regulator\n"); hdmi->pll = devm_regulator_get(&pdev->dev, "pll"); err = PTR_ERR_OR_ZERO(hdmi->pll); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get PLL regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get PLL regulator\n"); hdmi->vdd = devm_regulator_get(&pdev->dev, "vdd"); err = PTR_ERR_OR_ZERO(hdmi->vdd); - if (err) { - if (err == -EPROBE_DEFER) - level = KERN_DEBUG; - - dev_printk(level, &pdev->dev, - "failed to get VDD regulator: %d\n", err); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to get VDD regulator\n"); hdmi->output.dev = &pdev->dev; @@ -1712,14 +1857,15 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) return err; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - hdmi->regs = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + hdmi->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(hdmi->regs)) { + err = PTR_ERR(hdmi->regs); + goto remove; + } err = platform_get_irq(pdev, 0); if (err < 0) - return err; + goto remove; hdmi->irq = err; @@ -1728,11 +1874,18 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", hdmi->irq, err); - return err; + goto remove; } platform_set_drvdata(pdev, hdmi); - pm_runtime_enable(&pdev->dev); + + err = devm_pm_runtime_enable(&pdev->dev); + if (err) + goto remove; + + err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); + if (err) + goto remove; INIT_LIST_HEAD(&hdmi->client.list); hdmi->client.ops = &hdmi_client_ops; @@ -1742,29 +1895,23 @@ static int tegra_hdmi_probe(struct platform_device *pdev) if (err < 0) { dev_err(&pdev->dev, "failed to register host1x client: %d\n", err); - return err; + goto remove; } return 0; + +remove: + tegra_output_remove(&hdmi->output); + return err; } -static int tegra_hdmi_remove(struct platform_device *pdev) +static void tegra_hdmi_remove(struct platform_device *pdev) { struct tegra_hdmi *hdmi = platform_get_drvdata(pdev); - int err; - pm_runtime_disable(&pdev->dev); - - err = host1x_client_unregister(&hdmi->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; - } + host1x_client_unregister(&hdmi->client); tegra_output_remove(&hdmi->output); - - return 0; } struct platform_driver tegra_hdmi_driver = { diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c index b910155f80c4..c924ffba4094 100644 --- a/drivers/gpu/drm/tegra/hub.c +++ b/drivers/gpu/drm/tegra/hub.c @@ -5,18 +5,22 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/dma-mapping.h> #include <linux/host1x.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/of_graph.h> +#include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_blend.h> #include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include "drm.h" @@ -518,12 +522,11 @@ static void tegra_shared_plane_atomic_disable(struct drm_plane *plane, static inline u32 compute_phase_incr(fixed20_12 in, unsigned int out) { - u64 tmp, tmp1, tmp2; + u64 tmp, tmp1; tmp = (u64)dfixed_trunc(in); - tmp2 = (u64)out; - tmp1 = (tmp << NFB) + (tmp2 >> 1); - do_div(tmp1, tmp2); + tmp1 = (tmp << NFB) + ((u64)out >> 1); + do_div(tmp1, out); return lower_32_bits(tmp1); } @@ -540,8 +543,8 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, struct tegra_plane *p = to_tegra_plane(plane); u32 value, min_width, bypass = 0; dma_addr_t base, addr_flag = 0; - unsigned int bpc; - bool yuv, planar; + unsigned int bpc, planes; + bool yuv; int err; /* rien ne va plus */ @@ -559,7 +562,7 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, return; } - yuv = tegra_plane_format_is_yuv(tegra_plane_state->format, &planar, &bpc); + yuv = tegra_plane_format_is_yuv(tegra_plane_state->format, &planes, &bpc); tegra_dc_assign_shared_plane(dc, p); @@ -660,20 +663,26 @@ static void tegra_shared_plane_atomic_update(struct drm_plane *plane, value = PITCH(fb->pitches[0]); tegra_plane_writel(p, value, DC_WIN_PLANAR_STORAGE); - if (yuv && planar) { + if (yuv && planes > 1) { base = tegra_plane_state->iova[1] + fb->offsets[1]; base |= addr_flag; tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_U); tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_U); - base = tegra_plane_state->iova[2] + fb->offsets[2]; - base |= addr_flag; + if (planes > 2) { + base = tegra_plane_state->iova[2] + fb->offsets[2]; + base |= addr_flag; + + tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_V); + tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_V); + } - tegra_plane_writel(p, upper_32_bits(base), DC_WINBUF_START_ADDR_HI_V); - tegra_plane_writel(p, lower_32_bits(base), DC_WINBUF_START_ADDR_V); + value = PITCH_U(fb->pitches[1]); + + if (planes > 2) + value |= PITCH_V(fb->pitches[2]); - value = PITCH_U(fb->pitches[2]) | PITCH_V(fb->pitches[2]); tegra_plane_writel(p, value, DC_WIN_PLANAR_STORAGE_UV); } else { tegra_plane_writel(p, 0, DC_WINBUF_START_ADDR_U); @@ -747,9 +756,9 @@ static const struct drm_plane_helper_funcs tegra_shared_plane_helper_funcs = { struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, struct tegra_dc *dc, unsigned int wgrp, - unsigned int index) + unsigned int index, + enum drm_plane_type type) { - enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY; struct tegra_drm *tegra = drm->dev_private; struct tegra_display_hub *hub = tegra->hub; struct tegra_shared_plane *plane; @@ -1092,7 +1101,7 @@ static int tegra_display_hub_probe(struct platform_device *pdev) for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; - char id[8]; + char id[16]; snprintf(id, sizeof(id), "wgrp%u", i); mutex_init(&wgrp->lock); @@ -1165,17 +1174,12 @@ unregister: return err; } -static int tegra_display_hub_remove(struct platform_device *pdev) +static void tegra_display_hub_remove(struct platform_device *pdev) { struct tegra_display_hub *hub = platform_get_drvdata(pdev); unsigned int i; - int err; - err = host1x_client_unregister(&hub->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - } + host1x_client_unregister(&hub->client); for (i = 0; i < hub->soc->num_wgrps; i++) { struct tegra_windowgroup *wgrp = &hub->wgrps[i]; @@ -1184,8 +1188,6 @@ static int tegra_display_hub_remove(struct platform_device *pdev) } pm_runtime_disable(&pdev->dev); - - return err; } static const struct tegra_display_hub_soc tegra186_display_hub = { diff --git a/drivers/gpu/drm/tegra/hub.h b/drivers/gpu/drm/tegra/hub.h index 3efa1be07ff8..a66f18c4facc 100644 --- a/drivers/gpu/drm/tegra/hub.h +++ b/drivers/gpu/drm/tegra/hub.h @@ -72,7 +72,6 @@ to_tegra_display_hub_state(struct drm_private_state *priv) return container_of(priv, struct tegra_display_hub_state, base); } -struct tegra_dc; struct tegra_plane; int tegra_display_hub_prepare(struct tegra_display_hub *hub); @@ -81,7 +80,8 @@ void tegra_display_hub_cleanup(struct tegra_display_hub *hub); struct drm_plane *tegra_shared_plane_create(struct drm_device *drm, struct tegra_dc *dc, unsigned int wgrp, - unsigned int index); + unsigned int index, + enum drm_plane_type type); int tegra_display_hub_atomic_check(struct drm_device *drm, struct drm_atomic_state *state); diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c new file mode 100644 index 000000000000..7a38664e890e --- /dev/null +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2015-2022, NVIDIA Corporation. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/host1x.h> +#include <linux/iommu.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> + +#include <soc/tegra/mc.h> + +#include "drm.h" +#include "falcon.h" +#include "riscv.h" +#include "vic.h" + +#define NVDEC_FALCON_DEBUGINFO 0x1094 +#define NVDEC_TFBIF_TRANSCFG 0x2c44 + +struct nvdec_config { + const char *firmware; + unsigned int version; + bool supports_sid; + bool has_riscv; + bool has_extra_clocks; +}; + +struct nvdec { + struct falcon falcon; + + void __iomem *regs; + struct tegra_drm_client client; + struct host1x_channel *channel; + struct device *dev; + struct clk_bulk_data clks[3]; + unsigned int num_clks; + struct reset_control *reset; + + /* Platform configuration */ + const struct nvdec_config *config; + + /* RISC-V specific data */ + struct tegra_drm_riscv riscv; + phys_addr_t carveout_base; +}; + +static inline struct nvdec *to_nvdec(struct tegra_drm_client *client) +{ + return container_of(client, struct nvdec, client); +} + +static inline void nvdec_writel(struct nvdec *nvdec, u32 value, + unsigned int offset) +{ + writel(value, nvdec->regs + offset); +} + +static int nvdec_boot_falcon(struct nvdec *nvdec) +{ + u32 stream_id; + int err; + + if (nvdec->config->supports_sid && tegra_dev_iommu_get_stream_id(nvdec->dev, &stream_id)) { + u32 value; + + value = TRANSCFG_ATT(1, TRANSCFG_SID_FALCON) | TRANSCFG_ATT(0, TRANSCFG_SID_HW); + nvdec_writel(nvdec, value, NVDEC_TFBIF_TRANSCFG); + + nvdec_writel(nvdec, stream_id, VIC_THI_STREAMID0); + nvdec_writel(nvdec, stream_id, VIC_THI_STREAMID1); + } + + err = falcon_boot(&nvdec->falcon); + if (err < 0) + return err; + + err = falcon_wait_idle(&nvdec->falcon); + if (err < 0) { + dev_err(nvdec->dev, "falcon boot timed out\n"); + return err; + } + + return 0; +} + +static int nvdec_wait_debuginfo(struct nvdec *nvdec, const char *phase) +{ + int err; + u32 val; + + err = readl_poll_timeout(nvdec->regs + NVDEC_FALCON_DEBUGINFO, val, val == 0x0, 10, 100000); + if (err) { + dev_err(nvdec->dev, "failed to boot %s, debuginfo=0x%x\n", phase, val); + return err; + } + + return 0; +} + +static int nvdec_boot_riscv(struct nvdec *nvdec) +{ + int err; + + err = reset_control_acquire(nvdec->reset); + if (err) + return err; + + nvdec_writel(nvdec, 0xabcd1234, NVDEC_FALCON_DEBUGINFO); + + err = tegra_drm_riscv_boot_bootrom(&nvdec->riscv, nvdec->carveout_base, 1, + &nvdec->riscv.bl_desc); + if (err) { + dev_err(nvdec->dev, "failed to execute bootloader\n"); + goto release_reset; + } + + err = nvdec_wait_debuginfo(nvdec, "bootloader"); + if (err) + goto release_reset; + + err = reset_control_reset(nvdec->reset); + if (err) + goto release_reset; + + nvdec_writel(nvdec, 0xabcd1234, NVDEC_FALCON_DEBUGINFO); + + err = tegra_drm_riscv_boot_bootrom(&nvdec->riscv, nvdec->carveout_base, 1, + &nvdec->riscv.os_desc); + if (err) { + dev_err(nvdec->dev, "failed to execute firmware\n"); + goto release_reset; + } + + err = nvdec_wait_debuginfo(nvdec, "firmware"); + if (err) + goto release_reset; + +release_reset: + reset_control_release(nvdec->reset); + + return err; +} + +static int nvdec_init(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvdec *nvdec = to_nvdec(drm); + int err; + + err = host1x_client_iommu_attach(client); + if (err < 0 && err != -ENODEV) { + dev_err(nvdec->dev, "failed to attach to domain: %d\n", err); + return err; + } + + nvdec->channel = host1x_channel_request(client); + if (!nvdec->channel) { + err = -ENOMEM; + goto detach; + } + + client->syncpts[0] = host1x_syncpt_request(client, 0); + if (!client->syncpts[0]) { + err = -ENOMEM; + goto free_channel; + } + + err = tegra_drm_register_client(tegra, drm); + if (err < 0) + goto free_syncpt; + + /* + * Inherit the DMA parameters (such as maximum segment size) from the + * parent host1x device. + */ + client->dev->dma_parms = client->host->dma_parms; + + return 0; + +free_syncpt: + host1x_syncpt_put(client->syncpts[0]); +free_channel: + host1x_channel_put(nvdec->channel); +detach: + host1x_client_iommu_detach(client); + + return err; +} + +static int nvdec_exit(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvdec *nvdec = to_nvdec(drm); + int err; + + /* avoid a dangling pointer just in case this disappears */ + client->dev->dma_parms = NULL; + + err = tegra_drm_unregister_client(tegra, drm); + if (err < 0) + return err; + + pm_runtime_dont_use_autosuspend(client->dev); + pm_runtime_force_suspend(client->dev); + + host1x_syncpt_put(client->syncpts[0]); + host1x_channel_put(nvdec->channel); + host1x_client_iommu_detach(client); + + nvdec->channel = NULL; + + if (client->group) { + dma_unmap_single(nvdec->dev, nvdec->falcon.firmware.phys, + nvdec->falcon.firmware.size, DMA_TO_DEVICE); + tegra_drm_free(tegra, nvdec->falcon.firmware.size, + nvdec->falcon.firmware.virt, + nvdec->falcon.firmware.iova); + } else { + dma_free_coherent(nvdec->dev, nvdec->falcon.firmware.size, + nvdec->falcon.firmware.virt, + nvdec->falcon.firmware.iova); + } + + return 0; +} + +static const struct host1x_client_ops nvdec_client_ops = { + .init = nvdec_init, + .exit = nvdec_exit, +}; + +static int nvdec_load_falcon_firmware(struct nvdec *nvdec) +{ + struct host1x_client *client = &nvdec->client.base; + struct tegra_drm *tegra = nvdec->client.drm; + dma_addr_t iova; + size_t size; + void *virt; + int err; + + if (nvdec->falcon.firmware.virt) + return 0; + + err = falcon_read_firmware(&nvdec->falcon, nvdec->config->firmware); + if (err < 0) + return err; + + size = nvdec->falcon.firmware.size; + + if (!client->group) { + virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL); + if (!virt) + return -ENOMEM; + } else { + virt = tegra_drm_alloc(tegra, size, &iova); + if (IS_ERR(virt)) + return PTR_ERR(virt); + } + + nvdec->falcon.firmware.virt = virt; + nvdec->falcon.firmware.iova = iova; + + err = falcon_load_firmware(&nvdec->falcon); + if (err < 0) + goto cleanup; + + /* + * In this case we have received an IOVA from the shared domain, so we + * need to make sure to get the physical address so that the DMA API + * knows what memory pages to flush the cache for. + */ + if (client->group) { + dma_addr_t phys; + + phys = dma_map_single(nvdec->dev, virt, size, DMA_TO_DEVICE); + + err = dma_mapping_error(nvdec->dev, phys); + if (err < 0) + goto cleanup; + + nvdec->falcon.firmware.phys = phys; + } + + return 0; + +cleanup: + if (!client->group) + dma_free_coherent(nvdec->dev, size, virt, iova); + else + tegra_drm_free(tegra, size, virt, iova); + + return err; +} + +static __maybe_unused int nvdec_runtime_resume(struct device *dev) +{ + struct nvdec *nvdec = dev_get_drvdata(dev); + int err; + + err = clk_bulk_prepare_enable(nvdec->num_clks, nvdec->clks); + if (err < 0) + return err; + + usleep_range(10, 20); + + if (nvdec->config->has_riscv) { + err = nvdec_boot_riscv(nvdec); + if (err < 0) + goto disable; + } else { + err = nvdec_load_falcon_firmware(nvdec); + if (err < 0) + goto disable; + + err = nvdec_boot_falcon(nvdec); + if (err < 0) + goto disable; + } + + return 0; + +disable: + clk_bulk_disable_unprepare(nvdec->num_clks, nvdec->clks); + return err; +} + +static __maybe_unused int nvdec_runtime_suspend(struct device *dev) +{ + struct nvdec *nvdec = dev_get_drvdata(dev); + + host1x_channel_stop(nvdec->channel); + + clk_bulk_disable_unprepare(nvdec->num_clks, nvdec->clks); + + return 0; +} + +static int nvdec_open_channel(struct tegra_drm_client *client, + struct tegra_drm_context *context) +{ + struct nvdec *nvdec = to_nvdec(client); + + context->channel = host1x_channel_get(nvdec->channel); + if (!context->channel) + return -ENOMEM; + + return 0; +} + +static void nvdec_close_channel(struct tegra_drm_context *context) +{ + host1x_channel_put(context->channel); +} + +static int nvdec_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported) +{ + *supported = true; + + return 0; +} + +static const struct tegra_drm_client_ops nvdec_ops = { + .open_channel = nvdec_open_channel, + .close_channel = nvdec_close_channel, + .submit = tegra_drm_submit, + .get_streamid_offset = tegra_drm_get_streamid_offset_thi, + .can_use_memory_ctx = nvdec_can_use_memory_ctx, +}; + +#define NVIDIA_TEGRA_210_NVDEC_FIRMWARE "nvidia/tegra210/nvdec.bin" + +static const struct nvdec_config nvdec_t210_config = { + .firmware = NVIDIA_TEGRA_210_NVDEC_FIRMWARE, + .version = 0x21, + .supports_sid = false, +}; + +#define NVIDIA_TEGRA_186_NVDEC_FIRMWARE "nvidia/tegra186/nvdec.bin" + +static const struct nvdec_config nvdec_t186_config = { + .firmware = NVIDIA_TEGRA_186_NVDEC_FIRMWARE, + .version = 0x18, + .supports_sid = true, +}; + +#define NVIDIA_TEGRA_194_NVDEC_FIRMWARE "nvidia/tegra194/nvdec.bin" + +static const struct nvdec_config nvdec_t194_config = { + .firmware = NVIDIA_TEGRA_194_NVDEC_FIRMWARE, + .version = 0x19, + .supports_sid = true, +}; + +static const struct nvdec_config nvdec_t234_config = { + .version = 0x23, + .supports_sid = true, + .has_riscv = true, + .has_extra_clocks = true, +}; + +static const struct of_device_id tegra_nvdec_of_match[] = { + { .compatible = "nvidia,tegra210-nvdec", .data = &nvdec_t210_config }, + { .compatible = "nvidia,tegra186-nvdec", .data = &nvdec_t186_config }, + { .compatible = "nvidia,tegra194-nvdec", .data = &nvdec_t194_config }, + { .compatible = "nvidia,tegra234-nvdec", .data = &nvdec_t234_config }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_nvdec_of_match); + +static int nvdec_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct host1x_syncpt **syncpts; + struct nvdec *nvdec; + u32 host_class; + int err; + + /* inherit DMA mask from host1x parent */ + err = dma_coerce_mask_and_coherent(dev, *dev->parent->dma_mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + + nvdec = devm_kzalloc(dev, sizeof(*nvdec), GFP_KERNEL); + if (!nvdec) + return -ENOMEM; + + nvdec->config = of_device_get_match_data(dev); + + syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL); + if (!syncpts) + return -ENOMEM; + + nvdec->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(nvdec->regs)) + return PTR_ERR(nvdec->regs); + + nvdec->clks[0].id = "nvdec"; + nvdec->num_clks = 1; + + if (nvdec->config->has_extra_clocks) { + nvdec->num_clks = 3; + nvdec->clks[1].id = "fuse"; + nvdec->clks[2].id = "tsec_pka"; + } + + err = devm_clk_bulk_get(dev, nvdec->num_clks, nvdec->clks); + if (err) { + dev_err(&pdev->dev, "failed to get clock(s)\n"); + return err; + } + + err = clk_set_rate(nvdec->clks[0].clk, ULONG_MAX); + if (err < 0) { + dev_err(&pdev->dev, "failed to set clock rate\n"); + return err; + } + + err = of_property_read_u32(dev->of_node, "nvidia,host1x-class", &host_class); + if (err < 0) + host_class = HOST1X_CLASS_NVDEC; + + if (nvdec->config->has_riscv) { + struct tegra_mc *mc; + + mc = devm_tegra_memory_controller_get(dev); + if (IS_ERR(mc)) { + dev_err_probe(dev, PTR_ERR(mc), + "failed to get memory controller handle\n"); + return PTR_ERR(mc); + } + + err = tegra_mc_get_carveout_info(mc, 1, &nvdec->carveout_base, NULL); + if (err) { + dev_err(dev, "failed to get carveout info: %d\n", err); + return err; + } + + nvdec->reset = devm_reset_control_get_exclusive_released(dev, "nvdec"); + if (IS_ERR(nvdec->reset)) { + dev_err_probe(dev, PTR_ERR(nvdec->reset), "failed to get reset\n"); + return PTR_ERR(nvdec->reset); + } + + nvdec->riscv.dev = dev; + nvdec->riscv.regs = nvdec->regs; + + err = tegra_drm_riscv_read_descriptors(&nvdec->riscv); + if (err < 0) + return err; + } else { + nvdec->falcon.dev = dev; + nvdec->falcon.regs = nvdec->regs; + + err = falcon_init(&nvdec->falcon); + if (err < 0) + return err; + } + + platform_set_drvdata(pdev, nvdec); + + INIT_LIST_HEAD(&nvdec->client.base.list); + nvdec->client.base.ops = &nvdec_client_ops; + nvdec->client.base.dev = dev; + nvdec->client.base.class = host_class; + nvdec->client.base.syncpts = syncpts; + nvdec->client.base.num_syncpts = 1; + nvdec->dev = dev; + + INIT_LIST_HEAD(&nvdec->client.list); + nvdec->client.version = nvdec->config->version; + nvdec->client.ops = &nvdec_ops; + + err = host1x_client_register(&nvdec->client.base); + if (err < 0) { + dev_err(dev, "failed to register host1x client: %d\n", err); + goto exit_falcon; + } + + pm_runtime_enable(dev); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_autosuspend_delay(dev, 500); + + return 0; + +exit_falcon: + falcon_exit(&nvdec->falcon); + + return err; +} + +static void nvdec_remove(struct platform_device *pdev) +{ + struct nvdec *nvdec = platform_get_drvdata(pdev); + + pm_runtime_disable(&pdev->dev); + host1x_client_unregister(&nvdec->client.base); + falcon_exit(&nvdec->falcon); +} + +static const struct dev_pm_ops nvdec_pm_ops = { + SET_RUNTIME_PM_OPS(nvdec_runtime_suspend, nvdec_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) +}; + +struct platform_driver tegra_nvdec_driver = { + .driver = { + .name = "tegra-nvdec", + .of_match_table = tegra_nvdec_of_match, + .pm = &nvdec_pm_ops + }, + .probe = nvdec_probe, + .remove = nvdec_remove, +}; + +#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_210_NVDEC_FIRMWARE); +#endif +#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_186_NVDEC_FIRMWARE); +#endif +#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_194_NVDEC_FIRMWARE); +#endif diff --git a/drivers/gpu/drm/tegra/nvjpg.c b/drivers/gpu/drm/tegra/nvjpg.c new file mode 100644 index 000000000000..94503fd0d52d --- /dev/null +++ b/drivers/gpu/drm/tegra/nvjpg.c @@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/host1x.h> +#include <linux/iommu.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "drm.h" +#include "falcon.h" + +struct nvjpg_config { + const char *firmware; + unsigned int version; +}; + +struct nvjpg { + struct falcon falcon; + + void __iomem *regs; + struct tegra_drm_client client; + struct device *dev; + struct clk *clk; + + /* Platform configuration */ + const struct nvjpg_config *config; +}; + +static inline struct nvjpg *to_nvjpg(struct tegra_drm_client *client) +{ + return container_of(client, struct nvjpg, client); +} + +static int nvjpg_init(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvjpg *nvjpg = to_nvjpg(drm); + int err; + + err = host1x_client_iommu_attach(client); + if (err < 0 && err != -ENODEV) { + dev_err(nvjpg->dev, "failed to attach to domain: %d\n", err); + return err; + } + + err = tegra_drm_register_client(tegra, drm); + if (err < 0) + goto detach; + + /* + * Inherit the DMA parameters (such as maximum segment size) from the + * parent host1x device. + */ + client->dev->dma_parms = client->host->dma_parms; + + return 0; + +detach: + host1x_client_iommu_detach(client); + + return err; +} + +static int nvjpg_exit(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvjpg *nvjpg = to_nvjpg(drm); + int err; + + /* avoid a dangling pointer just in case this disappears */ + client->dev->dma_parms = NULL; + + err = tegra_drm_unregister_client(tegra, drm); + if (err < 0) + return err; + + pm_runtime_dont_use_autosuspend(client->dev); + pm_runtime_force_suspend(client->dev); + + host1x_client_iommu_detach(client); + + if (client->group) { + dma_unmap_single(nvjpg->dev, nvjpg->falcon.firmware.phys, + nvjpg->falcon.firmware.size, DMA_TO_DEVICE); + tegra_drm_free(tegra, nvjpg->falcon.firmware.size, + nvjpg->falcon.firmware.virt, + nvjpg->falcon.firmware.iova); + } else { + dma_free_coherent(nvjpg->dev, nvjpg->falcon.firmware.size, + nvjpg->falcon.firmware.virt, + nvjpg->falcon.firmware.iova); + } + + return 0; +} + +static const struct host1x_client_ops nvjpg_client_ops = { + .init = nvjpg_init, + .exit = nvjpg_exit, +}; + +static int nvjpg_load_falcon_firmware(struct nvjpg *nvjpg) +{ + struct host1x_client *client = &nvjpg->client.base; + struct tegra_drm *tegra = nvjpg->client.drm; + dma_addr_t iova; + size_t size; + void *virt; + int err; + + if (nvjpg->falcon.firmware.virt) + return 0; + + err = falcon_read_firmware(&nvjpg->falcon, nvjpg->config->firmware); + if (err < 0) + return err; + + size = nvjpg->falcon.firmware.size; + + if (!client->group) { + virt = dma_alloc_coherent(nvjpg->dev, size, &iova, GFP_KERNEL); + if (!virt) + return -ENOMEM; + } else { + virt = tegra_drm_alloc(tegra, size, &iova); + if (IS_ERR(virt)) + return PTR_ERR(virt); + } + + nvjpg->falcon.firmware.virt = virt; + nvjpg->falcon.firmware.iova = iova; + + err = falcon_load_firmware(&nvjpg->falcon); + if (err < 0) + goto cleanup; + + /* + * In this case we have received an IOVA from the shared domain, so we + * need to make sure to get the physical address so that the DMA API + * knows what memory pages to flush the cache for. + */ + if (client->group) { + dma_addr_t phys; + + phys = dma_map_single(nvjpg->dev, virt, size, DMA_TO_DEVICE); + + err = dma_mapping_error(nvjpg->dev, phys); + if (err < 0) + goto cleanup; + + nvjpg->falcon.firmware.phys = phys; + } + + return 0; + +cleanup: + if (!client->group) + dma_free_coherent(nvjpg->dev, size, virt, iova); + else + tegra_drm_free(tegra, size, virt, iova); + + return err; +} + +static __maybe_unused int nvjpg_runtime_resume(struct device *dev) +{ + struct nvjpg *nvjpg = dev_get_drvdata(dev); + int err; + + err = clk_prepare_enable(nvjpg->clk); + if (err < 0) + return err; + + usleep_range(20, 30); + + err = nvjpg_load_falcon_firmware(nvjpg); + if (err < 0) + goto disable_clk; + + err = falcon_boot(&nvjpg->falcon); + if (err < 0) + goto disable_clk; + + return 0; + +disable_clk: + clk_disable_unprepare(nvjpg->clk); + return err; +} + +static __maybe_unused int nvjpg_runtime_suspend(struct device *dev) +{ + struct nvjpg *nvjpg = dev_get_drvdata(dev); + + clk_disable_unprepare(nvjpg->clk); + + return 0; +} + +static int nvjpg_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported) +{ + *supported = false; + + return 0; +} + +static const struct tegra_drm_client_ops nvjpg_ops = { + .get_streamid_offset = NULL, + .can_use_memory_ctx = nvjpg_can_use_memory_ctx, +}; + +#define NVIDIA_TEGRA_210_NVJPG_FIRMWARE "nvidia/tegra210/nvjpg.bin" + +static const struct nvjpg_config tegra210_nvjpg_config = { + .firmware = NVIDIA_TEGRA_210_NVJPG_FIRMWARE, + .version = 0x21, +}; + +static const struct of_device_id tegra_nvjpg_of_match[] = { + { .compatible = "nvidia,tegra210-nvjpg", .data = &tegra210_nvjpg_config }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_nvjpg_of_match); + +static int nvjpg_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct nvjpg *nvjpg; + int err; + + /* inherit DMA mask from host1x parent */ + err = dma_coerce_mask_and_coherent(dev, *dev->parent->dma_mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + + nvjpg = devm_kzalloc(dev, sizeof(*nvjpg), GFP_KERNEL); + if (!nvjpg) + return -ENOMEM; + + nvjpg->config = of_device_get_match_data(dev); + + nvjpg->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(nvjpg->regs)) + return PTR_ERR(nvjpg->regs); + + nvjpg->clk = devm_clk_get(dev, "nvjpg"); + if (IS_ERR(nvjpg->clk)) { + dev_err(&pdev->dev, "failed to get clock\n"); + return PTR_ERR(nvjpg->clk); + } + + err = clk_set_rate(nvjpg->clk, ULONG_MAX); + if (err < 0) { + dev_err(&pdev->dev, "failed to set clock rate\n"); + return err; + } + + nvjpg->falcon.dev = dev; + nvjpg->falcon.regs = nvjpg->regs; + + err = falcon_init(&nvjpg->falcon); + if (err < 0) + return err; + + platform_set_drvdata(pdev, nvjpg); + + INIT_LIST_HEAD(&nvjpg->client.base.list); + nvjpg->client.base.ops = &nvjpg_client_ops; + nvjpg->client.base.dev = dev; + nvjpg->client.base.class = HOST1X_CLASS_NVJPG; + nvjpg->dev = dev; + + INIT_LIST_HEAD(&nvjpg->client.list); + nvjpg->client.version = nvjpg->config->version; + nvjpg->client.ops = &nvjpg_ops; + + err = host1x_client_register(&nvjpg->client.base); + if (err < 0) { + dev_err(dev, "failed to register host1x client: %d\n", err); + goto exit_falcon; + } + + pm_runtime_use_autosuspend(dev); + pm_runtime_set_autosuspend_delay(dev, 500); + devm_pm_runtime_enable(dev); + + return 0; + +exit_falcon: + falcon_exit(&nvjpg->falcon); + + return err; +} + +static void nvjpg_remove(struct platform_device *pdev) +{ + struct nvjpg *nvjpg = platform_get_drvdata(pdev); + + host1x_client_unregister(&nvjpg->client.base); + falcon_exit(&nvjpg->falcon); +} + +static const struct dev_pm_ops nvjpg_pm_ops = { + RUNTIME_PM_OPS(nvjpg_runtime_suspend, nvjpg_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) +}; + +struct platform_driver tegra_nvjpg_driver = { + .driver = { + .name = "tegra-nvjpg", + .of_match_table = tegra_nvjpg_of_match, + .pm = &nvjpg_pm_ops + }, + .probe = nvjpg_probe, + .remove = nvjpg_remove, +}; + +#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_210_NVJPG_FIRMWARE); +#endif diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c index 47d26b5d9945..49e4f63a5550 100644 --- a/drivers/gpu/drm/tegra/output.c +++ b/drivers/gpu/drm/tegra/output.c @@ -4,7 +4,11 @@ * Copyright (C) 2012 NVIDIA CORPORATION. All rights reserved. */ +#include <linux/i2c.h> +#include <linux/of.h> + #include <drm/drm_atomic_helper.h> +#include <drm/drm_edid.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> #include <drm/drm_simple_kms_helper.h> @@ -17,7 +21,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector) { struct tegra_output *output = connector_to_output(connector); - struct edid *edid = NULL; + const struct drm_edid *drm_edid = NULL; int err = 0; /* @@ -30,18 +34,17 @@ int tegra_output_connector_get_modes(struct drm_connector *connector) return err; } - if (output->edid) - edid = kmemdup(output->edid, sizeof(*edid), GFP_KERNEL); + if (output->drm_edid) + drm_edid = drm_edid_dup(output->drm_edid); else if (output->ddc) - edid = drm_get_edid(connector, output->ddc); + drm_edid = drm_edid_read_ddc(connector, output->ddc); - cec_notifier_set_phys_addr_from_edid(output->cec, edid); - drm_connector_update_edid_property(connector, edid); + drm_edid_connector_update(connector, drm_edid); + cec_notifier_set_phys_addr(output->cec, + connector->display_info.source_physical_address); - if (edid) { - err = drm_add_edid_modes(connector, edid); - kfree(edid); - } + err = drm_edid_connector_add_modes(connector); + drm_edid_free(drm_edid); return err; } @@ -94,6 +97,7 @@ static irqreturn_t hpd_irq(int irq, void *data) int tegra_output_probe(struct tegra_output *output) { struct device_node *ddc, *panel; + const void *edid; unsigned long flags; int err, size; @@ -120,8 +124,6 @@ int tegra_output_probe(struct tegra_output *output) return PTR_ERR(output->panel); } - output->edid = of_get_property(output->of_node, "nvidia,edid", &size); - ddc = of_parse_phandle(output->of_node, "nvidia,ddc-i2c-bus", 0); if (ddc) { output->ddc = of_get_i2c_adapter_by_node(ddc); @@ -133,14 +135,19 @@ int tegra_output_probe(struct tegra_output *output) } } - output->hpd_gpio = devm_gpiod_get_from_of_node(output->dev, - output->of_node, - "nvidia,hpd-gpio", 0, - GPIOD_IN, - "HDMI hotplug detect"); + edid = of_get_property(output->of_node, "nvidia,edid", &size); + output->drm_edid = drm_edid_alloc(edid, size); + + output->hpd_gpio = devm_fwnode_gpiod_get(output->dev, + of_fwnode_handle(output->of_node), + "nvidia,hpd", + GPIOD_IN, + "HDMI hotplug detect"); if (IS_ERR(output->hpd_gpio)) { - if (PTR_ERR(output->hpd_gpio) != -ENOENT) - return PTR_ERR(output->hpd_gpio); + if (PTR_ERR(output->hpd_gpio) != -ENOENT) { + err = PTR_ERR(output->hpd_gpio); + goto put_i2c; + } output->hpd_gpio = NULL; } @@ -149,7 +156,7 @@ int tegra_output_probe(struct tegra_output *output) err = gpiod_to_irq(output->hpd_gpio); if (err < 0) { dev_err(output->dev, "gpiod_to_irq(): %d\n", err); - return err; + goto put_i2c; } output->hpd_irq = err; @@ -162,7 +169,7 @@ int tegra_output_probe(struct tegra_output *output) if (err < 0) { dev_err(output->dev, "failed to request IRQ#%u: %d\n", output->hpd_irq, err); - return err; + goto put_i2c; } output->connector.polled = DRM_CONNECTOR_POLL_HPD; @@ -176,6 +183,14 @@ int tegra_output_probe(struct tegra_output *output) } return 0; + +put_i2c: + if (output->ddc) + i2c_put_adapter(output->ddc); + + drm_edid_free(output->drm_edid); + + return err; } void tegra_output_remove(struct tegra_output *output) @@ -185,6 +200,8 @@ void tegra_output_remove(struct tegra_output *output) if (output->ddc) i2c_put_adapter(output->ddc); + + drm_edid_free(output->drm_edid); } int tegra_output_init(struct drm_device *drm, struct tegra_output *output) diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 2e65b4075ce6..ffe5f06b770d 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -3,13 +3,15 @@ * Copyright (C) 2017 NVIDIA CORPORATION. All rights reserved. */ +#include <linux/dma-mapping.h> #include <linux/iommu.h> +#include <linux/interconnect.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fourcc.h> +#include <drm/drm_framebuffer.h> #include <drm/drm_gem_atomic_helper.h> -#include <drm/drm_plane_helper.h> #include "dc.h" #include "plane.h" @@ -64,13 +66,16 @@ tegra_plane_atomic_duplicate_state(struct drm_plane *plane) copy->reflect_x = state->reflect_x; copy->reflect_y = state->reflect_y; copy->opaque = state->opaque; + copy->total_peak_memory_bandwidth = state->total_peak_memory_bandwidth; + copy->peak_memory_bandwidth = state->peak_memory_bandwidth; + copy->avg_memory_bandwidth = state->avg_memory_bandwidth; for (i = 0; i < 2; i++) copy->blending[i] = state->blending[i]; for (i = 0; i < 3; i++) { copy->iova[i] = DMA_MAPPING_ERROR; - copy->sgt[i] = NULL; + copy->map[i] = NULL; } return ©->base; @@ -109,7 +114,7 @@ static bool tegra_plane_format_mod_supported(struct drm_plane *plane, return true; /* check for the sector layout bit */ - if ((modifier >> 56) == DRM_FORMAT_MOD_VENDOR_NVIDIA) { + if (fourcc_mod_is_vendor(modifier, NVIDIA)) { if (modifier & DRM_FORMAT_MOD_NVIDIA_SECTOR_LAYOUT) { if (!tegra_plane_supports_sector_layout(plane)) return false; @@ -134,55 +139,37 @@ const struct drm_plane_funcs tegra_plane_funcs = { static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dc->dev); unsigned int i; int err; for (i = 0; i < state->base.fb->format->num_planes; i++) { struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - dma_addr_t phys_addr, *phys; - struct sg_table *sgt; + struct host1x_bo_mapping *map; - /* - * If we're not attached to a domain, we already stored the - * physical address when the buffer was allocated. If we're - * part of a group that's shared between all display - * controllers, we've also already mapped the framebuffer - * through the SMMU. In both cases we can short-circuit the - * code below and retrieve the stored IOV address. - */ - if (!domain || dc->client.group) - phys = &phys_addr; - else - phys = NULL; - - sgt = host1x_bo_pin(dc->dev, &bo->base, phys); - if (IS_ERR(sgt)) { - err = PTR_ERR(sgt); + map = host1x_bo_pin(dc->dev, &bo->base, DMA_TO_DEVICE, &dc->client.cache); + if (IS_ERR(map)) { + err = PTR_ERR(map); goto unpin; } - if (sgt) { - err = dma_map_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - if (err) - goto unpin; - + if (!dc->client.group) { /* * The display controller needs contiguous memory, so * fail if the buffer is discontiguous and we fail to * map its SG table to a single contiguous chunk of * I/O virtual memory. */ - if (sgt->nents > 1) { + if (map->chunks > 1) { err = -EINVAL; goto unpin; } - state->iova[i] = sg_dma_address(sgt->sgl); - state->sgt[i] = sgt; + state->iova[i] = map->phys; } else { - state->iova[i] = phys_addr; + state->iova[i] = bo->iova; } + + state->map[i] = map; } return 0; @@ -191,15 +178,9 @@ unpin: dev_err(dc->dev, "failed to map plane %u: %d\n", i, err); while (i--) { - struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - struct sg_table *sgt = state->sgt[i]; - - if (sgt) - dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - - host1x_bo_unpin(dc->dev, &bo->base, sgt); + host1x_bo_unpin(state->map[i]); state->iova[i] = DMA_MAPPING_ERROR; - state->sgt[i] = NULL; + state->map[i] = NULL; } return err; @@ -210,15 +191,9 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state) unsigned int i; for (i = 0; i < state->base.fb->format->num_planes; i++) { - struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - struct sg_table *sgt = state->sgt[i]; - - if (sgt) - dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - - host1x_bo_unpin(dc->dev, &bo->base, sgt); + host1x_bo_unpin(state->map[i]); state->iova[i] = DMA_MAPPING_ERROR; - state->sgt[i] = NULL; + state->map[i] = NULL; } } @@ -226,11 +201,14 @@ int tegra_plane_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) { struct tegra_dc *dc = to_tegra_dc(state->crtc); + int err; if (!state->fb) return 0; - drm_gem_plane_helper_prepare_fb(plane, state); + err = drm_gem_plane_helper_prepare_fb(plane, state); + if (err < 0) + return err; return tegra_dc_pin(dc, to_tegra_plane_state(state)); } @@ -244,6 +222,78 @@ void tegra_plane_cleanup_fb(struct drm_plane *plane, tegra_dc_unpin(dc, to_tegra_plane_state(state)); } +static int tegra_plane_calculate_memory_bandwidth(struct drm_plane_state *state) +{ + struct tegra_plane_state *tegra_state = to_tegra_plane_state(state); + unsigned int i, bpp, dst_w, dst_h, src_w, src_h, mul; + const struct tegra_dc_soc_info *soc; + const struct drm_format_info *fmt; + struct drm_crtc_state *crtc_state; + u64 avg_bandwidth, peak_bandwidth; + + if (!state->visible) + return 0; + + crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc); + if (!crtc_state) + return -EINVAL; + + src_w = drm_rect_width(&state->src) >> 16; + src_h = drm_rect_height(&state->src) >> 16; + dst_w = drm_rect_width(&state->dst); + dst_h = drm_rect_height(&state->dst); + + fmt = state->fb->format; + soc = to_tegra_dc(state->crtc)->soc; + + /* + * Note that real memory bandwidth vary depending on format and + * memory layout, we are not taking that into account because small + * estimation error isn't important since bandwidth is rounded up + * anyway. + */ + for (i = 0, bpp = 0; i < fmt->num_planes; i++) { + unsigned int bpp_plane = fmt->cpp[i] * 8; + + /* + * Sub-sampling is relevant for chroma planes only and vertical + * readouts are not cached, hence only horizontal sub-sampling + * matters. + */ + if (i > 0) + bpp_plane /= fmt->hsub; + + bpp += bpp_plane; + } + + /* average bandwidth in kbytes/sec */ + avg_bandwidth = min(src_w, dst_w) * min(src_h, dst_h); + avg_bandwidth *= drm_mode_vrefresh(&crtc_state->adjusted_mode); + avg_bandwidth = DIV_ROUND_UP(avg_bandwidth * bpp, 8) + 999; + do_div(avg_bandwidth, 1000); + + /* mode.clock in kHz, peak bandwidth in kbytes/sec */ + peak_bandwidth = DIV_ROUND_UP(crtc_state->adjusted_mode.clock * bpp, 8); + + /* + * Tegra30/114 Memory Controller can't interleave DC memory requests + * for the tiled windows because DC uses 16-bytes atom, while DDR3 + * uses 32-bytes atom. Hence there is x2 memory overfetch for tiled + * framebuffer and DDR3 on these SoCs. + */ + if (soc->plane_tiled_memory_bandwidth_x2 && + tegra_state->tiling.mode == TEGRA_BO_TILING_MODE_TILED) + mul = 2; + else + mul = 1; + + /* ICC bandwidth in kbytes/sec */ + tegra_state->peak_memory_bandwidth = kBps_to_icc(peak_bandwidth) * mul; + tegra_state->avg_memory_bandwidth = kBps_to_icc(avg_bandwidth) * mul; + + return 0; +} + int tegra_plane_state_add(struct tegra_plane *plane, struct drm_plane_state *state) { @@ -262,6 +312,10 @@ int tegra_plane_state_add(struct tegra_plane *plane, if (err < 0) return err; + err = tegra_plane_calculate_memory_bandwidth(state); + if (err < 0) + return err; + tegra = to_dc_state(crtc_state); tegra->planes |= WIN_A_ACT_REQ << plane->index; @@ -360,6 +414,22 @@ int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap) *swap = BYTE_SWAP_SWAP2; break; + case DRM_FORMAT_YVYU: + if (!swap) + return -EINVAL; + + *format = WIN_COLOR_DEPTH_YCbCr422; + *swap = BYTE_SWAP_SWAP4; + break; + + case DRM_FORMAT_VYUY: + if (!swap) + return -EINVAL; + + *format = WIN_COLOR_DEPTH_YCbCr422; + *swap = BYTE_SWAP_SWAP4HW; + break; + case DRM_FORMAT_YUV420: *format = WIN_COLOR_DEPTH_YCbCr420P; break; @@ -368,6 +438,34 @@ int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap) *format = WIN_COLOR_DEPTH_YCbCr422P; break; + case DRM_FORMAT_YUV444: + *format = WIN_COLOR_DEPTH_YCbCr444P; + break; + + case DRM_FORMAT_NV12: + *format = WIN_COLOR_DEPTH_YCbCr420SP; + break; + + case DRM_FORMAT_NV21: + *format = WIN_COLOR_DEPTH_YCrCb420SP; + break; + + case DRM_FORMAT_NV16: + *format = WIN_COLOR_DEPTH_YCbCr422SP; + break; + + case DRM_FORMAT_NV61: + *format = WIN_COLOR_DEPTH_YCrCb422SP; + break; + + case DRM_FORMAT_NV24: + *format = WIN_COLOR_DEPTH_YCbCr444SP; + break; + + case DRM_FORMAT_NV42: + *format = WIN_COLOR_DEPTH_YCrCb444SP; + break; + default: return -EINVAL; } @@ -388,13 +486,13 @@ bool tegra_plane_format_is_indexed(unsigned int format) return false; } -bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int *bpc) +bool tegra_plane_format_is_yuv(unsigned int format, unsigned int *planes, unsigned int *bpc) { switch (format) { case WIN_COLOR_DEPTH_YCbCr422: case WIN_COLOR_DEPTH_YUV422: - if (planar) - *planar = false; + if (planes) + *planes = 1; if (bpc) *bpc = 8; @@ -409,8 +507,23 @@ bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int * case WIN_COLOR_DEPTH_YUV422R: case WIN_COLOR_DEPTH_YCbCr422RA: case WIN_COLOR_DEPTH_YUV422RA: - if (planar) - *planar = true; + case WIN_COLOR_DEPTH_YCbCr444P: + if (planes) + *planes = 3; + + if (bpc) + *bpc = 8; + + return true; + + case WIN_COLOR_DEPTH_YCrCb420SP: + case WIN_COLOR_DEPTH_YCbCr420SP: + case WIN_COLOR_DEPTH_YCrCb422SP: + case WIN_COLOR_DEPTH_YCbCr422SP: + case WIN_COLOR_DEPTH_YCrCb444SP: + case WIN_COLOR_DEPTH_YCbCr444SP: + if (planes) + *planes = 2; if (bpc) *bpc = 8; @@ -418,8 +531,8 @@ bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int * return true; } - if (planar) - *planar = false; + if (planes) + *planes = 1; return false; } @@ -646,3 +759,36 @@ int tegra_plane_setup_legacy_state(struct tegra_plane *tegra, return 0; } + +static const char * const tegra_plane_icc_names[TEGRA_DC_LEGACY_PLANES_NUM] = { + "wina", "winb", "winc", NULL, NULL, NULL, "cursor", +}; + +int tegra_plane_interconnect_init(struct tegra_plane *plane) +{ + const char *icc_name = tegra_plane_icc_names[plane->index]; + struct device *dev = plane->dc->dev; + struct tegra_dc *dc = plane->dc; + int err; + + if (WARN_ON(plane->index >= TEGRA_DC_LEGACY_PLANES_NUM) || + WARN_ON(!tegra_plane_icc_names[plane->index])) + return -EINVAL; + + plane->icc_mem = devm_of_icc_get(dev, icc_name); + err = PTR_ERR_OR_ZERO(plane->icc_mem); + if (err) + return dev_err_probe(dev, err, "failed to get %s interconnect\n", + icc_name); + + /* plane B on T20/30 has a dedicated memory client for a 6-tap vertical filter */ + if (plane->index == 1 && dc->soc->has_win_b_vfilter_mem_client) { + plane->icc_mem_vfilter = devm_of_icc_get(dev, "winb-vfilter"); + err = PTR_ERR_OR_ZERO(plane->icc_mem_vfilter); + if (err) + return dev_err_probe(dev, err, "failed to get %s interconnect\n", + "winb-vfilter"); + } + + return 0; +} diff --git a/drivers/gpu/drm/tegra/plane.h b/drivers/gpu/drm/tegra/plane.h index 1785c1559c0c..e33a581e6490 100644 --- a/drivers/gpu/drm/tegra/plane.h +++ b/drivers/gpu/drm/tegra/plane.h @@ -8,6 +8,7 @@ #include <drm/drm_plane.h> +struct icc_path; struct tegra_bo; struct tegra_dc; @@ -16,6 +17,9 @@ struct tegra_plane { struct tegra_dc *dc; unsigned int offset; unsigned int index; + + struct icc_path *icc_mem; + struct icc_path *icc_mem_vfilter; }; struct tegra_cursor { @@ -39,7 +43,7 @@ struct tegra_plane_legacy_blending_state { struct tegra_plane_state { struct drm_plane_state base; - struct sg_table *sgt[3]; + struct host1x_bo_mapping *map[3]; dma_addr_t iova[3]; struct tegra_bo_tiling tiling; @@ -52,6 +56,11 @@ struct tegra_plane_state { /* used for legacy blending support only */ struct tegra_plane_legacy_blending_state blending[2]; bool opaque; + + /* bandwidths are in ICC units, i.e. kbytes/sec */ + u32 total_peak_memory_bandwidth; + u32 peak_memory_bandwidth; + u32 avg_memory_bandwidth; }; static inline struct tegra_plane_state * @@ -63,6 +72,12 @@ to_tegra_plane_state(struct drm_plane_state *state) return NULL; } +static inline const struct tegra_plane_state * +to_const_tegra_plane_state(const struct drm_plane_state *state) +{ + return to_tegra_plane_state((struct drm_plane_state *)state); +} + extern const struct drm_plane_funcs tegra_plane_funcs; int tegra_plane_prepare_fb(struct drm_plane *plane, @@ -75,8 +90,9 @@ int tegra_plane_state_add(struct tegra_plane *plane, int tegra_plane_format(u32 fourcc, u32 *format, u32 *swap); bool tegra_plane_format_is_indexed(unsigned int format); -bool tegra_plane_format_is_yuv(unsigned int format, bool *planar, unsigned int *bpc); +bool tegra_plane_format_is_yuv(unsigned int format, unsigned int *planes, unsigned int *bpc); int tegra_plane_setup_legacy_state(struct tegra_plane *tegra, struct tegra_plane_state *state); +int tegra_plane_interconnect_init(struct tegra_plane *plane); #endif /* TEGRA_PLANE_H */ diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index 4142a56ca764..ff5a749710db 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -5,6 +5,7 @@ */ #include <linux/clk.h> +#include <linux/of.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge_connector.h> @@ -17,6 +18,8 @@ struct tegra_rgb { struct tegra_output output; struct tegra_dc *dc; + struct clk *pll_d_out0; + struct clk *pll_d2_out0; struct clk *clk_parent; struct clk *clk; }; @@ -96,6 +99,7 @@ static void tegra_rgb_encoder_disable(struct drm_encoder *encoder) static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) { + struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct tegra_output *output = encoder_to_output(encoder); struct tegra_rgb *rgb = to_rgb(output); u32 value; @@ -105,10 +109,19 @@ static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL; tegra_dc_writel(rgb->dc, value, DC_DISP_DATA_ENABLE_OPTIONS); - /* XXX: parameterize? */ + /* configure H- and V-sync signal polarities */ value = tegra_dc_readl(rgb->dc, DC_COM_PIN_OUTPUT_POLARITY(1)); - value &= ~LVS_OUTPUT_POLARITY_LOW; - value &= ~LHS_OUTPUT_POLARITY_LOW; + + if (mode->flags & DRM_MODE_FLAG_NHSYNC) + value |= LHS_OUTPUT_POLARITY_LOW; + else + value &= ~LHS_OUTPUT_POLARITY_LOW; + + if (mode->flags & DRM_MODE_FLAG_NVSYNC) + value |= LVS_OUTPUT_POLARITY_LOW; + else + value &= ~LVS_OUTPUT_POLARITY_LOW; + tegra_dc_writel(rgb->dc, value, DC_COM_PIN_OUTPUT_POLARITY(1)); /* XXX: parameterize? */ @@ -116,13 +129,21 @@ static void tegra_rgb_encoder_enable(struct drm_encoder *encoder) DISP_ORDER_RED_BLUE; tegra_dc_writel(rgb->dc, value, DC_DISP_DISP_INTERFACE_CONTROL); - /* XXX: parameterize? */ - value = SC0_H_QUALIFIER_NONE | SC1_H_QUALIFIER_NONE; - tegra_dc_writel(rgb->dc, value, DC_DISP_SHIFT_CLOCK_OPTIONS); - tegra_dc_commit(rgb->dc); } +static bool tegra_rgb_pll_rate_change_allowed(struct tegra_rgb *rgb) +{ + if (!rgb->pll_d2_out0) + return false; + + if (!clk_is_match(rgb->clk_parent, rgb->pll_d_out0) && + !clk_is_match(rgb->clk_parent, rgb->pll_d2_out0)) + return false; + + return true; +} + static int tegra_rgb_encoder_atomic_check(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state, @@ -151,8 +172,17 @@ tegra_rgb_encoder_atomic_check(struct drm_encoder *encoder, * and hope that the desired frequency can be matched (or at least * matched sufficiently close that the panel will still work). */ - div = ((clk_get_rate(rgb->clk) * 2) / pclk) - 2; - pclk = 0; + if (tegra_rgb_pll_rate_change_allowed(rgb)) { + /* + * Set display controller clock to x2 of PCLK in order to + * produce higher resolution pulse positions. + */ + div = 2; + pclk *= 2; + } else { + div = ((clk_get_rate(rgb->clk) * 2) / pclk) - 2; + pclk = 0; + } err = tegra_dc_state_setup_clock(dc, crtc_state, rgb->clk_parent, pclk, div); @@ -170,6 +200,11 @@ static const struct drm_encoder_helper_funcs tegra_rgb_encoder_helper_funcs = { .atomic_check = tegra_rgb_encoder_atomic_check, }; +static void tegra_dc_of_node_put(void *data) +{ + of_node_put(data); +} + int tegra_dc_rgb_probe(struct tegra_dc *dc) { struct device_node *np; @@ -177,7 +212,14 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) int err; np = of_get_child_by_name(dc->dev->of_node, "rgb"); - if (!np || !of_device_is_available(np)) + if (!np) + return -ENODEV; + + err = devm_add_action_or_reset(dc->dev, tegra_dc_of_node_put, np); + if (err < 0) + return err; + + if (!of_device_is_available(np)) return -ENODEV; rgb = devm_kzalloc(dc->dev, sizeof(*rgb), GFP_KERNEL); @@ -195,35 +237,63 @@ int tegra_dc_rgb_probe(struct tegra_dc *dc) rgb->clk = devm_clk_get(dc->dev, NULL); if (IS_ERR(rgb->clk)) { dev_err(dc->dev, "failed to get clock\n"); - return PTR_ERR(rgb->clk); + err = PTR_ERR(rgb->clk); + goto remove; } rgb->clk_parent = devm_clk_get(dc->dev, "parent"); if (IS_ERR(rgb->clk_parent)) { dev_err(dc->dev, "failed to get parent clock\n"); - return PTR_ERR(rgb->clk_parent); + err = PTR_ERR(rgb->clk_parent); + goto remove; } err = clk_set_parent(rgb->clk, rgb->clk_parent); if (err < 0) { dev_err(dc->dev, "failed to set parent clock: %d\n", err); - return err; + goto remove; + } + + rgb->pll_d_out0 = clk_get_sys(NULL, "pll_d_out0"); + if (IS_ERR(rgb->pll_d_out0)) { + err = PTR_ERR(rgb->pll_d_out0); + dev_err(dc->dev, "failed to get pll_d_out0: %d\n", err); + goto remove; + } + + if (dc->soc->has_pll_d2_out0) { + rgb->pll_d2_out0 = clk_get_sys(NULL, "pll_d2_out0"); + if (IS_ERR(rgb->pll_d2_out0)) { + err = PTR_ERR(rgb->pll_d2_out0); + dev_err(dc->dev, "failed to get pll_d2_out0: %d\n", err); + goto put_pll; + } } dc->rgb = &rgb->output; return 0; + +put_pll: + clk_put(rgb->pll_d_out0); +remove: + tegra_output_remove(&rgb->output); + return err; } -int tegra_dc_rgb_remove(struct tegra_dc *dc) +void tegra_dc_rgb_remove(struct tegra_dc *dc) { + struct tegra_rgb *rgb; + if (!dc->rgb) - return 0; + return; + + rgb = to_rgb(dc->rgb); + clk_put(rgb->pll_d2_out0); + clk_put(rgb->pll_d_out0); tegra_output_remove(dc->rgb); dc->rgb = NULL; - - return 0; } int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc) @@ -275,11 +345,8 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc) if (output->bridge) { err = drm_bridge_attach(&output->encoder, output->bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); - if (err) { - dev_err(output->dev, "failed to attach bridge: %d\n", - err); + if (err) return err; - } connector = drm_bridge_connector_init(drm, &output->encoder); if (IS_ERR(connector)) { diff --git a/drivers/gpu/drm/tegra/riscv.c b/drivers/gpu/drm/tegra/riscv.c new file mode 100644 index 000000000000..6580416408f8 --- /dev/null +++ b/drivers/gpu/drm/tegra/riscv.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022, NVIDIA Corporation. + */ + +#include <linux/dev_printk.h> +#include <linux/device.h> +#include <linux/iopoll.h> +#include <linux/of.h> + +#include "riscv.h" + +#define RISCV_CPUCTL 0x4388 +#define RISCV_CPUCTL_STARTCPU_TRUE (1 << 0) +#define RISCV_BR_RETCODE 0x465c +#define RISCV_BR_RETCODE_RESULT_V(x) ((x) & 0x3) +#define RISCV_BR_RETCODE_RESULT_PASS_V 3 +#define RISCV_BCR_CTRL 0x4668 +#define RISCV_BCR_CTRL_CORE_SELECT_RISCV (1 << 4) +#define RISCV_BCR_DMACFG 0x466c +#define RISCV_BCR_DMACFG_TARGET_LOCAL_FB (0 << 0) +#define RISCV_BCR_DMACFG_LOCK_LOCKED (1 << 31) +#define RISCV_BCR_DMAADDR_PKCPARAM_LO 0x4670 +#define RISCV_BCR_DMAADDR_PKCPARAM_HI 0x4674 +#define RISCV_BCR_DMAADDR_FMCCODE_LO 0x4678 +#define RISCV_BCR_DMAADDR_FMCCODE_HI 0x467c +#define RISCV_BCR_DMAADDR_FMCDATA_LO 0x4680 +#define RISCV_BCR_DMAADDR_FMCDATA_HI 0x4684 +#define RISCV_BCR_DMACFG_SEC 0x4694 +#define RISCV_BCR_DMACFG_SEC_GSCID(v) ((v) << 16) + +static void riscv_writel(struct tegra_drm_riscv *riscv, u32 value, u32 offset) +{ + writel(value, riscv->regs + offset); +} + +int tegra_drm_riscv_read_descriptors(struct tegra_drm_riscv *riscv) +{ + struct tegra_drm_riscv_descriptor *bl = &riscv->bl_desc; + struct tegra_drm_riscv_descriptor *os = &riscv->os_desc; + const struct device_node *np = riscv->dev->of_node; + int err; + +#define READ_PROP(name, location) \ + err = of_property_read_u32(np, name, location); \ + if (err) { \ + dev_err(riscv->dev, "failed to read " name ": %d\n", err); \ + return err; \ + } + + READ_PROP("nvidia,bl-manifest-offset", &bl->manifest_offset); + READ_PROP("nvidia,bl-code-offset", &bl->code_offset); + READ_PROP("nvidia,bl-data-offset", &bl->data_offset); + READ_PROP("nvidia,os-manifest-offset", &os->manifest_offset); + READ_PROP("nvidia,os-code-offset", &os->code_offset); + READ_PROP("nvidia,os-data-offset", &os->data_offset); +#undef READ_PROP + + if (bl->manifest_offset == 0 && bl->code_offset == 0 && + bl->data_offset == 0 && os->manifest_offset == 0 && + os->code_offset == 0 && os->data_offset == 0) { + dev_err(riscv->dev, "descriptors not available\n"); + return -EINVAL; + } + + return 0; +} + +int tegra_drm_riscv_boot_bootrom(struct tegra_drm_riscv *riscv, phys_addr_t image_address, + u32 gscid, const struct tegra_drm_riscv_descriptor *desc) +{ + phys_addr_t addr; + int err; + u32 val; + + riscv_writel(riscv, RISCV_BCR_CTRL_CORE_SELECT_RISCV, RISCV_BCR_CTRL); + + addr = image_address + desc->manifest_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_PKCPARAM_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_PKCPARAM_HI); + + addr = image_address + desc->code_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCCODE_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCCODE_HI); + + addr = image_address + desc->data_offset; + riscv_writel(riscv, lower_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCDATA_LO); + riscv_writel(riscv, upper_32_bits(addr >> 8), RISCV_BCR_DMAADDR_FMCDATA_HI); + + riscv_writel(riscv, RISCV_BCR_DMACFG_SEC_GSCID(gscid), RISCV_BCR_DMACFG_SEC); + riscv_writel(riscv, + RISCV_BCR_DMACFG_TARGET_LOCAL_FB | RISCV_BCR_DMACFG_LOCK_LOCKED, RISCV_BCR_DMACFG); + + riscv_writel(riscv, RISCV_CPUCTL_STARTCPU_TRUE, RISCV_CPUCTL); + + err = readl_poll_timeout( + riscv->regs + RISCV_BR_RETCODE, val, + RISCV_BR_RETCODE_RESULT_V(val) == RISCV_BR_RETCODE_RESULT_PASS_V, + 10, 100000); + if (err) { + dev_err(riscv->dev, "error during bootrom execution. BR_RETCODE=%d\n", val); + return err; + } + + return 0; +} diff --git a/drivers/gpu/drm/tegra/riscv.h b/drivers/gpu/drm/tegra/riscv.h new file mode 100644 index 000000000000..bbeb2db078b6 --- /dev/null +++ b/drivers/gpu/drm/tegra/riscv.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022, NVIDIA Corporation. + */ + +#ifndef DRM_TEGRA_RISCV_H +#define DRM_TEGRA_RISCV_H + +struct tegra_drm_riscv_descriptor { + u32 manifest_offset; + u32 code_offset; + u32 code_size; + u32 data_offset; + u32 data_size; +}; + +struct tegra_drm_riscv { + /* User initializes */ + struct device *dev; + void __iomem *regs; + + struct tegra_drm_riscv_descriptor bl_desc; + struct tegra_drm_riscv_descriptor os_desc; +}; + +int tegra_drm_riscv_read_descriptors(struct tegra_drm_riscv *riscv); +int tegra_drm_riscv_boot_bootrom(struct tegra_drm_riscv *riscv, phys_addr_t image_address, + u32 gscid, const struct tegra_drm_riscv_descriptor *desc); + +#endif diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index 0ea320c1092b..4023cb5998f1 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -8,7 +8,7 @@ #include <linux/debugfs.h> #include <linux/io.h> #include <linux/module.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regulator/consumer.h> @@ -16,12 +16,15 @@ #include <soc/tegra/pmc.h> +#include <drm/display/drm_dp_helper.h> +#include <drm/display/drm_scdc_helper.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_debugfs.h> -#include <drm/drm_dp_helper.h> +#include <drm/drm_edid.h> +#include <drm/drm_eld.h> #include <drm/drm_file.h> #include <drm/drm_panel.h> -#include <drm/drm_scdc_helper.h> +#include <drm/drm_print.h> #include <drm/drm_simple_kms_helper.h> #include "dc.h" @@ -586,6 +589,7 @@ static u8 tegra_clk_sor_pad_get_parent(struct clk_hw *hw) } static const struct clk_ops tegra_clk_sor_pad_ops = { + .determine_rate = clk_hw_determine_rate_no_reparent, .set_parent = tegra_clk_sor_pad_set_parent, .get_parent = tegra_clk_sor_pad_get_parent, }; @@ -1153,7 +1157,7 @@ static int tegra_sor_compute_config(struct tegra_sor *sor, struct drm_dp_link *link) { const u64 f = 100000, link_rate = link->rate * 1000; - const u64 pclk = mode->clock * 1000; + const u64 pclk = (u64)mode->clock * 1000; u64 input, output, watermark, num; struct tegra_sor_params params; u32 num_syms_per_line; @@ -1707,6 +1711,7 @@ static void tegra_sor_early_unregister(struct drm_connector *connector) struct tegra_sor *sor = to_sor(output); drm_debugfs_remove_files(sor->debugfs_files, count, + connector->debugfs_entry, connector->dev->primary); kfree(sor->debugfs_files); sor->debugfs_files = NULL; @@ -1785,7 +1790,7 @@ static int tegra_sor_connector_get_modes(struct drm_connector *connector) static enum drm_mode_status tegra_sor_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) + const struct drm_display_mode *mode) { return MODE_OK; } @@ -1860,7 +1865,7 @@ static void tegra_sor_hdmi_write_infopack(struct tegra_sor *sor, { const u8 *ptr = data; unsigned long offset; - size_t i, j; + size_t i; u32 value; switch (ptr[0]) { @@ -1893,7 +1898,7 @@ static void tegra_sor_hdmi_write_infopack(struct tegra_sor *sor, * - subpack_low: bytes 0 - 3 * - subpack_high: bytes 4 - 6 (with byte 7 padded to 0x00) */ - for (i = 3, j = 0; i < size; i += 7, j += 8) { + for (i = 3; i < size; i += 7) { size_t rem = size - i, num = min_t(size_t, rem, 4); value = tegra_sor_hdmi_subpack(&ptr[i], num); @@ -2140,10 +2145,8 @@ static void tegra_sor_hdmi_disable_scrambling(struct tegra_sor *sor) static void tegra_sor_hdmi_scdc_disable(struct tegra_sor *sor) { - struct i2c_adapter *ddc = sor->output.ddc; - - drm_scdc_set_high_tmds_clock_ratio(ddc, false); - drm_scdc_set_scrambling(ddc, false); + drm_scdc_set_high_tmds_clock_ratio(&sor->output.connector, false); + drm_scdc_set_scrambling(&sor->output.connector, false); tegra_sor_hdmi_disable_scrambling(sor); } @@ -2168,10 +2171,8 @@ static void tegra_sor_hdmi_enable_scrambling(struct tegra_sor *sor) static void tegra_sor_hdmi_scdc_enable(struct tegra_sor *sor) { - struct i2c_adapter *ddc = sor->output.ddc; - - drm_scdc_set_high_tmds_clock_ratio(ddc, true); - drm_scdc_set_scrambling(ddc, true); + drm_scdc_set_high_tmds_clock_ratio(&sor->output.connector, true); + drm_scdc_set_scrambling(&sor->output.connector, true); tegra_sor_hdmi_enable_scrambling(sor); } @@ -2179,9 +2180,8 @@ static void tegra_sor_hdmi_scdc_enable(struct tegra_sor *sor) static void tegra_sor_hdmi_scdc_work(struct work_struct *work) { struct tegra_sor *sor = container_of(work, struct tegra_sor, scdc.work); - struct i2c_adapter *ddc = sor->output.ddc; - if (!drm_scdc_get_scrambling_status(ddc)) { + if (!drm_scdc_get_scrambling_status(&sor->output.connector)) { DRM_DEBUG_KMS("SCDC not scrambled\n"); tegra_sor_hdmi_scdc_enable(sor); } @@ -2667,7 +2667,7 @@ static void tegra_sor_dp_disable(struct drm_encoder *encoder) * the AUX transactions would just be timing out. */ if (output->connector.status != connector_status_disconnected) { - err = drm_dp_link_power_down(sor->aux, &sor->link); + err = drm_dp_link_power_down(sor->aux, sor->link.revision); if (err < 0) dev_err(sor->dev, "failed to power down link: %d\n", err); @@ -2883,7 +2883,7 @@ static void tegra_sor_dp_enable(struct drm_encoder *encoder) else dev_dbg(sor->dev, "link training succeeded\n"); - err = drm_dp_link_power_up(sor->aux, &sor->link); + err = drm_dp_link_power_up(sor->aux, sor->link.revision); if (err < 0) dev_err(sor->dev, "failed to power up DP link: %d\n", err); @@ -2964,11 +2964,9 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) int err; sor->avdd_io_supply = devm_regulator_get(sor->dev, "avdd-io-hdmi-dp"); - if (IS_ERR(sor->avdd_io_supply)) { - dev_err(sor->dev, "cannot get AVDD I/O supply: %ld\n", - PTR_ERR(sor->avdd_io_supply)); - return PTR_ERR(sor->avdd_io_supply); - } + if (IS_ERR(sor->avdd_io_supply)) + return dev_err_probe(sor->dev, PTR_ERR(sor->avdd_io_supply), + "cannot get AVDD I/O supply\n"); err = tegra_sor_enable_regulator(sor, sor->avdd_io_supply); if (err < 0) { @@ -2978,11 +2976,9 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) } sor->vdd_pll_supply = devm_regulator_get(sor->dev, "vdd-hdmi-dp-pll"); - if (IS_ERR(sor->vdd_pll_supply)) { - dev_err(sor->dev, "cannot get VDD PLL supply: %ld\n", - PTR_ERR(sor->vdd_pll_supply)); - return PTR_ERR(sor->vdd_pll_supply); - } + if (IS_ERR(sor->vdd_pll_supply)) + return dev_err_probe(sor->dev, PTR_ERR(sor->vdd_pll_supply), + "cannot get VDD PLL supply\n"); err = tegra_sor_enable_regulator(sor, sor->vdd_pll_supply); if (err < 0) { @@ -2992,11 +2988,9 @@ static int tegra_sor_hdmi_probe(struct tegra_sor *sor) } sor->hdmi_supply = devm_regulator_get(sor->dev, "hdmi"); - if (IS_ERR(sor->hdmi_supply)) { - dev_err(sor->dev, "cannot get HDMI supply: %ld\n", - PTR_ERR(sor->hdmi_supply)); - return PTR_ERR(sor->hdmi_supply); - } + if (IS_ERR(sor->hdmi_supply)) + return dev_err_probe(sor->dev, PTR_ERR(sor->hdmi_supply), + "cannot get HDMI supply\n"); err = tegra_sor_enable_regulator(sor, sor->hdmi_supply); if (err < 0) { @@ -3718,7 +3712,6 @@ static int tegra_sor_probe(struct platform_device *pdev) { struct device_node *np; struct tegra_sor *sor; - struct resource *regs; int err; sor = devm_kzalloc(&pdev->dev, sizeof(*sor), GFP_KERNEL); @@ -3791,18 +3784,15 @@ static int tegra_sor_probe(struct platform_device *pdev) } } - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - sor->regs = devm_ioremap_resource(&pdev->dev, regs); + sor->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sor->regs)) { err = PTR_ERR(sor->regs); goto remove; } err = platform_get_irq(pdev, 0); - if (err < 0) { - dev_err(&pdev->dev, "failed to get IRQ: %d\n", err); + if (err < 0) goto remove; - } sor->irq = err; @@ -3978,17 +3968,11 @@ put_aux: return err; } -static int tegra_sor_remove(struct platform_device *pdev) +static void tegra_sor_remove(struct platform_device *pdev) { struct tegra_sor *sor = platform_get_drvdata(pdev); - int err; - err = host1x_client_unregister(&sor->client); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; - } + host1x_client_unregister(&sor->client); pm_runtime_disable(&pdev->dev); @@ -3998,8 +3982,6 @@ static int tegra_sor_remove(struct platform_device *pdev) } tegra_output_remove(&sor->output); - - return 0; } static int __maybe_unused tegra_sor_suspend(struct device *dev) diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c new file mode 100644 index 000000000000..2430fcc97448 --- /dev/null +++ b/drivers/gpu/drm/tegra/submit.c @@ -0,0 +1,684 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 NVIDIA Corporation */ + +#include <linux/dma-fence-array.h> +#include <linux/dma-mapping.h> +#include <linux/file.h> +#include <linux/host1x.h> +#include <linux/iommu.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/nospec.h> +#include <linux/pm_runtime.h> +#include <linux/scatterlist.h> +#include <linux/slab.h> +#include <linux/sync_file.h> + +#include <drm/drm_drv.h> +#include <drm/drm_file.h> +#include <drm/drm_syncobj.h> + +#include "drm.h" +#include "gem.h" +#include "submit.h" +#include "uapi.h" + +#define SUBMIT_ERR(context, fmt, ...) \ + dev_err_ratelimited(context->client->base.dev, \ + "%s: job submission failed: " fmt "\n", \ + current->comm, ##__VA_ARGS__) + +struct gather_bo { + struct host1x_bo base; + + struct kref ref; + + struct device *dev; + u32 *gather_data; + dma_addr_t gather_data_dma; + size_t gather_data_words; +}; + +static struct host1x_bo *gather_bo_get(struct host1x_bo *host_bo) +{ + struct gather_bo *bo = container_of(host_bo, struct gather_bo, base); + + kref_get(&bo->ref); + + return host_bo; +} + +static void gather_bo_release(struct kref *ref) +{ + struct gather_bo *bo = container_of(ref, struct gather_bo, ref); + + dma_free_attrs(bo->dev, bo->gather_data_words * 4, bo->gather_data, bo->gather_data_dma, + 0); + kfree(bo); +} + +static void gather_bo_put(struct host1x_bo *host_bo) +{ + struct gather_bo *bo = container_of(host_bo, struct gather_bo, base); + + kref_put(&bo->ref, gather_bo_release); +} + +static struct host1x_bo_mapping * +gather_bo_pin(struct device *dev, struct host1x_bo *bo, enum dma_data_direction direction) +{ + struct gather_bo *gather = container_of(bo, struct gather_bo, base); + struct host1x_bo_mapping *map; + int err; + + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return ERR_PTR(-ENOMEM); + + kref_init(&map->ref); + map->bo = host1x_bo_get(bo); + map->direction = direction; + map->dev = dev; + + map->sgt = kzalloc(sizeof(*map->sgt), GFP_KERNEL); + if (!map->sgt) { + err = -ENOMEM; + goto free; + } + + err = dma_get_sgtable(gather->dev, map->sgt, gather->gather_data, gather->gather_data_dma, + gather->gather_data_words * 4); + if (err) + goto free_sgt; + + err = dma_map_sgtable(dev, map->sgt, direction, 0); + if (err) + goto free_sgt; + + map->phys = sg_dma_address(map->sgt->sgl); + map->size = gather->gather_data_words * 4; + map->chunks = err; + + return map; + +free_sgt: + sg_free_table(map->sgt); + kfree(map->sgt); +free: + kfree(map); + return ERR_PTR(err); +} + +static void gather_bo_unpin(struct host1x_bo_mapping *map) +{ + if (!map) + return; + + dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0); + sg_free_table(map->sgt); + kfree(map->sgt); + host1x_bo_put(map->bo); + + kfree(map); +} + +static void *gather_bo_mmap(struct host1x_bo *host_bo) +{ + struct gather_bo *bo = container_of(host_bo, struct gather_bo, base); + + return bo->gather_data; +} + +static void gather_bo_munmap(struct host1x_bo *host_bo, void *addr) +{ +} + +static const struct host1x_bo_ops gather_bo_ops = { + .get = gather_bo_get, + .put = gather_bo_put, + .pin = gather_bo_pin, + .unpin = gather_bo_unpin, + .mmap = gather_bo_mmap, + .munmap = gather_bo_munmap, +}; + +static struct tegra_drm_mapping * +tegra_drm_mapping_get(struct tegra_drm_context *context, u32 id) +{ + struct tegra_drm_mapping *mapping; + + xa_lock(&context->mappings); + + mapping = xa_load(&context->mappings, id); + if (mapping) + kref_get(&mapping->ref); + + xa_unlock(&context->mappings); + + return mapping; +} + +static void *alloc_copy_user_array(void __user *from, size_t count, size_t size) +{ + size_t copy_len; + void *data; + + if (check_mul_overflow(count, size, ©_len)) + return ERR_PTR(-EINVAL); + + if (copy_len > 0x4000) + return ERR_PTR(-E2BIG); + + data = vmemdup_user(from, copy_len); + if (IS_ERR(data)) + return ERR_CAST(data); + + return data; +} + +static int submit_copy_gather_data(struct gather_bo **pbo, struct device *dev, + struct tegra_drm_context *context, + struct drm_tegra_channel_submit *args) +{ + struct gather_bo *bo; + size_t copy_len; + + if (args->gather_data_words == 0) { + SUBMIT_ERR(context, "gather_data_words cannot be zero"); + return -EINVAL; + } + + if (check_mul_overflow((size_t)args->gather_data_words, (size_t)4, ©_len)) { + SUBMIT_ERR(context, "gather_data_words is too large"); + return -EINVAL; + } + + bo = kzalloc(sizeof(*bo), GFP_KERNEL); + if (!bo) { + SUBMIT_ERR(context, "failed to allocate memory for bo info"); + return -ENOMEM; + } + + host1x_bo_init(&bo->base, &gather_bo_ops); + kref_init(&bo->ref); + bo->dev = dev; + + bo->gather_data = dma_alloc_attrs(dev, copy_len, &bo->gather_data_dma, + GFP_KERNEL | __GFP_NOWARN, 0); + if (!bo->gather_data) { + SUBMIT_ERR(context, "failed to allocate memory for gather data"); + kfree(bo); + return -ENOMEM; + } + + if (copy_from_user(bo->gather_data, u64_to_user_ptr(args->gather_data_ptr), copy_len)) { + SUBMIT_ERR(context, "failed to copy gather data from userspace"); + dma_free_attrs(dev, copy_len, bo->gather_data, bo->gather_data_dma, 0); + kfree(bo); + return -EFAULT; + } + + bo->gather_data_words = args->gather_data_words; + + *pbo = bo; + + return 0; +} + +static int submit_write_reloc(struct tegra_drm_context *context, struct gather_bo *bo, + struct drm_tegra_submit_buf *buf, struct tegra_drm_mapping *mapping) +{ + /* TODO check that target_offset is within bounds */ + dma_addr_t iova = mapping->iova + buf->reloc.target_offset; + u32 written_ptr; + +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + if (buf->flags & DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT) + iova |= BIT_ULL(39); +#endif + + written_ptr = iova >> buf->reloc.shift; + + if (buf->reloc.gather_offset_words >= bo->gather_data_words) { + SUBMIT_ERR(context, + "relocation has too large gather offset (%u vs gather length %zu)", + buf->reloc.gather_offset_words, bo->gather_data_words); + return -EINVAL; + } + + buf->reloc.gather_offset_words = array_index_nospec(buf->reloc.gather_offset_words, + bo->gather_data_words); + + bo->gather_data[buf->reloc.gather_offset_words] = written_ptr; + + return 0; +} + +static int submit_process_bufs(struct tegra_drm_context *context, struct gather_bo *bo, + struct drm_tegra_channel_submit *args, + struct tegra_drm_submit_data *job_data) +{ + struct tegra_drm_used_mapping *mappings; + struct drm_tegra_submit_buf *bufs; + int err; + u32 i; + + bufs = alloc_copy_user_array(u64_to_user_ptr(args->bufs_ptr), args->num_bufs, + sizeof(*bufs)); + if (IS_ERR(bufs)) { + SUBMIT_ERR(context, "failed to copy bufs array from userspace"); + return PTR_ERR(bufs); + } + + mappings = kcalloc(args->num_bufs, sizeof(*mappings), GFP_KERNEL); + if (!mappings) { + SUBMIT_ERR(context, "failed to allocate memory for mapping info"); + err = -ENOMEM; + goto done; + } + + for (i = 0; i < args->num_bufs; i++) { + struct drm_tegra_submit_buf *buf = &bufs[i]; + struct tegra_drm_mapping *mapping; + + if (buf->flags & ~DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT) { + SUBMIT_ERR(context, "invalid flag specified for buffer"); + err = -EINVAL; + goto drop_refs; + } + + mapping = tegra_drm_mapping_get(context, buf->mapping); + if (!mapping) { + SUBMIT_ERR(context, "invalid mapping ID '%u' for buffer", buf->mapping); + err = -EINVAL; + goto drop_refs; + } + + err = submit_write_reloc(context, bo, buf, mapping); + if (err) { + tegra_drm_mapping_put(mapping); + goto drop_refs; + } + + mappings[i].mapping = mapping; + mappings[i].flags = buf->flags; + } + + job_data->used_mappings = mappings; + job_data->num_used_mappings = i; + + err = 0; + + goto done; + +drop_refs: + while (i--) + tegra_drm_mapping_put(mappings[i].mapping); + + kfree(mappings); + job_data->used_mappings = NULL; + +done: + kvfree(bufs); + + return err; +} + +static int submit_get_syncpt(struct tegra_drm_context *context, struct host1x_job *job, + struct xarray *syncpoints, struct drm_tegra_channel_submit *args) +{ + struct host1x_syncpt *sp; + + if (args->syncpt.flags) { + SUBMIT_ERR(context, "invalid flag specified for syncpt"); + return -EINVAL; + } + + /* Syncpt ref will be dropped on job release */ + sp = xa_load(syncpoints, args->syncpt.id); + if (!sp) { + SUBMIT_ERR(context, "syncpoint specified in syncpt was not allocated"); + return -EINVAL; + } + + job->syncpt = host1x_syncpt_get(sp); + job->syncpt_incrs = args->syncpt.increments; + + return 0; +} + +static int submit_job_add_gather(struct host1x_job *job, struct tegra_drm_context *context, + struct drm_tegra_submit_cmd_gather_uptr *cmd, + struct gather_bo *bo, u32 *offset, + struct tegra_drm_submit_data *job_data, + u32 *class) +{ + u32 next_offset; + + if (cmd->reserved[0] || cmd->reserved[1] || cmd->reserved[2]) { + SUBMIT_ERR(context, "non-zero reserved field in GATHER_UPTR command"); + return -EINVAL; + } + + /* Check for maximum gather size */ + if (cmd->words > 16383) { + SUBMIT_ERR(context, "too many words in GATHER_UPTR command"); + return -EINVAL; + } + + if (check_add_overflow(*offset, cmd->words, &next_offset)) { + SUBMIT_ERR(context, "too many total words in job"); + return -EINVAL; + } + + if (next_offset > bo->gather_data_words) { + SUBMIT_ERR(context, "GATHER_UPTR command overflows gather data"); + return -EINVAL; + } + + if (tegra_drm_fw_validate(context->client, bo->gather_data, *offset, + cmd->words, job_data, class)) { + SUBMIT_ERR(context, "job was rejected by firewall"); + return -EINVAL; + } + + host1x_job_add_gather(job, &bo->base, cmd->words, *offset * 4); + + *offset = next_offset; + + return 0; +} + +static struct host1x_job * +submit_create_job(struct tegra_drm_context *context, struct gather_bo *bo, + struct drm_tegra_channel_submit *args, struct tegra_drm_submit_data *job_data, + struct xarray *syncpoints) +{ + struct drm_tegra_submit_cmd *cmds; + u32 i, gather_offset = 0, class; + struct host1x_job *job; + int err; + + /* Set initial class for firewall. */ + class = context->client->base.class; + + cmds = alloc_copy_user_array(u64_to_user_ptr(args->cmds_ptr), args->num_cmds, + sizeof(*cmds)); + if (IS_ERR(cmds)) { + SUBMIT_ERR(context, "failed to copy cmds array from userspace"); + return ERR_CAST(cmds); + } + + job = host1x_job_alloc(context->channel, args->num_cmds, 0, true); + if (!job) { + SUBMIT_ERR(context, "failed to allocate memory for job"); + job = ERR_PTR(-ENOMEM); + goto done; + } + + err = submit_get_syncpt(context, job, syncpoints, args); + if (err < 0) + goto free_job; + + job->client = &context->client->base; + job->class = context->client->base.class; + job->serialize = true; + + for (i = 0; i < args->num_cmds; i++) { + struct drm_tegra_submit_cmd *cmd = &cmds[i]; + + if (cmd->flags) { + SUBMIT_ERR(context, "unknown flags given for cmd"); + err = -EINVAL; + goto free_job; + } + + if (cmd->type == DRM_TEGRA_SUBMIT_CMD_GATHER_UPTR) { + err = submit_job_add_gather(job, context, &cmd->gather_uptr, bo, + &gather_offset, job_data, &class); + if (err) + goto free_job; + } else if (cmd->type == DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT) { + if (cmd->wait_syncpt.reserved[0] || cmd->wait_syncpt.reserved[1]) { + SUBMIT_ERR(context, "non-zero reserved value"); + err = -EINVAL; + goto free_job; + } + + host1x_job_add_wait(job, cmd->wait_syncpt.id, cmd->wait_syncpt.value, + false, class); + } else if (cmd->type == DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT_RELATIVE) { + if (cmd->wait_syncpt.reserved[0] || cmd->wait_syncpt.reserved[1]) { + SUBMIT_ERR(context, "non-zero reserved value"); + err = -EINVAL; + goto free_job; + } + + if (cmd->wait_syncpt.id != args->syncpt.id) { + SUBMIT_ERR(context, "syncpoint ID in CMD_WAIT_SYNCPT_RELATIVE is not used by the job"); + err = -EINVAL; + goto free_job; + } + + host1x_job_add_wait(job, cmd->wait_syncpt.id, cmd->wait_syncpt.value, + true, class); + } else { + SUBMIT_ERR(context, "unknown cmd type"); + err = -EINVAL; + goto free_job; + } + } + + if (gather_offset == 0) { + SUBMIT_ERR(context, "job must have at least one gather"); + err = -EINVAL; + goto free_job; + } + + goto done; + +free_job: + host1x_job_put(job); + job = ERR_PTR(err); + +done: + kvfree(cmds); + + return job; +} + +static void release_job(struct host1x_job *job) +{ + struct tegra_drm_client *client = container_of(job->client, struct tegra_drm_client, base); + struct tegra_drm_submit_data *job_data = job->user_data; + u32 i; + + if (job->memory_context) + host1x_memory_context_put(job->memory_context); + + for (i = 0; i < job_data->num_used_mappings; i++) + tegra_drm_mapping_put(job_data->used_mappings[i].mapping); + + kfree(job_data->used_mappings); + kfree(job_data); + + pm_runtime_mark_last_busy(client->base.dev); + pm_runtime_put_autosuspend(client->base.dev); +} + +int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data, + struct drm_file *file) +{ + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_channel_submit *args = data; + struct tegra_drm_submit_data *job_data; + struct drm_syncobj *syncobj = NULL; + struct tegra_drm_context *context; + struct host1x_job *job; + struct gather_bo *bo; + u32 i; + int err; + + mutex_lock(&fpriv->lock); + + context = xa_load(&fpriv->contexts, args->context); + if (!context) { + mutex_unlock(&fpriv->lock); + pr_err_ratelimited("%s: %s: invalid channel context '%#x'", __func__, + current->comm, args->context); + return -EINVAL; + } + + if (args->syncobj_in) { + struct dma_fence *fence; + + err = drm_syncobj_find_fence(file, args->syncobj_in, 0, 0, &fence); + if (err) { + SUBMIT_ERR(context, "invalid syncobj_in '%#x'", args->syncobj_in); + goto unlock; + } + + err = dma_fence_wait_timeout(fence, true, msecs_to_jiffies(10000)); + dma_fence_put(fence); + if (err) { + SUBMIT_ERR(context, "wait for syncobj_in timed out"); + goto unlock; + } + } + + if (args->syncobj_out) { + syncobj = drm_syncobj_find(file, args->syncobj_out); + if (!syncobj) { + SUBMIT_ERR(context, "invalid syncobj_out '%#x'", args->syncobj_out); + err = -ENOENT; + goto unlock; + } + } + + /* Allocate gather BO and copy gather words in. */ + err = submit_copy_gather_data(&bo, drm->dev, context, args); + if (err) + goto unlock; + + job_data = kzalloc(sizeof(*job_data), GFP_KERNEL); + if (!job_data) { + SUBMIT_ERR(context, "failed to allocate memory for job data"); + err = -ENOMEM; + goto put_bo; + } + + /* Get data buffer mappings and do relocation patching. */ + err = submit_process_bufs(context, bo, args, job_data); + if (err) + goto free_job_data; + + /* Allocate host1x_job and add gathers and waits to it. */ + job = submit_create_job(context, bo, args, job_data, &fpriv->syncpoints); + if (IS_ERR(job)) { + err = PTR_ERR(job); + goto free_job_data; + } + + /* Map gather data for Host1x. */ + err = host1x_job_pin(job, context->client->base.dev); + if (err) { + SUBMIT_ERR(context, "failed to pin job: %d", err); + goto put_job; + } + + if (context->client->ops->get_streamid_offset) { + err = context->client->ops->get_streamid_offset( + context->client, &job->engine_streamid_offset); + if (err) { + SUBMIT_ERR(context, "failed to get streamid offset: %d", err); + goto unpin_job; + } + } + + if (context->memory_context && context->client->ops->can_use_memory_ctx) { + bool supported; + + err = context->client->ops->can_use_memory_ctx(context->client, &supported); + if (err) { + SUBMIT_ERR(context, "failed to detect if engine can use memory context: %d", err); + goto unpin_job; + } + + if (supported) { + job->memory_context = context->memory_context; + host1x_memory_context_get(job->memory_context); + } + } else if (context->client->ops->get_streamid_offset) { + /* + * Job submission will need to temporarily change stream ID, + * so need to tell it what to change it back to. + */ + if (!tegra_dev_iommu_get_stream_id(context->client->base.dev, + &job->engine_fallback_streamid)) + job->engine_fallback_streamid = TEGRA_STREAM_ID_BYPASS; + } + + /* Boot engine. */ + err = pm_runtime_resume_and_get(context->client->base.dev); + if (err < 0) { + SUBMIT_ERR(context, "could not power up engine: %d", err); + goto put_memory_context; + } + + job->user_data = job_data; + job->release = release_job; + job->timeout = 10000; + + /* + * job_data is now part of job reference counting, so don't release + * it from here. + */ + job_data = NULL; + + /* Submit job to hardware. */ + err = host1x_job_submit(job); + if (err) { + SUBMIT_ERR(context, "host1x job submission failed: %d", err); + goto unpin_job; + } + + /* Return postfences to userspace and add fences to DMA reservations. */ + args->syncpt.value = job->syncpt_end; + + if (syncobj) { + struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end, true); + if (IS_ERR(fence)) { + err = PTR_ERR(fence); + SUBMIT_ERR(context, "failed to create postfence: %d", err); + } + + drm_syncobj_replace_fence(syncobj, fence); + } + + goto put_job; + +put_memory_context: + if (job->memory_context) + host1x_memory_context_put(job->memory_context); +unpin_job: + host1x_job_unpin(job); +put_job: + host1x_job_put(job); +free_job_data: + if (job_data && job_data->used_mappings) { + for (i = 0; i < job_data->num_used_mappings; i++) + tegra_drm_mapping_put(job_data->used_mappings[i].mapping); + + kfree(job_data->used_mappings); + } + + kfree(job_data); +put_bo: + gather_bo_put(&bo->base); +unlock: + if (syncobj) + drm_syncobj_put(syncobj); + + mutex_unlock(&fpriv->lock); + return err; +} diff --git a/drivers/gpu/drm/tegra/submit.h b/drivers/gpu/drm/tegra/submit.h new file mode 100644 index 000000000000..cf6a2f0a29fc --- /dev/null +++ b/drivers/gpu/drm/tegra/submit.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2020 NVIDIA Corporation */ + +#ifndef _TEGRA_DRM_UAPI_SUBMIT_H +#define _TEGRA_DRM_UAPI_SUBMIT_H + +struct tegra_drm_used_mapping { + struct tegra_drm_mapping *mapping; + u32 flags; +}; + +struct tegra_drm_submit_data { + struct tegra_drm_used_mapping *used_mappings; + u32 num_used_mappings; +}; + +int tegra_drm_fw_validate(struct tegra_drm_client *client, u32 *data, u32 start, + u32 words, struct tegra_drm_submit_data *submit, + u32 *job_class); + +#endif diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c new file mode 100644 index 000000000000..d0b6a1fa6efa --- /dev/null +++ b/drivers/gpu/drm/tegra/uapi.c @@ -0,0 +1,362 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 NVIDIA Corporation */ + +#include <linux/host1x.h> +#include <linux/iommu.h> +#include <linux/list.h> + +#include <drm/drm_drv.h> +#include <drm/drm_file.h> +#include <drm/drm_utils.h> + +#include "drm.h" +#include "uapi.h" + +static void tegra_drm_mapping_release(struct kref *ref) +{ + struct tegra_drm_mapping *mapping = + container_of(ref, struct tegra_drm_mapping, ref); + + host1x_bo_unpin(mapping->map); + host1x_bo_put(mapping->bo); + + kfree(mapping); +} + +void tegra_drm_mapping_put(struct tegra_drm_mapping *mapping) +{ + kref_put(&mapping->ref, tegra_drm_mapping_release); +} + +static void tegra_drm_channel_context_close(struct tegra_drm_context *context) +{ + struct tegra_drm_mapping *mapping; + unsigned long id; + + if (context->memory_context) + host1x_memory_context_put(context->memory_context); + + xa_for_each(&context->mappings, id, mapping) + tegra_drm_mapping_put(mapping); + + xa_destroy(&context->mappings); + + host1x_channel_put(context->channel); + + kfree(context); +} + +void tegra_drm_uapi_close_file(struct tegra_drm_file *file) +{ + struct tegra_drm_context *context; + struct host1x_syncpt *sp; + unsigned long id; + + xa_for_each(&file->contexts, id, context) + tegra_drm_channel_context_close(context); + + xa_for_each(&file->syncpoints, id, sp) + host1x_syncpt_put(sp); + + xa_destroy(&file->contexts); + xa_destroy(&file->syncpoints); +} + +static struct tegra_drm_client *tegra_drm_find_client(struct tegra_drm *tegra, u32 class) +{ + struct tegra_drm_client *client; + + list_for_each_entry(client, &tegra->clients, list) + if (client->base.class == class) + return client; + + return NULL; +} + +int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct host1x *host = tegra_drm_to_host1x(drm->dev_private); + struct tegra_drm_file *fpriv = file->driver_priv; + struct tegra_drm *tegra = drm->dev_private; + struct drm_tegra_channel_open *args = data; + struct tegra_drm_client *client = NULL; + struct tegra_drm_context *context; + int err; + + if (args->flags) + return -EINVAL; + + context = kzalloc(sizeof(*context), GFP_KERNEL); + if (!context) + return -ENOMEM; + + client = tegra_drm_find_client(tegra, args->host1x_class); + if (!client) { + err = -ENODEV; + goto free; + } + + if (client->shared_channel) { + context->channel = host1x_channel_get(client->shared_channel); + } else { + context->channel = host1x_channel_request(&client->base); + if (!context->channel) { + err = -EBUSY; + goto free; + } + } + + /* Only allocate context if the engine supports context isolation. */ + if (device_iommu_mapped(client->base.dev) && client->ops->can_use_memory_ctx) { + bool supported; + + err = client->ops->can_use_memory_ctx(client, &supported); + if (err) + goto put_channel; + + if (supported) { + struct pid *pid = get_task_pid(current, PIDTYPE_TGID); + context->memory_context = host1x_memory_context_alloc( + host, client->base.dev, pid); + put_pid(pid); + } + + if (IS_ERR(context->memory_context)) { + if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) { + err = PTR_ERR(context->memory_context); + goto put_channel; + } else { + /* + * OK, HW does not support contexts or contexts + * are disabled. + */ + context->memory_context = NULL; + } + } + } + + err = xa_alloc(&fpriv->contexts, &args->context, context, XA_LIMIT(1, U32_MAX), + GFP_KERNEL); + if (err < 0) + goto put_memctx; + + context->client = client; + xa_init_flags(&context->mappings, XA_FLAGS_ALLOC1); + + args->version = client->version; + args->capabilities = 0; + + if (device_get_dma_attr(client->base.dev) == DEV_DMA_COHERENT) + args->capabilities |= DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT; + + return 0; + +put_memctx: + if (context->memory_context) + host1x_memory_context_put(context->memory_context); +put_channel: + host1x_channel_put(context->channel); +free: + kfree(context); + + return err; +} + +int tegra_drm_ioctl_channel_close(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_channel_close *args = data; + struct tegra_drm_context *context; + + mutex_lock(&fpriv->lock); + + context = xa_load(&fpriv->contexts, args->context); + if (!context) { + mutex_unlock(&fpriv->lock); + return -EINVAL; + } + + xa_erase(&fpriv->contexts, args->context); + + mutex_unlock(&fpriv->lock); + + tegra_drm_channel_context_close(context); + + return 0; +} + +int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_channel_map *args = data; + struct tegra_drm_mapping *mapping; + struct tegra_drm_context *context; + enum dma_data_direction direction; + struct device *mapping_dev; + int err = 0; + + if (args->flags & ~DRM_TEGRA_CHANNEL_MAP_READ_WRITE) + return -EINVAL; + + mutex_lock(&fpriv->lock); + + context = xa_load(&fpriv->contexts, args->context); + if (!context) { + mutex_unlock(&fpriv->lock); + return -EINVAL; + } + + mapping = kzalloc(sizeof(*mapping), GFP_KERNEL); + if (!mapping) { + err = -ENOMEM; + goto unlock; + } + + kref_init(&mapping->ref); + + if (context->memory_context) + mapping_dev = &context->memory_context->dev; + else + mapping_dev = context->client->base.dev; + + mapping->bo = tegra_gem_lookup(file, args->handle); + if (!mapping->bo) { + err = -EINVAL; + goto free; + } + + switch (args->flags & DRM_TEGRA_CHANNEL_MAP_READ_WRITE) { + case DRM_TEGRA_CHANNEL_MAP_READ_WRITE: + direction = DMA_BIDIRECTIONAL; + break; + + case DRM_TEGRA_CHANNEL_MAP_WRITE: + direction = DMA_FROM_DEVICE; + break; + + case DRM_TEGRA_CHANNEL_MAP_READ: + direction = DMA_TO_DEVICE; + break; + + default: + err = -EINVAL; + goto put_gem; + } + + mapping->map = host1x_bo_pin(mapping_dev, mapping->bo, direction, NULL); + if (IS_ERR(mapping->map)) { + err = PTR_ERR(mapping->map); + goto put_gem; + } + + mapping->iova = mapping->map->phys; + mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size; + + err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX), + GFP_KERNEL); + if (err < 0) + goto unpin; + + mutex_unlock(&fpriv->lock); + + return 0; + +unpin: + host1x_bo_unpin(mapping->map); +put_gem: + host1x_bo_put(mapping->bo); +free: + kfree(mapping); +unlock: + mutex_unlock(&fpriv->lock); + return err; +} + +int tegra_drm_ioctl_channel_unmap(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_channel_unmap *args = data; + struct tegra_drm_mapping *mapping; + struct tegra_drm_context *context; + + mutex_lock(&fpriv->lock); + + context = xa_load(&fpriv->contexts, args->context); + if (!context) { + mutex_unlock(&fpriv->lock); + return -EINVAL; + } + + mapping = xa_erase(&context->mappings, args->mapping); + + mutex_unlock(&fpriv->lock); + + if (!mapping) + return -EINVAL; + + tegra_drm_mapping_put(mapping); + return 0; +} + +int tegra_drm_ioctl_syncpoint_allocate(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct host1x *host1x = tegra_drm_to_host1x(drm->dev_private); + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_syncpoint_allocate *args = data; + struct host1x_syncpt *sp; + int err; + + if (args->id) + return -EINVAL; + + sp = host1x_syncpt_alloc(host1x, HOST1X_SYNCPT_CLIENT_MANAGED, current->comm); + if (!sp) + return -EBUSY; + + args->id = host1x_syncpt_id(sp); + + err = xa_insert(&fpriv->syncpoints, args->id, sp, GFP_KERNEL); + if (err) { + host1x_syncpt_put(sp); + return err; + } + + return 0; +} + +int tegra_drm_ioctl_syncpoint_free(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct tegra_drm_file *fpriv = file->driver_priv; + struct drm_tegra_syncpoint_allocate *args = data; + struct host1x_syncpt *sp; + + mutex_lock(&fpriv->lock); + sp = xa_erase(&fpriv->syncpoints, args->id); + mutex_unlock(&fpriv->lock); + + if (!sp) + return -EINVAL; + + host1x_syncpt_put(sp); + + return 0; +} + +int tegra_drm_ioctl_syncpoint_wait(struct drm_device *drm, void *data, struct drm_file *file) +{ + struct host1x *host1x = tegra_drm_to_host1x(drm->dev_private); + struct drm_tegra_syncpoint_wait *args = data; + signed long timeout_jiffies; + struct host1x_syncpt *sp; + + if (args->padding != 0) + return -EINVAL; + + sp = host1x_syncpt_get_by_id_noref(host1x, args->id); + if (!sp) + return -EINVAL; + + timeout_jiffies = drm_timeout_abs_to_jiffies(args->timeout_ns); + + return host1x_syncpt_wait(sp, args->threshold, timeout_jiffies, &args->value); +} diff --git a/drivers/gpu/drm/tegra/uapi.h b/drivers/gpu/drm/tegra/uapi.h new file mode 100644 index 000000000000..92ff1e44ff15 --- /dev/null +++ b/drivers/gpu/drm/tegra/uapi.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2020 NVIDIA Corporation */ + +#ifndef _TEGRA_DRM_UAPI_H +#define _TEGRA_DRM_UAPI_H + +#include <linux/dma-mapping.h> +#include <linux/idr.h> +#include <linux/kref.h> +#include <linux/xarray.h> + +#include <drm/drm.h> + +struct drm_file; +struct drm_device; + +struct tegra_drm_file { + /* Legacy UAPI state */ + struct idr legacy_contexts; + struct mutex lock; + + /* New UAPI state */ + struct xarray contexts; + struct xarray syncpoints; +}; + +struct tegra_drm_mapping { + struct kref ref; + + struct host1x_bo_mapping *map; + struct host1x_bo *bo; + + dma_addr_t iova; + dma_addr_t iova_end; +}; + +int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_channel_close(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_channel_unmap(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_syncpoint_allocate(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_syncpoint_free(struct drm_device *drm, void *data, + struct drm_file *file); +int tegra_drm_ioctl_syncpoint_wait(struct drm_device *drm, void *data, + struct drm_file *file); + +void tegra_drm_uapi_close_file(struct tegra_drm_file *file); +void tegra_drm_mapping_put(struct tegra_drm_mapping *mapping); + +#endif diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c index c9d55a9a3180..332c9b563d3f 100644 --- a/drivers/gpu/drm/tegra/vic.c +++ b/drivers/gpu/drm/tegra/vic.c @@ -5,12 +5,11 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/dma-mapping.h> #include <linux/host1x.h> #include <linux/iommu.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_device.h> -#include <linux/of_platform.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/reset.h> @@ -29,7 +28,6 @@ struct vic_config { struct vic { struct falcon falcon; - bool booted; void __iomem *regs; struct tegra_drm_client client; @@ -38,6 +36,8 @@ struct vic { struct clk *clk; struct reset_control *rst; + bool can_use_context; + /* Platform configuration */ const struct vic_config *config; }; @@ -52,88 +52,32 @@ static void vic_writel(struct vic *vic, u32 value, unsigned int offset) writel(value, vic->regs + offset); } -static int vic_runtime_resume(struct device *dev) -{ - struct vic *vic = dev_get_drvdata(dev); - int err; - - err = clk_prepare_enable(vic->clk); - if (err < 0) - return err; - - usleep_range(10, 20); - - err = reset_control_deassert(vic->rst); - if (err < 0) - goto disable; - - usleep_range(10, 20); - - return 0; - -disable: - clk_disable_unprepare(vic->clk); - return err; -} - -static int vic_runtime_suspend(struct device *dev) -{ - struct vic *vic = dev_get_drvdata(dev); - int err; - - err = reset_control_assert(vic->rst); - if (err < 0) - return err; - - usleep_range(2000, 4000); - - clk_disable_unprepare(vic->clk); - - vic->booted = false; - - return 0; -} - static int vic_boot(struct vic *vic) { -#ifdef CONFIG_IOMMU_API - struct iommu_fwspec *spec = dev_iommu_fwspec_get(vic->dev); -#endif - u32 fce_ucode_size, fce_bin_data_offset; + u32 fce_ucode_size, fce_bin_data_offset, stream_id; void *hdr; int err = 0; - if (vic->booted) - return 0; - -#ifdef CONFIG_IOMMU_API - if (vic->config->supports_sid && spec) { + if (vic->config->supports_sid && tegra_dev_iommu_get_stream_id(vic->dev, &stream_id)) { u32 value; value = TRANSCFG_ATT(1, TRANSCFG_SID_FALCON) | TRANSCFG_ATT(0, TRANSCFG_SID_HW); vic_writel(vic, value, VIC_TFBIF_TRANSCFG); - if (spec->num_ids > 0) { - value = spec->ids[0] & 0xffff; - - /* - * STREAMID0 is used for input/output buffers. - * Initialize it to SID_VIC in case context isolation - * is not enabled, and SID_VIC is used for both firmware - * and data buffers. - * - * If context isolation is enabled, it will be - * overridden by the SETSTREAMID opcode as part of - * each job. - */ - vic_writel(vic, value, VIC_THI_STREAMID0); - - /* STREAMID1 is used for firmware loading. */ - vic_writel(vic, value, VIC_THI_STREAMID1); - } + /* + * STREAMID0 is used for input/output buffers. Initialize it to SID_VIC in case + * context isolation is not enabled, and SID_VIC is used for both firmware and + * data buffers. + * + * If context isolation is enabled, it will be overridden by the SETSTREAMID + * opcode as part of each job. + */ + vic_writel(vic, stream_id, VIC_THI_STREAMID0); + + /* STREAMID1 is used for firmware loading. */ + vic_writel(vic, stream_id, VIC_THI_STREAMID1); } -#endif /* setup clockgating registers */ vic_writel(vic, CG_IDLE_CG_DLY_CNT(4) | @@ -168,8 +112,6 @@ static int vic_boot(struct vic *vic) return err; } - vic->booted = true; - return 0; } @@ -236,10 +178,15 @@ static int vic_exit(struct host1x_client *client) if (err < 0) return err; + pm_runtime_dont_use_autosuspend(client->dev); + pm_runtime_force_suspend(client->dev); + host1x_syncpt_put(client->syncpts[0]); host1x_channel_put(vic->channel); host1x_client_iommu_detach(client); + vic->channel = NULL; + if (client->group) { dma_unmap_single(vic->dev, vic->falcon.firmware.phys, vic->falcon.firmware.size, DMA_TO_DEVICE); @@ -264,28 +211,38 @@ static int vic_load_firmware(struct vic *vic) { struct host1x_client *client = &vic->client.base; struct tegra_drm *tegra = vic->client.drm; + static DEFINE_MUTEX(lock); + u32 fce_bin_data_offset; dma_addr_t iova; size_t size; void *virt; int err; - if (vic->falcon.firmware.virt) - return 0; + mutex_lock(&lock); + + if (vic->falcon.firmware.virt) { + err = 0; + goto unlock; + } err = falcon_read_firmware(&vic->falcon, vic->config->firmware); if (err < 0) - return err; + goto unlock; size = vic->falcon.firmware.size; if (!client->group) { virt = dma_alloc_coherent(vic->dev, size, &iova, GFP_KERNEL); - - err = dma_mapping_error(vic->dev, iova); - if (err < 0) - return err; + if (!virt) { + err = -ENOMEM; + goto unlock; + } } else { virt = tegra_drm_alloc(tegra, size, &iova); + if (IS_ERR(virt)) { + err = PTR_ERR(virt); + goto unlock; + } } vic->falcon.firmware.virt = virt; @@ -312,7 +269,28 @@ static int vic_load_firmware(struct vic *vic) vic->falcon.firmware.phys = phys; } - return 0; + /* + * Check if firmware is new enough to not require mapping firmware + * to data buffer domains. + */ + fce_bin_data_offset = *(u32 *)(virt + VIC_UCODE_FCE_DATA_OFFSET); + + if (!vic->config->supports_sid) { + vic->can_use_context = false; + } else if (fce_bin_data_offset != 0x0 && fce_bin_data_offset != 0xa5a5a5a5) { + /* + * Firmware will access FCE through STREAMID0, so context + * isolation cannot be used. + */ + vic->can_use_context = false; + dev_warn_once(vic->dev, "context isolation disabled due to old firmware\n"); + } else { + vic->can_use_context = true; + } + +unlock: + mutex_unlock(&lock); + return err; cleanup: if (!client->group) @@ -320,53 +298,101 @@ cleanup: else tegra_drm_free(tegra, size, virt, iova); + mutex_unlock(&lock); return err; } -static int vic_open_channel(struct tegra_drm_client *client, - struct tegra_drm_context *context) + +static int __maybe_unused vic_runtime_resume(struct device *dev) { - struct vic *vic = to_vic(client); + struct vic *vic = dev_get_drvdata(dev); int err; - err = pm_runtime_resume_and_get(vic->dev); + err = clk_prepare_enable(vic->clk); if (err < 0) return err; + usleep_range(10, 20); + + err = reset_control_deassert(vic->rst); + if (err < 0) + goto disable; + + usleep_range(10, 20); + err = vic_load_firmware(vic); if (err < 0) - goto rpm_put; + goto assert; err = vic_boot(vic); if (err < 0) - goto rpm_put; - - context->channel = host1x_channel_get(vic->channel); - if (!context->channel) { - err = -ENOMEM; - goto rpm_put; - } + goto assert; return 0; -rpm_put: - pm_runtime_put(vic->dev); +assert: + reset_control_assert(vic->rst); +disable: + clk_disable_unprepare(vic->clk); return err; } -static void vic_close_channel(struct tegra_drm_context *context) +static int __maybe_unused vic_runtime_suspend(struct device *dev) +{ + struct vic *vic = dev_get_drvdata(dev); + int err; + + host1x_channel_stop(vic->channel); + + err = reset_control_assert(vic->rst); + if (err < 0) + return err; + + usleep_range(2000, 4000); + + clk_disable_unprepare(vic->clk); + + return 0; +} + +static int vic_open_channel(struct tegra_drm_client *client, + struct tegra_drm_context *context) { - struct vic *vic = to_vic(context->client); + struct vic *vic = to_vic(client); + + context->channel = host1x_channel_get(vic->channel); + if (!context->channel) + return -ENOMEM; + return 0; +} + +static void vic_close_channel(struct tegra_drm_context *context) +{ host1x_channel_put(context->channel); +} + +static int vic_can_use_memory_ctx(struct tegra_drm_client *client, bool *supported) +{ + struct vic *vic = to_vic(client); + int err; + + /* This doesn't access HW so it's safe to call without powering up. */ + err = vic_load_firmware(vic); + if (err < 0) + return err; + + *supported = vic->can_use_context; - pm_runtime_put(vic->dev); + return 0; } static const struct tegra_drm_client_ops vic_ops = { .open_channel = vic_open_channel, .close_channel = vic_close_channel, .submit = tegra_drm_submit, + .get_streamid_offset = tegra_drm_get_streamid_offset_thi, + .can_use_memory_ctx = vic_can_use_memory_ctx, }; #define NVIDIA_TEGRA_124_VIC_FIRMWARE "nvidia/tegra124/vic03_ucode.bin" @@ -401,11 +427,20 @@ static const struct vic_config vic_t194_config = { .supports_sid = true, }; +#define NVIDIA_TEGRA_234_VIC_FIRMWARE "nvidia/tegra234/vic.bin" + +static const struct vic_config vic_t234_config = { + .firmware = NVIDIA_TEGRA_234_VIC_FIRMWARE, + .version = 0x23, + .supports_sid = true, +}; + static const struct of_device_id tegra_vic_of_match[] = { { .compatible = "nvidia,tegra124-vic", .data = &vic_t124_config }, { .compatible = "nvidia,tegra210-vic", .data = &vic_t210_config }, { .compatible = "nvidia,tegra186-vic", .data = &vic_t186_config }, { .compatible = "nvidia,tegra194-vic", .data = &vic_t194_config }, + { .compatible = "nvidia,tegra234-vic", .data = &vic_t234_config }, { }, }; MODULE_DEVICE_TABLE(of, tegra_vic_of_match); @@ -414,7 +449,6 @@ static int vic_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct host1x_syncpt **syncpts; - struct resource *regs; struct vic *vic; int err; @@ -435,13 +469,7 @@ static int vic_probe(struct platform_device *pdev) if (!syncpts) return -ENOMEM; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!regs) { - dev_err(&pdev->dev, "failed to get registers\n"); - return -ENXIO; - } - - vic->regs = devm_ioremap_resource(dev, regs); + vic->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(vic->regs)) return PTR_ERR(vic->regs); @@ -451,6 +479,12 @@ static int vic_probe(struct platform_device *pdev) return PTR_ERR(vic->clk); } + err = clk_set_rate(vic->clk, ULONG_MAX); + if (err < 0) { + dev_err(&pdev->dev, "failed to set clock rate\n"); + return err; + } + if (!dev->pm_domain) { vic->rst = devm_reset_control_get(dev, "vic"); if (IS_ERR(vic->rst)) { @@ -486,47 +520,30 @@ static int vic_probe(struct platform_device *pdev) goto exit_falcon; } - pm_runtime_enable(&pdev->dev); - if (!pm_runtime_enabled(&pdev->dev)) { - err = vic_runtime_resume(&pdev->dev); - if (err < 0) - goto unregister_client; - } + pm_runtime_enable(dev); + pm_runtime_use_autosuspend(dev); + pm_runtime_set_autosuspend_delay(dev, 500); return 0; -unregister_client: - host1x_client_unregister(&vic->client.base); exit_falcon: falcon_exit(&vic->falcon); return err; } -static int vic_remove(struct platform_device *pdev) +static void vic_remove(struct platform_device *pdev) { struct vic *vic = platform_get_drvdata(pdev); - int err; - - err = host1x_client_unregister(&vic->client.base); - if (err < 0) { - dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", - err); - return err; - } - - if (pm_runtime_enabled(&pdev->dev)) - pm_runtime_disable(&pdev->dev); - else - vic_runtime_suspend(&pdev->dev); + pm_runtime_disable(&pdev->dev); + host1x_client_unregister(&vic->client.base); falcon_exit(&vic->falcon); - - return 0; } static const struct dev_pm_ops vic_pm_ops = { - SET_RUNTIME_PM_OPS(vic_runtime_suspend, vic_runtime_resume, NULL) + RUNTIME_PM_OPS(vic_runtime_suspend, vic_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) }; struct platform_driver tegra_vic_driver = { @@ -551,3 +568,6 @@ MODULE_FIRMWARE(NVIDIA_TEGRA_186_VIC_FIRMWARE); #if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) MODULE_FIRMWARE(NVIDIA_TEGRA_194_VIC_FIRMWARE); #endif +#if IS_ENABLED(CONFIG_ARCH_TEGRA_234_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_234_VIC_FIRMWARE); +#endif |