diff options
| author | Dave Airlie <airlied@redhat.com> | 2018-12-06 08:09:33 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2018-12-06 09:17:51 +1000 |
| commit | 467e8a516dcf922d1ea343cebb0e751f81f0dca3 (patch) | |
| tree | c22b6d971e922223286a4a181d6701c7d32e523d /drivers/gpu | |
| parent | 818182dd1097fdc492aaef9b08755ea13274352d (diff) | |
| parent | 4377d4e0d3d511986033ba7b4182d5a80b7f9ea2 (diff) | |
Merge tag 'drm-intel-next-2018-12-04' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
Final drm/i915 changes for v4.21:
- ICL DSI video mode enabling (Madhav, Vandita, Jani, Imre)
- eDP sink count fix (José)
- PSR fixes (José)
- DRM DP helper and i915 DSC enabling (Manasi, Gaurav, Anusha)
- DP FEC enabling (Anusha)
- SKL+ watermark/ddb programming improvements (Ville)
- Pixel format fixes (Ville)
- Selftest updates (Chris, Tvrtko)
- GT and engine workaround improvements (Tvrtko)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/87va496uoe.fsf@intel.com
Diffstat (limited to 'drivers/gpu')
56 files changed, 4859 insertions, 1965 deletions
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 1fafc2f8e8f9..e490fe2687db 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -32,7 +32,7 @@ drm-$(CONFIG_AGP) += drm_agpsupport.o drm-$(CONFIG_DEBUG_FS) += drm_debugfs.o drm_debugfs_crc.o drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o -drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_probe_helper.o \ +drm_kms_helper-y := drm_crtc_helper.o drm_dp_helper.o drm_dsc.o drm_probe_helper.o \ drm_plane_helper.o drm_dp_mst_topology.o drm_atomic_helper.o \ drm_kms_helper_common.o drm_dp_dual_mode_helper.o \ drm_simple_kms_helper.o drm_modeset_helper.o \ diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 6d483487f2b4..2d6c491a0542 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -1428,17 +1428,19 @@ u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) } EXPORT_SYMBOL(drm_dp_dsc_sink_line_buf_depth); -u8 drm_dp_dsc_sink_max_color_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) +int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], + u8 dsc_bpc[3]) { + int num_bpc = 0; u8 color_depth = dsc_dpcd[DP_DSC_DEC_COLOR_DEPTH_CAP - DP_DSC_SUPPORT]; if (color_depth & DP_DSC_12_BPC) - return 12; + dsc_bpc[num_bpc++] = 12; if (color_depth & DP_DSC_10_BPC) - return 10; + dsc_bpc[num_bpc++] = 10; if (color_depth & DP_DSC_8_BPC) - return 8; + dsc_bpc[num_bpc++] = 8; - return 0; + return num_bpc; } -EXPORT_SYMBOL(drm_dp_dsc_sink_max_color_depth); +EXPORT_SYMBOL(drm_dp_dsc_sink_supported_input_bpcs); diff --git a/drivers/gpu/drm/drm_dsc.c b/drivers/gpu/drm/drm_dsc.c new file mode 100644 index 000000000000..bc2b23adb072 --- /dev/null +++ b/drivers/gpu/drm/drm_dsc.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2018 Intel Corp + * + * Author: + * Manasi Navare <manasi.d.navare@intel.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/byteorder/generic.h> +#include <drm/drm_dp_helper.h> +#include <drm/drm_dsc.h> + +/** + * DOC: dsc helpers + * + * These functions contain some common logic and helpers to deal with VESA + * Display Stream Compression standard required for DSC on Display Port/eDP or + * MIPI display interfaces. + */ + +/** + * drm_dsc_dp_pps_header_init() - Initializes the PPS Header + * for DisplayPort as per the DP 1.4 spec. + * @pps_sdp: Secondary data packet for DSC Picture Parameter Set + */ +void drm_dsc_dp_pps_header_init(struct drm_dsc_pps_infoframe *pps_sdp) +{ + memset(&pps_sdp->pps_header, 0, sizeof(pps_sdp->pps_header)); + + pps_sdp->pps_header.HB1 = DP_SDP_PPS; + pps_sdp->pps_header.HB2 = DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1; +} +EXPORT_SYMBOL(drm_dsc_dp_pps_header_init); + +/** + * drm_dsc_pps_infoframe_pack() - Populates the DSC PPS infoframe + * using the DSC configuration parameters in the order expected + * by the DSC Display Sink device. For the DSC, the sink device + * expects the PPS payload in the big endian format for the fields + * that span more than 1 byte. + * + * @pps_sdp: + * Secondary data packet for DSC Picture Parameter Set + * @dsc_cfg: + * DSC Configuration data filled by driver + */ +void drm_dsc_pps_infoframe_pack(struct drm_dsc_pps_infoframe *pps_sdp, + const struct drm_dsc_config *dsc_cfg) +{ + int i; + + /* Protect against someone accidently changing struct size */ + BUILD_BUG_ON(sizeof(pps_sdp->pps_payload) != + DP_SDP_PPS_HEADER_PAYLOAD_BYTES_MINUS_1 + 1); + + memset(&pps_sdp->pps_payload, 0, sizeof(pps_sdp->pps_payload)); + + /* PPS 0 */ + pps_sdp->pps_payload.dsc_version = + dsc_cfg->dsc_version_minor | + dsc_cfg->dsc_version_major << DSC_PPS_VERSION_MAJOR_SHIFT; + + /* PPS 1, 2 is 0 */ + + /* PPS 3 */ + pps_sdp->pps_payload.pps_3 = + dsc_cfg->line_buf_depth | + dsc_cfg->bits_per_component << DSC_PPS_BPC_SHIFT; + + /* PPS 4 */ + pps_sdp->pps_payload.pps_4 = + ((dsc_cfg->bits_per_pixel & DSC_PPS_BPP_HIGH_MASK) >> + DSC_PPS_MSB_SHIFT) | + dsc_cfg->vbr_enable << DSC_PPS_VBR_EN_SHIFT | + dsc_cfg->enable422 << DSC_PPS_SIMPLE422_SHIFT | + dsc_cfg->convert_rgb << DSC_PPS_CONVERT_RGB_SHIFT | + dsc_cfg->block_pred_enable << DSC_PPS_BLOCK_PRED_EN_SHIFT; + + /* PPS 5 */ + pps_sdp->pps_payload.bits_per_pixel_low = + (dsc_cfg->bits_per_pixel & DSC_PPS_LSB_MASK); + + /* + * The DSC panel expects the PPS packet to have big endian format + * for data spanning 2 bytes. Use a macro cpu_to_be16() to convert + * to big endian format. If format is little endian, it will swap + * bytes to convert to Big endian else keep it unchanged. + */ + + /* PPS 6, 7 */ + pps_sdp->pps_payload.pic_height = cpu_to_be16(dsc_cfg->pic_height); + + /* PPS 8, 9 */ + pps_sdp->pps_payload.pic_width = cpu_to_be16(dsc_cfg->pic_width); + + /* PPS 10, 11 */ + pps_sdp->pps_payload.slice_height = cpu_to_be16(dsc_cfg->slice_height); + + /* PPS 12, 13 */ + pps_sdp->pps_payload.slice_width = cpu_to_be16(dsc_cfg->slice_width); + + /* PPS 14, 15 */ + pps_sdp->pps_payload.chunk_size = cpu_to_be16(dsc_cfg->slice_chunk_size); + + /* PPS 16 */ + pps_sdp->pps_payload.initial_xmit_delay_high = + ((dsc_cfg->initial_xmit_delay & + DSC_PPS_INIT_XMIT_DELAY_HIGH_MASK) >> + DSC_PPS_MSB_SHIFT); + + /* PPS 17 */ + pps_sdp->pps_payload.initial_xmit_delay_low = + (dsc_cfg->initial_xmit_delay & DSC_PPS_LSB_MASK); + + /* PPS 18, 19 */ + pps_sdp->pps_payload.initial_dec_delay = + cpu_to_be16(dsc_cfg->initial_dec_delay); + + /* PPS 20 is 0 */ + + /* PPS 21 */ + pps_sdp->pps_payload.initial_scale_value = + dsc_cfg->initial_scale_value; + + /* PPS 22, 23 */ + pps_sdp->pps_payload.scale_increment_interval = + cpu_to_be16(dsc_cfg->scale_increment_interval); + + /* PPS 24 */ + pps_sdp->pps_payload.scale_decrement_interval_high = + ((dsc_cfg->scale_decrement_interval & + DSC_PPS_SCALE_DEC_INT_HIGH_MASK) >> + DSC_PPS_MSB_SHIFT); + + /* PPS 25 */ + pps_sdp->pps_payload.scale_decrement_interval_low = + (dsc_cfg->scale_decrement_interval & DSC_PPS_LSB_MASK); + + /* PPS 26[7:0], PPS 27[7:5] RESERVED */ + + /* PPS 27 */ + pps_sdp->pps_payload.first_line_bpg_offset = + dsc_cfg->first_line_bpg_offset; + + /* PPS 28, 29 */ + pps_sdp->pps_payload.nfl_bpg_offset = + cpu_to_be16(dsc_cfg->nfl_bpg_offset); + + /* PPS 30, 31 */ + pps_sdp->pps_payload.slice_bpg_offset = + cpu_to_be16(dsc_cfg->slice_bpg_offset); + + /* PPS 32, 33 */ + pps_sdp->pps_payload.initial_offset = + cpu_to_be16(dsc_cfg->initial_offset); + + /* PPS 34, 35 */ + pps_sdp->pps_payload.final_offset = cpu_to_be16(dsc_cfg->final_offset); + + /* PPS 36 */ + pps_sdp->pps_payload.flatness_min_qp = dsc_cfg->flatness_min_qp; + + /* PPS 37 */ + pps_sdp->pps_payload.flatness_max_qp = dsc_cfg->flatness_max_qp; + + /* PPS 38, 39 */ + pps_sdp->pps_payload.rc_model_size = + cpu_to_be16(DSC_RC_MODEL_SIZE_CONST); + + /* PPS 40 */ + pps_sdp->pps_payload.rc_edge_factor = DSC_RC_EDGE_FACTOR_CONST; + + /* PPS 41 */ + pps_sdp->pps_payload.rc_quant_incr_limit0 = + dsc_cfg->rc_quant_incr_limit0; + + /* PPS 42 */ + pps_sdp->pps_payload.rc_quant_incr_limit1 = + dsc_cfg->rc_quant_incr_limit1; + + /* PPS 43 */ + pps_sdp->pps_payload.rc_tgt_offset = DSC_RC_TGT_OFFSET_LO_CONST | + DSC_RC_TGT_OFFSET_HI_CONST << DSC_PPS_RC_TGT_OFFSET_HI_SHIFT; + + /* PPS 44 - 57 */ + for (i = 0; i < DSC_NUM_BUF_RANGES - 1; i++) + pps_sdp->pps_payload.rc_buf_thresh[i] = + dsc_cfg->rc_buf_thresh[i]; + + /* PPS 58 - 87 */ + /* + * For DSC sink programming the RC Range parameter fields + * are as follows: Min_qp[15:11], max_qp[10:6], offset[5:0] + */ + for (i = 0; i < DSC_NUM_BUF_RANGES; i++) { + pps_sdp->pps_payload.rc_range_parameters[i] = + ((dsc_cfg->rc_range_params[i].range_min_qp << + DSC_PPS_RC_RANGE_MINQP_SHIFT) | + (dsc_cfg->rc_range_params[i].range_max_qp << + DSC_PPS_RC_RANGE_MAXQP_SHIFT) | + (dsc_cfg->rc_range_params[i].range_bpg_offset)); + pps_sdp->pps_payload.rc_range_parameters[i] = + cpu_to_be16(pps_sdp->pps_payload.rc_range_parameters[i]); + } + + /* PPS 88 */ + pps_sdp->pps_payload.native_422_420 = dsc_cfg->native_422 | + dsc_cfg->native_420 << DSC_PPS_NATIVE_420_SHIFT; + + /* PPS 89 */ + pps_sdp->pps_payload.second_line_bpg_offset = + dsc_cfg->second_line_bpg_offset; + + /* PPS 90, 91 */ + pps_sdp->pps_payload.nsl_bpg_offset = + cpu_to_be16(dsc_cfg->nsl_bpg_offset); + + /* PPS 92, 93 */ + pps_sdp->pps_payload.second_line_offset_adj = + cpu_to_be16(dsc_cfg->second_line_offset_adj); + + /* PPS 94 - 127 are O */ +} +EXPORT_SYMBOL(drm_dsc_pps_infoframe_pack); diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 0ff878c994e2..19b5fe5016bf 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -157,14 +157,17 @@ i915-y += dvo_ch7017.o \ intel_sdvo.o \ intel_tv.o \ vlv_dsi.o \ - vlv_dsi_pll.o + vlv_dsi_pll.o \ + intel_vdsc.o # Post-mortem debug and GPU hang state capture i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o i915-$(CONFIG_DRM_I915_SELFTEST) += \ selftests/i915_random.o \ selftests/i915_selftest.o \ - selftests/igt_flush_test.o + selftests/igt_flush_test.o \ + selftests/igt_reset.o \ + selftests/igt_spinner.o # virtual gpu code i915-y += i915_vgpu.o diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 7f455bca528e..38dcee1ca062 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -943,30 +943,30 @@ static int i915_gem_fence_regs_info(struct seq_file *m, void *data) static ssize_t gpu_state_read(struct file *file, char __user *ubuf, size_t count, loff_t *pos) { - struct i915_gpu_state *error = file->private_data; - struct drm_i915_error_state_buf str; + struct i915_gpu_state *error; ssize_t ret; - loff_t tmp; + void *buf; + error = file->private_data; if (!error) return 0; - ret = i915_error_state_buf_init(&str, error->i915, count, *pos); - if (ret) - return ret; + /* Bounce buffer required because of kernfs __user API convenience. */ + buf = kmalloc(count, GFP_KERNEL); + if (!buf) + return -ENOMEM; - ret = i915_error_state_to_str(&str, error); - if (ret) + ret = i915_gpu_state_copy_to_buffer(error, buf, *pos, count); + if (ret <= 0) goto out; - tmp = 0; - ret = simple_read_from_buffer(ubuf, count, &tmp, str.buf, str.bytes); - if (ret < 0) - goto out; + if (!copy_to_user(ubuf, buf, ret)) + *pos += ret; + else + ret = -EFAULT; - *pos = str.start + ret; out: - i915_error_state_buf_release(&str); + kfree(buf); return ret; } @@ -3375,13 +3375,15 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) static int i915_wa_registers(struct seq_file *m, void *unused) { - struct i915_workarounds *wa = &node_to_i915(m->private)->workarounds; - int i; + struct drm_i915_private *i915 = node_to_i915(m->private); + const struct i915_wa_list *wal = &i915->engine[RCS]->ctx_wa_list; + struct i915_wa *wa; + unsigned int i; - seq_printf(m, "Workarounds applied: %d\n", wa->count); - for (i = 0; i < wa->count; ++i) + seq_printf(m, "Workarounds applied: %u\n", wal->count); + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n", - wa->reg[i].addr, wa->reg[i].value, wa->reg[i].mask); + i915_mmio_reg_offset(wa->reg), wa->val, wa->mask); return 0; } @@ -3441,31 +3443,32 @@ static int i915_ddb_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); struct drm_device *dev = &dev_priv->drm; - struct skl_ddb_allocation *ddb; struct skl_ddb_entry *entry; - enum pipe pipe; - int plane; + struct intel_crtc *crtc; if (INTEL_GEN(dev_priv) < 9) return -ENODEV; drm_modeset_lock_all(dev); - ddb = &dev_priv->wm.skl_hw.ddb; - seq_printf(m, "%-15s%8s%8s%8s\n", "", "Start", "End", "Size"); - for_each_pipe(dev_priv, pipe) { + for_each_intel_crtc(&dev_priv->drm, crtc) { + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + enum pipe pipe = crtc->pipe; + enum plane_id plane_id; + seq_printf(m, "Pipe %c\n", pipe_name(pipe)); - for_each_universal_plane(dev_priv, pipe, plane) { - entry = &ddb->plane[pipe][plane]; - seq_printf(m, " Plane%-8d%8u%8u%8u\n", plane + 1, + for_each_plane_id_on_crtc(crtc, plane_id) { + entry = &crtc_state->wm.skl.plane_ddb_y[plane_id]; + seq_printf(m, " Plane%-8d%8u%8u%8u\n", plane_id + 1, entry->start, entry->end, skl_ddb_entry_size(entry)); } - entry = &ddb->plane[pipe][PLANE_CURSOR]; + entry = &crtc_state->wm.skl.plane_ddb_y[PLANE_CURSOR]; seq_printf(m, " %-13s%8u%8u%8u\n", "Cursor", entry->start, entry->end, skl_ddb_entry_size(entry)); } @@ -4592,6 +4595,13 @@ static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data) struct drm_i915_private *dev_priv = m->private; struct i915_hotplug *hotplug = &dev_priv->hotplug; + /* Synchronize with everything first in case there's been an HPD + * storm, but we haven't finished handling it in the kernel yet + */ + synchronize_irq(dev_priv->drm.irq); + flush_work(&dev_priv->hotplug.dig_port_work); + flush_work(&dev_priv->hotplug.hotplug_work); + seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold); seq_printf(m, "Detected: %s\n", yesno(delayed_work_pending(&hotplug->reenable_work))); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index b1d23c73c147..b310a897a4ad 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -53,6 +53,7 @@ #include "i915_vgpu.h" #include "intel_drv.h" #include "intel_uc.h" +#include "intel_workarounds.h" static struct drm_driver driver; @@ -287,7 +288,7 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv) * Use PCH_NOP (PCH but no South Display) for PCH platforms without * display. */ - if (pch && INTEL_INFO(dev_priv)->num_pipes == 0) { + if (pch && !HAS_DISPLAY(dev_priv)) { DRM_DEBUG_KMS("Display disabled, reverting to NOP PCH\n"); dev_priv->pch_type = PCH_NOP; dev_priv->pch_id = 0; @@ -645,7 +646,7 @@ static int i915_load_modeset_init(struct drm_device *dev) if (i915_inject_load_failure()) return -ENODEV; - if (INTEL_INFO(dev_priv)->num_pipes) { + if (HAS_DISPLAY(dev_priv)) { ret = drm_vblank_init(&dev_priv->drm, INTEL_INFO(dev_priv)->num_pipes); if (ret) @@ -696,7 +697,7 @@ static int i915_load_modeset_init(struct drm_device *dev) intel_overlay_setup(dev_priv); - if (INTEL_INFO(dev_priv)->num_pipes == 0) + if (!HAS_DISPLAY(dev_priv)) return 0; ret = intel_fbdev_init(dev); @@ -868,6 +869,7 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) pre |= IS_HSW_EARLY_SDV(dev_priv); pre |= IS_SKL_REVID(dev_priv, 0, SKL_REVID_F0); pre |= IS_BXT_REVID(dev_priv, 0, BXT_REVID_B_LAST); + pre |= IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0); if (pre) { DRM_ERROR("This is a pre-production stepping. " @@ -1383,6 +1385,20 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) } } + if (HAS_EXECLISTS(dev_priv)) { + /* + * Older GVT emulation depends upon intercepting CSB mmio, + * which we no longer use, preferring to use the HWSP cache + * instead. + */ + if (intel_vgpu_active(dev_priv) && + !intel_vgpu_has_hwsp_emulation(dev_priv)) { + i915_report_error(dev_priv, + "old vGPU host found, support for HWSP emulation required\n"); + return -ENXIO; + } + } + intel_sanitize_options(dev_priv); i915_perf_init(dev_priv); @@ -1452,6 +1468,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) intel_uncore_sanitize(dev_priv); + intel_gt_init_workarounds(dev_priv); i915_gem_load_init_fences(dev_priv); /* On the 945G/GM, the chipset reports the MSI capability on the @@ -1551,7 +1568,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) } else DRM_ERROR("Failed to register driver for userspace access!\n"); - if (INTEL_INFO(dev_priv)->num_pipes) { + if (HAS_DISPLAY(dev_priv)) { /* Must be done after probing outputs */ intel_opregion_register(dev_priv); acpi_video_register(); @@ -1575,7 +1592,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) * We need to coordinate the hotplugs with the asynchronous fbdev * configuration, for which we use the fbdev->async_cookie. */ - if (INTEL_INFO(dev_priv)->num_pipes) + if (HAS_DISPLAY(dev_priv)) drm_kms_helper_poll_init(dev); intel_power_domains_enable(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 4064e49dbf70..b1c31967194b 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -53,6 +53,7 @@ #include <drm/drm_auth.h> #include <drm/drm_cache.h> #include <drm/drm_util.h> +#include <drm/drm_dsc.h> #include "i915_fixed.h" #include "i915_params.h" @@ -68,6 +69,7 @@ #include "intel_ringbuffer.h" #include "intel_uncore.h" #include "intel_wopcm.h" +#include "intel_workarounds.h" #include "intel_uc.h" #include "i915_gem.h" @@ -88,8 +90,8 @@ #define DRIVER_NAME "i915" #define DRIVER_DESC "Intel Graphics" -#define DRIVER_DATE "20181122" -#define DRIVER_TIMESTAMP 1542898187 +#define DRIVER_DATE "20181204" +#define DRIVER_TIMESTAMP 1543944377 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and * WARN_ON()) for hw state sanity checks to check for unexpected conditions @@ -494,6 +496,7 @@ struct i915_psr { bool sink_support; bool prepared, enabled; struct intel_dp *dp; + enum pipe pipe; bool active; struct work_struct work; unsigned busy_frontbuffer_bits; @@ -504,6 +507,8 @@ struct i915_psr { u8 sink_sync_latency; ktime_t last_entry_attempt; ktime_t last_exit; + bool sink_not_reliable; + bool irq_aux_error; }; enum intel_pch { @@ -1093,9 +1098,6 @@ static inline bool skl_ddb_entry_equal(const struct skl_ddb_entry *e1, } struct skl_ddb_allocation { - /* packed/y */ - struct skl_ddb_entry plane[I915_MAX_PIPES][I915_MAX_PLANES]; - struct skl_ddb_entry uv_plane[I915_MAX_PIPES][I915_MAX_PLANES]; u8 enabled_slices; /* GEN11 has configurable 2 slices */ }; @@ -1188,20 +1190,6 @@ struct i915_frontbuffer_tracking { unsigned flip_bits; }; -struct i915_wa_reg { - u32 addr; - u32 value; - /* bitmask representing WA bits */ - u32 mask; -}; - -#define I915_MAX_WA_REGS 16 - -struct i915_workarounds { - struct i915_wa_reg reg[I915_MAX_WA_REGS]; - u32 count; -}; - struct i915_virtual_gpu { bool active; u32 caps; @@ -1651,7 +1639,7 @@ struct drm_i915_private { int dpio_phy_iosf_port[I915_NUM_PHYS_VLV]; - struct i915_workarounds workarounds; + struct i915_wa_list gt_wa_list; struct i915_frontbuffer_tracking fb_tracking; @@ -1995,6 +1983,8 @@ struct drm_i915_private { struct delayed_work idle_work; ktime_t last_init_time; + + struct i915_vma *scratch; } gt; /* perform PHY state sanity checks? */ @@ -2448,9 +2438,9 @@ intel_info(const struct drm_i915_private *dev_priv) ((sizes) & ~(dev_priv)->info.page_sizes) == 0; \ }) -#define HAS_OVERLAY(dev_priv) ((dev_priv)->info.has_overlay) +#define HAS_OVERLAY(dev_priv) ((dev_priv)->info.display.has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev_priv) \ - ((dev_priv)->info.overlay_needs_physical) + ((dev_priv)->info.display.overlay_needs_physical) /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv)) @@ -2471,31 +2461,31 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_128_BYTE_Y_TILING(dev_priv) (!IS_GEN2(dev_priv) && \ !(IS_I915G(dev_priv) || \ IS_I915GM(dev_priv))) -#define SUPPORTS_TV(dev_priv) ((dev_priv)->info.supports_tv) -#define I915_HAS_HOTPLUG(dev_priv) ((dev_priv)->info.has_hotplug) +#define SUPPORTS_TV(dev_priv) ((dev_priv)->info.display.supports_tv) +#define I915_HAS_HOTPLUG(dev_priv) ((dev_priv)->info.display.has_hotplug) #define HAS_FW_BLC(dev_priv) (INTEL_GEN(dev_priv) > 2) -#define HAS_FBC(dev_priv) ((dev_priv)->info.has_fbc) +#define HAS_FBC(dev_priv) ((dev_priv)->info.display.has_fbc) #define HAS_CUR_FBC(dev_priv) (!HAS_GMCH_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 7) #define HAS_IPS(dev_priv) (IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv)) -#define HAS_DP_MST(dev_priv) ((dev_priv)->info.has_dp_mst) +#define HAS_DP_MST(dev_priv) ((dev_priv)->info.display.has_dp_mst) -#define HAS_DDI(dev_priv) ((dev_priv)->info.has_ddi) +#define HAS_DDI(dev_priv) ((dev_priv)->info.display.has_ddi) #define HAS_FPGA_DBG_UNCLAIMED(dev_priv) ((dev_priv)->info.has_fpga_dbg) -#define HAS_PSR(dev_priv) ((dev_priv)->info.has_psr) +#define HAS_PSR(dev_priv) ((dev_priv)->info.display.has_psr) #define HAS_RC6(dev_priv) ((dev_priv)->info.has_rc6) #define HAS_RC6p(dev_priv) ((dev_priv)->info.has_rc6p) #define HAS_RC6pp(dev_priv) (false) /* HW was never validated */ -#define HAS_CSR(dev_priv) ((dev_priv)->info.has_csr) +#define HAS_CSR(dev_priv) ((dev_priv)->info.display.has_csr) #define HAS_RUNTIME_PM(dev_priv) ((dev_priv)->info.has_runtime_pm) #define HAS_64BIT_RELOC(dev_priv) ((dev_priv)->info.has_64bit_reloc) -#define HAS_IPC(dev_priv) ((dev_priv)->info.has_ipc) +#define HAS_IPC(dev_priv) ((dev_priv)->info.display.has_ipc) /* * For now, anything with a GuC requires uCode loading, and then supports @@ -2556,7 +2546,7 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_PCH_NOP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_NOP) #define HAS_PCH_SPLIT(dev_priv) (INTEL_PCH_TYPE(dev_priv) != PCH_NONE) -#define HAS_GMCH_DISPLAY(dev_priv) ((dev_priv)->info.has_gmch_display) +#define HAS_GMCH_DISPLAY(dev_priv) ((dev_priv)->info.display.has_gmch_display) #define HAS_LSPCON(dev_priv) (INTEL_GEN(dev_priv) >= 9) @@ -2568,6 +2558,8 @@ intel_info(const struct drm_i915_private *dev_priv) #define GT_FREQUENCY_MULTIPLIER 50 #define GEN9_FREQ_SCALER 3 +#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->num_pipes > 0) + #include "i915_trace.h" static inline bool intel_vtd_active(void) @@ -3340,6 +3332,9 @@ extern void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive); extern bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable); +void intel_dsc_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state); +void intel_dsc_disable(const struct intel_crtc_state *crtc_state); int i915_reg_read_ioctl(struct drm_device *dev, void *data, struct drm_file *file); @@ -3720,4 +3715,9 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) return I915_HWS_CSB_WRITE_INDEX; } +static inline u32 i915_scratch_offset(const struct drm_i915_private *i915) +{ + return i915_ggtt_offset(i915->gt.scratch); +} + #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c55b1f75c980..d36a9755ad91 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -3309,16 +3309,6 @@ void i915_gem_reset_finish(struct drm_i915_private *dev_priv) static void nop_submit_request(struct i915_request *request) { - GEM_TRACE("%s fence %llx:%d -> -EIO\n", - request->engine->name, - request->fence.context, request->fence.seqno); - dma_fence_set_error(&request->fence, -EIO); - - i915_request_submit(request); -} - -static void nop_complete_submit_request(struct i915_request *request) -{ unsigned long flags; GEM_TRACE("%s fence %llx:%d -> -EIO\n", @@ -3354,57 +3344,33 @@ void i915_gem_set_wedged(struct drm_i915_private *i915) * rolling the global seqno forward (since this would complete requests * for which we haven't set the fence error to EIO yet). */ - for_each_engine(engine, i915, id) { + for_each_engine(engine, i915, id) i915_gem_reset_prepare_engine(engine); - engine->submit_request = nop_submit_request; - engine->schedule = NULL; - } - i915->caps.scheduler = 0; - /* Even if the GPU reset fails, it should still stop the engines */ if (INTEL_GEN(i915) >= 5) intel_gpu_reset(i915, ALL_ENGINES); - /* - * Make sure no one is running the old callback before we proceed with - * cancelling requests and resetting the completion tracking. Otherwise - * we might submit a request to the hardware which never completes. - */ - synchronize_rcu(); - for_each_engine(engine, i915, id) { - /* Mark all executing requests as skipped */ - engine->cancel_requests(engine); - - /* - * Only once we've force-cancelled all in-flight requests can we - * start to complete all requests. - */ - engine->submit_request = nop_complete_submit_request; + engine->submit_request = nop_submit_request; + engine->schedule = NULL; } + i915->caps.scheduler = 0; /* * Make sure no request can slip through without getting completed by * either this call here to intel_engine_init_global_seqno, or the one - * in nop_complete_submit_request. + * in nop_submit_request. */ synchronize_rcu(); - for_each_engine(engine, i915, id) { - unsigned long flags; - - /* - * Mark all pending requests as complete so that any concurrent - * (lockless) lookup doesn't try and wait upon the request as we - * reset it. - */ - spin_lock_irqsave(&engine->timeline.lock, flags); - intel_engine_init_global_seqno(engine, - intel_engine_last_submit(engine)); - spin_unlock_irqrestore(&engine->timeline.lock, flags); + /* Mark all executing requests as skipped */ + for_each_engine(engine, i915, id) + engine->cancel_requests(engine); + for_each_engine(engine, i915, id) { i915_gem_reset_finish_engine(engine); + intel_engine_wakeup(engine); } out: @@ -5334,7 +5300,10 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) I915_WRITE(MI_PREDICATE_RESULT_2, IS_HSW_GT3(dev_priv) ? LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED); - intel_gt_workarounds_apply(dev_priv); + /* Apply the GT workarounds... */ + intel_gt_apply_workarounds(dev_priv); + /* ...and determine whether they are sticking. */ + intel_gt_verify_workarounds(dev_priv, "init"); i915_gem_init_swizzling(dev_priv); @@ -5529,6 +5498,44 @@ err_active: goto out_ctx; } +static int +i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int ret; + + obj = i915_gem_object_create_stolen(i915, size); + if (!obj) + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) { + DRM_ERROR("Failed to allocate scratch page\n"); + return PTR_ERR(obj); + } + + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unref; + } + + ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); + if (ret) + goto err_unref; + + i915->gt.scratch = vma; + return 0; + +err_unref: + i915_gem_object_put(obj); + return ret; +} + +static void i915_gem_fini_scratch(struct drm_i915_private *i915) +{ + i915_vma_unpin_and_release(&i915->gt.scratch, 0); +} + int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; @@ -5575,12 +5582,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv) goto err_unlock; } - ret = i915_gem_contexts_init(dev_priv); + ret = i915_gem_init_scratch(dev_priv, + IS_GEN2(dev_priv) ? SZ_256K : PAGE_SIZE); if (ret) { GEM_BUG_ON(ret == -EIO); goto err_ggtt; } + ret = i915_gem_contexts_init(dev_priv); + if (ret) { + GEM_BUG_ON(ret == -EIO); + goto err_scratch; + } + ret = intel_engines_init(dev_priv); if (ret) { GEM_BUG_ON(ret == -EIO); @@ -5653,6 +5667,8 @@ err_pm: err_context: if (ret != -EIO) i915_gem_contexts_fini(dev_priv); +err_scratch: + i915_gem_fini_scratch(dev_priv); err_ggtt: err_unlock: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); @@ -5704,8 +5720,11 @@ void i915_gem_fini(struct drm_i915_private *dev_priv) intel_uc_fini(dev_priv); i915_gem_cleanup_engines(dev_priv); i915_gem_contexts_fini(dev_priv); + i915_gem_fini_scratch(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); + intel_wa_list_free(&dev_priv->gt_wa_list); + intel_cleanup_gt_powersave(dev_priv); intel_uc_fini_misc(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index b97963db0287..371c07087095 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -535,16 +535,12 @@ static bool needs_preempt_context(struct drm_i915_private *i915) int i915_gem_contexts_init(struct drm_i915_private *dev_priv) { struct i915_gem_context *ctx; - int ret; /* Reassure ourselves we are only called once */ GEM_BUG_ON(dev_priv->kernel_context); GEM_BUG_ON(dev_priv->preempt_context); - ret = intel_ctx_workarounds_init(dev_priv); - if (ret) - return ret; - + intel_engine_init_ctx_wa(dev_priv->engine[RCS]); init_contexts(dev_priv); /* lowest priority; idle task */ diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8123bf0e4807..07465123c166 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -27,11 +27,14 @@ * */ -#include <linux/utsname.h> +#include <linux/ascii85.h> +#include <linux/nmi.h> +#include <linux/scatterlist.h> #include <linux/stop_machine.h> +#include <linux/utsname.h> #include <linux/zlib.h> + #include <drm/drm_print.h> -#include <linux/ascii85.h> #include "i915_gpu_error.h" #include "i915_drv.h" @@ -77,112 +80,110 @@ static const char *purgeable_flag(int purgeable) return purgeable ? " purgeable" : ""; } -static bool __i915_error_ok(struct drm_i915_error_state_buf *e) +static void __sg_set_buf(struct scatterlist *sg, + void *addr, unsigned int len, loff_t it) { - - if (!e->err && WARN(e->bytes > (e->size - 1), "overflow")) { - e->err = -ENOSPC; - return false; - } - - if (e->bytes == e->size - 1 || e->err) - return false; - - return true; + sg->page_link = (unsigned long)virt_to_page(addr); + sg->offset = offset_in_page(addr); + sg->length = len; + sg->dma_address = it; } -static bool __i915_error_seek(struct drm_i915_error_state_buf *e, - unsigned len) +static bool __i915_error_grow(struct drm_i915_error_state_buf *e, size_t len) { - if (e->pos + len <= e->start) { - e->pos += len; + if (!len) return false; - } - /* First vsnprintf needs to fit in its entirety for memmove */ - if (len >= e->size) { - e->err = -EIO; - return false; - } + if (e->bytes + len + 1 <= e->size) + return true; - return true; -} + if (e->bytes) { + __sg_set_buf(e->cur++, e->buf, e->bytes, e->iter); + e->iter += e->bytes; + e->buf = NULL; + e->bytes = 0; + } -static void __i915_error_advance(struct drm_i915_error_state_buf *e, - unsigned len) -{ - /* If this is first printf in this window, adjust it so that - * start position matches start of the buffer - */ + if (e->cur == e->end) { + struct scatterlist *sgl; - if (e->pos < e->start) { - const size_t off = e->start - e->pos; + sgl = (typeof(sgl))__get_free_page(GFP_KERNEL); + if (!sgl) { + e->err = -ENOMEM; + return false; + } - /* Should not happen but be paranoid */ - if (off > len || e->bytes) { - e->err = -EIO; - return; + if (e->cur) { + e->cur->offset = 0; + e->cur->length = 0; + e->cur->page_link = + (unsigned long)sgl | SG_CHAIN; + } else { + e->sgl = sgl; } - memmove(e->buf, e->buf + off, len - off); - e->bytes = len - off; - e->pos = e->start; - return; + e->cur = sgl; + e->end = sgl + SG_MAX_SINGLE_ALLOC - 1; } - e->bytes += len; - e->pos += len; + e->size = ALIGN(len + 1, SZ_64K); + e->buf = kmalloc(e->size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (!e->buf) { + e->size = PAGE_ALIGN(len + 1); + e->buf = kmalloc(e->size, GFP_KERNEL); + } + if (!e->buf) { + e->err = -ENOMEM; + return false; + } + + return true; } __printf(2, 0) static void i915_error_vprintf(struct drm_i915_error_state_buf *e, - const char *f, va_list args) + const char *fmt, va_list args) { - unsigned len; + va_list ap; + int len; - if (!__i915_error_ok(e)) + if (e->err) return; - /* Seek the first printf which is hits start position */ - if (e->pos < e->start) { - va_list tmp; - - va_copy(tmp, args); - len = vsnprintf(NULL, 0, f, tmp); - va_end(tmp); - - if (!__i915_error_seek(e, len)) - return; + va_copy(ap, args); + len = vsnprintf(NULL, 0, fmt, ap); + va_end(ap); + if (len <= 0) { + e->err = len; + return; } - len = vsnprintf(e->buf + e->bytes, e->size - e->bytes, f, args); - if (len >= e->size - e->bytes) - len = e->size - e->bytes - 1; + if (!__i915_error_grow(e, len)) + return; - __i915_error_advance(e, len); + GEM_BUG_ON(e->bytes >= e->size); + len = vscnprintf(e->buf + e->bytes, e->size - e->bytes, fmt, args); + if (len < 0) { + e->err = len; + return; + } + e->bytes += len; } -static void i915_error_puts(struct drm_i915_error_state_buf *e, - const char *str) +static void i915_error_puts(struct drm_i915_error_state_buf *e, const char *str) { unsigned len; - if (!__i915_error_ok(e)) + if (e->err || !str) return; len = strlen(str); + if (!__i915_error_grow(e, len)) + return; - /* Seek the first printf which is hits start position */ - if (e->pos < e->start) { - if (!__i915_error_seek(e, len)) - return; - } - - if (len >= e->size - e->bytes) - len = e->size - e->bytes - 1; + GEM_BUG_ON(e->bytes + len > e->size); memcpy(e->buf + e->bytes, str, len); - - __i915_error_advance(e, len); + e->bytes += len; } #define err_printf(e, ...) i915_error_printf(e, __VA_ARGS__) @@ -268,6 +269,8 @@ static int compress_page(struct compress *c, if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK) return -EIO; + + touch_nmi_watchdog(); } while (zstream->avail_in); /* Fallback to uncompressed if we increase size? */ @@ -635,21 +638,29 @@ static void err_print_uc(struct drm_i915_error_state_buf *m, print_error_obj(m, NULL, "GuC log buffer", error_uc->guc_log); } -int i915_error_state_to_str(struct drm_i915_error_state_buf *m, - const struct i915_gpu_state *error) +static void err_free_sgl(struct scatterlist *sgl) { - struct drm_i915_private *dev_priv = m->i915; - struct drm_i915_error_object *obj; - struct timespec64 ts; - int i, j; + while (sgl) { + struct scatterlist *sg; - if (!error) { - err_printf(m, "No error state collected\n"); - return 0; + for (sg = sgl; !sg_is_chain(sg); sg++) { + kfree(sg_virt(sg)); + if (sg_is_last(sg)) + break; + } + + sg = sg_is_last(sg) ? NULL : sg_chain_ptr(sg); + free_page((unsigned long)sgl); + sgl = sg; } +} - if (IS_ERR(error)) - return PTR_ERR(error); +static void __err_print_to_sgl(struct drm_i915_error_state_buf *m, + struct i915_gpu_state *error) +{ + struct drm_i915_error_object *obj; + struct timespec64 ts; + int i, j; if (*error->error_msg) err_printf(m, "%s\n", error->error_msg); @@ -683,12 +694,12 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_printf(m, "Reset count: %u\n", error->reset_count); err_printf(m, "Suspend count: %u\n", error->suspend_count); err_printf(m, "Platform: %s\n", intel_platform_name(error->device_info.platform)); - err_print_pciid(m, error->i915); + err_print_pciid(m, m->i915); err_printf(m, "IOMMU enabled?: %d\n", error->iommu); - if (HAS_CSR(dev_priv)) { - struct intel_csr *csr = &dev_priv->csr; + if (HAS_CSR(m->i915)) { + struct intel_csr *csr = &m->i915->csr; err_printf(m, "DMC loaded: %s\n", yesno(csr->dmc_payload != NULL)); @@ -708,22 +719,23 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_printf(m, "FORCEWAKE: 0x%08x\n", error->forcewake); err_printf(m, "DERRMR: 0x%08x\n", error->derrmr); err_printf(m, "CCID: 0x%08x\n", error->ccid); - err_printf(m, "Missed interrupts: 0x%08lx\n", dev_priv->gpu_error.missed_irq_rings); + err_printf(m, "Missed interrupts: 0x%08lx\n", + m->i915->gpu_error.missed_irq_rings); for (i = 0; i < error->nfence; i++) err_printf(m, " fence[%d] = %08llx\n", i, error->fence[i]); - if (INTEL_GEN(dev_priv) >= 6) { + if (INTEL_GEN(m->i915) >= 6) { err_printf(m, "ERROR: 0x%08x\n", error->error); - if (INTEL_GEN(dev_priv) >= 8) + if (INTEL_GEN(m->i915) >= 8) err_printf(m, "FAULT_TLB_DATA: 0x%08x 0x%08x\n", error->fault_data1, error->fault_data0); err_printf(m, "DONE_REG: 0x%08x\n", error->done_reg); } - if (IS_GEN7(dev_priv)) + if (IS_GEN7(m->i915)) err_printf(m, "ERR_INT: 0x%08x\n", error->err_int); for (i = 0; i < ARRAY_SIZE(error->engine); i++) { @@ -745,7 +757,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, len += scnprintf(buf + len, sizeof(buf), "%s%s", first ? "" : ", ", - dev_priv->engine[j]->name); + m->i915->engine[j]->name); first = 0; } scnprintf(buf + len, sizeof(buf), ")"); @@ -763,7 +775,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, obj = ee->batchbuffer; if (obj) { - err_puts(m, dev_priv->engine[i]->name); + err_puts(m, m->i915->engine[i]->name); if (ee->context.pid) err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d%s)", ee->context.comm, @@ -775,16 +787,16 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_printf(m, " --- gtt_offset = 0x%08x %08x\n", upper_32_bits(obj->gtt_offset), lower_32_bits(obj->gtt_offset)); - print_error_obj(m, dev_priv->engine[i], NULL, obj); + print_error_obj(m, m->i915->engine[i], NULL, obj); } for (j = 0; j < ee->user_bo_count; j++) - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "user", ee->user_bo[j]); if (ee->num_requests) { err_printf(m, "%s --- %d requests\n", - dev_priv->engine[i]->name, + m->i915->engine[i]->name, ee->num_requests); for (j = 0; j < ee->num_requests; j++) error_print_request(m, " ", @@ -794,10 +806,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, if (IS_ERR(ee->waiters)) { err_printf(m, "%s --- ? waiters [unable to acquire spinlock]\n", - dev_priv->engine[i]->name); + m->i915->engine[i]->name); } else if (ee->num_waiters) { err_printf(m, "%s --- %d waiters\n", - dev_priv->engine[i]->name, + m->i915->engine[i]->name, ee->num_waiters); for (j = 0; j < ee->num_waiters; j++) { err_printf(m, " seqno 0x%08x for %s [%d]\n", @@ -807,22 +819,22 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, } } - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "ringbuffer", ee->ringbuffer); - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "HW Status", ee->hws_page); - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "HW context", ee->ctx); - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "WA context", ee->wa_ctx); - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "WA batchbuffer", ee->wa_batchbuffer); - print_error_obj(m, dev_priv->engine[i], + print_error_obj(m, m->i915->engine[i], "NULL context", ee->default_state); } @@ -835,43 +847,107 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, err_print_capabilities(m, &error->device_info, &error->driver_caps); err_print_params(m, &error->params); err_print_uc(m, &error->uc); +} + +static int err_print_to_sgl(struct i915_gpu_state *error) +{ + struct drm_i915_error_state_buf m; + + if (IS_ERR(error)) + return PTR_ERR(error); + + if (READ_ONCE(error->sgl)) + return 0; + + memset(&m, 0, sizeof(m)); + m.i915 = error->i915; + + __err_print_to_sgl(&m, error); + + if (m.buf) { + __sg_set_buf(m.cur++, m.buf, m.bytes, m.iter); + m.bytes = 0; + m.buf = NULL; + } + if (m.cur) { + GEM_BUG_ON(m.end < m.cur); + sg_mark_end(m.cur - 1); + } + GEM_BUG_ON(m.sgl && !m.cur); + + if (m.err) { + err_free_sgl(m.sgl); + return m.err; + } - if (m->bytes == 0 && m->err) - return m->err; + if (cmpxchg(&error->sgl, NULL, m.sgl)) + err_free_sgl(m.sgl); return 0; } -int i915_error_state_buf_init(struct drm_i915_error_state_buf *ebuf, - struct drm_i915_private *i915, - size_t count, loff_t pos) +ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error, + char *buf, loff_t off, size_t rem) { - memset(ebuf, 0, sizeof(*ebuf)); - ebuf->i915 = i915; + struct scatterlist *sg; + size_t count; + loff_t pos; + int err; - /* We need to have enough room to store any i915_error_state printf - * so that we can move it to start position. - */ - ebuf->size = count + 1 > PAGE_SIZE ? count + 1 : PAGE_SIZE; - ebuf->buf = kmalloc(ebuf->size, - GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + if (!error || !rem) + return 0; - if (ebuf->buf == NULL) { - ebuf->size = PAGE_SIZE; - ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL); - } + err = err_print_to_sgl(error); + if (err) + return err; - if (ebuf->buf == NULL) { - ebuf->size = 128; - ebuf->buf = kmalloc(ebuf->size, GFP_KERNEL); - } + sg = READ_ONCE(error->fit); + if (!sg || off < sg->dma_address) + sg = error->sgl; + if (!sg) + return 0; - if (ebuf->buf == NULL) - return -ENOMEM; + pos = sg->dma_address; + count = 0; + do { + size_t len, start; + + if (sg_is_chain(sg)) { + sg = sg_chain_ptr(sg); + GEM_BUG_ON(sg_is_chain(sg)); + } + + len = sg->length; + if (pos + len <= off) { + pos += len; + continue; + } - ebuf->start = pos; + start = sg->offset; + if (pos < off) { + GEM_BUG_ON(off - pos > len); + len -= off - pos; + start += off - pos; + pos = off; + } - return 0; + len = min(len, rem); + GEM_BUG_ON(!len || len > sg->length); + + memcpy(buf, page_address(sg_page(sg)) + start, len); + + count += len; + pos += len; + + buf += len; + rem -= len; + if (!rem) { + WRITE_ONCE(error->fit, sg); + break; + } + } while (!sg_is_last(sg++)); + + return count; } static void i915_error_object_free(struct drm_i915_error_object *obj) @@ -944,6 +1020,7 @@ void __i915_gpu_state_free(struct kref *error_ref) cleanup_params(error); cleanup_uc_state(error); + err_free_sgl(error->sgl); kfree(error); } @@ -1494,7 +1571,7 @@ static void gem_record_rings(struct i915_gpu_state *error) if (HAS_BROKEN_CS_TLB(i915)) ee->wa_batchbuffer = i915_error_object_create(i915, - engine->scratch); + i915->gt.scratch); request_record_user_bo(request, ee); ee->ctx = diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 3ec89a504de5..ff2652bbb0b0 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -192,6 +192,8 @@ struct i915_gpu_state { } *active_bo[I915_NUM_ENGINES], *pinned_bo; u32 active_bo_count[I915_NUM_ENGINES], pinned_bo_count; struct i915_address_space *active_vm[I915_NUM_ENGINES]; + + struct scatterlist *sgl, *fit; }; struct i915_gpu_error { @@ -298,29 +300,20 @@ struct i915_gpu_error { struct drm_i915_error_state_buf { struct drm_i915_private *i915; - unsigned int bytes; - unsigned int size; + struct scatterlist *sgl, *cur, *end; + + char *buf; + size_t bytes; + size_t size; + loff_t iter; + int err; - u8 *buf; - loff_t start; - loff_t pos; }; #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) __printf(2, 3) void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...); -int i915_error_state_to_str(struct drm_i915_error_state_buf *estr, - const struct i915_gpu_state *gpu); -int i915_error_state_buf_init(struct drm_i915_error_state_buf *eb, - struct drm_i915_private *i915, - size_t count, loff_t pos); - -static inline void -i915_error_state_buf_release(struct drm_i915_error_state_buf *eb) -{ - kfree(eb->buf); -} struct i915_gpu_state *i915_capture_gpu_state(struct drm_i915_private *i915); void i915_capture_error_state(struct drm_i915_private *dev_priv, @@ -334,6 +327,9 @@ i915_gpu_state_get(struct i915_gpu_state *gpu) return gpu; } +ssize_t i915_gpu_state_copy_to_buffer(struct i915_gpu_state *error, + char *buf, loff_t offset, size_t count); + void __i915_gpu_state_free(struct kref *kref); static inline void i915_gpu_state_put(struct i915_gpu_state *gpu) { diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 1b81d7cb209e..6350db5503cd 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -79,8 +79,9 @@ #define GEN2_FEATURES \ GEN(2), \ .num_pipes = 1, \ - .has_overlay = 1, .overlay_needs_physical = 1, \ - .has_gmch_display = 1, \ + .display.has_overlay = 1, \ + .display.overlay_needs_physical = 1, \ + .display.has_gmch_display = 1, \ .hws_needs_physical = 1, \ .unfenced_needs_alignment = 1, \ .ring_mask = RENDER_RING, \ @@ -93,7 +94,8 @@ static const struct intel_device_info intel_i830_info = { GEN2_FEATURES, PLATFORM(INTEL_I830), - .is_mobile = 1, .cursor_needs_physical = 1, + .is_mobile = 1, + .display.cursor_needs_physical = 1, .num_pipes = 2, /* legal, last one wins */ }; @@ -107,8 +109,8 @@ static const struct intel_device_info intel_i85x_info = { PLATFORM(INTEL_I85X), .is_mobile = 1, .num_pipes = 2, /* legal, last one wins */ - .cursor_needs_physical = 1, - .has_fbc = 1, + .display.cursor_needs_physical = 1, + .display.has_fbc = 1, }; static const struct intel_device_info intel_i865g_info = { @@ -119,7 +121,7 @@ static const struct intel_device_info intel_i865g_info = { #define GEN3_FEATURES \ GEN(3), \ .num_pipes = 2, \ - .has_gmch_display = 1, \ + .display.has_gmch_display = 1, \ .ring_mask = RENDER_RING, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -131,8 +133,9 @@ static const struct intel_device_info intel_i915g_info = { GEN3_FEATURES, PLATFORM(INTEL_I915G), .has_coherent_ggtt = false, - .cursor_needs_physical = 1, - .has_overlay = 1, .overlay_needs_physical = 1, + .display.cursor_needs_physical = 1, + .display.has_overlay = 1, + .display.overlay_needs_physical = 1, .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -141,10 +144,11 @@ static const struct intel_device_info intel_i915gm_info = { GEN3_FEATURES, PLATFORM(INTEL_I915GM), .is_mobile = 1, - .cursor_needs_physical = 1, - .has_overlay = 1, .overlay_needs_physical = 1, - .supports_tv = 1, - .has_fbc = 1, + .display.cursor_needs_physical = 1, + .display.has_overlay = 1, + .display.overlay_needs_physical = 1, + .display.supports_tv = 1, + .display.has_fbc = 1, .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -152,8 +156,10 @@ static const struct intel_device_info intel_i915gm_info = { static const struct intel_device_info intel_i945g_info = { GEN3_FEATURES, PLATFORM(INTEL_I945G), - .has_hotplug = 1, .cursor_needs_physical = 1, - .has_overlay = 1, .overlay_needs_physical = 1, + .display.has_hotplug = 1, + .display.cursor_needs_physical = 1, + .display.has_overlay = 1, + .display.overlay_needs_physical = 1, .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -162,10 +168,12 @@ static const struct intel_device_info intel_i945gm_info = { GEN3_FEATURES, PLATFORM(INTEL_I945GM), .is_mobile = 1, - .has_hotplug = 1, .cursor_needs_physical = 1, - .has_overlay = 1, .overlay_needs_physical = 1, - .supports_tv = 1, - .has_fbc = 1, + .display.has_hotplug = 1, + .display.cursor_needs_physical = 1, + .display.has_overlay = 1, + .display.overlay_needs_physical = 1, + .display.supports_tv = 1, + .display.has_fbc = 1, .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -173,23 +181,23 @@ static const struct intel_device_info intel_i945gm_info = { static const struct intel_device_info intel_g33_info = { GEN3_FEATURES, PLATFORM(INTEL_G33), - .has_hotplug = 1, - .has_overlay = 1, + .display.has_hotplug = 1, + .display.has_overlay = 1, }; static const struct intel_device_info intel_pineview_info = { GEN3_FEATURES, PLATFORM(INTEL_PINEVIEW), .is_mobile = 1, - .has_hotplug = 1, - .has_overlay = 1, + .display.has_hotplug = 1, + .display.has_overlay = 1, }; #define GEN4_FEATURES \ GEN(4), \ .num_pipes = 2, \ - .has_hotplug = 1, \ - .has_gmch_display = 1, \ + .display.has_hotplug = 1, \ + .display.has_gmch_display = 1, \ .ring_mask = RENDER_RING, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -200,7 +208,7 @@ static const struct intel_device_info intel_pineview_info = { static const struct intel_device_info intel_i965g_info = { GEN4_FEATURES, PLATFORM(INTEL_I965G), - .has_overlay = 1, + .display.has_overlay = 1, .hws_needs_physical = 1, .has_snoop = false, }; @@ -208,9 +216,10 @@ static const struct intel_device_info intel_i965g_info = { static const struct intel_device_info intel_i965gm_info = { GEN4_FEATURES, PLATFORM(INTEL_I965GM), - .is_mobile = 1, .has_fbc = 1, - .has_overlay = 1, - .supports_tv = 1, + .is_mobile = 1, + .display.has_fbc = 1, + .display.has_overlay = 1, + .display.supports_tv = 1, .hws_needs_physical = 1, .has_snoop = false, }; @@ -224,15 +233,16 @@ static const struct intel_device_info intel_g45_info = { static const struct intel_device_info intel_gm45_info = { GEN4_FEATURES, PLATFORM(INTEL_GM45), - .is_mobile = 1, .has_fbc = 1, - .supports_tv = 1, + .is_mobile = 1, + .display.has_fbc = 1, + .display.supports_tv = 1, .ring_mask = RENDER_RING | BSD_RING, }; #define GEN5_FEATURES \ GEN(5), \ .num_pipes = 2, \ - .has_hotplug = 1, \ + .display.has_hotplug = 1, \ .ring_mask = RENDER_RING | BSD_RING, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -250,14 +260,15 @@ static const struct intel_device_info intel_ironlake_d_info = { static const struct intel_device_info intel_ironlake_m_info = { GEN5_FEATURES, PLATFORM(INTEL_IRONLAKE), - .is_mobile = 1, .has_fbc = 1, + .is_mobile = 1, + .display.has_fbc = 1, }; #define GEN6_FEATURES \ GEN(6), \ .num_pipes = 2, \ - .has_hotplug = 1, \ - .has_fbc = 1, \ + .display.has_hotplug = 1, \ + .display.has_fbc = 1, \ .ring_mask = RENDER_RING | BSD_RING | BLT_RING, \ .has_coherent_ggtt = true, \ .has_llc = 1, \ @@ -301,8 +312,8 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = { #define GEN7_FEATURES \ GEN(7), \ .num_pipes = 3, \ - .has_hotplug = 1, \ - .has_fbc = 1, \ + .display.has_hotplug = 1, \ + .display.has_fbc = 1, \ .ring_mask = RENDER_RING | BSD_RING | BLT_RING, \ .has_coherent_ggtt = true, \ .has_llc = 1, \ @@ -359,8 +370,8 @@ static const struct intel_device_info intel_valleyview_info = { .num_pipes = 2, .has_runtime_pm = 1, .has_rc6 = 1, - .has_gmch_display = 1, - .has_hotplug = 1, + .display.has_gmch_display = 1, + .display.has_hotplug = 1, .ppgtt = INTEL_PPGTT_FULL, .has_snoop = true, .has_coherent_ggtt = false, @@ -374,10 +385,10 @@ static const struct intel_device_info intel_valleyview_info = { #define G75_FEATURES \ GEN7_FEATURES, \ .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, \ - .has_ddi = 1, \ + .display.has_ddi = 1, \ .has_fpga_dbg = 1, \ - .has_psr = 1, \ - .has_dp_mst = 1, \ + .display.has_psr = 1, \ + .display.has_dp_mst = 1, \ .has_rc6p = 0 /* RC6p removed-by HSW */, \ .has_runtime_pm = 1 @@ -444,14 +455,14 @@ static const struct intel_device_info intel_cherryview_info = { PLATFORM(INTEL_CHERRYVIEW), GEN(8), .num_pipes = 3, - .has_hotplug = 1, + .display.has_hotplug = 1, .is_lp = 1, .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, .has_64bit_reloc = 1, .has_runtime_pm = 1, .has_rc6 = 1, .has_logical_ring_contexts = 1, - .has_gmch_display = 1, + .display.has_gmch_display = 1, .ppgtt = INTEL_PPGTT_FULL, .has_reset_engine = 1, .has_snoop = true, @@ -473,15 +484,15 @@ static const struct intel_device_info intel_cherryview_info = { GEN(9), \ GEN9_DEFAULT_PAGE_SIZES, \ .has_logical_ring_preemption = 1, \ - .has_csr = 1, \ + .display.has_csr = 1, \ .has_guc = 1, \ - .has_ipc = 1, \ + .display.has_ipc = 1, \ .ddb_size = 896 #define SKL_PLATFORM \ GEN9_FEATURES, \ /* Display WA #0477 WaDisableIPC: skl */ \ - .has_ipc = 0, \ + .display.has_ipc = 0, \ PLATFORM(INTEL_SKYLAKE) static const struct intel_device_info intel_skylake_gt1_info = { @@ -512,19 +523,19 @@ static const struct intel_device_info intel_skylake_gt4_info = { #define GEN9_LP_FEATURES \ GEN(9), \ .is_lp = 1, \ - .has_hotplug = 1, \ + .display.has_hotplug = 1, \ .ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING, \ .num_pipes = 3, \ .has_64bit_reloc = 1, \ - .has_ddi = 1, \ + .display.has_ddi = 1, \ .has_fpga_dbg = 1, \ - .has_fbc = 1, \ - .has_psr = 1, \ + .display.has_fbc = 1, \ + .display.has_psr = 1, \ .has_runtime_pm = 1, \ .has_pooled_eu = 0, \ - .has_csr = 1, \ + .display.has_csr = 1, \ .has_rc6 = 1, \ - .has_dp_mst = 1, \ + .display.has_dp_mst = 1, \ .has_logical_ring_contexts = 1, \ .has_logical_ring_preemption = 1, \ .has_guc = 1, \ @@ -532,7 +543,7 @@ static const struct intel_device_info intel_skylake_gt4_info = { .has_reset_engine = 1, \ .has_snoop = true, \ .has_coherent_ggtt = false, \ - .has_ipc = 1, \ + .display.has_ipc = 1, \ GEN9_DEFAULT_PAGE_SIZES, \ GEN_DEFAULT_PIPEOFFSETS, \ IVB_CURSOR_OFFSETS, \ diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 47baf2fe8f71..0a7d60509ca7 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4570,6 +4570,7 @@ enum { * of the infoframe structure specified by CEA-861. */ #define VIDEO_DIP_DATA_SIZE 32 #define VIDEO_DIP_VSC_DATA_SIZE 36 +#define VIDEO_DIP_PPS_DATA_SIZE 132 #define VIDEO_DIP_CTL _MMIO(0x61170) /* Pre HSW: */ #define VIDEO_DIP_ENABLE (1 << 31) @@ -4617,6 +4618,17 @@ enum { #define _PP_STATUS 0x61200 #define PP_STATUS(pps_idx) _MMIO_PPS(pps_idx, _PP_STATUS) #define PP_ON (1 << 31) + +#define _PP_CONTROL_1 0xc7204 +#define _PP_CONTROL_2 0xc7304 +#define ICP_PP_CONTROL(x) _MMIO(((x) == 1) ? _PP_CONTROL_1 : \ + _PP_CONTROL_2) +#define POWER_CYCLE_DELAY_MASK (0x1f << 4) +#define POWER_CYCLE_DELAY_SHIFT 4 +#define VDD_OVERRIDE_FORCE (1 << 3) +#define BACKLIGHT_ENABLE (1 << 2) +#define PWR_DOWN_ON_RESET (1 << 1) +#define PWR_STATE_TARGET (1 << 0) /* * Indicates that all dependencies of the panel are on: * @@ -7750,6 +7762,7 @@ enum { #define ICP_DDIB_HPD_LONG_DETECT (2 << 4) #define ICP_DDIB_HPD_SHORT_LONG_DETECT (3 << 4) #define ICP_DDIA_HPD_ENABLE (1 << 3) +#define ICP_DDIA_HPD_OP_DRIVE_1 (1 << 2) #define ICP_DDIA_HPD_STATUS_MASK (3 << 0) #define ICP_DDIA_HPD_NO_DETECT (0 << 0) #define ICP_DDIA_HPD_SHORT_DETECT (1 << 0) @@ -9197,6 +9210,7 @@ enum skl_power_gate { #define _DP_TP_CTL_B 0x64140 #define DP_TP_CTL(port) _MMIO_PORT(port, _DP_TP_CTL_A, _DP_TP_CTL_B) #define DP_TP_CTL_ENABLE (1 << 31) +#define DP_TP_CTL_FEC_ENABLE (1 << 30) #define DP_TP_CTL_MODE_SST (0 << 27) #define DP_TP_CTL_MODE_MST (1 << 27) #define DP_TP_CTL_FORCE_ACT (1 << 25) @@ -9215,6 +9229,7 @@ enum skl_power_gate { #define _DP_TP_STATUS_A 0x64044 #define _DP_TP_STATUS_B 0x64144 #define DP_TP_STATUS(port) _MMIO_PORT(port, _DP_TP_STATUS_A, _DP_TP_STATUS_B) +#define DP_TP_STATUS_FEC_ENABLE_LIVE (1 << 28) #define DP_TP_STATUS_IDLE_DONE (1 << 25) #define DP_TP_STATUS_ACT_SENT (1 << 24) #define DP_TP_STATUS_MODE_STATUS_MST (1 << 23) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 71107540581d..ca95ab2f4cfa 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -136,6 +136,9 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno) intel_engine_get_seqno(engine), seqno); + if (seqno == engine->timeline.seqno) + continue; + kthread_park(engine->breadcrumbs.signaler); if (!i915_seqno_passed(seqno, engine->timeline.seqno)) { diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 6dbeed079ae5..fc2eeab823b7 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -1,10 +1,7 @@ /* - * (C) Copyright 2016 Intel Corporation + * SPDX-License-Identifier: MIT * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. + * (C) Copyright 2016 Intel Corporation */ #include <linux/slab.h> diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index fe2ef4dadfc6..0e055ea0179f 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -1,10 +1,9 @@ /* + * SPDX-License-Identifier: MIT + * * i915_sw_fence.h - library routines for N:M synchronisation points * * Copyright (C) 2016 Intel Corporation - * - * This file is released under the GPLv2. - * */ #ifndef _I915_SW_FENCE_H_ diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c index e5e6f6bb2b05..535caebd9813 100644 --- a/drivers/gpu/drm/i915/i915_sysfs.c +++ b/drivers/gpu/drm/i915/i915_sysfs.c @@ -483,7 +483,7 @@ static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr return snprintf(buf, PAGE_SIZE, "%d\n", val); } -static const struct attribute *gen6_attrs[] = { +static const struct attribute * const gen6_attrs[] = { &dev_attr_gt_act_freq_mhz.attr, &dev_attr_gt_cur_freq_mhz.attr, &dev_attr_gt_boost_freq_mhz.attr, @@ -495,7 +495,7 @@ static const struct attribute *gen6_attrs[] = { NULL, }; -static const struct attribute *vlv_attrs[] = { +static const struct attribute * const vlv_attrs[] = { &dev_attr_gt_act_freq_mhz.attr, &dev_attr_gt_cur_freq_mhz.attr, &dev_attr_gt_boost_freq_mhz.attr, @@ -516,26 +516,21 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj, { struct device *kdev = kobj_to_dev(kobj); - struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev); - struct drm_i915_error_state_buf error_str; + struct drm_i915_private *i915 = kdev_minor_to_i915(kdev); struct i915_gpu_state *gpu; ssize_t ret; - ret = i915_error_state_buf_init(&error_str, dev_priv, count, off); - if (ret) - return ret; - - gpu = i915_first_error_state(dev_priv); - ret = i915_error_state_to_str(&error_str, gpu); - if (ret) - goto out; - - ret = count < error_str.bytes ? count : error_str.bytes; - memcpy(buf, error_str.buf, ret); + gpu = i915_first_error_state(i915); + if (gpu) { + ret = i915_gpu_state_copy_to_buffer(gpu, buf, off, count); + i915_gpu_state_put(gpu); + } else { + const char *str = "No error state collected\n"; + size_t len = strlen(str); -out: - i915_gpu_state_put(gpu); - i915_error_state_buf_release(&error_str); + ret = min_t(size_t, count, len - off); + memcpy(buf, str + off, ret); + } return ret; } diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 5858a43e19da..9726df37c4c4 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -44,16 +44,19 @@ __stringify(x), (long)(x)) #if defined(GCC_VERSION) && GCC_VERSION >= 70000 -#define add_overflows(A, B) \ - __builtin_add_overflow_p((A), (B), (typeof((A) + (B)))0) +#define add_overflows_t(T, A, B) \ + __builtin_add_overflow_p((A), (B), (T)0) #else -#define add_overflows(A, B) ({ \ +#define add_overflows_t(T, A, B) ({ \ typeof(A) a = (A); \ typeof(B) b = (B); \ - a + b < a; \ + (T)(a + b) < a; \ }) #endif +#define add_overflows(A, B) \ + add_overflows_t(typeof((A) + (B)), (A), (B)) + #define range_overflows(start, size, max) ({ \ typeof(start) start__ = (start); \ typeof(size) size__ = (size); \ diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c index 01f422df8c23..4dd793b78996 100644 --- a/drivers/gpu/drm/i915/icl_dsi.c +++ b/drivers/gpu/drm/i915/icl_dsi.c @@ -26,6 +26,7 @@ */ #include <drm/drm_mipi_dsi.h> +#include <drm/drm_atomic_helper.h> #include "intel_dsi.h" static inline int header_credits_available(struct drm_i915_private *dev_priv, @@ -107,6 +108,90 @@ static void wait_for_cmds_dispatched_to_panel(struct intel_encoder *encoder) } } +static bool add_payld_to_queue(struct intel_dsi_host *host, const u8 *data, + u32 len) +{ + struct intel_dsi *intel_dsi = host->intel_dsi; + struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev); + enum transcoder dsi_trans = dsi_port_to_transcoder(host->port); + int free_credits; + int i, j; + + for (i = 0; i < len; i += 4) { + u32 tmp = 0; + + free_credits = payload_credits_available(dev_priv, dsi_trans); + if (free_credits < 1) { + DRM_ERROR("Payload credit not available\n"); + return false; + } + + for (j = 0; j < min_t(u32, len - i, 4); j++) + tmp |= *data++ << 8 * j; + + I915_WRITE(DSI_CMD_TXPYLD(dsi_trans), tmp); + } + + return true; +} + +static int dsi_send_pkt_hdr(struct intel_dsi_host *host, + struct mipi_dsi_packet pkt, bool enable_lpdt) +{ + struct intel_dsi *intel_dsi = host->intel_dsi; + struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev); + enum transcoder dsi_trans = dsi_port_to_transcoder(host->port); + u32 tmp; + int free_credits; + + /* check if header credit available */ + free_credits = header_credits_available(dev_priv, dsi_trans); + if (free_credits < 1) { + DRM_ERROR("send pkt header failed, not enough hdr credits\n"); + return -1; + } + + tmp = I915_READ(DSI_CMD_TXHDR(dsi_trans)); + + if (pkt.payload) + tmp |= PAYLOAD_PRESENT; + else + tmp &= ~PAYLOAD_PRESENT; + + tmp &= ~VBLANK_FENCE; + + if (enable_lpdt) + tmp |= LP_DATA_TRANSFER; + + tmp &= ~(PARAM_WC_MASK | VC_MASK | DT_MASK); + tmp |= ((pkt.header[0] & VC_MASK) << VC_SHIFT); + tmp |= ((pkt.header[0] & DT_MASK) << DT_SHIFT); + tmp |= (pkt.header[1] << PARAM_WC_LOWER_SHIFT); + tmp |= (pkt.header[2] << PARAM_WC_UPPER_SHIFT); + I915_WRITE(DSI_CMD_TXHDR(dsi_trans), tmp); + + return 0; +} + +static int dsi_send_pkt_payld(struct intel_dsi_host *host, + struct mipi_dsi_packet pkt) +{ + /* payload queue can accept *256 bytes*, check limit */ + if (pkt.payload_length > MAX_PLOAD_CREDIT * 4) { + DRM_ERROR("payload size exceeds max queue limit\n"); + return -1; + } + + /* load data into command payload queue */ + if (!add_payld_to_queue(host, pkt.payload, + pkt.payload_length)) { + DRM_ERROR("adding payload to queue failed\n"); + return -1; + } + + return 0; +} + static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); @@ -172,6 +257,45 @@ static void dsi_program_swing_and_deemphasis(struct intel_encoder *encoder) } } +static void configure_dual_link_mode(struct intel_encoder *encoder, + const struct intel_crtc_state *pipe_config) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 dss_ctl1; + + dss_ctl1 = I915_READ(DSS_CTL1); + dss_ctl1 |= SPLITTER_ENABLE; + dss_ctl1 &= ~OVERLAP_PIXELS_MASK; + dss_ctl1 |= OVERLAP_PIXELS(intel_dsi->pixel_overlap); + + if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) { + const struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; + u32 dss_ctl2; + u16 hactive = adjusted_mode->crtc_hdisplay; + u16 dl_buffer_depth; + + dss_ctl1 &= ~DUAL_LINK_MODE_INTERLEAVE; + dl_buffer_depth = hactive / 2 + intel_dsi->pixel_overlap; + + if (dl_buffer_depth > MAX_DL_BUFFER_TARGET_DEPTH) + DRM_ERROR("DL buffer depth exceed max value\n"); + + dss_ctl1 &= ~LEFT_DL_BUF_TARGET_DEPTH_MASK; + dss_ctl1 |= LEFT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); + dss_ctl2 = I915_READ(DSS_CTL2); + dss_ctl2 &= ~RIGHT_DL_BUF_TARGET_DEPTH_MASK; + dss_ctl2 |= RIGHT_DL_BUF_TARGET_DEPTH(dl_buffer_depth); + I915_WRITE(DSS_CTL2, dss_ctl2); + } else { + /* Interleave */ + dss_ctl1 |= DUAL_LINK_MODE_INTERLEAVE; + } + + I915_WRITE(DSS_CTL1, dss_ctl1); +} + static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); @@ -412,6 +536,62 @@ static void gen11_dsi_setup_dphy_timings(struct intel_encoder *encoder) } } +static void gen11_dsi_gate_clocks(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 tmp; + enum port port; + + mutex_lock(&dev_priv->dpll_lock); + tmp = I915_READ(DPCLKA_CFGCR0_ICL); + for_each_dsi_port(port, intel_dsi->ports) { + tmp |= DPCLKA_CFGCR0_DDI_CLK_OFF(port); + } + + I915_WRITE(DPCLKA_CFGCR0_ICL, tmp); + mutex_unlock(&dev_priv->dpll_lock); +} + +static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 tmp; + enum port port; + + mutex_lock(&dev_priv->dpll_lock); + tmp = I915_READ(DPCLKA_CFGCR0_ICL); + for_each_dsi_port(port, intel_dsi->ports) { + tmp &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port); + } + + I915_WRITE(DPCLKA_CFGCR0_ICL, tmp); + mutex_unlock(&dev_priv->dpll_lock); +} + +static void gen11_dsi_map_pll(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + struct intel_shared_dpll *pll = crtc_state->shared_dpll; + enum port port; + u32 val; + + mutex_lock(&dev_priv->dpll_lock); + + val = I915_READ(DPCLKA_CFGCR0_ICL); + for_each_dsi_port(port, intel_dsi->ports) { + val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port); + val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port); + } + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + POSTING_READ(DPCLKA_CFGCR0_ICL); + + mutex_unlock(&dev_priv->dpll_lock); +} + static void gen11_dsi_configure_transcoder(struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config) @@ -506,7 +686,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, I915_WRITE(TRANS_DDI_FUNC_CTL2(dsi_trans), tmp); } - //TODO: configure DSS_CTL1 + /* configure stream splitting */ + configure_dual_link_mode(encoder, pipe_config); } for_each_dsi_port(port, intel_dsi->ports) { @@ -758,6 +939,9 @@ gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder, /* Step (4h, 4i, 4j, 4k): Configure transcoder */ gen11_dsi_configure_transcoder(encoder, pipe_config); + + /* Step 4l: Gate DDI clocks */ + gen11_dsi_gate_clocks(encoder); } static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) @@ -799,18 +983,25 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) wait_for_cmds_dispatched_to_panel(encoder); } -static void __attribute__((unused)) -gen11_dsi_pre_enable(struct intel_encoder *encoder, - const struct intel_crtc_state *pipe_config, - const struct drm_connector_state *conn_state) +static void gen11_dsi_pre_pll_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *pipe_config, + const struct drm_connector_state *conn_state) { - struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); - /* step2: enable IO power */ gen11_dsi_enable_io_power(encoder); /* step3: enable DSI PLL */ gen11_dsi_program_esc_clk_div(encoder); +} + +static void gen11_dsi_pre_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *pipe_config, + const struct drm_connector_state *conn_state) +{ + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + + /* step3b */ + gen11_dsi_map_pll(encoder, pipe_config); /* step4: enable DSI port and DPHY */ gen11_dsi_enable_port_and_phy(encoder, pipe_config); @@ -912,6 +1103,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder) u32 tmp; enum port port; + gen11_dsi_ungate_clocks(encoder); for_each_dsi_port(port, intel_dsi->ports) { tmp = I915_READ(DDI_BUF_CTL(port)); tmp &= ~DDI_BUF_CTL_ENABLE; @@ -923,6 +1115,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder) DRM_ERROR("DDI port:%c buffer not idle\n", port_name(port)); } + gen11_dsi_ungate_clocks(encoder); } static void gen11_dsi_disable_io_power(struct intel_encoder *encoder) @@ -945,10 +1138,9 @@ static void gen11_dsi_disable_io_power(struct intel_encoder *encoder) } } -static void __attribute__((unused)) gen11_dsi_disable( - struct intel_encoder *encoder, - const struct intel_crtc_state *old_crtc_state, - const struct drm_connector_state *old_conn_state) +static void gen11_dsi_disable(struct intel_encoder *encoder, + const struct intel_crtc_state *old_crtc_state, + const struct drm_connector_state *old_conn_state) { struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); @@ -972,10 +1164,289 @@ static void __attribute__((unused)) gen11_dsi_disable( gen11_dsi_disable_io_power(encoder); } +static void gen11_dsi_get_config(struct intel_encoder *encoder, + struct intel_crtc_state *pipe_config) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 pll_id; + + /* FIXME: adapt icl_ddi_clock_get() for DSI and use that? */ + pll_id = intel_get_shared_dpll_id(dev_priv, pipe_config->shared_dpll); + pipe_config->port_clock = cnl_calc_wrpll_link(dev_priv, pll_id); + pipe_config->base.adjusted_mode.crtc_clock = intel_dsi->pclk; + pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI); +} + +static bool gen11_dsi_compute_config(struct intel_encoder *encoder, + struct intel_crtc_state *pipe_config, + struct drm_connector_state *conn_state) +{ + struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi, + base); + struct intel_connector *intel_connector = intel_dsi->attached_connector; + struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc); + const struct drm_display_mode *fixed_mode = + intel_connector->panel.fixed_mode; + struct drm_display_mode *adjusted_mode = + &pipe_config->base.adjusted_mode; + + intel_fixed_panel_mode(fixed_mode, adjusted_mode); + intel_pch_panel_fitting(crtc, pipe_config, conn_state->scaling_mode); + + adjusted_mode->flags = 0; + + /* Dual link goes to trancoder DSI'0' */ + if (intel_dsi->ports == BIT(PORT_B)) + pipe_config->cpu_transcoder = TRANSCODER_DSI_1; + else + pipe_config->cpu_transcoder = TRANSCODER_DSI_0; + + pipe_config->clock_set = true; + pipe_config->port_clock = intel_dsi_bitrate(intel_dsi) / 5; + + return true; +} + +static u64 gen11_dsi_get_power_domains(struct intel_encoder *encoder, + struct intel_crtc_state *crtc_state) +{ + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u64 domains = 0; + enum port port; + + for_each_dsi_port(port, intel_dsi->ports) + if (port == PORT_A) + domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO); + else + domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO); + + return domains; +} + +static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder, + enum pipe *pipe) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base); + u32 tmp; + enum port port; + enum transcoder dsi_trans; + bool ret = false; + + if (!intel_display_power_get_if_enabled(dev_priv, + encoder->power_domain)) + return false; + + for_each_dsi_port(port, intel_dsi->ports) { + dsi_trans = dsi_port_to_transcoder(port); + tmp = I915_READ(TRANS_DDI_FUNC_CTL(dsi_trans)); + switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { + case TRANS_DDI_EDP_INPUT_A_ON: + *pipe = PIPE_A; + break; + case TRANS_DDI_EDP_INPUT_B_ONOFF: + *pipe = PIPE_B; + break; + case TRANS_DDI_EDP_INPUT_C_ONOFF: + *pipe = PIPE_C; + break; + default: + DRM_ERROR("Invalid PIPE input\n"); + goto out; + } + + tmp = I915_READ(PIPECONF(dsi_trans)); + ret = tmp & PIPECONF_ENABLE; + } +out: + intel_display_power_put(dev_priv, encoder->power_domain); + return ret; +} + +static void gen11_dsi_encoder_destroy(struct drm_encoder *encoder) +{ + intel_encoder_destroy(encoder); +} + +static const struct drm_encoder_funcs gen11_dsi_encoder_funcs = { + .destroy = gen11_dsi_encoder_destroy, +}; + +static const struct drm_connector_funcs gen11_dsi_connector_funcs = { + .late_register = intel_connector_register, + .early_unregister = intel_connector_unregister, + .destroy = intel_connector_destroy, + .fill_modes = drm_helper_probe_single_connector_modes, + .atomic_get_property = intel_digital_connector_atomic_get_property, + .atomic_set_property = intel_digital_connector_atomic_set_property, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, + .atomic_duplicate_state = intel_digital_connector_duplicate_state, +}; + +static const struct drm_connector_helper_funcs gen11_dsi_connector_helper_funcs = { + .get_modes = intel_dsi_get_modes, + .mode_valid = intel_dsi_mode_valid, + .atomic_check = intel_digital_connector_atomic_check, +}; + +static int gen11_dsi_host_attach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dsi) +{ + return 0; +} + +static int gen11_dsi_host_detach(struct mipi_dsi_host *host, + struct mipi_dsi_device *dsi) +{ + return 0; +} + +static ssize_t gen11_dsi_host_transfer(struct mipi_dsi_host *host, + const struct mipi_dsi_msg *msg) +{ + struct intel_dsi_host *intel_dsi_host = to_intel_dsi_host(host); + struct mipi_dsi_packet dsi_pkt; + ssize_t ret; + bool enable_lpdt = false; + + ret = mipi_dsi_create_packet(&dsi_pkt, msg); + if (ret < 0) + return ret; + + if (msg->flags & MIPI_DSI_MSG_USE_LPM) + enable_lpdt = true; + + /* send packet header */ + ret = dsi_send_pkt_hdr(intel_dsi_host, dsi_pkt, enable_lpdt); + if (ret < 0) + return ret; + + /* only long packet contains payload */ + if (mipi_dsi_packet_format_is_long(msg->type)) { + ret = dsi_send_pkt_payld(intel_dsi_host, dsi_pkt); + if (ret < 0) + return ret; + } + + //TODO: add payload receive code if needed + + ret = sizeof(dsi_pkt.header) + dsi_pkt.payload_length; + + return ret; +} + +static const struct mipi_dsi_host_ops gen11_dsi_host_ops = { + .attach = gen11_dsi_host_attach, + .detach = gen11_dsi_host_detach, + .transfer = gen11_dsi_host_transfer, +}; + void icl_dsi_init(struct drm_i915_private *dev_priv) { + struct drm_device *dev = &dev_priv->drm; + struct intel_dsi *intel_dsi; + struct intel_encoder *encoder; + struct intel_connector *intel_connector; + struct drm_connector *connector; + struct drm_display_mode *scan, *fixed_mode = NULL; enum port port; if (!intel_bios_is_dsi_present(dev_priv, &port)) return; + + intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL); + if (!intel_dsi) + return; + + intel_connector = intel_connector_alloc(); + if (!intel_connector) { + kfree(intel_dsi); + return; + } + + encoder = &intel_dsi->base; + intel_dsi->attached_connector = intel_connector; + connector = &intel_connector->base; + + /* register DSI encoder with DRM subsystem */ + drm_encoder_init(dev, &encoder->base, &gen11_dsi_encoder_funcs, + DRM_MODE_ENCODER_DSI, "DSI %c", port_name(port)); + + encoder->pre_pll_enable = gen11_dsi_pre_pll_enable; + encoder->pre_enable = gen11_dsi_pre_enable; + encoder->disable = gen11_dsi_disable; + encoder->port = port; + encoder->get_config = gen11_dsi_get_config; + encoder->compute_config = gen11_dsi_compute_config; + encoder->get_hw_state = gen11_dsi_get_hw_state; + encoder->type = INTEL_OUTPUT_DSI; + encoder->cloneable = 0; + encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C); + encoder->power_domain = POWER_DOMAIN_PORT_DSI; + encoder->get_power_domains = gen11_dsi_get_power_domains; + + /* register DSI connector with DRM subsystem */ + drm_connector_init(dev, connector, &gen11_dsi_connector_funcs, + DRM_MODE_CONNECTOR_DSI); + drm_connector_helper_add(connector, &gen11_dsi_connector_helper_funcs); + connector->display_info.subpixel_order = SubPixelHorizontalRGB; + connector->interlace_allowed = false; + connector->doublescan_allowed = false; + intel_connector->get_hw_state = intel_connector_get_hw_state; + + /* attach connector to encoder */ + intel_connector_attach_encoder(intel_connector, encoder); + + /* fill mode info from VBT */ + mutex_lock(&dev->mode_config.mutex); + intel_dsi_vbt_get_modes(intel_dsi); + list_for_each_entry(scan, &connector->probed_modes, head) { + if (scan->type & DRM_MODE_TYPE_PREFERRED) { + fixed_mode = drm_mode_duplicate(dev, scan); + break; + } + } + mutex_unlock(&dev->mode_config.mutex); + + if (!fixed_mode) { + DRM_ERROR("DSI fixed mode info missing\n"); + goto err; + } + + connector->display_info.width_mm = fixed_mode->width_mm; + connector->display_info.height_mm = fixed_mode->height_mm; + intel_panel_init(&intel_connector->panel, fixed_mode, NULL); + intel_panel_setup_backlight(connector, INVALID_PIPE); + + + if (dev_priv->vbt.dsi.config->dual_link) + intel_dsi->ports = BIT(PORT_A) | BIT(PORT_B); + else + intel_dsi->ports = BIT(port); + + intel_dsi->dcs_backlight_ports = dev_priv->vbt.dsi.bl_ports; + intel_dsi->dcs_cabc_ports = dev_priv->vbt.dsi.cabc_ports; + + for_each_dsi_port(port, intel_dsi->ports) { + struct intel_dsi_host *host; + + host = intel_dsi_host_init(intel_dsi, &gen11_dsi_host_ops, port); + if (!host) + goto err; + + intel_dsi->dsi_hosts[port] = host; + } + + if (!intel_dsi_vbt_init(intel_dsi, MIPI_DSI_GENERIC_PANEL_ID)) { + DRM_DEBUG_KMS("no device found\n"); + goto err; + } + + return; + +err: + drm_encoder_cleanup(&encoder->base); + kfree(intel_dsi); + kfree(intel_connector); } diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c index a5a2c8fe58a7..8cb02f28d30c 100644 --- a/drivers/gpu/drm/i915/intel_atomic.c +++ b/drivers/gpu/drm/i915/intel_atomic.c @@ -184,6 +184,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc) crtc_state->fifo_changed = false; crtc_state->wm.need_postvbl_update = false; crtc_state->fb_bits = 0; + crtc_state->update_planes = 0; return &crtc_state->base; } diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c index 905f8ef3ba4f..0a73e6e65c20 100644 --- a/drivers/gpu/drm/i915/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/intel_atomic_plane.c @@ -139,6 +139,9 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ if (state->visible && state->fb->format->format == DRM_FORMAT_NV12) crtc_state->nv12_planes |= BIT(intel_plane->id); + if (state->visible || old_plane_state->base.visible) + crtc_state->update_planes |= BIT(intel_plane->id); + return intel_plane_atomic_calc_changes(old_crtc_state, &crtc_state->base, old_plane_state, @@ -168,27 +171,75 @@ static int intel_plane_atomic_check(struct drm_plane *plane, to_intel_plane_state(new_plane_state)); } -void intel_update_planes_on_crtc(struct intel_atomic_state *old_state, - struct intel_crtc *crtc, - struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) +static struct intel_plane * +skl_next_plane_to_commit(struct intel_atomic_state *state, + struct intel_crtc *crtc, + struct skl_ddb_entry entries_y[I915_MAX_PLANES], + struct skl_ddb_entry entries_uv[I915_MAX_PLANES], + unsigned int *update_mask) { - struct intel_plane_state *new_plane_state; + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + struct intel_plane_state *plane_state; struct intel_plane *plane; - u32 update_mask; int i; - update_mask = old_crtc_state->active_planes; - update_mask |= new_crtc_state->active_planes; + if (*update_mask == 0) + return NULL; + + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + enum plane_id plane_id = plane->id; - for_each_new_intel_plane_in_state(old_state, plane, new_plane_state, i) { if (crtc->pipe != plane->pipe || - !(update_mask & BIT(plane->id))) + !(*update_mask & BIT(plane_id))) + continue; + + if (skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb_y[plane_id], + entries_y, + I915_MAX_PLANES, plane_id) || + skl_ddb_allocation_overlaps(&crtc_state->wm.skl.plane_ddb_uv[plane_id], + entries_uv, + I915_MAX_PLANES, plane_id)) continue; + *update_mask &= ~BIT(plane_id); + entries_y[plane_id] = crtc_state->wm.skl.plane_ddb_y[plane_id]; + entries_uv[plane_id] = crtc_state->wm.skl.plane_ddb_uv[plane_id]; + + return plane; + } + + /* should never happen */ + WARN_ON(1); + + return NULL; +} + +void skl_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + struct skl_ddb_entry entries_y[I915_MAX_PLANES]; + struct skl_ddb_entry entries_uv[I915_MAX_PLANES]; + u32 update_mask = new_crtc_state->update_planes; + struct intel_plane *plane; + + memcpy(entries_y, old_crtc_state->wm.skl.plane_ddb_y, + sizeof(old_crtc_state->wm.skl.plane_ddb_y)); + memcpy(entries_uv, old_crtc_state->wm.skl.plane_ddb_uv, + sizeof(old_crtc_state->wm.skl.plane_ddb_uv)); + + while ((plane = skl_next_plane_to_commit(state, crtc, + entries_y, entries_uv, + &update_mask))) { + struct intel_plane_state *new_plane_state = + intel_atomic_get_new_plane_state(state, plane); + if (new_plane_state->base.visible) { trace_intel_update_plane(&plane->base, crtc); - plane->update_plane(plane, new_crtc_state, new_plane_state); } else if (new_plane_state->slave) { struct intel_plane *master = @@ -204,15 +255,38 @@ void intel_update_planes_on_crtc(struct intel_atomic_state *old_state, * plane_state. */ new_plane_state = - intel_atomic_get_new_plane_state(old_state, master); + intel_atomic_get_new_plane_state(state, master); trace_intel_update_plane(&plane->base, crtc); - plane->update_slave(plane, new_crtc_state, new_plane_state); } else { trace_intel_disable_plane(&plane->base, crtc); + plane->disable_plane(plane, new_crtc_state); + } + } +} + +void i9xx_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + u32 update_mask = new_crtc_state->update_planes; + struct intel_plane_state *new_plane_state; + struct intel_plane *plane; + int i; - plane->disable_plane(plane, crtc); + for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) { + if (crtc->pipe != plane->pipe || + !(update_mask & BIT(plane->id))) + continue; + + if (new_plane_state->base.visible) { + trace_intel_update_plane(&plane->base, crtc); + plane->update_plane(plane, new_crtc_state, new_plane_state); + } else { + trace_intel_disable_plane(&plane->base, crtc); + plane->disable_plane(plane, new_crtc_state); } } } diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 0694aa8bb9bc..6d3e0260d49c 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -1752,7 +1752,7 @@ void intel_bios_init(struct drm_i915_private *dev_priv) const struct bdb_header *bdb; u8 __iomem *bios = NULL; - if (INTEL_INFO(dev_priv)->num_pipes == 0) { + if (!HAS_DISPLAY(dev_priv)) { DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n"); return; } diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 84bf8d827136..447c5256f63a 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -27,11 +27,7 @@ #include "i915_drv.h" -#ifdef CONFIG_SMP -#define task_asleep(tsk) ((tsk)->state & TASK_NORMAL && !(tsk)->on_cpu) -#else -#define task_asleep(tsk) ((tsk)->state & TASK_NORMAL) -#endif +#define task_asleep(tsk) ((tsk)->state & TASK_NORMAL && !(tsk)->on_rq) static unsigned int __intel_breadcrumbs_wakeup(struct intel_breadcrumbs *b) { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index ad11540ac436..f3e1d6a0b7dd 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -28,6 +28,7 @@ #include <drm/drm_scdc_helper.h> #include "i915_drv.h" #include "intel_drv.h" +#include "intel_dsi.h" struct ddi_buf_trans { u32 trans1; /* balance leg enable, de-emph level */ @@ -1363,8 +1364,8 @@ static int skl_calc_wrpll_link(struct drm_i915_private *dev_priv, return dco_freq / (p0 * p1 * p2 * 5); } -static int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv, - enum intel_dpll_id pll_id) +int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv, + enum intel_dpll_id pll_id) { uint32_t cfgcr0, cfgcr1; uint32_t p0, p1, p2, dco_freq, ref_clock; @@ -2154,6 +2155,12 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder, intel_port_is_tc(dev_priv, encoder->port)) domains |= BIT_ULL(intel_ddi_main_link_aux_domain(dig_port)); + /* + * VDSC power is needed when DSC is enabled + */ + if (crtc_state->dsc_params.compression_enable) + domains |= BIT_ULL(intel_dsc_power_domain(crtc_state)); + return domains; } @@ -2785,77 +2792,54 @@ uint32_t icl_dpclka_cfgcr0_clk_off(struct drm_i915_private *dev_priv, return 0; } -void icl_map_plls_to_ports(struct drm_crtc *crtc, - struct intel_crtc_state *crtc_state, - struct drm_atomic_state *old_state) +static void icl_map_plls_to_ports(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_shared_dpll *pll = crtc_state->shared_dpll; - struct drm_i915_private *dev_priv = to_i915(crtc->dev); - struct drm_connector_state *conn_state; - struct drm_connector *conn; - int i; - - for_each_new_connector_in_state(old_state, conn, conn_state, i) { - struct intel_encoder *encoder = - to_intel_encoder(conn_state->best_encoder); - enum port port; - uint32_t val; - - if (conn_state->crtc != crtc) - continue; - - port = encoder->port; - mutex_lock(&dev_priv->dpll_lock); + enum port port = encoder->port; + u32 val; - val = I915_READ(DPCLKA_CFGCR0_ICL); - WARN_ON((val & icl_dpclka_cfgcr0_clk_off(dev_priv, port)) == 0); + mutex_lock(&dev_priv->dpll_lock); - if (intel_port_is_combophy(dev_priv, port)) { - val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port); - val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port); - I915_WRITE(DPCLKA_CFGCR0_ICL, val); - POSTING_READ(DPCLKA_CFGCR0_ICL); - } + val = I915_READ(DPCLKA_CFGCR0_ICL); + WARN_ON((val & icl_dpclka_cfgcr0_clk_off(dev_priv, port)) == 0); - val &= ~icl_dpclka_cfgcr0_clk_off(dev_priv, port); + if (intel_port_is_combophy(dev_priv, port)) { + val &= ~DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port); + val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port); I915_WRITE(DPCLKA_CFGCR0_ICL, val); - - mutex_unlock(&dev_priv->dpll_lock); + POSTING_READ(DPCLKA_CFGCR0_ICL); } + + val &= ~icl_dpclka_cfgcr0_clk_off(dev_priv, port); + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + + mutex_unlock(&dev_priv->dpll_lock); } -void icl_unmap_plls_to_ports(struct drm_crtc *crtc, - struct intel_crtc_state *crtc_state, - struct drm_atomic_state *old_state) +static void icl_unmap_plls_to_ports(struct intel_encoder *encoder) { - struct drm_i915_private *dev_priv = to_i915(crtc->dev); - struct drm_connector_state *old_conn_state; - struct drm_connector *conn; - int i; + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum port port = encoder->port; + u32 val; - for_each_old_connector_in_state(old_state, conn, old_conn_state, i) { - struct intel_encoder *encoder = - to_intel_encoder(old_conn_state->best_encoder); - enum port port; + mutex_lock(&dev_priv->dpll_lock); - if (old_conn_state->crtc != crtc) - continue; + val = I915_READ(DPCLKA_CFGCR0_ICL); + val |= icl_dpclka_cfgcr0_clk_off(dev_priv, port); + I915_WRITE(DPCLKA_CFGCR0_ICL, val); - port = encoder->port; - mutex_lock(&dev_priv->dpll_lock); - I915_WRITE(DPCLKA_CFGCR0_ICL, - I915_READ(DPCLKA_CFGCR0_ICL) | - icl_dpclka_cfgcr0_clk_off(dev_priv, port)); - mutex_unlock(&dev_priv->dpll_lock); - } + mutex_unlock(&dev_priv->dpll_lock); } void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); u32 val; - enum port port = encoder->port; - bool clk_enabled; + enum port port; + u32 port_mask; + bool ddi_clk_needed; /* * In case of DP MST, we sanitize the primary encoder only, not the @@ -2864,9 +2848,6 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder) if (encoder->type == INTEL_OUTPUT_DP_MST) return; - val = I915_READ(DPCLKA_CFGCR0_ICL); - clk_enabled = !(val & icl_dpclka_cfgcr0_clk_off(dev_priv, port)); - if (!encoder->base.crtc && intel_encoder_is_dp(encoder)) { u8 pipe_mask; bool is_mst; @@ -2880,20 +2861,52 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder) return; } - if (clk_enabled == !!encoder->base.crtc) - return; + port_mask = BIT(encoder->port); + ddi_clk_needed = encoder->base.crtc; - /* - * Punt on the case now where clock is disabled, but the encoder is - * enabled, something else is really broken then. - */ - if (WARN_ON(!clk_enabled)) - return; + if (encoder->type == INTEL_OUTPUT_DSI) { + struct intel_encoder *other_encoder; - DRM_NOTE("Port %c is disabled but it has a mapped PLL, unmap it\n", - port_name(port)); - val |= icl_dpclka_cfgcr0_clk_off(dev_priv, port); - I915_WRITE(DPCLKA_CFGCR0_ICL, val); + port_mask = intel_dsi_encoder_ports(encoder); + /* + * Sanity check that we haven't incorrectly registered another + * encoder using any of the ports of this DSI encoder. + */ + for_each_intel_encoder(&dev_priv->drm, other_encoder) { + if (other_encoder == encoder) + continue; + + if (WARN_ON(port_mask & BIT(other_encoder->port))) + return; + } + /* + * DSI ports should have their DDI clock ungated when disabled + * and gated when enabled. + */ + ddi_clk_needed = !encoder->base.crtc; + } + + val = I915_READ(DPCLKA_CFGCR0_ICL); + for_each_port_masked(port, port_mask) { + bool ddi_clk_ungated = !(val & + icl_dpclka_cfgcr0_clk_off(dev_priv, + port)); + + if (ddi_clk_needed == ddi_clk_ungated) + continue; + + /* + * Punt on the case now where clock is gated, but it would + * be needed by the port. Something else is really broken then. + */ + if (WARN_ON(ddi_clk_needed)) + continue; + + DRM_NOTE("Port %c is disabled/in DSI mode with an ungated DDI clock, gate it\n", + port_name(port)); + val |= icl_dpclka_cfgcr0_clk_off(dev_priv, port); + I915_WRITE(DPCLKA_CFGCR0_ICL, val); + } } static void intel_ddi_clk_select(struct intel_encoder *encoder, @@ -3096,6 +3109,53 @@ static void icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port) I915_WRITE(MG_DP_MODE(port, 1), ln1); } +static void intel_dp_sink_set_fec_ready(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state) +{ + if (!crtc_state->fec_enable) + return; + + if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_FEC_CONFIGURATION, DP_FEC_READY) <= 0) + DRM_DEBUG_KMS("Failed to set FEC_READY in the sink\n"); +} + +static void intel_ddi_enable_fec(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum port port = encoder->port; + u32 val; + + if (!crtc_state->fec_enable) + return; + + val = I915_READ(DP_TP_CTL(port)); + val |= DP_TP_CTL_FEC_ENABLE; + I915_WRITE(DP_TP_CTL(port), val); + + if (intel_wait_for_register(dev_priv, DP_TP_STATUS(port), + DP_TP_STATUS_FEC_ENABLE_LIVE, + DP_TP_STATUS_FEC_ENABLE_LIVE, + 1)) + DRM_ERROR("Timed out waiting for FEC Enable Status\n"); +} + +static void intel_ddi_disable_fec_state(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum port port = encoder->port; + u32 val; + + if (!crtc_state->fec_enable) + return; + + val = I915_READ(DP_TP_CTL(port)); + val &= ~DP_TP_CTL_FEC_ENABLE; + I915_WRITE(DP_TP_CTL(port), val); + POSTING_READ(DP_TP_CTL(port)); +} + static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state) @@ -3134,14 +3194,21 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, intel_ddi_init_dp_buf_reg(encoder); if (!is_mst) intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON); + intel_dp_sink_set_decompression_state(intel_dp, crtc_state, + true); + intel_dp_sink_set_fec_ready(intel_dp, crtc_state); intel_dp_start_link_train(intel_dp); if (port != PORT_A || INTEL_GEN(dev_priv) >= 9) intel_dp_stop_link_train(intel_dp); + intel_ddi_enable_fec(encoder, crtc_state); + icl_enable_phy_clock_gating(dig_port); if (!is_mst) intel_ddi_enable_pipe_clock(crtc_state); + + intel_dsc_enable(encoder, crtc_state); } static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, @@ -3208,6 +3275,9 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder, WARN_ON(crtc_state->has_pch_encoder); + if (INTEL_GEN(dev_priv) >= 11) + icl_map_plls_to_ports(encoder, crtc_state); + intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { @@ -3228,7 +3298,8 @@ static void intel_ddi_pre_enable(struct intel_encoder *encoder, } } -static void intel_disable_ddi_buf(struct intel_encoder *encoder) +static void intel_disable_ddi_buf(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum port port = encoder->port; @@ -3247,6 +3318,9 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder) val |= DP_TP_CTL_LINK_TRAIN_PAT1; I915_WRITE(DP_TP_CTL(port), val); + /* Disable FEC in DP Sink */ + intel_ddi_disable_fec_state(encoder, crtc_state); + if (wait) intel_wait_ddi_buf_idle(dev_priv, port); } @@ -3270,7 +3344,7 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); } - intel_disable_ddi_buf(encoder); + intel_disable_ddi_buf(encoder, old_crtc_state); intel_edp_panel_vdd_on(intel_dp); intel_edp_panel_off(intel_dp); @@ -3293,7 +3367,7 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder, intel_ddi_disable_pipe_clock(old_crtc_state); - intel_disable_ddi_buf(encoder); + intel_disable_ddi_buf(encoder, old_crtc_state); intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain); @@ -3306,6 +3380,8 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder, const struct intel_crtc_state *old_crtc_state, const struct drm_connector_state *old_conn_state) { + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + /* * When called from DP MST code: * - old_conn_state will be NULL @@ -3325,6 +3401,9 @@ static void intel_ddi_post_disable(struct intel_encoder *encoder, else intel_ddi_post_disable_dp(encoder, old_crtc_state, old_conn_state); + + if (INTEL_GEN(dev_priv) >= 11) + icl_unmap_plls_to_ports(encoder); } void intel_ddi_fdi_post_disable(struct intel_encoder *encoder, @@ -3344,7 +3423,7 @@ void intel_ddi_fdi_post_disable(struct intel_encoder *encoder, val &= ~FDI_RX_ENABLE; I915_WRITE(FDI_RX_CTL(PIPE_A), val); - intel_disable_ddi_buf(encoder); + intel_disable_ddi_buf(encoder, old_crtc_state); intel_ddi_clk_disable(encoder); val = I915_READ(FDI_RX_MISC(PIPE_A)); @@ -3491,6 +3570,9 @@ static void intel_disable_ddi_dp(struct intel_encoder *encoder, intel_edp_drrs_disable(intel_dp, old_crtc_state); intel_psr_disable(intel_dp, old_crtc_state); intel_edp_backlight_off(old_conn_state); + /* Disable the decompression in DP Sink */ + intel_dp_sink_set_decompression_state(intel_dp, old_crtc_state, + false); } static void intel_disable_ddi_hdmi(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index ceecb5bd5226..1e56319334f3 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -77,6 +77,10 @@ void intel_device_info_dump_flags(const struct intel_device_info *info, #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->name)); DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG + +#define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, yesno(info->display.name)); + DEV_INFO_DISPLAY_FOR_EACH_FLAG(PRINT_FLAG); +#undef PRINT_FLAG } static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p) @@ -782,7 +786,7 @@ void intel_device_info_runtime_init(struct intel_device_info *info) if (i915_modparams.disable_display) { DRM_INFO("Display disabled (module parameter)\n"); info->num_pipes = 0; - } else if (info->num_pipes > 0 && + } else if (HAS_DISPLAY(dev_priv) && (IS_GEN7(dev_priv) || IS_GEN8(dev_priv)) && HAS_PCH_SPLIT(dev_priv)) { u32 fuse_strap = I915_READ(FUSE_STRAP); @@ -807,7 +811,7 @@ void intel_device_info_runtime_init(struct intel_device_info *info) DRM_INFO("PipeC fused off\n"); info->num_pipes -= 1; } - } else if (info->num_pipes > 0 && IS_GEN9(dev_priv)) { + } else if (HAS_DISPLAY(dev_priv) && IS_GEN9(dev_priv)) { u32 dfsm = I915_READ(SKL_DFSM); u8 disabled_mask = 0; bool invalid; diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 88f97210dc49..1caf24e2cf0b 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -89,35 +89,38 @@ enum intel_ppgtt { func(is_alpha_support); \ /* Keep has_* in alphabetical order */ \ func(has_64bit_reloc); \ - func(has_csr); \ - func(has_ddi); \ - func(has_dp_mst); \ func(has_reset_engine); \ - func(has_fbc); \ func(has_fpga_dbg); \ - func(has_gmch_display); \ func(has_guc); \ func(has_guc_ct); \ - func(has_hotplug); \ func(has_l3_dpf); \ func(has_llc); \ func(has_logical_ring_contexts); \ func(has_logical_ring_elsq); \ func(has_logical_ring_preemption); \ - func(has_overlay); \ func(has_pooled_eu); \ - func(has_psr); \ func(has_rc6); \ func(has_rc6p); \ func(has_runtime_pm); \ func(has_snoop); \ func(has_coherent_ggtt); \ func(unfenced_needs_alignment); \ + func(hws_needs_physical); + +#define DEV_INFO_DISPLAY_FOR_EACH_FLAG(func) \ + /* Keep in alphabetical order */ \ func(cursor_needs_physical); \ - func(hws_needs_physical); \ + func(has_csr); \ + func(has_ddi); \ + func(has_dp_mst); \ + func(has_fbc); \ + func(has_gmch_display); \ + func(has_hotplug); \ + func(has_ipc); \ + func(has_overlay); \ + func(has_psr); \ func(overlay_needs_physical); \ - func(supports_tv); \ - func(has_ipc); + func(supports_tv); #define GEN_MAX_SLICES (6) /* CNL upper bound */ #define GEN_MAX_SUBSLICES (8) /* ICL upper bound */ @@ -172,6 +175,13 @@ struct intel_device_info { #define DEFINE_FLAG(name) u8 name:1 DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG); #undef DEFINE_FLAG + + struct { +#define DEFINE_FLAG(name) u8 name:1 + DEV_INFO_DISPLAY_FOR_EACH_FLAG(DEFINE_FLAG); +#undef DEFINE_FLAG + } display; + u16 ddb_size; /* in blocks */ /* Register offsets for the various display pipes and transcoders */ diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 812ec5ae5c7b..07c861884c70 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2341,10 +2341,26 @@ static int intel_fb_offset_to_xy(int *x, int *y, int color_plane) { struct drm_i915_private *dev_priv = to_i915(fb->dev); + unsigned int height; if (fb->modifier != DRM_FORMAT_MOD_LINEAR && - fb->offsets[color_plane] % intel_tile_size(dev_priv)) + fb->offsets[color_plane] % intel_tile_size(dev_priv)) { + DRM_DEBUG_KMS("Misaligned offset 0x%08x for color plane %d\n", + fb->offsets[color_plane], color_plane); return -EINVAL; + } + + height = drm_framebuffer_plane_height(fb->height, fb, color_plane); + height = ALIGN(height, intel_tile_height(fb, color_plane)); + + /* Catch potential overflows early */ + if (add_overflows_t(u32, mul_u32_u32(height, fb->pitches[color_plane]), + fb->offsets[color_plane])) { + DRM_DEBUG_KMS("Bad offset 0x%08x or pitch %d for color plane %d\n", + fb->offsets[color_plane], fb->pitches[color_plane], + color_plane); + return -ERANGE; + } *x = 0; *y = 0; @@ -2767,7 +2783,7 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc, intel_pre_disable_primary_noatomic(&crtc->base); trace_intel_disable_plane(&plane->base, crtc); - plane->disable_plane(plane, crtc); + plane->disable_plane(plane, crtc_state); } static void @@ -3315,7 +3331,6 @@ static void i9xx_update_plane(struct intel_plane *plane, enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; u32 linear_offset; u32 dspcntr = plane_state->ctl; - i915_reg_t reg = DSPCNTR(i9xx_plane); int x = plane_state->color_plane[0].x; int y = plane_state->color_plane[0].y; unsigned long irqflags; @@ -3330,47 +3345,51 @@ static void i9xx_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + I915_WRITE_FW(DSPSTRIDE(i9xx_plane), plane_state->color_plane[0].stride); + if (INTEL_GEN(dev_priv) < 4) { /* pipesrc and dspsize control the size that is scaled from, * which should always be the user's requested size. */ + I915_WRITE_FW(DSPPOS(i9xx_plane), 0); I915_WRITE_FW(DSPSIZE(i9xx_plane), ((crtc_state->pipe_src_h - 1) << 16) | (crtc_state->pipe_src_w - 1)); - I915_WRITE_FW(DSPPOS(i9xx_plane), 0); } else if (IS_CHERRYVIEW(dev_priv) && i9xx_plane == PLANE_B) { + I915_WRITE_FW(PRIMPOS(i9xx_plane), 0); I915_WRITE_FW(PRIMSIZE(i9xx_plane), ((crtc_state->pipe_src_h - 1) << 16) | (crtc_state->pipe_src_w - 1)); - I915_WRITE_FW(PRIMPOS(i9xx_plane), 0); I915_WRITE_FW(PRIMCNSTALPHA(i9xx_plane), 0); } - I915_WRITE_FW(reg, dspcntr); - - I915_WRITE_FW(DSPSTRIDE(i9xx_plane), plane_state->color_plane[0].stride); if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { - I915_WRITE_FW(DSPSURF(i9xx_plane), - intel_plane_ggtt_offset(plane_state) + - dspaddr_offset); I915_WRITE_FW(DSPOFFSET(i9xx_plane), (y << 16) | x); } else if (INTEL_GEN(dev_priv) >= 4) { + I915_WRITE_FW(DSPLINOFF(i9xx_plane), linear_offset); + I915_WRITE_FW(DSPTILEOFF(i9xx_plane), (y << 16) | x); + } + + /* + * The control register self-arms if the plane was previously + * disabled. Try to make the plane enable atomic by writing + * the control register just before the surface register. + */ + I915_WRITE_FW(DSPCNTR(i9xx_plane), dspcntr); + if (INTEL_GEN(dev_priv) >= 4) I915_WRITE_FW(DSPSURF(i9xx_plane), intel_plane_ggtt_offset(plane_state) + dspaddr_offset); - I915_WRITE_FW(DSPTILEOFF(i9xx_plane), (y << 16) | x); - I915_WRITE_FW(DSPLINOFF(i9xx_plane), linear_offset); - } else { + else I915_WRITE_FW(DSPADDR(i9xx_plane), intel_plane_ggtt_offset(plane_state) + dspaddr_offset); - } spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void i9xx_disable_plane(struct intel_plane *plane, - struct intel_crtc *crtc) + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum i9xx_plane_id i9xx_plane = plane->i9xx_plane; @@ -3456,6 +3475,21 @@ static void skl_detach_scalers(const struct intel_crtc_state *crtc_state) } } +static unsigned int skl_plane_stride_mult(const struct drm_framebuffer *fb, + int color_plane, unsigned int rotation) +{ + /* + * The stride is either expressed as a multiple of 64 bytes chunks for + * linear buffers or in number of tiles for tiled buffers. + */ + if (fb->modifier == DRM_FORMAT_MOD_LINEAR) + return 64; + else if (drm_rotation_90_or_270(rotation)) + return intel_tile_height(fb, color_plane); + else + return intel_tile_width_bytes(fb, color_plane); +} + u32 skl_plane_stride(const struct intel_plane_state *plane_state, int color_plane) { @@ -3466,16 +3500,7 @@ u32 skl_plane_stride(const struct intel_plane_state *plane_state, if (color_plane >= fb->format->num_planes) return 0; - /* - * The stride is either expressed as a multiple of 64 bytes chunks for - * linear buffers or in number of tiles for tiled buffers. - */ - if (drm_rotation_90_or_270(rotation)) - stride /= intel_tile_height(fb, color_plane); - else - stride /= intel_fb_stride_alignment(fb, color_plane); - - return stride; + return stride / skl_plane_stride_mult(fb, color_plane, rotation); } static u32 skl_plane_ctl_format(uint32_t pixel_format) @@ -5403,23 +5428,32 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state, intel_update_watermarks(crtc); } -static void intel_crtc_disable_planes(struct intel_crtc *crtc, unsigned plane_mask) +static void intel_crtc_disable_planes(struct intel_atomic_state *state, + struct intel_crtc *crtc) { - struct drm_device *dev = crtc->base.dev; + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + const struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + unsigned int update_mask = new_crtc_state->update_planes; + const struct intel_plane_state *old_plane_state; struct intel_plane *plane; unsigned fb_bits = 0; + int i; intel_crtc_dpms_overlay_disable(crtc); - for_each_intel_plane_on_crtc(dev, crtc, plane) { - if (plane_mask & BIT(plane->id)) { - plane->disable_plane(plane, crtc); + for_each_old_intel_plane_in_state(state, plane, old_plane_state, i) { + if (crtc->pipe != plane->pipe || + !(update_mask & BIT(plane->id))) + continue; + plane->disable_plane(plane, new_crtc_state); + + if (old_plane_state->base.visible) fb_bits |= plane->frontbuffer_bit; - } } - intel_frontbuffer_flip(to_i915(dev), fb_bits); + intel_frontbuffer_flip(dev_priv, fb_bits); } static void intel_encoders_pre_pll_enable(struct drm_crtc *crtc, @@ -5692,9 +5726,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, if (pipe_config->shared_dpll) intel_enable_shared_dpll(pipe_config); - if (INTEL_GEN(dev_priv) >= 11) - icl_map_plls_to_ports(crtc, pipe_config, old_state); - intel_encoders_pre_enable(crtc, pipe_config, old_state); if (intel_crtc_has_dp_encoder(pipe_config)) @@ -5889,6 +5920,8 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, if (!transcoder_is_dsi(cpu_transcoder)) intel_ddi_disable_transcoder_func(old_crtc_state); + intel_dsc_disable(old_crtc_state); + if (INTEL_GEN(dev_priv) >= 9) skylake_scaler_disable(intel_crtc); else @@ -5896,9 +5929,6 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_encoders_post_disable(crtc, old_crtc_state, old_state); - if (INTEL_GEN(dev_priv) >= 11) - icl_unmap_plls_to_ports(crtc, old_crtc_state, old_state); - intel_encoders_post_pll_disable(crtc, old_crtc_state, old_state); } @@ -6724,7 +6754,7 @@ static void compute_m_n(unsigned int m, unsigned int n, } void -intel_link_compute_m_n(int bits_per_pixel, int nlanes, +intel_link_compute_m_n(u16 bits_per_pixel, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, bool constant_n) @@ -8939,7 +8969,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, fb->width = ((val >> 0) & 0x1fff) + 1; val = I915_READ(PLANE_STRIDE(pipe, plane_id)); - stride_mult = intel_fb_stride_alignment(fb, 0); + stride_mult = skl_plane_stride_mult(fb, 0, DRM_MODE_ROTATE_0); fb->pitches[0] = (val & 0x3ff) * stride_mult; aligned_height = intel_fb_align_height(fb, 0, fb->height); @@ -9303,10 +9333,12 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv) static int haswell_crtc_compute_clock(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state) { + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state); - if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) { + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI) || + IS_ICELAKE(dev_priv)) { struct intel_encoder *encoder = intel_get_crtc_new_encoder(state, crtc_state); @@ -9444,11 +9476,18 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); enum intel_display_power_domain power_domain; + unsigned long panel_transcoder_mask = BIT(TRANSCODER_EDP); + unsigned long enabled_panel_transcoders = 0; + enum transcoder panel_transcoder; u32 tmp; + if (IS_ICELAKE(dev_priv)) + panel_transcoder_mask |= + BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1); + /* * The pipe->transcoder mapping is fixed with the exception of the eDP - * transcoder handled below. + * and DSI transcoders handled below. */ pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; @@ -9456,29 +9495,49 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc, * XXX: Do intel_display_power_get_if_enabled before reading this (for * consistency and less surprising code; it's in always on power). */ - tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); - if (tmp & TRANS_DDI_FUNC_ENABLE) { - enum pipe trans_edp_pipe; + for_each_set_bit(panel_transcoder, &panel_transcoder_mask, 32) { + enum pipe trans_pipe; + + tmp = I915_READ(TRANS_DDI_FUNC_CTL(panel_transcoder)); + if (!(tmp & TRANS_DDI_FUNC_ENABLE)) + continue; + + /* + * Log all enabled ones, only use the first one. + * + * FIXME: This won't work for two separate DSI displays. + */ + enabled_panel_transcoders |= BIT(panel_transcoder); + if (enabled_panel_transcoders != BIT(panel_transcoder)) + continue; + switch (tmp & TRANS_DDI_EDP_INPUT_MASK) { default: - WARN(1, "unknown pipe linked to edp transcoder\n"); + WARN(1, "unknown pipe linked to transcoder %s\n", + transcoder_name(panel_transcoder)); /* fall through */ case TRANS_DDI_EDP_INPUT_A_ONOFF: case TRANS_DDI_EDP_INPUT_A_ON: - trans_edp_pipe = PIPE_A; + trans_pipe = PIPE_A; break; case TRANS_DDI_EDP_INPUT_B_ONOFF: - trans_edp_pipe = PIPE_B; + trans_pipe = PIPE_B; break; case TRANS_DDI_EDP_INPUT_C_ONOFF: - trans_edp_pipe = PIPE_C; + trans_pipe = PIPE_C; break; } - if (trans_edp_pipe == crtc->pipe) - pipe_config->cpu_transcoder = TRANSCODER_EDP; + if (trans_pipe == crtc->pipe) + pipe_config->cpu_transcoder = panel_transcoder; } + /* + * Valid combos: none, eDP, DSI0, DSI1, DSI0+DSI1 + */ + WARN_ON((enabled_panel_transcoders & BIT(TRANSCODER_EDP)) && + enabled_panel_transcoders != BIT(TRANSCODER_EDP)); + power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder); if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; @@ -9611,7 +9670,8 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, if (!active) goto out; - if (!transcoder_is_dsi(pipe_config->cpu_transcoder)) { + if (!transcoder_is_dsi(pipe_config->cpu_transcoder) || + IS_ICELAKE(dev_priv)) { haswell_get_ddi_port_state(crtc, pipe_config); intel_get_pipe_timings(crtc, pipe_config); } @@ -9667,7 +9727,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state) const struct drm_i915_gem_object *obj = intel_fb_obj(fb); u32 base; - if (INTEL_INFO(dev_priv)->cursor_needs_physical) + if (INTEL_INFO(dev_priv)->display.cursor_needs_physical) base = obj->phys_handle->busaddr; else base = intel_plane_ggtt_offset(plane_state); @@ -9894,9 +9954,9 @@ static void i845_update_cursor(struct intel_plane *plane, } static void i845_disable_cursor(struct intel_plane *plane, - struct intel_crtc *crtc) + const struct intel_crtc_state *crtc_state) { - i845_update_cursor(plane, NULL, NULL); + i845_update_cursor(plane, crtc_state, NULL); } static bool i845_cursor_get_hw_state(struct intel_plane *plane, @@ -10087,8 +10147,8 @@ static void i9xx_update_cursor(struct intel_plane *plane, * On some platforms writing CURCNTR first will also * cause CURPOS to be armed by the CURBASE write. * Without the CURCNTR write the CURPOS write would - * arm itself. Thus we always start the full update - * with a CURCNTR write. + * arm itself. Thus we always update CURCNTR before + * CURPOS. * * On other platforms CURPOS always requires the * CURBASE write to arm the update. Additonally @@ -10098,15 +10158,20 @@ static void i9xx_update_cursor(struct intel_plane *plane, * cursor that doesn't appear to move, or even change * shape. Thus we always write CURBASE. * - * CURCNTR and CUR_FBC_CTL are always - * armed by the CURBASE write only. + * The other registers are armed by by the CURBASE write + * except when the plane is getting enabled at which time + * the CURCNTR write arms the update. */ + + if (INTEL_GEN(dev_priv) >= 9) + skl_write_cursor_wm(plane, crtc_state); + if (plane->cursor.base != base || plane->cursor.size != fbc_ctl || plane->cursor.cntl != cntl) { - I915_WRITE_FW(CURCNTR(pipe), cntl); if (HAS_CUR_FBC(dev_priv)) I915_WRITE_FW(CUR_FBC_CTL(pipe), fbc_ctl); + I915_WRITE_FW(CURCNTR(pipe), cntl); I915_WRITE_FW(CURPOS(pipe), pos); I915_WRITE_FW(CURBASE(pipe), base); @@ -10122,9 +10187,9 @@ static void i9xx_update_cursor(struct intel_plane *plane, } static void i9xx_disable_cursor(struct intel_plane *plane, - struct intel_crtc *crtc) + const struct intel_crtc_state *crtc_state) { - i9xx_update_cursor(plane, NULL, NULL); + i9xx_update_cursor(plane, crtc_state, NULL); } static bool i9xx_cursor_get_hw_state(struct intel_plane *plane, @@ -10835,8 +10900,10 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) continue; plane_state->linked_plane = NULL; - if (plane_state->slave && !plane_state->base.visible) + if (plane_state->slave && !plane_state->base.visible) { crtc_state->active_planes &= ~BIT(plane->id); + crtc_state->update_planes |= BIT(plane->id); + } plane_state->slave = false; } @@ -10877,6 +10944,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) linked_state->slave = true; linked_state->linked_plane = plane; crtc_state->active_planes |= BIT(linked->id); + crtc_state->update_planes |= BIT(linked->id); DRM_DEBUG_KMS("Using %s as Y plane for %s\n", linked->base.name, plane->base.name); } @@ -11887,6 +11955,8 @@ static void verify_wm_state(struct drm_crtc *crtc, struct skl_pipe_wm hw_wm, *sw_wm; struct skl_plane_wm *hw_plane_wm, *sw_plane_wm; struct skl_ddb_entry *hw_ddb_entry, *sw_ddb_entry; + struct skl_ddb_entry hw_ddb_y[I915_MAX_PLANES]; + struct skl_ddb_entry hw_ddb_uv[I915_MAX_PLANES]; struct intel_crtc *intel_crtc = to_intel_crtc(crtc); const enum pipe pipe = intel_crtc->pipe; int plane, level, max_level = ilk_wm_max_level(dev_priv); @@ -11897,6 +11967,8 @@ static void verify_wm_state(struct drm_crtc *crtc, skl_pipe_wm_get_hw_state(crtc, &hw_wm); sw_wm = &to_intel_crtc_state(new_state)->wm.skl.optimal; + skl_pipe_ddb_get_hw_state(intel_crtc, hw_ddb_y, hw_ddb_uv); + skl_ddb_get_hw_state(dev_priv, &hw_ddb); sw_ddb = &dev_priv->wm.skl_hw.ddb; @@ -11939,8 +12011,8 @@ static void verify_wm_state(struct drm_crtc *crtc, } /* DDB */ - hw_ddb_entry = &hw_ddb.plane[pipe][plane]; - sw_ddb_entry = &sw_ddb->plane[pipe][plane]; + hw_ddb_entry = &hw_ddb_y[plane]; + sw_ddb_entry = &to_intel_crtc_state(new_state)->wm.skl.plane_ddb_y[plane]; if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) { DRM_ERROR("mismatch in DDB state pipe %c plane %d (expected (%u,%u), found (%u,%u))\n", @@ -11989,8 +12061,8 @@ static void verify_wm_state(struct drm_crtc *crtc, } /* DDB */ - hw_ddb_entry = &hw_ddb.plane[pipe][PLANE_CURSOR]; - sw_ddb_entry = &sw_ddb->plane[pipe][PLANE_CURSOR]; + hw_ddb_entry = &hw_ddb_y[PLANE_CURSOR]; + sw_ddb_entry = &to_intel_crtc_state(new_state)->wm.skl.plane_ddb_y[PLANE_CURSOR]; if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) { DRM_ERROR("mismatch in DDB state pipe %c cursor (expected (%u,%u), found (%u,%u))\n", @@ -12668,7 +12740,6 @@ static void intel_update_crtc(struct drm_crtc *crtc, struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_crtc_state *old_intel_cstate = to_intel_crtc_state(old_crtc_state); struct intel_crtc_state *pipe_config = to_intel_crtc_state(new_crtc_state); bool modeset = needs_modeset(new_crtc_state); struct intel_plane_state *new_plane_state = @@ -12691,8 +12762,10 @@ static void intel_update_crtc(struct drm_crtc *crtc, intel_begin_crtc_commit(crtc, old_crtc_state); - intel_update_planes_on_crtc(to_intel_atomic_state(state), intel_crtc, - old_intel_cstate, pipe_config); + if (INTEL_GEN(dev_priv) >= 9) + skl_update_planes_on_crtc(to_intel_atomic_state(state), intel_crtc); + else + i9xx_update_planes_on_crtc(to_intel_atomic_state(state), intel_crtc); intel_finish_crtc_commit(crtc, old_crtc_state); } @@ -12885,7 +12958,7 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_pre_plane_update(old_intel_crtc_state, new_intel_crtc_state); if (old_crtc_state->active) { - intel_crtc_disable_planes(intel_crtc, old_intel_crtc_state->active_planes); + intel_crtc_disable_planes(intel_state, intel_crtc); /* * We need to disable pipe CRC before disabling the pipe, @@ -13240,7 +13313,7 @@ static int intel_plane_pin_fb(struct intel_plane_state *plane_state) struct i915_vma *vma; if (plane->id == PLANE_CURSOR && - INTEL_INFO(dev_priv)->cursor_needs_physical) { + INTEL_INFO(dev_priv)->display.cursor_needs_physical) { struct drm_i915_gem_object *obj = intel_fb_obj(fb); const int align = intel_cursor_alignment(dev_priv); int err; @@ -13735,7 +13808,7 @@ intel_legacy_cursor_update(struct drm_plane *plane, to_intel_plane_state(plane->state)); } else { trace_intel_disable_plane(plane, to_intel_crtc(crtc)); - intel_plane->disable_plane(intel_plane, to_intel_crtc(crtc)); + intel_plane->disable_plane(intel_plane, crtc_state); } intel_plane_unpin_fb(to_intel_plane_state(old_plane_state)); @@ -14186,7 +14259,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) intel_pps_init(dev_priv); - if (INTEL_INFO(dev_priv)->num_pipes == 0) + if (!HAS_DISPLAY(dev_priv)) return; /* @@ -14451,7 +14524,6 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, { struct drm_i915_private *dev_priv = to_i915(obj->base.dev); struct drm_framebuffer *fb = &intel_fb->base; - struct drm_format_name_buf format_name; u32 pitch_limit; unsigned int tiling, stride; int ret = -EINVAL; @@ -14482,39 +14554,14 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, } } - /* Passed in modifier sanity checking. */ - switch (mode_cmd->modifier[0]) { - case I915_FORMAT_MOD_Y_TILED_CCS: - case I915_FORMAT_MOD_Yf_TILED_CCS: - switch (mode_cmd->pixel_format) { - case DRM_FORMAT_XBGR8888: - case DRM_FORMAT_ABGR8888: - case DRM_FORMAT_XRGB8888: - case DRM_FORMAT_ARGB8888: - break; - default: - DRM_DEBUG_KMS("RC supported only with RGB8888 formats\n"); - goto err; - } - /* fall through */ - case I915_FORMAT_MOD_Yf_TILED: - if (mode_cmd->pixel_format == DRM_FORMAT_C8) { - DRM_DEBUG_KMS("Indexed format does not support Yf tiling\n"); - goto err; - } - /* fall through */ - case I915_FORMAT_MOD_Y_TILED: - if (INTEL_GEN(dev_priv) < 9) { - DRM_DEBUG_KMS("Unsupported tiling 0x%llx!\n", - mode_cmd->modifier[0]); - goto err; - } - break; - case DRM_FORMAT_MOD_LINEAR: - case I915_FORMAT_MOD_X_TILED: - break; - default: - DRM_DEBUG_KMS("Unsupported fb modifier 0x%llx!\n", + if (!drm_any_plane_has_format(&dev_priv->drm, + mode_cmd->pixel_format, + mode_cmd->modifier[0])) { + struct drm_format_name_buf format_name; + + DRM_DEBUG_KMS("unsupported pixel format %s / modifier 0x%llx\n", + drm_get_format_name(mode_cmd->pixel_format, + &format_name), mode_cmd->modifier[0]); goto err; } @@ -14549,69 +14596,6 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, goto err; } - /* Reject formats not supported by any plane early. */ - switch (mode_cmd->pixel_format) { - case DRM_FORMAT_C8: - case DRM_FORMAT_RGB565: - case DRM_FORMAT_XRGB8888: - case DRM_FORMAT_ARGB8888: - break; - case DRM_FORMAT_XRGB1555: - if (INTEL_GEN(dev_priv) > 3) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - break; - case DRM_FORMAT_ABGR8888: - if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv) && - INTEL_GEN(dev_priv) < 9) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - break; - case DRM_FORMAT_XBGR8888: - case DRM_FORMAT_XRGB2101010: - case DRM_FORMAT_XBGR2101010: - if (INTEL_GEN(dev_priv) < 4) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - break; - case DRM_FORMAT_ABGR2101010: - if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - break; - case DRM_FORMAT_YUYV: - case DRM_FORMAT_UYVY: - case DRM_FORMAT_YVYU: - case DRM_FORMAT_VYUY: - if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - break; - case DRM_FORMAT_NV12: - if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) || - IS_BROXTON(dev_priv)) { - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, - &format_name)); - goto err; - } - break; - default: - DRM_DEBUG_KMS("unsupported pixel format: %s\n", - drm_get_format_name(mode_cmd->pixel_format, &format_name)); - goto err; - } - /* FIXME need to adjust LINOFF/TILEOFF accordingly. */ if (mode_cmd->offsets[0] != 0) goto err; @@ -16066,7 +16050,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv) }; int i; - if (INTEL_INFO(dev_priv)->num_pipes == 0) + if (!HAS_DISPLAY(dev_priv)) return NULL; error = kzalloc(sizeof(*error), GFP_ATOMIC); diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h index 5f2955b944da..4262452963b3 100644 --- a/drivers/gpu/drm/i915/intel_display.h +++ b/drivers/gpu/drm/i915/intel_display.h @@ -242,6 +242,7 @@ enum intel_display_power_domain { POWER_DOMAIN_TRANSCODER_B, POWER_DOMAIN_TRANSCODER_C, POWER_DOMAIN_TRANSCODER_EDP, + POWER_DOMAIN_TRANSCODER_EDP_VDSC, POWER_DOMAIN_TRANSCODER_DSI_A, POWER_DOMAIN_TRANSCODER_DSI_C, POWER_DOMAIN_PORT_DDI_A_LANES, @@ -398,6 +399,14 @@ struct intel_link_m_n { for_each_power_well_reverse(__dev_priv, __power_well) \ for_each_if((__power_well)->desc->domains & (__domain_mask)) +#define for_each_old_intel_plane_in_state(__state, plane, old_plane_state, __i) \ + for ((__i) = 0; \ + (__i) < (__state)->base.dev->mode_config.num_total_plane && \ + ((plane) = to_intel_plane((__state)->base.planes[__i].ptr), \ + (old_plane_state) = to_intel_plane_state((__state)->base.planes[__i].old_state), 1); \ + (__i)++) \ + for_each_if(plane) + #define for_each_new_intel_plane_in_state(__state, plane, new_plane_state, __i) \ for ((__i) = 0; \ (__i) < (__state)->base.dev->mode_config.num_total_plane && \ @@ -423,10 +432,18 @@ struct intel_link_m_n { (__i)++) \ for_each_if(plane) -void intel_link_compute_m_n(int bpp, int nlanes, +#define for_each_oldnew_intel_crtc_in_state(__state, crtc, old_crtc_state, new_crtc_state, __i) \ + for ((__i) = 0; \ + (__i) < (__state)->base.dev->mode_config.num_crtc && \ + ((crtc) = to_intel_crtc((__state)->base.crtcs[__i].ptr), \ + (old_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].old_state), \ + (new_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].new_state), 1); \ + (__i)++) \ + for_each_if(crtc) + +void intel_link_compute_m_n(u16 bpp, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, bool constant_n); - bool is_ccs_modifier(u64 modifier); #endif diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 7699f9b7b2d2..fdd2cbc56fa3 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -47,6 +47,8 @@ /* DP DSC small joiner has 2 FIFOs each of 640 x 6 bytes */ #define DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER 61440 +#define DP_DSC_MIN_SUPPORTED_BPC 8 +#define DP_DSC_MAX_SUPPORTED_BPC 10 /* DP DSC throughput values used for slice count calculations KPixels/s */ #define DP_DSC_PEAK_PIXEL_RATE 2720000 @@ -543,7 +545,7 @@ intel_dp_mode_valid(struct drm_connector *connector, dsc_slice_count = drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, true); - } else { + } else if (drm_dp_sink_supports_fec(intel_dp->fec_capable)) { dsc_max_output_bpp = intel_dp_dsc_get_output_bpp(max_link_clock, max_lanes, @@ -1708,6 +1710,41 @@ struct link_config_limits { int min_bpp, max_bpp; }; +static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return INTEL_GEN(dev_priv) >= 11 && + pipe_config->cpu_transcoder != TRANSCODER_A; +} + +static bool intel_dp_supports_fec(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config) +{ + return intel_dp_source_supports_fec(intel_dp, pipe_config) && + drm_dp_sink_supports_fec(intel_dp->fec_capable); +} + +static bool intel_dp_source_supports_dsc(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return INTEL_GEN(dev_priv) >= 10 && + pipe_config->cpu_transcoder != TRANSCODER_A; +} + +static bool intel_dp_supports_dsc(struct intel_dp *intel_dp, + const struct intel_crtc_state *pipe_config) +{ + if (!intel_dp_is_edp(intel_dp) && !pipe_config->fec_enable) + return false; + + return intel_dp_source_supports_dsc(intel_dp, pipe_config) && + drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd); +} + static int intel_dp_compute_bpp(struct intel_dp *intel_dp, struct intel_crtc_state *pipe_config) { @@ -1842,14 +1879,122 @@ intel_dp_compute_link_config_fast(struct intel_dp *intel_dp, return false; } +static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc) +{ + int i, num_bpc; + u8 dsc_bpc[3] = {0}; + + num_bpc = drm_dp_dsc_sink_supported_input_bpcs(intel_dp->dsc_dpcd, + dsc_bpc); + for (i = 0; i < num_bpc; i++) { + if (dsc_max_bpc >= dsc_bpc[i]) + return dsc_bpc[i] * 3; + } + + return 0; +} + +static bool intel_dp_dsc_compute_config(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config, + struct drm_connector_state *conn_state, + struct link_config_limits *limits) +{ + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); + struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; + u8 dsc_max_bpc; + int pipe_bpp; + + if (!intel_dp_supports_dsc(intel_dp, pipe_config)) + return false; + + dsc_max_bpc = min_t(u8, DP_DSC_MAX_SUPPORTED_BPC, + conn_state->max_requested_bpc); + + pipe_bpp = intel_dp_dsc_compute_bpp(intel_dp, dsc_max_bpc); + if (pipe_bpp < DP_DSC_MIN_SUPPORTED_BPC * 3) { + DRM_DEBUG_KMS("No DSC support for less than 8bpc\n"); + return false; + } + + /* + * For now enable DSC for max bpp, max link rate, max lane count. + * Optimize this later for the minimum possible link rate/lane count + * with DSC enabled for the requested mode. + */ + pipe_config->pipe_bpp = pipe_bpp; + pipe_config->port_clock = intel_dp->common_rates[limits->max_clock]; + pipe_config->lane_count = limits->max_lane_count; + + if (intel_dp_is_edp(intel_dp)) { + pipe_config->dsc_params.compressed_bpp = + min_t(u16, drm_edp_dsc_sink_output_bpp(intel_dp->dsc_dpcd) >> 4, + pipe_config->pipe_bpp); + pipe_config->dsc_params.slice_count = + drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd, + true); + } else { + u16 dsc_max_output_bpp; + u8 dsc_dp_slice_count; + + dsc_max_output_bpp = + intel_dp_dsc_get_output_bpp(pipe_config->port_clock, + pipe_config->lane_count, + adjusted_mode->crtc_clock, + adjusted_mode->crtc_hdisplay); + dsc_dp_slice_count = + intel_dp_dsc_get_slice_count(intel_dp, + adjusted_mode->crtc_clock, + adjusted_mode->crtc_hdisplay); + if (!dsc_max_output_bpp || !dsc_dp_slice_count) { + DRM_DEBUG_KMS("Compressed BPP/Slice Count not supported\n"); + return false; + } + pipe_config->dsc_params.compressed_bpp = min_t(u16, + dsc_max_output_bpp >> 4, + pipe_config->pipe_bpp); + pipe_config->dsc_params.slice_count = dsc_dp_slice_count; + } + /* + * VDSC engine operates at 1 Pixel per clock, so if peak pixel rate + * is greater than the maximum Cdclock and if slice count is even + * then we need to use 2 VDSC instances. + */ + if (adjusted_mode->crtc_clock > dev_priv->max_cdclk_freq) { + if (pipe_config->dsc_params.slice_count > 1) { + pipe_config->dsc_params.dsc_split = true; + } else { + DRM_DEBUG_KMS("Cannot split stream to use 2 VDSC instances\n"); + return false; + } + } + if (intel_dp_compute_dsc_params(intel_dp, pipe_config) < 0) { + DRM_DEBUG_KMS("Cannot compute valid DSC parameters for Input Bpp = %d " + "Compressed BPP = %d\n", + pipe_config->pipe_bpp, + pipe_config->dsc_params.compressed_bpp); + return false; + } + pipe_config->dsc_params.compression_enable = true; + DRM_DEBUG_KMS("DP DSC computed with Input Bpp = %d " + "Compressed Bpp = %d Slice Count = %d\n", + pipe_config->pipe_bpp, + pipe_config->dsc_params.compressed_bpp, + pipe_config->dsc_params.slice_count); + + return true; +} + static bool intel_dp_compute_link_config(struct intel_encoder *encoder, - struct intel_crtc_state *pipe_config) + struct intel_crtc_state *pipe_config, + struct drm_connector_state *conn_state) { struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode; struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); struct link_config_limits limits; int common_len; + bool ret; common_len = intel_dp_common_len_rate_limit(intel_dp, intel_dp->max_link_rate); @@ -1888,7 +2033,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, intel_dp->common_rates[limits.max_clock], limits.max_bpp, adjusted_mode->crtc_clock); - if (intel_dp_is_edp(intel_dp)) { + if (intel_dp_is_edp(intel_dp)) /* * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4 * section A.1: "It is recommended that the minimum number of @@ -1898,26 +2043,42 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, * Note that we use the max clock and lane count for eDP 1.3 and * earlier, and fast vs. wide is irrelevant. */ - if (!intel_dp_compute_link_config_fast(intel_dp, pipe_config, - &limits)) - return false; - } else { + ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config, + &limits); + else /* Optimize for slow and wide. */ - if (!intel_dp_compute_link_config_wide(intel_dp, pipe_config, - &limits)) + ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, + &limits); + + /* enable compression if the mode doesn't fit available BW */ + if (!ret) { + if (!intel_dp_dsc_compute_config(intel_dp, pipe_config, + conn_state, &limits)) return false; } - DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n", - pipe_config->lane_count, pipe_config->port_clock, - pipe_config->pipe_bpp); + if (pipe_config->dsc_params.compression_enable) { + DRM_DEBUG_KMS("DP lane count %d clock %d Input bpp %d Compressed bpp %d\n", + pipe_config->lane_count, pipe_config->port_clock, + pipe_config->pipe_bpp, + pipe_config->dsc_params.compressed_bpp); - DRM_DEBUG_KMS("DP link rate required %i available %i\n", - intel_dp_link_required(adjusted_mode->crtc_clock, - pipe_config->pipe_bpp), - intel_dp_max_data_rate(pipe_config->port_clock, - pipe_config->lane_count)); + DRM_DEBUG_KMS("DP link rate required %i available %i\n", + intel_dp_link_required(adjusted_mode->crtc_clock, + pipe_config->dsc_params.compressed_bpp), + intel_dp_max_data_rate(pipe_config->port_clock, + pipe_config->lane_count)); + } else { + DRM_DEBUG_KMS("DP lane count %d clock %d bpp %d\n", + pipe_config->lane_count, pipe_config->port_clock, + pipe_config->pipe_bpp); + DRM_DEBUG_KMS("DP link rate required %i available %i\n", + intel_dp_link_required(adjusted_mode->crtc_clock, + pipe_config->pipe_bpp), + intel_dp_max_data_rate(pipe_config->port_clock, + pipe_config->lane_count)); + } return true; } @@ -1983,7 +2144,10 @@ intel_dp_compute_config(struct intel_encoder *encoder, if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) return false; - if (!intel_dp_compute_link_config(encoder, pipe_config)) + pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) && + intel_dp_supports_fec(intel_dp, pipe_config); + + if (!intel_dp_compute_link_config(encoder, pipe_config, conn_state)) return false; if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) { @@ -2001,11 +2165,20 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED; } - intel_link_compute_m_n(pipe_config->pipe_bpp, pipe_config->lane_count, - adjusted_mode->crtc_clock, - pipe_config->port_clock, - &pipe_config->dp_m_n, - constant_n); + if (!pipe_config->dsc_params.compression_enable) + intel_link_compute_m_n(pipe_config->pipe_bpp, + pipe_config->lane_count, + adjusted_mode->crtc_clock, + pipe_config->port_clock, + &pipe_config->dp_m_n, + constant_n); + else + intel_link_compute_m_n(pipe_config->dsc_params.compressed_bpp, + pipe_config->lane_count, + adjusted_mode->crtc_clock, + pipe_config->port_clock, + &pipe_config->dp_m_n, + constant_n); if (intel_connector->panel.downclock_mode != NULL && dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) { @@ -2702,6 +2875,22 @@ static bool downstream_hpd_needs_d0(struct intel_dp *intel_dp) intel_dp->downstream_ports[0] & DP_DS_PORT_HPD; } +void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + bool enable) +{ + int ret; + + if (!crtc_state->dsc_params.compression_enable) + return; + + ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_DSC_ENABLE, + enable ? DP_DECOMPRESSION_EN : 0); + if (ret < 0) + DRM_DEBUG_KMS("Failed to %s sink decompression state\n", + enable ? "enable" : "disable"); +} + /* If the sink supports it, try to set the power state appropriately */ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode) { @@ -3837,15 +4026,14 @@ static void intel_dp_get_dsc_sink_cap(struct intel_dp *intel_dp) DRM_DEBUG_KMS("DSC DPCD: %*ph\n", (int)sizeof(intel_dp->dsc_dpcd), intel_dp->dsc_dpcd); + /* FEC is supported only on DP 1.4 */ - if (!intel_dp_is_edp(intel_dp)) { - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_FEC_CAPABILITY, - &intel_dp->fec_capable) < 0) - DRM_ERROR("Failed to read FEC DPCD register\n"); + if (!intel_dp_is_edp(intel_dp) && + drm_dp_dpcd_readb(&intel_dp->aux, DP_FEC_CAPABILITY, + &intel_dp->fec_capable) < 0) + DRM_ERROR("Failed to read FEC DPCD register\n"); - DRM_DEBUG_KMS("FEC CAPABILITY: %x\n", - intel_dp->fec_capable); - } + DRM_DEBUG_KMS("FEC CAPABILITY: %x\n", intel_dp->fec_capable); } } @@ -3936,8 +4124,6 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp) static bool intel_dp_get_dpcd(struct intel_dp *intel_dp) { - u8 sink_count; - if (!intel_dp_read_dpcd(intel_dp)) return false; @@ -3947,25 +4133,35 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) intel_dp_set_common_rates(intel_dp); } - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_COUNT, &sink_count) <= 0) - return false; - /* - * Sink count can change between short pulse hpd hence - * a member variable in intel_dp will track any changes - * between short pulse interrupts. + * Some eDP panels do not set a valid value for sink count, that is why + * it don't care about read it here and in intel_edp_init_dpcd(). */ - intel_dp->sink_count = DP_GET_SINK_COUNT(sink_count); + if (!intel_dp_is_edp(intel_dp)) { + u8 count; + ssize_t r; - /* - * SINK_COUNT == 0 and DOWNSTREAM_PORT_PRESENT == 1 implies that - * a dongle is present but no display. Unless we require to know - * if a dongle is present or not, we don't need to update - * downstream port information. So, an early return here saves - * time from performing other operations which are not required. - */ - if (!intel_dp_is_edp(intel_dp) && !intel_dp->sink_count) - return false; + r = drm_dp_dpcd_readb(&intel_dp->aux, DP_SINK_COUNT, &count); + if (r < 1) + return false; + + /* + * Sink count can change between short pulse hpd hence + * a member variable in intel_dp will track any changes + * between short pulse interrupts. + */ + intel_dp->sink_count = DP_GET_SINK_COUNT(count); + + /* + * SINK_COUNT == 0 and DOWNSTREAM_PORT_PRESENT == 1 implies that + * a dongle is present but no display. Unless we require to know + * if a dongle is present or not, we don't need to update + * downstream port information. So, an early return here saves + * time from performing other operations which are not required. + */ + if (!intel_dp->sink_count) + return false; + } if (!drm_dp_is_branch(intel_dp->dpcd)) return true; /* native DP sink */ @@ -4375,6 +4571,17 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp) if (!intel_dp->link_trained) return false; + /* + * While PSR source HW is enabled, it will control main-link sending + * frames, enabling and disabling it so trying to do a retrain will fail + * as the link would or not be on or it could mix training patterns + * and frame data at the same time causing retrain to fail. + * Also when exiting PSR, HW will retrain the link anyways fixing + * any link status error. + */ + if (intel_psr_enabled(intel_dp)) + return false; + if (!intel_dp_get_link_status(intel_dp, link_status)) return false; diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index 901e15063b24..d513ca875c67 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -2523,7 +2523,8 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state, if (intel_port_is_tc(dev_priv, encoder->port)) ret = icl_calc_tbt_pll(dev_priv, clock, &pll_params); - else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) || + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) ret = cnl_ddi_calculate_wrpll(clock, dev_priv, &pll_params); else ret = icl_calc_dp_combo_pll(dev_priv, clock, &pll_params); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index a7d9ac912125..f94a04b4ad87 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -706,6 +706,8 @@ struct intel_crtc_wm_state { /* gen9+ only needs 1-step wm programming */ struct skl_pipe_wm optimal; struct skl_ddb_entry ddb; + struct skl_ddb_entry plane_ddb_y[I915_MAX_PLANES]; + struct skl_ddb_entry plane_ddb_uv[I915_MAX_PLANES]; } skl; struct { @@ -926,6 +928,9 @@ struct intel_crtc_state { u8 active_planes; u8 nv12_planes; + /* bitmask of planes that will be updated during the commit */ + u8 update_planes; + /* HDMI scrambling status */ bool hdmi_scrambling; @@ -937,6 +942,18 @@ struct intel_crtc_state { /* Output down scaling is done in LSPCON device */ bool lspcon_downsampling; + + /* Display Stream compression state */ + struct { + bool compression_enable; + bool dsc_split; + u16 compressed_bpp; + u8 slice_count; + } dsc_params; + struct drm_dsc_config dp_dsc_cfg; + + /* Forward Error correction State */ + bool fec_enable; }; struct intel_crtc { @@ -1013,7 +1030,7 @@ struct intel_plane { const struct intel_crtc_state *crtc_state, const struct intel_plane_state *plane_state); void (*disable_plane)(struct intel_plane *plane, - struct intel_crtc *crtc); + const struct intel_crtc_state *crtc_state); bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe); int (*check_plane)(struct intel_crtc_state *crtc_state, struct intel_plane_state *plane_state); @@ -1517,13 +1534,9 @@ u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder, u8 voltage_swing); int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, bool enable); -void icl_map_plls_to_ports(struct drm_crtc *crtc, - struct intel_crtc_state *crtc_state, - struct drm_atomic_state *old_state); -void icl_unmap_plls_to_ports(struct drm_crtc *crtc, - struct intel_crtc_state *crtc_state, - struct drm_atomic_state *old_state); void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder); +int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv, + enum intel_dpll_id pll_id); unsigned int intel_fb_align_height(const struct drm_framebuffer *fb, int color_plane, unsigned int height); @@ -1788,6 +1801,9 @@ void intel_dp_stop_link_train(struct intel_dp *intel_dp); int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp, + const struct intel_crtc_state *crtc_state, + bool enable); void intel_dp_encoder_reset(struct drm_encoder *encoder); void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); @@ -1843,6 +1859,12 @@ uint16_t intel_dp_dsc_get_output_bpp(int link_clock, uint8_t lane_count, uint8_t intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock, int mode_hdisplay); +/* intel_vdsc.c */ +int intel_dp_compute_dsc_params(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config); +enum intel_display_power_domain +intel_dsc_power_domain(const struct intel_crtc_state *crtc_state); + static inline unsigned int intel_dp_unused_lane_mask(int lane_count) { return ~((1 << lane_count) - 1) & 0xf; @@ -2047,6 +2069,7 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir); void intel_psr_short_pulse(struct intel_dp *intel_dp); int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state, u32 *out_value); +bool intel_psr_enabled(struct intel_dp *intel_dp); /* intel_quirks.c */ void intel_init_quirks(struct drm_i915_private *dev_priv); @@ -2181,6 +2204,9 @@ void g4x_wm_get_hw_state(struct drm_device *dev); void vlv_wm_get_hw_state(struct drm_device *dev); void ilk_wm_get_hw_state(struct drm_device *dev); void skl_wm_get_hw_state(struct drm_device *dev); +void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc, + struct skl_ddb_entry *ddb_y, + struct skl_ddb_entry *ddb_uv); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc, @@ -2195,6 +2221,10 @@ bool skl_wm_level_equals(const struct skl_wm_level *l1, bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, const struct skl_ddb_entry entries[], int num_entries, int ignore_idx); +void skl_write_plane_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); +void skl_write_cursor_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); bool ilk_disable_lp_wm(struct drm_device *dev); int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc, struct intel_crtc_state *cstate); @@ -2287,10 +2317,10 @@ struct drm_plane_state *intel_plane_duplicate_state(struct drm_plane *plane); void intel_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *state); extern const struct drm_plane_helper_funcs intel_plane_helper_funcs; -void intel_update_planes_on_crtc(struct intel_atomic_state *old_state, - struct intel_crtc *crtc, - struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state); +void skl_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); +void i9xx_update_planes_on_crtc(struct intel_atomic_state *state, + struct intel_crtc *crtc); int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state, struct intel_crtc_state *crtc_state, const struct intel_plane_state *old_plane_state, diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h index ee93137f4433..d968f1f13e09 100644 --- a/drivers/gpu/drm/i915/intel_dsi.h +++ b/drivers/gpu/drm/i915/intel_dsi.h @@ -146,6 +146,11 @@ static inline bool is_cmd_mode(struct intel_dsi *intel_dsi) return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE; } +static inline u16 intel_dsi_encoder_ports(struct intel_encoder *encoder) +{ + return enc_to_intel_dsi(&encoder->base)->ports; +} + /* intel_dsi.c */ int intel_dsi_bitrate(const struct intel_dsi *intel_dsi); int intel_dsi_tlpx_ns(const struct intel_dsi *intel_dsi); diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c index a72de81f4832..a1a8b3790e61 100644 --- a/drivers/gpu/drm/i915/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c @@ -103,6 +103,18 @@ static struct gpio_map vlv_gpio_table[] = { #define CHV_GPIO_PAD_CFG1(f, i) (0x4400 + (f) * 0x400 + (i) * 8 + 4) #define CHV_GPIO_CFGLOCK (1 << 31) +/* ICL DSI Display GPIO Pins */ +#define ICL_GPIO_DDSP_HPD_A 0 +#define ICL_GPIO_L_VDDEN_1 1 +#define ICL_GPIO_L_BKLTEN_1 2 +#define ICL_GPIO_DDPA_CTRLCLK_1 3 +#define ICL_GPIO_DDPA_CTRLDATA_1 4 +#define ICL_GPIO_DDSP_HPD_B 5 +#define ICL_GPIO_L_VDDEN_2 6 +#define ICL_GPIO_L_BKLTEN_2 7 +#define ICL_GPIO_DDPA_CTRLCLK_2 8 +#define ICL_GPIO_DDPA_CTRLDATA_2 9 + static inline enum port intel_dsi_seq_port_to_port(u8 port) { return port ? PORT_C : PORT_A; @@ -324,6 +336,12 @@ static void bxt_exec_gpio(struct drm_i915_private *dev_priv, gpiod_set_value(gpio_desc, value); } +static void icl_exec_gpio(struct drm_i915_private *dev_priv, + u8 gpio_source, u8 gpio_index, bool value) +{ + DRM_DEBUG_KMS("Skipping ICL GPIO element execution\n"); +} + static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) { struct drm_device *dev = intel_dsi->base.base.dev; @@ -347,7 +365,9 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) /* pull up/down */ value = *data++ & 1; - if (IS_VALLEYVIEW(dev_priv)) + if (IS_ICELAKE(dev_priv)) + icl_exec_gpio(dev_priv, gpio_source, gpio_index, value); + else if (IS_VALLEYVIEW(dev_priv)) vlv_exec_gpio(dev_priv, gpio_source, gpio_number, value); else if (IS_CHERRYVIEW(dev_priv)) chv_exec_gpio(dev_priv, gpio_source, gpio_number, value); diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 759c0fd58f8c..af2873403009 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -493,46 +493,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine) intel_engine_init_cmd_parser(engine); } -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size) -{ - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - int ret; - - WARN_ON(engine->scratch); - - obj = i915_gem_object_create_stolen(engine->i915, size); - if (!obj) - obj = i915_gem_object_create_internal(engine->i915, size); - if (IS_ERR(obj)) { - DRM_ERROR("Failed to allocate scratch page\n"); - return PTR_ERR(obj); - } - - vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unref; - } - - ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); - if (ret) - goto err_unref; - - engine->scratch = vma; - return 0; - -err_unref: - i915_gem_object_put(obj); - return ret; -} - -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine) -{ - i915_vma_unpin_and_release(&engine->scratch, 0); -} - static void cleanup_status_page(struct intel_engine_cs *engine) { if (HWS_NEEDS_PHYSICAL(engine->i915)) { @@ -707,8 +667,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - intel_engine_cleanup_scratch(engine); - cleanup_status_page(engine); intel_engine_fini_breadcrumbs(engine); @@ -723,6 +681,10 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) __intel_context_unpin(i915->kernel_context, engine); i915_timeline_fini(&engine->timeline); + + intel_wa_list_free(&engine->ctx_wa_list); + intel_wa_list_free(&engine->wa_list); + intel_wa_list_free(&engine->whitelist); } u64 intel_engine_get_active_head(const struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 14cbaf4a0e93..f23570c44323 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -1309,7 +1309,7 @@ void intel_fbc_init(struct drm_i915_private *dev_priv) fbc->active = false; if (need_fbc_vtd_wa(dev_priv)) - mkwrite_device_info(dev_priv)->has_fbc = false; + mkwrite_device_info(dev_priv)->display.has_fbc = false; i915_modparams.enable_fbc = intel_sanitize_fbc_option(dev_priv); DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 2480c7d6edee..fb5bb5b32a60 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -672,7 +672,7 @@ int intel_fbdev_init(struct drm_device *dev) struct intel_fbdev *ifbdev; int ret; - if (WARN_ON(INTEL_INFO(dev_priv)->num_pipes == 0)) + if (WARN_ON(!HAS_DISPLAY(dev_priv))) return -ENODEV; ifbdev = kzalloc(sizeof(struct intel_fbdev), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index e2c6a2b3e8f2..07e803a604bd 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -115,6 +115,8 @@ static u32 hsw_infoframe_enable(unsigned int type) switch (type) { case DP_SDP_VSC: return VIDEO_DIP_ENABLE_VSC_HSW; + case DP_SDP_PPS: + return VDIP_ENABLE_PPS; case HDMI_INFOFRAME_TYPE_AVI: return VIDEO_DIP_ENABLE_AVI_HSW; case HDMI_INFOFRAME_TYPE_SPD: @@ -136,6 +138,8 @@ hsw_dip_data_reg(struct drm_i915_private *dev_priv, switch (type) { case DP_SDP_VSC: return HSW_TVIDEO_DIP_VSC_DATA(cpu_transcoder, i); + case DP_SDP_PPS: + return ICL_VIDEO_DIP_PPS_DATA(cpu_transcoder, i); case HDMI_INFOFRAME_TYPE_AVI: return HSW_TVIDEO_DIP_AVI_DATA(cpu_transcoder, i); case HDMI_INFOFRAME_TYPE_SPD: @@ -148,6 +152,18 @@ hsw_dip_data_reg(struct drm_i915_private *dev_priv, } } +static int hsw_dip_data_size(unsigned int type) +{ + switch (type) { + case DP_SDP_VSC: + return VIDEO_DIP_VSC_DATA_SIZE; + case DP_SDP_PPS: + return VIDEO_DIP_PPS_DATA_SIZE; + default: + return VIDEO_DIP_DATA_SIZE; + } +} + static void g4x_write_infoframe(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state, unsigned int type, @@ -382,11 +398,12 @@ static void hsw_write_infoframe(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; i915_reg_t ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder); - int data_size = type == DP_SDP_VSC ? - VIDEO_DIP_VSC_DATA_SIZE : VIDEO_DIP_DATA_SIZE; + int data_size; int i; u32 val = I915_READ(ctl_reg); + data_size = hsw_dip_data_size(type); + val &= ~hsw_infoframe_enable(type); I915_WRITE(ctl_reg, val); diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 33d87ab93fdd..802d0394ccc4 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -817,7 +817,7 @@ int intel_setup_gmbus(struct drm_i915_private *dev_priv) unsigned int pin; int ret; - if (INTEL_INFO(dev_priv)->num_pipes == 0) + if (!HAS_DISPLAY(dev_priv)) return 0; if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 08fd9b12e4d7..d7fa301b5ec7 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -767,6 +767,8 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) static void reset_csb_pointers(struct intel_engine_execlists *execlists) { + const unsigned int reset_value = GEN8_CSB_ENTRIES - 1; + /* * After a reset, the HW starts writing into CSB entry [0]. We * therefore have to set our HEAD pointer back one entry so that @@ -776,8 +778,8 @@ static void reset_csb_pointers(struct intel_engine_execlists *execlists) * inline comparison of our cached head position against the last HW * write works even before the first interrupt. */ - execlists->csb_head = execlists->csb_write_reset; - WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset); + execlists->csb_head = reset_value; + WRITE_ONCE(*execlists->csb_write, reset_value); } static void nop_submission_tasklet(unsigned long data) @@ -818,8 +820,11 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) /* Mark all executing requests as skipped. */ list_for_each_entry(rq, &engine->timeline.requests, link) { GEM_BUG_ON(!rq->global_seqno); - if (!i915_request_completed(rq)) - dma_fence_set_error(&rq->fence, -EIO); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) + continue; + + dma_fence_set_error(&rq->fence, -EIO); } /* Flush the queued requests to the timeline list (for retiring). */ @@ -839,6 +844,10 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine) kmem_cache_free(engine->i915->priorities, p); } + intel_write_status_page(engine, + I915_GEM_HWS_INDEX, + intel_engine_last_submit(engine)); + /* Remaining _unready_ requests will be nop'ed when submitted */ execlists->queue_priority = INT_MIN; @@ -1279,9 +1288,10 @@ static int execlists_request_alloc(struct i915_request *request) static u32 * gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) { + /* NB no one else is allowed to scribble over scratch + 256! */ *batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; *batch++ = MI_LOAD_REGISTER_IMM(1); @@ -1295,7 +1305,7 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; return batch; @@ -1332,7 +1342,7 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) + + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES); *batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -1401,18 +1411,6 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) batch = emit_lri(batch, lri, ARRAY_SIZE(lri)); - /* WaClearSlmSpaceAtContextSwitch:kbl */ - /* Actual scratch location is at 128 bytes offset */ - if (IS_KBL_REVID(engine->i915, 0, KBL_REVID_A0)) { - batch = gen8_emit_pipe_control(batch, - PIPE_CONTROL_FLUSH_L3 | - PIPE_CONTROL_GLOBAL_GTT_IVB | - PIPE_CONTROL_CS_STALL | - PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) - + 2 * CACHELINE_BYTES); - } - /* WaMediaPoolStateCmdInWABB:bxt,glk */ if (HAS_POOLED_EU(engine->i915)) { /* @@ -1629,6 +1627,8 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine) static int gen8_init_common_ring(struct intel_engine_cs *engine) { + intel_engine_apply_workarounds(engine); + intel_mocs_init_engine(engine); intel_engine_reset_breadcrumbs(engine); @@ -1653,7 +1653,7 @@ static int gen8_init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - intel_whitelist_workarounds_apply(engine); + intel_engine_apply_whitelist(engine); /* We need to disable the AsyncFlip performance optimisations in order * to use MI_WAIT_FOR_EVENT within the CS. It should already be @@ -1676,7 +1676,7 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - intel_whitelist_workarounds_apply(engine); + intel_engine_apply_whitelist(engine); return 0; } @@ -1974,7 +1974,7 @@ static int gen8_emit_flush_render(struct i915_request *request, { struct intel_engine_cs *engine = request->engine; u32 scratch_addr = - i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES; + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES; bool vf_flush_wa = false, dc_flush_wa = false; u32 *cs, flags = 0; int len; @@ -2088,7 +2088,7 @@ static int gen8_init_rcs_context(struct i915_request *rq) { int ret; - ret = intel_ctx_workarounds_emit(rq); + ret = intel_engine_emit_ctx_wa(rq); if (ret) return ret; @@ -2229,12 +2229,6 @@ logical_ring_setup(struct intel_engine_cs *engine) logical_ring_default_irqs(engine); } -static bool csb_force_mmio(struct drm_i915_private *i915) -{ - /* Older GVT emulation depends upon intercepting CSB mmio */ - return intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915); -} - static int logical_ring_init(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; @@ -2264,24 +2258,12 @@ static int logical_ring_init(struct intel_engine_cs *engine) upper_32_bits(ce->lrc_desc); } - execlists->csb_read = - i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)); - if (csb_force_mmio(i915)) { - execlists->csb_status = (u32 __force *) - (i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0))); + execlists->csb_status = + &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX]; - execlists->csb_write = (u32 __force *)execlists->csb_read; - execlists->csb_write_reset = - _MASKED_FIELD(GEN8_CSB_WRITE_PTR_MASK, - GEN8_CSB_ENTRIES - 1); - } else { - execlists->csb_status = - &engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX]; + execlists->csb_write = + &engine->status_page.page_addr[intel_hws_csb_write_index(i915)]; - execlists->csb_write = - &engine->status_page.page_addr[intel_hws_csb_write_index(i915)]; - execlists->csb_write_reset = GEN8_CSB_ENTRIES - 1; - } reset_csb_pointers(execlists); return 0; @@ -2311,10 +2293,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_engine_create_scratch(engine, PAGE_SIZE); - if (ret) - goto err_cleanup_common; - ret = intel_init_workaround_bb(engine); if (ret) { /* @@ -2326,11 +2304,10 @@ int logical_render_ring_init(struct intel_engine_cs *engine) ret); } - return 0; + intel_engine_init_whitelist(engine); + intel_engine_init_workarounds(engine); -err_cleanup_common: - intel_engine_cleanup_common(engine); - return ret; + return 0; } int logical_xcs_ring_init(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_opregion.h b/drivers/gpu/drm/i915/intel_opregion.h index d84b6d2d2fae..4aa68ffbd30e 100644 --- a/drivers/gpu/drm/i915/intel_opregion.h +++ b/drivers/gpu/drm/i915/intel_opregion.h @@ -87,12 +87,12 @@ static inline void intel_opregion_unregister(struct drm_i915_private *dev_priv) { } -void intel_opregion_resume(struct drm_i915_private *dev_priv) +static inline void intel_opregion_resume(struct drm_i915_private *dev_priv) { } -void intel_opregion_suspend(struct drm_i915_private *dev_priv, - pci_power_t state) +static inline void intel_opregion_suspend(struct drm_i915_private *dev_priv, + pci_power_t state) { } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 897a791662c5..a26b4eddda25 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3951,68 +3951,68 @@ static void skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv, const enum pipe pipe, const enum plane_id plane_id, - struct skl_ddb_allocation *ddb /* out */) + struct skl_ddb_entry *ddb_y, + struct skl_ddb_entry *ddb_uv) { - u32 val, val2 = 0; - int fourcc, pixel_format; + u32 val, val2; + u32 fourcc = 0; /* Cursor doesn't support NV12/planar, so no extra calculation needed */ if (plane_id == PLANE_CURSOR) { val = I915_READ(CUR_BUF_CFG(pipe)); - skl_ddb_entry_init_from_hw(dev_priv, - &ddb->plane[pipe][plane_id], val); + skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val); return; } val = I915_READ(PLANE_CTL(pipe, plane_id)); /* No DDB allocated for disabled planes */ - if (!(val & PLANE_CTL_ENABLE)) - return; - - pixel_format = val & PLANE_CTL_FORMAT_MASK; - fourcc = skl_format_to_fourcc(pixel_format, - val & PLANE_CTL_ORDER_RGBX, - val & PLANE_CTL_ALPHA_MASK); + if (val & PLANE_CTL_ENABLE) + fourcc = skl_format_to_fourcc(val & PLANE_CTL_FORMAT_MASK, + val & PLANE_CTL_ORDER_RGBX, + val & PLANE_CTL_ALPHA_MASK); - val = I915_READ(PLANE_BUF_CFG(pipe, plane_id)); - if (fourcc == DRM_FORMAT_NV12 && INTEL_GEN(dev_priv) < 11) { + if (INTEL_GEN(dev_priv) >= 11) { + val = I915_READ(PLANE_BUF_CFG(pipe, plane_id)); + skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val); + } else { + val = I915_READ(PLANE_BUF_CFG(pipe, plane_id)); val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id)); - skl_ddb_entry_init_from_hw(dev_priv, - &ddb->plane[pipe][plane_id], val2); - skl_ddb_entry_init_from_hw(dev_priv, - &ddb->uv_plane[pipe][plane_id], val); - } else { - skl_ddb_entry_init_from_hw(dev_priv, - &ddb->plane[pipe][plane_id], val); + if (fourcc == DRM_FORMAT_NV12) + swap(val, val2); + + skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val); + skl_ddb_entry_init_from_hw(dev_priv, ddb_uv, val2); } } -void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, - struct skl_ddb_allocation *ddb /* out */) +void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc, + struct skl_ddb_entry *ddb_y, + struct skl_ddb_entry *ddb_uv) { - struct intel_crtc *crtc; - - memset(ddb, 0, sizeof(*ddb)); - - ddb->enabled_slices = intel_enabled_dbuf_slices_num(dev_priv); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum intel_display_power_domain power_domain; + enum pipe pipe = crtc->pipe; + enum plane_id plane_id; - for_each_intel_crtc(&dev_priv->drm, crtc) { - enum intel_display_power_domain power_domain; - enum plane_id plane_id; - enum pipe pipe = crtc->pipe; + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + return; - power_domain = POWER_DOMAIN_PIPE(pipe); - if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) - continue; + for_each_plane_id_on_crtc(crtc, plane_id) + skl_ddb_get_hw_plane_state(dev_priv, pipe, + plane_id, + &ddb_y[plane_id], + &ddb_uv[plane_id]); - for_each_plane_id_on_crtc(crtc, plane_id) - skl_ddb_get_hw_plane_state(dev_priv, pipe, - plane_id, ddb); + intel_display_power_put(dev_priv, power_domain); +} - intel_display_power_put(dev_priv, power_domain); - } +void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, + struct skl_ddb_allocation *ddb /* out */) +{ + ddb->enabled_slices = intel_enabled_dbuf_slices_num(dev_priv); } /* @@ -4410,7 +4410,6 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, struct drm_crtc *crtc = cstate->base.crtc; struct drm_i915_private *dev_priv = to_i915(crtc->dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum pipe pipe = intel_crtc->pipe; struct skl_ddb_entry *alloc = &cstate->wm.skl.ddb; uint16_t alloc_size, start; uint16_t minimum[I915_MAX_PLANES] = {}; @@ -4423,8 +4422,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, uint16_t total_min_blocks = 0; /* Clear the partitioning for disabled planes. */ - memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); - memset(ddb->uv_plane[pipe], 0, sizeof(ddb->uv_plane[pipe])); + memset(cstate->wm.skl.plane_ddb_y, 0, sizeof(cstate->wm.skl.plane_ddb_y)); + memset(cstate->wm.skl.plane_ddb_uv, 0, sizeof(cstate->wm.skl.plane_ddb_uv)); if (WARN_ON(!state)) return 0; @@ -4471,8 +4470,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, } alloc_size -= total_min_blocks; - ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR]; - ddb->plane[pipe][PLANE_CURSOR].end = alloc->end; + cstate->wm.skl.plane_ddb_y[PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR]; + cstate->wm.skl.plane_ddb_y[PLANE_CURSOR].end = alloc->end; /* * 2. Distribute the remaining space in proportion to the amount of @@ -4503,8 +4502,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, /* Leave disabled planes at (0,0) */ if (data_rate) { - ddb->plane[pipe][plane_id].start = start; - ddb->plane[pipe][plane_id].end = start + plane_blocks; + cstate->wm.skl.plane_ddb_y[plane_id].start = start; + cstate->wm.skl.plane_ddb_y[plane_id].end = start + plane_blocks; } start += plane_blocks; @@ -4519,8 +4518,8 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, WARN_ON(INTEL_GEN(dev_priv) >= 11 && uv_plane_blocks); if (uv_data_rate) { - ddb->uv_plane[pipe][plane_id].start = start; - ddb->uv_plane[pipe][plane_id].end = + cstate->wm.skl.plane_ddb_uv[plane_id].start = start; + cstate->wm.skl.plane_ddb_uv[plane_id].end = start + uv_plane_blocks; } @@ -4617,12 +4616,12 @@ skl_adjusted_plane_pixel_rate(const struct intel_crtc_state *cstate, } static int -skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv, - const struct intel_crtc_state *cstate, +skl_compute_plane_wm_params(const struct intel_crtc_state *cstate, const struct intel_plane_state *intel_pstate, - struct skl_wm_params *wp, int plane_id) + struct skl_wm_params *wp, int color_plane) { struct intel_plane *plane = to_intel_plane(intel_pstate->base.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); const struct drm_plane_state *pstate = &intel_pstate->base; const struct drm_framebuffer *fb = pstate->fb; uint32_t interm_pbpl; @@ -4630,11 +4629,8 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv, to_intel_atomic_state(cstate->base.state); bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state); - if (!intel_wm_plane_visible(cstate, intel_pstate)) - return 0; - /* only NV12 format has two planes */ - if (plane_id == 1 && fb->format->format != DRM_FORMAT_NV12) { + if (color_plane == 1 && fb->format->format != DRM_FORMAT_NV12) { DRM_DEBUG_KMS("Non NV12 format have single plane\n"); return -EINVAL; } @@ -4659,10 +4655,10 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv, wp->width = drm_rect_width(&intel_pstate->base.src) >> 16; } - if (plane_id == 1 && wp->is_planar) + if (color_plane == 1 && wp->is_planar) wp->width /= 2; - wp->cpp = fb->format->cpp[plane_id]; + wp->cpp = fb->format->cpp[color_plane]; wp->plane_pixel_rate = skl_adjusted_plane_pixel_rate(cstate, intel_pstate); @@ -4724,8 +4720,7 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv, return 0; } -static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, - const struct intel_crtc_state *cstate, +static int skl_compute_plane_wm(const struct intel_crtc_state *cstate, const struct intel_plane_state *intel_pstate, uint16_t ddb_allocation, int level, @@ -4733,6 +4728,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, const struct skl_wm_level *result_prev, struct skl_wm_level *result /* out */) { + struct drm_i915_private *dev_priv = + to_i915(intel_pstate->base.plane->dev); const struct drm_plane_state *pstate = &intel_pstate->base; uint32_t latency = dev_priv->wm.skl_latency[level]; uint_fixed_16_16_t method1, method2; @@ -4743,11 +4740,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state); uint32_t min_disp_buf_needed; - if (latency == 0 || - !intel_wm_plane_visible(cstate, intel_pstate)) { - result->plane_en = false; - return 0; - } + if (latency == 0) + return level == 0 ? -EINVAL : 0; /* Display WA #1141: kbl,cfl */ if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) || @@ -4844,8 +4838,6 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, if ((level > 0 && res_lines > 31) || res_blocks >= ddb_allocation || min_disp_buf_needed >= ddb_allocation) { - result->plane_en = false; - /* * If there are no valid level 0 watermarks, then we can't * support this display configuration. @@ -4872,27 +4864,22 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, } static int -skl_compute_wm_levels(const struct drm_i915_private *dev_priv, - struct skl_ddb_allocation *ddb, - const struct intel_crtc_state *cstate, +skl_compute_wm_levels(const struct intel_crtc_state *cstate, const struct intel_plane_state *intel_pstate, uint16_t ddb_blocks, const struct skl_wm_params *wm_params, - struct skl_plane_wm *wm, struct skl_wm_level *levels) { + struct drm_i915_private *dev_priv = + to_i915(intel_pstate->base.plane->dev); int level, max_level = ilk_wm_max_level(dev_priv); struct skl_wm_level *result_prev = &levels[0]; int ret; - if (WARN_ON(!intel_pstate->base.fb)) - return -EINVAL; - for (level = 0; level <= max_level; level++) { struct skl_wm_level *result = &levels[level]; - ret = skl_compute_plane_wm(dev_priv, - cstate, + ret = skl_compute_plane_wm(cstate, intel_pstate, ddb_blocks, level, @@ -4905,9 +4892,6 @@ skl_compute_wm_levels(const struct drm_i915_private *dev_priv, result_prev = result; } - if (intel_pstate->base.fb->format->format == DRM_FORMAT_NV12) - wm->is_planar = true; - return 0; } @@ -4935,10 +4919,9 @@ skl_compute_linetime_wm(const struct intel_crtc_state *cstate) } static void skl_compute_transition_wm(const struct intel_crtc_state *cstate, - struct skl_wm_params *wp, - struct skl_wm_level *wm_l0, - uint16_t ddb_allocation, - struct skl_wm_level *trans_wm /* out */) + const struct skl_wm_params *wp, + struct skl_plane_wm *wm, + uint16_t ddb_allocation) { struct drm_device *dev = cstate->base.crtc->dev; const struct drm_i915_private *dev_priv = to_i915(dev); @@ -4946,16 +4929,13 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *cstate, const uint16_t trans_amount = 10; /* This is configurable amount */ uint16_t wm0_sel_res_b, trans_offset_b, res_blocks; - if (!cstate->base.active) - goto exit; - /* Transition WM are not recommended by HW team for GEN9 */ if (INTEL_GEN(dev_priv) <= 9) - goto exit; + return; /* Transition WM don't make any sense if ipc is disabled */ if (!dev_priv->ipc_enabled) - goto exit; + return; trans_min = 14; if (INTEL_GEN(dev_priv) >= 11) @@ -4973,7 +4953,7 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *cstate, * Result Blocks is Result Blocks minus 1 and it should work for the * current platforms. */ - wm0_sel_res_b = wm_l0->plane_res_b - 1; + wm0_sel_res_b = wm->wm[0].plane_res_b - 1; if (wp->y_tiled) { trans_y_tile_min = (uint16_t) mul_round_up_u32_fixed16(2, @@ -4992,107 +4972,129 @@ static void skl_compute_transition_wm(const struct intel_crtc_state *cstate, res_blocks += 1; if (res_blocks < ddb_allocation) { - trans_wm->plane_res_b = res_blocks; - trans_wm->plane_en = true; - return; + wm->trans_wm.plane_res_b = res_blocks; + wm->trans_wm.plane_en = true; } - -exit: - trans_wm->plane_en = false; } -static int __skl_build_plane_wm_single(struct skl_ddb_allocation *ddb, - struct skl_pipe_wm *pipe_wm, - enum plane_id plane_id, - const struct intel_crtc_state *cstate, - const struct intel_plane_state *pstate, - int color_plane) +static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + enum plane_id plane_id, int color_plane) { - struct drm_i915_private *dev_priv = to_i915(pstate->base.plane->dev); - struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; - enum pipe pipe = to_intel_plane(pstate->base.plane)->pipe; + struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id]; + u16 ddb_blocks = skl_ddb_entry_size(&crtc_state->wm.skl.plane_ddb_y[plane_id]); struct skl_wm_params wm_params; - uint16_t ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][plane_id]); int ret; - ret = skl_compute_plane_wm_params(dev_priv, cstate, pstate, + ret = skl_compute_plane_wm_params(crtc_state, plane_state, &wm_params, color_plane); if (ret) return ret; - ret = skl_compute_wm_levels(dev_priv, ddb, cstate, pstate, - ddb_blocks, &wm_params, wm, wm->wm); - + ret = skl_compute_wm_levels(crtc_state, plane_state, + ddb_blocks, &wm_params, wm->wm); if (ret) return ret; - skl_compute_transition_wm(cstate, &wm_params, &wm->wm[0], - ddb_blocks, &wm->trans_wm); + skl_compute_transition_wm(crtc_state, &wm_params, wm, ddb_blocks); return 0; } -static int skl_build_plane_wm_single(struct skl_ddb_allocation *ddb, - struct skl_pipe_wm *pipe_wm, - const struct intel_crtc_state *cstate, - const struct intel_plane_state *pstate) -{ - enum plane_id plane_id = to_intel_plane(pstate->base.plane)->id; - - return __skl_build_plane_wm_single(ddb, pipe_wm, plane_id, cstate, pstate, 0); -} - -static int skl_build_plane_wm_planar(struct skl_ddb_allocation *ddb, - struct skl_pipe_wm *pipe_wm, - const struct intel_crtc_state *cstate, - const struct intel_plane_state *pstate) +static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + enum plane_id plane_id) { - struct intel_plane *plane = to_intel_plane(pstate->base.plane); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - enum plane_id plane_id = plane->id; - struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id]; + u16 ddb_blocks = skl_ddb_entry_size(&crtc_state->wm.skl.plane_ddb_uv[plane_id]); struct skl_wm_params wm_params; - enum pipe pipe = plane->pipe; - uint16_t ddb_blocks = skl_ddb_entry_size(&ddb->plane[pipe][plane_id]); int ret; - ret = __skl_build_plane_wm_single(ddb, pipe_wm, plane_id, cstate, pstate, 0); - if (ret) - return ret; + wm->is_planar = true; /* uv plane watermarks must also be validated for NV12/Planar */ - ddb_blocks = skl_ddb_entry_size(&ddb->uv_plane[pipe][plane_id]); + ret = skl_compute_plane_wm_params(crtc_state, plane_state, + &wm_params, 1); + if (ret) + return ret; - ret = skl_compute_plane_wm_params(dev_priv, cstate, pstate, &wm_params, 1); + ret = skl_compute_wm_levels(crtc_state, plane_state, + ddb_blocks, &wm_params, wm->uv_wm); if (ret) return ret; - return skl_compute_wm_levels(dev_priv, ddb, cstate, pstate, - ddb_blocks, &wm_params, wm, wm->uv_wm); + return 0; } -static int icl_build_plane_wm_planar(struct skl_ddb_allocation *ddb, - struct skl_pipe_wm *pipe_wm, - const struct intel_crtc_state *cstate, - const struct intel_plane_state *pstate) +static int skl_build_plane_wm(struct skl_pipe_wm *pipe_wm, + struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { + struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + const struct drm_framebuffer *fb = plane_state->base.fb; + enum plane_id plane_id = plane->id; int ret; - enum plane_id y_plane_id = pstate->linked_plane->id; - enum plane_id uv_plane_id = to_intel_plane(pstate->base.plane)->id; - ret = __skl_build_plane_wm_single(ddb, pipe_wm, y_plane_id, - cstate, pstate, 0); + if (!intel_wm_plane_visible(crtc_state, plane_state)) + return 0; + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane_id, 0); if (ret) return ret; - return __skl_build_plane_wm_single(ddb, pipe_wm, uv_plane_id, - cstate, pstate, 1); + if (fb->format->is_yuv && fb->format->num_planes > 1) { + ret = skl_build_plane_wm_uv(crtc_state, plane_state, + plane_id); + if (ret) + return ret; + } + + return 0; +} + +static int icl_build_plane_wm(struct skl_pipe_wm *pipe_wm, + struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + enum plane_id plane_id = to_intel_plane(plane_state->base.plane)->id; + int ret; + + /* Watermarks calculated in master */ + if (plane_state->slave) + return 0; + + if (plane_state->linked_plane) { + const struct drm_framebuffer *fb = plane_state->base.fb; + enum plane_id y_plane_id = plane_state->linked_plane->id; + + WARN_ON(!intel_wm_plane_visible(crtc_state, plane_state)); + WARN_ON(!fb->format->is_yuv || + fb->format->num_planes == 1); + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + y_plane_id, 0); + if (ret) + return ret; + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane_id, 1); + if (ret) + return ret; + } else if (intel_wm_plane_visible(crtc_state, plane_state)) { + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane_id, 0); + if (ret) + return ret; + } + + return 0; } static int skl_build_pipe_wm(struct intel_crtc_state *cstate, - struct skl_ddb_allocation *ddb, struct skl_pipe_wm *pipe_wm) { + struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev); struct drm_crtc_state *crtc_state = &cstate->base; struct drm_plane *plane; const struct drm_plane_state *pstate; @@ -5108,18 +5110,12 @@ static int skl_build_pipe_wm(struct intel_crtc_state *cstate, const struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate); - /* Watermarks calculated in master */ - if (intel_pstate->slave) - continue; - - if (intel_pstate->linked_plane) - ret = icl_build_plane_wm_planar(ddb, pipe_wm, cstate, intel_pstate); - else if (intel_pstate->base.fb && - intel_pstate->base.fb->format->format == DRM_FORMAT_NV12) - ret = skl_build_plane_wm_planar(ddb, pipe_wm, cstate, intel_pstate); + if (INTEL_GEN(dev_priv) >= 11) + ret = icl_build_plane_wm(pipe_wm, + cstate, intel_pstate); else - ret = skl_build_plane_wm_single(ddb, pipe_wm, cstate, intel_pstate); - + ret = skl_build_plane_wm(pipe_wm, + cstate, intel_pstate); if (ret) return ret; } @@ -5134,9 +5130,9 @@ static void skl_ddb_entry_write(struct drm_i915_private *dev_priv, const struct skl_ddb_entry *entry) { if (entry->end) - I915_WRITE(reg, (entry->end - 1) << 16 | entry->start); + I915_WRITE_FW(reg, (entry->end - 1) << 16 | entry->start); else - I915_WRITE(reg, 0); + I915_WRITE_FW(reg, 0); } static void skl_write_wm_level(struct drm_i915_private *dev_priv, @@ -5151,19 +5147,22 @@ static void skl_write_wm_level(struct drm_i915_private *dev_priv, val |= level->plane_res_l << PLANE_WM_LINES_SHIFT; } - I915_WRITE(reg, val); + I915_WRITE_FW(reg, val); } -static void skl_write_plane_wm(struct intel_crtc *intel_crtc, - const struct skl_plane_wm *wm, - const struct skl_ddb_allocation *ddb, - enum plane_id plane_id) +void skl_write_plane_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = &intel_crtc->base; - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); int level, max_level = ilk_wm_max_level(dev_priv); - enum pipe pipe = intel_crtc->pipe; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + const struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + const struct skl_ddb_entry *ddb_uv = + &crtc_state->wm.skl.plane_ddb_uv[plane_id]; for (level = 0; level <= max_level; level++) { skl_write_wm_level(dev_priv, PLANE_WM(pipe, plane_id, level), @@ -5172,29 +5171,32 @@ static void skl_write_plane_wm(struct intel_crtc *intel_crtc, skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id), &wm->trans_wm); - if (wm->is_planar && INTEL_GEN(dev_priv) < 11) { - skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id), - &ddb->uv_plane[pipe][plane_id]); + if (INTEL_GEN(dev_priv) >= 11) { skl_ddb_entry_write(dev_priv, - PLANE_NV12_BUF_CFG(pipe, plane_id), - &ddb->plane[pipe][plane_id]); - } else { - skl_ddb_entry_write(dev_priv, PLANE_BUF_CFG(pipe, plane_id), - &ddb->plane[pipe][plane_id]); - if (INTEL_GEN(dev_priv) < 11) - I915_WRITE(PLANE_NV12_BUF_CFG(pipe, plane_id), 0x0); + PLANE_BUF_CFG(pipe, plane_id), ddb_y); + return; } + + if (wm->is_planar) + swap(ddb_y, ddb_uv); + + skl_ddb_entry_write(dev_priv, + PLANE_BUF_CFG(pipe, plane_id), ddb_y); + skl_ddb_entry_write(dev_priv, + PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_uv); } -static void skl_write_cursor_wm(struct intel_crtc *intel_crtc, - const struct skl_plane_wm *wm, - const struct skl_ddb_allocation *ddb) +void skl_write_cursor_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = &intel_crtc->base; - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); int level, max_level = ilk_wm_max_level(dev_priv); - enum pipe pipe = intel_crtc->pipe; + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; for (level = 0; level <= max_level; level++) { skl_write_wm_level(dev_priv, CUR_WM(pipe, level), @@ -5202,22 +5204,30 @@ static void skl_write_cursor_wm(struct intel_crtc *intel_crtc, } skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), &wm->trans_wm); - skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), - &ddb->plane[pipe][PLANE_CURSOR]); + skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), ddb); } bool skl_wm_level_equals(const struct skl_wm_level *l1, const struct skl_wm_level *l2) { - if (l1->plane_en != l2->plane_en) - return false; + return l1->plane_en == l2->plane_en && + l1->plane_res_l == l2->plane_res_l && + l1->plane_res_b == l2->plane_res_b; +} - /* If both planes aren't enabled, the rest shouldn't matter */ - if (!l1->plane_en) - return true; +static bool skl_plane_wm_equals(struct drm_i915_private *dev_priv, + const struct skl_plane_wm *wm1, + const struct skl_plane_wm *wm2) +{ + int level, max_level = ilk_wm_max_level(dev_priv); - return (l1->plane_res_l == l2->plane_res_l && - l1->plane_res_b == l2->plane_res_b); + for (level = 0; level <= max_level; level++) { + if (!skl_wm_level_equals(&wm1->wm[level], &wm2->wm[level]) || + !skl_wm_level_equals(&wm1->uv_wm[level], &wm2->uv_wm[level])) + return false; + } + + return skl_wm_level_equals(&wm1->trans_wm, &wm2->trans_wm); } static inline bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a, @@ -5244,13 +5254,12 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, static int skl_update_pipe_wm(struct drm_crtc_state *cstate, const struct skl_pipe_wm *old_pipe_wm, struct skl_pipe_wm *pipe_wm, /* out */ - struct skl_ddb_allocation *ddb, /* out */ bool *changed /* out */) { struct intel_crtc_state *intel_cstate = to_intel_crtc_state(cstate); int ret; - ret = skl_build_pipe_wm(intel_cstate, ddb, pipe_wm); + ret = skl_build_pipe_wm(intel_cstate, pipe_wm); if (ret) return ret; @@ -5276,42 +5285,29 @@ pipes_modified(struct drm_atomic_state *state) } static int -skl_ddb_add_affected_planes(struct intel_crtc_state *cstate) +skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state, + struct intel_crtc_state *new_crtc_state) { - struct drm_atomic_state *state = cstate->base.state; - struct drm_device *dev = state->dev; - struct drm_crtc *crtc = cstate->base.crtc; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb; - struct skl_ddb_allocation *cur_ddb = &dev_priv->wm.skl_hw.ddb; - struct drm_plane *plane; - enum pipe pipe = intel_crtc->pipe; + struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->base.state); + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + struct intel_plane *plane; - drm_for_each_plane_mask(plane, dev, cstate->base.plane_mask) { - struct drm_plane_state *plane_state; - struct intel_plane *linked; - enum plane_id plane_id = to_intel_plane(plane)->id; + for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + struct intel_plane_state *plane_state; + enum plane_id plane_id = plane->id; - if (skl_ddb_entry_equal(&cur_ddb->plane[pipe][plane_id], - &new_ddb->plane[pipe][plane_id]) && - skl_ddb_entry_equal(&cur_ddb->uv_plane[pipe][plane_id], - &new_ddb->uv_plane[pipe][plane_id])) + if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id], + &new_crtc_state->wm.skl.plane_ddb_y[plane_id]) && + skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_uv[plane_id], + &new_crtc_state->wm.skl.plane_ddb_uv[plane_id])) continue; - plane_state = drm_atomic_get_plane_state(state, plane); + plane_state = intel_atomic_get_plane_state(state, plane); if (IS_ERR(plane_state)) return PTR_ERR(plane_state); - /* Make sure linked plane is updated too */ - linked = to_intel_plane_state(plane_state)->linked_plane; - if (!linked) - continue; - - plane_state = drm_atomic_get_plane_state(state, &linked->base); - if (IS_ERR(plane_state)) - return PTR_ERR(plane_state); + new_crtc_state->update_planes |= BIT(plane_id); } return 0; @@ -5323,18 +5319,21 @@ skl_compute_ddb(struct drm_atomic_state *state) const struct drm_i915_private *dev_priv = to_i915(state->dev); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); struct skl_ddb_allocation *ddb = &intel_state->wm_results.ddb; + struct intel_crtc_state *old_crtc_state; + struct intel_crtc_state *new_crtc_state; struct intel_crtc *crtc; - struct intel_crtc_state *cstate; int ret, i; memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb)); - for_each_new_intel_crtc_in_state(intel_state, crtc, cstate, i) { - ret = skl_allocate_pipe_ddb(cstate, ddb); + for_each_oldnew_intel_crtc_in_state(intel_state, crtc, old_crtc_state, + new_crtc_state, i) { + ret = skl_allocate_pipe_ddb(new_crtc_state, ddb); if (ret) return ret; - ret = skl_ddb_add_affected_planes(cstate); + ret = skl_ddb_add_affected_planes(old_crtc_state, + new_crtc_state); if (ret) return ret; } @@ -5343,36 +5342,29 @@ skl_compute_ddb(struct drm_atomic_state *state) } static void -skl_print_wm_changes(const struct drm_atomic_state *state) +skl_print_wm_changes(struct intel_atomic_state *state) { - const struct drm_device *dev = state->dev; - const struct drm_i915_private *dev_priv = to_i915(dev); - const struct intel_atomic_state *intel_state = - to_intel_atomic_state(state); - const struct drm_crtc *crtc; - const struct drm_crtc_state *cstate; - const struct intel_plane *intel_plane; - const struct skl_ddb_allocation *old_ddb = &dev_priv->wm.skl_hw.ddb; - const struct skl_ddb_allocation *new_ddb = &intel_state->wm_results.ddb; + struct drm_i915_private *dev_priv = to_i915(state->base.dev); + const struct intel_crtc_state *old_crtc_state; + const struct intel_crtc_state *new_crtc_state; + struct intel_plane *plane; + struct intel_crtc *crtc; int i; - for_each_new_crtc_in_state(state, crtc, cstate, i) { - const struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum pipe pipe = intel_crtc->pipe; - - for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane) { - enum plane_id plane_id = intel_plane->id; + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) { + for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + enum plane_id plane_id = plane->id; const struct skl_ddb_entry *old, *new; - old = &old_ddb->plane[pipe][plane_id]; - new = &new_ddb->plane[pipe][plane_id]; + old = &old_crtc_state->wm.skl.plane_ddb_y[plane_id]; + new = &new_crtc_state->wm.skl.plane_ddb_y[plane_id]; if (skl_ddb_entry_equal(old, new)) continue; DRM_DEBUG_KMS("[PLANE:%d:%s] ddb (%d - %d) -> (%d - %d)\n", - intel_plane->base.base.id, - intel_plane->base.name, + plane->base.base.id, plane->base.name, old->start, old->end, new->start, new->end); } @@ -5469,6 +5461,66 @@ skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed) return 0; } +/* + * To make sure the cursor watermark registers are always consistent + * with our computed state the following scenario needs special + * treatment: + * + * 1. enable cursor + * 2. move cursor entirely offscreen + * 3. disable cursor + * + * Step 2. does call .disable_plane() but does not zero the watermarks + * (since we consider an offscreen cursor still active for the purposes + * of watermarks). Step 3. would not normally call .disable_plane() + * because the actual plane visibility isn't changing, and we don't + * deallocate the cursor ddb until the pipe gets disabled. So we must + * force step 3. to call .disable_plane() to update the watermark + * registers properly. + * + * Other planes do not suffer from this issues as their watermarks are + * calculated based on the actual plane visibility. The only time this + * can trigger for the other planes is during the initial readout as the + * default value of the watermarks registers is not zero. + */ +static int skl_wm_add_affected_planes(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + struct intel_plane *plane; + + for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { + struct intel_plane_state *plane_state; + enum plane_id plane_id = plane->id; + + /* + * Force a full wm update for every plane on modeset. + * Required because the reset value of the wm registers + * is non-zero, whereas we want all disabled planes to + * have zero watermarks. So if we turn off the relevant + * power well the hardware state will go out of sync + * with the software state. + */ + if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->base) && + skl_plane_wm_equals(dev_priv, + &old_crtc_state->wm.skl.optimal.planes[plane_id], + &new_crtc_state->wm.skl.optimal.planes[plane_id])) + continue; + + plane_state = intel_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + + new_crtc_state->update_planes |= BIT(plane_id); + } + + return 0; +} + static int skl_compute_wm(struct drm_atomic_state *state) { @@ -5508,8 +5560,12 @@ skl_compute_wm(struct drm_atomic_state *state) &to_intel_crtc_state(crtc->state)->wm.skl.optimal; pipe_wm = &intel_cstate->wm.skl.optimal; - ret = skl_update_pipe_wm(cstate, old_pipe_wm, pipe_wm, - &results->ddb, &changed); + ret = skl_update_pipe_wm(cstate, old_pipe_wm, pipe_wm, &changed); + if (ret) + return ret; + + ret = skl_wm_add_affected_planes(intel_state, + to_intel_crtc(crtc)); if (ret) return ret; @@ -5523,7 +5579,7 @@ skl_compute_wm(struct drm_atomic_state *state) intel_cstate->update_wm_pre = true; } - skl_print_wm_changes(state); + skl_print_wm_changes(intel_state); return 0; } @@ -5534,23 +5590,12 @@ static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state, struct intel_crtc *crtc = to_intel_crtc(cstate->base.crtc); struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal; - const struct skl_ddb_allocation *ddb = &state->wm_results.ddb; enum pipe pipe = crtc->pipe; - enum plane_id plane_id; if (!(state->wm_results.dirty_pipes & drm_crtc_mask(&crtc->base))) return; I915_WRITE(PIPE_WM_LINETIME(pipe), pipe_wm->linetime); - - for_each_plane_id_on_crtc(crtc, plane_id) { - if (plane_id != PLANE_CURSOR) - skl_write_plane_wm(crtc, &pipe_wm->planes[plane_id], - ddb, plane_id); - else - skl_write_cursor_wm(crtc, &pipe_wm->planes[plane_id], - ddb); - } } static void skl_initial_wm(struct intel_atomic_state *state, @@ -5560,8 +5605,6 @@ static void skl_initial_wm(struct intel_atomic_state *state, struct drm_device *dev = intel_crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); struct skl_ddb_values *results = &state->wm_results; - struct skl_ddb_values *hw_vals = &dev_priv->wm.skl_hw; - enum pipe pipe = intel_crtc->pipe; if ((results->dirty_pipes & drm_crtc_mask(&intel_crtc->base)) == 0) return; @@ -5571,11 +5614,6 @@ static void skl_initial_wm(struct intel_atomic_state *state, if (cstate->base.active_changed) skl_atomic_update_crtc_wm(state, cstate); - memcpy(hw_vals->ddb.uv_plane[pipe], results->ddb.uv_plane[pipe], - sizeof(hw_vals->ddb.uv_plane[pipe])); - memcpy(hw_vals->ddb.plane[pipe], results->ddb.plane[pipe], - sizeof(hw_vals->ddb.plane[pipe])); - mutex_unlock(&dev_priv->wm.wm_mutex); } @@ -5726,13 +5764,6 @@ void skl_wm_get_hw_state(struct drm_device *dev) if (dev_priv->active_crtcs) { /* Fully recompute DDB on first atomic commit */ dev_priv->wm.distrust_bios_wm = true; - } else { - /* - * Easy/common case; just sanitize DDB now if everything off - * Keep dbuf slice info intact - */ - memset(ddb->plane, 0, sizeof(ddb->plane)); - memset(ddb->uv_plane, 0, sizeof(ddb->uv_plane)); } } diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index 54fa17a5596a..419e56342523 100644 --- a/drivers/gpu/drm/i915/intel_psr.c +++ b/drivers/gpu/drm/i915/intel_psr.c @@ -75,6 +75,10 @@ static bool intel_psr2_enabled(struct drm_i915_private *dev_priv, if (i915_modparams.enable_psr == -1) return false; + /* Cannot enable DSC and PSR2 simultaneously */ + WARN_ON(crtc_state->dsc_params.compression_enable && + crtc_state->has_psr2); + switch (dev_priv->psr.debug & I915_PSR_DEBUG_MODE_MASK) { case I915_PSR_DEBUG_FORCE_PSR1: return false; @@ -169,6 +173,7 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) u32 transcoders = BIT(TRANSCODER_EDP); enum transcoder cpu_transcoder; ktime_t time_ns = ktime_get(); + u32 mask = 0; if (INTEL_GEN(dev_priv) >= 8) transcoders |= BIT(TRANSCODER_A) | @@ -178,10 +183,22 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) { int shift = edp_psr_shift(cpu_transcoder); - /* FIXME: Exit PSR and link train manually when this happens. */ - if (psr_iir & EDP_PSR_ERROR(shift)) - DRM_DEBUG_KMS("[transcoder %s] PSR aux error\n", - transcoder_name(cpu_transcoder)); + if (psr_iir & EDP_PSR_ERROR(shift)) { + DRM_WARN("[transcoder %s] PSR aux error\n", + transcoder_name(cpu_transcoder)); + + dev_priv->psr.irq_aux_error = true; + + /* + * If this interruption is not masked it will keep + * interrupting so fast that it prevents the scheduled + * work to run. + * Also after a PSR error, we don't want to arm PSR + * again so we don't care about unmask the interruption + * or unset irq_aux_error. + */ + mask |= EDP_PSR_ERROR(shift); + } if (psr_iir & EDP_PSR_PRE_ENTRY(shift)) { dev_priv->psr.last_entry_attempt = time_ns; @@ -203,6 +220,13 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir) } } } + + if (mask) { + mask |= I915_READ(EDP_PSR_IMR); + I915_WRITE(EDP_PSR_IMR, mask); + + schedule_work(&dev_priv->psr.work); + } } static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp) @@ -482,6 +506,16 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, if (!dev_priv->psr.sink_psr2_support) return false; + /* + * DSC and PSR2 cannot be enabled simultaneously. If a requested + * resolution requires DSC to be enabled, priority is given to DSC + * over PSR2. + */ + if (crtc_state->dsc_params.compression_enable) { + DRM_DEBUG_KMS("PSR2 cannot be enabled since DSC is enabled\n"); + return false; + } + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) { psr_max_h = 4096; psr_max_v = 2304; @@ -527,10 +561,8 @@ void intel_psr_compute_config(struct intel_dp *intel_dp, return; } - if (IS_HASWELL(dev_priv) && - I915_READ(HSW_STEREO_3D_CTL(crtc_state->cpu_transcoder)) & - S3D_ENABLE) { - DRM_DEBUG_KMS("PSR condition failed: Stereo 3D is Enabled\n"); + if (dev_priv->psr.sink_not_reliable) { + DRM_DEBUG_KMS("PSR sink implementation is not reliable\n"); return; } @@ -687,6 +719,7 @@ void intel_psr_enable(struct intel_dp *intel_dp, dev_priv->psr.psr2_enabled = intel_psr2_enabled(dev_priv, crtc_state); dev_priv->psr.busy_frontbuffer_bits = 0; dev_priv->psr.prepared = true; + dev_priv->psr.pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; if (psr_global_enabled(dev_priv->psr.debug)) intel_psr_enable_locked(dev_priv, crtc_state); @@ -933,6 +966,16 @@ int intel_psr_set_debugfs_mode(struct drm_i915_private *dev_priv, return ret; } +static void intel_psr_handle_irq(struct drm_i915_private *dev_priv) +{ + struct i915_psr *psr = &dev_priv->psr; + + intel_psr_disable_locked(psr->dp); + psr->sink_not_reliable = true; + /* let's make sure that sink is awaken */ + drm_dp_dpcd_writeb(&psr->dp->aux, DP_SET_POWER, DP_SET_POWER_D0); +} + static void intel_psr_work(struct work_struct *work) { struct drm_i915_private *dev_priv = @@ -943,6 +986,9 @@ static void intel_psr_work(struct work_struct *work) if (!dev_priv->psr.enabled) goto unlock; + if (READ_ONCE(dev_priv->psr.irq_aux_error)) + intel_psr_handle_irq(dev_priv); + /* * We have to make sure PSR is ready for re-enable * otherwise it keeps disabled until next full enable/disable cycle. @@ -981,9 +1027,6 @@ unlock: void intel_psr_invalidate(struct drm_i915_private *dev_priv, unsigned frontbuffer_bits, enum fb_op_origin origin) { - struct drm_crtc *crtc; - enum pipe pipe; - if (!CAN_PSR(dev_priv)) return; @@ -996,10 +1039,7 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv, return; } - crtc = dp_to_dig_port(dev_priv->psr.dp)->base.base.crtc; - pipe = to_intel_crtc(crtc)->pipe; - - frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(pipe); + frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(dev_priv->psr.pipe); dev_priv->psr.busy_frontbuffer_bits |= frontbuffer_bits; if (frontbuffer_bits) @@ -1024,9 +1064,6 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv, void intel_psr_flush(struct drm_i915_private *dev_priv, unsigned frontbuffer_bits, enum fb_op_origin origin) { - struct drm_crtc *crtc; - enum pipe pipe; - if (!CAN_PSR(dev_priv)) return; @@ -1039,10 +1076,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, return; } - crtc = dp_to_dig_port(dev_priv->psr.dp)->base.base.crtc; - pipe = to_intel_crtc(crtc)->pipe; - - frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(pipe); + frontbuffer_bits &= INTEL_FRONTBUFFER_ALL_MASK(dev_priv->psr.pipe); dev_priv->psr.busy_frontbuffer_bits &= ~frontbuffer_bits; /* By definition flush = invalidate + flush */ @@ -1056,7 +1090,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, * but it makes more sense write to the current active * pipe. */ - I915_WRITE(CURSURFLIVE(pipe), 0); + I915_WRITE(CURSURFLIVE(dev_priv->psr.pipe), 0); } if (!dev_priv->psr.active && !dev_priv->psr.busy_frontbuffer_bits) @@ -1073,6 +1107,8 @@ void intel_psr_flush(struct drm_i915_private *dev_priv, */ void intel_psr_init(struct drm_i915_private *dev_priv) { + u32 val; + if (!HAS_PSR(dev_priv)) return; @@ -1086,6 +1122,22 @@ void intel_psr_init(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) < 9 || !dev_priv->vbt.psr.enable) i915_modparams.enable_psr = 0; + /* + * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR + * will still keep the error set even after the reset done in the + * irq_preinstall and irq_uninstall hooks. + * And enabling in this situation cause the screen to freeze in the + * first time that PSR HW tries to activate so lets keep PSR disabled + * to avoid any rendering problems. + */ + val = I915_READ(EDP_PSR_IIR); + val &= EDP_PSR_ERROR(edp_psr_shift(TRANSCODER_EDP)); + if (val) { + DRM_DEBUG_KMS("PSR interruption error set\n"); + dev_priv->psr.sink_not_reliable = true; + return; + } + /* Set link_standby x link_off defaults */ if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) /* HSW and BDW require workarounds that we don't implement. */ @@ -1123,6 +1175,7 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp) if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) { DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n"); intel_psr_disable_locked(intel_dp); + psr->sink_not_reliable = true; } if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ERROR_STATUS, &val) != 1) { @@ -1140,10 +1193,27 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp) if (val & ~errors) DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n", val & ~errors); - if (val & errors) + if (val & errors) { intel_psr_disable_locked(intel_dp); + psr->sink_not_reliable = true; + } /* clear status register */ drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val); exit: mutex_unlock(&psr->lock); } + +bool intel_psr_enabled(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + bool ret; + + if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp)) + return false; + + mutex_lock(&dev_priv->psr.lock); + ret = (dev_priv->psr.dp == intel_dp && dev_priv->psr.enabled); + mutex_unlock(&dev_priv->psr.lock); + + return ret; +} diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 87eebc13c0d8..c5eb26a7ee79 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -150,8 +150,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) */ if (mode & EMIT_INVALIDATE) { *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -159,8 +158,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; } @@ -212,8 +210,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) static int intel_emit_post_sync_nonzero_flush(struct i915_request *rq) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs; cs = intel_ring_begin(rq, 6); @@ -246,8 +243,7 @@ intel_emit_post_sync_nonzero_flush(struct i915_request *rq) static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; int ret; @@ -316,8 +312,7 @@ gen7_render_ring_cs_stall_wa(struct i915_request *rq) static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; /* @@ -529,6 +524,13 @@ static int init_ring_common(struct intel_engine_cs *engine) intel_engine_reset_breadcrumbs(engine); + if (HAS_LEGACY_SEMAPHORES(engine->i915)) { + I915_WRITE(RING_SYNC_0(engine->mmio_base), 0); + I915_WRITE(RING_SYNC_1(engine->mmio_base), 0); + if (HAS_VEBOX(dev_priv)) + I915_WRITE(RING_SYNC_2(engine->mmio_base), 0); + } + /* Enforce ordering by reading HEAD register back */ I915_READ_HEAD(engine); @@ -546,10 +548,11 @@ static int init_ring_common(struct intel_engine_cs *engine) /* Check that the ring offsets point within the ring! */ GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head)); GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail)); - intel_ring_update_space(ring); + + /* First wake the ring up to an empty/idle ring */ I915_WRITE_HEAD(engine, ring->head); - I915_WRITE_TAIL(engine, ring->tail); + I915_WRITE_TAIL(engine, ring->head); (void)I915_READ_TAIL(engine); I915_WRITE_CTL(engine, RING_CTL_SIZE(ring->size) | RING_VALID); @@ -574,6 +577,12 @@ static int init_ring_common(struct intel_engine_cs *engine) if (INTEL_GEN(dev_priv) > 2) I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING)); + /* Now awake, let it get started */ + if (ring->tail != ring->head) { + I915_WRITE_TAIL(engine, ring->tail); + (void)I915_READ_TAIL(engine); + } + /* Papering over lost _interrupts_ immediately following the restart */ intel_engine_wakeup(engine); out: @@ -642,7 +651,7 @@ static int intel_rcs_ctx_init(struct i915_request *rq) { int ret; - ret = intel_ctx_workarounds_emit(rq); + ret = intel_engine_emit_ctx_wa(rq); if (ret != 0) return ret; @@ -660,8 +669,6 @@ static int init_render_ring(struct intel_engine_cs *engine) if (ret) return ret; - intel_whitelist_workarounds_apply(engine); - /* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */ if (IS_GEN(dev_priv, 4, 6)) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH)); @@ -743,9 +750,18 @@ static void cancel_requests(struct intel_engine_cs *engine) /* Mark all submitted requests as skipped. */ list_for_each_entry(request, &engine->timeline.requests, link) { GEM_BUG_ON(!request->global_seqno); - if (!i915_request_completed(request)) - dma_fence_set_error(&request->fence, -EIO); + + if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, + &request->fence.flags)) + continue; + + dma_fence_set_error(&request->fence, -EIO); } + + intel_write_status_page(engine, + I915_GEM_HWS_INDEX, + intel_engine_last_submit(engine)); + /* Remaining _unready_ requests will be nop'ed when submitted */ spin_unlock_irqrestore(&engine->timeline.lock, flags); @@ -973,7 +989,7 @@ i965_emit_bb_start(struct i915_request *rq, } /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ -#define I830_BATCH_LIMIT (256*1024) +#define I830_BATCH_LIMIT SZ_256K #define I830_TLB_ENTRIES (2) #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT) static int @@ -981,7 +997,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = i915_ggtt_offset(rq->engine->scratch); + u32 *cs, cs_offset = i915_scratch_offset(rq->i915); + + GEM_BUG_ON(rq->i915->gt.scratch->size < I830_WA_SIZE); cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1438,7 +1456,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) { struct i915_timeline *timeline; struct intel_ring *ring; - unsigned int size; int err; intel_engine_setup_common(engine); @@ -1463,21 +1480,12 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) GEM_BUG_ON(engine->buffer); engine->buffer = ring; - size = PAGE_SIZE; - if (HAS_BROKEN_CS_TLB(engine->i915)) - size = I830_WA_SIZE; - err = intel_engine_create_scratch(engine, size); - if (err) - goto err_unpin; - err = intel_engine_init_common(engine); if (err) - goto err_scratch; + goto err_unpin; return 0; -err_scratch: - intel_engine_cleanup_scratch(engine); err_unpin: intel_ring_unpin(ring); err_ring: @@ -1551,7 +1559,7 @@ static int flush_pd_dir(struct i915_request *rq) /* Stall until the page table load is complete */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine)); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1660,7 +1668,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* Insert a delay before the next switch! */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(last_reg); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 8a2270b209b0..72edaa7ff411 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -15,6 +15,7 @@ #include "i915_selftest.h" #include "i915_timeline.h" #include "intel_gpu_commands.h" +#include "intel_workarounds.h" struct drm_printer; struct i915_sched_attr; @@ -313,13 +314,6 @@ struct intel_engine_execlists { struct rb_root_cached queue; /** - * @csb_read: control register for Context Switch buffer - * - * Note this register is always in mmio. - */ - u32 __iomem *csb_read; - - /** * @csb_write: control register for Context Switch buffer * * Note this register may be either mmio or HWSP shadow. @@ -339,15 +333,6 @@ struct intel_engine_execlists { u32 preempt_complete_status; /** - * @csb_write_reset: reset value for CSB write pointer - * - * As the CSB write pointer maybe either in HWSP or as a field - * inside an mmio register, we want to reprogram it slightly - * differently to avoid later confusion. - */ - u32 csb_write_reset; - - /** * @csb_head: context status buffer head */ u8 csb_head; @@ -451,7 +436,9 @@ struct intel_engine_cs { struct intel_hw_status_page status_page; struct i915_ctx_workarounds wa_ctx; - struct i915_vma *scratch; + struct i915_wa_list ctx_wa_list; + struct i915_wa_list wa_list; + struct i915_wa_list whitelist; u32 irq_keep_mask; /* always keep these interrupts */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ @@ -908,10 +895,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine); int intel_engine_init_common(struct intel_engine_cs *engine); void intel_engine_cleanup_common(struct intel_engine_cs *engine); -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size); -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine); - int intel_init_render_ring_buffer(struct intel_engine_cs *engine); int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine); int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 1c2de9b69a19..4350a5270423 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -76,6 +76,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain) return "TRANSCODER_C"; case POWER_DOMAIN_TRANSCODER_EDP: return "TRANSCODER_EDP"; + case POWER_DOMAIN_TRANSCODER_EDP_VDSC: + return "TRANSCODER_EDP_VDSC"; case POWER_DOMAIN_TRANSCODER_DSI_A: return "TRANSCODER_DSI_A"; case POWER_DOMAIN_TRANSCODER_DSI_C: @@ -2028,9 +2030,9 @@ void intel_display_power_put(struct drm_i915_private *dev_priv, */ #define ICL_PW_2_POWER_DOMAINS ( \ ICL_PW_3_POWER_DOMAINS | \ + BIT_ULL(POWER_DOMAIN_TRANSCODER_EDP_VDSC) | \ BIT_ULL(POWER_DOMAIN_INIT)) /* - * - eDP/DSI VDSC * - KVMR (HW control) */ #define ICL_DISPLAY_DC_OFF_POWER_DOMAINS ( \ diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index abe193815ccc..d2e003d8f3db 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -373,14 +373,12 @@ skl_program_scaler(struct intel_plane *plane, #define BOFF(x) (((x) & 0xffff) << 16) static void -icl_program_input_csc_coeff(const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +icl_program_input_csc(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { - struct drm_i915_private *dev_priv = - to_i915(plane_state->base.plane->dev); - struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); - enum pipe pipe = crtc->pipe; - struct intel_plane *plane = to_intel_plane(plane_state->base.plane); + struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + enum pipe pipe = plane->pipe; enum plane_id plane_id = plane->id; static const u16 input_csc_matrix[][9] = { @@ -508,28 +506,12 @@ skl_program_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) - I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id), - plane_state->color_ctl); - - if (fb->format->is_yuv && icl_is_hdr_plane(plane)) - icl_program_input_csc_coeff(crtc_state, plane_state); - - I915_WRITE_FW(PLANE_KEYVAL(pipe, plane_id), key->min_value); - I915_WRITE_FW(PLANE_KEYMAX(pipe, plane_id), keymax); - I915_WRITE_FW(PLANE_KEYMSK(pipe, plane_id), keymsk); - - I915_WRITE_FW(PLANE_OFFSET(pipe, plane_id), (y << 16) | x); I915_WRITE_FW(PLANE_STRIDE(pipe, plane_id), stride); + I915_WRITE_FW(PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x); I915_WRITE_FW(PLANE_SIZE(pipe, plane_id), (src_h << 16) | src_w); I915_WRITE_FW(PLANE_AUX_DIST(pipe, plane_id), (plane_state->color_plane[1].offset - surf_addr) | aux_stride); - if (INTEL_GEN(dev_priv) < 11) - I915_WRITE_FW(PLANE_AUX_OFFSET(pipe, plane_id), - (plane_state->color_plane[1].y << 16) | - plane_state->color_plane[1].x); - if (icl_is_hdr_plane(plane)) { u32 cus_ctl = 0; @@ -551,15 +533,38 @@ skl_program_plane(struct intel_plane *plane, I915_WRITE_FW(PLANE_CUS_CTL(pipe, plane_id), cus_ctl); } - if (!slave && plane_state->scaler_id >= 0) - skl_program_scaler(plane, crtc_state, plane_state); + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) + I915_WRITE_FW(PLANE_COLOR_CTL(pipe, plane_id), + plane_state->color_ctl); - I915_WRITE_FW(PLANE_POS(pipe, plane_id), (crtc_y << 16) | crtc_x); + if (fb->format->is_yuv && icl_is_hdr_plane(plane)) + icl_program_input_csc(plane, crtc_state, plane_state); + + skl_write_plane_wm(plane, crtc_state); + I915_WRITE_FW(PLANE_KEYVAL(pipe, plane_id), key->min_value); + I915_WRITE_FW(PLANE_KEYMSK(pipe, plane_id), keymsk); + I915_WRITE_FW(PLANE_KEYMAX(pipe, plane_id), keymax); + + I915_WRITE_FW(PLANE_OFFSET(pipe, plane_id), (y << 16) | x); + + if (INTEL_GEN(dev_priv) < 11) + I915_WRITE_FW(PLANE_AUX_OFFSET(pipe, plane_id), + (plane_state->color_plane[1].y << 16) | + plane_state->color_plane[1].x); + + /* + * The control register self-arms if the plane was previously + * disabled. Try to make the plane enable atomic by writing + * the control register just before the surface register. + */ I915_WRITE_FW(PLANE_CTL(pipe, plane_id), plane_ctl); I915_WRITE_FW(PLANE_SURF(pipe, plane_id), intel_plane_ggtt_offset(plane_state) + surf_addr); + if (!slave && plane_state->scaler_id >= 0) + skl_program_scaler(plane, crtc_state, plane_state); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } @@ -589,7 +594,8 @@ icl_update_slave(struct intel_plane *plane, } static void -skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) +skl_disable_plane(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum plane_id plane_id = plane->id; @@ -598,6 +604,8 @@ skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + skl_write_plane_wm(plane, crtc_state); + I915_WRITE_FW(PLANE_CTL(pipe, plane_id), 0); I915_WRITE_FW(PLANE_SURF(pipe, plane_id), 0); @@ -819,35 +827,41 @@ vlv_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); - vlv_update_clrc(plane_state); + I915_WRITE_FW(SPSTRIDE(pipe, plane_id), + plane_state->color_plane[0].stride); + I915_WRITE_FW(SPPOS(pipe, plane_id), (crtc_y << 16) | crtc_x); + I915_WRITE_FW(SPSIZE(pipe, plane_id), (crtc_h << 16) | crtc_w); + I915_WRITE_FW(SPCONSTALPHA(pipe, plane_id), 0); if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_B) chv_update_csc(plane_state); if (key->flags) { I915_WRITE_FW(SPKEYMINVAL(pipe, plane_id), key->min_value); - I915_WRITE_FW(SPKEYMAXVAL(pipe, plane_id), key->max_value); I915_WRITE_FW(SPKEYMSK(pipe, plane_id), key->channel_mask); + I915_WRITE_FW(SPKEYMAXVAL(pipe, plane_id), key->max_value); } - I915_WRITE_FW(SPSTRIDE(pipe, plane_id), - plane_state->color_plane[0].stride); - I915_WRITE_FW(SPPOS(pipe, plane_id), (crtc_y << 16) | crtc_x); - I915_WRITE_FW(SPTILEOFF(pipe, plane_id), (y << 16) | x); I915_WRITE_FW(SPLINOFF(pipe, plane_id), linear_offset); + I915_WRITE_FW(SPTILEOFF(pipe, plane_id), (y << 16) | x); - I915_WRITE_FW(SPCONSTALPHA(pipe, plane_id), 0); - - I915_WRITE_FW(SPSIZE(pipe, plane_id), (crtc_h << 16) | crtc_w); + /* + * The control register self-arms if the plane was previously + * disabled. Try to make the plane enable atomic by writing + * the control register just before the surface register. + */ I915_WRITE_FW(SPCNTR(pipe, plane_id), sprctl); I915_WRITE_FW(SPSURF(pipe, plane_id), intel_plane_ggtt_offset(plane_state) + sprsurf_offset); + vlv_update_clrc(plane_state); + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); } static void -vlv_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) +vlv_disable_plane(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -980,27 +994,32 @@ ivb_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + I915_WRITE_FW(SPRSTRIDE(pipe), plane_state->color_plane[0].stride); + I915_WRITE_FW(SPRPOS(pipe), (crtc_y << 16) | crtc_x); + I915_WRITE_FW(SPRSIZE(pipe), (crtc_h << 16) | crtc_w); + if (IS_IVYBRIDGE(dev_priv)) + I915_WRITE_FW(SPRSCALE(pipe), sprscale); + if (key->flags) { I915_WRITE_FW(SPRKEYVAL(pipe), key->min_value); - I915_WRITE_FW(SPRKEYMAX(pipe), key->max_value); I915_WRITE_FW(SPRKEYMSK(pipe), key->channel_mask); + I915_WRITE_FW(SPRKEYMAX(pipe), key->max_value); } - I915_WRITE_FW(SPRSTRIDE(pipe), plane_state->color_plane[0].stride); - I915_WRITE_FW(SPRPOS(pipe), (crtc_y << 16) | crtc_x); - /* HSW consolidates SPRTILEOFF and SPRLINOFF into a single SPROFFSET * register */ if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { I915_WRITE_FW(SPROFFSET(pipe), (y << 16) | x); } else { - I915_WRITE_FW(SPRTILEOFF(pipe), (y << 16) | x); I915_WRITE_FW(SPRLINOFF(pipe), linear_offset); + I915_WRITE_FW(SPRTILEOFF(pipe), (y << 16) | x); } - I915_WRITE_FW(SPRSIZE(pipe), (crtc_h << 16) | crtc_w); - if (IS_IVYBRIDGE(dev_priv)) - I915_WRITE_FW(SPRSCALE(pipe), sprscale); + /* + * The control register self-arms if the plane was previously + * disabled. Try to make the plane enable atomic by writing + * the control register just before the surface register. + */ I915_WRITE_FW(SPRCTL(pipe), sprctl); I915_WRITE_FW(SPRSURF(pipe), intel_plane_ggtt_offset(plane_state) + sprsurf_offset); @@ -1009,7 +1028,8 @@ ivb_update_plane(struct intel_plane *plane, } static void -ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) +ivb_disable_plane(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; @@ -1018,7 +1038,7 @@ ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); I915_WRITE_FW(SPRCTL(pipe), 0); - /* Can't leave the scaler enabled... */ + /* Disable the scaler */ if (IS_IVYBRIDGE(dev_priv)) I915_WRITE_FW(SPRSCALE(pipe), 0); I915_WRITE_FW(SPRSURF(pipe), 0); @@ -1148,20 +1168,25 @@ g4x_update_plane(struct intel_plane *plane, spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + I915_WRITE_FW(DVSSTRIDE(pipe), plane_state->color_plane[0].stride); + I915_WRITE_FW(DVSPOS(pipe), (crtc_y << 16) | crtc_x); + I915_WRITE_FW(DVSSIZE(pipe), (crtc_h << 16) | crtc_w); + I915_WRITE_FW(DVSSCALE(pipe), dvsscale); + if (key->flags) { I915_WRITE_FW(DVSKEYVAL(pipe), key->min_value); - I915_WRITE_FW(DVSKEYMAX(pipe), key->max_value); I915_WRITE_FW(DVSKEYMSK(pipe), key->channel_mask); + I915_WRITE_FW(DVSKEYMAX(pipe), key->max_value); } - I915_WRITE_FW(DVSSTRIDE(pipe), plane_state->color_plane[0].stride); - I915_WRITE_FW(DVSPOS(pipe), (crtc_y << 16) | crtc_x); - - I915_WRITE_FW(DVSTILEOFF(pipe), (y << 16) | x); I915_WRITE_FW(DVSLINOFF(pipe), linear_offset); + I915_WRITE_FW(DVSTILEOFF(pipe), (y << 16) | x); - I915_WRITE_FW(DVSSIZE(pipe), (crtc_h << 16) | crtc_w); - I915_WRITE_FW(DVSSCALE(pipe), dvsscale); + /* + * The control register self-arms if the plane was previously + * disabled. Try to make the plane enable atomic by writing + * the control register just before the surface register. + */ I915_WRITE_FW(DVSCNTR(pipe), dvscntr); I915_WRITE_FW(DVSSURF(pipe), intel_plane_ggtt_offset(plane_state) + dvssurf_offset); @@ -1170,7 +1195,8 @@ g4x_update_plane(struct intel_plane *plane, } static void -g4x_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc) +g4x_disable_plane(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(plane->base.dev); enum pipe pipe = plane->pipe; diff --git a/drivers/gpu/drm/i915/intel_vdsc.c b/drivers/gpu/drm/i915/intel_vdsc.c new file mode 100644 index 000000000000..c56ba0e04044 --- /dev/null +++ b/drivers/gpu/drm/i915/intel_vdsc.c @@ -0,0 +1,1088 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2018 Intel Corporation + * + * Author: Gaurav K Singh <gaurav.k.singh@intel.com> + * Manasi Navare <manasi.d.navare@intel.com> + */ + +#include <drm/drmP.h> +#include <drm/i915_drm.h> +#include "i915_drv.h" +#include "intel_drv.h" + +enum ROW_INDEX_BPP { + ROW_INDEX_6BPP = 0, + ROW_INDEX_8BPP, + ROW_INDEX_10BPP, + ROW_INDEX_12BPP, + ROW_INDEX_15BPP, + MAX_ROW_INDEX +}; + +enum COLUMN_INDEX_BPC { + COLUMN_INDEX_8BPC = 0, + COLUMN_INDEX_10BPC, + COLUMN_INDEX_12BPC, + COLUMN_INDEX_14BPC, + COLUMN_INDEX_16BPC, + MAX_COLUMN_INDEX +}; + +#define DSC_SUPPORTED_VERSION_MIN 1 + +/* From DSC_v1.11 spec, rc_parameter_Set syntax element typically constant */ +static u16 rc_buf_thresh[] = { + 896, 1792, 2688, 3584, 4480, 5376, 6272, 6720, 7168, 7616, + 7744, 7872, 8000, 8064 +}; + +struct rc_parameters { + u16 initial_xmit_delay; + u8 first_line_bpg_offset; + u16 initial_offset; + u8 flatness_min_qp; + u8 flatness_max_qp; + u8 rc_quant_incr_limit0; + u8 rc_quant_incr_limit1; + struct drm_dsc_rc_range_parameters rc_range_params[DSC_NUM_BUF_RANGES]; +}; + +/* + * Selected Rate Control Related Parameter Recommended Values + * from DSC_v1.11 spec & C Model release: DSC_model_20161212 + */ +static struct rc_parameters rc_params[][MAX_COLUMN_INDEX] = { +{ + /* 6BPP/8BPC */ + { 768, 15, 6144, 3, 13, 11, 11, { + { 0, 4, 0 }, { 1, 6, -2 }, { 3, 8, -2 }, { 4, 8, -4 }, + { 5, 9, -6 }, { 5, 9, -6 }, { 6, 9, -6 }, { 6, 10, -8 }, + { 7, 11, -8 }, { 8, 12, -10 }, { 9, 12, -10 }, { 10, 12, -12 }, + { 10, 12, -12 }, { 11, 12, -12 }, { 13, 14, -12 } + } + }, + /* 6BPP/10BPC */ + { 768, 15, 6144, 7, 17, 15, 15, { + { 0, 8, 0 }, { 3, 10, -2 }, { 7, 12, -2 }, { 8, 12, -4 }, + { 9, 13, -6 }, { 9, 13, -6 }, { 10, 13, -6 }, { 10, 14, -8 }, + { 11, 15, -8 }, { 12, 16, -10 }, { 13, 16, -10 }, + { 14, 16, -12 }, { 14, 16, -12 }, { 15, 16, -12 }, + { 17, 18, -12 } + } + }, + /* 6BPP/12BPC */ + { 768, 15, 6144, 11, 21, 19, 19, { + { 0, 12, 0 }, { 5, 14, -2 }, { 11, 16, -2 }, { 12, 16, -4 }, + { 13, 17, -6 }, { 13, 17, -6 }, { 14, 17, -6 }, { 14, 18, -8 }, + { 15, 19, -8 }, { 16, 20, -10 }, { 17, 20, -10 }, + { 18, 20, -12 }, { 18, 20, -12 }, { 19, 20, -12 }, + { 21, 22, -12 } + } + }, + /* 6BPP/14BPC */ + { 768, 15, 6144, 15, 25, 23, 27, { + { 0, 16, 0 }, { 7, 18, -2 }, { 15, 20, -2 }, { 16, 20, -4 }, + { 17, 21, -6 }, { 17, 21, -6 }, { 18, 21, -6 }, { 18, 22, -8 }, + { 19, 23, -8 }, { 20, 24, -10 }, { 21, 24, -10 }, + { 22, 24, -12 }, { 22, 24, -12 }, { 23, 24, -12 }, + { 25, 26, -12 } + } + }, + /* 6BPP/16BPC */ + { 768, 15, 6144, 19, 29, 27, 27, { + { 0, 20, 0 }, { 9, 22, -2 }, { 19, 24, -2 }, { 20, 24, -4 }, + { 21, 25, -6 }, { 21, 25, -6 }, { 22, 25, -6 }, { 22, 26, -8 }, + { 23, 27, -8 }, { 24, 28, -10 }, { 25, 28, -10 }, + { 26, 28, -12 }, { 26, 28, -12 }, { 27, 28, -12 }, + { 29, 30, -12 } + } + }, +}, +{ + /* 8BPP/8BPC */ + { 512, 12, 6144, 3, 12, 11, 11, { + { 0, 4, 2 }, { 0, 4, 0 }, { 1, 5, 0 }, { 1, 6, -2 }, + { 3, 7, -4 }, { 3, 7, -6 }, { 3, 7, -8 }, { 3, 8, -8 }, + { 3, 9, -8 }, { 3, 10, -10 }, { 5, 11, -10 }, { 5, 12, -12 }, + { 5, 13, -12 }, { 7, 13, -12 }, { 13, 15, -12 } + } + }, + /* 8BPP/10BPC */ + { 512, 12, 6144, 7, 16, 15, 15, { + { 0, 4, 2 }, { 4, 8, 0 }, { 5, 9, 0 }, { 5, 10, -2 }, + { 7, 11, -4 }, { 7, 11, -6 }, { 7, 11, -8 }, { 7, 12, -8 }, + { 7, 13, -8 }, { 7, 14, -10 }, { 9, 15, -10 }, { 9, 16, -12 }, + { 9, 17, -12 }, { 11, 17, -12 }, { 17, 19, -12 } + } + }, + /* 8BPP/12BPC */ + { 512, 12, 6144, 11, 20, 19, 19, { + { 0, 12, 2 }, { 4, 12, 0 }, { 9, 13, 0 }, { 9, 14, -2 }, + { 11, 15, -4 }, { 11, 15, -6 }, { 11, 15, -8 }, { 11, 16, -8 }, + { 11, 17, -8 }, { 11, 18, -10 }, { 13, 19, -10 }, + { 13, 20, -12 }, { 13, 21, -12 }, { 15, 21, -12 }, + { 21, 23, -12 } + } + }, + /* 8BPP/14BPC */ + { 512, 12, 6144, 15, 24, 23, 23, { + { 0, 12, 0 }, { 5, 13, 0 }, { 11, 15, 0 }, { 12, 17, -2 }, + { 15, 19, -4 }, { 15, 19, -6 }, { 15, 19, -8 }, { 15, 20, -8 }, + { 15, 21, -8 }, { 15, 22, -10 }, { 17, 22, -10 }, + { 17, 23, -12 }, { 17, 23, -12 }, { 21, 24, -12 }, + { 24, 25, -12 } + } + }, + /* 8BPP/16BPC */ + { 512, 12, 6144, 19, 28, 27, 27, { + { 0, 12, 2 }, { 6, 14, 0 }, { 13, 17, 0 }, { 15, 20, -2 }, + { 19, 23, -4 }, { 19, 23, -6 }, { 19, 23, -8 }, { 19, 24, -8 }, + { 19, 25, -8 }, { 19, 26, -10 }, { 21, 26, -10 }, + { 21, 27, -12 }, { 21, 27, -12 }, { 25, 28, -12 }, + { 28, 29, -12 } + } + }, +}, +{ + /* 10BPP/8BPC */ + { 410, 15, 5632, 3, 12, 11, 11, { + { 0, 3, 2 }, { 0, 4, 0 }, { 1, 5, 0 }, { 2, 6, -2 }, + { 3, 7, -4 }, { 3, 7, -6 }, { 3, 7, -8 }, { 3, 8, -8 }, + { 3, 9, -8 }, { 3, 9, -10 }, { 5, 10, -10 }, { 5, 10, -10 }, + { 5, 11, -12 }, { 7, 11, -12 }, { 11, 12, -12 } + } + }, + /* 10BPP/10BPC */ + { 410, 15, 5632, 7, 16, 15, 15, { + { 0, 7, 2 }, { 4, 8, 0 }, { 5, 9, 0 }, { 6, 10, -2 }, + { 7, 11, -4 }, { 7, 11, -6 }, { 7, 11, -8 }, { 7, 12, -8 }, + { 7, 13, -8 }, { 7, 13, -10 }, { 9, 14, -10 }, { 9, 14, -10 }, + { 9, 15, -12 }, { 11, 15, -12 }, { 15, 16, -12 } + } + }, + /* 10BPP/12BPC */ + { 410, 15, 5632, 11, 20, 19, 19, { + { 0, 11, 2 }, { 4, 12, 0 }, { 9, 13, 0 }, { 10, 14, -2 }, + { 11, 15, -4 }, { 11, 15, -6 }, { 11, 15, -8 }, { 11, 16, -8 }, + { 11, 17, -8 }, { 11, 17, -10 }, { 13, 18, -10 }, + { 13, 18, -10 }, { 13, 19, -12 }, { 15, 19, -12 }, + { 19, 20, -12 } + } + }, + /* 10BPP/14BPC */ + { 410, 15, 5632, 15, 24, 23, 23, { + { 0, 11, 2 }, { 5, 13, 0 }, { 11, 15, 0 }, { 13, 18, -2 }, + { 15, 19, -4 }, { 15, 19, -6 }, { 15, 19, -8 }, { 15, 20, -8 }, + { 15, 21, -8 }, { 15, 21, -10 }, { 17, 22, -10 }, + { 17, 22, -10 }, { 17, 23, -12 }, { 19, 23, -12 }, + { 23, 24, -12 } + } + }, + /* 10BPP/16BPC */ + { 410, 15, 5632, 19, 28, 27, 27, { + { 0, 11, 2 }, { 6, 14, 0 }, { 13, 17, 0 }, { 16, 20, -2 }, + { 19, 23, -4 }, { 19, 23, -6 }, { 19, 23, -8 }, { 19, 24, -8 }, + { 19, 25, -8 }, { 19, 25, -10 }, { 21, 26, -10 }, + { 21, 26, -10 }, { 21, 27, -12 }, { 23, 27, -12 }, + { 27, 28, -12 } + } + }, +}, +{ + /* 12BPP/8BPC */ + { 341, 15, 2048, 3, 12, 11, 11, { + { 0, 2, 2 }, { 0, 4, 0 }, { 1, 5, 0 }, { 1, 6, -2 }, + { 3, 7, -4 }, { 3, 7, -6 }, { 3, 7, -8 }, { 3, 8, -8 }, + { 3, 9, -8 }, { 3, 10, -10 }, { 5, 11, -10 }, + { 5, 12, -12 }, { 5, 13, -12 }, { 7, 13, -12 }, { 13, 15, -12 } + } + }, + /* 12BPP/10BPC */ + { 341, 15, 2048, 7, 16, 15, 15, { + { 0, 2, 2 }, { 2, 5, 0 }, { 3, 7, 0 }, { 4, 8, -2 }, + { 6, 9, -4 }, { 7, 10, -6 }, { 7, 11, -8 }, { 7, 12, -8 }, + { 7, 13, -8 }, { 7, 14, -10 }, { 9, 15, -10 }, { 9, 16, -12 }, + { 9, 17, -12 }, { 11, 17, -12 }, { 17, 19, -12 } + } + }, + /* 12BPP/12BPC */ + { 341, 15, 2048, 11, 20, 19, 19, { + { 0, 6, 2 }, { 4, 9, 0 }, { 7, 11, 0 }, { 8, 12, -2 }, + { 10, 13, -4 }, { 11, 14, -6 }, { 11, 15, -8 }, { 11, 16, -8 }, + { 11, 17, -8 }, { 11, 18, -10 }, { 13, 19, -10 }, + { 13, 20, -12 }, { 13, 21, -12 }, { 15, 21, -12 }, + { 21, 23, -12 } + } + }, + /* 12BPP/14BPC */ + { 341, 15, 2048, 15, 24, 23, 23, { + { 0, 6, 2 }, { 7, 10, 0 }, { 9, 13, 0 }, { 11, 16, -2 }, + { 14, 17, -4 }, { 15, 18, -6 }, { 15, 19, -8 }, { 15, 20, -8 }, + { 15, 20, -8 }, { 15, 21, -10 }, { 17, 21, -10 }, + { 17, 21, -12 }, { 17, 21, -12 }, { 19, 22, -12 }, + { 22, 23, -12 } + } + }, + /* 12BPP/16BPC */ + { 341, 15, 2048, 19, 28, 27, 27, { + { 0, 6, 2 }, { 6, 11, 0 }, { 11, 15, 0 }, { 14, 18, -2 }, + { 18, 21, -4 }, { 19, 22, -6 }, { 19, 23, -8 }, { 19, 24, -8 }, + { 19, 24, -8 }, { 19, 25, -10 }, { 21, 25, -10 }, + { 21, 25, -12 }, { 21, 25, -12 }, { 23, 26, -12 }, + { 26, 27, -12 } + } + }, +}, +{ + /* 15BPP/8BPC */ + { 273, 15, 2048, 3, 12, 11, 11, { + { 0, 0, 10 }, { 0, 1, 8 }, { 0, 1, 6 }, { 0, 2, 4 }, + { 1, 2, 2 }, { 1, 3, 0 }, { 1, 3, -2 }, { 2, 4, -4 }, + { 2, 5, -6 }, { 3, 5, -8 }, { 4, 6, -10 }, { 4, 7, -10 }, + { 5, 7, -12 }, { 7, 8, -12 }, { 8, 9, -12 } + } + }, + /* 15BPP/10BPC */ + { 273, 15, 2048, 7, 16, 15, 15, { + { 0, 2, 10 }, { 2, 5, 8 }, { 3, 5, 6 }, { 4, 6, 4 }, + { 5, 6, 2 }, { 5, 7, 0 }, { 5, 7, -2 }, { 6, 8, -4 }, + { 6, 9, -6 }, { 7, 9, -8 }, { 8, 10, -10 }, { 8, 11, -10 }, + { 9, 11, -12 }, { 11, 12, -12 }, { 12, 13, -12 } + } + }, + /* 15BPP/12BPC */ + { 273, 15, 2048, 11, 20, 19, 19, { + { 0, 4, 10 }, { 2, 7, 8 }, { 4, 9, 6 }, { 6, 11, 4 }, + { 9, 11, 2 }, { 9, 11, 0 }, { 9, 12, -2 }, { 10, 12, -4 }, + { 11, 13, -6 }, { 11, 13, -8 }, { 12, 14, -10 }, + { 13, 15, -10 }, { 13, 15, -12 }, { 15, 16, -12 }, + { 16, 17, -12 } + } + }, + /* 15BPP/14BPC */ + { 273, 15, 2048, 15, 24, 23, 23, { + { 0, 4, 10 }, { 3, 8, 8 }, { 6, 11, 6 }, { 9, 14, 4 }, + { 13, 15, 2 }, { 13, 15, 0 }, { 13, 16, -2 }, { 14, 16, -4 }, + { 15, 17, -6 }, { 15, 17, -8 }, { 16, 18, -10 }, + { 17, 19, -10 }, { 17, 19, -12 }, { 19, 20, -12 }, + { 20, 21, -12 } + } + }, + /* 15BPP/16BPC */ + { 273, 15, 2048, 19, 28, 27, 27, { + { 0, 4, 10 }, { 4, 9, 8 }, { 8, 13, 6 }, { 12, 17, 4 }, + { 17, 19, 2 }, { 17, 20, 0 }, { 17, 20, -2 }, { 18, 20, -4 }, + { 19, 21, -6 }, { 19, 21, -8 }, { 20, 22, -10 }, + { 21, 23, -10 }, { 21, 23, -12 }, { 23, 24, -12 }, + { 24, 25, -12 } + } + } +} + +}; + +static int get_row_index_for_rc_params(u16 compressed_bpp) +{ + switch (compressed_bpp) { + case 6: + return ROW_INDEX_6BPP; + case 8: + return ROW_INDEX_8BPP; + case 10: + return ROW_INDEX_10BPP; + case 12: + return ROW_INDEX_12BPP; + case 15: + return ROW_INDEX_15BPP; + default: + return -EINVAL; + } +} + +static int get_column_index_for_rc_params(u8 bits_per_component) +{ + switch (bits_per_component) { + case 8: + return COLUMN_INDEX_8BPC; + case 10: + return COLUMN_INDEX_10BPC; + case 12: + return COLUMN_INDEX_12BPC; + case 14: + return COLUMN_INDEX_14BPC; + case 16: + return COLUMN_INDEX_16BPC; + default: + return -EINVAL; + } +} + +static int intel_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg) +{ + unsigned long groups_per_line = 0; + unsigned long groups_total = 0; + unsigned long num_extra_mux_bits = 0; + unsigned long slice_bits = 0; + unsigned long hrd_delay = 0; + unsigned long final_scale = 0; + unsigned long rbs_min = 0; + + /* Number of groups used to code each line of a slice */ + groups_per_line = DIV_ROUND_UP(vdsc_cfg->slice_width, + DSC_RC_PIXELS_PER_GROUP); + + /* chunksize in Bytes */ + vdsc_cfg->slice_chunk_size = DIV_ROUND_UP(vdsc_cfg->slice_width * + vdsc_cfg->bits_per_pixel, + (8 * 16)); + + if (vdsc_cfg->convert_rgb) + num_extra_mux_bits = 3 * (vdsc_cfg->mux_word_size + + (4 * vdsc_cfg->bits_per_component + 4) + - 2); + else + num_extra_mux_bits = 3 * vdsc_cfg->mux_word_size + + (4 * vdsc_cfg->bits_per_component + 4) + + 2 * (4 * vdsc_cfg->bits_per_component) - 2; + /* Number of bits in one Slice */ + slice_bits = 8 * vdsc_cfg->slice_chunk_size * vdsc_cfg->slice_height; + + while ((num_extra_mux_bits > 0) && + ((slice_bits - num_extra_mux_bits) % vdsc_cfg->mux_word_size)) + num_extra_mux_bits--; + + if (groups_per_line < vdsc_cfg->initial_scale_value - 8) + vdsc_cfg->initial_scale_value = groups_per_line + 8; + + /* scale_decrement_interval calculation according to DSC spec 1.11 */ + if (vdsc_cfg->initial_scale_value > 8) + vdsc_cfg->scale_decrement_interval = groups_per_line / + (vdsc_cfg->initial_scale_value - 8); + else + vdsc_cfg->scale_decrement_interval = DSC_SCALE_DECREMENT_INTERVAL_MAX; + + vdsc_cfg->final_offset = vdsc_cfg->rc_model_size - + (vdsc_cfg->initial_xmit_delay * + vdsc_cfg->bits_per_pixel + 8) / 16 + num_extra_mux_bits; + + if (vdsc_cfg->final_offset >= vdsc_cfg->rc_model_size) { + DRM_DEBUG_KMS("FinalOfs < RcModelSze for this InitialXmitDelay\n"); + return -ERANGE; + } + + final_scale = (vdsc_cfg->rc_model_size * 8) / + (vdsc_cfg->rc_model_size - vdsc_cfg->final_offset); + if (vdsc_cfg->slice_height > 1) + /* + * NflBpgOffset is 16 bit value with 11 fractional bits + * hence we multiply by 2^11 for preserving the + * fractional part + */ + vdsc_cfg->nfl_bpg_offset = DIV_ROUND_UP((vdsc_cfg->first_line_bpg_offset << 11), + (vdsc_cfg->slice_height - 1)); + else + vdsc_cfg->nfl_bpg_offset = 0; + + /* 2^16 - 1 */ + if (vdsc_cfg->nfl_bpg_offset > 65535) { + DRM_DEBUG_KMS("NflBpgOffset is too large for this slice height\n"); + return -ERANGE; + } + + /* Number of groups used to code the entire slice */ + groups_total = groups_per_line * vdsc_cfg->slice_height; + + /* slice_bpg_offset is 16 bit value with 11 fractional bits */ + vdsc_cfg->slice_bpg_offset = DIV_ROUND_UP(((vdsc_cfg->rc_model_size - + vdsc_cfg->initial_offset + + num_extra_mux_bits) << 11), + groups_total); + + if (final_scale > 9) { + /* + * ScaleIncrementInterval = + * finaloffset/((NflBpgOffset + SliceBpgOffset)*8(finalscale - 1.125)) + * as (NflBpgOffset + SliceBpgOffset) has 11 bit fractional value, + * we need divide by 2^11 from pstDscCfg values + */ + vdsc_cfg->scale_increment_interval = + (vdsc_cfg->final_offset * (1 << 11)) / + ((vdsc_cfg->nfl_bpg_offset + + vdsc_cfg->slice_bpg_offset) * + (final_scale - 9)); + } else { + /* + * If finalScaleValue is less than or equal to 9, a value of 0 should + * be used to disable the scale increment at the end of the slice + */ + vdsc_cfg->scale_increment_interval = 0; + } + + if (vdsc_cfg->scale_increment_interval > 65535) { + DRM_DEBUG_KMS("ScaleIncrementInterval is large for slice height\n"); + return -ERANGE; + } + + /* + * DSC spec mentions that bits_per_pixel specifies the target + * bits/pixel (bpp) rate that is used by the encoder, + * in steps of 1/16 of a bit per pixel + */ + rbs_min = vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset + + DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay * + vdsc_cfg->bits_per_pixel, 16) + + groups_per_line * vdsc_cfg->first_line_bpg_offset; + + hrd_delay = DIV_ROUND_UP((rbs_min * 16), vdsc_cfg->bits_per_pixel); + vdsc_cfg->rc_bits = (hrd_delay * vdsc_cfg->bits_per_pixel) / 16; + vdsc_cfg->initial_dec_delay = hrd_delay - vdsc_cfg->initial_xmit_delay; + + return 0; +} + +int intel_dp_compute_dsc_params(struct intel_dp *intel_dp, + struct intel_crtc_state *pipe_config) +{ + struct drm_dsc_config *vdsc_cfg = &pipe_config->dp_dsc_cfg; + u16 compressed_bpp = pipe_config->dsc_params.compressed_bpp; + u8 i = 0; + int row_index = 0; + int column_index = 0; + u8 line_buf_depth = 0; + + vdsc_cfg->pic_width = pipe_config->base.adjusted_mode.crtc_hdisplay; + vdsc_cfg->pic_height = pipe_config->base.adjusted_mode.crtc_vdisplay; + vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width, + pipe_config->dsc_params.slice_count); + /* + * Slice Height of 8 works for all currently available panels. So start + * with that if pic_height is an integral multiple of 8. + * Eventually add logic to try multiple slice heights. + */ + if (vdsc_cfg->pic_height % 8 == 0) + vdsc_cfg->slice_height = 8; + else if (vdsc_cfg->pic_height % 4 == 0) + vdsc_cfg->slice_height = 4; + else + vdsc_cfg->slice_height = 2; + + /* Values filled from DSC Sink DPCD */ + vdsc_cfg->dsc_version_major = + (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] & + DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT; + vdsc_cfg->dsc_version_minor = + min(DSC_SUPPORTED_VERSION_MIN, + (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] & + DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT); + + vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] & + DP_DSC_RGB; + + line_buf_depth = drm_dp_dsc_sink_line_buf_depth(intel_dp->dsc_dpcd); + if (!line_buf_depth) { + DRM_DEBUG_KMS("DSC Sink Line Buffer Depth invalid\n"); + return -EINVAL; + } + if (vdsc_cfg->dsc_version_minor == 2) + vdsc_cfg->line_buf_depth = (line_buf_depth == DSC_1_2_MAX_LINEBUF_DEPTH_BITS) ? + DSC_1_2_MAX_LINEBUF_DEPTH_VAL : line_buf_depth; + else + vdsc_cfg->line_buf_depth = (line_buf_depth > DSC_1_1_MAX_LINEBUF_DEPTH_BITS) ? + DSC_1_1_MAX_LINEBUF_DEPTH_BITS : line_buf_depth; + + /* Gen 11 does not support YCbCr */ + vdsc_cfg->enable422 = false; + /* Gen 11 does not support VBR */ + vdsc_cfg->vbr_enable = false; + vdsc_cfg->block_pred_enable = + intel_dp->dsc_dpcd[DP_DSC_BLK_PREDICTION_SUPPORT - DP_DSC_SUPPORT] & + DP_DSC_BLK_PREDICTION_IS_SUPPORTED; + + /* Gen 11 only supports integral values of bpp */ + vdsc_cfg->bits_per_pixel = compressed_bpp << 4; + vdsc_cfg->bits_per_component = pipe_config->pipe_bpp / 3; + + for (i = 0; i < DSC_NUM_BUF_RANGES - 1; i++) { + /* + * six 0s are appended to the lsb of each threshold value + * internally in h/w. + * Only 8 bits are allowed for programming RcBufThreshold + */ + vdsc_cfg->rc_buf_thresh[i] = rc_buf_thresh[i] >> 6; + } + + /* + * For 6bpp, RC Buffer threshold 12 and 13 need a different value + * as per C Model + */ + if (compressed_bpp == 6) { + vdsc_cfg->rc_buf_thresh[12] = 0x7C; + vdsc_cfg->rc_buf_thresh[13] = 0x7D; + } + + row_index = get_row_index_for_rc_params(compressed_bpp); + column_index = + get_column_index_for_rc_params(vdsc_cfg->bits_per_component); + + if (row_index < 0 || column_index < 0) + return -EINVAL; + + vdsc_cfg->first_line_bpg_offset = + rc_params[row_index][column_index].first_line_bpg_offset; + vdsc_cfg->initial_xmit_delay = + rc_params[row_index][column_index].initial_xmit_delay; + vdsc_cfg->initial_offset = + rc_params[row_index][column_index].initial_offset; + vdsc_cfg->flatness_min_qp = + rc_params[row_index][column_index].flatness_min_qp; + vdsc_cfg->flatness_max_qp = + rc_params[row_index][column_index].flatness_max_qp; + vdsc_cfg->rc_quant_incr_limit0 = + rc_params[row_index][column_index].rc_quant_incr_limit0; + vdsc_cfg->rc_quant_incr_limit1 = + rc_params[row_index][column_index].rc_quant_incr_limit1; + + for (i = 0; i < DSC_NUM_BUF_RANGES; i++) { + vdsc_cfg->rc_range_params[i].range_min_qp = + rc_params[row_index][column_index].rc_range_params[i].range_min_qp; + vdsc_cfg->rc_range_params[i].range_max_qp = + rc_params[row_index][column_index].rc_range_params[i].range_max_qp; + /* + * Range BPG Offset uses 2's complement and is only a 6 bits. So + * mask it to get only 6 bits. + */ + vdsc_cfg->rc_range_params[i].range_bpg_offset = + rc_params[row_index][column_index].rc_range_params[i].range_bpg_offset & + DSC_RANGE_BPG_OFFSET_MASK; + } + + /* + * BitsPerComponent value determines mux_word_size: + * When BitsPerComponent is 12bpc, muxWordSize will be equal to 64 bits + * When BitsPerComponent is 8 or 10bpc, muxWordSize will be equal to + * 48 bits + */ + if (vdsc_cfg->bits_per_component == 8 || + vdsc_cfg->bits_per_component == 10) + vdsc_cfg->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; + else if (vdsc_cfg->bits_per_component == 12) + vdsc_cfg->mux_word_size = DSC_MUX_WORD_SIZE_12_BPC; + + /* RC_MODEL_SIZE is a constant across all configurations */ + vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + /* InitialScaleValue is a 6 bit value with 3 fractional bits (U3.3) */ + vdsc_cfg->initial_scale_value = (vdsc_cfg->rc_model_size << 3) / + (vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset); + + return intel_compute_rc_parameters(vdsc_cfg); +} + +enum intel_display_power_domain +intel_dsc_power_domain(const struct intel_crtc_state *crtc_state) +{ + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + + /* + * On ICL VDSC/joining for eDP transcoder uses a separate power well PW2 + * This requires POWER_DOMAIN_TRANSCODER_EDP_VDSC power domain. + * For any other transcoder, VDSC/joining uses the power well associated + * with the pipe/transcoder in use. Hence another reference on the + * transcoder power domain will suffice. + */ + if (cpu_transcoder == TRANSCODER_EDP) + return POWER_DOMAIN_TRANSCODER_EDP_VDSC; + else + return POWER_DOMAIN_TRANSCODER(cpu_transcoder); +} + +static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dp_dsc_cfg; + enum pipe pipe = crtc->pipe; + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; + u32 pps_val = 0; + u32 rc_buf_thresh_dword[4]; + u32 rc_range_params_dword[8]; + u8 num_vdsc_instances = (crtc_state->dsc_params.dsc_split) ? 2 : 1; + int i = 0; + + /* Populate PICTURE_PARAMETER_SET_0 registers */ + pps_val = DSC_VER_MAJ | vdsc_cfg->dsc_version_minor << + DSC_VER_MIN_SHIFT | + vdsc_cfg->bits_per_component << DSC_BPC_SHIFT | + vdsc_cfg->line_buf_depth << DSC_LINE_BUF_DEPTH_SHIFT; + if (vdsc_cfg->block_pred_enable) + pps_val |= DSC_BLOCK_PREDICTION; + if (vdsc_cfg->convert_rgb) + pps_val |= DSC_COLOR_SPACE_CONVERSION; + if (vdsc_cfg->enable422) + pps_val |= DSC_422_ENABLE; + if (vdsc_cfg->vbr_enable) + pps_val |= DSC_VBR_ENABLE; + DRM_INFO("PPS0 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_0, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_0, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_1 registers */ + pps_val = 0; + pps_val |= DSC_BPP(vdsc_cfg->bits_per_pixel); + DRM_INFO("PPS1 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_1, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_1, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_2 registers */ + pps_val = 0; + pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) | + DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances); + DRM_INFO("PPS2 = 0x%08x\n", pps_val); + if (encoder->type == INTEL_OUTPUT_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_2, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_3 registers */ + pps_val = 0; + pps_val |= DSC_SLICE_HEIGHT(vdsc_cfg->slice_height) | + DSC_SLICE_WIDTH(vdsc_cfg->slice_width); + DRM_INFO("PPS3 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_3, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_3, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_4 registers */ + pps_val = 0; + pps_val |= DSC_INITIAL_XMIT_DELAY(vdsc_cfg->initial_xmit_delay) | + DSC_INITIAL_DEC_DELAY(vdsc_cfg->initial_dec_delay); + DRM_INFO("PPS4 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_4, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_4, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_5 registers */ + pps_val = 0; + pps_val |= DSC_SCALE_INC_INT(vdsc_cfg->scale_increment_interval) | + DSC_SCALE_DEC_INT(vdsc_cfg->scale_decrement_interval); + DRM_INFO("PPS5 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_5, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_5, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_6 registers */ + pps_val = 0; + pps_val |= DSC_INITIAL_SCALE_VALUE(vdsc_cfg->initial_scale_value) | + DSC_FIRST_LINE_BPG_OFFSET(vdsc_cfg->first_line_bpg_offset) | + DSC_FLATNESS_MIN_QP(vdsc_cfg->flatness_min_qp) | + DSC_FLATNESS_MAX_QP(vdsc_cfg->flatness_max_qp); + DRM_INFO("PPS6 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_6, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_6, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_7 registers */ + pps_val = 0; + pps_val |= DSC_SLICE_BPG_OFFSET(vdsc_cfg->slice_bpg_offset) | + DSC_NFL_BPG_OFFSET(vdsc_cfg->nfl_bpg_offset); + DRM_INFO("PPS7 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_7, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_7, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_8 registers */ + pps_val = 0; + pps_val |= DSC_FINAL_OFFSET(vdsc_cfg->final_offset) | + DSC_INITIAL_OFFSET(vdsc_cfg->initial_offset); + DRM_INFO("PPS8 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_8, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_8, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_9 registers */ + pps_val = 0; + pps_val |= DSC_RC_MODEL_SIZE(DSC_RC_MODEL_SIZE_CONST) | + DSC_RC_EDGE_FACTOR(DSC_RC_EDGE_FACTOR_CONST); + DRM_INFO("PPS9 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_9, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_9, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe), + pps_val); + } + + /* Populate PICTURE_PARAMETER_SET_10 registers */ + pps_val = 0; + pps_val |= DSC_RC_QUANT_INC_LIMIT0(vdsc_cfg->rc_quant_incr_limit0) | + DSC_RC_QUANT_INC_LIMIT1(vdsc_cfg->rc_quant_incr_limit1) | + DSC_RC_TARGET_OFF_HIGH(DSC_RC_TGT_OFFSET_HI_CONST) | + DSC_RC_TARGET_OFF_LOW(DSC_RC_TGT_OFFSET_LO_CONST); + DRM_INFO("PPS10 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_10, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_10, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe), + pps_val); + } + + /* Populate Picture parameter set 16 */ + pps_val = 0; + pps_val |= DSC_SLICE_CHUNK_SIZE(vdsc_cfg->slice_chunk_size) | + DSC_SLICE_PER_LINE((vdsc_cfg->pic_width / num_vdsc_instances) / + vdsc_cfg->slice_width) | + DSC_SLICE_ROW_PER_FRAME(vdsc_cfg->pic_height / + vdsc_cfg->slice_height); + DRM_INFO("PPS16 = 0x%08x\n", pps_val); + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_PICTURE_PARAMETER_SET_16, pps_val); + /* + * If 2 VDSC instances are needed, configure PPS for second + * VDSC + */ + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(DSCC_PICTURE_PARAMETER_SET_16, pps_val); + } else { + I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe), pps_val); + if (crtc_state->dsc_params.dsc_split) + I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe), + pps_val); + } + + /* Populate the RC_BUF_THRESH registers */ + memset(rc_buf_thresh_dword, 0, sizeof(rc_buf_thresh_dword)); + for (i = 0; i < DSC_NUM_BUF_RANGES - 1; i++) { + rc_buf_thresh_dword[i / 4] |= + (u32)(vdsc_cfg->rc_buf_thresh[i] << + BITS_PER_BYTE * (i % 4)); + DRM_INFO(" RC_BUF_THRESH%d = 0x%08x\n", i, + rc_buf_thresh_dword[i / 4]); + } + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_RC_BUF_THRESH_0, rc_buf_thresh_dword[0]); + I915_WRITE(DSCA_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]); + I915_WRITE(DSCA_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]); + I915_WRITE(DSCA_RC_BUF_THRESH_1_UDW, rc_buf_thresh_dword[3]); + if (crtc_state->dsc_params.dsc_split) { + I915_WRITE(DSCC_RC_BUF_THRESH_0, + rc_buf_thresh_dword[0]); + I915_WRITE(DSCC_RC_BUF_THRESH_0_UDW, + rc_buf_thresh_dword[1]); + I915_WRITE(DSCC_RC_BUF_THRESH_1, + rc_buf_thresh_dword[2]); + I915_WRITE(DSCC_RC_BUF_THRESH_1_UDW, + rc_buf_thresh_dword[3]); + } + } else { + I915_WRITE(ICL_DSC0_RC_BUF_THRESH_0(pipe), + rc_buf_thresh_dword[0]); + I915_WRITE(ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe), + rc_buf_thresh_dword[1]); + I915_WRITE(ICL_DSC0_RC_BUF_THRESH_1(pipe), + rc_buf_thresh_dword[2]); + I915_WRITE(ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe), + rc_buf_thresh_dword[3]); + if (crtc_state->dsc_params.dsc_split) { + I915_WRITE(ICL_DSC1_RC_BUF_THRESH_0(pipe), + rc_buf_thresh_dword[0]); + I915_WRITE(ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe), + rc_buf_thresh_dword[1]); + I915_WRITE(ICL_DSC1_RC_BUF_THRESH_1(pipe), + rc_buf_thresh_dword[2]); + I915_WRITE(ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe), + rc_buf_thresh_dword[3]); + } + } + + /* Populate the RC_RANGE_PARAMETERS registers */ + memset(rc_range_params_dword, 0, sizeof(rc_range_params_dword)); + for (i = 0; i < DSC_NUM_BUF_RANGES; i++) { + rc_range_params_dword[i / 2] |= + (u32)(((vdsc_cfg->rc_range_params[i].range_bpg_offset << + RC_BPG_OFFSET_SHIFT) | + (vdsc_cfg->rc_range_params[i].range_max_qp << + RC_MAX_QP_SHIFT) | + (vdsc_cfg->rc_range_params[i].range_min_qp << + RC_MIN_QP_SHIFT)) << 16 * (i % 2)); + DRM_INFO(" RC_RANGE_PARAM_%d = 0x%08x\n", i, + rc_range_params_dword[i / 2]); + } + if (cpu_transcoder == TRANSCODER_EDP) { + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0, + rc_range_params_dword[0]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_0_UDW, + rc_range_params_dword[1]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_1, + rc_range_params_dword[2]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_1_UDW, + rc_range_params_dword[3]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_2, + rc_range_params_dword[4]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_2_UDW, + rc_range_params_dword[5]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_3, + rc_range_params_dword[6]); + I915_WRITE(DSCA_RC_RANGE_PARAMETERS_3_UDW, + rc_range_params_dword[7]); + if (crtc_state->dsc_params.dsc_split) { + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_0, + rc_range_params_dword[0]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_0_UDW, + rc_range_params_dword[1]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_1, + rc_range_params_dword[2]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_1_UDW, + rc_range_params_dword[3]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_2, + rc_range_params_dword[4]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_2_UDW, + rc_range_params_dword[5]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_3, + rc_range_params_dword[6]); + I915_WRITE(DSCC_RC_RANGE_PARAMETERS_3_UDW, + rc_range_params_dword[7]); + } + } else { + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe), + rc_range_params_dword[0]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe), + rc_range_params_dword[1]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe), + rc_range_params_dword[2]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe), + rc_range_params_dword[3]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe), + rc_range_params_dword[4]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe), + rc_range_params_dword[5]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe), + rc_range_params_dword[6]); + I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe), + rc_range_params_dword[7]); + if (crtc_state->dsc_params.dsc_split) { + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe), + rc_range_params_dword[0]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe), + rc_range_params_dword[1]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe), + rc_range_params_dword[2]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe), + rc_range_params_dword[3]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe), + rc_range_params_dword[4]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe), + rc_range_params_dword[5]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe), + rc_range_params_dword[6]); + I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe), + rc_range_params_dword[7]); + } + } +} + +static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp); + const struct drm_dsc_config *vdsc_cfg = &crtc_state->dp_dsc_cfg; + struct drm_dsc_pps_infoframe dp_dsc_pps_sdp; + + /* Prepare DP SDP PPS header as per DP 1.4 spec, Table 2-123 */ + drm_dsc_dp_pps_header_init(&dp_dsc_pps_sdp); + + /* Fill the PPS payload bytes as per DSC spec 1.2 Table 4-1 */ + drm_dsc_pps_infoframe_pack(&dp_dsc_pps_sdp, vdsc_cfg); + + intel_dig_port->write_infoframe(encoder, crtc_state, + DP_SDP_PPS, &dp_dsc_pps_sdp, + sizeof(dp_dsc_pps_sdp)); +} + +void intel_dsc_enable(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + enum pipe pipe = crtc->pipe; + i915_reg_t dss_ctl1_reg, dss_ctl2_reg; + u32 dss_ctl1_val = 0; + u32 dss_ctl2_val = 0; + + if (!crtc_state->dsc_params.compression_enable) + return; + + /* Enable Power wells for VDSC/joining */ + intel_display_power_get(dev_priv, + intel_dsc_power_domain(crtc_state)); + + intel_configure_pps_for_dsc_encoder(encoder, crtc_state); + + intel_dp_write_dsc_pps_sdp(encoder, crtc_state); + + if (crtc_state->cpu_transcoder == TRANSCODER_EDP) { + dss_ctl1_reg = DSS_CTL1; + dss_ctl2_reg = DSS_CTL2; + } else { + dss_ctl1_reg = ICL_PIPE_DSS_CTL1(pipe); + dss_ctl2_reg = ICL_PIPE_DSS_CTL2(pipe); + } + dss_ctl2_val |= LEFT_BRANCH_VDSC_ENABLE; + if (crtc_state->dsc_params.dsc_split) { + dss_ctl2_val |= RIGHT_BRANCH_VDSC_ENABLE; + dss_ctl1_val |= JOINER_ENABLE; + } + I915_WRITE(dss_ctl1_reg, dss_ctl1_val); + I915_WRITE(dss_ctl2_reg, dss_ctl2_val); +} + +void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; + i915_reg_t dss_ctl1_reg, dss_ctl2_reg; + u32 dss_ctl1_val = 0, dss_ctl2_val = 0; + + if (!old_crtc_state->dsc_params.compression_enable) + return; + + if (old_crtc_state->cpu_transcoder == TRANSCODER_EDP) { + dss_ctl1_reg = DSS_CTL1; + dss_ctl2_reg = DSS_CTL2; + } else { + dss_ctl1_reg = ICL_PIPE_DSS_CTL1(pipe); + dss_ctl2_reg = ICL_PIPE_DSS_CTL2(pipe); + } + dss_ctl1_val = I915_READ(dss_ctl1_reg); + if (dss_ctl1_val & JOINER_ENABLE) + dss_ctl1_val &= ~JOINER_ENABLE; + I915_WRITE(dss_ctl1_reg, dss_ctl1_val); + + dss_ctl2_val = I915_READ(dss_ctl2_reg); + if (dss_ctl2_val & LEFT_BRANCH_VDSC_ENABLE || + dss_ctl2_val & RIGHT_BRANCH_VDSC_ENABLE) + dss_ctl2_val &= ~(LEFT_BRANCH_VDSC_ENABLE | + RIGHT_BRANCH_VDSC_ENABLE); + I915_WRITE(dss_ctl2_reg, dss_ctl2_val); + + /* Disable Power wells for VDSC/joining */ + intel_display_power_put(dev_priv, + intel_dsc_power_domain(old_crtc_state)); +} diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index ca1f78a42b17..4f41e326f3f3 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -48,58 +48,112 @@ * - Public functions to init or apply the given workaround type. */ -static void wa_add(struct drm_i915_private *i915, - i915_reg_t reg, const u32 mask, const u32 val) +static void wa_init_start(struct i915_wa_list *wal, const char *name) { - struct i915_workarounds *wa = &i915->workarounds; - unsigned int start = 0, end = wa->count; - unsigned int addr = i915_mmio_reg_offset(reg); - struct i915_wa_reg *r; + wal->name = name; +} + +#define WA_LIST_CHUNK (1 << 4) + +static void wa_init_finish(struct i915_wa_list *wal) +{ + /* Trim unused entries. */ + if (!IS_ALIGNED(wal->count, WA_LIST_CHUNK)) { + struct i915_wa *list = kmemdup(wal->list, + wal->count * sizeof(*list), + GFP_KERNEL); + + if (list) { + kfree(wal->list); + wal->list = list; + } + } + + if (!wal->count) + return; + + DRM_DEBUG_DRIVER("Initialized %u %s workarounds\n", + wal->wa_count, wal->name); +} + +static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) +{ + unsigned int addr = i915_mmio_reg_offset(wa->reg); + unsigned int start = 0, end = wal->count; + const unsigned int grow = WA_LIST_CHUNK; + struct i915_wa *wa_; + + GEM_BUG_ON(!is_power_of_2(grow)); + + if (IS_ALIGNED(wal->count, grow)) { /* Either uninitialized or full. */ + struct i915_wa *list; + + list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), + GFP_KERNEL); + if (!list) { + DRM_ERROR("No space for workaround init!\n"); + return; + } + + if (wal->list) + memcpy(list, wal->list, sizeof(*wa) * wal->count); + + wal->list = list; + } while (start < end) { unsigned int mid = start + (end - start) / 2; - if (wa->reg[mid].addr < addr) { + if (i915_mmio_reg_offset(wal->list[mid].reg) < addr) { start = mid + 1; - } else if (wa->reg[mid].addr > addr) { + } else if (i915_mmio_reg_offset(wal->list[mid].reg) > addr) { end = mid; } else { - r = &wa->reg[mid]; + wa_ = &wal->list[mid]; - if ((mask & ~r->mask) == 0) { + if ((wa->mask & ~wa_->mask) == 0) { DRM_ERROR("Discarding overwritten w/a for reg %04x (mask: %08x, value: %08x)\n", - addr, r->mask, r->value); + i915_mmio_reg_offset(wa_->reg), + wa_->mask, wa_->val); - r->value &= ~mask; + wa_->val &= ~wa->mask; } - r->value |= val; - r->mask |= mask; + wal->wa_count++; + wa_->val |= wa->val; + wa_->mask |= wa->mask; return; } } - if (WARN_ON_ONCE(wa->count >= I915_MAX_WA_REGS)) { - DRM_ERROR("Dropping w/a for reg %04x (mask: %08x, value: %08x)\n", - addr, mask, val); - return; - } - - r = &wa->reg[wa->count++]; - r->addr = addr; - r->value = val; - r->mask = mask; + wal->wa_count++; + wa_ = &wal->list[wal->count++]; + *wa_ = *wa; - while (r-- > wa->reg) { - GEM_BUG_ON(r[0].addr == r[1].addr); - if (r[1].addr > r[0].addr) + while (wa_-- > wal->list) { + GEM_BUG_ON(i915_mmio_reg_offset(wa_[0].reg) == + i915_mmio_reg_offset(wa_[1].reg)); + if (i915_mmio_reg_offset(wa_[1].reg) > + i915_mmio_reg_offset(wa_[0].reg)) break; - swap(r[1], r[0]); + swap(wa_[1], wa_[0]); } } -#define WA_REG(addr, mask, val) wa_add(dev_priv, (addr), (mask), (val)) +static void +__wa_add(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, u32 val) +{ + struct i915_wa wa = { + .reg = reg, + .mask = mask, + .val = val + }; + + _wa_add(wal, &wa); +} + +#define WA_REG(addr, mask, val) __wa_add(wal, (addr), (mask), (val)) #define WA_SET_BIT_MASKED(addr, mask) \ WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask)) @@ -110,8 +164,10 @@ static void wa_add(struct drm_i915_private *i915, #define WA_SET_FIELD_MASKED(addr, mask, value) \ WA_REG(addr, (mask), _MASKED_FIELD(mask, value)) -static int gen8_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine) { + struct i915_wa_list *wal = &engine->ctx_wa_list; + WA_SET_BIT_MASKED(INSTPM, INSTPM_FORCE_ORDERING); /* WaDisableAsyncFlipPerfMode:bdw,chv */ @@ -155,17 +211,14 @@ static int gen8_ctx_workarounds_init(struct drm_i915_private *dev_priv) WA_SET_FIELD_MASKED(GEN7_GT_MODE, GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4); - - return 0; } -static int bdw_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void bdw_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; - ret = gen8_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + gen8_ctx_workarounds_init(engine); /* WaDisableThreadStallDopClockGating:bdw (pre-production) */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); @@ -185,31 +238,28 @@ static int bdw_ctx_workarounds_init(struct drm_i915_private *dev_priv) /* WaForceContextSaveRestoreNonCoherent:bdw */ HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT | /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */ - (IS_BDW_GT3(dev_priv) ? HDC_FENCE_DEST_SLM_DISABLE : 0)); - - return 0; + (IS_BDW_GT3(i915) ? HDC_FENCE_DEST_SLM_DISABLE : 0)); } -static int chv_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void chv_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; + struct i915_wa_list *wal = &engine->ctx_wa_list; - ret = gen8_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + gen8_ctx_workarounds_init(engine); /* WaDisableThreadStallDopClockGating:chv */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, STALL_DOP_GATING_DISABLE); /* Improve HiZ throughput on CHV. */ WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X); - - return 0; } -static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine) { - if (HAS_LLC(dev_priv)) { + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; + + if (HAS_LLC(i915)) { /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl * * Must match Display Engine. See @@ -228,7 +278,7 @@ static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv) PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* Syncing dependencies between camera and graphics:skl,bxt,kbl */ - if (!IS_COFFEELAKE(dev_priv)) + if (!IS_COFFEELAKE(i915)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC); @@ -271,9 +321,7 @@ static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv) HDC_FORCE_NON_COHERENT); /* WaDisableSamplerPowerBypassForSOPingPong:skl,bxt,kbl,cfl */ - if (IS_SKYLAKE(dev_priv) || - IS_KABYLAKE(dev_priv) || - IS_COFFEELAKE(dev_priv)) + if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915)) WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3, GEN8_SAMPLER_POWER_BYPASS_DIS); @@ -300,14 +348,14 @@ static int gen9_ctx_workarounds_init(struct drm_i915_private *dev_priv) GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); /* WaClearHIZ_WM_CHICKEN3:bxt,glk */ - if (IS_GEN9_LP(dev_priv)) + if (IS_GEN9_LP(i915)) WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ); - - return 0; } -static int skl_tune_iz_hashing(struct drm_i915_private *dev_priv) +static void skl_tune_iz_hashing(struct intel_engine_cs *engine) { + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; u8 vals[3] = { 0, 0, 0 }; unsigned int i; @@ -318,7 +366,7 @@ static int skl_tune_iz_hashing(struct drm_i915_private *dev_priv) * Only consider slices where one, and only one, subslice has 7 * EUs */ - if (!is_power_of_2(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i])) + if (!is_power_of_2(INTEL_INFO(i915)->sseu.subslice_7eu[i])) continue; /* @@ -327,12 +375,12 @@ static int skl_tune_iz_hashing(struct drm_i915_private *dev_priv) * * -> 0 <= ss <= 3; */ - ss = ffs(INTEL_INFO(dev_priv)->sseu.subslice_7eu[i]) - 1; + ss = ffs(INTEL_INFO(i915)->sseu.subslice_7eu[i]) - 1; vals[i] = 3 - ss; } if (vals[0] == 0 && vals[1] == 0 && vals[2] == 0) - return 0; + return; /* Tune IZ hashing. See intel_device_info_runtime_init() */ WA_SET_FIELD_MASKED(GEN7_GT_MODE, @@ -342,28 +390,19 @@ static int skl_tune_iz_hashing(struct drm_i915_private *dev_priv) GEN9_IZ_HASHING(2, vals[2]) | GEN9_IZ_HASHING(1, vals[1]) | GEN9_IZ_HASHING(0, vals[0])); - - return 0; } -static int skl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void skl_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; - - ret = gen9_ctx_workarounds_init(dev_priv); - if (ret) - return ret; - - return skl_tune_iz_hashing(dev_priv); + gen9_ctx_workarounds_init(engine); + skl_tune_iz_hashing(engine); } -static int bxt_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void bxt_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; + struct i915_wa_list *wal = &engine->ctx_wa_list; - ret = gen9_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + gen9_ctx_workarounds_init(engine); /* WaDisableThreadStallDopClockGating:bxt */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, @@ -372,57 +411,41 @@ static int bxt_ctx_workarounds_init(struct drm_i915_private *dev_priv) /* WaToEnableHwFixForPushConstHWBug:bxt */ WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - return 0; } -static int kbl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; - - ret = gen9_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; - /* WaDisableFenceDestinationToSLM:kbl (pre-prod) */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_A0)) - WA_SET_BIT_MASKED(HDC_CHICKEN0, - HDC_FENCE_DEST_SLM_DISABLE); + gen9_ctx_workarounds_init(engine); /* WaToEnableHwFixForPushConstHWBug:kbl */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER)) + if (IS_KBL_REVID(i915, KBL_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableSbeCacheDispatchPortSharing:kbl */ WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); - - return 0; } -static int glk_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void glk_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; + struct i915_wa_list *wal = &engine->ctx_wa_list; - ret = gen9_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + gen9_ctx_workarounds_init(engine); /* WaToEnableHwFixForPushConstHWBug:glk */ WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); - - return 0; } -static int cfl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void cfl_ctx_workarounds_init(struct intel_engine_cs *engine) { - int ret; + struct i915_wa_list *wal = &engine->ctx_wa_list; - ret = gen9_ctx_workarounds_init(dev_priv); - if (ret) - return ret; + gen9_ctx_workarounds_init(engine); /* WaToEnableHwFixForPushConstHWBug:cfl */ WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, @@ -431,18 +454,19 @@ static int cfl_ctx_workarounds_init(struct drm_i915_private *dev_priv) /* WaDisableSbeCacheDispatchPortSharing:cfl */ WA_SET_BIT_MASKED(GEN7_HALF_SLICE_CHICKEN1, GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE); - - return 0; } -static int cnl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void cnl_ctx_workarounds_init(struct intel_engine_cs *engine) { + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; + /* WaForceContextSaveRestoreNonCoherent:cnl */ WA_SET_BIT_MASKED(CNL_HDC_CHICKEN0, HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT); /* WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) + if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0)) WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, THROTTLE_12_5); /* WaDisableReplayBufferBankArbitrationOptimization:cnl */ @@ -450,7 +474,7 @@ static int cnl_ctx_workarounds_init(struct drm_i915_private *dev_priv) GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); /* WaDisableEnhancedSBEVertexCaching:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, 0, CNL_REVID_B0)) + if (IS_CNL_REVID(i915, 0, CNL_REVID_B0)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE); @@ -470,16 +494,17 @@ static int cnl_ctx_workarounds_init(struct drm_i915_private *dev_priv) /* WaDisableEarlyEOT:cnl */ WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN, DISABLE_EARLY_EOT); - - return 0; } -static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) +static void icl_ctx_workarounds_init(struct intel_engine_cs *engine) { + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; + /* Wa_1604370585:icl (pre-prod) * Formerly known as WaPushConstantDereferenceHoldDisable */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, PUSH_CONSTANT_DEREF_DISABLE); @@ -495,7 +520,7 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) /* Wa_2006611047:icl (pre-prod) * Formerly known as WaDisableImprovedTdlClkGating */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0)) WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2, GEN11_TDL_CLOCK_GATING_FIX_DISABLE); @@ -504,70 +529,67 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv) GEN11_STATE_CACHE_REDIRECT_TO_CS); /* Wa_2006665173:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0)) WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3, GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC); - - return 0; } -int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv) +void intel_engine_init_ctx_wa(struct intel_engine_cs *engine) { - int err = 0; - - dev_priv->workarounds.count = 0; - - if (INTEL_GEN(dev_priv) < 8) - err = 0; - else if (IS_BROADWELL(dev_priv)) - err = bdw_ctx_workarounds_init(dev_priv); - else if (IS_CHERRYVIEW(dev_priv)) - err = chv_ctx_workarounds_init(dev_priv); - else if (IS_SKYLAKE(dev_priv)) - err = skl_ctx_workarounds_init(dev_priv); - else if (IS_BROXTON(dev_priv)) - err = bxt_ctx_workarounds_init(dev_priv); - else if (IS_KABYLAKE(dev_priv)) - err = kbl_ctx_workarounds_init(dev_priv); - else if (IS_GEMINILAKE(dev_priv)) - err = glk_ctx_workarounds_init(dev_priv); - else if (IS_COFFEELAKE(dev_priv)) - err = cfl_ctx_workarounds_init(dev_priv); - else if (IS_CANNONLAKE(dev_priv)) - err = cnl_ctx_workarounds_init(dev_priv); - else if (IS_ICELAKE(dev_priv)) - err = icl_ctx_workarounds_init(dev_priv); + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->ctx_wa_list; + + wa_init_start(wal, "context"); + + if (INTEL_GEN(i915) < 8) + return; + else if (IS_BROADWELL(i915)) + bdw_ctx_workarounds_init(engine); + else if (IS_CHERRYVIEW(i915)) + chv_ctx_workarounds_init(engine); + else if (IS_SKYLAKE(i915)) + skl_ctx_workarounds_init(engine); + else if (IS_BROXTON(i915)) + bxt_ctx_workarounds_init(engine); + else if (IS_KABYLAKE(i915)) + kbl_ctx_workarounds_init(engine); + else if (IS_GEMINILAKE(i915)) + glk_ctx_workarounds_init(engine); + else if (IS_COFFEELAKE(i915)) + cfl_ctx_workarounds_init(engine); + else if (IS_CANNONLAKE(i915)) + cnl_ctx_workarounds_init(engine); + else if (IS_ICELAKE(i915)) + icl_ctx_workarounds_init(engine); else - MISSING_CASE(INTEL_GEN(dev_priv)); - if (err) - return err; + MISSING_CASE(INTEL_GEN(i915)); - DRM_DEBUG_DRIVER("Number of context specific w/a: %d\n", - dev_priv->workarounds.count); - return 0; + wa_init_finish(wal); } -int intel_ctx_workarounds_emit(struct i915_request *rq) +int intel_engine_emit_ctx_wa(struct i915_request *rq) { - struct i915_workarounds *w = &rq->i915->workarounds; + struct i915_wa_list *wal = &rq->engine->ctx_wa_list; + struct i915_wa *wa; + unsigned int i; u32 *cs; - int ret, i; + int ret; - if (w->count == 0) + if (wal->count == 0) return 0; ret = rq->engine->emit_flush(rq, EMIT_BARRIER); if (ret) return ret; - cs = intel_ring_begin(rq, (w->count * 2 + 2)); + cs = intel_ring_begin(rq, (wal->count * 2 + 2)); if (IS_ERR(cs)) return PTR_ERR(cs); - *cs++ = MI_LOAD_REGISTER_IMM(w->count); - for (i = 0; i < w->count; i++) { - *cs++ = w->reg[i].addr; - *cs++ = w->reg[i].value; + *cs++ = MI_LOAD_REGISTER_IMM(wal->count); + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { + *cs++ = i915_mmio_reg_offset(wa->reg); + *cs++ = wa->val; } *cs++ = MI_NOOP; @@ -580,160 +602,149 @@ int intel_ctx_workarounds_emit(struct i915_request *rq) return 0; } -static void bdw_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) +{ + struct i915_wa wa = { + .reg = reg, + .mask = val, + .val = _MASKED_BIT_ENABLE(val) + }; + + _wa_add(wal, &wa); +} + +static void +wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, + u32 val) { + struct i915_wa wa = { + .reg = reg, + .mask = mask, + .val = val + }; + + _wa_add(wal, &wa); } -static void chv_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { + wa_write_masked_or(wal, reg, ~0, val); } -static void gen9_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { - /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ - I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, - _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + wa_write_masked_or(wal, reg, val, val); +} - /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); +static void gen9_gt_workarounds_init(struct drm_i915_private *i915) +{ + struct i915_wa_list *wal = &i915->gt_wa_list; /* WaDisableKillLogic:bxt,skl,kbl */ - if (!IS_COFFEELAKE(dev_priv)) - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - ECOCHK_DIS_TLB); + if (!IS_COFFEELAKE(i915)) + wa_write_or(wal, + GAM_ECOCHK, + ECOCHK_DIS_TLB); - if (HAS_LLC(dev_priv)) { + if (HAS_LLC(i915)) { /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl * * Must match Display Engine. See * WaCompressedResourceDisplayNewHashMode. */ - I915_WRITE(MMCD_MISC_CTRL, - I915_READ(MMCD_MISC_CTRL) | - MMCD_PCLA | - MMCD_HOTSPOT_EN); + wa_write_or(wal, + MMCD_MISC_CTRL, + MMCD_PCLA | MMCD_HOTSPOT_EN); } /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - - /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ - if (IS_GEN9_LP(dev_priv)) { - u32 val = I915_READ(GEN8_L3SQCREG1); - - val &= ~L3_PRIO_CREDITS_MASK; - val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2); - I915_WRITE(GEN8_L3SQCREG1, val); - } - - /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - I915_WRITE(GEN8_L3SQCREG4, - I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_write_or(wal, + GAM_ECOCHK, + BDW_DISABLE_HDC_INVALIDATION); } -static void skl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void skl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:skl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableGafsUnitClkGating:skl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER)) - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + if (IS_SKL_REVID(i915, SKL_REVID_H0, REVID_FOREVER)) + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void bxt_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void bxt_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaDisablePooledEuLoadBalancingFix:bxt */ - I915_WRITE(FF_SLICE_CS_CHICKEN2, - _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE)); + gen9_gt_workarounds_init(i915); /* WaInPlaceDecompressionHang:bxt */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void kbl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:kbl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + if (IS_KBL_REVID(i915, 0, KBL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); /* WaDisableGafsUnitClkGating:kbl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:kbl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_E0)) { - struct intel_engine_cs *engine; - unsigned int tmp; - - for_each_engine(engine, dev_priv, tmp) { - if (engine->id == RCS) - continue; - - I915_WRITE(RING_SEMA_WAIT_POLL(engine->mmio_base), 1); - } - } + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void glk_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + gen9_gt_workarounds_init(i915); } -static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cfl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:cfl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableGafsUnitClkGating:cfl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:cfl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } static void wa_init_mcr(struct drm_i915_private *dev_priv) { const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); - u32 mcr; + struct i915_wa_list *wal = &dev_priv->gt_wa_list; u32 mcr_slice_subslice_mask; /* @@ -770,8 +781,6 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) WARN_ON((enabled_mask & disabled_mask) != enabled_mask); } - mcr = I915_READ(GEN8_MCR_SELECTOR); - if (INTEL_GEN(dev_priv) >= 11) mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK; @@ -789,186 +798,220 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) * occasions, such as INSTDONE, where this value is dependent * on s/ss combo, the read should be done with read_subslice_reg. */ - mcr &= ~mcr_slice_subslice_mask; - mcr |= intel_calculate_mcr_s_ss_select(dev_priv); - I915_WRITE(GEN8_MCR_SELECTOR, mcr); + wa_write_masked_or(wal, + GEN8_MCR_SELECTOR, + mcr_slice_subslice_mask, + intel_calculate_mcr_s_ss_select(dev_priv)); } -static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cnl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_mcr(i915); /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); + if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); /* WaInPlaceDecompressionHang:cnl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaEnablePreemptionGranularityControlByUMD:cnl */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void icl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* This is not an Wa. Enable for better image quality */ - I915_WRITE(_3D_CHICKEN3, - _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE)); + wa_init_mcr(i915); /* WaInPlaceDecompressionHang:icl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaPipelineFlushCoherentLines:icl */ - I915_WRITE(GEN8_L3SQCREG4, - I915_READ(GEN8_L3SQCREG4) | - GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* Wa_1405543622:icl - * Formerly known as WaGAPZPriorityScheme - */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | - GEN11_ARBITRATION_PRIO_ORDER_MASK); - - /* Wa_1604223664:icl - * Formerly known as WaL3BankAddressHashing - */ - I915_WRITE(GEN8_GARBCNTL, - (I915_READ(GEN8_GARBCNTL) & ~GEN11_HASH_CTRL_EXCL_MASK) | - GEN11_HASH_CTRL_EXCL_BIT0); - I915_WRITE(GEN11_GLBLINVL, - (I915_READ(GEN11_GLBLINVL) & ~GEN11_BANK_HASH_ADDR_EXCL_MASK) | - GEN11_BANK_HASH_ADDR_EXCL_BIT0); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); /* WaModifyGamTlbPartitioning:icl */ - I915_WRITE(GEN11_GACB_PERF_CTRL, - (I915_READ(GEN11_GACB_PERF_CTRL) & ~GEN11_HASH_CTRL_MASK) | - GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); - - /* Wa_1405733216:icl - * Formerly known as WaDisableCleanEvicts - */ - I915_WRITE(GEN8_L3SQCREG4, - I915_READ(GEN8_L3SQCREG4) | - GEN11_LQSC_CLEAN_EVICT_DISABLE); + wa_write_masked_or(wal, + GEN11_GACB_PERF_CTRL, + GEN11_HASH_CTRL_MASK, + GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); /* Wa_1405766107:icl * Formerly known as WaCL2SFHalfMaxAlloc */ - I915_WRITE(GEN11_LSN_UNSLCVC, - I915_READ(GEN11_LSN_UNSLCVC) | - GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | - GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); + wa_write_or(wal, + GEN11_LSN_UNSLCVC, + GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | + GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); /* Wa_220166154:icl * Formerly known as WaDisCtxReload */ - I915_WRITE(GEN8_GAMW_ECO_DEV_RW_IA, - I915_READ(GEN8_GAMW_ECO_DEV_RW_IA) | - GAMW_ECO_DEV_CTX_RELOAD_DISABLE); + wa_write_or(wal, + GEN8_GAMW_ECO_DEV_RW_IA, + GAMW_ECO_DEV_CTX_RELOAD_DISABLE); /* Wa_1405779004:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) - I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SLICE_UNIT_LEVEL_CLKGATE) | - MSCUNIT_CLKGATE_DIS); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0)) + wa_write_or(wal, + SLICE_UNIT_LEVEL_CLKGATE, + MSCUNIT_CLKGATE_DIS); /* Wa_1406680159:icl */ - I915_WRITE(SUBSLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SUBSLICE_UNIT_LEVEL_CLKGATE) | - GWUNIT_CLKGATE_DIS); - - /* Wa_1604302699:icl */ - I915_WRITE(GEN10_L3_CHICKEN_MODE_REGISTER, - I915_READ(GEN10_L3_CHICKEN_MODE_REGISTER) | - GEN11_I2M_WRITE_DISABLE); + wa_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); /* Wa_1406838659:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) - I915_WRITE(INF_UNIT_LEVEL_CLKGATE, - I915_READ(INF_UNIT_LEVEL_CLKGATE) | - CGPSF_CLKGATE_DIS); - - /* WaForwardProgressSoftReset:icl */ - I915_WRITE(GEN10_SCRATCH_LNCF2, - I915_READ(GEN10_SCRATCH_LNCF2) | - PMFLUSHDONE_LNICRSDROP | - PMFLUSH_GAPL3UNBLOCK | - PMFLUSHDONE_LNEBLK); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) + wa_write_or(wal, + INF_UNIT_LEVEL_CLKGATE, + CGPSF_CLKGATE_DIS); /* Wa_1406463099:icl * Formerly known as WaGamTlbPendError */ - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_L3_COH_PIPE); - - /* Wa_1406609255:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) - I915_WRITE(GEN7_SARCHKMD, - I915_READ(GEN7_SARCHKMD) | - GEN7_DISABLE_DEMAND_PREFETCH | - GEN7_DISABLE_SAMPLER_PREFETCH); + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_L3_COH_PIPE); } -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) +void intel_gt_init_workarounds(struct drm_i915_private *i915) { - if (INTEL_GEN(dev_priv) < 8) + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_start(wal, "GT"); + + if (INTEL_GEN(i915) < 8) + return; + else if (IS_BROADWELL(i915)) return; - else if (IS_BROADWELL(dev_priv)) - bdw_gt_workarounds_apply(dev_priv); - else if (IS_CHERRYVIEW(dev_priv)) - chv_gt_workarounds_apply(dev_priv); - else if (IS_SKYLAKE(dev_priv)) - skl_gt_workarounds_apply(dev_priv); - else if (IS_BROXTON(dev_priv)) - bxt_gt_workarounds_apply(dev_priv); - else if (IS_KABYLAKE(dev_priv)) - kbl_gt_workarounds_apply(dev_priv); - else if (IS_GEMINILAKE(dev_priv)) - glk_gt_workarounds_apply(dev_priv); - else if (IS_COFFEELAKE(dev_priv)) - cfl_gt_workarounds_apply(dev_priv); - else if (IS_CANNONLAKE(dev_priv)) - cnl_gt_workarounds_apply(dev_priv); - else if (IS_ICELAKE(dev_priv)) - icl_gt_workarounds_apply(dev_priv); + else if (IS_CHERRYVIEW(i915)) + return; + else if (IS_SKYLAKE(i915)) + skl_gt_workarounds_init(i915); + else if (IS_BROXTON(i915)) + bxt_gt_workarounds_init(i915); + else if (IS_KABYLAKE(i915)) + kbl_gt_workarounds_init(i915); + else if (IS_GEMINILAKE(i915)) + glk_gt_workarounds_init(i915); + else if (IS_COFFEELAKE(i915)) + cfl_gt_workarounds_init(i915); + else if (IS_CANNONLAKE(i915)) + cnl_gt_workarounds_init(i915); + else if (IS_ICELAKE(i915)) + icl_gt_workarounds_init(i915); else - MISSING_CASE(INTEL_GEN(dev_priv)); + MISSING_CASE(INTEL_GEN(i915)); + + wa_init_finish(wal); } -struct whitelist { - i915_reg_t reg[RING_MAX_NONPRIV_SLOTS]; - unsigned int count; - u32 nopid; -}; +static enum forcewake_domains +wal_get_fw_for_rmw(struct drm_i915_private *dev_priv, + const struct i915_wa_list *wal) +{ + enum forcewake_domains fw = 0; + struct i915_wa *wa; + unsigned int i; -static void whitelist_reg(struct whitelist *w, i915_reg_t reg) + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + fw |= intel_uncore_forcewake_for_reg(dev_priv, + wa->reg, + FW_REG_READ | + FW_REG_WRITE); + + return fw; +} + +static void +wa_list_apply(struct drm_i915_private *dev_priv, const struct i915_wa_list *wal) { - if (GEM_DEBUG_WARN_ON(w->count >= RING_MAX_NONPRIV_SLOTS)) + enum forcewake_domains fw; + unsigned long flags; + struct i915_wa *wa; + unsigned int i; + + if (!wal->count) return; - w->reg[w->count++] = reg; + fw = wal_get_fw_for_rmw(dev_priv, wal); + + spin_lock_irqsave(&dev_priv->uncore.lock, flags); + intel_uncore_forcewake_get__locked(dev_priv, fw); + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { + u32 val = I915_READ_FW(wa->reg); + + val &= ~wa->mask; + val |= wa->val; + + I915_WRITE_FW(wa->reg, val); + } + + intel_uncore_forcewake_put__locked(dev_priv, fw); + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); + + DRM_DEBUG_DRIVER("Applied %u %s workarounds\n", wal->count, wal->name); +} + +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv) +{ + wa_list_apply(dev_priv, &dev_priv->gt_wa_list); +} + +static bool +wa_verify(const struct i915_wa *wa, u32 cur, const char *name, const char *from) +{ + if ((cur ^ wa->val) & wa->mask) { + DRM_ERROR("%s workaround lost on %s! (%x=%x/%x, expected %x, mask=%x)\n", + name, from, i915_mmio_reg_offset(wa->reg), cur, + cur & wa->mask, wa->val, wa->mask); + + return false; + } + + return true; } -static void bdw_whitelist_build(struct whitelist *w) +static bool wa_list_verify(struct drm_i915_private *dev_priv, + const struct i915_wa_list *wal, + const char *from) { + struct i915_wa *wa; + unsigned int i; + bool ok = true; + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + ok &= wa_verify(wa, I915_READ(wa->reg), wal->name, from); + + return ok; } -static void chv_whitelist_build(struct whitelist *w) +bool intel_gt_verify_workarounds(struct drm_i915_private *dev_priv, + const char *from) { + return wa_list_verify(dev_priv, &dev_priv->gt_wa_list, from); } -static void gen9_whitelist_build(struct whitelist *w) +static void +whitelist_reg(struct i915_wa_list *wal, i915_reg_t reg) +{ + struct i915_wa wa = { + .reg = reg + }; + + if (GEM_DEBUG_WARN_ON(wal->count >= RING_MAX_NONPRIV_SLOTS)) + return; + + _wa_add(wal, &wa); +} + +static void gen9_whitelist_build(struct i915_wa_list *w) { /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ whitelist_reg(w, GEN9_CTX_PREEMPT_REG); @@ -980,7 +1023,7 @@ static void gen9_whitelist_build(struct whitelist *w) whitelist_reg(w, GEN8_HDC_CHICKEN1); } -static void skl_whitelist_build(struct whitelist *w) +static void skl_whitelist_build(struct i915_wa_list *w) { gen9_whitelist_build(w); @@ -988,12 +1031,12 @@ static void skl_whitelist_build(struct whitelist *w) whitelist_reg(w, GEN8_L3SQCREG4); } -static void bxt_whitelist_build(struct whitelist *w) +static void bxt_whitelist_build(struct i915_wa_list *w) { gen9_whitelist_build(w); } -static void kbl_whitelist_build(struct whitelist *w) +static void kbl_whitelist_build(struct i915_wa_list *w) { gen9_whitelist_build(w); @@ -1001,7 +1044,7 @@ static void kbl_whitelist_build(struct whitelist *w) whitelist_reg(w, GEN8_L3SQCREG4); } -static void glk_whitelist_build(struct whitelist *w) +static void glk_whitelist_build(struct i915_wa_list *w) { gen9_whitelist_build(w); @@ -1009,18 +1052,18 @@ static void glk_whitelist_build(struct whitelist *w) whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1); } -static void cfl_whitelist_build(struct whitelist *w) +static void cfl_whitelist_build(struct i915_wa_list *w) { gen9_whitelist_build(w); } -static void cnl_whitelist_build(struct whitelist *w) +static void cnl_whitelist_build(struct i915_wa_list *w) { /* WaEnablePreemptionGranularityControlByUMD:cnl */ whitelist_reg(w, GEN8_CS_CHICKEN1); } -static void icl_whitelist_build(struct whitelist *w) +static void icl_whitelist_build(struct i915_wa_list *w) { /* WaAllowUMDToModifyHalfSliceChicken7:icl */ whitelist_reg(w, GEN9_HALF_SLICE_CHICKEN7); @@ -1029,22 +1072,21 @@ static void icl_whitelist_build(struct whitelist *w) whitelist_reg(w, GEN10_SAMPLER_MODE); } -static struct whitelist *whitelist_build(struct intel_engine_cs *engine, - struct whitelist *w) +void intel_engine_init_whitelist(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *w = &engine->whitelist; GEM_BUG_ON(engine->id != RCS); - w->count = 0; - w->nopid = i915_mmio_reg_offset(RING_NOPID(engine->mmio_base)); + wa_init_start(w, "whitelist"); if (INTEL_GEN(i915) < 8) - return NULL; + return; else if (IS_BROADWELL(i915)) - bdw_whitelist_build(w); + return; else if (IS_CHERRYVIEW(i915)) - chv_whitelist_build(w); + return; else if (IS_SKYLAKE(i915)) skl_whitelist_build(w); else if (IS_BROXTON(i915)) @@ -1062,39 +1104,180 @@ static struct whitelist *whitelist_build(struct intel_engine_cs *engine, else MISSING_CASE(INTEL_GEN(i915)); - return w; + wa_init_finish(w); } -static void whitelist_apply(struct intel_engine_cs *engine, - const struct whitelist *w) +void intel_engine_apply_whitelist(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + const struct i915_wa_list *wal = &engine->whitelist; const u32 base = engine->mmio_base; + struct i915_wa *wa; unsigned int i; - if (!w) + if (!wal->count) return; - intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL); - - for (i = 0; i < w->count; i++) - I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i), - i915_mmio_reg_offset(w->reg[i])); + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + I915_WRITE(RING_FORCE_TO_NONPRIV(base, i), + i915_mmio_reg_offset(wa->reg)); /* And clear the rest just in case of garbage */ for (; i < RING_MAX_NONPRIV_SLOTS; i++) - I915_WRITE_FW(RING_FORCE_TO_NONPRIV(base, i), w->nopid); + I915_WRITE(RING_FORCE_TO_NONPRIV(base, i), + i915_mmio_reg_offset(RING_NOPID(base))); - intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL); + DRM_DEBUG_DRIVER("Applied %u %s workarounds\n", wal->count, wal->name); } -void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine) +static void rcs_engine_wa_init(struct intel_engine_cs *engine) { - struct whitelist w; + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + if (IS_ICELAKE(i915)) { + /* This is not an Wa. Enable for better image quality */ + wa_masked_en(wal, + _3D_CHICKEN3, + _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE); + + /* WaPipelineFlushCoherentLines:icl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + + /* + * Wa_1405543622:icl + * Formerly known as WaGAPZPriorityScheme + */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN11_ARBITRATION_PRIO_ORDER_MASK); + + /* + * Wa_1604223664:icl + * Formerly known as WaL3BankAddressHashing + */ + wa_write_masked_or(wal, + GEN8_GARBCNTL, + GEN11_HASH_CTRL_EXCL_MASK, + GEN11_HASH_CTRL_EXCL_BIT0); + wa_write_masked_or(wal, + GEN11_GLBLINVL, + GEN11_BANK_HASH_ADDR_EXCL_MASK, + GEN11_BANK_HASH_ADDR_EXCL_BIT0); - whitelist_apply(engine, whitelist_build(engine, &w)); + /* + * Wa_1405733216:icl + * Formerly known as WaDisableCleanEvicts + */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); + + /* WaForwardProgressSoftReset:icl */ + wa_write_or(wal, + GEN10_SCRATCH_LNCF2, + PMFLUSHDONE_LNICRSDROP | + PMFLUSH_GAPL3UNBLOCK | + PMFLUSHDONE_LNEBLK); + + /* Wa_1406609255:icl (pre-prod) */ + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) + wa_write_or(wal, + GEN7_SARCHKMD, + GEN7_DISABLE_DEMAND_PREFETCH | + GEN7_DISABLE_SAMPLER_PREFETCH); + } + + if (IS_GEN9(i915) || IS_CANNONLAKE(i915)) { + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,cnl */ + wa_masked_en(wal, + GEN7_FF_SLICE_CS_CHICKEN1, + GEN9_FFSC_PERCTX_PREEMPT_CTRL); + } + + if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915)) { + /* WaEnableGapsTsvCreditFix:skl,kbl,cfl */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); + } + + if (IS_BROXTON(i915)) { + /* WaDisablePooledEuLoadBalancingFix:bxt */ + wa_masked_en(wal, + FF_SLICE_CS_CHICKEN2, + GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); + } + + if (IS_GEN9(i915)) { + /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ + wa_masked_en(wal, + GEN9_CSFE_CHICKEN1_RCS, + GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ + wa_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + + /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ + if (IS_GEN9_LP(i915)) + wa_write_masked_or(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); + + /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + } +} + +static void xcs_engine_wa_init(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + /* WaKBLVECSSemaphoreWaitPoll:kbl */ + if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { + wa_write(wal, + RING_SEMA_WAIT_POLL(engine->mmio_base), + 1); + } +} + +void intel_engine_init_workarounds(struct intel_engine_cs *engine) +{ + struct i915_wa_list *wal = &engine->wa_list; + + if (GEM_WARN_ON(INTEL_GEN(engine->i915) < 8)) + return; + + wa_init_start(wal, engine->name); + + if (engine->id == RCS) + rcs_engine_wa_init(engine); + else + xcs_engine_wa_init(engine); + + wa_init_finish(wal); +} + +void intel_engine_apply_workarounds(struct intel_engine_cs *engine) +{ + wa_list_apply(engine->i915, &engine->wa_list); } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) +static bool intel_engine_verify_workarounds(struct intel_engine_cs *engine, + const char *from) +{ + return wa_list_verify(engine->i915, &engine->wa_list, from); +} + #include "selftests/intel_workarounds.c" #endif diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h index b11d0623e626..7c734714b05e 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.h +++ b/drivers/gpu/drm/i915/intel_workarounds.h @@ -7,11 +7,39 @@ #ifndef _I915_WORKAROUNDS_H_ #define _I915_WORKAROUNDS_H_ -int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv); -int intel_ctx_workarounds_emit(struct i915_request *rq); +#include <linux/slab.h> -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv); +struct i915_wa { + i915_reg_t reg; + u32 mask; + u32 val; +}; -void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); +struct i915_wa_list { + const char *name; + struct i915_wa *list; + unsigned int count; + unsigned int wa_count; +}; + +static inline void intel_wa_list_free(struct i915_wa_list *wal) +{ + kfree(wal->list); + memset(wal, 0, sizeof(*wal)); +} + +void intel_engine_init_ctx_wa(struct intel_engine_cs *engine); +int intel_engine_emit_ctx_wa(struct i915_request *rq); + +void intel_gt_init_workarounds(struct drm_i915_private *dev_priv); +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv); +bool intel_gt_verify_workarounds(struct drm_i915_private *dev_priv, + const char *from); + +void intel_engine_init_whitelist(struct intel_engine_cs *engine); +void intel_engine_apply_whitelist(struct intel_engine_cs *engine); + +void intel_engine_init_workarounds(struct intel_engine_cs *engine); +void intel_engine_apply_workarounds(struct intel_engine_cs *engine); #endif diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.c b/drivers/gpu/drm/i915/selftests/igt_reset.c new file mode 100644 index 000000000000..208a966da8ca --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_reset.c @@ -0,0 +1,44 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#include "igt_reset.h" + +#include "../i915_drv.h" +#include "../intel_ringbuffer.h" + +void igt_global_reset_lock(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + pr_debug("%s: current gpu_error=%08lx\n", + __func__, i915->gpu_error.flags); + + while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags)) + wait_event(i915->gpu_error.reset_queue, + !test_bit(I915_RESET_BACKOFF, + &i915->gpu_error.flags)); + + for_each_engine(engine, i915, id) { + while (test_and_set_bit(I915_RESET_ENGINE + id, + &i915->gpu_error.flags)) + wait_on_bit(&i915->gpu_error.flags, + I915_RESET_ENGINE + id, + TASK_UNINTERRUPTIBLE); + } +} + +void igt_global_reset_unlock(struct drm_i915_private *i915) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, i915, id) + clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); + + clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags); + wake_up_all(&i915->gpu_error.reset_queue); +} diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.h b/drivers/gpu/drm/i915/selftests/igt_reset.h new file mode 100644 index 000000000000..5f0234d045d5 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_reset.h @@ -0,0 +1,15 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#ifndef __I915_SELFTESTS_IGT_RESET_H__ +#define __I915_SELFTESTS_IGT_RESET_H__ + +#include "../i915_drv.h" + +void igt_global_reset_lock(struct drm_i915_private *i915); +void igt_global_reset_unlock(struct drm_i915_private *i915); + +#endif diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c new file mode 100644 index 000000000000..8cd34f6e6859 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -0,0 +1,199 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#include "igt_spinner.h" + +int igt_spinner_init(struct igt_spinner *spin, struct drm_i915_private *i915) +{ + unsigned int mode; + void *vaddr; + int err; + + GEM_BUG_ON(INTEL_GEN(i915) < 8); + + memset(spin, 0, sizeof(*spin)); + spin->i915 = i915; + + spin->hws = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(spin->hws)) { + err = PTR_ERR(spin->hws); + goto err; + } + + spin->obj = i915_gem_object_create_internal(i915, PAGE_SIZE); + if (IS_ERR(spin->obj)) { + err = PTR_ERR(spin->obj); + goto err_hws; + } + + i915_gem_object_set_cache_level(spin->hws, I915_CACHE_LLC); + vaddr = i915_gem_object_pin_map(spin->hws, I915_MAP_WB); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto err_obj; + } + spin->seqno = memset(vaddr, 0xff, PAGE_SIZE); + + mode = i915_coherent_map_type(i915); + vaddr = i915_gem_object_pin_map(spin->obj, mode); + if (IS_ERR(vaddr)) { + err = PTR_ERR(vaddr); + goto err_unpin_hws; + } + spin->batch = vaddr; + + return 0; + +err_unpin_hws: + i915_gem_object_unpin_map(spin->hws); +err_obj: + i915_gem_object_put(spin->obj); +err_hws: + i915_gem_object_put(spin->hws); +err: + return err; +} + +static unsigned int seqno_offset(u64 fence) +{ + return offset_in_page(sizeof(u32) * fence); +} + +static u64 hws_address(const struct i915_vma *hws, + const struct i915_request *rq) +{ + return hws->node.start + seqno_offset(rq->fence.context); +} + +static int emit_recurse_batch(struct igt_spinner *spin, + struct i915_request *rq, + u32 arbitration_command) +{ + struct i915_address_space *vm = &rq->gem_context->ppgtt->vm; + struct i915_vma *hws, *vma; + u32 *batch; + int err; + + vma = i915_vma_instance(spin->obj, vm, NULL); + if (IS_ERR(vma)) + return PTR_ERR(vma); + + hws = i915_vma_instance(spin->hws, vm, NULL); + if (IS_ERR(hws)) + return PTR_ERR(hws); + + err = i915_vma_pin(vma, 0, 0, PIN_USER); + if (err) + return err; + + err = i915_vma_pin(hws, 0, 0, PIN_USER); + if (err) + goto unpin_vma; + + err = i915_vma_move_to_active(vma, rq, 0); + if (err) + goto unpin_hws; + + if (!i915_gem_object_has_active_reference(vma->obj)) { + i915_gem_object_get(vma->obj); + i915_gem_object_set_active_reference(vma->obj); + } + + err = i915_vma_move_to_active(hws, rq, 0); + if (err) + goto unpin_hws; + + if (!i915_gem_object_has_active_reference(hws->obj)) { + i915_gem_object_get(hws->obj); + i915_gem_object_set_active_reference(hws->obj); + } + + batch = spin->batch; + + *batch++ = MI_STORE_DWORD_IMM_GEN4; + *batch++ = lower_32_bits(hws_address(hws, rq)); + *batch++ = upper_32_bits(hws_address(hws, rq)); + *batch++ = rq->fence.seqno; + + *batch++ = arbitration_command; + + *batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1; + *batch++ = lower_32_bits(vma->node.start); + *batch++ = upper_32_bits(vma->node.start); + *batch++ = MI_BATCH_BUFFER_END; /* not reached */ + + i915_gem_chipset_flush(spin->i915); + + err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0); + +unpin_hws: + i915_vma_unpin(hws); +unpin_vma: + i915_vma_unpin(vma); + return err; +} + +struct i915_request * +igt_spinner_create_request(struct igt_spinner *spin, + struct i915_gem_context *ctx, + struct intel_engine_cs *engine, + u32 arbitration_command) +{ + struct i915_request *rq; + int err; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) + return rq; + + err = emit_recurse_batch(spin, rq, arbitration_command); + if (err) { + i915_request_add(rq); + return ERR_PTR(err); + } + + return rq; +} + +static u32 +hws_seqno(const struct igt_spinner *spin, const struct i915_request *rq) +{ + u32 *seqno = spin->seqno + seqno_offset(rq->fence.context); + + return READ_ONCE(*seqno); +} + +void igt_spinner_end(struct igt_spinner *spin) +{ + *spin->batch = MI_BATCH_BUFFER_END; + i915_gem_chipset_flush(spin->i915); +} + +void igt_spinner_fini(struct igt_spinner *spin) +{ + igt_spinner_end(spin); + + i915_gem_object_unpin_map(spin->obj); + i915_gem_object_put(spin->obj); + + i915_gem_object_unpin_map(spin->hws); + i915_gem_object_put(spin->hws); +} + +bool igt_wait_for_spinner(struct igt_spinner *spin, struct i915_request *rq) +{ + if (!wait_event_timeout(rq->execute, + READ_ONCE(rq->global_seqno), + msecs_to_jiffies(10))) + return false; + + return !(wait_for_us(i915_seqno_passed(hws_seqno(spin, rq), + rq->fence.seqno), + 10) && + wait_for(i915_seqno_passed(hws_seqno(spin, rq), + rq->fence.seqno), + 1000)); +} diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.h b/drivers/gpu/drm/i915/selftests/igt_spinner.h new file mode 100644 index 000000000000..391777c76dc7 --- /dev/null +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.h @@ -0,0 +1,37 @@ +/* + * SPDX-License-Identifier: MIT + * + * Copyright © 2018 Intel Corporation + */ + +#ifndef __I915_SELFTESTS_IGT_SPINNER_H__ +#define __I915_SELFTESTS_IGT_SPINNER_H__ + +#include "../i915_selftest.h" + +#include "../i915_drv.h" +#include "../i915_request.h" +#include "../intel_ringbuffer.h" +#include "../i915_gem_context.h" + +struct igt_spinner { + struct drm_i915_private *i915; + struct drm_i915_gem_object *hws; + struct drm_i915_gem_object *obj; + u32 *batch; + void *seqno; +}; + +int igt_spinner_init(struct igt_spinner *spin, struct drm_i915_private *i915); +void igt_spinner_fini(struct igt_spinner *spin); + +struct i915_request * +igt_spinner_create_request(struct igt_spinner *spin, + struct i915_gem_context *ctx, + struct intel_engine_cs *engine, + u32 arbitration_command); +void igt_spinner_end(struct igt_spinner *spin); + +bool igt_wait_for_spinner(struct igt_spinner *spin, struct i915_request *rq); + +#endif diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c index defe671130ab..40efbed611de 100644 --- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c @@ -27,6 +27,7 @@ #include "../i915_selftest.h" #include "i915_random.h" #include "igt_flush_test.h" +#include "igt_reset.h" #include "igt_wedge_me.h" #include "mock_context.h" @@ -308,6 +309,7 @@ static int igt_hang_sanitycheck(void *arg) goto unlock; for_each_engine(engine, i915, id) { + struct igt_wedge_me w; long timeout; if (!intel_engine_can_store_dword(engine)) @@ -328,9 +330,14 @@ static int igt_hang_sanitycheck(void *arg) i915_request_add(rq); - timeout = i915_request_wait(rq, - I915_WAIT_LOCKED, - MAX_SCHEDULE_TIMEOUT); + timeout = 0; + igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/) + timeout = i915_request_wait(rq, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + if (i915_terminally_wedged(&i915->gpu_error)) + timeout = -EIO; + i915_request_put(rq); if (timeout < 0) { @@ -348,40 +355,6 @@ unlock: return err; } -static void global_reset_lock(struct drm_i915_private *i915) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - - pr_debug("%s: current gpu_error=%08lx\n", - __func__, i915->gpu_error.flags); - - while (test_and_set_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags)) - wait_event(i915->gpu_error.reset_queue, - !test_bit(I915_RESET_BACKOFF, - &i915->gpu_error.flags)); - - for_each_engine(engine, i915, id) { - while (test_and_set_bit(I915_RESET_ENGINE + id, - &i915->gpu_error.flags)) - wait_on_bit(&i915->gpu_error.flags, - I915_RESET_ENGINE + id, - TASK_UNINTERRUPTIBLE); - } -} - -static void global_reset_unlock(struct drm_i915_private *i915) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - - for_each_engine(engine, i915, id) - clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags); - - clear_bit(I915_RESET_BACKOFF, &i915->gpu_error.flags); - wake_up_all(&i915->gpu_error.reset_queue); -} - static int igt_global_reset(void *arg) { struct drm_i915_private *i915 = arg; @@ -390,7 +363,7 @@ static int igt_global_reset(void *arg) /* Check that we can issue a global GPU reset */ - global_reset_lock(i915); + igt_global_reset_lock(i915); set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); mutex_lock(&i915->drm.struct_mutex); @@ -405,7 +378,7 @@ static int igt_global_reset(void *arg) mutex_unlock(&i915->drm.struct_mutex); GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags)); - global_reset_unlock(i915); + igt_global_reset_unlock(i915); if (i915_terminally_wedged(&i915->gpu_error)) err = -EIO; @@ -936,7 +909,7 @@ static int igt_reset_wait(void *arg) /* Check that we detect a stuck waiter and issue a reset */ - global_reset_lock(i915); + igt_global_reset_lock(i915); mutex_lock(&i915->drm.struct_mutex); err = hang_init(&h, i915); @@ -988,7 +961,7 @@ fini: hang_fini(&h); unlock: mutex_unlock(&i915->drm.struct_mutex); - global_reset_unlock(i915); + igt_global_reset_unlock(i915); if (i915_terminally_wedged(&i915->gpu_error)) return -EIO; @@ -1066,7 +1039,7 @@ static int __igt_reset_evict_vma(struct drm_i915_private *i915, /* Check that we can recover an unbind stuck on a hanging request */ - global_reset_lock(i915); + igt_global_reset_lock(i915); mutex_lock(&i915->drm.struct_mutex); err = hang_init(&h, i915); @@ -1186,7 +1159,7 @@ fini: hang_fini(&h); unlock: mutex_unlock(&i915->drm.struct_mutex); - global_reset_unlock(i915); + igt_global_reset_unlock(i915); if (i915_terminally_wedged(&i915->gpu_error)) return -EIO; @@ -1266,7 +1239,7 @@ static int igt_reset_queue(void *arg) /* Check that we replay pending requests following a hang */ - global_reset_lock(i915); + igt_global_reset_lock(i915); mutex_lock(&i915->drm.struct_mutex); err = hang_init(&h, i915); @@ -1397,7 +1370,7 @@ fini: hang_fini(&h); unlock: mutex_unlock(&i915->drm.struct_mutex); - global_reset_unlock(i915); + igt_global_reset_unlock(i915); if (i915_terminally_wedged(&i915->gpu_error)) return -EIO; diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 94fc0e5c8766..ca461e3a5f27 100644 --- a/drivers/gpu/drm/i915/selftests/intel_lrc.c +++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c @@ -6,216 +6,18 @@ #include "../i915_selftest.h" #include "igt_flush_test.h" +#include "igt_spinner.h" #include "i915_random.h" #include "mock_context.h" -struct spinner { - struct drm_i915_private *i915; - struct drm_i915_gem_object *hws; - struct drm_i915_gem_object *obj; - u32 *batch; - void *seqno; -}; - -static int spinner_init(struct spinner *spin, struct drm_i915_private *i915) -{ - unsigned int mode; - void *vaddr; - int err; - - GEM_BUG_ON(INTEL_GEN(i915) < 8); - - memset(spin, 0, sizeof(*spin)); - spin->i915 = i915; - - spin->hws = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(spin->hws)) { - err = PTR_ERR(spin->hws); - goto err; - } - - spin->obj = i915_gem_object_create_internal(i915, PAGE_SIZE); - if (IS_ERR(spin->obj)) { - err = PTR_ERR(spin->obj); - goto err_hws; - } - - i915_gem_object_set_cache_level(spin->hws, I915_CACHE_LLC); - vaddr = i915_gem_object_pin_map(spin->hws, I915_MAP_WB); - if (IS_ERR(vaddr)) { - err = PTR_ERR(vaddr); - goto err_obj; - } - spin->seqno = memset(vaddr, 0xff, PAGE_SIZE); - - mode = i915_coherent_map_type(i915); - vaddr = i915_gem_object_pin_map(spin->obj, mode); - if (IS_ERR(vaddr)) { - err = PTR_ERR(vaddr); - goto err_unpin_hws; - } - spin->batch = vaddr; - - return 0; - -err_unpin_hws: - i915_gem_object_unpin_map(spin->hws); -err_obj: - i915_gem_object_put(spin->obj); -err_hws: - i915_gem_object_put(spin->hws); -err: - return err; -} - -static unsigned int seqno_offset(u64 fence) -{ - return offset_in_page(sizeof(u32) * fence); -} - -static u64 hws_address(const struct i915_vma *hws, - const struct i915_request *rq) -{ - return hws->node.start + seqno_offset(rq->fence.context); -} - -static int emit_recurse_batch(struct spinner *spin, - struct i915_request *rq, - u32 arbitration_command) -{ - struct i915_address_space *vm = &rq->gem_context->ppgtt->vm; - struct i915_vma *hws, *vma; - u32 *batch; - int err; - - vma = i915_vma_instance(spin->obj, vm, NULL); - if (IS_ERR(vma)) - return PTR_ERR(vma); - - hws = i915_vma_instance(spin->hws, vm, NULL); - if (IS_ERR(hws)) - return PTR_ERR(hws); - - err = i915_vma_pin(vma, 0, 0, PIN_USER); - if (err) - return err; - - err = i915_vma_pin(hws, 0, 0, PIN_USER); - if (err) - goto unpin_vma; - - err = i915_vma_move_to_active(vma, rq, 0); - if (err) - goto unpin_hws; - - if (!i915_gem_object_has_active_reference(vma->obj)) { - i915_gem_object_get(vma->obj); - i915_gem_object_set_active_reference(vma->obj); - } - - err = i915_vma_move_to_active(hws, rq, 0); - if (err) - goto unpin_hws; - - if (!i915_gem_object_has_active_reference(hws->obj)) { - i915_gem_object_get(hws->obj); - i915_gem_object_set_active_reference(hws->obj); - } - - batch = spin->batch; - - *batch++ = MI_STORE_DWORD_IMM_GEN4; - *batch++ = lower_32_bits(hws_address(hws, rq)); - *batch++ = upper_32_bits(hws_address(hws, rq)); - *batch++ = rq->fence.seqno; - - *batch++ = arbitration_command; - - *batch++ = MI_BATCH_BUFFER_START | 1 << 8 | 1; - *batch++ = lower_32_bits(vma->node.start); - *batch++ = upper_32_bits(vma->node.start); - *batch++ = MI_BATCH_BUFFER_END; /* not reached */ - - i915_gem_chipset_flush(spin->i915); - - err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0); - -unpin_hws: - i915_vma_unpin(hws); -unpin_vma: - i915_vma_unpin(vma); - return err; -} - -static struct i915_request * -spinner_create_request(struct spinner *spin, - struct i915_gem_context *ctx, - struct intel_engine_cs *engine, - u32 arbitration_command) -{ - struct i915_request *rq; - int err; - - rq = i915_request_alloc(engine, ctx); - if (IS_ERR(rq)) - return rq; - - err = emit_recurse_batch(spin, rq, arbitration_command); - if (err) { - i915_request_add(rq); - return ERR_PTR(err); - } - - return rq; -} - -static u32 hws_seqno(const struct spinner *spin, const struct i915_request *rq) -{ - u32 *seqno = spin->seqno + seqno_offset(rq->fence.context); - - return READ_ONCE(*seqno); -} - -static void spinner_end(struct spinner *spin) -{ - *spin->batch = MI_BATCH_BUFFER_END; - i915_gem_chipset_flush(spin->i915); -} - -static void spinner_fini(struct spinner *spin) -{ - spinner_end(spin); - - i915_gem_object_unpin_map(spin->obj); - i915_gem_object_put(spin->obj); - - i915_gem_object_unpin_map(spin->hws); - i915_gem_object_put(spin->hws); -} - -static bool wait_for_spinner(struct spinner *spin, struct i915_request *rq) -{ - if (!wait_event_timeout(rq->execute, - READ_ONCE(rq->global_seqno), - msecs_to_jiffies(10))) - return false; - - return !(wait_for_us(i915_seqno_passed(hws_seqno(spin, rq), - rq->fence.seqno), - 10) && - wait_for(i915_seqno_passed(hws_seqno(spin, rq), - rq->fence.seqno), - 1000)); -} - static int live_sanitycheck(void *arg) { struct drm_i915_private *i915 = arg; struct intel_engine_cs *engine; struct i915_gem_context *ctx; enum intel_engine_id id; - struct spinner spin; + struct igt_spinner spin; int err = -ENOMEM; if (!HAS_LOGICAL_RING_CONTEXTS(i915)) @@ -224,7 +26,7 @@ static int live_sanitycheck(void *arg) mutex_lock(&i915->drm.struct_mutex); intel_runtime_pm_get(i915); - if (spinner_init(&spin, i915)) + if (igt_spinner_init(&spin, i915)) goto err_unlock; ctx = kernel_context(i915); @@ -234,14 +36,14 @@ static int live_sanitycheck(void *arg) for_each_engine(engine, i915, id) { struct i915_request *rq; - rq = spinner_create_request(&spin, ctx, engine, MI_NOOP); + rq = igt_spinner_create_request(&spin, ctx, engine, MI_NOOP); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto err_ctx; } i915_request_add(rq); - if (!wait_for_spinner(&spin, rq)) { + if (!igt_wait_for_spinner(&spin, rq)) { GEM_TRACE("spinner failed to start\n"); GEM_TRACE_DUMP(); i915_gem_set_wedged(i915); @@ -249,7 +51,7 @@ static int live_sanitycheck(void *arg) goto err_ctx; } - spinner_end(&spin); + igt_spinner_end(&spin); if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx; @@ -260,7 +62,7 @@ static int live_sanitycheck(void *arg) err_ctx: kernel_context_close(ctx); err_spin: - spinner_fini(&spin); + igt_spinner_fini(&spin); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); intel_runtime_pm_put(i915); @@ -272,7 +74,7 @@ static int live_preempt(void *arg) { struct drm_i915_private *i915 = arg; struct i915_gem_context *ctx_hi, *ctx_lo; - struct spinner spin_hi, spin_lo; + struct igt_spinner spin_hi, spin_lo; struct intel_engine_cs *engine; enum intel_engine_id id; int err = -ENOMEM; @@ -283,10 +85,10 @@ static int live_preempt(void *arg) mutex_lock(&i915->drm.struct_mutex); intel_runtime_pm_get(i915); - if (spinner_init(&spin_hi, i915)) + if (igt_spinner_init(&spin_hi, i915)) goto err_unlock; - if (spinner_init(&spin_lo, i915)) + if (igt_spinner_init(&spin_lo, i915)) goto err_spin_hi; ctx_hi = kernel_context(i915); @@ -304,15 +106,15 @@ static int live_preempt(void *arg) for_each_engine(engine, i915, id) { struct i915_request *rq; - rq = spinner_create_request(&spin_lo, ctx_lo, engine, - MI_ARB_CHECK); + rq = igt_spinner_create_request(&spin_lo, ctx_lo, engine, + MI_ARB_CHECK); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto err_ctx_lo; } i915_request_add(rq); - if (!wait_for_spinner(&spin_lo, rq)) { + if (!igt_wait_for_spinner(&spin_lo, rq)) { GEM_TRACE("lo spinner failed to start\n"); GEM_TRACE_DUMP(); i915_gem_set_wedged(i915); @@ -320,16 +122,16 @@ static int live_preempt(void *arg) goto err_ctx_lo; } - rq = spinner_create_request(&spin_hi, ctx_hi, engine, - MI_ARB_CHECK); + rq = igt_spinner_create_request(&spin_hi, ctx_hi, engine, + MI_ARB_CHECK); if (IS_ERR(rq)) { - spinner_end(&spin_lo); + igt_spinner_end(&spin_lo); err = PTR_ERR(rq); goto err_ctx_lo; } i915_request_add(rq); - if (!wait_for_spinner(&spin_hi, rq)) { + if (!igt_wait_for_spinner(&spin_hi, rq)) { GEM_TRACE("hi spinner failed to start\n"); GEM_TRACE_DUMP(); i915_gem_set_wedged(i915); @@ -337,8 +139,8 @@ static int live_preempt(void *arg) goto err_ctx_lo; } - spinner_end(&spin_hi); - spinner_end(&spin_lo); + igt_spinner_end(&spin_hi); + igt_spinner_end(&spin_lo); if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx_lo; @@ -351,9 +153,9 @@ err_ctx_lo: err_ctx_hi: kernel_context_close(ctx_hi); err_spin_lo: - spinner_fini(&spin_lo); + igt_spinner_fini(&spin_lo); err_spin_hi: - spinner_fini(&spin_hi); + igt_spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); intel_runtime_pm_put(i915); @@ -365,7 +167,7 @@ static int live_late_preempt(void *arg) { struct drm_i915_private *i915 = arg; struct i915_gem_context *ctx_hi, *ctx_lo; - struct spinner spin_hi, spin_lo; + struct igt_spinner spin_hi, spin_lo; struct intel_engine_cs *engine; struct i915_sched_attr attr = {}; enum intel_engine_id id; @@ -377,10 +179,10 @@ static int live_late_preempt(void *arg) mutex_lock(&i915->drm.struct_mutex); intel_runtime_pm_get(i915); - if (spinner_init(&spin_hi, i915)) + if (igt_spinner_init(&spin_hi, i915)) goto err_unlock; - if (spinner_init(&spin_lo, i915)) + if (igt_spinner_init(&spin_lo, i915)) goto err_spin_hi; ctx_hi = kernel_context(i915); @@ -394,28 +196,29 @@ static int live_late_preempt(void *arg) for_each_engine(engine, i915, id) { struct i915_request *rq; - rq = spinner_create_request(&spin_lo, ctx_lo, engine, - MI_ARB_CHECK); + rq = igt_spinner_create_request(&spin_lo, ctx_lo, engine, + MI_ARB_CHECK); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto err_ctx_lo; } i915_request_add(rq); - if (!wait_for_spinner(&spin_lo, rq)) { + if (!igt_wait_for_spinner(&spin_lo, rq)) { pr_err("First context failed to start\n"); goto err_wedged; } - rq = spinner_create_request(&spin_hi, ctx_hi, engine, MI_NOOP); + rq = igt_spinner_create_request(&spin_hi, ctx_hi, engine, + MI_NOOP); if (IS_ERR(rq)) { - spinner_end(&spin_lo); + igt_spinner_end(&spin_lo); err = PTR_ERR(rq); goto err_ctx_lo; } i915_request_add(rq); - if (wait_for_spinner(&spin_hi, rq)) { + if (igt_wait_for_spinner(&spin_hi, rq)) { pr_err("Second context overtook first?\n"); goto err_wedged; } @@ -423,14 +226,14 @@ static int live_late_preempt(void *arg) attr.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX); engine->schedule(rq, &attr); - if (!wait_for_spinner(&spin_hi, rq)) { + if (!igt_wait_for_spinner(&spin_hi, rq)) { pr_err("High priority context failed to preempt the low priority context\n"); GEM_TRACE_DUMP(); goto err_wedged; } - spinner_end(&spin_hi); - spinner_end(&spin_lo); + igt_spinner_end(&spin_hi); + igt_spinner_end(&spin_lo); if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx_lo; @@ -443,9 +246,9 @@ err_ctx_lo: err_ctx_hi: kernel_context_close(ctx_hi); err_spin_lo: - spinner_fini(&spin_lo); + igt_spinner_fini(&spin_lo); err_spin_hi: - spinner_fini(&spin_hi); + igt_spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); intel_runtime_pm_put(i915); @@ -453,8 +256,8 @@ err_unlock: return err; err_wedged: - spinner_end(&spin_hi); - spinner_end(&spin_lo); + igt_spinner_end(&spin_hi); + igt_spinner_end(&spin_lo); i915_gem_set_wedged(i915); err = -EIO; goto err_ctx_lo; @@ -464,7 +267,7 @@ static int live_preempt_hang(void *arg) { struct drm_i915_private *i915 = arg; struct i915_gem_context *ctx_hi, *ctx_lo; - struct spinner spin_hi, spin_lo; + struct igt_spinner spin_hi, spin_lo; struct intel_engine_cs *engine; enum intel_engine_id id; int err = -ENOMEM; @@ -478,10 +281,10 @@ static int live_preempt_hang(void *arg) mutex_lock(&i915->drm.struct_mutex); intel_runtime_pm_get(i915); - if (spinner_init(&spin_hi, i915)) + if (igt_spinner_init(&spin_hi, i915)) goto err_unlock; - if (spinner_init(&spin_lo, i915)) + if (igt_spinner_init(&spin_lo, i915)) goto err_spin_hi; ctx_hi = kernel_context(i915); @@ -500,15 +303,15 @@ static int live_preempt_hang(void *arg) if (!intel_engine_has_preemption(engine)) continue; - rq = spinner_create_request(&spin_lo, ctx_lo, engine, - MI_ARB_CHECK); + rq = igt_spinner_create_request(&spin_lo, ctx_lo, engine, + MI_ARB_CHECK); if (IS_ERR(rq)) { err = PTR_ERR(rq); goto err_ctx_lo; } i915_request_add(rq); - if (!wait_for_spinner(&spin_lo, rq)) { + if (!igt_wait_for_spinner(&spin_lo, rq)) { GEM_TRACE("lo spinner failed to start\n"); GEM_TRACE_DUMP(); i915_gem_set_wedged(i915); @@ -516,10 +319,10 @@ static int live_preempt_hang(void *arg) goto err_ctx_lo; } - rq = spinner_create_request(&spin_hi, ctx_hi, engine, - MI_ARB_CHECK); + rq = igt_spinner_create_request(&spin_hi, ctx_hi, engine, + MI_ARB_CHECK); if (IS_ERR(rq)) { - spinner_end(&spin_lo); + igt_spinner_end(&spin_lo); err = PTR_ERR(rq); goto err_ctx_lo; } @@ -544,7 +347,7 @@ static int live_preempt_hang(void *arg) engine->execlists.preempt_hang.inject_hang = false; - if (!wait_for_spinner(&spin_hi, rq)) { + if (!igt_wait_for_spinner(&spin_hi, rq)) { GEM_TRACE("hi spinner failed to start\n"); GEM_TRACE_DUMP(); i915_gem_set_wedged(i915); @@ -552,8 +355,8 @@ static int live_preempt_hang(void *arg) goto err_ctx_lo; } - spinner_end(&spin_hi); - spinner_end(&spin_lo); + igt_spinner_end(&spin_hi); + igt_spinner_end(&spin_lo); if (igt_flush_test(i915, I915_WAIT_LOCKED)) { err = -EIO; goto err_ctx_lo; @@ -566,9 +369,9 @@ err_ctx_lo: err_ctx_hi: kernel_context_close(ctx_hi); err_spin_lo: - spinner_fini(&spin_lo); + igt_spinner_fini(&spin_lo); err_spin_hi: - spinner_fini(&spin_hi); + igt_spinner_fini(&spin_hi); err_unlock: igt_flush_test(i915, I915_WAIT_LOCKED); intel_runtime_pm_put(i915); diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c index d1a0923d2f38..67017d5175b8 100644 --- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c +++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c @@ -6,6 +6,9 @@ #include "../i915_selftest.h" +#include "igt_flush_test.h" +#include "igt_reset.h" +#include "igt_spinner.h" #include "igt_wedge_me.h" #include "mock_context.h" @@ -91,17 +94,23 @@ err_obj: return ERR_PTR(err); } -static u32 get_whitelist_reg(const struct whitelist *w, unsigned int i) +static u32 +get_whitelist_reg(const struct intel_engine_cs *engine, unsigned int i) { - return i < w->count ? i915_mmio_reg_offset(w->reg[i]) : w->nopid; + i915_reg_t reg = i < engine->whitelist.count ? + engine->whitelist.list[i].reg : + RING_NOPID(engine->mmio_base); + + return i915_mmio_reg_offset(reg); } -static void print_results(const struct whitelist *w, const u32 *results) +static void +print_results(const struct intel_engine_cs *engine, const u32 *results) { unsigned int i; for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) { - u32 expected = get_whitelist_reg(w, i); + u32 expected = get_whitelist_reg(engine, i); u32 actual = results[i]; pr_info("RING_NONPRIV[%d]: expected 0x%08x, found 0x%08x\n", @@ -109,8 +118,7 @@ static void print_results(const struct whitelist *w, const u32 *results) } } -static int check_whitelist(const struct whitelist *w, - struct i915_gem_context *ctx, +static int check_whitelist(struct i915_gem_context *ctx, struct intel_engine_cs *engine) { struct drm_i915_gem_object *results; @@ -138,11 +146,11 @@ static int check_whitelist(const struct whitelist *w, } for (i = 0; i < RING_MAX_NONPRIV_SLOTS; i++) { - u32 expected = get_whitelist_reg(w, i); + u32 expected = get_whitelist_reg(engine, i); u32 actual = vaddr[i]; if (expected != actual) { - print_results(w, vaddr); + print_results(engine, vaddr); pr_err("Invalid RING_NONPRIV[%d], expected 0x%08x, found 0x%08x\n", i, expected, actual); @@ -159,66 +167,107 @@ out_put: static int do_device_reset(struct intel_engine_cs *engine) { - i915_reset(engine->i915, ENGINE_MASK(engine->id), NULL); + set_bit(I915_RESET_HANDOFF, &engine->i915->gpu_error.flags); + i915_reset(engine->i915, ENGINE_MASK(engine->id), "live_workarounds"); return 0; } static int do_engine_reset(struct intel_engine_cs *engine) { - return i915_reset_engine(engine, NULL); + return i915_reset_engine(engine, "live_workarounds"); } -static int switch_to_scratch_context(struct intel_engine_cs *engine) +static int +switch_to_scratch_context(struct intel_engine_cs *engine, + struct igt_spinner *spin) { struct i915_gem_context *ctx; struct i915_request *rq; + int err = 0; ctx = kernel_context(engine->i915); if (IS_ERR(ctx)) return PTR_ERR(ctx); intel_runtime_pm_get(engine->i915); - rq = i915_request_alloc(engine, ctx); + + if (spin) + rq = igt_spinner_create_request(spin, ctx, engine, MI_NOOP); + else + rq = i915_request_alloc(engine, ctx); + intel_runtime_pm_put(engine->i915); kernel_context_close(ctx); - if (IS_ERR(rq)) - return PTR_ERR(rq); + + if (IS_ERR(rq)) { + spin = NULL; + err = PTR_ERR(rq); + goto err; + } i915_request_add(rq); - return 0; + if (spin && !igt_wait_for_spinner(spin, rq)) { + pr_err("Spinner failed to start\n"); + err = -ETIMEDOUT; + } + +err: + if (err && spin) + igt_spinner_end(spin); + + return err; } static int check_whitelist_across_reset(struct intel_engine_cs *engine, int (*reset)(struct intel_engine_cs *), - const struct whitelist *w, const char *name) { + struct drm_i915_private *i915 = engine->i915; + bool want_spin = reset == do_engine_reset; struct i915_gem_context *ctx; + struct igt_spinner spin; int err; - ctx = kernel_context(engine->i915); + pr_info("Checking %d whitelisted registers (RING_NONPRIV) [%s]\n", + engine->whitelist.count, name); + + if (want_spin) { + err = igt_spinner_init(&spin, i915); + if (err) + return err; + } + + ctx = kernel_context(i915); if (IS_ERR(ctx)) return PTR_ERR(ctx); - err = check_whitelist(w, ctx, engine); + err = check_whitelist(ctx, engine); if (err) { pr_err("Invalid whitelist *before* %s reset!\n", name); goto out; } - err = switch_to_scratch_context(engine); + err = switch_to_scratch_context(engine, want_spin ? &spin : NULL); if (err) goto out; + intel_runtime_pm_get(i915); err = reset(engine); + intel_runtime_pm_put(i915); + + if (want_spin) { + igt_spinner_end(&spin); + igt_spinner_fini(&spin); + } + if (err) { pr_err("%s reset failed\n", name); goto out; } - err = check_whitelist(w, ctx, engine); + err = check_whitelist(ctx, engine); if (err) { pr_err("Whitelist not preserved in context across %s reset!\n", name); @@ -227,11 +276,11 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine, kernel_context_close(ctx); - ctx = kernel_context(engine->i915); + ctx = kernel_context(i915); if (IS_ERR(ctx)) return PTR_ERR(ctx); - err = check_whitelist(w, ctx, engine); + err = check_whitelist(ctx, engine); if (err) { pr_err("Invalid whitelist *after* %s reset in fresh context!\n", name); @@ -247,26 +296,18 @@ static int live_reset_whitelist(void *arg) { struct drm_i915_private *i915 = arg; struct intel_engine_cs *engine = i915->engine[RCS]; - struct i915_gpu_error *error = &i915->gpu_error; - struct whitelist w; int err = 0; /* If we reset the gpu, we should not lose the RING_NONPRIV */ - if (!engine) - return 0; - - if (!whitelist_build(engine, &w)) + if (!engine || engine->whitelist.count == 0) return 0; - pr_info("Checking %d whitelisted registers (RING_NONPRIV)\n", w.count); - - set_bit(I915_RESET_BACKOFF, &error->flags); - set_bit(I915_RESET_ENGINE + engine->id, &error->flags); + igt_global_reset_lock(i915); if (intel_has_reset_engine(i915)) { err = check_whitelist_across_reset(engine, - do_engine_reset, &w, + do_engine_reset, "engine"); if (err) goto out; @@ -274,22 +315,156 @@ static int live_reset_whitelist(void *arg) if (intel_has_gpu_reset(i915)) { err = check_whitelist_across_reset(engine, - do_device_reset, &w, + do_device_reset, "device"); if (err) goto out; } out: - clear_bit(I915_RESET_ENGINE + engine->id, &error->flags); - clear_bit(I915_RESET_BACKOFF, &error->flags); + igt_global_reset_unlock(i915); return err; } +static bool verify_gt_engine_wa(struct drm_i915_private *i915, const char *str) +{ + struct intel_engine_cs *engine; + enum intel_engine_id id; + bool ok = true; + + ok &= intel_gt_verify_workarounds(i915, str); + + for_each_engine(engine, i915, id) + ok &= intel_engine_verify_workarounds(engine, str); + + return ok; +} + +static int +live_gpu_reset_gt_engine_workarounds(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct i915_gpu_error *error = &i915->gpu_error; + bool ok; + + if (!intel_has_gpu_reset(i915)) + return 0; + + pr_info("Verifying after GPU reset...\n"); + + igt_global_reset_lock(i915); + + ok = verify_gt_engine_wa(i915, "before reset"); + if (!ok) + goto out; + + intel_runtime_pm_get(i915); + set_bit(I915_RESET_HANDOFF, &error->flags); + i915_reset(i915, ALL_ENGINES, "live_workarounds"); + intel_runtime_pm_put(i915); + + ok = verify_gt_engine_wa(i915, "after reset"); + +out: + igt_global_reset_unlock(i915); + + return ok ? 0 : -ESRCH; +} + +static int +live_engine_reset_gt_engine_workarounds(void *arg) +{ + struct drm_i915_private *i915 = arg; + struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + struct igt_spinner spin; + enum intel_engine_id id; + struct i915_request *rq; + int ret = 0; + + if (!intel_has_reset_engine(i915)) + return 0; + + ctx = kernel_context(i915); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + igt_global_reset_lock(i915); + + for_each_engine(engine, i915, id) { + bool ok; + + pr_info("Verifying after %s reset...\n", engine->name); + + ok = verify_gt_engine_wa(i915, "before reset"); + if (!ok) { + ret = -ESRCH; + goto err; + } + + intel_runtime_pm_get(i915); + i915_reset_engine(engine, "live_workarounds"); + intel_runtime_pm_put(i915); + + ok = verify_gt_engine_wa(i915, "after idle reset"); + if (!ok) { + ret = -ESRCH; + goto err; + } + + ret = igt_spinner_init(&spin, i915); + if (ret) + goto err; + + intel_runtime_pm_get(i915); + + rq = igt_spinner_create_request(&spin, ctx, engine, MI_NOOP); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + igt_spinner_fini(&spin); + intel_runtime_pm_put(i915); + goto err; + } + + i915_request_add(rq); + + if (!igt_wait_for_spinner(&spin, rq)) { + pr_err("Spinner failed to start\n"); + igt_spinner_fini(&spin); + intel_runtime_pm_put(i915); + ret = -ETIMEDOUT; + goto err; + } + + i915_reset_engine(engine, "live_workarounds"); + + intel_runtime_pm_put(i915); + + igt_spinner_end(&spin); + igt_spinner_fini(&spin); + + ok = verify_gt_engine_wa(i915, "after busy reset"); + if (!ok) { + ret = -ESRCH; + goto err; + } + } + +err: + igt_global_reset_unlock(i915); + kernel_context_close(ctx); + + igt_flush_test(i915, I915_WAIT_LOCKED); + + return ret; +} + int intel_workarounds_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(live_reset_whitelist), + SUBTEST(live_gpu_reset_gt_engine_workarounds), + SUBTEST(live_engine_reset_gt_engine_workarounds), }; int err; |