diff options
103 files changed, 7746 insertions, 4881 deletions
diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst index 4b4dc236ef6f..b422eb8edf16 100644 --- a/Documentation/gpu/drm-kms-helpers.rst +++ b/Documentation/gpu/drm-kms-helpers.rst @@ -232,6 +232,18 @@ MIPI DSI Helper Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_mipi_dsi.c :export: +Display Stream Compression Helper Functions Reference +===================================================== + +.. kernel-doc:: drivers/gpu/drm/drm_dsc.c + :doc: dsc helpers + +.. kernel-doc:: include/drm/drm_dsc.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/drm_dsc.c + :export: + Output Probing Helper Functions Reference ========================================= diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 7f3be3506057..65a643da48d7 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..516e82d0ed50 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -1273,6 +1273,8 @@ static const struct dpcd_quirk dpcd_quirk_list[] = { { OUI(0x00, 0x22, 0xb9), DEVICE_ID_ANY, true, BIT(DP_DPCD_QUIRK_CONSTANT_N) }, /* LG LP140WF6-SPM1 eDP panel */ { OUI(0x00, 0x22, 0xb9), DEVICE_ID('s', 'i', 'v', 'a', 'r', 'T'), false, BIT(DP_DPCD_QUIRK_CONSTANT_N) }, + /* Apple panels need some additional handling to support PSR */ + { OUI(0x00, 0x10, 0xfa), DEVICE_ID_ANY, false, BIT(DP_DPCD_QUIRK_NO_PSR) } }; #undef OUI @@ -1428,17 +1430,19 @@ 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 <[email protected]> + */ + +#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..c34bee16730d 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -40,7 +40,7 @@ i915-y := i915_drv.o \ i915_mm.o \ i915_params.o \ i915_pci.o \ - i915_suspend.o \ + i915_suspend.o \ i915_syncmap.o \ i915_sw_fence.o \ i915_sysfs.o \ @@ -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/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index c628be05fbfe..e1c860f80eb0 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -148,10 +148,10 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm, high_avail / vgpu_types[i].high_mm); - if (IS_GEN8(gvt->dev_priv)) + if (IS_GEN(gvt->dev_priv, 8)) sprintf(gvt->types[i].name, "GVTg_V4_%s", vgpu_types[i].name); - else if (IS_GEN9(gvt->dev_priv)) + else if (IS_GEN(gvt->dev_priv, 9)) sprintf(gvt->types[i].name, "GVTg_V5_%s", vgpu_types[i].name); diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c index 95478db9998b..33e8eed64423 100644 --- a/drivers/gpu/drm/i915/i915_cmd_parser.c +++ b/drivers/gpu/drm/i915/i915_cmd_parser.c @@ -865,7 +865,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine) int cmd_table_count; int ret; - if (!IS_GEN7(engine->i915)) + if (!IS_GEN(engine->i915, 7)) return; switch (engine->id) { diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 7f455bca528e..c77326a7d058 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -48,7 +48,7 @@ static int i915_capabilities(struct seq_file *m, void *data) seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev_priv)); intel_device_info_dump_flags(info, &p); - intel_device_info_dump_runtime(info, &p); + intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p); intel_driver_caps_print(&dev_priv->caps, &p); kernel_param_lock(THIS_MODULE); @@ -297,11 +297,12 @@ out: } struct file_stats { - struct drm_i915_file_private *file_priv; + struct i915_address_space *vm; unsigned long count; u64 total, unbound; u64 global, shared; u64 active, inactive; + u64 closed; }; static int per_file_stats(int id, void *ptr, void *data) @@ -326,9 +327,7 @@ static int per_file_stats(int id, void *ptr, void *data) if (i915_vma_is_ggtt(vma)) { stats->global += vma->node.size; } else { - struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm); - - if (ppgtt->vm.file != stats->file_priv) + if (vma->vm != stats->vm) continue; } @@ -336,6 +335,9 @@ static int per_file_stats(int id, void *ptr, void *data) stats->active += vma->node.size; else stats->inactive += vma->node.size; + + if (i915_vma_is_closed(vma)) + stats->closed += vma->node.size; } return 0; @@ -343,7 +345,7 @@ static int per_file_stats(int id, void *ptr, void *data) #define print_file_stats(m, name, stats) do { \ if (stats.count) \ - seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound)\n", \ + seq_printf(m, "%s: %lu objects, %llu bytes (%llu active, %llu inactive, %llu global, %llu shared, %llu unbound, %llu closed)\n", \ name, \ stats.count, \ stats.total, \ @@ -351,20 +353,19 @@ static int per_file_stats(int id, void *ptr, void *data) stats.inactive, \ stats.global, \ stats.shared, \ - stats.unbound); \ + stats.unbound, \ + stats.closed); \ } while (0) static void print_batch_pool_stats(struct seq_file *m, struct drm_i915_private *dev_priv) { struct drm_i915_gem_object *obj; - struct file_stats stats; struct intel_engine_cs *engine; + struct file_stats stats = {}; enum intel_engine_id id; int j; - memset(&stats, 0, sizeof(stats)); - for_each_engine(engine, dev_priv, id) { for (j = 0; j < ARRAY_SIZE(engine->batch_pool.cache_list); j++) { list_for_each_entry(obj, @@ -377,44 +378,47 @@ static void print_batch_pool_stats(struct seq_file *m, print_file_stats(m, "[k]batch pool", stats); } -static int per_file_ctx_stats(int idx, void *ptr, void *data) +static void print_context_stats(struct seq_file *m, + struct drm_i915_private *i915) { - struct i915_gem_context *ctx = ptr; - struct intel_engine_cs *engine; - enum intel_engine_id id; + struct file_stats kstats = {}; + struct i915_gem_context *ctx; - for_each_engine(engine, ctx->i915, id) { - struct intel_context *ce = to_intel_context(ctx, engine); + list_for_each_entry(ctx, &i915->contexts.list, link) { + struct intel_engine_cs *engine; + enum intel_engine_id id; - if (ce->state) - per_file_stats(0, ce->state->obj, data); - if (ce->ring) - per_file_stats(0, ce->ring->vma->obj, data); - } + for_each_engine(engine, i915, id) { + struct intel_context *ce = to_intel_context(ctx, engine); - return 0; -} + if (ce->state) + per_file_stats(0, ce->state->obj, &kstats); + if (ce->ring) + per_file_stats(0, ce->ring->vma->obj, &kstats); + } -static void print_context_stats(struct seq_file *m, - struct drm_i915_private *dev_priv) -{ - struct drm_device *dev = &dev_priv->drm; - struct file_stats stats; - struct drm_file *file; + if (!IS_ERR_OR_NULL(ctx->file_priv)) { + struct file_stats stats = { .vm = &ctx->ppgtt->vm, }; + struct drm_file *file = ctx->file_priv->file; + struct task_struct *task; + char name[80]; - memset(&stats, 0, sizeof(stats)); + spin_lock(&file->table_lock); + idr_for_each(&file->object_idr, per_file_stats, &stats); + spin_unlock(&file->table_lock); - mutex_lock(&dev->struct_mutex); - if (dev_priv->kernel_context) - per_file_ctx_stats(0, dev_priv->kernel_context, &stats); + rcu_read_lock(); + task = pid_task(ctx->pid ?: file->pid, PIDTYPE_PID); + snprintf(name, sizeof(name), "%s/%d", + task ? task->comm : "<unknown>", + ctx->user_handle); + rcu_read_unlock(); - list_for_each_entry(file, &dev->filelist, lhead) { - struct drm_i915_file_private *fpriv = file->driver_priv; - idr_for_each(&fpriv->context_idr, per_file_ctx_stats, &stats); + print_file_stats(m, name, stats); + } } - mutex_unlock(&dev->struct_mutex); - print_file_stats(m, "[k]contexts", stats); + print_file_stats(m, "[k]contexts", kstats); } static int i915_gem_object_info(struct seq_file *m, void *data) @@ -426,14 +430,9 @@ static int i915_gem_object_info(struct seq_file *m, void *data) u64 size, mapped_size, purgeable_size, dpy_size, huge_size; struct drm_i915_gem_object *obj; unsigned int page_sizes = 0; - struct drm_file *file; char buf[80]; int ret; - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; - seq_printf(m, "%u objects, %llu bytes\n", dev_priv->mm.object_count, dev_priv->mm.object_memory); @@ -514,43 +513,14 @@ static int i915_gem_object_info(struct seq_file *m, void *data) buf, sizeof(buf))); seq_putc(m, '\n'); - print_batch_pool_stats(m, dev_priv); - mutex_unlock(&dev->struct_mutex); - mutex_lock(&dev->filelist_mutex); - print_context_stats(m, dev_priv); - list_for_each_entry_reverse(file, &dev->filelist, lhead) { - struct file_stats stats; - struct drm_i915_file_private *file_priv = file->driver_priv; - struct i915_request *request; - struct task_struct *task; - - mutex_lock(&dev->struct_mutex); - - memset(&stats, 0, sizeof(stats)); - stats.file_priv = file->driver_priv; - spin_lock(&file->table_lock); - idr_for_each(&file->object_idr, per_file_stats, &stats); - spin_unlock(&file->table_lock); - /* - * Although we have a valid reference on file->pid, that does - * not guarantee that the task_struct who called get_pid() is - * still alive (e.g. get_pid(current) => fork() => exit()). - * Therefore, we need to protect this ->comm access using RCU. - */ - request = list_first_entry_or_null(&file_priv->mm.request_list, - struct i915_request, - client_link); - rcu_read_lock(); - task = pid_task(request && request->gem_context->pid ? - request->gem_context->pid : file->pid, - PIDTYPE_PID); - print_file_stats(m, task ? task->comm : "<unknown>", stats); - rcu_read_unlock(); + ret = mutex_lock_interruptible(&dev->struct_mutex); + if (ret) + return ret; - mutex_unlock(&dev->struct_mutex); - } - mutex_unlock(&dev->filelist_mutex); + print_batch_pool_stats(m, dev_priv); + print_context_stats(m, dev_priv); + mutex_unlock(&dev->struct_mutex); return 0; } @@ -943,30 +913,30 @@ 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; } @@ -984,8 +954,8 @@ static int i915_gpu_info_open(struct inode *inode, struct file *file) intel_runtime_pm_get(i915); gpu = i915_capture_gpu_state(i915); intel_runtime_pm_put(i915); - if (!gpu) - return -ENOMEM; + if (IS_ERR(gpu)) + return PTR_ERR(gpu); file->private_data = gpu; return 0; @@ -1018,7 +988,13 @@ i915_error_state_write(struct file *filp, static int i915_error_state_open(struct inode *inode, struct file *file) { - file->private_data = i915_first_error_state(inode->i_private); + struct i915_gpu_state *error; + + error = i915_first_error_state(inode->i_private); + if (IS_ERR(error)) + return PTR_ERR(error); + + file->private_data = error; return 0; } @@ -1032,30 +1008,6 @@ static const struct file_operations i915_error_state_fops = { }; #endif -static int -i915_next_seqno_set(void *data, u64 val) -{ - struct drm_i915_private *dev_priv = data; - struct drm_device *dev = &dev_priv->drm; - int ret; - - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - return ret; - - intel_runtime_pm_get(dev_priv); - ret = i915_gem_set_global_seqno(dev, val); - intel_runtime_pm_put(dev_priv); - - mutex_unlock(&dev->struct_mutex); - - return ret; -} - -DEFINE_SIMPLE_ATTRIBUTE(i915_next_seqno_fops, - NULL, i915_next_seqno_set, - "0x%llx\n"); - static int i915_frequency_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -1064,7 +1016,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused) intel_runtime_pm_get(dev_priv); - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { u16 rgvswctl = I915_READ16(MEMSWCTL); u16 rgvstat = I915_READ16(MEMSTAT_ILK); @@ -1785,7 +1737,7 @@ static int i915_emon_status(struct seq_file *m, void *unused) unsigned long temp, chipset, gfx; int ret; - if (!IS_GEN5(dev_priv)) + if (!IS_GEN(dev_priv, 5)) return -ENODEV; intel_runtime_pm_get(dev_priv); @@ -2034,7 +1986,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data) seq_printf(m, "bit6 swizzle for Y-tiling = %s\n", swizzle_string(dev_priv->mm.bit_6_swizzle_y)); - if (IS_GEN3(dev_priv) || IS_GEN4(dev_priv)) { + if (IS_GEN_RANGE(dev_priv, 3, 4)) { seq_printf(m, "DDC = 0x%08x\n", I915_READ(DCC)); seq_printf(m, "DDC2 = 0x%08x\n", @@ -2070,124 +2022,6 @@ static int i915_swizzle_info(struct seq_file *m, void *data) return 0; } -static int per_file_ctx(int id, void *ptr, void *data) -{ - struct i915_gem_context *ctx = ptr; - struct seq_file *m = data; - struct i915_hw_ppgtt *ppgtt = ctx->ppgtt; - - if (!ppgtt) { - seq_printf(m, " no ppgtt for context %d\n", - ctx->user_handle); - return 0; - } - - if (i915_gem_context_is_default(ctx)) - seq_puts(m, " default context:\n"); - else - seq_printf(m, " context %d:\n", ctx->user_handle); - ppgtt->debug_dump(ppgtt, m); - - return 0; -} - -static void gen8_ppgtt_info(struct seq_file *m, - struct drm_i915_private *dev_priv) -{ - struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; - struct intel_engine_cs *engine; - enum intel_engine_id id; - int i; - - if (!ppgtt) - return; - - for_each_engine(engine, dev_priv, id) { - seq_printf(m, "%s\n", engine->name); - for (i = 0; i < 4; i++) { - u64 pdp = I915_READ(GEN8_RING_PDP_UDW(engine, i)); - pdp <<= 32; - pdp |= I915_READ(GEN8_RING_PDP_LDW(engine, i)); - seq_printf(m, "\tPDP%d 0x%016llx\n", i, pdp); - } - } -} - -static void gen6_ppgtt_info(struct seq_file *m, - struct drm_i915_private *dev_priv) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - - if (IS_GEN6(dev_priv)) - seq_printf(m, "GFX_MODE: 0x%08x\n", I915_READ(GFX_MODE)); - - for_each_engine(engine, dev_priv, id) { - seq_printf(m, "%s\n", engine->name); - if (IS_GEN7(dev_priv)) - seq_printf(m, "GFX_MODE: 0x%08x\n", - I915_READ(RING_MODE_GEN7(engine))); - seq_printf(m, "PP_DIR_BASE: 0x%08x\n", - I915_READ(RING_PP_DIR_BASE(engine))); - seq_printf(m, "PP_DIR_BASE_READ: 0x%08x\n", - I915_READ(RING_PP_DIR_BASE_READ(engine))); - seq_printf(m, "PP_DIR_DCLV: 0x%08x\n", - I915_READ(RING_PP_DIR_DCLV(engine))); - } - if (dev_priv->mm.aliasing_ppgtt) { - struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; - - seq_puts(m, "aliasing PPGTT:\n"); - seq_printf(m, "pd gtt offset: 0x%08x\n", ppgtt->pd.base.ggtt_offset); - - ppgtt->debug_dump(ppgtt, m); - } - - seq_printf(m, "ECOCHK: 0x%08x\n", I915_READ(GAM_ECOCHK)); -} - -static int i915_ppgtt_info(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = node_to_i915(m->private); - struct drm_device *dev = &dev_priv->drm; - struct drm_file *file; - int ret; - - mutex_lock(&dev->filelist_mutex); - ret = mutex_lock_interruptible(&dev->struct_mutex); - if (ret) - goto out_unlock; - - intel_runtime_pm_get(dev_priv); - - if (INTEL_GEN(dev_priv) >= 8) - gen8_ppgtt_info(m, dev_priv); - else if (INTEL_GEN(dev_priv) >= 6) - gen6_ppgtt_info(m, dev_priv); - - list_for_each_entry_reverse(file, &dev->filelist, lhead) { - struct drm_i915_file_private *file_priv = file->driver_priv; - struct task_struct *task; - - task = get_pid_task(file->pid, PIDTYPE_PID); - if (!task) { - ret = -ESRCH; - goto out_rpm; - } - seq_printf(m, "\nproc: %s\n", task->comm); - put_task_struct(task); - idr_for_each(&file_priv->context_idr, per_file_ctx, - (void *)(unsigned long)m); - } - -out_rpm: - intel_runtime_pm_put(dev_priv); - mutex_unlock(&dev->struct_mutex); -out_unlock: - mutex_unlock(&dev->filelist_mutex); - return ret; -} - static int count_irq_waiters(struct drm_i915_private *i915) { struct intel_engine_cs *engine; @@ -3293,7 +3127,7 @@ static int i915_engine_info(struct seq_file *m, void *unused) seq_printf(m, "Global active requests: %d\n", dev_priv->gt.active_requests); seq_printf(m, "CS timestamp frequency: %u kHz\n", - dev_priv->info.cs_timestamp_frequency_khz); + RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz); p = drm_seq_file_printer(m); for_each_engine(engine, dev_priv, id) @@ -3309,7 +3143,7 @@ static int i915_rcs_topology(struct seq_file *m, void *unused) struct drm_i915_private *dev_priv = node_to_i915(m->private); struct drm_printer p = drm_seq_file_printer(m); - intel_device_info_dump_topology(&INTEL_INFO(dev_priv)->sseu, &p); + intel_device_info_dump_topology(&RUNTIME_INFO(dev_priv)->sseu, &p); return 0; } @@ -3375,13 +3209,15 @@ 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 +3277,32 @@ 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)); } @@ -4210,9 +4047,6 @@ i915_drop_caches_set(void *data, u64 val) I915_WAIT_LOCKED, MAX_SCHEDULE_TIMEOUT); - if (ret == 0 && val & DROP_RESET_SEQNO) - ret = i915_gem_set_global_seqno(&i915->drm, 1); - if (val & DROP_RETIRE) i915_retire_requests(i915); @@ -4265,7 +4099,7 @@ i915_cache_sharing_get(void *data, u64 *val) struct drm_i915_private *dev_priv = data; u32 snpcr; - if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv))) + if (!(IS_GEN_RANGE(dev_priv, 6, 7))) return -ENODEV; intel_runtime_pm_get(dev_priv); @@ -4285,7 +4119,7 @@ i915_cache_sharing_set(void *data, u64 val) struct drm_i915_private *dev_priv = data; u32 snpcr; - if (!(IS_GEN6(dev_priv) || IS_GEN7(dev_priv))) + if (!(IS_GEN_RANGE(dev_priv, 6, 7))) return -ENODEV; if (val > 3) @@ -4345,7 +4179,7 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv, struct sseu_dev_info *sseu) { #define SS_MAX 6 - const struct intel_device_info *info = INTEL_INFO(dev_priv); + const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv); u32 s_reg[SS_MAX], eu_reg[2 * SS_MAX], eu_mask[2]; int s, ss; @@ -4401,7 +4235,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv, struct sseu_dev_info *sseu) { #define SS_MAX 3 - const struct intel_device_info *info = INTEL_INFO(dev_priv); + const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv); u32 s_reg[SS_MAX], eu_reg[2 * SS_MAX], eu_mask[2]; int s, ss; @@ -4429,7 +4263,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv, if (IS_GEN9_BC(dev_priv)) sseu->subslice_mask[s] = - INTEL_INFO(dev_priv)->sseu.subslice_mask[s]; + RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s]; for (ss = 0; ss < info->sseu.max_subslices; ss++) { unsigned int eu_cnt; @@ -4463,10 +4297,10 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv, if (sseu->slice_mask) { sseu->eu_per_subslice = - INTEL_INFO(dev_priv)->sseu.eu_per_subslice; + RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice; for (s = 0; s < fls(sseu->slice_mask); s++) { sseu->subslice_mask[s] = - INTEL_INFO(dev_priv)->sseu.subslice_mask[s]; + RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s]; } sseu->eu_total = sseu->eu_per_subslice * sseu_subslice_total(sseu); @@ -4474,7 +4308,7 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv, /* subtract fused off EU(s) from enabled slice(s) */ for (s = 0; s < fls(sseu->slice_mask); s++) { u8 subslice_7eu = - INTEL_INFO(dev_priv)->sseu.subslice_7eu[s]; + RUNTIME_INFO(dev_priv)->sseu.subslice_7eu[s]; sseu->eu_total -= hweight8(subslice_7eu); } @@ -4527,14 +4361,14 @@ static int i915_sseu_status(struct seq_file *m, void *unused) return -ENODEV; seq_puts(m, "SSEU Device Info\n"); - i915_print_sseu_info(m, true, &INTEL_INFO(dev_priv)->sseu); + i915_print_sseu_info(m, true, &RUNTIME_INFO(dev_priv)->sseu); seq_puts(m, "SSEU Device Status\n"); memset(&sseu, 0, sizeof(sseu)); - sseu.max_slices = INTEL_INFO(dev_priv)->sseu.max_slices; - sseu.max_subslices = INTEL_INFO(dev_priv)->sseu.max_subslices; + sseu.max_slices = RUNTIME_INFO(dev_priv)->sseu.max_slices; + sseu.max_subslices = RUNTIME_INFO(dev_priv)->sseu.max_subslices; sseu.max_eus_per_subslice = - INTEL_INFO(dev_priv)->sseu.max_eus_per_subslice; + RUNTIME_INFO(dev_priv)->sseu.max_eus_per_subslice; intel_runtime_pm_get(dev_priv); @@ -4542,7 +4376,7 @@ static int i915_sseu_status(struct seq_file *m, void *unused) cherryview_sseu_device_status(dev_priv, &sseu); } else if (IS_BROADWELL(dev_priv)) { broadwell_sseu_device_status(dev_priv, &sseu); - } else if (IS_GEN9(dev_priv)) { + } else if (IS_GEN(dev_priv, 9)) { gen9_sseu_device_status(dev_priv, &sseu); } else if (INTEL_GEN(dev_priv) >= 10) { gen10_sseu_device_status(dev_priv, &sseu); @@ -4592,6 +4426,13 @@ 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))); @@ -4896,7 +4737,6 @@ static const struct drm_info_list i915_debugfs_list[] = { {"i915_context_status", i915_context_status, 0}, {"i915_forcewake_domains", i915_forcewake_domains, 0}, {"i915_swizzle_info", i915_swizzle_info, 0}, - {"i915_ppgtt_info", i915_ppgtt_info, 0}, {"i915_llc", i915_llc, 0}, {"i915_edp_psr_status", i915_edp_psr_status, 0}, {"i915_energy_uJ", i915_energy_uJ, 0}, @@ -4931,7 +4771,6 @@ static const struct i915_debugfs_files { {"i915_gpu_info", &i915_gpu_info_fops}, #endif {"i915_fifo_underrun_reset", &i915_fifo_underrun_reset_ops}, - {"i915_next_seqno", &i915_next_seqno_fops}, {"i915_pri_wm_latency", &i915_pri_wm_latency_fops}, {"i915_spr_wm_latency", &i915_spr_wm_latency_fops}, {"i915_cur_wm_latency", &i915_cur_wm_latency_fops}, @@ -5078,6 +4917,106 @@ static int i915_hdcp_sink_capability_show(struct seq_file *m, void *data) } DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); +static int i915_dsc_fec_support_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct drm_device *dev = connector->dev; + struct drm_crtc *crtc; + struct intel_dp *intel_dp; + struct drm_modeset_acquire_ctx ctx; + struct intel_crtc_state *crtc_state = NULL; + int ret = 0; + bool try_again = false; + + drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE); + + do { + try_again = false; + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, + &ctx); + if (ret) { + ret = -EINTR; + break; + } + crtc = connector->state->crtc; + if (connector->status != connector_status_connected || !crtc) { + ret = -ENODEV; + break; + } + ret = drm_modeset_lock(&crtc->mutex, &ctx); + if (ret == -EDEADLK) { + ret = drm_modeset_backoff(&ctx); + if (!ret) { + try_again = true; + continue; + } + break; + } else if (ret) { + break; + } + intel_dp = enc_to_intel_dp(&intel_attached_encoder(connector)->base); + crtc_state = to_intel_crtc_state(crtc->state); + seq_printf(m, "DSC_Enabled: %s\n", + yesno(crtc_state->dsc_params.compression_enable)); + if (intel_dp->dsc_dpcd) + seq_printf(m, "DSC_Sink_Support: %s\n", + yesno(drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd))); + if (!intel_dp_is_edp(intel_dp)) + seq_printf(m, "FEC_Sink_Support: %s\n", + yesno(drm_dp_sink_supports_fec(intel_dp->fec_capable))); + } while (try_again); + + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + + return ret; +} + +static ssize_t i915_dsc_fec_support_write(struct file *file, + const char __user *ubuf, + size_t len, loff_t *offp) +{ + bool dsc_enable = false; + int ret; + struct drm_connector *connector = + ((struct seq_file *)file->private_data)->private; + struct intel_encoder *encoder = intel_attached_encoder(connector); + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + + if (len == 0) + return 0; + + DRM_DEBUG_DRIVER("Copied %zu bytes from user to force DSC\n", + len); + + ret = kstrtobool_from_user(ubuf, len, &dsc_enable); + if (ret < 0) + return ret; + + DRM_DEBUG_DRIVER("Got %s for DSC Enable\n", + (dsc_enable) ? "true" : "false"); + intel_dp->force_dsc_en = dsc_enable; + + *offp += len; + return len; +} + +static int i915_dsc_fec_support_open(struct inode *inode, + struct file *file) +{ + return single_open(file, i915_dsc_fec_support_show, + inode->i_private); +} + +static const struct file_operations i915_dsc_fec_support_fops = { + .owner = THIS_MODULE, + .open = i915_dsc_fec_support_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = i915_dsc_fec_support_write +}; + /** * i915_debugfs_connector_add - add i915 specific connector debugfs files * @connector: pointer to a registered drm_connector @@ -5090,6 +5029,7 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); int i915_debugfs_connector_add(struct drm_connector *connector) { struct dentry *root = connector->debugfs_entry; + struct drm_i915_private *dev_priv = to_i915(connector->dev); /* The connector must have been registered beforehands. */ if (!root) @@ -5114,5 +5054,11 @@ int i915_debugfs_connector_add(struct drm_connector *connector) connector, &i915_hdcp_sink_capability_fops); } + if (INTEL_GEN(dev_priv) >= 10 && + (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector->connector_type == DRM_MODE_CONNECTOR_eDP)) + debugfs_create_file("i915_dsc_fec_support", S_IRUGO, root, + connector, &i915_dsc_fec_support_fops); + return 0; } diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index b1d23c73c147..17fca3ba343e 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; @@ -131,15 +132,15 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) switch (id) { case INTEL_PCH_IBX_DEVICE_ID_TYPE: DRM_DEBUG_KMS("Found Ibex Peak PCH\n"); - WARN_ON(!IS_GEN5(dev_priv)); + WARN_ON(!IS_GEN(dev_priv, 5)); return PCH_IBX; case INTEL_PCH_CPT_DEVICE_ID_TYPE: DRM_DEBUG_KMS("Found CougarPoint PCH\n"); - WARN_ON(!IS_GEN6(dev_priv) && !IS_IVYBRIDGE(dev_priv)); + WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv)); return PCH_CPT; case INTEL_PCH_PPT_DEVICE_ID_TYPE: DRM_DEBUG_KMS("Found PantherPoint PCH\n"); - WARN_ON(!IS_GEN6(dev_priv) && !IS_IVYBRIDGE(dev_priv)); + WARN_ON(!IS_GEN(dev_priv, 6) && !IS_IVYBRIDGE(dev_priv)); /* PantherPoint is CPT compatible */ return PCH_CPT; case INTEL_PCH_LPT_DEVICE_ID_TYPE: @@ -216,9 +217,9 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv) * make an educated guess as to which PCH is really there. */ - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) id = INTEL_PCH_IBX_DEVICE_ID_TYPE; - else if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) + else if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) id = INTEL_PCH_CPT_DEVICE_ID_TYPE; else if (IS_HSW_ULT(dev_priv) || IS_BDW_ULT(dev_priv)) id = INTEL_PCH_LPT_LP_DEVICE_ID_TYPE; @@ -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; @@ -348,7 +349,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, value = min_t(int, INTEL_PPGTT(dev_priv), I915_GEM_PPGTT_FULL); break; case I915_PARAM_HAS_SEMAPHORES: - value = HAS_LEGACY_SEMAPHORES(dev_priv); + value = 0; break; case I915_PARAM_HAS_SECURE_BATCHES: value = capable(CAP_SYS_ADMIN); @@ -357,12 +358,12 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, value = i915_cmd_parser_get_version(dev_priv); break; case I915_PARAM_SUBSLICE_TOTAL: - value = sseu_subslice_total(&INTEL_INFO(dev_priv)->sseu); + value = sseu_subslice_total(&RUNTIME_INFO(dev_priv)->sseu); if (!value) return -ENODEV; break; case I915_PARAM_EU_TOTAL: - value = INTEL_INFO(dev_priv)->sseu.eu_total; + value = RUNTIME_INFO(dev_priv)->sseu.eu_total; if (!value) return -ENODEV; break; @@ -379,7 +380,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, value = HAS_POOLED_EU(dev_priv); break; case I915_PARAM_MIN_EU_IN_POOL: - value = INTEL_INFO(dev_priv)->sseu.min_eu_in_pool; + value = RUNTIME_INFO(dev_priv)->sseu.min_eu_in_pool; break; case I915_PARAM_HUC_STATUS: value = intel_huc_check_status(&dev_priv->huc); @@ -429,17 +430,17 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data, value = intel_engines_has_context_isolation(dev_priv); break; case I915_PARAM_SLICE_MASK: - value = INTEL_INFO(dev_priv)->sseu.slice_mask; + value = RUNTIME_INFO(dev_priv)->sseu.slice_mask; if (!value) return -ENODEV; break; case I915_PARAM_SUBSLICE_MASK: - value = INTEL_INFO(dev_priv)->sseu.subslice_mask[0]; + value = RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0]; if (!value) return -ENODEV; break; case I915_PARAM_CS_TIMESTAMP_FREQUENCY: - value = 1000 * INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz; + value = 1000 * RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz; break; case I915_PARAM_MMAP_GTT_COHERENT: value = INTEL_INFO(dev_priv)->has_coherent_ggtt; @@ -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. " @@ -964,7 +966,7 @@ static int i915_mmio_setup(struct drm_i915_private *dev_priv) int mmio_bar; int mmio_size; - mmio_bar = IS_GEN2(dev_priv) ? 1 : 0; + mmio_bar = IS_GEN(dev_priv, 2) ? 1 : 0; /* * Before gen4, the registers and the GTT are behind different BARs. * However, from gen4 onwards, the registers and the GTT are shared @@ -1339,7 +1341,7 @@ intel_get_dram_info(struct drm_i915_private *dev_priv) /* Need to calculate bandwidth only for Gen9 */ if (IS_BROXTON(dev_priv)) ret = bxt_get_dram_info(dev_priv); - else if (IS_GEN9(dev_priv)) + else if (IS_GEN(dev_priv, 9)) ret = skl_get_dram_info(dev_priv); else ret = skl_dram_get_channels_info(dev_priv); @@ -1372,7 +1374,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) if (i915_inject_load_failure()) return -ENODEV; - intel_device_info_runtime_init(mkwrite_device_info(dev_priv)); + intel_device_info_runtime_init(dev_priv); if (HAS_PPGTT(dev_priv)) { if (intel_vgpu_active(dev_priv) && @@ -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); @@ -1420,7 +1436,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) pci_set_master(pdev); /* overlay on gen2 is broken and can't address above 1G */ - if (IS_GEN2(dev_priv)) { + if (IS_GEN(dev_priv, 2)) { ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(30)); if (ret) { DRM_ERROR("failed to set DMA mask\n"); @@ -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 @@ -1551,13 +1568,13 @@ 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(); } - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) intel_gpu_ips_init(dev_priv); intel_audio_init(dev_priv); @@ -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); @@ -1619,8 +1636,14 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv) if (drm_debug & DRM_UT_DRIVER) { struct drm_printer p = drm_debug_printer("i915 device info:"); - intel_device_info_dump(&dev_priv->info, &p); - intel_device_info_dump_runtime(&dev_priv->info, &p); + drm_printf(&p, "pciid=0x%04x rev=0x%02x platform=%s gen=%i\n", + INTEL_DEVID(dev_priv), + INTEL_REVID(dev_priv), + intel_platform_name(INTEL_INFO(dev_priv)->platform), + INTEL_GEN(dev_priv)); + + intel_device_info_dump_flags(INTEL_INFO(dev_priv), &p); + intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p); } if (IS_ENABLED(CONFIG_DRM_I915_DEBUG)) @@ -1657,7 +1680,7 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the write-once "constant" device info */ device_info = mkwrite_device_info(i915); memcpy(device_info, match_info, sizeof(*device_info)); - device_info->device_id = pdev->device; + RUNTIME_INFO(i915)->device_id = pdev->device; BUILD_BUG_ON(INTEL_MAX_PLATFORMS > BITS_PER_TYPE(device_info->platform_mask)); @@ -2157,7 +2180,7 @@ static int i915_drm_resume_early(struct drm_device *dev) intel_power_domains_resume(dev_priv); - intel_engines_sanitize(dev_priv); + intel_engines_sanitize(dev_priv, true); enable_rpm_wakeref_asserts(dev_priv); @@ -2209,6 +2232,7 @@ void i915_reset(struct drm_i915_private *i915, might_sleep(); lockdep_assert_held(&i915->drm.struct_mutex); + assert_rpm_wakelock_held(i915); GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags)); if (!test_bit(I915_RESET_HANDOFF, &error->flags)) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 4064e49dbf70..7fa2a405c5fe 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 "20181221" +#define DRIVER_TIMESTAMP 1545422678 /* 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 @@ -279,16 +281,14 @@ struct drm_i915_display_funcs { int (*get_fifo_size)(struct drm_i915_private *dev_priv, enum i9xx_plane_id i9xx_plane); int (*compute_pipe_wm)(struct intel_crtc_state *cstate); - int (*compute_intermediate_wm)(struct drm_device *dev, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *newstate); + int (*compute_intermediate_wm)(struct intel_crtc_state *newstate); void (*initial_watermarks)(struct intel_atomic_state *state, struct intel_crtc_state *cstate); void (*atomic_update_watermarks)(struct intel_atomic_state *state, struct intel_crtc_state *cstate); void (*optimize_watermarks)(struct intel_atomic_state *state, struct intel_crtc_state *cstate); - int (*compute_global_watermarks)(struct drm_atomic_state *state); + int (*compute_global_watermarks)(struct intel_atomic_state *state); void (*update_wm)(struct intel_crtc *crtc); int (*modeset_calc_cdclk)(struct drm_atomic_state *state); /* Returns the active state of the crtc, and if the crtc is active, @@ -320,8 +320,8 @@ struct drm_i915_display_funcs { /* display clock increase/decrease */ /* pll clock increase/decrease */ - void (*load_csc_matrix)(struct drm_crtc_state *crtc_state); - void (*load_luts)(struct drm_crtc_state *crtc_state); + void (*load_csc_matrix)(struct intel_crtc_state *crtc_state); + void (*load_luts)(struct intel_crtc_state *crtc_state); }; #define CSR_VERSION(major, minor) ((major) << 16 | (minor)) @@ -494,6 +494,7 @@ 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 +505,9 @@ struct i915_psr { u8 sink_sync_latency; ktime_t last_entry_attempt; ktime_t last_exit; + bool sink_not_reliable; + bool irq_aux_error; + u16 su_x_granularity; }; enum intel_pch { @@ -931,6 +935,8 @@ struct ddi_vbt_port_info { uint8_t supports_hdmi:1; uint8_t supports_dp:1; uint8_t supports_edp:1; + uint8_t supports_typec_usb:1; + uint8_t supports_tbt:1; uint8_t alternate_aux_channel; uint8_t alternate_ddc_pin; @@ -1093,9 +1099,6 @@ 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 +1191,6 @@ 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; @@ -1442,7 +1431,8 @@ struct drm_i915_private { struct kmem_cache *dependencies; struct kmem_cache *priorities; - const struct intel_device_info info; + const struct intel_device_info __info; /* Use INTEL_INFO() to access. */ + struct intel_runtime_info __runtime; /* Use RUNTIME_INFO() to access. */ struct intel_driver_caps caps; /** @@ -1651,7 +1641,7 @@ 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; @@ -1959,7 +1949,6 @@ struct drm_i915_private { struct list_head active_rings; struct list_head closed_vma; u32 active_requests; - u32 request_serial; /** * Is the GPU currently considered idle, or busy executing @@ -1995,6 +1984,8 @@ struct drm_i915_private { struct delayed_work idle_work; ktime_t last_init_time; + + struct i915_vma *scratch; } gt; /* perform PHY state sanity checks? */ @@ -2201,17 +2192,12 @@ static inline unsigned int i915_sg_segment_size(void) return size; } -static inline const struct intel_device_info * -intel_info(const struct drm_i915_private *dev_priv) -{ - return &dev_priv->info; -} - -#define INTEL_INFO(dev_priv) intel_info((dev_priv)) +#define INTEL_INFO(dev_priv) (&(dev_priv)->__info) +#define RUNTIME_INFO(dev_priv) (&(dev_priv)->__runtime) #define DRIVER_CAPS(dev_priv) (&(dev_priv)->caps) -#define INTEL_GEN(dev_priv) ((dev_priv)->info.gen) -#define INTEL_DEVID(dev_priv) ((dev_priv)->info.device_id) +#define INTEL_GEN(dev_priv) (INTEL_INFO(dev_priv)->gen) +#define INTEL_DEVID(dev_priv) (RUNTIME_INFO(dev_priv)->device_id) #define REVID_FOREVER 0xff #define INTEL_REVID(dev_priv) ((dev_priv)->drm.pdev->revision) @@ -2222,8 +2208,12 @@ intel_info(const struct drm_i915_private *dev_priv) GENMASK((e) - 1, (s) - 1)) /* Returns true if Gen is in inclusive range [Start, End] */ -#define IS_GEN(dev_priv, s, e) \ - (!!((dev_priv)->info.gen_mask & INTEL_GEN_MASK((s), (e)))) +#define IS_GEN_RANGE(dev_priv, s, e) \ + (!!(INTEL_INFO(dev_priv)->gen_mask & INTEL_GEN_MASK((s), (e)))) + +#define IS_GEN(dev_priv, n) \ + (BUILD_BUG_ON_ZERO(!__builtin_constant_p(n)) + \ + INTEL_INFO(dev_priv)->gen == (n)) /* * Return true if revision is in range [since,until] inclusive. @@ -2233,7 +2223,7 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_REVID(p, since, until) \ (INTEL_REVID(p) >= (since) && INTEL_REVID(p) <= (until)) -#define IS_PLATFORM(dev_priv, p) ((dev_priv)->info.platform_mask & BIT(p)) +#define IS_PLATFORM(dev_priv, p) (INTEL_INFO(dev_priv)->platform_mask & BIT(p)) #define IS_I830(dev_priv) IS_PLATFORM(dev_priv, INTEL_I830) #define IS_I845G(dev_priv) IS_PLATFORM(dev_priv, INTEL_I845G) @@ -2255,7 +2245,7 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_IRONLAKE_M(dev_priv) (INTEL_DEVID(dev_priv) == 0x0046) #define IS_IVYBRIDGE(dev_priv) IS_PLATFORM(dev_priv, INTEL_IVYBRIDGE) #define IS_IVB_GT1(dev_priv) (IS_IVYBRIDGE(dev_priv) && \ - (dev_priv)->info.gt == 1) + INTEL_INFO(dev_priv)->gt == 1) #define IS_VALLEYVIEW(dev_priv) IS_PLATFORM(dev_priv, INTEL_VALLEYVIEW) #define IS_CHERRYVIEW(dev_priv) IS_PLATFORM(dev_priv, INTEL_CHERRYVIEW) #define IS_HASWELL(dev_priv) IS_PLATFORM(dev_priv, INTEL_HASWELL) @@ -2267,7 +2257,7 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_COFFEELAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_COFFEELAKE) #define IS_CANNONLAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_CANNONLAKE) #define IS_ICELAKE(dev_priv) IS_PLATFORM(dev_priv, INTEL_ICELAKE) -#define IS_MOBILE(dev_priv) ((dev_priv)->info.is_mobile) +#define IS_MOBILE(dev_priv) (INTEL_INFO(dev_priv)->is_mobile) #define IS_HSW_EARLY_SDV(dev_priv) (IS_HASWELL(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0xFF00) == 0x0C00) #define IS_BDW_ULT(dev_priv) (IS_BROADWELL(dev_priv) && \ @@ -2278,11 +2268,13 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_BDW_ULX(dev_priv) (IS_BROADWELL(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0xf) == 0xe) #define IS_BDW_GT3(dev_priv) (IS_BROADWELL(dev_priv) && \ - (dev_priv)->info.gt == 3) + INTEL_INFO(dev_priv)->gt == 3) #define IS_HSW_ULT(dev_priv) (IS_HASWELL(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0xFF00) == 0x0A00) #define IS_HSW_GT3(dev_priv) (IS_HASWELL(dev_priv) && \ - (dev_priv)->info.gt == 3) + INTEL_INFO(dev_priv)->gt == 3) +#define IS_HSW_GT1(dev_priv) (IS_HASWELL(dev_priv) && \ + INTEL_INFO(dev_priv)->gt == 1) /* ULX machines are also considered ULT. */ #define IS_HSW_ULX(dev_priv) (INTEL_DEVID(dev_priv) == 0x0A0E || \ INTEL_DEVID(dev_priv) == 0x0A1E) @@ -2305,21 +2297,21 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_AML_ULX(dev_priv) (INTEL_DEVID(dev_priv) == 0x591C || \ INTEL_DEVID(dev_priv) == 0x87C0) #define IS_SKL_GT2(dev_priv) (IS_SKYLAKE(dev_priv) && \ - (dev_priv)->info.gt == 2) + INTEL_INFO(dev_priv)->gt == 2) #define IS_SKL_GT3(dev_priv) (IS_SKYLAKE(dev_priv) && \ - (dev_priv)->info.gt == 3) + INTEL_INFO(dev_priv)->gt == 3) #define IS_SKL_GT4(dev_priv) (IS_SKYLAKE(dev_priv) && \ - (dev_priv)->info.gt == 4) + INTEL_INFO(dev_priv)->gt == 4) #define IS_KBL_GT2(dev_priv) (IS_KABYLAKE(dev_priv) && \ - (dev_priv)->info.gt == 2) + INTEL_INFO(dev_priv)->gt == 2) #define IS_KBL_GT3(dev_priv) (IS_KABYLAKE(dev_priv) && \ - (dev_priv)->info.gt == 3) + INTEL_INFO(dev_priv)->gt == 3) #define IS_CFL_ULT(dev_priv) (IS_COFFEELAKE(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0x00F0) == 0x00A0) #define IS_CFL_GT2(dev_priv) (IS_COFFEELAKE(dev_priv) && \ - (dev_priv)->info.gt == 2) + INTEL_INFO(dev_priv)->gt == 2) #define IS_CFL_GT3(dev_priv) (IS_COFFEELAKE(dev_priv) && \ - (dev_priv)->info.gt == 3) + INTEL_INFO(dev_priv)->gt == 3) #define IS_CNL_WITH_PORT_F(dev_priv) (IS_CANNONLAKE(dev_priv) && \ (INTEL_DEVID(dev_priv) & 0x0004) == 0x0004) @@ -2376,26 +2368,9 @@ intel_info(const struct drm_i915_private *dev_priv) #define IS_ICL_REVID(p, since, until) \ (IS_ICELAKE(p) && IS_REVID(p, since, until)) -/* - * The genX designation typically refers to the render engine, so render - * capability related checks should use IS_GEN, while display and other checks - * have their own (e.g. HAS_PCH_SPLIT for ILK+ display, IS_foo for particular - * chips, etc.). - */ -#define IS_GEN2(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(1))) -#define IS_GEN3(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(2))) -#define IS_GEN4(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(3))) -#define IS_GEN5(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(4))) -#define IS_GEN6(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(5))) -#define IS_GEN7(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(6))) -#define IS_GEN8(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(7))) -#define IS_GEN9(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(8))) -#define IS_GEN10(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(9))) -#define IS_GEN11(dev_priv) (!!((dev_priv)->info.gen_mask & BIT(10))) - #define IS_LP(dev_priv) (INTEL_INFO(dev_priv)->is_lp) -#define IS_GEN9_LP(dev_priv) (IS_GEN9(dev_priv) && IS_LP(dev_priv)) -#define IS_GEN9_BC(dev_priv) (IS_GEN9(dev_priv) && !IS_LP(dev_priv)) +#define IS_GEN9_LP(dev_priv) (IS_GEN(dev_priv, 9) && IS_LP(dev_priv)) +#define IS_GEN9_BC(dev_priv) (IS_GEN(dev_priv, 9) && !IS_LP(dev_priv)) #define ENGINE_MASK(id) BIT(id) #define RENDER_RING ENGINE_MASK(RCS) @@ -2409,29 +2384,27 @@ intel_info(const struct drm_i915_private *dev_priv) #define ALL_ENGINES (~0) #define HAS_ENGINE(dev_priv, id) \ - (!!((dev_priv)->info.ring_mask & ENGINE_MASK(id))) + (!!(INTEL_INFO(dev_priv)->ring_mask & ENGINE_MASK(id))) #define HAS_BSD(dev_priv) HAS_ENGINE(dev_priv, VCS) #define HAS_BSD2(dev_priv) HAS_ENGINE(dev_priv, VCS2) #define HAS_BLT(dev_priv) HAS_ENGINE(dev_priv, BCS) #define HAS_VEBOX(dev_priv) HAS_ENGINE(dev_priv, VECS) -#define HAS_LEGACY_SEMAPHORES(dev_priv) IS_GEN7(dev_priv) - -#define HAS_LLC(dev_priv) ((dev_priv)->info.has_llc) -#define HAS_SNOOP(dev_priv) ((dev_priv)->info.has_snoop) +#define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc) +#define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop) #define HAS_EDRAM(dev_priv) (!!((dev_priv)->edram_cap & EDRAM_ENABLED)) #define HAS_WT(dev_priv) ((IS_HASWELL(dev_priv) || \ IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv)) -#define HWS_NEEDS_PHYSICAL(dev_priv) ((dev_priv)->info.hws_needs_physical) +#define HWS_NEEDS_PHYSICAL(dev_priv) (INTEL_INFO(dev_priv)->hws_needs_physical) #define HAS_LOGICAL_RING_CONTEXTS(dev_priv) \ - ((dev_priv)->info.has_logical_ring_contexts) + (INTEL_INFO(dev_priv)->has_logical_ring_contexts) #define HAS_LOGICAL_RING_ELSQ(dev_priv) \ - ((dev_priv)->info.has_logical_ring_elsq) + (INTEL_INFO(dev_priv)->has_logical_ring_elsq) #define HAS_LOGICAL_RING_PREEMPTION(dev_priv) \ - ((dev_priv)->info.has_logical_ring_preemption) + (INTEL_INFO(dev_priv)->has_logical_ring_preemption) #define HAS_EXECLISTS(dev_priv) HAS_LOGICAL_RING_CONTEXTS(dev_priv) @@ -2445,12 +2418,12 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_PAGE_SIZES(dev_priv, sizes) ({ \ GEM_BUG_ON((sizes) == 0); \ - ((sizes) & ~(dev_priv)->info.page_sizes) == 0; \ + ((sizes) & ~INTEL_INFO(dev_priv)->page_sizes) == 0; \ }) -#define HAS_OVERLAY(dev_priv) ((dev_priv)->info.has_overlay) +#define HAS_OVERLAY(dev_priv) (INTEL_INFO(dev_priv)->display.has_overlay) #define OVERLAY_NEEDS_PHYSICAL(dev_priv) \ - ((dev_priv)->info.overlay_needs_physical) + (INTEL_INFO(dev_priv)->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)) @@ -2468,42 +2441,42 @@ intel_info(const struct drm_i915_private *dev_priv) /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte * rows, which changed the alignment requirements and fence programming. */ -#define HAS_128_BYTE_Y_TILING(dev_priv) (!IS_GEN2(dev_priv) && \ +#define HAS_128_BYTE_Y_TILING(dev_priv) (!IS_GEN(dev_priv, 2) && \ !(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) (INTEL_INFO(dev_priv)->display.supports_tv) +#define I915_HAS_HOTPLUG(dev_priv) (INTEL_INFO(dev_priv)->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) (INTEL_INFO(dev_priv)->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) (INTEL_INFO(dev_priv)->display.has_dp_mst) -#define HAS_DDI(dev_priv) ((dev_priv)->info.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_DDI(dev_priv) (INTEL_INFO(dev_priv)->display.has_ddi) +#define HAS_FPGA_DBG_UNCLAIMED(dev_priv) (INTEL_INFO(dev_priv)->has_fpga_dbg) +#define HAS_PSR(dev_priv) (INTEL_INFO(dev_priv)->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_RC6(dev_priv) (INTEL_INFO(dev_priv)->has_rc6) +#define HAS_RC6p(dev_priv) (INTEL_INFO(dev_priv)->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) (INTEL_INFO(dev_priv)->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_RUNTIME_PM(dev_priv) (INTEL_INFO(dev_priv)->has_runtime_pm) +#define HAS_64BIT_RELOC(dev_priv) (INTEL_INFO(dev_priv)->has_64bit_reloc) -#define HAS_IPC(dev_priv) ((dev_priv)->info.has_ipc) +#define HAS_IPC(dev_priv) (INTEL_INFO(dev_priv)->display.has_ipc) /* * For now, anything with a GuC requires uCode loading, and then supports * command submission once loaded. But these are logically independent * properties, so we have separate macros to test them. */ -#define HAS_GUC(dev_priv) ((dev_priv)->info.has_guc) -#define HAS_GUC_CT(dev_priv) ((dev_priv)->info.has_guc_ct) +#define HAS_GUC(dev_priv) (INTEL_INFO(dev_priv)->has_guc) +#define HAS_GUC_CT(dev_priv) (INTEL_INFO(dev_priv)->has_guc_ct) #define HAS_GUC_UCODE(dev_priv) (HAS_GUC(dev_priv)) #define HAS_GUC_SCHED(dev_priv) (HAS_GUC(dev_priv)) @@ -2512,11 +2485,11 @@ intel_info(const struct drm_i915_private *dev_priv) #define HAS_HUC_UCODE(dev_priv) (HAS_GUC(dev_priv)) /* Having a GuC is not the same as using a GuC */ -#define USES_GUC(dev_priv) intel_uc_is_using_guc() -#define USES_GUC_SUBMISSION(dev_priv) intel_uc_is_using_guc_submission() -#define USES_HUC(dev_priv) intel_uc_is_using_huc() +#define USES_GUC(dev_priv) intel_uc_is_using_guc(dev_priv) +#define USES_GUC_SUBMISSION(dev_priv) intel_uc_is_using_guc_submission(dev_priv) +#define USES_HUC(dev_priv) intel_uc_is_using_huc(dev_priv) -#define HAS_POOLED_EU(dev_priv) ((dev_priv)->info.has_pooled_eu) +#define HAS_POOLED_EU(dev_priv) (INTEL_INFO(dev_priv)->has_pooled_eu) #define INTEL_PCH_DEVICE_ID_MASK 0xff80 #define INTEL_PCH_IBX_DEVICE_ID_TYPE 0x3b00 @@ -2556,18 +2529,20 @@ 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) (INTEL_INFO(dev_priv)->display.has_gmch_display) #define HAS_LSPCON(dev_priv) (INTEL_GEN(dev_priv) >= 9) /* DPF == dynamic parity feature */ -#define HAS_L3_DPF(dev_priv) ((dev_priv)->info.has_l3_dpf) +#define HAS_L3_DPF(dev_priv) (INTEL_INFO(dev_priv)->has_l3_dpf) #define NUM_L3_SLICES(dev_priv) (IS_HSW_GT3(dev_priv) ? \ 2 : HAS_L3_DPF(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) @@ -3321,7 +3296,7 @@ static inline void intel_unregister_dsm_handler(void) { return; } static inline struct intel_device_info * mkwrite_device_info(struct drm_i915_private *dev_priv) { - return (struct intel_device_info *)&dev_priv->info; + return (struct intel_device_info *)INTEL_INFO(dev_priv); } /* modesetting */ @@ -3340,6 +3315,9 @@ 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); @@ -3604,90 +3582,6 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms) } } -static inline bool -__i915_request_irq_complete(const struct i915_request *rq) -{ - struct intel_engine_cs *engine = rq->engine; - u32 seqno; - - /* Note that the engine may have wrapped around the seqno, and - * so our request->global_seqno will be ahead of the hardware, - * even though it completed the request before wrapping. We catch - * this by kicking all the waiters before resetting the seqno - * in hardware, and also signal the fence. - */ - if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) - return true; - - /* The request was dequeued before we were awoken. We check after - * inspecting the hw to confirm that this was the same request - * that generated the HWS update. The memory barriers within - * the request execution are sufficient to ensure that a check - * after reading the value from hw matches this request. - */ - seqno = i915_request_global_seqno(rq); - if (!seqno) - return false; - - /* Before we do the heavier coherent read of the seqno, - * check the value (hopefully) in the CPU cacheline. - */ - if (__i915_request_completed(rq, seqno)) - return true; - - /* Ensure our read of the seqno is coherent so that we - * do not "miss an interrupt" (i.e. if this is the last - * request and the seqno write from the GPU is not visible - * by the time the interrupt fires, we will see that the - * request is incomplete and go back to sleep awaiting - * another interrupt that will never come.) - * - * Strictly, we only need to do this once after an interrupt, - * but it is easier and safer to do it every time the waiter - * is woken. - */ - if (engine->irq_seqno_barrier && - test_and_clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted)) { - struct intel_breadcrumbs *b = &engine->breadcrumbs; - - /* The ordering of irq_posted versus applying the barrier - * is crucial. The clearing of the current irq_posted must - * be visible before we perform the barrier operation, - * such that if a subsequent interrupt arrives, irq_posted - * is reasserted and our task rewoken (which causes us to - * do another __i915_request_irq_complete() immediately - * and reapply the barrier). Conversely, if the clear - * occurs after the barrier, then an interrupt that arrived - * whilst we waited on the barrier would not trigger a - * barrier on the next pass, and the read may not see the - * seqno update. - */ - engine->irq_seqno_barrier(engine); - - /* If we consume the irq, but we are no longer the bottom-half, - * the real bottom-half may not have serialised their own - * seqno check with the irq-barrier (i.e. may have inspected - * the seqno before we believe it coherent since they see - * irq_posted == false but we are still running). - */ - spin_lock_irq(&b->irq_lock); - if (b->irq_wait && b->irq_wait->tsk != current) - /* Note that if the bottom-half is changed as we - * are sending the wake-up, the new bottom-half will - * be woken by whomever made the change. We only have - * to worry about when we steal the irq-posted for - * ourself. - */ - wake_up_process(b->irq_wait->tsk); - spin_unlock_irq(&b->irq_lock); - - if (__i915_request_completed(rq, seqno)) - return true; - } - - return false; -} - void i915_memcpy_init_early(struct drm_i915_private *dev_priv); bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len); @@ -3720,4 +3614,9 @@ 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..25534d17496f 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -859,58 +859,6 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains) obj->write_domain = 0; } -static inline int -__copy_to_user_swizzled(char __user *cpu_vaddr, - const char *gpu_vaddr, int gpu_offset, - int length) -{ - int ret, cpu_offset = 0; - - while (length > 0) { - int cacheline_end = ALIGN(gpu_offset + 1, 64); - int this_length = min(cacheline_end - gpu_offset, length); - int swizzled_gpu_offset = gpu_offset ^ 64; - - ret = __copy_to_user(cpu_vaddr + cpu_offset, - gpu_vaddr + swizzled_gpu_offset, - this_length); - if (ret) - return ret + length; - - cpu_offset += this_length; - gpu_offset += this_length; - length -= this_length; - } - - return 0; -} - -static inline int -__copy_from_user_swizzled(char *gpu_vaddr, int gpu_offset, - const char __user *cpu_vaddr, - int length) -{ - int ret, cpu_offset = 0; - - while (length > 0) { - int cacheline_end = ALIGN(gpu_offset + 1, 64); - int this_length = min(cacheline_end - gpu_offset, length); - int swizzled_gpu_offset = gpu_offset ^ 64; - - ret = __copy_from_user(gpu_vaddr + swizzled_gpu_offset, - cpu_vaddr + cpu_offset, - this_length); - if (ret) - return ret + length; - - cpu_offset += this_length; - gpu_offset += this_length; - length -= this_length; - } - - return 0; -} - /* * Pins the specified object's pages and synchronizes the object with * GPU accesses. Sets needs_clflush to non-zero if the caller should @@ -1030,72 +978,23 @@ err_unpin: return ret; } -static void -shmem_clflush_swizzled_range(char *addr, unsigned long length, - bool swizzled) -{ - if (unlikely(swizzled)) { - unsigned long start = (unsigned long) addr; - unsigned long end = (unsigned long) addr + length; - - /* For swizzling simply ensure that we always flush both - * channels. Lame, but simple and it works. Swizzled - * pwrite/pread is far from a hotpath - current userspace - * doesn't use it at all. */ - start = round_down(start, 128); - end = round_up(end, 128); - - drm_clflush_virt_range((void *)start, end - start); - } else { - drm_clflush_virt_range(addr, length); - } - -} - -/* Only difference to the fast-path function is that this can handle bit17 - * and uses non-atomic copy and kmap functions. */ static int -shmem_pread_slow(struct page *page, int offset, int length, - char __user *user_data, - bool page_do_bit17_swizzling, bool needs_clflush) +shmem_pread(struct page *page, int offset, int len, char __user *user_data, + bool needs_clflush) { char *vaddr; int ret; vaddr = kmap(page); - if (needs_clflush) - shmem_clflush_swizzled_range(vaddr + offset, length, - page_do_bit17_swizzling); - - if (page_do_bit17_swizzling) - ret = __copy_to_user_swizzled(user_data, vaddr, offset, length); - else - ret = __copy_to_user(user_data, vaddr + offset, length); - kunmap(page); - - return ret ? - EFAULT : 0; -} -static int -shmem_pread(struct page *page, int offset, int length, char __user *user_data, - bool page_do_bit17_swizzling, bool needs_clflush) -{ - int ret; + if (needs_clflush) + drm_clflush_virt_range(vaddr + offset, len); - ret = -ENODEV; - if (!page_do_bit17_swizzling) { - char *vaddr = kmap_atomic(page); + ret = __copy_to_user(user_data, vaddr + offset, len); - if (needs_clflush) - drm_clflush_virt_range(vaddr + offset, length); - ret = __copy_to_user_inatomic(user_data, vaddr + offset, length); - kunmap_atomic(vaddr); - } - if (ret == 0) - return 0; + kunmap(page); - return shmem_pread_slow(page, offset, length, user_data, - page_do_bit17_swizzling, needs_clflush); + return ret ? -EFAULT : 0; } static int @@ -1104,15 +1003,10 @@ i915_gem_shmem_pread(struct drm_i915_gem_object *obj, { char __user *user_data; u64 remain; - unsigned int obj_do_bit17_swizzling; unsigned int needs_clflush; unsigned int idx, offset; int ret; - obj_do_bit17_swizzling = 0; - if (i915_gem_object_needs_bit17_swizzle(obj)) - obj_do_bit17_swizzling = BIT(17); - ret = mutex_lock_interruptible(&obj->base.dev->struct_mutex); if (ret) return ret; @@ -1130,7 +1024,6 @@ i915_gem_shmem_pread(struct drm_i915_gem_object *obj, unsigned int length = min_t(u64, remain, PAGE_SIZE - offset); ret = shmem_pread(page, offset, length, user_data, - page_to_phys(page) & obj_do_bit17_swizzling, needs_clflush); if (ret) break; @@ -1471,33 +1364,6 @@ out_unlock: return ret; } -static int -shmem_pwrite_slow(struct page *page, int offset, int length, - char __user *user_data, - bool page_do_bit17_swizzling, - bool needs_clflush_before, - bool needs_clflush_after) -{ - char *vaddr; - int ret; - - vaddr = kmap(page); - if (unlikely(needs_clflush_before || page_do_bit17_swizzling)) - shmem_clflush_swizzled_range(vaddr + offset, length, - page_do_bit17_swizzling); - if (page_do_bit17_swizzling) - ret = __copy_from_user_swizzled(vaddr, offset, user_data, - length); - else - ret = __copy_from_user(vaddr + offset, user_data, length); - if (needs_clflush_after) - shmem_clflush_swizzled_range(vaddr + offset, length, - page_do_bit17_swizzling); - kunmap(page); - - return ret ? -EFAULT : 0; -} - /* Per-page copy function for the shmem pwrite fastpath. * Flushes invalid cachelines before writing to the target if * needs_clflush_before is set and flushes out any written cachelines after @@ -1505,31 +1371,24 @@ shmem_pwrite_slow(struct page *page, int offset, int length, */ static int shmem_pwrite(struct page *page, int offset, int len, char __user *user_data, - bool page_do_bit17_swizzling, bool needs_clflush_before, bool needs_clflush_after) { + char *vaddr; int ret; - ret = -ENODEV; - if (!page_do_bit17_swizzling) { - char *vaddr = kmap_atomic(page); + vaddr = kmap(page); - if (needs_clflush_before) - drm_clflush_virt_range(vaddr + offset, len); - ret = __copy_from_user_inatomic(vaddr + offset, user_data, len); - if (needs_clflush_after) - drm_clflush_virt_range(vaddr + offset, len); + if (needs_clflush_before) + drm_clflush_virt_range(vaddr + offset, len); - kunmap_atomic(vaddr); - } - if (ret == 0) - return ret; + ret = __copy_from_user(vaddr + offset, user_data, len); + if (!ret && needs_clflush_after) + drm_clflush_virt_range(vaddr + offset, len); + + kunmap(page); - return shmem_pwrite_slow(page, offset, len, user_data, - page_do_bit17_swizzling, - needs_clflush_before, - needs_clflush_after); + return ret ? -EFAULT : 0; } static int @@ -1539,7 +1398,6 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj, struct drm_i915_private *i915 = to_i915(obj->base.dev); void __user *user_data; u64 remain; - unsigned int obj_do_bit17_swizzling; unsigned int partial_cacheline_write; unsigned int needs_clflush; unsigned int offset, idx; @@ -1554,10 +1412,6 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj, if (ret) return ret; - obj_do_bit17_swizzling = 0; - if (i915_gem_object_needs_bit17_swizzle(obj)) - obj_do_bit17_swizzling = BIT(17); - /* If we don't overwrite a cacheline completely we need to be * careful to have up-to-date data by first clflushing. Don't * overcomplicate things and flush the entire patch. @@ -1574,7 +1428,6 @@ i915_gem_shmem_pwrite(struct drm_i915_gem_object *obj, unsigned int length = min_t(u64, remain, PAGE_SIZE - offset); ret = shmem_pwrite(page, offset, length, user_data, - page_to_phys(page) & obj_do_bit17_swizzling, (offset | length) & partial_cacheline_write, needs_clflush & CLFLUSH_AFTER); if (ret) @@ -3230,13 +3083,6 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine, struct i915_request *request, bool stalled) { - /* - * Make sure this write is visible before we re-enable the interrupt - * handlers on another CPU, as tasklet_enable() resolves to just - * a compiler barrier which is insufficient for our purpose here. - */ - smp_store_mb(engine->irq_posted, 0); - if (request) request = i915_gem_reset_request(engine, request, stalled); @@ -3309,16 +3155,6 @@ 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", @@ -3328,7 +3164,7 @@ static void nop_complete_submit_request(struct i915_request *request) spin_lock_irqsave(&request->engine->timeline.lock, flags); __i915_request_submit(request); - intel_engine_init_global_seqno(request->engine, request->global_seqno); + intel_engine_write_global_seqno(request->engine, request->global_seqno); spin_unlock_irqrestore(&request->engine->timeline.lock, flags); } @@ -3354,57 +3190,33 @@ 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. + * either this call here to intel_engine_write_global_seqno, or the one + * 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: @@ -3421,6 +3233,9 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915) if (!test_bit(I915_WEDGED, &i915->gpu_error.flags)) return true; + if (!i915->gt.scratch) /* Never full initialised, recovery impossible */ + return false; + GEM_TRACE("start\n"); /* @@ -3459,8 +3274,7 @@ bool i915_gem_unset_wedged(struct drm_i915_private *i915) i915_retire_requests(i915); GEM_BUG_ON(i915->gt.active_requests); - if (!intel_gpu_reset(i915, ALL_ENGINES)) - intel_engines_sanitize(i915); + intel_engines_sanitize(i915, false); /* * Undo nop_submit_request. We prevent all new i915 requests from @@ -5064,8 +4878,6 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj) void i915_gem_sanitize(struct drm_i915_private *i915) { - int err; - GEM_TRACE("\n"); mutex_lock(&i915->drm.struct_mutex); @@ -5090,11 +4902,7 @@ void i915_gem_sanitize(struct drm_i915_private *i915) * it may impact the display and we are uncertain about the stability * of the reset, so this could be applied to even earlier gen. */ - err = -ENODEV; - if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915)) - err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES)); - if (!err) - intel_engines_sanitize(i915); + intel_engines_sanitize(i915, false); intel_uncore_forcewake_put(i915, FORCEWAKE_ALL); intel_runtime_pm_put(i915); @@ -5260,15 +5068,15 @@ void i915_gem_init_swizzling(struct drm_i915_private *dev_priv) I915_WRITE(DISP_ARB_CTL, I915_READ(DISP_ARB_CTL) | DISP_TILE_SURFACE_SWIZZLING); - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) return; I915_WRITE(TILECTL, I915_READ(TILECTL) | TILECTL_SWZCTL); - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) I915_WRITE(ARB_MODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_SNB)); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) I915_WRITE(ARB_MODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_IVB)); - else if (IS_GEN8(dev_priv)) + else if (IS_GEN(dev_priv, 8)) I915_WRITE(GAMTARBMODE, _MASKED_BIT_ENABLE(ARB_MODE_SWIZZLE_BDW)); else BUG(); @@ -5290,10 +5098,10 @@ static void init_unused_rings(struct drm_i915_private *dev_priv) init_unused_ring(dev_priv, SRB1_BASE); init_unused_ring(dev_priv, SRB2_BASE); init_unused_ring(dev_priv, SRB3_BASE); - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { init_unused_ring(dev_priv, SRB0_BASE); init_unused_ring(dev_priv, SRB1_BASE); - } else if (IS_GEN3(dev_priv)) { + } else if (IS_GEN(dev_priv, 3)) { init_unused_ring(dev_priv, PRB1_BASE); init_unused_ring(dev_priv, PRB2_BASE); } @@ -5334,7 +5142,10 @@ 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 +5340,44 @@ 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 +5424,19 @@ 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_GEN(dev_priv, 2) ? 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 +5509,8 @@ 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 +5562,11 @@ 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..014152e2bc68 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -311,7 +311,7 @@ static u32 default_desc_template(const struct drm_i915_private *i915, address_mode = INTEL_LEGACY_64B_CONTEXT; desc |= address_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - if (IS_GEN8(i915)) + if (IS_GEN(i915, 8)) desc |= GEN8_CTX_L3LLC_COHERENT; /* TODO: WaDisableLiteRestore when we start using semaphore @@ -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_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 7b3ae2333dbf..844bd5ad87bc 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1268,7 +1268,7 @@ relocate_entry(struct i915_vma *vma, else if (gen >= 4) len = 4; else - len = 6; + len = 3; batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) @@ -1309,11 +1309,6 @@ relocate_entry(struct i915_vma *vma, *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; *batch++ = addr; *batch++ = target_offset; - - /* And again for good measure (blb/pnv) */ - *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; - *batch++ = addr; - *batch++ = target_offset; } goto out; @@ -1385,7 +1380,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, * batchbuffers. */ if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION && - IS_GEN6(eb->i915)) { + IS_GEN(eb->i915, 6)) { err = i915_vma_bind(target, target->obj->cache_level, PIN_GLOBAL); if (WARN_ONCE(err, @@ -1898,7 +1893,7 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq) u32 *cs; int i; - if (!IS_GEN7(rq->i915) || rq->engine->id != RCS) { + if (!IS_GEN(rq->i915, 7) || rq->engine->id != RCS) { DRM_DEBUG("sol reset is gen7/rcs only\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c index d548ac05ccd7..24df2e2a8fc1 100644 --- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c +++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c @@ -193,9 +193,9 @@ static void fence_write(struct drm_i915_fence_reg *fence, * and explicitly managed for internal users. */ - if (IS_GEN2(fence->i915)) + if (IS_GEN(fence->i915, 2)) i830_write_fence_reg(fence, vma); - else if (IS_GEN3(fence->i915)) + else if (IS_GEN(fence->i915, 3)) i915_write_fence_reg(fence, vma); else i965_write_fence_reg(fence, vma); @@ -596,13 +596,13 @@ i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv) swizzle_y = I915_BIT_6_SWIZZLE_NONE; } } - } else if (IS_GEN5(dev_priv)) { + } else if (IS_GEN(dev_priv, 5)) { /* On Ironlake whatever DRAM config, GPU always do * same swizzling setup. */ swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { /* As far as we know, the 865 doesn't have these bit 6 * swizzling issues. */ @@ -647,7 +647,7 @@ i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv) } /* check for L-shaped memory aka modified enhanced addressing */ - if (IS_GEN4(dev_priv) && + if (IS_GEN(dev_priv, 4) && !(I915_READ(DCC2) & DCC2_MODIFIED_ENHANCED_DISABLE)) { swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN; swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index add1fe7aeb93..d4c5973ea33d 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1423,8 +1423,6 @@ static int gen8_ppgtt_alloc_pdp(struct i915_address_space *vm, gen8_initialize_pd(vm, pd); gen8_ppgtt_set_pdpe(vm, pdp, pd, pdpe); GEM_BUG_ON(pdp->used_pdpes > i915_pdpes_per_pdp(vm)); - - mark_tlbs_dirty(i915_vm_to_ppgtt(vm)); } ret = gen8_ppgtt_alloc_pd(vm, pd, start, length); @@ -1490,84 +1488,6 @@ unwind: return -ENOMEM; } -static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt, - struct i915_page_directory_pointer *pdp, - u64 start, u64 length, - gen8_pte_t scratch_pte, - struct seq_file *m) -{ - struct i915_address_space *vm = &ppgtt->vm; - struct i915_page_directory *pd; - u32 pdpe; - - gen8_for_each_pdpe(pd, pdp, start, length, pdpe) { - struct i915_page_table *pt; - u64 pd_len = length; - u64 pd_start = start; - u32 pde; - - if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd) - continue; - - seq_printf(m, "\tPDPE #%d\n", pdpe); - gen8_for_each_pde(pt, pd, pd_start, pd_len, pde) { - u32 pte; - gen8_pte_t *pt_vaddr; - - if (pd->page_table[pde] == ppgtt->vm.scratch_pt) - continue; - - pt_vaddr = kmap_atomic_px(pt); - for (pte = 0; pte < GEN8_PTES; pte += 4) { - u64 va = (pdpe << GEN8_PDPE_SHIFT | - pde << GEN8_PDE_SHIFT | - pte << GEN8_PTE_SHIFT); - int i; - bool found = false; - - for (i = 0; i < 4; i++) - if (pt_vaddr[pte + i] != scratch_pte) - found = true; - if (!found) - continue; - - seq_printf(m, "\t\t0x%llx [%03d,%03d,%04d]: =", va, pdpe, pde, pte); - for (i = 0; i < 4; i++) { - if (pt_vaddr[pte + i] != scratch_pte) - seq_printf(m, " %llx", pt_vaddr[pte + i]); - else - seq_puts(m, " SCRATCH "); - } - seq_puts(m, "\n"); - } - kunmap_atomic(pt_vaddr); - } - } -} - -static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m) -{ - struct i915_address_space *vm = &ppgtt->vm; - const gen8_pte_t scratch_pte = vm->scratch_pte; - u64 start = 0, length = ppgtt->vm.total; - - if (use_4lvl(vm)) { - u64 pml4e; - struct i915_pml4 *pml4 = &ppgtt->pml4; - struct i915_page_directory_pointer *pdp; - - gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) { - if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp) - continue; - - seq_printf(m, " PML4E #%llu\n", pml4e); - gen8_dump_pdp(ppgtt, pdp, start, length, scratch_pte, m); - } - } else { - gen8_dump_pdp(ppgtt, &ppgtt->pdp, start, length, scratch_pte, m); - } -} - static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt) { struct i915_address_space *vm = &ppgtt->vm; @@ -1672,7 +1592,6 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915) gen8_ppgtt_notify_vgt(ppgtt, true); ppgtt->vm.cleanup = gen8_ppgtt_cleanup; - ppgtt->debug_dump = gen8_dump_ppgtt; ppgtt->vm.vma_ops.bind_vma = ppgtt_bind_vma; ppgtt->vm.vma_ops.unbind_vma = ppgtt_unbind_vma; @@ -1688,60 +1607,6 @@ err_free: return ERR_PTR(err); } -static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m) -{ - struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base); - const gen6_pte_t scratch_pte = base->vm.scratch_pte; - struct i915_page_table *pt; - u32 pte, pde; - - gen6_for_all_pdes(pt, &base->pd, pde) { - gen6_pte_t *vaddr; - - if (pt == base->vm.scratch_pt) - continue; - - if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND)) { - u32 expected = - GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | - GEN6_PDE_VALID; - u32 pd_entry = readl(ppgtt->pd_addr + pde); - - if (pd_entry != expected) - seq_printf(m, - "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n", - pde, - pd_entry, - expected); - - seq_printf(m, "\tPDE: %x\n", pd_entry); - } - - vaddr = kmap_atomic_px(base->pd.page_table[pde]); - for (pte = 0; pte < GEN6_PTES; pte += 4) { - int i; - - for (i = 0; i < 4; i++) - if (vaddr[pte + i] != scratch_pte) - break; - if (i == 4) - continue; - - seq_printf(m, "\t\t(%03d, %04d) %08llx: ", - pde, pte, - (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE); - for (i = 0; i < 4; i++) { - if (vaddr[pte + i] != scratch_pte) - seq_printf(m, " %08x", vaddr[pte + i]); - else - seq_puts(m, " SCRATCH"); - } - seq_puts(m, "\n"); - } - kunmap_atomic(vaddr); - } -} - /* Write pde (index) from the page directory @pd to the page table @pt */ static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt, const unsigned int pde, @@ -2075,6 +1940,7 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size) int gen6_ppgtt_pin(struct i915_hw_ppgtt *base) { struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base); + int err; /* * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt @@ -2090,9 +1956,17 @@ int gen6_ppgtt_pin(struct i915_hw_ppgtt *base) * allocator works in address space sizes, so it's multiplied by page * size. We allocate at the top of the GTT to avoid fragmentation. */ - return i915_vma_pin(ppgtt->vma, - 0, GEN6_PD_ALIGN, - PIN_GLOBAL | PIN_HIGH); + err = i915_vma_pin(ppgtt->vma, + 0, GEN6_PD_ALIGN, + PIN_GLOBAL | PIN_HIGH); + if (err) + goto unpin; + + return 0; + +unpin: + ppgtt->pin_count = 0; + return err; } void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base) @@ -2129,7 +2003,6 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915) ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range; ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries; ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup; - ppgtt->base.debug_dump = gen6_dump_ppgtt; ppgtt->base.vm.vma_ops.bind_vma = ppgtt_bind_vma; ppgtt->base.vm.vma_ops.unbind_vma = ppgtt_unbind_vma; @@ -2195,9 +2068,9 @@ int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv) { gtt_write_workarounds(dev_priv); - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) gen6_ppgtt_enable(dev_priv); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) gen7_ppgtt_enable(dev_priv); return 0; @@ -2279,7 +2152,7 @@ static bool needs_idle_maps(struct drm_i915_private *dev_priv) /* Query intel_iommu to see if we need the workaround. Presumably that * was loaded first. */ - return IS_GEN5(dev_priv) && IS_MOBILE(dev_priv) && intel_vtd_active(); + return IS_GEN(dev_priv, 5) && IS_MOBILE(dev_priv) && intel_vtd_active(); } static void gen6_check_faults(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 4874da09a3c4..e2360f16427a 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -413,8 +413,6 @@ struct i915_hw_ppgtt { struct i915_page_directory_pointer pdp; /* GEN8+ */ struct i915_page_directory pd; /* GEN6-7 */ }; - - void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m); }; struct gen6_hw_ppgtt { diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index f29a7ff7c362..2f756a97689a 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -102,7 +102,7 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv, resource_size_t ggtt_start; ggtt_start = I915_READ(PGTBL_CTL); - if (IS_GEN4(dev_priv)) + if (IS_GEN(dev_priv, 4)) ggtt_start = (ggtt_start & PGTBL_ADDRESS_LO_MASK) | (ggtt_start & PGTBL_ADDRESS_HI_MASK) << 28; else @@ -156,7 +156,7 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv, * GEN3 firmware likes to smash pci bridges into the stolen * range. Apparently this works. */ - if (r == NULL && !IS_GEN3(dev_priv)) { + if (r == NULL && !IS_GEN(dev_priv, 3)) { DRM_ERROR("conflict detected with stolen region: %pR\n", dsm); @@ -194,7 +194,8 @@ static void g4x_get_stolen_reserved(struct drm_i915_private *dev_priv, * Whether ILK really reuses the ELK register for this is unclear. * Let's see if we catch anyone with this supposedly enabled on ILK. */ - WARN(IS_GEN5(dev_priv), "ILK stolen reserved found? 0x%08x\n", reg_val); + WARN(IS_GEN(dev_priv, 5), "ILK stolen reserved found? 0x%08x\n", + reg_val); if (!(reg_val & G4X_STOLEN_RESERVED_ADDR2_MASK)) return; diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index d9dc9df523b5..39319ff1679c 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -87,7 +87,7 @@ u32 i915_gem_fence_size(struct drm_i915_private *i915, } /* Previous chips need a power-of-two fence region when tiling */ - if (IS_GEN3(i915)) + if (IS_GEN(i915, 3)) ggtt_size = 1024*1024; else ggtt_size = 512*1024; @@ -162,7 +162,7 @@ i915_tiling_ok(struct drm_i915_gem_object *obj, return false; } - if (IS_GEN2(i915) || + if (IS_GEN(i915, 2) || (tiling == I915_TILING_Y && HAS_128_BYTE_Y_TILING(i915))) tile_width = 128; else diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 8123bf0e4807..5533a741abeb 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; + + if (e->bytes) { + __sg_set_buf(e->cur++, e->buf, e->bytes, e->iter); + e->iter += e->bytes; + e->buf = NULL; + e->bytes = 0; } - return true; -} + if (e->cur == e->end) { + struct scatterlist *sgl; -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->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? */ @@ -591,13 +594,14 @@ static void print_error_obj(struct drm_i915_error_state_buf *m, static void err_print_capabilities(struct drm_i915_error_state_buf *m, const struct intel_device_info *info, + const struct intel_runtime_info *runtime, const struct intel_driver_caps *caps) { struct drm_printer p = i915_error_printer(m); intel_device_info_dump_flags(info, &p); intel_driver_caps_print(caps, &p); - intel_device_info_dump_topology(&info->sseu, &p); + intel_device_info_dump_topology(&runtime->sseu, &p); } static void err_print_params(struct drm_i915_error_state_buf *m, @@ -635,25 +639,35 @@ 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); - err_printf(m, "Kernel: %s\n", init_utsname()->release); + err_printf(m, "Kernel: %s %s\n", + init_utsname()->release, + init_utsname()->machine); ts = ktime_to_timespec64(error->time); err_printf(m, "Time: %lld s %ld us\n", (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC); @@ -683,12 +697,12 @@ 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 +722,23 @@ 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_GEN(m->i915, 7)) err_printf(m, "ERR_INT: 0x%08x\n", error->err_int); for (i = 0; i < ARRAY_SIZE(error->engine); i++) { @@ -745,7 +760,7 @@ 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 +778,7 @@ 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 +790,16 @@ 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 +809,10 @@ 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 +822,22 @@ 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); } @@ -832,46 +847,111 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m, if (error->display) intel_display_print_error_state(m, error->display); - err_print_capabilities(m, &error->device_info, &error->driver_caps); + err_print_capabilities(m, &error->device_info, &error->runtime_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->bytes == 0 && m->err) - return m->err; + 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 (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)); + } - ebuf->start = pos; + len = sg->length; + if (pos + len <= off) { + pos += len; + continue; + } - return 0; + start = sg->offset; + if (pos < off) { + GEM_BUG_ON(off - pos > len); + len -= off - pos; + start += off - pos; + pos = off; + } + + 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) @@ -887,17 +967,10 @@ static void i915_error_object_free(struct drm_i915_error_object *obj) kfree(obj); } -static __always_inline void free_param(const char *type, void *x) -{ - if (!__builtin_strcmp(type, "char *")) - kfree(*(void **)x); -} static void cleanup_params(struct i915_gpu_state *error) { -#define FREE(T, x, ...) free_param(#T, &error->params.x); - I915_PARAMS_FOR_EACH(FREE); -#undef FREE + i915_params_free(&error->params); } static void cleanup_uc_state(struct i915_gpu_state *error) @@ -944,6 +1017,7 @@ void __i915_gpu_state_free(struct kref *error_ref) cleanup_params(error); cleanup_uc_state(error); + err_free_sgl(error->sgl); kfree(error); } @@ -1237,7 +1311,7 @@ static void error_record_engine_registers(struct i915_gpu_state *error, if (!HWS_NEEDS_PHYSICAL(dev_priv)) { i915_reg_t mmio; - if (IS_GEN7(dev_priv)) { + if (IS_GEN(dev_priv, 7)) { switch (engine->id) { default: case RCS: @@ -1253,7 +1327,7 @@ static void error_record_engine_registers(struct i915_gpu_state *error, mmio = VEBOX_HWS_PGA_GEN7; break; } - } else if (IS_GEN6(engine->i915)) { + } else if (IS_GEN(engine->i915, 6)) { mmio = RING_HWS_PGA_GEN6(engine->mmio_base); } else { /* XXX: gen8 returns to sanity */ @@ -1275,10 +1349,10 @@ static void error_record_engine_registers(struct i915_gpu_state *error, ee->vm_info.gfx_mode = I915_READ(RING_MODE_GEN7(engine)); - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) ee->vm_info.pp_dir_base = I915_READ(RING_PP_DIR_BASE_READ(engine)); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) ee->vm_info.pp_dir_base = I915_READ(RING_PP_DIR_BASE(engine)); else if (INTEL_GEN(dev_priv) >= 8) @@ -1494,7 +1568,7 @@ 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 = @@ -1648,7 +1722,7 @@ static void capture_reg_state(struct i915_gpu_state *error) error->forcewake = I915_READ_FW(FORCEWAKE_VLV); } - if (IS_GEN7(dev_priv)) + if (IS_GEN(dev_priv, 7)) error->err_int = I915_READ(GEN7_ERR_INT); if (INTEL_GEN(dev_priv) >= 8) { @@ -1656,7 +1730,7 @@ static void capture_reg_state(struct i915_gpu_state *error) error->fault_data1 = I915_READ(GEN8_FAULT_TLB_DATA1); } - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { error->forcewake = I915_READ_FW(FORCEWAKE); error->gab_ctl = I915_READ(GAB_CTL); error->gfx_mode = I915_READ(GFX_MODE); @@ -1676,7 +1750,7 @@ static void capture_reg_state(struct i915_gpu_state *error) error->ccid = I915_READ(CCID); /* 3: Feature specific registers */ - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) { + if (IS_GEN_RANGE(dev_priv, 6, 7)) { error->gam_ecochk = I915_READ(GAM_ECOCHK); error->gac_eco = I915_READ(GAC_ECO_BITS); } @@ -1700,7 +1774,7 @@ static void capture_reg_state(struct i915_gpu_state *error) error->ier = I915_READ(DEIER); error->gtier[0] = I915_READ(GTIER); error->ngtier = 1; - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { error->ier = I915_READ16(IER); } else if (!IS_VALLEYVIEW(dev_priv)) { error->ier = I915_READ(IER); @@ -1754,21 +1828,15 @@ static void capture_gen_state(struct i915_gpu_state *error) memcpy(&error->device_info, INTEL_INFO(i915), sizeof(error->device_info)); + memcpy(&error->runtime_info, + RUNTIME_INFO(i915), + sizeof(error->runtime_info)); error->driver_caps = i915->caps; } -static __always_inline void dup_param(const char *type, void *x) -{ - if (!__builtin_strcmp(type, "char *")) - *(void **)x = kstrdup(*(void **)x, GFP_ATOMIC); -} - static void capture_params(struct i915_gpu_state *error) { - error->params = i915_modparams; -#define DUP(T, x, ...) dup_param(#T, &error->params.x); - I915_PARAMS_FOR_EACH(DUP); -#undef DUP + i915_params_copy(&error->params, &i915_modparams); } static unsigned long capture_find_epoch(const struct i915_gpu_state *error) @@ -1830,9 +1898,16 @@ i915_capture_gpu_state(struct drm_i915_private *i915) { struct i915_gpu_state *error; + /* Check if GPU capture has been disabled */ + error = READ_ONCE(i915->gpu_error.first_error); + if (IS_ERR(error)) + return error; + error = kzalloc(sizeof(*error), GFP_ATOMIC); - if (!error) - return NULL; + if (!error) { + i915_disable_error_state(i915, -ENOMEM); + return ERR_PTR(-ENOMEM); + } kref_init(&error->ref); error->i915 = i915; @@ -1868,11 +1943,8 @@ void i915_capture_error_state(struct drm_i915_private *i915, return; error = i915_capture_gpu_state(i915); - if (!error) { - DRM_DEBUG_DRIVER("out of memory, not capturing error state\n"); - i915_disable_error_state(i915, -ENOMEM); + if (IS_ERR(error)) return; - } i915_error_capture_msg(i915, error, engine_mask, error_msg); DRM_INFO("%s\n", error->error_msg); @@ -1910,7 +1982,7 @@ i915_first_error_state(struct drm_i915_private *i915) spin_lock_irq(&i915->gpu_error.lock); error = i915->gpu_error.first_error; - if (error) + if (!IS_ERR_OR_NULL(error)) i915_gpu_state_get(error); spin_unlock_irq(&i915->gpu_error.lock); @@ -1923,10 +1995,11 @@ void i915_reset_error_state(struct drm_i915_private *i915) spin_lock_irq(&i915->gpu_error.lock); error = i915->gpu_error.first_error; - i915->gpu_error.first_error = NULL; + if (error != ERR_PTR(-ENODEV)) /* if disabled, always disabled */ + i915->gpu_error.first_error = NULL; spin_unlock_irq(&i915->gpu_error.lock); - if (!IS_ERR(error)) + if (!IS_ERR_OR_NULL(error)) i915_gpu_state_put(error); } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 3ec89a504de5..6d9f45468ac1 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -45,6 +45,7 @@ struct i915_gpu_state { u32 reset_count; u32 suspend_count; struct intel_device_info device_info; + struct intel_runtime_info runtime_info; struct intel_driver_caps driver_caps; struct i915_params params; @@ -192,6 +193,8 @@ 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 +301,20 @@ 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 +328,9 @@ 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_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d447d7d508f4..fbb094ecf6c9 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -950,7 +950,7 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc) if (mode->flags & DRM_MODE_FLAG_INTERLACE) vtotal /= 2; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN2; else position = I915_READ_FW(PIPEDSL(pipe)) & DSL_LINEMASK_GEN3; @@ -1030,7 +1030,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, if (stime) *stime = ktime_get(); - if (IS_GEN2(dev_priv) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { + if (IS_GEN(dev_priv, 2) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { /* No obvious pixelcount register. Only query vertical * scanout position from Display scan line register. */ @@ -1090,7 +1090,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe, else position += vtotal - vbl_end; - if (IS_GEN2(dev_priv) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { + if (IS_GEN(dev_priv, 2) || IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { *vpos = position; *hpos = 0; } else { @@ -1189,13 +1189,6 @@ static void notify_ring(struct intel_engine_cs *engine) rq = i915_request_get(waiter); tsk = wait->tsk; - } else { - if (engine->irq_seqno_barrier && - i915_seqno_passed(seqno, wait->seqno - 1)) { - set_bit(ENGINE_IRQ_BREADCRUMB, - &engine->irq_posted); - tsk = wait->tsk; - } } engine->breadcrumbs.irq_count++; @@ -2547,7 +2540,7 @@ static void ilk_display_irq_handler(struct drm_i915_private *dev_priv, I915_WRITE(SDEIIR, pch_iir); } - if (IS_GEN5(dev_priv) && de_iir & DE_PCU_EVENT) + if (IS_GEN(dev_priv, 5) && de_iir & DE_PCU_EVENT) ironlake_rps_change_irq_handler(dev_priv); } @@ -3243,7 +3236,7 @@ void i915_clear_error_registers(struct drm_i915_private *dev_priv) { u32 eir; - if (!IS_GEN2(dev_priv)) + if (!IS_GEN(dev_priv, 2)) I915_WRITE(PGTBL_ER, I915_READ(PGTBL_ER)); if (INTEL_GEN(dev_priv) < 4) @@ -3586,11 +3579,8 @@ static void ironlake_irq_reset(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); - if (IS_GEN5(dev_priv)) - I915_WRITE(HWSTAM, 0xffffffff); - GEN3_IRQ_RESET(DE); - if (IS_GEN7(dev_priv)) + if (IS_GEN(dev_priv, 7)) I915_WRITE(GEN7_ERR_INT, 0xffffffff); if (IS_HASWELL(dev_priv)) { @@ -4045,7 +4035,7 @@ static void gen5_gt_irq_postinstall(struct drm_device *dev) } gt_irqs |= GT_RENDER_USER_INTERRUPT; - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { gt_irqs |= ILK_BSD_USER_INTERRUPT; } else { gt_irqs |= GT_BLT_USER_INTERRUPT | GT_BSD_USER_INTERRUPT; @@ -4368,8 +4358,6 @@ static void i8xx_irq_reset(struct drm_device *dev) i9xx_pipestat_irq_reset(dev_priv); - I915_WRITE16(HWSTAM, 0xffff); - GEN2_IRQ_RESET(); } @@ -4537,8 +4525,6 @@ static void i915_irq_reset(struct drm_device *dev) i9xx_pipestat_irq_reset(dev_priv); - I915_WRITE(HWSTAM, 0xffffffff); - GEN3_IRQ_RESET(); } @@ -4648,8 +4634,6 @@ static void i965_irq_reset(struct drm_device *dev) i9xx_pipestat_irq_reset(dev_priv); - I915_WRITE(HWSTAM, 0xffffffff); - GEN3_IRQ_RESET(); } @@ -4836,7 +4820,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) >= 8) rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC; - if (IS_GEN2(dev_priv)) { + if (IS_GEN(dev_priv, 2)) { /* Gen2 doesn't have a hardware frame counter */ dev->max_vblank_count = 0; } else if (IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { @@ -4852,7 +4836,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv) * Gen2 doesn't have a hardware frame counter and so depends on * vblank interrupts to produce sane vblank seuquence numbers. */ - if (!IS_GEN2(dev_priv)) + if (!IS_GEN(dev_priv, 2)) dev->vblank_disable_immediate = true; /* Most platforms treat the display irq block as an always-on @@ -4924,14 +4908,14 @@ void intel_irq_init(struct drm_i915_private *dev_priv) dev->driver->disable_vblank = ironlake_disable_vblank; dev_priv->display.hpd_irq_setup = ilk_hpd_irq_setup; } else { - if (IS_GEN2(dev_priv)) { + if (IS_GEN(dev_priv, 2)) { dev->driver->irq_preinstall = i8xx_irq_reset; dev->driver->irq_postinstall = i8xx_irq_postinstall; dev->driver->irq_handler = i8xx_irq_handler; dev->driver->irq_uninstall = i8xx_irq_reset; dev->driver->enable_vblank = i8xx_enable_vblank; dev->driver->disable_vblank = i8xx_disable_vblank; - } else if (IS_GEN3(dev_priv)) { + } else if (IS_GEN(dev_priv, 3)) { dev->driver->irq_preinstall = i915_irq_reset; dev->driver->irq_postinstall = i915_irq_postinstall; dev->driver->irq_uninstall = i915_irq_reset; diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 2e0356561839..9f0539bdaa39 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -77,7 +77,7 @@ i915_param_named(error_capture, bool, 0600, "triaging and debugging hangs."); #endif -i915_param_named_unsafe(enable_hangcheck, bool, 0644, +i915_param_named_unsafe(enable_hangcheck, bool, 0600, "Periodically check GPU activity for detecting hangs. " "WARNING: Disabling this can cause system wide hangs. " "(default: true)"); @@ -203,3 +203,33 @@ void i915_params_dump(const struct i915_params *params, struct drm_printer *p) I915_PARAMS_FOR_EACH(PRINT); #undef PRINT } + +static __always_inline void dup_param(const char *type, void *x) +{ + if (!__builtin_strcmp(type, "char *")) + *(void **)x = kstrdup(*(void **)x, GFP_ATOMIC); +} + +void i915_params_copy(struct i915_params *dest, const struct i915_params *src) +{ + *dest = *src; +#define DUP(T, x, ...) dup_param(#T, &dest->x); + I915_PARAMS_FOR_EACH(DUP); +#undef DUP +} + +static __always_inline void free_param(const char *type, void *x) +{ + if (!__builtin_strcmp(type, "char *")) { + kfree(*(void **)x); + *(void **)x = NULL; + } +} + +/* free the allocated members, *not* the passed in params itself */ +void i915_params_free(struct i915_params *params) +{ +#define FREE(T, x, ...) free_param(#T, ¶ms->x); + I915_PARAMS_FOR_EACH(FREE); +#undef FREE +} diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h index 7e56c516c815..6efcf330bdab 100644 --- a/drivers/gpu/drm/i915/i915_params.h +++ b/drivers/gpu/drm/i915/i915_params.h @@ -33,6 +33,15 @@ struct drm_printer; #define ENABLE_GUC_SUBMISSION BIT(0) #define ENABLE_GUC_LOAD_HUC BIT(1) +/* + * Invoke param, a function-like macro, for each i915 param, with arguments: + * + * param(type, name, value) + * + * type: parameter type, one of {bool, int, unsigned int, char *} + * name: name of the parameter + * value: initial/default value of the parameter + */ #define I915_PARAMS_FOR_EACH(param) \ param(char *, vbt_firmware, NULL) \ param(int, modeset, -1) \ @@ -78,6 +87,8 @@ struct i915_params { extern struct i915_params i915_modparams __read_mostly; void i915_params_dump(const struct i915_params *params, struct drm_printer *p); +void i915_params_copy(struct i915_params *dest, const struct i915_params *src); +void i915_params_free(struct i915_params *params); #endif diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 1b81d7cb209e..dd4aff2b256e 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -79,8 +79,10 @@ #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, \ + .gpu_reset_clobbers_display = true, \ .hws_needs_physical = 1, \ .unfenced_needs_alignment = 1, \ .ring_mask = RENDER_RING, \ @@ -93,7 +95,8 @@ 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 +110,8 @@ 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 +122,8 @@ 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, \ + .gpu_reset_clobbers_display = true, \ .ring_mask = RENDER_RING, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -131,8 +135,9 @@ 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 +146,11 @@ 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 +158,10 @@ 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 +170,12 @@ 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 +183,24 @@ 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, \ + .gpu_reset_clobbers_display = true, \ .ring_mask = RENDER_RING, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -200,7 +211,7 @@ 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 +219,10 @@ 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, }; @@ -219,20 +231,23 @@ static const struct intel_device_info intel_g45_info = { GEN4_FEATURES, PLATFORM(INTEL_G45), .ring_mask = RENDER_RING | BSD_RING, + .gpu_reset_clobbers_display = false, }; 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, + .gpu_reset_clobbers_display = false, }; #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 +265,15 @@ 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 +317,8 @@ 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 +375,8 @@ 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 +390,10 @@ 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 +460,14 @@ 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 +489,15 @@ 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 +528,18 @@ 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 +547,7 @@ 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_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 4529edfdcfc8..289b90065d27 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1796,7 +1796,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) * be read back from automatically triggered reports, as part of the * RPT_ID field. */ - if (IS_GEN(dev_priv, 9, 11)) { + if (IS_GEN_RANGE(dev_priv, 9, 11)) { I915_WRITE(GEN8_OA_DEBUG, _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS | GEN9_OA_DEBUG_INCLUDE_CLK_RATIO)); @@ -2646,7 +2646,7 @@ err: static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent) { return div64_u64(1000000000ULL * (2ULL << exponent), - 1000ULL * INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz); + 1000ULL * RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz); } /** @@ -3415,7 +3415,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.read = gen8_oa_read; dev_priv->perf.oa.ops.oa_hw_tail_read = gen8_oa_hw_tail_read; - if (IS_GEN8(dev_priv) || IS_GEN9(dev_priv)) { + if (IS_GEN_RANGE(dev_priv, 8, 9)) { dev_priv->perf.oa.ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; dev_priv->perf.oa.ops.is_valid_mux_reg = @@ -3431,7 +3431,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set; dev_priv->perf.oa.ops.disable_metric_set = gen8_disable_metric_set; - if (IS_GEN8(dev_priv)) { + if (IS_GEN(dev_priv, 8)) { dev_priv->perf.oa.ctx_oactxctrl_offset = 0x120; dev_priv->perf.oa.ctx_flexeu0_offset = 0x2ce; @@ -3442,7 +3442,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv) dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16); } - } else if (IS_GEN(dev_priv, 10, 11)) { + } else if (IS_GEN_RANGE(dev_priv, 10, 11)) { dev_priv->perf.oa.ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr; dev_priv->perf.oa.ops.is_valid_mux_reg = @@ -3471,7 +3471,7 @@ void i915_perf_init(struct drm_i915_private *dev_priv) spin_lock_init(&dev_priv->perf.oa.oa_buffer.ptr_lock); oa_sample_rate_hard_limit = 1000 * - (INTEL_INFO(dev_priv)->cs_timestamp_frequency_khz / 2); + (RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz / 2); dev_priv->perf.sysctl_header = register_sysctl_table(dev_root); mutex_init(&dev_priv->perf.metrics_lock); diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c index 6fc4b8eeab42..95a343934cbd 100644 --- a/drivers/gpu/drm/i915/i915_query.c +++ b/drivers/gpu/drm/i915/i915_query.c @@ -13,7 +13,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv, struct drm_i915_query_item *query_item) { - const struct sseu_dev_info *sseu = &INTEL_INFO(dev_priv)->sseu; + const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; struct drm_i915_query_topology_info topo; u32 slice_length, subslice_length, eu_length, total_length; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 47baf2fe8f71..44958d994bfa 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -139,6 +139,12 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG); } +#define VLV_DISPLAY_BASE 0x180000 +#define VLV_MIPI_BASE VLV_DISPLAY_BASE +#define BXT_MIPI_BASE 0x60000 + +#define DISPLAY_MMIO_BASE(dev_priv) (INTEL_INFO(dev_priv)->display_mmio_offset) + /* * Given the first two numbers __a and __b of arbitrarily many evenly spaced * numbers, pick the 0-based __index'th value. @@ -179,15 +185,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) * Device info offset array based helpers for groups of registers with unevenly * spaced base offsets. */ -#define _MMIO_PIPE2(pipe, reg) _MMIO(dev_priv->info.pipe_offsets[pipe] - \ - dev_priv->info.pipe_offsets[PIPE_A] + (reg) + \ - dev_priv->info.display_mmio_offset) -#define _MMIO_TRANS2(pipe, reg) _MMIO(dev_priv->info.trans_offsets[(pipe)] - \ - dev_priv->info.trans_offsets[TRANSCODER_A] + (reg) + \ - dev_priv->info.display_mmio_offset) -#define _CURSOR2(pipe, reg) _MMIO(dev_priv->info.cursor_offsets[(pipe)] - \ - dev_priv->info.cursor_offsets[PIPE_A] + (reg) + \ - dev_priv->info.display_mmio_offset) +#define _MMIO_PIPE2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->pipe_offsets[pipe] - \ + INTEL_INFO(dev_priv)->pipe_offsets[PIPE_A] + (reg) + \ + DISPLAY_MMIO_BASE(dev_priv)) +#define _MMIO_TRANS2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->trans_offsets[(pipe)] - \ + INTEL_INFO(dev_priv)->trans_offsets[TRANSCODER_A] + (reg) + \ + DISPLAY_MMIO_BASE(dev_priv)) +#define _CURSOR2(pipe, reg) _MMIO(INTEL_INFO(dev_priv)->cursor_offsets[(pipe)] - \ + INTEL_INFO(dev_priv)->cursor_offsets[PIPE_A] + (reg) + \ + DISPLAY_MMIO_BASE(dev_priv)) #define __MASKED_FIELD(mask, value) ((mask) << 16 | (value)) #define _MASKED_FIELD(mask, value) ({ \ @@ -347,6 +353,24 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN11_GRDOM_MEDIA4 (1 << 8) #define GEN11_GRDOM_VECS (1 << 13) #define GEN11_GRDOM_VECS2 (1 << 14) +#define GEN11_GRDOM_SFC0 (1 << 17) +#define GEN11_GRDOM_SFC1 (1 << 18) + +#define GEN11_VCS_SFC_RESET_BIT(instance) (GEN11_GRDOM_SFC0 << ((instance) >> 1)) +#define GEN11_VECS_SFC_RESET_BIT(instance) (GEN11_GRDOM_SFC0 << (instance)) + +#define GEN11_VCS_SFC_FORCED_LOCK(engine) _MMIO((engine)->mmio_base + 0x88C) +#define GEN11_VCS_SFC_FORCED_LOCK_BIT (1 << 0) +#define GEN11_VCS_SFC_LOCK_STATUS(engine) _MMIO((engine)->mmio_base + 0x890) +#define GEN11_VCS_SFC_USAGE_BIT (1 << 0) +#define GEN11_VCS_SFC_LOCK_ACK_BIT (1 << 1) + +#define GEN11_VECS_SFC_FORCED_LOCK(engine) _MMIO((engine)->mmio_base + 0x201C) +#define GEN11_VECS_SFC_FORCED_LOCK_BIT (1 << 0) +#define GEN11_VECS_SFC_LOCK_ACK(engine) _MMIO((engine)->mmio_base + 0x2018) +#define GEN11_VECS_SFC_LOCK_ACK_BIT (1 << 0) +#define GEN11_VECS_SFC_USAGE(engine) _MMIO((engine)->mmio_base + 0x2014) +#define GEN11_VECS_SFC_USAGE_BIT (1 << 0) #define RING_PP_DIR_BASE(engine) _MMIO((engine)->mmio_base + 0x228) #define RING_PP_DIR_BASE_READ(engine) _MMIO((engine)->mmio_base + 0x518) @@ -1866,6 +1890,10 @@ enum i915_power_well_id { #define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 7)) #define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 7)) +#define ICL_PORT_TX_DW7_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(7, port)) +#define ICL_PORT_TX_DW7_GRP(port) _MMIO(_ICL_PORT_TX_DW_GRP(7, port)) +#define ICL_PORT_TX_DW7_LN0(port) _MMIO(_ICL_PORT_TX_DW_LN(7, 0, port)) +#define ICL_PORT_TX_DW7_LN(port, ln) _MMIO(_ICL_PORT_TX_DW_LN(7, ln, port)) #define N_SCALAR(x) ((x) << 24) #define N_SCALAR_MASK (0x7F << 24) @@ -2592,10 +2620,6 @@ enum i915_power_well_id { #define GEN11_GFX_DISABLE_LEGACY_MODE (1 << 3) -#define VLV_DISPLAY_BASE 0x180000 -#define VLV_MIPI_BASE VLV_DISPLAY_BASE -#define BXT_MIPI_BASE 0x60000 - #define VLV_GU_CTL0 _MMIO(VLV_DISPLAY_BASE + 0x2030) #define VLV_GU_CTL1 _MMIO(VLV_DISPLAY_BASE + 0x2034) #define SCPD0 _MMIO(0x209c) /* 915+ only */ @@ -3152,9 +3176,9 @@ enum i915_power_well_id { /* * Clock control & power management */ -#define _DPLL_A (dev_priv->info.display_mmio_offset + 0x6014) -#define _DPLL_B (dev_priv->info.display_mmio_offset + 0x6018) -#define _CHV_DPLL_C (dev_priv->info.display_mmio_offset + 0x6030) +#define _DPLL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x6014) +#define _DPLL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x6018) +#define _CHV_DPLL_C (DISPLAY_MMIO_BASE(dev_priv) + 0x6030) #define DPLL(pipe) _MMIO_PIPE3((pipe), _DPLL_A, _DPLL_B, _CHV_DPLL_C) #define VGA0 _MMIO(0x6000) @@ -3251,9 +3275,9 @@ enum i915_power_well_id { #define SDVO_MULTIPLIER_SHIFT_HIRES 4 #define SDVO_MULTIPLIER_SHIFT_VGA 0 -#define _DPLL_A_MD (dev_priv->info.display_mmio_offset + 0x601c) -#define _DPLL_B_MD (dev_priv->info.display_mmio_offset + 0x6020) -#define _CHV_DPLL_C_MD (dev_priv->info.display_mmio_offset + 0x603c) +#define _DPLL_A_MD (DISPLAY_MMIO_BASE(dev_priv) + 0x601c) +#define _DPLL_B_MD (DISPLAY_MMIO_BASE(dev_priv) + 0x6020) +#define _CHV_DPLL_C_MD (DISPLAY_MMIO_BASE(dev_priv) + 0x603c) #define DPLL_MD(pipe) _MMIO_PIPE3((pipe), _DPLL_A_MD, _DPLL_B_MD, _CHV_DPLL_C_MD) /* @@ -3325,7 +3349,7 @@ enum i915_power_well_id { #define DSTATE_PLL_D3_OFF (1 << 3) #define DSTATE_GFX_CLOCK_GATING (1 << 1) #define DSTATE_DOT_CLOCK_GATING (1 << 0) -#define DSPCLK_GATE_D _MMIO(dev_priv->info.display_mmio_offset + 0x6200) +#define DSPCLK_GATE_D _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x6200) # define DPUNIT_B_CLOCK_GATE_DISABLE (1 << 30) /* 965 */ # define VSUNIT_CLOCK_GATE_DISABLE (1 << 29) /* 965 */ # define VRHUNIT_CLOCK_GATE_DISABLE (1 << 28) /* 965 */ @@ -3465,7 +3489,7 @@ enum i915_power_well_id { #define _PALETTE_A 0xa000 #define _PALETTE_B 0xa800 #define _CHV_PALETTE_C 0xc000 -#define PALETTE(pipe, i) _MMIO(dev_priv->info.display_mmio_offset + \ +#define PALETTE(pipe, i) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + \ _PICK((pipe), _PALETTE_A, \ _PALETTE_B, _CHV_PALETTE_C) + \ (i) * 4) @@ -4298,7 +4322,7 @@ enum { /* Hotplug control (945+ only) */ -#define PORT_HOTPLUG_EN _MMIO(dev_priv->info.display_mmio_offset + 0x61110) +#define PORT_HOTPLUG_EN _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61110) #define PORTB_HOTPLUG_INT_EN (1 << 29) #define PORTC_HOTPLUG_INT_EN (1 << 28) #define PORTD_HOTPLUG_INT_EN (1 << 27) @@ -4328,7 +4352,7 @@ enum { #define CRT_HOTPLUG_DETECT_VOLTAGE_325MV (0 << 2) #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV (1 << 2) -#define PORT_HOTPLUG_STAT _MMIO(dev_priv->info.display_mmio_offset + 0x61114) +#define PORT_HOTPLUG_STAT _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61114) /* * HDMI/DP bits are g4x+ * @@ -4410,7 +4434,7 @@ enum { #define PORT_DFT_I9XX _MMIO(0x61150) #define DC_BALANCE_RESET (1 << 25) -#define PORT_DFT2_G4X _MMIO(dev_priv->info.display_mmio_offset + 0x61154) +#define PORT_DFT2_G4X _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61154) #define DC_BALANCE_RESET_VLV (1 << 31) #define PIPE_SCRAMBLE_RESET_MASK ((1 << 14) | (0x3 << 0)) #define PIPE_C_SCRAMBLE_RESET (1 << 14) /* chv */ @@ -4570,6 +4594,7 @@ 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 +4642,17 @@ 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: * @@ -4683,7 +4719,7 @@ enum { #define PANEL_POWER_CYCLE_DELAY_SHIFT 0 /* Panel fitting */ -#define PFIT_CONTROL _MMIO(dev_priv->info.display_mmio_offset + 0x61230) +#define PFIT_CONTROL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61230) #define PFIT_ENABLE (1 << 31) #define PFIT_PIPE_MASK (3 << 29) #define PFIT_PIPE_SHIFT 29 @@ -4701,7 +4737,7 @@ enum { #define PFIT_SCALING_PROGRAMMED (1 << 26) #define PFIT_SCALING_PILLAR (2 << 26) #define PFIT_SCALING_LETTER (3 << 26) -#define PFIT_PGM_RATIOS _MMIO(dev_priv->info.display_mmio_offset + 0x61234) +#define PFIT_PGM_RATIOS _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61234) /* Pre-965 */ #define PFIT_VERT_SCALE_SHIFT 20 #define PFIT_VERT_SCALE_MASK 0xfff00000 @@ -4713,25 +4749,25 @@ enum { #define PFIT_HORIZ_SCALE_SHIFT_965 0 #define PFIT_HORIZ_SCALE_MASK_965 0x00001fff -#define PFIT_AUTO_RATIOS _MMIO(dev_priv->info.display_mmio_offset + 0x61238) +#define PFIT_AUTO_RATIOS _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61238) -#define _VLV_BLC_PWM_CTL2_A (dev_priv->info.display_mmio_offset + 0x61250) -#define _VLV_BLC_PWM_CTL2_B (dev_priv->info.display_mmio_offset + 0x61350) +#define _VLV_BLC_PWM_CTL2_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61250) +#define _VLV_BLC_PWM_CTL2_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61350) #define VLV_BLC_PWM_CTL2(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL2_A, \ _VLV_BLC_PWM_CTL2_B) -#define _VLV_BLC_PWM_CTL_A (dev_priv->info.display_mmio_offset + 0x61254) -#define _VLV_BLC_PWM_CTL_B (dev_priv->info.display_mmio_offset + 0x61354) +#define _VLV_BLC_PWM_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61254) +#define _VLV_BLC_PWM_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61354) #define VLV_BLC_PWM_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL_A, \ _VLV_BLC_PWM_CTL_B) -#define _VLV_BLC_HIST_CTL_A (dev_priv->info.display_mmio_offset + 0x61260) -#define _VLV_BLC_HIST_CTL_B (dev_priv->info.display_mmio_offset + 0x61360) +#define _VLV_BLC_HIST_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61260) +#define _VLV_BLC_HIST_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61360) #define VLV_BLC_HIST_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_HIST_CTL_A, \ _VLV_BLC_HIST_CTL_B) /* Backlight control */ -#define BLC_PWM_CTL2 _MMIO(dev_priv->info.display_mmio_offset + 0x61250) /* 965+ only */ +#define BLC_PWM_CTL2 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61250) /* 965+ only */ #define BLM_PWM_ENABLE (1 << 31) #define BLM_COMBINATION_MODE (1 << 30) /* gen4 only */ #define BLM_PIPE_SELECT (1 << 29) @@ -4754,7 +4790,7 @@ enum { #define BLM_PHASE_IN_COUNT_MASK (0xff << 8) #define BLM_PHASE_IN_INCR_SHIFT (0) #define BLM_PHASE_IN_INCR_MASK (0xff << 0) -#define BLC_PWM_CTL _MMIO(dev_priv->info.display_mmio_offset + 0x61254) +#define BLC_PWM_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61254) /* * This is the most significant 15 bits of the number of backlight cycles in a * complete cycle of the modulated backlight control. @@ -4776,7 +4812,7 @@ enum { #define BACKLIGHT_DUTY_CYCLE_MASK_PNV (0xfffe) #define BLM_POLARITY_PNV (1 << 0) /* pnv only */ -#define BLC_HIST_CTL _MMIO(dev_priv->info.display_mmio_offset + 0x61260) +#define BLC_HIST_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61260) #define BLM_HISTOGRAM_ENABLE (1 << 31) /* New registers for PCH-split platforms. Safe where new bits show up, the @@ -5400,47 +5436,47 @@ enum { * is 20 bytes in each direction, hence the 5 fixed * data registers */ -#define _DPA_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64010) -#define _DPA_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64014) -#define _DPA_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64018) -#define _DPA_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6401c) -#define _DPA_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64020) -#define _DPA_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64024) - -#define _DPB_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64110) -#define _DPB_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64114) -#define _DPB_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64118) -#define _DPB_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6411c) -#define _DPB_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64120) -#define _DPB_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64124) - -#define _DPC_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64210) -#define _DPC_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64214) -#define _DPC_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64218) -#define _DPC_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6421c) -#define _DPC_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64220) -#define _DPC_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64224) - -#define _DPD_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64310) -#define _DPD_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64314) -#define _DPD_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64318) -#define _DPD_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6431c) -#define _DPD_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64320) -#define _DPD_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64324) - -#define _DPE_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64410) -#define _DPE_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64414) -#define _DPE_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64418) -#define _DPE_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6441c) -#define _DPE_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64420) -#define _DPE_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64424) - -#define _DPF_AUX_CH_CTL (dev_priv->info.display_mmio_offset + 0x64510) -#define _DPF_AUX_CH_DATA1 (dev_priv->info.display_mmio_offset + 0x64514) -#define _DPF_AUX_CH_DATA2 (dev_priv->info.display_mmio_offset + 0x64518) -#define _DPF_AUX_CH_DATA3 (dev_priv->info.display_mmio_offset + 0x6451c) -#define _DPF_AUX_CH_DATA4 (dev_priv->info.display_mmio_offset + 0x64520) -#define _DPF_AUX_CH_DATA5 (dev_priv->info.display_mmio_offset + 0x64524) +#define _DPA_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64010) +#define _DPA_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64014) +#define _DPA_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64018) +#define _DPA_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6401c) +#define _DPA_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64020) +#define _DPA_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64024) + +#define _DPB_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64110) +#define _DPB_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64114) +#define _DPB_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64118) +#define _DPB_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6411c) +#define _DPB_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64120) +#define _DPB_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64124) + +#define _DPC_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64210) +#define _DPC_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64214) +#define _DPC_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64218) +#define _DPC_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6421c) +#define _DPC_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64220) +#define _DPC_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64224) + +#define _DPD_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64310) +#define _DPD_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64314) +#define _DPD_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64318) +#define _DPD_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6431c) +#define _DPD_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64320) +#define _DPD_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64324) + +#define _DPE_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64410) +#define _DPE_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64414) +#define _DPE_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64418) +#define _DPE_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6441c) +#define _DPE_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64420) +#define _DPE_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64424) + +#define _DPF_AUX_CH_CTL (DISPLAY_MMIO_BASE(dev_priv) + 0x64510) +#define _DPF_AUX_CH_DATA1 (DISPLAY_MMIO_BASE(dev_priv) + 0x64514) +#define _DPF_AUX_CH_DATA2 (DISPLAY_MMIO_BASE(dev_priv) + 0x64518) +#define _DPF_AUX_CH_DATA3 (DISPLAY_MMIO_BASE(dev_priv) + 0x6451c) +#define _DPF_AUX_CH_DATA4 (DISPLAY_MMIO_BASE(dev_priv) + 0x64520) +#define _DPF_AUX_CH_DATA5 (DISPLAY_MMIO_BASE(dev_priv) + 0x64524) #define DP_AUX_CH_CTL(aux_ch) _MMIO_PORT(aux_ch, _DPA_AUX_CH_CTL, _DPB_AUX_CH_CTL) #define DP_AUX_CH_DATA(aux_ch, i) _MMIO(_PORT(aux_ch, _DPA_AUX_CH_DATA1, _DPB_AUX_CH_DATA1) + (i) * 4) /* 5 registers */ @@ -5716,7 +5752,7 @@ enum { #define DPINVGTT_STATUS_MASK 0xff #define DPINVGTT_STATUS_MASK_CHV 0xfff -#define DSPARB _MMIO(dev_priv->info.display_mmio_offset + 0x70030) +#define DSPARB _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x70030) #define DSPARB_CSTART_MASK (0x7f << 7) #define DSPARB_CSTART_SHIFT 7 #define DSPARB_BSTART_MASK (0x7f) @@ -5751,7 +5787,7 @@ enum { #define DSPARB_SPRITEF_MASK_VLV (0xff << 8) /* pnv/gen4/g4x/vlv/chv */ -#define DSPFW1 _MMIO(dev_priv->info.display_mmio_offset + 0x70034) +#define DSPFW1 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x70034) #define DSPFW_SR_SHIFT 23 #define DSPFW_SR_MASK (0x1ff << 23) #define DSPFW_CURSORB_SHIFT 16 @@ -5762,7 +5798,7 @@ enum { #define DSPFW_PLANEA_SHIFT 0 #define DSPFW_PLANEA_MASK (0x7f << 0) #define DSPFW_PLANEA_MASK_VLV (0xff << 0) /* vlv/chv */ -#define DSPFW2 _MMIO(dev_priv->info.display_mmio_offset + 0x70038) +#define DSPFW2 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x70038) #define DSPFW_FBC_SR_EN (1 << 31) /* g4x */ #define DSPFW_FBC_SR_SHIFT 28 #define DSPFW_FBC_SR_MASK (0x7 << 28) /* g4x */ @@ -5778,7 +5814,7 @@ enum { #define DSPFW_SPRITEA_SHIFT 0 #define DSPFW_SPRITEA_MASK (0x7f << 0) /* g4x */ #define DSPFW_SPRITEA_MASK_VLV (0xff << 0) /* vlv/chv */ -#define DSPFW3 _MMIO(dev_priv->info.display_mmio_offset + 0x7003c) +#define DSPFW3 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x7003c) #define DSPFW_HPLL_SR_EN (1 << 31) #define PINEVIEW_SELF_REFRESH_EN (1 << 30) #define DSPFW_CURSOR_SR_SHIFT 24 @@ -6194,35 +6230,35 @@ enum { * [10:1f] all * [30:32] all */ -#define SWF0(i) _MMIO(dev_priv->info.display_mmio_offset + 0x70410 + (i) * 4) -#define SWF1(i) _MMIO(dev_priv->info.display_mmio_offset + 0x71410 + (i) * 4) -#define SWF3(i) _MMIO(dev_priv->info.display_mmio_offset + 0x72414 + (i) * 4) +#define SWF0(i) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x70410 + (i) * 4) +#define SWF1(i) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x71410 + (i) * 4) +#define SWF3(i) _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x72414 + (i) * 4) #define SWF_ILK(i) _MMIO(0x4F000 + (i) * 4) /* Pipe B */ -#define _PIPEBDSL (dev_priv->info.display_mmio_offset + 0x71000) -#define _PIPEBCONF (dev_priv->info.display_mmio_offset + 0x71008) -#define _PIPEBSTAT (dev_priv->info.display_mmio_offset + 0x71024) +#define _PIPEBDSL (DISPLAY_MMIO_BASE(dev_priv) + 0x71000) +#define _PIPEBCONF (DISPLAY_MMIO_BASE(dev_priv) + 0x71008) +#define _PIPEBSTAT (DISPLAY_MMIO_BASE(dev_priv) + 0x71024) #define _PIPEBFRAMEHIGH 0x71040 #define _PIPEBFRAMEPIXEL 0x71044 -#define _PIPEB_FRMCOUNT_G4X (dev_priv->info.display_mmio_offset + 0x71040) -#define _PIPEB_FLIPCOUNT_G4X (dev_priv->info.display_mmio_offset + 0x71044) +#define _PIPEB_FRMCOUNT_G4X (DISPLAY_MMIO_BASE(dev_priv) + 0x71040) +#define _PIPEB_FLIPCOUNT_G4X (DISPLAY_MMIO_BASE(dev_priv) + 0x71044) /* Display B control */ -#define _DSPBCNTR (dev_priv->info.display_mmio_offset + 0x71180) +#define _DSPBCNTR (DISPLAY_MMIO_BASE(dev_priv) + 0x71180) #define DISPPLANE_ALPHA_TRANS_ENABLE (1 << 15) #define DISPPLANE_ALPHA_TRANS_DISABLE 0 #define DISPPLANE_SPRITE_ABOVE_DISPLAY 0 #define DISPPLANE_SPRITE_ABOVE_OVERLAY (1) -#define _DSPBADDR (dev_priv->info.display_mmio_offset + 0x71184) -#define _DSPBSTRIDE (dev_priv->info.display_mmio_offset + 0x71188) -#define _DSPBPOS (dev_priv->info.display_mmio_offset + 0x7118C) -#define _DSPBSIZE (dev_priv->info.display_mmio_offset + 0x71190) -#define _DSPBSURF (dev_priv->info.display_mmio_offset + 0x7119C) -#define _DSPBTILEOFF (dev_priv->info.display_mmio_offset + 0x711A4) -#define _DSPBOFFSET (dev_priv->info.display_mmio_offset + 0x711A4) -#define _DSPBSURFLIVE (dev_priv->info.display_mmio_offset + 0x711AC) +#define _DSPBADDR (DISPLAY_MMIO_BASE(dev_priv) + 0x71184) +#define _DSPBSTRIDE (DISPLAY_MMIO_BASE(dev_priv) + 0x71188) +#define _DSPBPOS (DISPLAY_MMIO_BASE(dev_priv) + 0x7118C) +#define _DSPBSIZE (DISPLAY_MMIO_BASE(dev_priv) + 0x71190) +#define _DSPBSURF (DISPLAY_MMIO_BASE(dev_priv) + 0x7119C) +#define _DSPBTILEOFF (DISPLAY_MMIO_BASE(dev_priv) + 0x711A4) +#define _DSPBOFFSET (DISPLAY_MMIO_BASE(dev_priv) + 0x711A4) +#define _DSPBSURFLIVE (DISPLAY_MMIO_BASE(dev_priv) + 0x711AC) /* ICL DSI 0 and 1 */ #define _PIPEDSI0CONF 0x7b008 @@ -7750,6 +7786,7 @@ 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) @@ -8773,7 +8810,7 @@ enum { #define GEN9_ENABLE_GPGPU_PREEMPTION (1 << 2) /* Audio */ -#define G4X_AUD_VID_DID _MMIO(dev_priv->info.display_mmio_offset + 0x62020) +#define G4X_AUD_VID_DID _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x62020) #define INTEL_AUDIO_DEVCL 0x808629FB #define INTEL_AUDIO_DEVBLC 0x80862801 #define INTEL_AUDIO_DEVCTG 0x80862802 @@ -9197,6 +9234,7 @@ 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 +9253,7 @@ 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..346418c942a2 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -111,96 +111,10 @@ i915_request_remove_from_client(struct i915_request *request) spin_unlock(&file_priv->mm.lock); } -static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno) +static void reserve_gt(struct drm_i915_private *i915) { - struct intel_engine_cs *engine; - struct i915_timeline *timeline; - enum intel_engine_id id; - int ret; - - /* Carefully retire all requests without writing to the rings */ - ret = i915_gem_wait_for_idle(i915, - I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED, - MAX_SCHEDULE_TIMEOUT); - if (ret) - return ret; - - GEM_BUG_ON(i915->gt.active_requests); - - /* If the seqno wraps around, we need to clear the breadcrumb rbtree */ - for_each_engine(engine, i915, id) { - GEM_TRACE("%s seqno %d (current %d) -> %d\n", - engine->name, - engine->timeline.seqno, - intel_engine_get_seqno(engine), - seqno); - - kthread_park(engine->breadcrumbs.signaler); - - if (!i915_seqno_passed(seqno, engine->timeline.seqno)) { - /* Flush any waiters before we reuse the seqno */ - intel_engine_disarm_breadcrumbs(engine); - intel_engine_init_hangcheck(engine); - GEM_BUG_ON(!list_empty(&engine->breadcrumbs.signals)); - } - - /* Check we are idle before we fiddle with hw state! */ - GEM_BUG_ON(!intel_engine_is_idle(engine)); - GEM_BUG_ON(i915_gem_active_isset(&engine->timeline.last_request)); - - /* Finally reset hw state */ - intel_engine_init_global_seqno(engine, seqno); - engine->timeline.seqno = seqno; - - kthread_unpark(engine->breadcrumbs.signaler); - } - - list_for_each_entry(timeline, &i915->gt.timelines, link) - memset(timeline->global_sync, 0, sizeof(timeline->global_sync)); - - i915->gt.request_serial = seqno; - - return 0; -} - -int i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno) -{ - struct drm_i915_private *i915 = to_i915(dev); - - lockdep_assert_held(&i915->drm.struct_mutex); - - if (seqno == 0) - return -EINVAL; - - /* HWS page needs to be set less than what we will inject to ring */ - return reset_all_global_seqno(i915, seqno - 1); -} - -static int reserve_gt(struct drm_i915_private *i915) -{ - int ret; - - /* - * Reservation is fine until we may need to wrap around - * - * By incrementing the serial for every request, we know that no - * individual engine may exceed that serial (as each is reset to 0 - * on any wrap). This protects even the most pessimistic of migrations - * of every request from all engines onto just one. - */ - while (unlikely(++i915->gt.request_serial == 0)) { - ret = reset_all_global_seqno(i915, 0); - if (ret) { - i915->gt.request_serial--; - return ret; - } - } - if (!i915->gt.active_requests++) i915_gem_unpark(i915); - - return 0; } static void unreserve_gt(struct drm_i915_private *i915) @@ -605,13 +519,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) if (IS_ERR(ce)) return ERR_CAST(ce); - ret = reserve_gt(i915); - if (ret) - goto err_unpin; - - ret = intel_ring_wait_for_space(ce->ring, MIN_SPACE_FOR_ADD_REQUEST); - if (ret) - goto err_unreserve; + reserve_gt(i915); /* Move our oldest request to the slab-cache (if not in use!) */ rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link); @@ -704,9 +612,13 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) * i915_request_add() call can't fail. Note that the reserve may need * to be redone if the request is not actually submitted straight * away, e.g. because a GPU scheduler has deferred it. + * + * Note that due to how we add reserved_space to intel_ring_begin() + * we need to double our request to ensure that if we need to wrap + * around inside i915_request_add() there is sufficient space at + * the beginning of the ring as well. */ - rq->reserved_space = MIN_SPACE_FOR_ADD_REQUEST; - GEM_BUG_ON(rq->reserved_space < engine->emit_breadcrumb_sz); + rq->reserved_space = 2 * engine->emit_breadcrumb_sz * sizeof(u32); /* * Record the position of the start of the request so that @@ -716,11 +628,6 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx) */ rq->head = rq->ring->emit; - /* Unconditionally invalidate GPU caches and TLBs. */ - ret = engine->emit_flush(rq, EMIT_INVALIDATE); - if (ret) - goto err_unwind; - ret = engine->request_alloc(rq); if (ret) goto err_unwind; @@ -745,7 +652,6 @@ err_unwind: kmem_cache_free(i915->requests, rq); err_unreserve: unreserve_gt(i915); -err_unpin: intel_context_unpin(ce); return ERR_PTR(ret); } @@ -773,34 +679,12 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) ret = i915_sw_fence_await_sw_fence_gfp(&to->submit, &from->submit, I915_FENCE_GFP); - return ret < 0 ? ret : 0; - } - - if (to->engine->semaphore.sync_to) { - u32 seqno; - - GEM_BUG_ON(!from->engine->semaphore.signal); - - seqno = i915_request_global_seqno(from); - if (!seqno) - goto await_dma_fence; - - if (seqno <= to->timeline->global_sync[from->engine->id]) - return 0; - - trace_i915_gem_ring_sync_to(to, from); - ret = to->engine->semaphore.sync_to(to, from); - if (ret) - return ret; - - to->timeline->global_sync[from->engine->id] = seqno; - return 0; + } else { + ret = i915_sw_fence_await_dma_fence(&to->submit, + &from->fence, 0, + I915_FENCE_GFP); } -await_dma_fence: - ret = i915_sw_fence_await_dma_fence(&to->submit, - &from->fence, 0, - I915_FENCE_GFP); return ret < 0 ? ret : 0; } @@ -976,8 +860,8 @@ void i915_request_add(struct i915_request *request) * should already have been reserved in the ring buffer. Let the ring * know that it is time to use that space up. */ + GEM_BUG_ON(request->reserved_space > request->ring->space); request->reserved_space = 0; - engine->emit_flush(request, EMIT_FLUSH); /* * Record the position of the start of the breadcrumb so that @@ -1295,13 +1179,7 @@ restart: set_current_state(state); wakeup: - /* - * Carefully check if the request is complete, giving time - * for the seqno to be visible following the interrupt. - * We also have to check in case we are kicked by the GPU - * reset in order to drop the struct_mutex. - */ - if (__i915_request_irq_complete(rq)) + if (i915_request_completed(rq)) break; /* diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 90e9d170a0cd..d014b0605445 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -30,7 +30,6 @@ #include "i915_gem.h" #include "i915_scheduler.h" #include "i915_sw_fence.h" -#include "i915_scheduler.h" #include <uapi/drm/i915_drm.h> diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c index 8f3aa4dc0c98..f40ba5e429e0 100644 --- a/drivers/gpu/drm/i915/i915_suspend.c +++ b/drivers/gpu/drm/i915/i915_suspend.c @@ -65,7 +65,7 @@ int i915_save_state(struct drm_i915_private *dev_priv) i915_save_display(dev_priv); - if (IS_GEN4(dev_priv)) + if (IS_GEN(dev_priv, 4)) pci_read_config_word(pdev, GCDGMBUS, &dev_priv->regfile.saveGCDGMBUS); @@ -77,14 +77,14 @@ int i915_save_state(struct drm_i915_private *dev_priv) dev_priv->regfile.saveMI_ARB_STATE = I915_READ(MI_ARB_STATE); /* Scratch space */ - if (IS_GEN2(dev_priv) && IS_MOBILE(dev_priv)) { + if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { dev_priv->regfile.saveSWF0[i] = I915_READ(SWF0(i)); dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i)); } for (i = 0; i < 3; i++) dev_priv->regfile.saveSWF3[i] = I915_READ(SWF3(i)); - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { for (i = 0; i < 7; i++) dev_priv->regfile.saveSWF1[i] = I915_READ(SWF1(i)); } else if (HAS_GMCH_DISPLAY(dev_priv)) { @@ -108,7 +108,7 @@ int i915_restore_state(struct drm_i915_private *dev_priv) mutex_lock(&dev_priv->drm.struct_mutex); - if (IS_GEN4(dev_priv)) + if (IS_GEN(dev_priv, 4)) pci_write_config_word(pdev, GCDGMBUS, dev_priv->regfile.saveGCDGMBUS); i915_restore_display(dev_priv); @@ -122,14 +122,14 @@ int i915_restore_state(struct drm_i915_private *dev_priv) I915_WRITE(MI_ARB_STATE, dev_priv->regfile.saveMI_ARB_STATE | 0xffff0000); /* Scratch space */ - if (IS_GEN2(dev_priv) && IS_MOBILE(dev_priv)) { + if (IS_GEN(dev_priv, 2) && IS_MOBILE(dev_priv)) { for (i = 0; i < 7; i++) { I915_WRITE(SWF0(i), dev_priv->regfile.saveSWF0[i]); I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]); } for (i = 0; i < 3; i++) I915_WRITE(SWF3(i), dev_priv->regfile.saveSWF3[i]); - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { for (i = 0; i < 7; i++) I915_WRITE(SWF1(i), dev_priv->regfile.saveSWF1[i]); } else if (HAS_GMCH_DISPLAY(dev_priv)) { 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..c0cfe7ae2ba5 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 +516,23 @@ 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 (IS_ERR(gpu)) { + ret = PTR_ERR(gpu); + } else 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_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h index ebd71b487220..38c1e15e927a 100644 --- a/drivers/gpu/drm/i915/i915_timeline.h +++ b/drivers/gpu/drm/i915/i915_timeline.h @@ -63,14 +63,6 @@ struct i915_timeline { * redundant and we can discard it without loss of generality. */ struct i915_syncmap *sync; - /** - * Separately to the inter-context seqno map above, we track the last - * barrier (e.g. semaphore wait) to the global engine timelines. Note - * that this tracks global_seqno rather than the context.seqno, and - * so it is subject to the limitations of hw wraparound and that we - * may need to revoke global_seqno (on pre-emption). - */ - u32 global_sync[I915_NUM_ENGINES]; struct list_head link; const char *name; diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index b50c6b829715..5cf378936b05 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -585,35 +585,6 @@ TRACE_EVENT(i915_gem_evict_vm, TP_printk("dev=%d, vm=%p", __entry->dev, __entry->vm) ); -TRACE_EVENT(i915_gem_ring_sync_to, - TP_PROTO(struct i915_request *to, struct i915_request *from), - TP_ARGS(to, from), - - TP_STRUCT__entry( - __field(u32, dev) - __field(u32, from_class) - __field(u32, from_instance) - __field(u32, to_class) - __field(u32, to_instance) - __field(u32, seqno) - ), - - TP_fast_assign( - __entry->dev = from->i915->drm.primary->index; - __entry->from_class = from->engine->uabi_class; - __entry->from_instance = from->engine->instance; - __entry->to_class = to->engine->uabi_class; - __entry->to_instance = to->engine->instance; - __entry->seqno = from->global_seqno; - ), - - TP_printk("dev=%u, sync-from=%u:%u, sync-to=%u:%u, seqno=%u", - __entry->dev, - __entry->from_class, __entry->from_instance, - __entry->to_class, __entry->to_instance, - __entry->seqno) -); - TRACE_EVENT(i915_request_queue, TP_PROTO(struct i915_request *rq, u32 flags), TP_ARGS(rq, flags), 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..fdfc7425e644 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; } @@ -232,7 +233,7 @@ static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_sta if (plane_state && plane_state->base.fb && plane_state->base.fb->format->is_yuv && plane_state->base.fb->format->num_planes > 1) { - if (IS_GEN9(dev_priv) && + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) { mode = SKL_PS_SCALER_MODE_NV12; } else if (icl_is_hdr_plane(to_intel_plane(plane_state->base.plane))) { 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_audio.c b/drivers/gpu/drm/i915/intel_audio.c index ae55a6865d5c..0571aa2846a7 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -758,7 +758,7 @@ static void i915_audio_component_codec_wake_override(struct device *kdev, struct drm_i915_private *dev_priv = kdev_to_i915(kdev); u32 tmp; - if (!IS_GEN9(dev_priv)) + if (!IS_GEN(dev_priv, 9)) return; i915_audio_component_get_power(kdev); diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c index 0694aa8bb9bc..764d84d4109b 100644 --- a/drivers/gpu/drm/i915/intel_bios.c +++ b/drivers/gpu/drm/i915/intel_bios.c @@ -453,7 +453,7 @@ parse_sdvo_device_mapping(struct drm_i915_private *dev_priv, u8 bdb_version) * Only parse SDVO mappings on gens that could have SDVO. This isn't * accurate and doesn't have to be, as long as it's not too strict. */ - if (!IS_GEN(dev_priv, 3, 7)) { + if (!IS_GEN_RANGE(dev_priv, 3, 7)) { DRM_DEBUG_KMS("Skipping SDVO device mapping\n"); return; } @@ -1386,8 +1386,15 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port, info->supports_dp = is_dp; info->supports_edp = is_edp; - DRM_DEBUG_KMS("Port %c VBT info: DP:%d HDMI:%d DVI:%d EDP:%d CRT:%d\n", - port_name(port), is_dp, is_hdmi, is_dvi, is_edp, is_crt); + if (bdb_version >= 195) + info->supports_typec_usb = child->dp_usb_type_c; + + if (bdb_version >= 209) + info->supports_tbt = child->tbt; + + DRM_DEBUG_KMS("Port %c VBT info: DP:%d HDMI:%d DVI:%d EDP:%d CRT:%d TCUSB:%d TBT:%d\n", + port_name(port), is_dp, is_hdmi, is_dvi, is_edp, is_crt, + info->supports_typec_usb, info->supports_tbt); if (is_edp && is_dvi) DRM_DEBUG_KMS("Internal DP port %c is TMDS compatible\n", @@ -1752,7 +1759,7 @@ 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..4ed7105d7ff5 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) { @@ -170,12 +166,6 @@ static void irq_enable(struct intel_engine_cs *engine) */ GEM_BUG_ON(!intel_irqs_enabled(engine->i915)); - /* Enabling the IRQ may miss the generation of the interrupt, but - * we still need to force the barrier before reading the seqno, - * just in case. - */ - set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); - /* Caller disables interrupts */ if (engine->irq_enable) { spin_lock(&engine->i915->irq_lock); @@ -687,16 +677,6 @@ static int intel_breadcrumbs_signaler(void *arg) } if (unlikely(do_schedule)) { - /* Before we sleep, check for a missed seqno */ - if (current->state & TASK_NORMAL && - !list_empty(&b->signals) && - engine->irq_seqno_barrier && - test_and_clear_bit(ENGINE_IRQ_BREADCRUMB, - &engine->irq_posted)) { - engine->irq_seqno_barrier(engine); - intel_engine_wakeup(engine); - } - sleep: if (kthread_should_park()) kthread_parkme(); @@ -863,16 +843,6 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine) else irq_disable(engine); - /* - * We set the IRQ_BREADCRUMB bit when we enable the irq presuming the - * GPU is active and may have already executed the MI_USER_INTERRUPT - * before the CPU is ready to receive. However, the engine is currently - * idle (we haven't started it yet), there is no possibility for a - * missed interrupt as we enabled the irq and so we can clear the - * immediate wakeup (until a real interrupt arrives for the waiter). - */ - clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); - spin_unlock_irqrestore(&b->irq_lock, flags); } diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 25e3aba9cded..2021e484a287 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2140,7 +2140,7 @@ static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv, { if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return DIV_ROUND_UP(pixel_rate, 2); - else if (IS_GEN9(dev_priv) || + else if (IS_GEN(dev_priv, 9) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return pixel_rate; else if (IS_CHERRYVIEW(dev_priv)) @@ -2176,7 +2176,7 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) { /* Display WA #1145: glk,cnl */ min_cdclk = max(316800, min_cdclk); - } else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv)) { + } else if (IS_GEN(dev_priv, 9) || IS_BROADWELL(dev_priv)) { /* Display WA #1144: skl,bxt */ min_cdclk = max(432000, min_cdclk); } @@ -2537,7 +2537,7 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 2 * max_cdclk_freq; - else if (IS_GEN9(dev_priv) || + else if (IS_GEN(dev_priv, 9) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return max_cdclk_freq; else if (IS_CHERRYVIEW(dev_priv)) @@ -2785,9 +2785,9 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv) dev_priv->display.get_cdclk = hsw_get_cdclk; else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) dev_priv->display.get_cdclk = vlv_get_cdclk; - else if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) + else if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) dev_priv->display.get_cdclk = fixed_400mhz_get_cdclk; - else if (IS_GEN5(dev_priv)) + else if (IS_GEN(dev_priv, 5)) dev_priv->display.get_cdclk = fixed_450mhz_get_cdclk; else if (IS_GM45(dev_priv)) dev_priv->display.get_cdclk = gm45_get_cdclk; diff --git a/drivers/gpu/drm/i915/intel_color.c b/drivers/gpu/drm/i915/intel_color.c index 5127da286a2b..37fd9ddf762e 100644 --- a/drivers/gpu/drm/i915/intel_color.c +++ b/drivers/gpu/drm/i915/intel_color.c @@ -74,12 +74,17 @@ #define ILK_CSC_COEFF_1_0 \ ((7 << 12) | ILK_CSC_COEFF_FP(CTM_COEFF_1_0, 8)) -static bool crtc_state_is_legacy_gamma(struct drm_crtc_state *state) +static bool lut_is_legacy(struct drm_property_blob *lut) { - return !state->degamma_lut && - !state->ctm && - state->gamma_lut && - drm_color_lut_size(state->gamma_lut) == LEGACY_LUT_LENGTH; + return drm_color_lut_size(lut) == LEGACY_LUT_LENGTH; +} + +static bool crtc_state_is_legacy_gamma(struct intel_crtc_state *crtc_state) +{ + return !crtc_state->base.degamma_lut && + !crtc_state->base.ctm && + crtc_state->base.gamma_lut && + lut_is_legacy(crtc_state->base.gamma_lut); } /* @@ -108,10 +113,10 @@ static u64 *ctm_mult_by_limited(u64 *result, const u64 *input) return result; } -static void ilk_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) +static void ilk_load_ycbcr_conversion_matrix(struct intel_crtc *crtc) { - int pipe = intel_crtc->pipe; - struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); + int pipe = crtc->pipe; + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); I915_WRITE(PIPE_CSC_PREOFF_HI(pipe), 0); I915_WRITE(PIPE_CSC_PREOFF_ME(pipe), 0); @@ -132,14 +137,12 @@ static void ilk_load_ycbcr_conversion_matrix(struct intel_crtc *intel_crtc) I915_WRITE(PIPE_CSC_MODE(pipe), 0); } -static void ilk_load_csc_matrix(struct drm_crtc_state *crtc_state) +static void ilk_load_csc_matrix(struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = crtc_state->crtc; - struct drm_i915_private *dev_priv = to_i915(crtc->dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - int i, pipe = intel_crtc->pipe; + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + int i, pipe = crtc->pipe; uint16_t coeffs[9] = { 0, }; - struct intel_crtc_state *intel_crtc_state = to_intel_crtc_state(crtc_state); bool limited_color_range = false; /* @@ -147,14 +150,14 @@ static void ilk_load_csc_matrix(struct drm_crtc_state *crtc_state) * do the range compression using the gamma LUT instead. */ if (INTEL_GEN(dev_priv) >= 8 || IS_HASWELL(dev_priv)) - limited_color_range = intel_crtc_state->limited_color_range; + limited_color_range = crtc_state->limited_color_range; - if (intel_crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 || - intel_crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444) { - ilk_load_ycbcr_conversion_matrix(intel_crtc); + if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 || + crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444) { + ilk_load_ycbcr_conversion_matrix(crtc); return; - } else if (crtc_state->ctm) { - struct drm_color_ctm *ctm = crtc_state->ctm->data; + } else if (crtc_state->base.ctm) { + struct drm_color_ctm *ctm = crtc_state->base.ctm->data; const u64 *input; u64 temp[9]; @@ -253,16 +256,15 @@ static void ilk_load_csc_matrix(struct drm_crtc_state *crtc_state) /* * Set up the pipe CSC unit on CherryView. */ -static void cherryview_load_csc_matrix(struct drm_crtc_state *state) +static void cherryview_load_csc_matrix(struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = state->crtc; - struct drm_device *dev = crtc->dev; + struct drm_device *dev = crtc_state->base.crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); - int pipe = to_intel_crtc(crtc)->pipe; + int pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; uint32_t mode; - if (state->ctm) { - struct drm_color_ctm *ctm = state->ctm->data; + if (crtc_state->base.ctm) { + struct drm_color_ctm *ctm = crtc_state->base.ctm->data; uint16_t coeffs[9] = { 0, }; int i; @@ -293,17 +295,17 @@ static void cherryview_load_csc_matrix(struct drm_crtc_state *state) I915_WRITE(CGM_PIPE_CSC_COEFF8(pipe), coeffs[8]); } - mode = (state->ctm ? CGM_PIPE_MODE_CSC : 0); - if (!crtc_state_is_legacy_gamma(state)) { - mode |= (state->degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | - (state->gamma_lut ? CGM_PIPE_MODE_GAMMA : 0); + mode = (crtc_state->base.ctm ? CGM_PIPE_MODE_CSC : 0); + if (!crtc_state_is_legacy_gamma(crtc_state)) { + mode |= (crtc_state->base.degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | + (crtc_state->base.gamma_lut ? CGM_PIPE_MODE_GAMMA : 0); } I915_WRITE(CGM_PIPE_MODE(pipe), mode); } -void intel_color_set_csc(struct drm_crtc_state *crtc_state) +void intel_color_set_csc(struct intel_crtc_state *crtc_state) { - struct drm_device *dev = crtc_state->crtc->dev; + struct drm_device *dev = crtc_state->base.crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); if (dev_priv->display.load_csc_matrix) @@ -311,14 +313,12 @@ void intel_color_set_csc(struct drm_crtc_state *crtc_state) } /* Loads the legacy palette/gamma unit for the CRTC. */ -static void i9xx_load_luts_internal(struct drm_crtc *crtc, - struct drm_property_blob *blob, - struct intel_crtc_state *crtc_state) +static void i9xx_load_luts_internal(struct intel_crtc_state *crtc_state, + struct drm_property_blob *blob) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - enum pipe pipe = intel_crtc->pipe; + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; int i; if (HAS_GMCH_DISPLAY(dev_priv)) { @@ -353,53 +353,48 @@ static void i9xx_load_luts_internal(struct drm_crtc *crtc, } } -static void i9xx_load_luts(struct drm_crtc_state *crtc_state) +static void i9xx_load_luts(struct intel_crtc_state *crtc_state) { - i9xx_load_luts_internal(crtc_state->crtc, crtc_state->gamma_lut, - to_intel_crtc_state(crtc_state)); + i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut); } /* Loads the legacy palette/gamma unit for the CRTC on Haswell. */ -static void haswell_load_luts(struct drm_crtc_state *crtc_state) +static void haswell_load_luts(struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = crtc_state->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 *intel_crtc_state = - to_intel_crtc_state(crtc_state); + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); bool reenable_ips = false; /* * Workaround : Do not read or write the pipe palette/gamma data while * GAMMA_MODE is configured for split gamma and IPS_CTL has IPS enabled. */ - if (IS_HASWELL(dev_priv) && intel_crtc_state->ips_enabled && - (intel_crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)) { - hsw_disable_ips(intel_crtc_state); + if (IS_HASWELL(dev_priv) && crtc_state->ips_enabled && + (crtc_state->gamma_mode == GAMMA_MODE_MODE_SPLIT)) { + hsw_disable_ips(crtc_state); reenable_ips = true; } - intel_crtc_state->gamma_mode = GAMMA_MODE_MODE_8BIT; - I915_WRITE(GAMMA_MODE(intel_crtc->pipe), GAMMA_MODE_MODE_8BIT); + crtc_state->gamma_mode = GAMMA_MODE_MODE_8BIT; + I915_WRITE(GAMMA_MODE(crtc->pipe), GAMMA_MODE_MODE_8BIT); i9xx_load_luts(crtc_state); if (reenable_ips) - hsw_enable_ips(intel_crtc_state); + hsw_enable_ips(crtc_state); } -static void bdw_load_degamma_lut(struct drm_crtc_state *state) +static void bdw_load_degamma_lut(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(state->crtc->dev); - enum pipe pipe = to_intel_crtc(state->crtc)->pipe; + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; uint32_t i, lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size; I915_WRITE(PREC_PAL_INDEX(pipe), PAL_PREC_SPLIT_MODE | PAL_PREC_AUTO_INCREMENT); - if (state->degamma_lut) { - struct drm_color_lut *lut = state->degamma_lut->data; + if (crtc_state->base.degamma_lut) { + struct drm_color_lut *lut = crtc_state->base.degamma_lut->data; for (i = 0; i < lut_size; i++) { uint32_t word = @@ -419,10 +414,10 @@ static void bdw_load_degamma_lut(struct drm_crtc_state *state) } } -static void bdw_load_gamma_lut(struct drm_crtc_state *state, u32 offset) +static void bdw_load_gamma_lut(struct intel_crtc_state *crtc_state, u32 offset) { - struct drm_i915_private *dev_priv = to_i915(state->crtc->dev); - enum pipe pipe = to_intel_crtc(state->crtc)->pipe; + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; uint32_t i, lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size; WARN_ON(offset & ~PAL_PREC_INDEX_VALUE_MASK); @@ -432,8 +427,8 @@ static void bdw_load_gamma_lut(struct drm_crtc_state *state, u32 offset) PAL_PREC_AUTO_INCREMENT | offset); - if (state->gamma_lut) { - struct drm_color_lut *lut = state->gamma_lut->data; + if (crtc_state->base.gamma_lut) { + struct drm_color_lut *lut = crtc_state->base.gamma_lut->data; for (i = 0; i < lut_size; i++) { uint32_t word = @@ -467,22 +462,21 @@ static void bdw_load_gamma_lut(struct drm_crtc_state *state, u32 offset) } /* Loads the palette/gamma unit for the CRTC on Broadwell+. */ -static void broadwell_load_luts(struct drm_crtc_state *state) +static void broadwell_load_luts(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(state->crtc->dev); - struct intel_crtc_state *intel_state = to_intel_crtc_state(state); - enum pipe pipe = to_intel_crtc(state->crtc)->pipe; + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; - if (crtc_state_is_legacy_gamma(state)) { - haswell_load_luts(state); + if (crtc_state_is_legacy_gamma(crtc_state)) { + haswell_load_luts(crtc_state); return; } - bdw_load_degamma_lut(state); - bdw_load_gamma_lut(state, + bdw_load_degamma_lut(crtc_state); + bdw_load_gamma_lut(crtc_state, INTEL_INFO(dev_priv)->color.degamma_lut_size); - intel_state->gamma_mode = GAMMA_MODE_MODE_SPLIT; + crtc_state->gamma_mode = GAMMA_MODE_MODE_SPLIT; I915_WRITE(GAMMA_MODE(pipe), GAMMA_MODE_MODE_SPLIT); POSTING_READ(GAMMA_MODE(pipe)); @@ -493,10 +487,10 @@ static void broadwell_load_luts(struct drm_crtc_state *state) I915_WRITE(PREC_PAL_INDEX(pipe), 0); } -static void glk_load_degamma_lut(struct drm_crtc_state *state) +static void glk_load_degamma_lut(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(state->crtc->dev); - enum pipe pipe = to_intel_crtc(state->crtc)->pipe; + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; const uint32_t lut_size = 33; uint32_t i; @@ -523,49 +517,46 @@ static void glk_load_degamma_lut(struct drm_crtc_state *state) I915_WRITE(PRE_CSC_GAMC_DATA(pipe), (1 << 16)); } -static void glk_load_luts(struct drm_crtc_state *state) +static void glk_load_luts(struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = state->crtc; - struct drm_device *dev = crtc->dev; + struct drm_device *dev = crtc_state->base.crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_crtc_state *intel_state = to_intel_crtc_state(state); - enum pipe pipe = to_intel_crtc(crtc)->pipe; + enum pipe pipe = to_intel_crtc(crtc_state->base.crtc)->pipe; - glk_load_degamma_lut(state); + glk_load_degamma_lut(crtc_state); - if (crtc_state_is_legacy_gamma(state)) { - haswell_load_luts(state); + if (crtc_state_is_legacy_gamma(crtc_state)) { + haswell_load_luts(crtc_state); return; } - bdw_load_gamma_lut(state, 0); + bdw_load_gamma_lut(crtc_state, 0); - intel_state->gamma_mode = GAMMA_MODE_MODE_10BIT; + crtc_state->gamma_mode = GAMMA_MODE_MODE_10BIT; I915_WRITE(GAMMA_MODE(pipe), GAMMA_MODE_MODE_10BIT); POSTING_READ(GAMMA_MODE(pipe)); } /* Loads the palette/gamma unit for the CRTC on CherryView. */ -static void cherryview_load_luts(struct drm_crtc_state *state) +static void cherryview_load_luts(struct intel_crtc_state *crtc_state) { - struct drm_crtc *crtc = state->crtc; + struct drm_crtc *crtc = crtc_state->base.crtc; struct drm_i915_private *dev_priv = to_i915(crtc->dev); enum pipe pipe = to_intel_crtc(crtc)->pipe; struct drm_color_lut *lut; uint32_t i, lut_size; uint32_t word0, word1; - if (crtc_state_is_legacy_gamma(state)) { + if (crtc_state_is_legacy_gamma(crtc_state)) { /* Turn off degamma/gamma on CGM block. */ I915_WRITE(CGM_PIPE_MODE(pipe), - (state->ctm ? CGM_PIPE_MODE_CSC : 0)); - i9xx_load_luts_internal(crtc, state->gamma_lut, - to_intel_crtc_state(state)); + (crtc_state->base.ctm ? CGM_PIPE_MODE_CSC : 0)); + i9xx_load_luts_internal(crtc_state, crtc_state->base.gamma_lut); return; } - if (state->degamma_lut) { - lut = state->degamma_lut->data; + if (crtc_state->base.degamma_lut) { + lut = crtc_state->base.degamma_lut->data; lut_size = INTEL_INFO(dev_priv)->color.degamma_lut_size; for (i = 0; i < lut_size; i++) { /* Write LUT in U0.14 format. */ @@ -579,8 +570,8 @@ static void cherryview_load_luts(struct drm_crtc_state *state) } } - if (state->gamma_lut) { - lut = state->gamma_lut->data; + if (crtc_state->base.gamma_lut) { + lut = crtc_state->base.gamma_lut->data; lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size; for (i = 0; i < lut_size; i++) { /* Write LUT in U0.10 format. */ @@ -595,29 +586,28 @@ static void cherryview_load_luts(struct drm_crtc_state *state) } I915_WRITE(CGM_PIPE_MODE(pipe), - (state->ctm ? CGM_PIPE_MODE_CSC : 0) | - (state->degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | - (state->gamma_lut ? CGM_PIPE_MODE_GAMMA : 0)); + (crtc_state->base.ctm ? CGM_PIPE_MODE_CSC : 0) | + (crtc_state->base.degamma_lut ? CGM_PIPE_MODE_DEGAMMA : 0) | + (crtc_state->base.gamma_lut ? CGM_PIPE_MODE_GAMMA : 0)); /* * Also program a linear LUT in the legacy block (behind the * CGM block). */ - i9xx_load_luts_internal(crtc, NULL, to_intel_crtc_state(state)); + i9xx_load_luts_internal(crtc_state, NULL); } -void intel_color_load_luts(struct drm_crtc_state *crtc_state) +void intel_color_load_luts(struct intel_crtc_state *crtc_state) { - struct drm_device *dev = crtc_state->crtc->dev; + struct drm_device *dev = crtc_state->base.crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); dev_priv->display.load_luts(crtc_state); } -int intel_color_check(struct drm_crtc *crtc, - struct drm_crtc_state *crtc_state) +int intel_color_check(struct intel_crtc_state *crtc_state) { - struct drm_i915_private *dev_priv = to_i915(crtc->dev); + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); size_t gamma_length, degamma_length; degamma_length = INTEL_INFO(dev_priv)->color.degamma_lut_size; @@ -627,10 +617,10 @@ int intel_color_check(struct drm_crtc *crtc, * We allow both degamma & gamma luts at the right size or * NULL. */ - if ((!crtc_state->degamma_lut || - drm_color_lut_size(crtc_state->degamma_lut) == degamma_length) && - (!crtc_state->gamma_lut || - drm_color_lut_size(crtc_state->gamma_lut) == gamma_length)) + if ((!crtc_state->base.degamma_lut || + drm_color_lut_size(crtc_state->base.degamma_lut) == degamma_length) && + (!crtc_state->base.gamma_lut || + drm_color_lut_size(crtc_state->base.gamma_lut) == gamma_length)) return 0; /* @@ -643,11 +633,11 @@ int intel_color_check(struct drm_crtc *crtc, return -EINVAL; } -void intel_color_init(struct drm_crtc *crtc) +void intel_color_init(struct intel_crtc *crtc) { - struct drm_i915_private *dev_priv = to_i915(crtc->dev); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - drm_mode_crtc_set_gamma_size(crtc, 256); + drm_mode_crtc_set_gamma_size(&crtc->base, 256); if (IS_CHERRYVIEW(dev_priv)) { dev_priv->display.load_csc_matrix = cherryview_load_csc_matrix; @@ -669,7 +659,7 @@ void intel_color_init(struct drm_crtc *crtc) /* Enable color management support when we have degamma & gamma LUTs. */ if (INTEL_INFO(dev_priv)->color.degamma_lut_size != 0 && INTEL_INFO(dev_priv)->color.gamma_lut_size != 0) - drm_crtc_enable_color_mgmt(crtc, + drm_crtc_enable_color_mgmt(&crtc->base, INTEL_INFO(dev_priv)->color.degamma_lut_size, true, INTEL_INFO(dev_priv)->color.gamma_lut_size); diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 68f2fb89ece3..0a41e58d61de 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -322,7 +322,7 @@ intel_crt_mode_valid(struct drm_connector *connector, * DAC limit supposedly 355 MHz. */ max_clock = 270000; - else if (IS_GEN3(dev_priv) || IS_GEN4(dev_priv)) + else if (IS_GEN_RANGE(dev_priv, 3, 4)) max_clock = 400000; else max_clock = 350000; @@ -666,7 +666,7 @@ intel_crt_load_detect(struct intel_crt *crt, uint32_t pipe) /* Set the border color to purple. */ I915_WRITE(bclrpat_reg, 0x500050); - if (!IS_GEN2(dev_priv)) { + if (!IS_GEN(dev_priv, 2)) { uint32_t pipeconf = I915_READ(pipeconf_reg); I915_WRITE(pipeconf_reg, pipeconf | PIPECONF_FORCE_BORDER); POSTING_READ(pipeconf_reg); @@ -981,7 +981,7 @@ void intel_crt_init(struct drm_i915_private *dev_priv) else crt->base.crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) connector->interlace_allowed = 0; else connector->interlace_allowed = 1; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index ad11540ac436..2d6ed990a232 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 */ @@ -493,103 +494,58 @@ static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = { { 0x2, 0x7F, 0x3F, 0x00, 0x00 }, /* 400 400 0.0 */ }; -struct icl_combo_phy_ddi_buf_trans { - u32 dw2_swing_select; - u32 dw2_swing_scalar; - u32 dw4_scaling; -}; - -/* Voltage Swing Programming for VccIO 0.85V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_85V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0xB, 0x70, 0x0018 }, /* 600 0.0 */ - { 0xB, 0x70, 0x3015 }, /* 600 3.5 */ - { 0xB, 0x70, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x00, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x00, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ -}; - -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.85V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_85V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ -}; - -/* Voltage Swing Programming for VccIO 0.95V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_95V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x76, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x76, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +/* icl_combo_phy_ddi_translations */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.95V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_95V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2[] = { + /* NT mV Trans mV db */ + { 0x0, 0x7F, 0x3F, 0x00, 0x00 }, /* 200 200 0.0 */ + { 0x8, 0x7F, 0x38, 0x00, 0x07 }, /* 200 250 1.9 */ + { 0x1, 0x7F, 0x33, 0x00, 0x0C }, /* 200 300 3.5 */ + { 0x9, 0x7F, 0x31, 0x00, 0x0E }, /* 200 350 4.9 */ + { 0x8, 0x7F, 0x3F, 0x00, 0x00 }, /* 250 250 0.0 */ + { 0x1, 0x7F, 0x38, 0x00, 0x07 }, /* 250 300 1.6 */ + { 0x9, 0x7F, 0x35, 0x00, 0x0A }, /* 250 350 2.9 */ + { 0x1, 0x7F, 0x3F, 0x00, 0x00 }, /* 300 300 0.0 */ + { 0x9, 0x7F, 0x38, 0x00, 0x07 }, /* 300 350 1.3 */ + { 0x9, 0x7F, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ }; -/* Voltage Swing Programming for VccIO 1.05V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_1_05V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x71, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x71, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr3[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 1.05V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_1_05V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = { + /* NT mV Trans mV db */ + { 0xA, 0x60, 0x3F, 0x00, 0x00 }, /* 450 450 0.0 */ + { 0xB, 0x73, 0x36, 0x00, 0x09 }, /* 450 650 3.2 */ + { 0x6, 0x7F, 0x31, 0x00, 0x0E }, /* 450 850 5.5 */ + { 0xB, 0x73, 0x3F, 0x00, 0x00 }, /* 650 650 0.0 ALS */ + { 0x6, 0x7F, 0x37, 0x00, 0x08 }, /* 650 850 2.3 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 850 850 0.0 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 850 3.0 */ }; struct icl_mg_phy_ddi_buf_trans { @@ -870,43 +826,23 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) } } -static const struct icl_combo_phy_ddi_buf_trans * +static const struct cnl_ddi_buf_trans * icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port, - int type, int *n_entries) + int type, int rate, int *n_entries) { - u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK; - - if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V); - return icl_combo_phy_ddi_translations_edp_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V); - return icl_combo_phy_ddi_translations_edp_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V); - return icl_combo_phy_ddi_translations_edp_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } - } else { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V); - return icl_combo_phy_ddi_translations_dp_hdmi_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } + if (type == INTEL_OUTPUT_HDMI) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + } else if (rate > 540000 && type == INTEL_OUTPUT_EDP) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; } + + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2); + return icl_combo_phy_ddi_translations_dp_hbr2; } static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) @@ -917,8 +853,8 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) - icl_get_combo_buf_trans(dev_priv, port, - INTEL_OUTPUT_HDMI, &n_entries); + icl_get_combo_buf_trans(dev_priv, port, INTEL_OUTPUT_HDMI, + 0, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); default_entry = n_entries - 1; @@ -1360,11 +1296,14 @@ static int skl_calc_wrpll_link(struct drm_i915_private *dev_priv, dco_freq += (((cfgcr1_val & DPLL_CFGCR1_DCO_FRACTION_MASK) >> 9) * 24 * 1000) / 0x8000; + if (WARN_ON(p0 == 0 || p1 == 0 || p2 == 0)) + return 0; + 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; @@ -1879,7 +1818,7 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) temp |= TRANS_DDI_MODE_SELECT_DVI; if (crtc_state->hdmi_scrambling) - temp |= TRANS_DDI_HDMI_SCRAMBLING_MASK; + temp |= TRANS_DDI_HDMI_SCRAMBLING; if (crtc_state->hdmi_high_tmds_clock_ratio) temp |= TRANS_DDI_HIGH_TMDS_CHAR_RATE; } else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG)) { @@ -2154,6 +2093,12 @@ 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; } @@ -2268,13 +2213,14 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder, u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = encoder->port; int n_entries; if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) icl_get_combo_buf_trans(dev_priv, port, encoder->type, - &n_entries); + intel_dp->link_rate, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); } else if (IS_CANNONLAKE(dev_priv)) { @@ -2455,14 +2401,15 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, } static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) + u32 level, enum port port, int type, + int rate) { - const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL; + const struct cnl_ddi_buf_trans *ddi_translations = NULL; u32 n_entries, val; int ln; ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type, - &n_entries); + rate, &n_entries); if (!ddi_translations) return; @@ -2471,34 +2418,23 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, level = n_entries - 1; } - /* Set PORT_TX_DW5 Rterm Sel to 110b. */ + /* Set PORT_TX_DW5 */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - val &= ~RTERM_SELECT_MASK; + val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | + TAP2_DISABLE | TAP3_DISABLE); + val |= SCALING_MODE_SEL(0x2); val |= RTERM_SELECT(0x6); - I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); - - /* Program PORT_TX_DW5 */ - val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - /* Set DisableTap2 and DisableTap3 if MIPI DSI - * Clear DisableTap2 and DisableTap3 for all other Ports - */ - if (type == INTEL_OUTPUT_DSI) { - val |= TAP2_DISABLE; - val |= TAP3_DISABLE; - } else { - val &= ~TAP2_DISABLE; - val &= ~TAP3_DISABLE; - } + val |= TAP3_DISABLE; I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* Program PORT_TX_DW2 */ val = I915_READ(ICL_PORT_TX_DW2_LN0(port)); val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select); - val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select); + val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel); + val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel); /* Program Rcomp scalar for every table entry */ - val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar); + val |= RCOMP_SCALAR(0x98); I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val); /* Program PORT_TX_DW4 */ @@ -2507,9 +2443,17 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK); - val |= ddi_translations[level].dw4_scaling; + val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1); + val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2); + val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff); I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); } + + /* Program PORT_TX_DW7 */ + val = I915_READ(ICL_PORT_TX_DW7_LN0(port)); + val &= ~N_SCALAR_MASK; + val |= N_SCALAR(ddi_translations[level].dw7_n_scalar); + I915_WRITE(ICL_PORT_TX_DW7_GRP(port), val); } static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, @@ -2574,7 +2518,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* 5. Program swing and de-emphasis */ - icl_ddi_combo_vswing_program(dev_priv, level, port, type); + icl_ddi_combo_vswing_program(dev_priv, level, port, type, rate); /* 6. Set training enable to trigger update */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); @@ -2785,77 +2729,54 @@ 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 +2785,6 @@ 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 +2798,52 @@ 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 +3046,53 @@ 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 +3131,21 @@ 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 +3212,9 @@ 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 +3235,8 @@ 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 +3255,9 @@ 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 +3281,7 @@ 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 +3304,7 @@ 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 +3317,8 @@ 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 +3338,9 @@ 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 +3360,7 @@ 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 +3507,9 @@ 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, @@ -3521,6 +3540,24 @@ static void intel_disable_ddi(struct intel_encoder *encoder, intel_disable_ddi_dp(encoder, old_crtc_state, old_conn_state); } +static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); + + intel_psr_enable(intel_dp, crtc_state); + intel_edp_drrs_enable(intel_dp, crtc_state); +} + +static void intel_ddi_update_pipe(struct intel_encoder *encoder, + const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) + intel_ddi_update_pipe_dp(encoder, crtc_state, conn_state); +} + static void intel_ddi_set_fia_lane_count(struct intel_encoder *encoder, const struct intel_crtc_state *pipe_config, enum port port) @@ -3711,8 +3748,7 @@ void intel_ddi_get_config(struct intel_encoder *encoder, if (intel_dig_port->infoframe_enabled(encoder, pipe_config)) pipe_config->has_infoframe = true; - if ((temp & TRANS_DDI_HDMI_SCRAMBLING_MASK) == - TRANS_DDI_HDMI_SCRAMBLING_MASK) + if (temp & TRANS_DDI_HDMI_SCRAMBLING) pipe_config->hdmi_scrambling = true; if (temp & TRANS_DDI_HIGH_TMDS_CHAR_RATE) pipe_config->hdmi_high_tmds_clock_ratio = true; @@ -3819,9 +3855,50 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } +static void intel_ddi_encoder_suspend(struct intel_encoder *encoder) +{ + struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + + intel_dp_encoder_suspend(encoder); + + /* + * TODO: disconnect also from USB DP alternate mode once we have a + * way to handle the modeset restore in that mode during resume + * even if the sink has disappeared while being suspended. + */ + if (dig_port->tc_legacy_port) + icl_tc_phy_disconnect(i915, dig_port); +} + +static void intel_ddi_encoder_reset(struct drm_encoder *drm_encoder) +{ + struct intel_digital_port *dig_port = enc_to_dig_port(drm_encoder); + struct drm_i915_private *i915 = to_i915(drm_encoder->dev); + + if (intel_port_is_tc(i915, dig_port->base.port)) + intel_digital_port_connected(&dig_port->base); + + intel_dp_encoder_reset(drm_encoder); +} + +static void intel_ddi_encoder_destroy(struct drm_encoder *encoder) +{ + struct intel_digital_port *dig_port = enc_to_dig_port(encoder); + struct drm_i915_private *i915 = to_i915(encoder->dev); + + intel_dp_encoder_flush_work(encoder); + + if (intel_port_is_tc(i915, dig_port->base.port)) + icl_tc_phy_disconnect(i915, dig_port); + + drm_encoder_cleanup(encoder); + kfree(dig_port); +} + static const struct drm_encoder_funcs intel_ddi_funcs = { - .reset = intel_dp_encoder_reset, - .destroy = intel_dp_encoder_destroy, + .reset = intel_ddi_encoder_reset, + .destroy = intel_ddi_encoder_destroy, }; static struct intel_connector * @@ -4065,16 +4142,16 @@ intel_ddi_max_lanes(struct intel_digital_port *intel_dport) void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) { + struct ddi_vbt_port_info *port_info = + &dev_priv->vbt.ddi_port_info[port]; struct intel_digital_port *intel_dig_port; struct intel_encoder *intel_encoder; struct drm_encoder *encoder; bool init_hdmi, init_dp, init_lspcon = false; enum pipe pipe; - - init_hdmi = (dev_priv->vbt.ddi_port_info[port].supports_dvi || - dev_priv->vbt.ddi_port_info[port].supports_hdmi); - init_dp = dev_priv->vbt.ddi_port_info[port].supports_dp; + init_hdmi = port_info->supports_dvi || port_info->supports_hdmi; + init_dp = port_info->supports_dp; if (intel_bios_is_lspcon_present(dev_priv, port)) { /* @@ -4113,9 +4190,10 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) intel_encoder->pre_enable = intel_ddi_pre_enable; intel_encoder->disable = intel_disable_ddi; intel_encoder->post_disable = intel_ddi_post_disable; + intel_encoder->update_pipe = intel_ddi_update_pipe; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; - intel_encoder->suspend = intel_dp_encoder_suspend; + intel_encoder->suspend = intel_ddi_encoder_suspend; intel_encoder->get_power_domains = intel_ddi_get_power_domains; intel_encoder->type = INTEL_OUTPUT_DDI; intel_encoder->power_domain = intel_port_to_power_domain(port); @@ -4134,6 +4212,10 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) intel_dig_port->max_lanes = intel_ddi_max_lanes(intel_dig_port); intel_dig_port->aux_ch = intel_bios_port_aux_ch(dev_priv, port); + intel_dig_port->tc_legacy_port = intel_port_is_tc(dev_priv, port) && + !port_info->supports_typec_usb && + !port_info->supports_tbt; + switch (port) { case PORT_A: intel_dig_port->ddi_io_power_domain = @@ -4192,6 +4274,10 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port) } intel_infoframe_init(intel_dig_port); + + if (intel_port_is_tc(dev_priv, port)) + intel_digital_port_connected(intel_encoder); + return; err: diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index ceecb5bd5226..855a5074ad77 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) @@ -100,7 +104,7 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p) drm_printf(p, "has EU power gating: %s\n", yesno(sseu->has_eu_pg)); } -void intel_device_info_dump_runtime(const struct intel_device_info *info, +void intel_device_info_dump_runtime(const struct intel_runtime_info *info, struct drm_printer *p) { sseu_dump(&info->sseu, p); @@ -109,21 +113,6 @@ void intel_device_info_dump_runtime(const struct intel_device_info *info, info->cs_timestamp_frequency_khz); } -void intel_device_info_dump(const struct intel_device_info *info, - struct drm_printer *p) -{ - struct drm_i915_private *dev_priv = - container_of(info, struct drm_i915_private, info); - - drm_printf(p, "pciid=0x%04x rev=0x%02x platform=%s gen=%i\n", - INTEL_DEVID(dev_priv), - INTEL_REVID(dev_priv), - intel_platform_name(info->platform), - info->gen); - - intel_device_info_dump_flags(info, p); -} - void intel_device_info_dump_topology(const struct sseu_dev_info *sseu, struct drm_printer *p) { @@ -160,7 +149,7 @@ static u16 compute_eu_total(const struct sseu_dev_info *sseu) static void gen11_sseu_info_init(struct drm_i915_private *dev_priv) { - struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; u8 s_en; u32 ss_en, ss_en_mask; u8 eu_en; @@ -199,7 +188,7 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv) static void gen10_sseu_info_init(struct drm_i915_private *dev_priv) { - struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; const u32 fuse2 = I915_READ(GEN8_FUSE2); int s, ss; const int eu_mask = 0xff; @@ -276,7 +265,7 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv) static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv) { - struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; u32 fuse; fuse = I915_READ(CHV_FUSE_GT); @@ -330,7 +319,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv) static void gen9_sseu_info_init(struct drm_i915_private *dev_priv) { struct intel_device_info *info = mkwrite_device_info(dev_priv); - struct sseu_dev_info *sseu = &info->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; int s, ss; u32 fuse2, eu_disable, subslice_mask; const u8 eu_mask = 0xff; @@ -433,7 +422,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv) static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv) { - struct sseu_dev_info *sseu = &mkwrite_device_info(dev_priv)->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; int s, ss; u32 fuse2, subslice_mask, eu_disable[3]; /* s_max */ @@ -515,8 +504,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv) static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) { - struct intel_device_info *info = mkwrite_device_info(dev_priv); - struct sseu_dev_info *sseu = &info->sseu; + struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; u32 fuse1; int s, ss; @@ -524,9 +512,9 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv) * There isn't a register to tell us how many slices/subslices. We * work off the PCI-ids here. */ - switch (info->gt) { + switch (INTEL_INFO(dev_priv)->gt) { default: - MISSING_CASE(info->gt); + MISSING_CASE(INTEL_INFO(dev_priv)->gt); /* fall through */ case 1: sseu->slice_mask = BIT(0); @@ -721,7 +709,7 @@ static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv) /** * intel_device_info_runtime_init - initialize runtime info - * @info: intel device info struct + * @dev_priv: the i915 device * * Determine various intel_device_info fields at runtime. * @@ -735,29 +723,29 @@ static u32 read_timestamp_frequency(struct drm_i915_private *dev_priv) * - after the PCH has been detected, * - before the first usage of the fields it can tweak. */ -void intel_device_info_runtime_init(struct intel_device_info *info) +void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = - container_of(info, struct drm_i915_private, info); + struct intel_device_info *info = mkwrite_device_info(dev_priv); + struct intel_runtime_info *runtime = RUNTIME_INFO(dev_priv); enum pipe pipe; if (INTEL_GEN(dev_priv) >= 10) { for_each_pipe(dev_priv, pipe) - info->num_scalers[pipe] = 2; - } else if (IS_GEN9(dev_priv)) { - info->num_scalers[PIPE_A] = 2; - info->num_scalers[PIPE_B] = 2; - info->num_scalers[PIPE_C] = 1; + runtime->num_scalers[pipe] = 2; + } else if (IS_GEN(dev_priv, 9)) { + runtime->num_scalers[PIPE_A] = 2; + runtime->num_scalers[PIPE_B] = 2; + runtime->num_scalers[PIPE_C] = 1; } BUILD_BUG_ON(I915_NUM_ENGINES > BITS_PER_TYPE(intel_ring_mask_t)); - if (IS_GEN11(dev_priv)) + if (IS_GEN(dev_priv, 11)) for_each_pipe(dev_priv, pipe) - info->num_sprites[pipe] = 6; - else if (IS_GEN10(dev_priv) || IS_GEMINILAKE(dev_priv)) + runtime->num_sprites[pipe] = 6; + else if (IS_GEN(dev_priv, 10) || IS_GEMINILAKE(dev_priv)) for_each_pipe(dev_priv, pipe) - info->num_sprites[pipe] = 3; + runtime->num_sprites[pipe] = 3; else if (IS_BROXTON(dev_priv)) { /* * Skylake and Broxton currently don't expose the topmost plane as its @@ -768,22 +756,22 @@ void intel_device_info_runtime_init(struct intel_device_info *info) * down the line. */ - info->num_sprites[PIPE_A] = 2; - info->num_sprites[PIPE_B] = 2; - info->num_sprites[PIPE_C] = 1; + runtime->num_sprites[PIPE_A] = 2; + runtime->num_sprites[PIPE_B] = 2; + runtime->num_sprites[PIPE_C] = 1; } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { for_each_pipe(dev_priv, pipe) - info->num_sprites[pipe] = 2; + runtime->num_sprites[pipe] = 2; } else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { for_each_pipe(dev_priv, pipe) - info->num_sprites[pipe] = 1; + runtime->num_sprites[pipe] = 1; } if (i915_modparams.disable_display) { DRM_INFO("Display disabled (module parameter)\n"); info->num_pipes = 0; - } else if (info->num_pipes > 0 && - (IS_GEN7(dev_priv) || IS_GEN8(dev_priv)) && + } else if (HAS_DISPLAY(dev_priv) && + (IS_GEN_RANGE(dev_priv, 7, 8)) && HAS_PCH_SPLIT(dev_priv)) { u32 fuse_strap = I915_READ(FUSE_STRAP); u32 sfuse_strap = I915_READ(SFUSE_STRAP); @@ -807,7 +795,7 @@ 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) && INTEL_GEN(dev_priv) >= 9) { u32 dfsm = I915_READ(SKL_DFSM); u8 disabled_mask = 0; bool invalid; @@ -847,20 +835,20 @@ void intel_device_info_runtime_init(struct intel_device_info *info) cherryview_sseu_info_init(dev_priv); else if (IS_BROADWELL(dev_priv)) broadwell_sseu_info_init(dev_priv); - else if (IS_GEN9(dev_priv)) + else if (IS_GEN(dev_priv, 9)) gen9_sseu_info_init(dev_priv); - else if (IS_GEN10(dev_priv)) + else if (IS_GEN(dev_priv, 10)) gen10_sseu_info_init(dev_priv); else if (INTEL_GEN(dev_priv) >= 11) gen11_sseu_info_init(dev_priv); - if (IS_GEN6(dev_priv) && intel_vtd_active()) { + if (IS_GEN(dev_priv, 6) && intel_vtd_active()) { DRM_INFO("Disabling ppGTT for VT-d support\n"); info->ppgtt = INTEL_PPGTT_NONE; } /* Initialize command stream timestamp frequency */ - info->cs_timestamp_frequency_khz = read_timestamp_frequency(dev_priv); + runtime->cs_timestamp_frequency_khz = read_timestamp_frequency(dev_priv); } void intel_driver_caps_print(const struct intel_driver_caps *caps, @@ -880,35 +868,44 @@ void intel_driver_caps_print(const struct intel_driver_caps *caps, void intel_device_info_init_mmio(struct drm_i915_private *dev_priv) { struct intel_device_info *info = mkwrite_device_info(dev_priv); - u32 media_fuse; + unsigned int logical_vdbox = 0; unsigned int i; + u32 media_fuse; if (INTEL_GEN(dev_priv) < 11) return; media_fuse = ~I915_READ(GEN11_GT_VEBOX_VDBOX_DISABLE); - info->vdbox_enable = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK; - info->vebox_enable = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >> - GEN11_GT_VEBOX_DISABLE_SHIFT; + RUNTIME_INFO(dev_priv)->vdbox_enable = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK; + RUNTIME_INFO(dev_priv)->vebox_enable = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >> + GEN11_GT_VEBOX_DISABLE_SHIFT; - DRM_DEBUG_DRIVER("vdbox enable: %04x\n", info->vdbox_enable); + DRM_DEBUG_DRIVER("vdbox enable: %04x\n", RUNTIME_INFO(dev_priv)->vdbox_enable); for (i = 0; i < I915_MAX_VCS; i++) { if (!HAS_ENGINE(dev_priv, _VCS(i))) continue; - if (!(BIT(i) & info->vdbox_enable)) { + if (!(BIT(i) & RUNTIME_INFO(dev_priv)->vdbox_enable)) { info->ring_mask &= ~ENGINE_MASK(_VCS(i)); DRM_DEBUG_DRIVER("vcs%u fused off\n", i); + continue; } + + /* + * In Gen11, only even numbered logical VDBOXes are + * hooked up to an SFC (Scaler & Format Converter) unit. + */ + if (logical_vdbox++ % 2 == 0) + RUNTIME_INFO(dev_priv)->vdbox_sfc_access |= BIT(i); } - DRM_DEBUG_DRIVER("vebox enable: %04x\n", info->vebox_enable); + DRM_DEBUG_DRIVER("vebox enable: %04x\n", RUNTIME_INFO(dev_priv)->vebox_enable); for (i = 0; i < I915_MAX_VECS; i++) { if (!HAS_ENGINE(dev_priv, _VECS(i))) continue; - if (!(BIT(i) & info->vebox_enable)) { + if (!(BIT(i) & RUNTIME_INFO(dev_priv)->vebox_enable)) { info->ring_mask &= ~ENGINE_MASK(_VECS(i)); DRM_DEBUG_DRIVER("vecs%u fused off\n", i); } diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index 88f97210dc49..957c6527f76b 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -89,35 +89,39 @@ 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(gpu_reset_clobbers_display); \ 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 */ @@ -149,12 +153,10 @@ struct sseu_dev_info { typedef u8 intel_ring_mask_t; struct intel_device_info { - u16 device_id; u16 gen_mask; u8 gen; u8 gt; /* GT number, 0 if undefined */ - u8 num_rings; intel_ring_mask_t ring_mask; /* Rings supported by the HW */ enum intel_platform platform; @@ -166,12 +168,17 @@ struct intel_device_info { u32 display_mmio_offset; u8 num_pipes; - u8 num_sprites[I915_MAX_PIPES]; - u8 num_scalers[I915_MAX_PIPES]; #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 */ @@ -179,6 +186,20 @@ struct intel_device_info { int trans_offsets[I915_MAX_TRANSCODERS]; int cursor_offsets[I915_MAX_PIPES]; + struct color_luts { + u16 degamma_lut_size; + u16 gamma_lut_size; + } color; +}; + +struct intel_runtime_info { + u16 device_id; + + u8 num_sprites[I915_MAX_PIPES]; + u8 num_scalers[I915_MAX_PIPES]; + + u8 num_rings; + /* Slice/subslice/EU info */ struct sseu_dev_info sseu; @@ -188,10 +209,8 @@ struct intel_device_info { u8 vdbox_enable; u8 vebox_enable; - struct color_luts { - u16 degamma_lut_size; - u16 gamma_lut_size; - } color; + /* Media engine access to SFC per instance */ + u8 vdbox_sfc_access; }; struct intel_driver_caps { @@ -248,12 +267,10 @@ static inline void sseu_set_eus(struct sseu_dev_info *sseu, const char *intel_platform_name(enum intel_platform platform); -void intel_device_info_runtime_init(struct intel_device_info *info); -void intel_device_info_dump(const struct intel_device_info *info, - struct drm_printer *p); +void intel_device_info_runtime_init(struct drm_i915_private *dev_priv); void intel_device_info_dump_flags(const struct intel_device_info *info, struct drm_printer *p); -void intel_device_info_dump_runtime(const struct intel_device_info *info, +void intel_device_info_dump_runtime(const struct intel_runtime_info *info, struct drm_printer *p); void intel_device_info_dump_topology(const struct sseu_dev_info *sseu, struct drm_printer *p); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 812ec5ae5c7b..699ee6946891 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -984,7 +984,7 @@ static bool pipe_scanline_is_moving(struct drm_i915_private *dev_priv, u32 line1, line2; u32 line_mask; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) line_mask = DSL_LINEMASK_GEN2; else line_mask = DSL_LINEMASK_GEN3; @@ -1110,7 +1110,7 @@ static void assert_fdi_tx_pll_enabled(struct drm_i915_private *dev_priv, u32 val; /* ILK FDI PLL is always enabled */ - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) return; /* On Haswell, DDI ports are responsible for the FDI PLL setup */ @@ -1850,7 +1850,7 @@ static void intel_disable_pipe(const struct intel_crtc_state *old_crtc_state) static unsigned int intel_tile_size(const struct drm_i915_private *dev_priv) { - return IS_GEN2(dev_priv) ? 2048 : 4096; + return IS_GEN(dev_priv, 2) ? 2048 : 4096; } static unsigned int @@ -1863,7 +1863,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) case DRM_FORMAT_MOD_LINEAR: return cpp; case I915_FORMAT_MOD_X_TILED: - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) return 128; else return 512; @@ -1872,7 +1872,7 @@ intel_tile_width_bytes(const struct drm_framebuffer *fb, int color_plane) return 128; /* fall through */ case I915_FORMAT_MOD_Y_TILED: - if (IS_GEN2(dev_priv) || HAS_128_BYTE_Y_TILING(dev_priv)) + if (IS_GEN(dev_priv, 2) || HAS_128_BYTE_Y_TILING(dev_priv)) return 128; else return 512; @@ -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 @@ -3177,8 +3193,8 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state, dspcntr = DISPLAY_PLANE_ENABLE | DISPPLANE_GAMMA_ENABLE; - if (IS_G4X(dev_priv) || IS_GEN5(dev_priv) || - IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) + if (IS_G4X(dev_priv) || IS_GEN(dev_priv, 5) || + IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) dspcntr |= DISPPLANE_TRICKLE_FEED_DISABLE; if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) @@ -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) @@ -3721,8 +3746,8 @@ __intel_display_resume(struct drm_device *dev, static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv) { - return intel_has_gpu_reset(dev_priv) && - INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv); + return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display && + intel_has_gpu_reset(dev_priv)); } void intel_prepare_reset(struct drm_i915_private *dev_priv) @@ -4095,7 +4120,7 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc, temp = I915_READ(reg); temp &= ~FDI_LINK_TRAIN_NONE; temp |= FDI_LINK_TRAIN_PATTERN_2; - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { temp &= ~FDI_LINK_TRAIN_VOL_EMP_MASK; /* SNB-B */ temp |= FDI_LINK_TRAIN_400MV_0DB_SNB_B; @@ -4894,10 +4919,10 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, /* range checks */ if (src_w < SKL_MIN_SRC_W || src_h < SKL_MIN_SRC_H || dst_w < SKL_MIN_DST_W || dst_h < SKL_MIN_DST_H || - (IS_GEN11(dev_priv) && + (IS_GEN(dev_priv, 11) && (src_w > ICL_MAX_SRC_W || src_h > ICL_MAX_SRC_H || dst_w > ICL_MAX_DST_W || dst_h > ICL_MAX_DST_H)) || - (!IS_GEN11(dev_priv) && + (!IS_GEN(dev_priv, 11) && (src_w > SKL_MAX_SRC_W || src_h > SKL_MAX_SRC_H || dst_w > SKL_MAX_DST_W || dst_h > SKL_MAX_DST_H))) { DRM_DEBUG_KMS("scaler_user index %u.%u: src %ux%u dst %ux%u " @@ -5188,7 +5213,7 @@ intel_post_enable_primary(struct drm_crtc *crtc, * FIXME: Need to fix the logic to work when we turn off all planes * but leave the pipe running. */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); /* Underruns don't always raise interrupts, so check manually. */ @@ -5209,7 +5234,7 @@ intel_pre_disable_primary_noatomic(struct drm_crtc *crtc) * Gen2 reports pipe underruns whenever all planes are disabled. * So disable underrun reporting before all the planes get disabled. */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); hsw_disable_ips(to_intel_crtc_state(crtc->state)); @@ -5267,7 +5292,7 @@ static bool needs_nv12_wa(struct drm_i915_private *dev_priv, return false; /* WA Display #0827: Gen9:all */ - if (IS_GEN9(dev_priv) && !IS_GEMINILAKE(dev_priv)) + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) return true; return false; @@ -5340,7 +5365,7 @@ static void intel_pre_plane_update(struct intel_crtc_state *old_crtc_state, * Gen2 reports pipe underruns whenever all planes are disabled. * So disable underrun reporting before all the planes get disabled. */ - if (IS_GEN2(dev_priv) && old_primary_state->visible && + if (IS_GEN(dev_priv, 2) && old_primary_state->visible && (modeset || !new_primary_state->base.visible)) intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, false); } @@ -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, @@ -5544,6 +5578,26 @@ static void intel_encoders_post_pll_disable(struct drm_crtc *crtc, } } +static void intel_encoders_update_pipe(struct drm_crtc *crtc, + struct intel_crtc_state *crtc_state, + struct drm_atomic_state *old_state) +{ + 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); + + if (conn_state->crtc != crtc) + continue; + + if (encoder->update_pipe) + encoder->update_pipe(encoder, crtc_state, conn_state); + } +} + static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config, struct drm_atomic_state *old_state) { @@ -5607,7 +5661,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config, * On ILK+ LUT must be loaded before the pipe is running but with * clocks enabled */ - intel_color_load_luts(&pipe_config->base); + intel_color_load_luts(pipe_config); if (dev_priv->display.initial_watermarks != NULL) dev_priv->display.initial_watermarks(old_intel_state, pipe_config); @@ -5692,9 +5746,6 @@ 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)) @@ -5721,7 +5772,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, haswell_set_pipemisc(pipe_config); - intel_color_set_csc(&pipe_config->base); + intel_color_set_csc(pipe_config); intel_crtc->active = true; @@ -5740,7 +5791,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config, * On ILK+ LUT must be loaded before the pipe is running but with * clocks enabled */ - intel_color_load_luts(&pipe_config->base); + intel_color_load_luts(pipe_config); /* * Display WA #1153: enable hardware to bypass the alpha math @@ -5889,6 +5940,8 @@ 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 +5949,6 @@ 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); } @@ -6087,7 +6137,7 @@ static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config, i9xx_set_pipeconf(pipe_config); - intel_color_set_csc(&pipe_config->base); + intel_color_set_csc(pipe_config); intel_crtc->active = true; @@ -6107,7 +6157,7 @@ static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config, i9xx_pfit_enable(pipe_config); - intel_color_load_luts(&pipe_config->base); + intel_color_load_luts(pipe_config); dev_priv->display.initial_watermarks(old_intel_state, pipe_config); @@ -6154,7 +6204,7 @@ static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config, intel_crtc->active = true; - if (!IS_GEN2(dev_priv)) + if (!IS_GEN(dev_priv, 2)) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true); intel_encoders_pre_enable(crtc, pipe_config, old_state); @@ -6163,7 +6213,7 @@ static void i9xx_crtc_enable(struct intel_crtc_state *pipe_config, i9xx_pfit_enable(pipe_config); - intel_color_load_luts(&pipe_config->base); + intel_color_load_luts(pipe_config); if (dev_priv->display.initial_watermarks != NULL) dev_priv->display.initial_watermarks(old_intel_state, @@ -6206,7 +6256,7 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state, * On gen2 planes are double buffered but the pipe isn't, so we must * wait for planes to fully turn off before disabling the pipe. */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) intel_wait_for_vblank(dev_priv, pipe); intel_encoders_disable(crtc, old_crtc_state, old_state); @@ -6231,7 +6281,7 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_encoders_post_pll_disable(crtc, old_crtc_state, old_state); - if (!IS_GEN2(dev_priv)) + if (!IS_GEN(dev_priv, 2)) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); if (!dev_priv->display.initial_watermarks) @@ -6724,7 +6774,7 @@ 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) @@ -6838,7 +6888,7 @@ static bool transcoder_has_m2_n2(struct drm_i915_private *dev_priv, * Strictly speaking some registers are available before * gen7, but we only support DRRS on gen7+ */ - return IS_GEN7(dev_priv) || IS_CHERRYVIEW(dev_priv); + return IS_GEN(dev_priv, 7) || IS_CHERRYVIEW(dev_priv); } static void intel_cpu_transcoder_set_m_n(const struct intel_crtc_state *crtc_state, @@ -8939,7 +8989,7 @@ 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); @@ -8975,7 +9025,7 @@ static void ironlake_get_pfit_config(struct intel_crtc *crtc, /* We currently do not free assignements of panel fitters on * ivb/hsw (since we don't use the higher upscaling modes which * differentiates them) so just WARN about this case for now. */ - if (IS_GEN7(dev_priv)) { + if (IS_GEN(dev_priv, 7)) { WARN_ON((tmp & PF_PIPE_SEL_MASK_IVB) != PF_PIPE_SEL_IVB(crtc->pipe)); } @@ -9303,10 +9353,12 @@ 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 +9496,18 @@ 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 +9515,49 @@ 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 +9690,8 @@ 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 +9747,7 @@ 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 +9974,9 @@ 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, @@ -9935,7 +10015,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state, struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); u32 cntl = 0; - if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) + if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) cntl |= MCURSOR_TRICKLE_FEED_DISABLE; if (INTEL_GEN(dev_priv) <= 10) { @@ -10087,8 +10167,8 @@ 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 +10178,20 @@ 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 +10207,9 @@ 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, @@ -10403,7 +10488,7 @@ static int i9xx_pll_refclk(struct drm_device *dev, return dev_priv->vbt.lvds_ssc_freq; else if (HAS_PCH_SPLIT(dev_priv)) return 120000; - else if (!IS_GEN2(dev_priv)) + else if (!IS_GEN(dev_priv, 2)) return 96000; else return 48000; @@ -10436,7 +10521,7 @@ static void i9xx_crtc_clock_get(struct intel_crtc *crtc, clock.m2 = (fp & FP_M2_DIV_MASK) >> FP_M2_DIV_SHIFT; } - if (!IS_GEN2(dev_priv)) { + if (!IS_GEN(dev_priv, 2)) { if (IS_PINEVIEW(dev_priv)) clock.p1 = ffs((dpll & DPLL_FPA01_P1_POST_DIV_MASK_PINEVIEW) >> DPLL_FPA01_P1_POST_DIV_SHIFT_PINEVIEW); @@ -10588,20 +10673,17 @@ static void intel_crtc_destroy(struct drm_crtc *crtc) /** * intel_wm_need_update - Check whether watermarks need updating - * @plane: drm plane - * @state: new plane state + * @cur: current plane state + * @new: new plane state * * Check current plane state versus the new one to determine whether * watermarks need to be recalculated. * * Returns true or false. */ -static bool intel_wm_need_update(struct drm_plane *plane, - struct drm_plane_state *state) +static bool intel_wm_need_update(struct intel_plane_state *cur, + struct intel_plane_state *new) { - struct intel_plane_state *new = to_intel_plane_state(state); - struct intel_plane_state *cur = to_intel_plane_state(plane->state); - /* Update watermarks on tiling or size changes. */ if (new->base.visible != cur->base.visible) return true; @@ -10710,7 +10792,8 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat /* must disable cxsr around plane enable/disable */ if (plane->id != PLANE_CURSOR) pipe_config->disable_cxsr = true; - } else if (intel_wm_need_update(&plane->base, plane_state)) { + } else if (intel_wm_need_update(to_intel_plane_state(plane->base.state), + to_intel_plane_state(plane_state))) { if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv)) { /* FIXME bollocks */ pipe_config->update_wm_pre = true; @@ -10752,7 +10835,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat * the w/a on all three platforms. */ if (plane->id == PLANE_SPRITE0 && - (IS_GEN5(dev_priv) || IS_GEN6(dev_priv) || + (IS_GEN_RANGE(dev_priv, 5, 6) || IS_IVYBRIDGE(dev_priv)) && (turn_on || (!needs_scaling(old_plane_state) && needs_scaling(to_intel_plane_state(plane_state))))) @@ -10835,8 +10918,10 @@ 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 +10962,7 @@ 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); } @@ -10886,8 +10972,7 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state) static int intel_crtc_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *crtc_state) { - struct drm_device *dev = crtc->dev; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = to_i915(crtc->dev); struct intel_crtc *intel_crtc = to_intel_crtc(crtc); struct intel_crtc_state *pipe_config = to_intel_crtc_state(crtc_state); @@ -10907,7 +10992,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, } if (crtc_state->color_mgmt_changed) { - ret = intel_color_check(crtc, crtc_state); + ret = intel_color_check(pipe_config); if (ret) return ret; @@ -10936,9 +11021,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, * old state and the new state. We can program these * immediately. */ - ret = dev_priv->display.compute_intermediate_wm(dev, - intel_crtc, - pipe_config); + ret = dev_priv->display.compute_intermediate_wm(pipe_config); if (ret) { DRM_DEBUG_KMS("No valid intermediate pipe watermarks are possible\n"); return ret; @@ -10946,7 +11029,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc, } if (INTEL_GEN(dev_priv) >= 9) { - if (mode_changed) + if (mode_changed || pipe_config->update_pipe) ret = skl_update_scaler_crtc(pipe_config); if (!ret) @@ -11887,6 +11970,8 @@ 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); @@ -11894,9 +11979,11 @@ static void verify_wm_state(struct drm_crtc *crtc, if (INTEL_GEN(dev_priv) < 9 || !new_state->active) return; - skl_pipe_wm_get_hw_state(crtc, &hw_wm); + skl_pipe_wm_get_hw_state(intel_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 +12026,8 @@ 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 +12076,8 @@ 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", @@ -12306,7 +12393,7 @@ static void update_scanline_offset(const struct intel_crtc_state *crtc_state) * However if queried just before the start of vblank we'll get an * answer that's slightly in the future. */ - if (IS_GEN2(dev_priv)) { + if (IS_GEN(dev_priv, 2)) { const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode; int vtotal; @@ -12547,9 +12634,9 @@ static int intel_modeset_checks(struct drm_atomic_state *state) * phase. The code here should be run after the per-crtc and per-plane 'check' * handlers to ensure that all derived state has been updated. */ -static int calc_watermark_data(struct drm_atomic_state *state) +static int calc_watermark_data(struct intel_atomic_state *state) { - struct drm_device *dev = state->dev; + struct drm_device *dev = state->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); /* Is there platform-specific watermark information to calculate? */ @@ -12641,7 +12728,7 @@ static int intel_atomic_check(struct drm_device *dev, return ret; intel_fbc_choose_crtc(dev_priv, intel_state); - return calc_watermark_data(state); + return calc_watermark_data(intel_state); } static int intel_atomic_prepare_commit(struct drm_device *dev, @@ -12668,7 +12755,6 @@ 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 = @@ -12684,15 +12770,22 @@ static void intel_update_crtc(struct drm_crtc *crtc, } else { intel_pre_plane_update(to_intel_crtc_state(old_crtc_state), pipe_config); + + if (pipe_config->update_pipe) + intel_encoders_update_pipe(crtc, pipe_config, state); } - if (new_plane_state) + if (pipe_config->update_pipe && !pipe_config->enable_fbc) + intel_fbc_disable(intel_crtc); + else if (new_plane_state) intel_fbc_enable(intel_crtc, pipe_config, new_plane_state); 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 +12978,7 @@ 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 +13333,7 @@ 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; @@ -13479,8 +13572,8 @@ static void intel_begin_crtc_commit(struct drm_crtc *crtc, if (!modeset && (intel_cstate->base.color_mgmt_changed || intel_cstate->update_pipe)) { - intel_color_set_csc(&intel_cstate->base); - intel_color_load_luts(&intel_cstate->base); + intel_color_set_csc(intel_cstate); + intel_color_load_luts(intel_cstate); } /* Perform vblank evasion around commit operation */ @@ -13505,7 +13598,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc, { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - if (!IS_GEN2(dev_priv)) + if (!IS_GEN(dev_priv, 2)) intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true); if (crtc_state->has_pch_encoder) { @@ -13735,7 +13828,7 @@ 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)); @@ -13967,7 +14060,7 @@ static void intel_crtc_init_scalers(struct intel_crtc *crtc, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); int i; - crtc->num_scalers = dev_priv->info.num_scalers[crtc->pipe]; + crtc->num_scalers = RUNTIME_INFO(dev_priv)->num_scalers[crtc->pipe]; if (!crtc->num_scalers) return; @@ -14053,7 +14146,7 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe) drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs); - intel_color_init(&intel_crtc->base); + intel_color_init(intel_crtc); WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe); @@ -14112,7 +14205,7 @@ static bool has_edp_a(struct drm_i915_private *dev_priv) if ((I915_READ(DP_A) & DP_DETECTED) == 0) return false; - if (IS_GEN5(dev_priv) && (I915_READ(FUSE_STRAP) & ILK_eDP_A_DISABLE)) + if (IS_GEN(dev_priv, 5) && (I915_READ(FUSE_STRAP) & ILK_eDP_A_DISABLE)) return false; return true; @@ -14186,7 +14279,7 @@ 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; /* @@ -14324,7 +14417,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) } vlv_dsi_init(dev_priv); - } else if (!IS_GEN2(dev_priv) && !IS_PINEVIEW(dev_priv)) { + } else if (!IS_GEN(dev_priv, 2) && !IS_PINEVIEW(dev_priv)) { bool found = false; if (I915_READ(GEN3_SDVOB) & SDVO_DETECTED) { @@ -14358,7 +14451,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) if (IS_G4X(dev_priv) && (I915_READ(DP_D) & DP_DETECTED)) intel_dp_init(dev_priv, DP_D, PORT_D); - } else if (IS_GEN2(dev_priv)) + } else if (IS_GEN(dev_priv, 2)) intel_dvo_init(dev_priv); if (SUPPORTS_TV(dev_priv)) @@ -14451,7 +14544,6 @@ 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 +14574,14 @@ 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 +14616,6 @@ 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; @@ -14645,7 +14649,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, * require the entire fb to accommodate that to avoid * potential runtime errors at plane configuration time. */ - if (IS_GEN9(dev_priv) && i == 0 && fb->width > 3840 && + if (IS_GEN(dev_priv, 9) && i == 0 && fb->width > 3840 && is_ccs_modifier(fb->modifier)) stride_alignment *= 4; @@ -14850,7 +14854,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) dev_priv->display.crtc_compute_clock = pnv_crtc_compute_clock; dev_priv->display.crtc_enable = i9xx_crtc_enable; dev_priv->display.crtc_disable = i9xx_crtc_disable; - } else if (!IS_GEN2(dev_priv)) { + } else if (!IS_GEN(dev_priv, 2)) { dev_priv->display.get_pipe_config = i9xx_get_pipe_config; dev_priv->display.get_initial_plane_config = i9xx_get_initial_plane_config; @@ -14866,9 +14870,9 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) dev_priv->display.crtc_disable = i9xx_crtc_disable; } - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { dev_priv->display.fdi_link_train = ironlake_fdi_link_train; - } else if (IS_GEN6(dev_priv)) { + } else if (IS_GEN(dev_priv, 6)) { dev_priv->display.fdi_link_train = gen6_fdi_link_train; } else if (IS_IVYBRIDGE(dev_priv)) { /* FIXME: detect B0+ stepping and use auto training */ @@ -15000,12 +15004,12 @@ fail: static void intel_update_fdi_pll_freq(struct drm_i915_private *dev_priv) { - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { u32 fdi_pll_clk = I915_READ(FDI_PLL_BIOS_0) & FDI_PLL_FB_CLOCK_MASK; dev_priv->fdi_pll_freq = (fdi_pll_clk + 2) * 10000; - } else if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv)) { + } else if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv)) { dev_priv->fdi_pll_freq = 270000; } else { return; @@ -15121,10 +15125,10 @@ int intel_modeset_init(struct drm_device *dev) } /* maximum framebuffer dimensions */ - if (IS_GEN2(dev_priv)) { + if (IS_GEN(dev_priv, 2)) { dev->mode_config.max_width = 2048; dev->mode_config.max_height = 2048; - } else if (IS_GEN3(dev_priv)) { + } else if (IS_GEN(dev_priv, 3)) { dev->mode_config.max_width = 4096; dev->mode_config.max_height = 4096; } else { @@ -15135,7 +15139,7 @@ int intel_modeset_init(struct drm_device *dev) if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) { dev->mode_config.cursor_width = IS_I845G(dev_priv) ? 64 : 512; dev->mode_config.cursor_height = 1023; - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { dev->mode_config.cursor_width = 64; dev->mode_config.cursor_height = 64; } else { @@ -15859,15 +15863,15 @@ intel_modeset_setup_hw_state(struct drm_device *dev, } if (IS_G4X(dev_priv)) { - g4x_wm_get_hw_state(dev); + g4x_wm_get_hw_state(dev_priv); g4x_wm_sanitize(dev_priv); } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - vlv_wm_get_hw_state(dev); + vlv_wm_get_hw_state(dev_priv); vlv_wm_sanitize(dev_priv); } else if (INTEL_GEN(dev_priv) >= 9) { - skl_wm_get_hw_state(dev); + skl_wm_get_hw_state(dev_priv); } else if (HAS_PCH_SPLIT(dev_priv)) { - ilk_wm_get_hw_state(dev); + ilk_wm_get_hw_state(dev_priv); } for_each_intel_crtc(dev, crtc) { @@ -16066,7 +16070,7 @@ 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..c7c068662288 100644 --- a/drivers/gpu/drm/i915/intel_display.h +++ b/drivers/gpu/drm/i915/intel_display.h @@ -121,7 +121,7 @@ enum i9xx_plane_id { }; #define plane_name(p) ((p) + 'A') -#define sprite_name(p, s) ((p) * INTEL_INFO(dev_priv)->num_sprites[(p)] + (s) + 'A') +#define sprite_name(p, s) ((p) * RUNTIME_INFO(dev_priv)->num_sprites[(p)] + (s) + 'A') /* * Per-pipe plane identifier. @@ -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, @@ -310,12 +311,12 @@ struct intel_link_m_n { #define for_each_universal_plane(__dev_priv, __pipe, __p) \ for ((__p) = 0; \ - (__p) < INTEL_INFO(__dev_priv)->num_sprites[(__pipe)] + 1; \ + (__p) < RUNTIME_INFO(__dev_priv)->num_sprites[(__pipe)] + 1; \ (__p)++) #define for_each_sprite(__dev_priv, __p, __s) \ for ((__s) = 0; \ - (__s) < INTEL_INFO(__dev_priv)->num_sprites[(__p)]; \ + (__s) < RUNTIME_INFO(__dev_priv)->num_sprites[(__p)]; \ (__s)++) #define for_each_port_masked(__port, __ports_mask) \ @@ -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..62fd11540942 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 @@ -302,9 +304,11 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp) static int icl_max_source_rate(struct intel_dp *intel_dp) { 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); enum port port = dig_port->base.port; - if (port == PORT_B) + if (intel_port_is_combophy(dev_priv, port) && + !intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -342,7 +346,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) if (INTEL_GEN(dev_priv) >= 10) { source_rates = cnl_rates; size = ARRAY_SIZE(cnl_rates); - if (IS_GEN10(dev_priv)) + if (IS_GEN(dev_priv, 10)) max_rate = cnl_max_source_rate(intel_dp); else max_rate = icl_max_source_rate(intel_dp); @@ -543,7 +547,7 @@ 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, @@ -1126,7 +1130,7 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp, to_i915(intel_dig_port->base.base.dev); uint32_t precharge, timeout; - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) precharge = 3; else precharge = 5; @@ -1708,6 +1712,41 @@ 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 +1881,122 @@ 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 +2035,7 @@ 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 +2045,43 @@ 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 */ + DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en); + if (!ret || intel_dp->force_dsc_en) { + 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 +2147,10 @@ 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 +2168,20 @@ 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) { @@ -2412,7 +2588,7 @@ static void edp_panel_on(struct intel_dp *intel_dp) pp_ctrl_reg = _pp_ctrl_reg(intel_dp); pp = ironlake_get_pp_control(intel_dp); - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { /* ILK workaround: disable reset around power sequence */ pp &= ~PANEL_POWER_RESET; I915_WRITE(pp_ctrl_reg, pp); @@ -2420,7 +2596,7 @@ static void edp_panel_on(struct intel_dp *intel_dp) } pp |= PANEL_POWER_ON; - if (!IS_GEN5(dev_priv)) + if (!IS_GEN(dev_priv, 5)) pp |= PANEL_POWER_RESET; I915_WRITE(pp_ctrl_reg, pp); @@ -2429,7 +2605,7 @@ static void edp_panel_on(struct intel_dp *intel_dp) wait_panel_on(intel_dp); intel_dp->last_power_on = jiffies; - if (IS_GEN5(dev_priv)) { + if (IS_GEN(dev_priv, 5)) { pp |= PANEL_POWER_RESET; /* restore panel reset bit */ I915_WRITE(pp_ctrl_reg, pp); POSTING_READ(pp_ctrl_reg); @@ -2658,7 +2834,7 @@ static void ironlake_edp_pll_on(struct intel_dp *intel_dp, * 1. Wait for the start of vertical blank on the enabled pipe going to FDI * 2. Program DP PLL enable */ - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) intel_wait_for_vblank_if_active(dev_priv, !crtc->pipe); intel_dp->DP |= DP_PLL_ENABLE; @@ -2702,6 +2878,22 @@ 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) { @@ -3660,7 +3852,7 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp) } else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) { signal_levels = ivb_cpu_edp_signal_levels(train_set); mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB; - } else if (IS_GEN6(dev_priv) && port == PORT_A) { + } else if (IS_GEN(dev_priv, 6) && port == PORT_A) { signal_levels = snb_cpu_edp_signal_levels(train_set); mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB; } else { @@ -3802,6 +3994,42 @@ intel_dp_link_down(struct intel_encoder *encoder, } } +static void +intel_dp_extended_receiver_capabilities(struct intel_dp *intel_dp) +{ + u8 dpcd_ext[6]; + + /* + * Prior to DP1.3 the bit represented by + * DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT was reserved. + * if it is set DP_DPCD_REV at 0000h could be at a value less than + * the true capability of the panel. The only way to check is to + * then compare 0000h and 2200h. + */ + if (!(intel_dp->dpcd[DP_TRAINING_AUX_RD_INTERVAL] & + DP_EXTENDED_RECEIVER_CAP_FIELD_PRESENT)) + return; + + if (drm_dp_dpcd_read(&intel_dp->aux, DP_DP13_DPCD_REV, + &dpcd_ext, sizeof(dpcd_ext)) != sizeof(dpcd_ext)) { + DRM_ERROR("DPCD failed read at extended capabilities\n"); + return; + } + + if (intel_dp->dpcd[DP_DPCD_REV] > dpcd_ext[DP_DPCD_REV]) { + DRM_DEBUG_KMS("DPCD extended DPCD rev less than base DPCD rev\n"); + return; + } + + if (!memcmp(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext))) + return; + + DRM_DEBUG_KMS("Base DPCD: %*ph\n", + (int)sizeof(intel_dp->dpcd), intel_dp->dpcd); + + memcpy(intel_dp->dpcd, dpcd_ext, sizeof(dpcd_ext)); +} + bool intel_dp_read_dpcd(struct intel_dp *intel_dp) { @@ -3809,6 +4037,8 @@ intel_dp_read_dpcd(struct intel_dp *intel_dp) sizeof(intel_dp->dpcd)) < 0) return false; /* aux transfer failed */ + intel_dp_extended_receiver_capabilities(intel_dp); + DRM_DEBUG_KMS("DPCD: %*ph\n", (int) sizeof(intel_dp->dpcd), intel_dp->dpcd); return intel_dp->dpcd[DP_DPCD_REV] != 0; @@ -3837,15 +4067,14 @@ 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 +4165,6 @@ 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 +4174,35 @@ 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 +4612,17 @@ 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; @@ -4821,28 +5069,38 @@ static bool icl_combo_port_connected(struct drm_i915_private *dev_priv, return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(port); } +static const char *tc_type_name(enum tc_port_type type) +{ + static const char * const names[] = { + [TC_PORT_UNKNOWN] = "unknown", + [TC_PORT_LEGACY] = "legacy", + [TC_PORT_TYPEC] = "typec", + [TC_PORT_TBT] = "tbt", + }; + + if (WARN_ON(type >= ARRAY_SIZE(names))) + type = TC_PORT_UNKNOWN; + + return names[type]; +} + static void icl_update_tc_port_type(struct drm_i915_private *dev_priv, struct intel_digital_port *intel_dig_port, bool is_legacy, bool is_typec, bool is_tbt) { enum port port = intel_dig_port->base.port; enum tc_port_type old_type = intel_dig_port->tc_type; - const char *type_str; WARN_ON(is_legacy + is_typec + is_tbt != 1); - if (is_legacy) { + if (is_legacy) intel_dig_port->tc_type = TC_PORT_LEGACY; - type_str = "legacy"; - } else if (is_typec) { + else if (is_typec) intel_dig_port->tc_type = TC_PORT_TYPEC; - type_str = "typec"; - } else if (is_tbt) { + else if (is_tbt) intel_dig_port->tc_type = TC_PORT_TBT; - type_str = "tbt"; - } else { + else return; - } /* Types are not supposed to be changed at runtime. */ WARN_ON(old_type != TC_PORT_UNKNOWN && @@ -4850,12 +5108,9 @@ static void icl_update_tc_port_type(struct drm_i915_private *dev_priv, if (old_type != intel_dig_port->tc_type) DRM_DEBUG_KMS("Port %c has TC type %s\n", port_name(port), - type_str); + tc_type_name(intel_dig_port->tc_type)); } -static void icl_tc_phy_disconnect(struct drm_i915_private *dev_priv, - struct intel_digital_port *dig_port); - /* * This function implements the first part of the Connect Flow described by our * specification, Gen11 TypeC Programming chapter. The rest of the flow (reading @@ -4890,6 +5145,7 @@ static bool icl_tc_phy_connect(struct drm_i915_private *dev_priv, val = I915_READ(PORT_TX_DFLEXDPPMS); if (!(val & DP_PHY_MODE_STATUS_COMPLETED(tc_port))) { DRM_DEBUG_KMS("DP PHY for TC port %d not ready\n", tc_port); + WARN_ON(dig_port->tc_legacy_port); return false; } @@ -4921,8 +5177,8 @@ static bool icl_tc_phy_connect(struct drm_i915_private *dev_priv, * See the comment at the connect function. This implements the Disconnect * Flow. */ -static void icl_tc_phy_disconnect(struct drm_i915_private *dev_priv, - struct intel_digital_port *dig_port) +void icl_tc_phy_disconnect(struct drm_i915_private *dev_priv, + struct intel_digital_port *dig_port) { enum tc_port tc_port = intel_port_to_tc(dev_priv, dig_port->base.port); @@ -4942,6 +5198,10 @@ static void icl_tc_phy_disconnect(struct drm_i915_private *dev_priv, I915_WRITE(PORT_TX_DFLEXDPCSSS, val); } + DRM_DEBUG_KMS("Port %c TC type %s disconnected\n", + port_name(dig_port->base.port), + tc_type_name(dig_port->tc_type)); + dig_port->tc_type = TC_PORT_UNKNOWN; } @@ -4963,7 +5223,14 @@ static bool icl_tc_port_connected(struct drm_i915_private *dev_priv, bool is_legacy, is_typec, is_tbt; u32 dpsp; - is_legacy = I915_READ(SDEISR) & SDE_TC_HOTPLUG_ICP(tc_port); + /* + * WARN if we got a legacy port HPD, but VBT didn't mark the port as + * legacy. Treat the port as legacy from now on. + */ + if (WARN_ON(!intel_dig_port->tc_legacy_port && + I915_READ(SDEISR) & SDE_TC_HOTPLUG_ICP(tc_port))) + intel_dig_port->tc_legacy_port = true; + is_legacy = intel_dig_port->tc_legacy_port; /* * The spec says we shouldn't be using the ISR bits for detecting @@ -4975,6 +5242,7 @@ static bool icl_tc_port_connected(struct drm_i915_private *dev_priv, if (!is_legacy && !is_typec && !is_tbt) { icl_tc_phy_disconnect(dev_priv, intel_dig_port); + return false; } @@ -5026,17 +5294,17 @@ bool intel_digital_port_connected(struct intel_encoder *encoder) if (INTEL_GEN(dev_priv) >= 11) return icl_digital_port_connected(encoder); - else if (IS_GEN10(dev_priv) || IS_GEN9_BC(dev_priv)) + else if (IS_GEN(dev_priv, 10) || IS_GEN9_BC(dev_priv)) return spt_digital_port_connected(encoder); else if (IS_GEN9_LP(dev_priv)) return bxt_digital_port_connected(encoder); - else if (IS_GEN8(dev_priv)) + else if (IS_GEN(dev_priv, 8)) return bdw_digital_port_connected(encoder); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) return ivb_digital_port_connected(encoder); - else if (IS_GEN6(dev_priv)) + else if (IS_GEN(dev_priv, 6)) return snb_digital_port_connected(encoder); - else if (IS_GEN5(dev_priv)) + else if (IS_GEN(dev_priv, 5)) return ilk_digital_port_connected(encoder); MISSING_CASE(INTEL_GEN(dev_priv)); @@ -5283,7 +5551,7 @@ intel_dp_connector_unregister(struct drm_connector *connector) intel_connector_unregister(connector); } -void intel_dp_encoder_destroy(struct drm_encoder *encoder) +void intel_dp_encoder_flush_work(struct drm_encoder *encoder) { struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder); struct intel_dp *intel_dp = &intel_dig_port->dp; @@ -5306,9 +5574,14 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) } intel_dp_aux_fini(intel_dp); +} + +static void intel_dp_encoder_destroy(struct drm_encoder *encoder) +{ + intel_dp_encoder_flush_work(encoder); drm_encoder_cleanup(encoder); - kfree(intel_dig_port); + kfree(enc_to_dig_port(encoder)); } void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) @@ -5371,7 +5644,12 @@ int intel_dp_hdcp_write_an_aksv(struct intel_digital_port *intel_dig_port, } reply = (rxbuf[0] >> 4) & DP_AUX_NATIVE_REPLY_MASK; - return reply == DP_AUX_NATIVE_REPLY_ACK ? 0 : -EIO; + if (reply != DP_AUX_NATIVE_REPLY_ACK) { + DRM_DEBUG_KMS("Aksv write: no DP_AUX_NATIVE_REPLY_ACK %x\n", + reply); + return -EIO; + } + return 0; } static int intel_dp_hdcp_read_bksv(struct intel_digital_port *intel_dig_port, @@ -6154,8 +6432,8 @@ void intel_edp_drrs_enable(struct intel_dp *intel_dp, } mutex_lock(&dev_priv->drrs.mutex); - if (WARN_ON(dev_priv->drrs.dp)) { - DRM_ERROR("DRRS already enabled\n"); + if (dev_priv->drrs.dp) { + DRM_DEBUG_KMS("DRRS already enabled\n"); goto unlock; } 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..1a11c2beb7f3 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -243,6 +243,9 @@ struct intel_encoder { void (*post_pll_disable)(struct intel_encoder *, const struct intel_crtc_state *, const struct drm_connector_state *); + void (*update_pipe)(struct intel_encoder *, + const struct intel_crtc_state *, + const struct drm_connector_state *); /* Read out the current hw state of this connector, returning true if * the encoder is active. If the encoder is enabled it also set the pipe * it is connected to in the pipe parameter. */ @@ -706,6 +709,8 @@ 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 +931,9 @@ 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 +945,18 @@ 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 +1033,7 @@ 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); @@ -1192,6 +1212,9 @@ struct intel_dp { /* Displayport compliance testing */ struct intel_dp_compliance compliance; + + /* Display stream compression testing */ + bool force_dsc_en; }; enum lspcon_vendor { @@ -1217,6 +1240,7 @@ struct intel_digital_port { /* Used for DP and ICL+ TypeC/DP and TypeC/HDMI ports. */ enum aux_ch aux_ch; enum intel_display_power_domain ddi_io_power_domain; + bool tc_legacy_port:1; enum tc_port_type tc_type; void (*write_infoframe)(struct intel_encoder *encoder, @@ -1517,13 +1541,9 @@ 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); @@ -1788,9 +1808,12 @@ 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); +void intel_dp_encoder_flush_work(struct drm_encoder *encoder); bool intel_dp_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state); @@ -1843,6 +1866,12 @@ 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; @@ -1852,6 +1881,8 @@ bool intel_dp_read_dpcd(struct intel_dp *intel_dp); int intel_dp_link_required(int pixel_clock, int bpp); int intel_dp_max_data_rate(int max_link_clock, int max_lanes); bool intel_digital_port_connected(struct intel_encoder *encoder); +void icl_tc_phy_disconnect(struct drm_i915_private *dev_priv, + struct intel_digital_port *dig_port); /* intel_dp_aux_backlight.c */ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector); @@ -2047,6 +2078,7 @@ 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); @@ -2177,13 +2209,16 @@ void gen6_rps_busy(struct drm_i915_private *dev_priv); void gen6_rps_reset_ei(struct drm_i915_private *dev_priv); void gen6_rps_idle(struct drm_i915_private *dev_priv); void gen6_rps_boost(struct i915_request *rq, struct intel_rps_client *rps); -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 g4x_wm_get_hw_state(struct drm_i915_private *dev_priv); +void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv); +void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv); +void skl_wm_get_hw_state(struct drm_i915_private *dev_priv); +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, +void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc, struct skl_pipe_wm *out); void g4x_wm_sanitize(struct drm_i915_private *dev_priv); void vlv_wm_sanitize(struct drm_i915_private *dev_priv); @@ -2195,6 +2230,10 @@ 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); @@ -2287,20 +2326,20 @@ 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, struct intel_plane_state *intel_state); /* intel_color.c */ -void intel_color_init(struct drm_crtc *crtc); -int intel_color_check(struct drm_crtc *crtc, struct drm_crtc_state *state); -void intel_color_set_csc(struct drm_crtc_state *crtc_state); -void intel_color_load_luts(struct drm_crtc_state *crtc_state); +void intel_color_init(struct intel_crtc *crtc); +int intel_color_check(struct intel_crtc_state *crtc_state); +void intel_color_set_csc(struct intel_crtc_state *crtc_state); +void intel_color_load_luts(struct intel_crtc_state *crtc_state); /* intel_lspcon.c */ bool lspcon_init(struct intel_digital_port *intel_dig_port); 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..5b7e9118d97f 100644 --- a/drivers/gpu/drm/i915/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c @@ -32,7 +32,6 @@ #include <linux/slab.h> #include <video/mipi_display.h> #include <asm/intel-mid.h> -#include <video/mipi_display.h> #include "i915_drv.h" #include "intel_drv.h" #include "intel_dsi.h" @@ -103,6 +102,18 @@ 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 +335,12 @@ 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 +364,9 @@ 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..5990f8500bca 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -261,6 +261,31 @@ static void __sprint_engine_name(char *name, const struct engine_info *info) info->instance) >= INTEL_ENGINE_CS_MAX_NAME); } +void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask) +{ + struct drm_i915_private *dev_priv = engine->i915; + i915_reg_t hwstam; + + /* + * Though they added more rings on g4x/ilk, they did not add + * per-engine HWSTAM until gen6. + */ + if (INTEL_GEN(dev_priv) < 6 && engine->class != RENDER_CLASS) + return; + + hwstam = RING_HWSTAM(engine->mmio_base); + if (INTEL_GEN(dev_priv) >= 3) + I915_WRITE(hwstam, mask); + else + I915_WRITE16(hwstam, mask); +} + +static void intel_engine_sanitize_mmio(struct intel_engine_cs *engine) +{ + /* Mask off all writes into the unknown HWSP */ + intel_engine_set_hwsp_writemask(engine, ~0u); +} + static int intel_engine_setup(struct drm_i915_private *dev_priv, enum intel_engine_id id) @@ -312,6 +337,9 @@ intel_engine_setup(struct drm_i915_private *dev_priv, ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier); + /* Scrub mmio state on takeover */ + intel_engine_sanitize_mmio(engine); + dev_priv->engine_class[info->class][info->instance] = engine; dev_priv->engine[id] = engine; return 0; @@ -365,7 +393,7 @@ int intel_engines_init_mmio(struct drm_i915_private *dev_priv) goto cleanup; } - device_info->num_rings = hweight32(mask); + RUNTIME_INFO(dev_priv)->num_rings = hweight32(mask); i915_check_and_clear_faults(dev_priv); @@ -426,27 +454,9 @@ cleanup: return err; } -void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno) +void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno) { - struct drm_i915_private *dev_priv = engine->i915; - - /* Our semaphore implementation is strictly monotonic (i.e. we proceed - * so long as the semaphore value in the register/page is greater - * than the sync value), so whenever we reset the seqno, - * so long as we reset the tracking semaphore value to 0, it will - * always be before the next request's seqno. If we don't reset - * the semaphore value, then when the seqno moves backwards all - * future waits will complete instantly (causing rendering corruption). - */ - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) { - 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); - } - intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno); - clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted); /* After manually advancing the seqno, fake the interrupt in case * there are any waiters for that seqno. @@ -493,48 +503,11 @@ 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) { + /* Prevent writes into HWSP after returning the page to the system */ + intel_engine_set_hwsp_writemask(engine, ~0u); + if (HWS_NEEDS_PHYSICAL(engine->i915)) { void *addr = fetch_and_zero(&engine->status_page.page_addr); @@ -707,8 +680,6 @@ 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 +694,10 @@ 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) @@ -807,12 +782,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type) u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv) { - const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); + const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; u32 mcr_s_ss_select; u32 slice = fls(sseu->slice_mask); u32 subslice = fls(sseu->subslice_mask[slice]); - if (IS_GEN10(dev_priv)) + if (IS_GEN(dev_priv, 10)) mcr_s_ss_select = GEN8_MCR_SLICE(slice) | GEN8_MCR_SUBSLICE(subslice); else if (INTEL_GEN(dev_priv) >= 11) @@ -1068,22 +1043,34 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915) engine->set_default_submission(engine); } +static bool reset_engines(struct drm_i915_private *i915) +{ + if (INTEL_INFO(i915)->gpu_reset_clobbers_display) + return false; + + return intel_gpu_reset(i915, ALL_ENGINES) == 0; +} + /** * intel_engines_sanitize: called after the GPU has lost power * @i915: the i915 device + * @force: ignore a failed reset and sanitize engine state anyway * * Anytime we reset the GPU, either with an explicit GPU reset or through a * PCI power cycle, the GPU loses state and we must reset our state tracking * to match. Note that calling intel_engines_sanitize() if the GPU has not * been reset results in much confusion! */ -void intel_engines_sanitize(struct drm_i915_private *i915) +void intel_engines_sanitize(struct drm_i915_private *i915, bool force) { struct intel_engine_cs *engine; enum intel_engine_id id; GEM_TRACE("\n"); + if (!reset_engines(i915) && !force) + return; + for_each_engine(engine, i915, id) { if (engine->reset.reset) engine->reset.reset(engine, NULL); @@ -1286,7 +1273,7 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine, &engine->execlists; u64 addr; - if (engine->id == RCS && IS_GEN(dev_priv, 4, 7)) + if (engine->id == RCS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID)); drm_printf(m, "\tRING_START: 0x%08x\n", I915_READ(RING_START(engine->mmio_base))); @@ -1307,16 +1294,6 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine, drm_printf(m, "\tRING_IMR: %08x\n", I915_READ_IMR(engine)); } - if (HAS_LEGACY_SEMAPHORES(dev_priv)) { - drm_printf(m, "\tSYNC_0: 0x%08x\n", - I915_READ(RING_SYNC_0(engine->mmio_base))); - drm_printf(m, "\tSYNC_1: 0x%08x\n", - I915_READ(RING_SYNC_1(engine->mmio_base))); - if (HAS_VEBOX(dev_priv)) - drm_printf(m, "\tSYNC_2: 0x%08x\n", - I915_READ(RING_SYNC_2(engine->mmio_base))); - } - addr = intel_engine_get_active_head(engine); drm_printf(m, "\tACTHD: 0x%08x_%08x\n", upper_32_bits(addr), lower_32_bits(addr)); @@ -1570,11 +1547,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, spin_unlock(&b->rb_lock); local_irq_restore(flags); - drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n", - engine->irq_posted, - yesno(test_bit(ENGINE_IRQ_BREADCRUMB, - &engine->irq_posted))); - drm_printf(m, "HWSP:\n"); hexdump(m, engine->status_page.page_addr, PAGE_SIZE); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 14cbaf4a0e93..ccd5e110a19c 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -84,7 +84,7 @@ static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv, int lines; intel_fbc_get_plane_source_size(cache, NULL, &lines); - if (IS_GEN7(dev_priv)) + if (IS_GEN(dev_priv, 7)) lines = min(lines, 2048); else if (INTEL_GEN(dev_priv) >= 8) lines = min(lines, 2560); @@ -127,7 +127,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) cfb_pitch = params->fb.stride; /* FBC_CTL wants 32B or 64B units */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) cfb_pitch = (cfb_pitch / 32) - 1; else cfb_pitch = (cfb_pitch / 64) - 1; @@ -136,7 +136,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv) for (i = 0; i < (FBC_LL_SIZE / 32) + 1; i++) I915_WRITE(FBC_TAG(i), 0); - if (IS_GEN4(dev_priv)) { + if (IS_GEN(dev_priv, 4)) { u32 fbc_ctl2; /* Set it up... */ @@ -233,9 +233,9 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) if (params->flags & PLANE_HAS_FENCE) { dpfc_ctl |= DPFC_CTL_FENCE_EN; - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) dpfc_ctl |= params->vma->fence->id; - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { I915_WRITE(SNB_DPFC_CTL_SA, SNB_CPU_FENCE_ENABLE | params->vma->fence->id); @@ -243,7 +243,7 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv) params->crtc.fence_y_offset); } } else { - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { I915_WRITE(SNB_DPFC_CTL_SA, 0); I915_WRITE(DPFC_CPU_FENCE_OFFSET, 0); } @@ -282,7 +282,7 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv) int threshold = dev_priv->fbc.threshold; /* Display WA #0529: skl, kbl, bxt. */ - if (IS_GEN9(dev_priv) && !IS_GEMINILAKE(dev_priv)) { + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) { u32 val = I915_READ(CHICKEN_MISC_4); val &= ~(FBC_STRIDE_OVERRIDE | FBC_STRIDE_MASK); @@ -581,10 +581,10 @@ static bool stride_is_valid(struct drm_i915_private *dev_priv, if (stride < 512) return false; - if (IS_GEN2(dev_priv) || IS_GEN3(dev_priv)) + if (IS_GEN(dev_priv, 2) || IS_GEN(dev_priv, 3)) return stride == 4096 || stride == 8192; - if (IS_GEN4(dev_priv) && !IS_G4X(dev_priv) && stride < 2048) + if (IS_GEN(dev_priv, 4) && !IS_G4X(dev_priv) && stride < 2048) return false; if (stride > 16384) @@ -603,7 +603,7 @@ static bool pixel_format_is_valid(struct drm_i915_private *dev_priv, case DRM_FORMAT_XRGB1555: case DRM_FORMAT_RGB565: /* 16bpp not supported on gen2 */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) return false; /* WaFbcOnly1to1Ratio:ctg */ if (IS_G4X(dev_priv)) @@ -626,7 +626,10 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc) struct intel_fbc *fbc = &dev_priv->fbc; unsigned int effective_w, effective_h, max_w, max_h; - if (INTEL_GEN(dev_priv) >= 8 || IS_HASWELL(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) { + max_w = 5120; + max_h = 4096; + } else if (INTEL_GEN(dev_priv) >= 8 || IS_HASWELL(dev_priv)) { max_w = 4096; max_h = 4096; } else if (IS_G4X(dev_priv) || INTEL_GEN(dev_priv) >= 5) { @@ -784,7 +787,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc) * having a Y offset that isn't divisible by 4 causes FIFO underrun * and screen flicker. */ - if (IS_GEN(dev_priv, 9, 10) && + if (IS_GEN_RANGE(dev_priv, 9, 10) && (fbc->state_cache.plane.adjusted_y & 3)) { fbc->no_fbc_reason = "plane Y offset is misaligned"; return false; @@ -839,7 +842,7 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc, params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache); - if (IS_GEN9(dev_priv) && !IS_GEMINILAKE(dev_priv)) + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) params->gen9_wa_cfb_stride = DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8; } @@ -1126,8 +1129,6 @@ void intel_fbc_disable(struct intel_crtc *crtc) if (!fbc_supported(dev_priv)) return; - WARN_ON(crtc->active); - mutex_lock(&fbc->lock); if (fbc->crtc == crtc) __intel_fbc_disable(dev_priv); @@ -1309,7 +1310,7 @@ 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_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c index 77c123cc8817..9b39975c8389 100644 --- a/drivers/gpu/drm/i915/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c @@ -260,9 +260,9 @@ static bool __intel_set_cpu_fifo_underrun_reporting(struct drm_device *dev, if (HAS_GMCH_DISPLAY(dev_priv)) i9xx_set_fifo_underrun_reporting(dev, pipe, enable, old); - else if (IS_GEN5(dev_priv) || IS_GEN6(dev_priv)) + else if (IS_GEN_RANGE(dev_priv, 5, 6)) ironlake_set_fifo_underrun_reporting(dev, pipe, enable); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) ivybridge_set_fifo_underrun_reporting(dev, pipe, enable, old); else if (INTEL_GEN(dev_priv) >= 8) broadwell_set_fifo_underrun_reporting(dev, pipe, enable); @@ -423,7 +423,7 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv) if (HAS_GMCH_DISPLAY(dev_priv)) i9xx_check_fifo_underruns(crtc); - else if (IS_GEN7(dev_priv)) + else if (IS_GEN(dev_priv, 7)) ivybridge_check_fifo_underruns(crtc); } diff --git a/drivers/gpu/drm/i915/intel_guc_fw.c b/drivers/gpu/drm/i915/intel_guc_fw.c index a67144ee5ceb..4b437e05e2cd 100644 --- a/drivers/gpu/drm/i915/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/intel_guc_fw.c @@ -115,7 +115,7 @@ static void guc_prepare_xfer(struct intel_guc *guc) else I915_WRITE(GEN9_GT_PM_CONFIG, GT_DOORBELL_ENABLE); - if (IS_GEN9(dev_priv)) { + if (IS_GEN(dev_priv, 9)) { /* DOP Clock Gating Enable for GuC clocks */ I915_WRITE(GEN7_MISCCPCTL, (GEN8_DOP_CLOCK_GATE_GUC_ENABLE | I915_READ(GEN7_MISCCPCTL))); diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c index 1570dcbe249c..ab1c49b106f2 100644 --- a/drivers/gpu/drm/i915/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/intel_guc_submission.c @@ -572,7 +572,8 @@ static void inject_preempt_context(struct work_struct *work) if (engine->id == RCS) { cs = gen8_emit_ggtt_write_rcs(cs, GUC_PREEMPT_FINISHED, - addr); + addr, + PIPE_CONTROL_CS_STALL); } else { cs = gen8_emit_ggtt_write(cs, GUC_PREEMPT_FINISHED, diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c index e26d05a46451..51e9efec5116 100644 --- a/drivers/gpu/drm/i915/intel_hangcheck.c +++ b/drivers/gpu/drm/i915/intel_hangcheck.c @@ -24,144 +24,6 @@ #include "i915_drv.h" -static bool -ipehr_is_semaphore_wait(struct intel_engine_cs *engine, u32 ipehr) -{ - ipehr &= ~MI_SEMAPHORE_SYNC_MASK; - return ipehr == (MI_SEMAPHORE_MBOX | MI_SEMAPHORE_COMPARE | - MI_SEMAPHORE_REGISTER); -} - -static struct intel_engine_cs * -semaphore_wait_to_signaller_ring(struct intel_engine_cs *engine, u32 ipehr, - u64 offset) -{ - struct drm_i915_private *dev_priv = engine->i915; - u32 sync_bits = ipehr & MI_SEMAPHORE_SYNC_MASK; - struct intel_engine_cs *signaller; - enum intel_engine_id id; - - for_each_engine(signaller, dev_priv, id) { - if (engine == signaller) - continue; - - if (sync_bits == signaller->semaphore.mbox.wait[engine->hw_id]) - return signaller; - } - - DRM_DEBUG_DRIVER("No signaller ring found for %s, ipehr 0x%08x\n", - engine->name, ipehr); - - return ERR_PTR(-ENODEV); -} - -static struct intel_engine_cs * -semaphore_waits_for(struct intel_engine_cs *engine, u32 *seqno) -{ - struct drm_i915_private *dev_priv = engine->i915; - void __iomem *vaddr; - u32 cmd, ipehr, head; - u64 offset = 0; - int i, backwards; - - /* - * This function does not support execlist mode - any attempt to - * proceed further into this function will result in a kernel panic - * when dereferencing ring->buffer, which is not set up in execlist - * mode. - * - * The correct way of doing it would be to derive the currently - * executing ring buffer from the current context, which is derived - * from the currently running request. Unfortunately, to get the - * current request we would have to grab the struct_mutex before doing - * anything else, which would be ill-advised since some other thread - * might have grabbed it already and managed to hang itself, causing - * the hang checker to deadlock. - * - * Therefore, this function does not support execlist mode in its - * current form. Just return NULL and move on. - */ - if (engine->buffer == NULL) - return NULL; - - ipehr = I915_READ(RING_IPEHR(engine->mmio_base)); - if (!ipehr_is_semaphore_wait(engine, ipehr)) - return NULL; - - /* - * HEAD is likely pointing to the dword after the actual command, - * so scan backwards until we find the MBOX. But limit it to just 3 - * or 4 dwords depending on the semaphore wait command size. - * Note that we don't care about ACTHD here since that might - * point at at batch, and semaphores are always emitted into the - * ringbuffer itself. - */ - head = I915_READ_HEAD(engine) & HEAD_ADDR; - backwards = (INTEL_GEN(dev_priv) >= 8) ? 5 : 4; - vaddr = (void __iomem *)engine->buffer->vaddr; - - for (i = backwards; i; --i) { - /* - * Be paranoid and presume the hw has gone off into the wild - - * our ring is smaller than what the hardware (and hence - * HEAD_ADDR) allows. Also handles wrap-around. - */ - head &= engine->buffer->size - 1; - - /* This here seems to blow up */ - cmd = ioread32(vaddr + head); - if (cmd == ipehr) - break; - - head -= 4; - } - - if (!i) - return NULL; - - *seqno = ioread32(vaddr + head + 4) + 1; - return semaphore_wait_to_signaller_ring(engine, ipehr, offset); -} - -static int semaphore_passed(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - struct intel_engine_cs *signaller; - u32 seqno; - - engine->hangcheck.deadlock++; - - signaller = semaphore_waits_for(engine, &seqno); - if (signaller == NULL) - return -1; - - if (IS_ERR(signaller)) - return 0; - - /* Prevent pathological recursion due to driver bugs */ - if (signaller->hangcheck.deadlock >= I915_NUM_ENGINES) - return -1; - - if (intel_engine_signaled(signaller, seqno)) - return 1; - - /* cursory check for an unkickable deadlock */ - if (I915_READ_CTL(signaller) & RING_WAIT_SEMAPHORE && - semaphore_passed(signaller) < 0) - return -1; - - return 0; -} - -static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv) -{ - struct intel_engine_cs *engine; - enum intel_engine_id id; - - for_each_engine(engine, dev_priv, id) - engine->hangcheck.deadlock = 0; -} - static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone) { u32 tmp = current_instdone | *old_instdone; @@ -236,7 +98,7 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd) if (ha != ENGINE_DEAD) return ha; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) return ENGINE_DEAD; /* Is the chip hanging on a WAIT_FOR_EVENT? @@ -252,37 +114,12 @@ engine_stuck(struct intel_engine_cs *engine, u64 acthd) return ENGINE_WAIT_KICK; } - if (IS_GEN(dev_priv, 6, 7) && tmp & RING_WAIT_SEMAPHORE) { - switch (semaphore_passed(engine)) { - default: - return ENGINE_DEAD; - case 1: - i915_handle_error(dev_priv, ALL_ENGINES, 0, - "stuck semaphore on %s", - engine->name); - I915_WRITE_CTL(engine, tmp); - return ENGINE_WAIT_KICK; - case 0: - return ENGINE_WAIT; - } - } - return ENGINE_DEAD; } static void hangcheck_load_sample(struct intel_engine_cs *engine, struct intel_engine_hangcheck *hc) { - /* We don't strictly need an irq-barrier here, as we are not - * serving an interrupt request, be paranoid in case the - * barrier has side-effects (such as preventing a broken - * cacheline snoop) and so be sure that we can see the seqno - * advance. If the seqno should stick, due to a stale - * cacheline, we would erroneously declare the GPU hung. - */ - if (engine->irq_seqno_barrier) - engine->irq_seqno_barrier(engine); - hc->acthd = intel_engine_get_active_head(engine); hc->seqno = intel_engine_get_seqno(engine); } @@ -433,8 +270,6 @@ static void i915_hangcheck_elapsed(struct work_struct *work) for_each_engine(engine, dev_priv, id) { struct intel_engine_hangcheck hc; - semaphore_clear_deadlocks(dev_priv); - hangcheck_load_sample(engine, &hc); hangcheck_accumulate_sample(engine, &hc); hangcheck_store_sample(engine, &hc); diff --git a/drivers/gpu/drm/i915/intel_hdcp.c b/drivers/gpu/drm/i915/intel_hdcp.c index 1bf487f94254..e000e54ad569 100644 --- a/drivers/gpu/drm/i915/intel_hdcp.c +++ b/drivers/gpu/drm/i915/intel_hdcp.c @@ -15,6 +15,7 @@ #include "i915_reg.h" #define KEY_LOAD_TRIES 5 +#define ENCRYPT_STATUS_CHANGE_TIMEOUT_MS 50 static bool intel_hdcp_is_ksv_valid(u8 *ksv) @@ -157,10 +158,11 @@ static int intel_hdcp_load_keys(struct drm_i915_private *dev_priv) /* * Initiate loading the HDCP key from fuses. * - * BXT+ platforms, HDCP key needs to be loaded by SW. Only SKL and KBL - * differ in the key load trigger process from other platforms. + * BXT+ platforms, HDCP key needs to be loaded by SW. Only Gen 9 + * platforms except BXT and GLK, differ in the key load trigger process + * from other platforms. So GEN9_BC uses the GT Driver Mailbox i/f. */ - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_GEN9_BC(dev_priv)) { mutex_lock(&dev_priv->pcu_lock); ret = sandybridge_pcode_write(dev_priv, SKL_PCODE_LOAD_HDCP_KEYS, 1); @@ -636,7 +638,8 @@ static int intel_hdcp_auth(struct intel_digital_port *intel_dig_port, /* Wait for encryption confirmation */ if (intel_wait_for_register(dev_priv, PORT_HDCP_STATUS(port), - HDCP_STATUS_ENC, HDCP_STATUS_ENC, 20)) { + HDCP_STATUS_ENC, HDCP_STATUS_ENC, + ENCRYPT_STATUS_CHANGE_TIMEOUT_MS)) { DRM_ERROR("Timed out waiting for encryption\n"); return -ETIMEDOUT; } @@ -666,7 +669,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) I915_WRITE(PORT_HDCP_CONF(port), 0); if (intel_wait_for_register(dev_priv, PORT_HDCP_STATUS(port), ~0, 0, - 20)) { + ENCRYPT_STATUS_CHANGE_TIMEOUT_MS)) { DRM_ERROR("Failed to disable HDCP, timeout clearing status\n"); return -ETIMEDOUT; } @@ -768,8 +771,7 @@ static void intel_hdcp_prop_work(struct work_struct *work) bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port) { /* PORT E doesn't have HDCP, and PORT F is disabled */ - return ((INTEL_GEN(dev_priv) >= 8 || IS_HASWELL(dev_priv)) && - !IS_CHERRYVIEW(dev_priv) && port < PORT_E); + return INTEL_GEN(dev_priv) >= 9 && port < PORT_E; } int intel_hdcp_init(struct intel_connector *connector, 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_huc_fw.c b/drivers/gpu/drm/i915/intel_huc_fw.c index f93d2384d482..9612227b3c44 100644 --- a/drivers/gpu/drm/i915/intel_huc_fw.c +++ b/drivers/gpu/drm/i915/intel_huc_fw.c @@ -23,8 +23,8 @@ */ #define BXT_HUC_FW_MAJOR 01 -#define BXT_HUC_FW_MINOR 07 -#define BXT_BLD_NUM 1398 +#define BXT_HUC_FW_MINOR 8 +#define BXT_BLD_NUM 2893 #define SKL_HUC_FW_MAJOR 01 #define SKL_HUC_FW_MINOR 07 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..d81ae121c45e 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -363,31 +363,12 @@ execlists_context_schedule_out(struct i915_request *rq, unsigned long status) trace_i915_request_out(rq); } -static void -execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state) -{ - ASSIGN_CTX_PDP(ppgtt, reg_state, 3); - ASSIGN_CTX_PDP(ppgtt, reg_state, 2); - ASSIGN_CTX_PDP(ppgtt, reg_state, 1); - ASSIGN_CTX_PDP(ppgtt, reg_state, 0); -} - static u64 execlists_update_context(struct i915_request *rq) { - struct i915_hw_ppgtt *ppgtt = rq->gem_context->ppgtt; struct intel_context *ce = rq->hw_context; - u32 *reg_state = ce->lrc_reg_state; - reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail); - - /* - * True 32b PPGTT with dynamic page allocation: update PDP - * registers and point the unallocated PDPs to scratch page. - * PML4 is allocated during ppgtt init, so this is not needed - * in 48-bit mode. - */ - if (!i915_vm_is_48bit(&ppgtt->vm)) - execlists_update_context_pdps(ppgtt, reg_state); + ce->lrc_reg_state[CTX_RING_TAIL + 1] = + intel_ring_set_tail(rq->ring, rq->tail); /* * Make sure the context image is complete before we submit it to HW. @@ -398,8 +379,13 @@ static u64 execlists_update_context(struct i915_request *rq) * may not be visible to the HW prior to the completion of the UC * register write and that we may begin execution from the context * before its image is complete leading to invalid PD chasing. + * + * Furthermore, Braswell, at least, wants a full mb to be sure that + * the writes are coherent in memory (visible to the GPU) prior to + * execution, and not just visible to other CPUs (as is the result of + * wmb). */ - wmb(); + mb(); return ce->lrc_desc; } @@ -765,8 +751,17 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) execlists_clear_all_active(execlists); } +static inline void +invalidate_csb_entries(const u32 *first, const u32 *last) +{ + clflush((void *)first); + clflush((void *)last); +} + 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 +771,11 @@ 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); + + invalidate_csb_entries(&execlists->csb_status[0], + &execlists->csb_status[GEN8_CSB_ENTRIES - 1]); } static void nop_submission_tasklet(unsigned long data) @@ -818,8 +816,11 @@ 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 +840,10 @@ 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; @@ -1006,6 +1011,19 @@ static void process_csb(struct intel_engine_cs *engine) } while (head != tail); execlists->csb_head = head; + + /* + * Gen11 has proven to fail wrt global observation point between + * entry and tail update, failing on the ordering and thus + * we see an old entry in the context status buffer. + * + * Forcibly evict out entries for the next gpu csb update, + * to increase the odds that we get a fresh entries with non + * working hardware. The cost for doing so comes out mostly with + * the wash as hardware, working or not, will need to do the + * invalidation before. + */ + invalidate_csb_entries(&buf[0], &buf[GEN8_CSB_ENTRIES - 1]); } static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) @@ -1233,29 +1251,88 @@ execlists_context_pin(struct intel_engine_cs *engine, return __execlists_context_pin(engine, ctx, ce); } +static int emit_pdps(struct i915_request *rq) +{ + const struct intel_engine_cs * const engine = rq->engine; + struct i915_hw_ppgtt * const ppgtt = rq->gem_context->ppgtt; + int err, i; + u32 *cs; + + GEM_BUG_ON(intel_vgpu_active(rq->i915)); + + /* + * Beware ye of the dragons, this sequence is magic! + * + * Small changes to this sequence can cause anything from + * GPU hangs to forcewake errors and machine lockups! + */ + + /* Flush any residual operations from the context load */ + err = engine->emit_flush(rq, EMIT_FLUSH); + if (err) + return err; + + /* Magic required to prevent forcewake errors! */ + err = engine->emit_flush(rq, EMIT_INVALIDATE); + if (err) + return err; + + cs = intel_ring_begin(rq, 4 * GEN8_3LVL_PDPES + 2); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + /* Ensure the LRI have landed before we invalidate & continue */ + *cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED; + for (i = GEN8_3LVL_PDPES; i--; ) { + const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); + + *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(engine, i)); + *cs++ = upper_32_bits(pd_daddr); + *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, i)); + *cs++ = lower_32_bits(pd_daddr); + } + *cs++ = MI_NOOP; + + intel_ring_advance(rq, cs); + + /* Be doubly sure the LRI have landed before proceeding */ + err = engine->emit_flush(rq, EMIT_FLUSH); + if (err) + return err; + + /* Re-invalidate the TLB for luck */ + return engine->emit_flush(rq, EMIT_INVALIDATE); +} + static int execlists_request_alloc(struct i915_request *request) { int ret; GEM_BUG_ON(!request->hw_context->pin_count); - /* Flush enough space to reduce the likelihood of waiting after + /* + * Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just * have to repeat work. */ request->reserved_space += EXECLISTS_REQUEST_SIZE; - ret = intel_ring_wait_for_space(request->ring, request->reserved_space); - if (ret) - return ret; - - /* Note that after this point, we have committed to using + /* + * Note that after this point, we have committed to using * this request as it is being used to both track the * state of engine initialisation and liveness of the * golden renderstate above. Think twice before you try * to cancel/unwind this request now. */ + /* Unconditionally invalidate GPU caches and TLBs. */ + if (i915_vm_is_48bit(&request->gem_context->ppgtt->vm)) + ret = request->engine->emit_flush(request, EMIT_INVALIDATE); + else + ret = emit_pdps(request); + if (ret) + return ret; + request->reserved_space -= EXECLISTS_REQUEST_SIZE; return 0; } @@ -1279,9 +1356,10 @@ 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 +1373,7 @@ 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 +1410,7 @@ 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 +1479,6 @@ 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)) { /* @@ -1589,7 +1655,7 @@ static void enable_execlists(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; - I915_WRITE(RING_HWSTAM(engine->mmio_base), 0xffffffff); + intel_engine_set_hwsp_writemask(engine, ~0u); /* HWSTAM */ /* * Make sure we're not enabling the new 12-deep CSB @@ -1629,6 +1695,9 @@ 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_engine_apply_whitelist(engine); + intel_mocs_init_engine(engine); intel_engine_reset_breadcrumbs(engine); @@ -1644,43 +1713,6 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) return 0; } -static int gen8_init_render_ring(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; - int ret; - - ret = gen8_init_common_ring(engine); - if (ret) - return ret; - - intel_whitelist_workarounds_apply(engine); - - /* We need to disable the AsyncFlip performance optimisations in order - * to use MI_WAIT_FOR_EVENT within the CS. It should already be - * programmed to '1' on all products. - * - * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv,bdw,chv - */ - I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE)); - - I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING)); - - return 0; -} - -static int gen9_init_render_ring(struct intel_engine_cs *engine) -{ - int ret; - - ret = gen8_init_common_ring(engine); - if (ret) - return ret; - - intel_whitelist_workarounds_apply(engine); - - return 0; -} - static struct i915_request * execlists_reset_prepare(struct intel_engine_cs *engine) { @@ -1836,56 +1868,11 @@ static void execlists_reset_finish(struct intel_engine_cs *engine) atomic_read(&execlists->tasklet.count)); } -static int intel_logical_ring_emit_pdps(struct i915_request *rq) -{ - struct i915_hw_ppgtt *ppgtt = rq->gem_context->ppgtt; - struct intel_engine_cs *engine = rq->engine; - const int num_lri_cmds = GEN8_3LVL_PDPES * 2; - u32 *cs; - int i; - - cs = intel_ring_begin(rq, num_lri_cmds * 2 + 2); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - *cs++ = MI_LOAD_REGISTER_IMM(num_lri_cmds); - for (i = GEN8_3LVL_PDPES - 1; i >= 0; i--) { - const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i); - - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(engine, i)); - *cs++ = upper_32_bits(pd_daddr); - *cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, i)); - *cs++ = lower_32_bits(pd_daddr); - } - - *cs++ = MI_NOOP; - intel_ring_advance(rq, cs); - - return 0; -} - static int gen8_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, const unsigned int flags) { u32 *cs; - int ret; - - /* Don't rely in hw updating PDPs, specially in lite-restore. - * Ideally, we should set Force PD Restore in ctx descriptor, - * but we can't. Force Restore would be a second option, but - * it is unsafe in case of lite-restore (because the ctx is - * not idle). PML4 is allocated during ppgtt init so this is - * not needed in 48-bit.*/ - if ((intel_engine_flag(rq->engine) & rq->gem_context->ppgtt->pd_dirty_rings) && - !i915_vm_is_48bit(&rq->gem_context->ppgtt->vm) && - !intel_vgpu_active(rq->i915)) { - ret = intel_logical_ring_emit_pdps(rq); - if (ret) - return ret; - - rq->gem_context->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine); - } cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1918,6 +1905,7 @@ static int gen8_emit_bb_start(struct i915_request *rq, *cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; *cs++ = MI_NOOP; + intel_ring_advance(rq, cs); return 0; @@ -1974,7 +1962,7 @@ 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; @@ -2002,7 +1990,7 @@ static int gen8_emit_flush_render(struct i915_request *request, * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL * pipe control. */ - if (IS_GEN9(request->i915)) + if (IS_GEN(request->i915, 9)) vf_flush_wa = true; /* WaForGAMHang:kbl */ @@ -2073,10 +2061,18 @@ static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs) /* We're using qword write, seqno should be aligned to 8 bytes. */ BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1); - cs = gen8_emit_ggtt_write_rcs(cs, request->global_seqno, - intel_hws_seqno_address(request->engine)); + cs = gen8_emit_ggtt_write_rcs(cs, + request->global_seqno, + intel_hws_seqno_address(request->engine), + PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE | + PIPE_CONTROL_FLUSH_ENABLE | + PIPE_CONTROL_CS_STALL); + *cs++ = MI_USER_INTERRUPT; *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; + request->tail = intel_ring_offset(request, cs); assert_ring_tail_valid(request->ring, request->tail); @@ -2088,7 +2084,7 @@ 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 +2225,6 @@ 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 +2254,12 @@ 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; @@ -2298,10 +2276,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine) engine->irq_keep_mask |= GT_RENDER_L3_PARITY_ERROR_INTERRUPT; /* Override some for render ring. */ - if (INTEL_GEN(dev_priv) >= 9) - engine->init_hw = gen9_init_render_ring; - else - engine->init_hw = gen8_init_render_ring; engine->init_context = gen8_init_rcs_context; engine->emit_flush = gen8_emit_flush_render; engine->emit_breadcrumb = gen8_emit_breadcrumb_rcs; @@ -2311,10 +2285,6 @@ 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 +2296,10 @@ 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) @@ -2343,9 +2312,9 @@ int logical_xcs_ring_init(struct intel_engine_cs *engine) static u32 make_rpcs(struct drm_i915_private *dev_priv) { - bool subslice_pg = INTEL_INFO(dev_priv)->sseu.has_subslice_pg; - u8 slices = hweight8(INTEL_INFO(dev_priv)->sseu.slice_mask); - u8 subslices = hweight8(INTEL_INFO(dev_priv)->sseu.subslice_mask[0]); + bool subslice_pg = RUNTIME_INFO(dev_priv)->sseu.has_subslice_pg; + u8 slices = hweight8(RUNTIME_INFO(dev_priv)->sseu.slice_mask); + u8 subslices = hweight8(RUNTIME_INFO(dev_priv)->sseu.subslice_mask[0]); u32 rpcs = 0; /* @@ -2380,7 +2349,7 @@ make_rpcs(struct drm_i915_private *dev_priv) * subslices are enabled, or a count between one and four on the first * slice. */ - if (IS_GEN11(dev_priv) && slices == 1 && subslices >= 4) { + if (IS_GEN(dev_priv, 11) && slices == 1 && subslices >= 4) { GEM_BUG_ON(subslices & 1); subslice_pg = false; @@ -2393,7 +2362,7 @@ make_rpcs(struct drm_i915_private *dev_priv) * must make an explicit request through RPCS for full * enablement. */ - if (INTEL_INFO(dev_priv)->sseu.has_slice_pg) { + if (RUNTIME_INFO(dev_priv)->sseu.has_slice_pg) { u32 mask, val = slices; if (INTEL_GEN(dev_priv) >= 11) { @@ -2421,17 +2390,17 @@ make_rpcs(struct drm_i915_private *dev_priv) rpcs |= GEN8_RPCS_ENABLE | GEN8_RPCS_SS_CNT_ENABLE | val; } - if (INTEL_INFO(dev_priv)->sseu.has_eu_pg) { + if (RUNTIME_INFO(dev_priv)->sseu.has_eu_pg) { u32 val; - val = INTEL_INFO(dev_priv)->sseu.eu_per_subslice << + val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice << GEN8_RPCS_EU_MIN_SHIFT; GEM_BUG_ON(val & ~GEN8_RPCS_EU_MIN_MASK); val &= GEN8_RPCS_EU_MIN_MASK; rpcs |= val; - val = INTEL_INFO(dev_priv)->sseu.eu_per_subslice << + val = RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice << GEN8_RPCS_EU_MAX_SHIFT; GEM_BUG_ON(val & ~GEN8_RPCS_EU_MAX_MASK); val &= GEN8_RPCS_EU_MAX_MASK; @@ -2556,6 +2525,11 @@ static void execlists_init_reg_state(u32 *regs, * other PDP Descriptors are ignored. */ ASSIGN_CTX_PML4(ctx->ppgtt, regs); + } else { + ASSIGN_CTX_PDP(ctx->ppgtt, regs, 3); + ASSIGN_CTX_PDP(ctx->ppgtt, regs, 2); + ASSIGN_CTX_PDP(ctx->ppgtt, regs, 1); + ASSIGN_CTX_PDP(ctx->ppgtt, regs, 0); } if (rcs) { diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index e6c5d985ea0a..b85e195f7c8a 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -279,7 +279,7 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder, * special lvds dither control bit on pch-split platforms, dithering is * only controlled through the PIPECONF reg. */ - if (IS_GEN4(dev_priv)) { + if (IS_GEN(dev_priv, 4)) { /* * Bspec wording suggests that LVDS port dithering only exists * for 18bpp panels. @@ -919,7 +919,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) intel_encoder->cloneable = 0; if (HAS_PCH_SPLIT(dev_priv)) intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2); - else if (IS_GEN4(dev_priv)) + else if (IS_GEN(dev_priv, 4)) intel_encoder->crtc_mask = (1 << 0) | (1 << 1); else intel_encoder->crtc_mask = (1 << 1); diff --git a/drivers/gpu/drm/i915/intel_mocs.c b/drivers/gpu/drm/i915/intel_mocs.c index 77e9871a8c9a..e976c5ce5479 100644 --- a/drivers/gpu/drm/i915/intel_mocs.c +++ b/drivers/gpu/drm/i915/intel_mocs.c @@ -193,7 +193,7 @@ static bool get_mocs_settings(struct drm_i915_private *dev_priv, } /* WaDisableSkipCaching:skl,bxt,kbl,glk */ - if (IS_GEN9(dev_priv)) { + if (IS_GEN(dev_priv, 9)) { int i; for (i = 0; i < table->size; i++) 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_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index 20ea7c99d13a..c153be043078 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -541,7 +541,7 @@ static u32 calc_swidthsw(struct drm_i915_private *dev_priv, u32 offset, u32 widt { u32 sw; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) sw = ALIGN((offset & 31) + width, 32); else sw = ALIGN((offset & 63) + width, 64); @@ -778,7 +778,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, u32 oconfig; oconfig = OCONF_CC_OUT_8BIT; - if (IS_GEN4(dev_priv)) + if (IS_GEN(dev_priv, 4)) oconfig |= OCONF_CSC_MODE_BT709; oconfig |= pipe == 0 ? OCONF_PIPE_A : OCONF_PIPE_B; @@ -1012,7 +1012,7 @@ static int check_overlay_src(struct drm_i915_private *dev_priv, if (rec->stride_Y & stride_mask || rec->stride_UV & stride_mask) return -EINVAL; - if (IS_GEN4(dev_priv) && rec->stride_Y < 512) + if (IS_GEN(dev_priv, 4) && rec->stride_Y < 512) return -EINVAL; tmp = (rec->flags & I915_OVERLAY_TYPE_MASK) == I915_OVERLAY_YUV_PLANAR ? @@ -1246,7 +1246,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, attrs->contrast = overlay->contrast; attrs->saturation = overlay->saturation; - if (!IS_GEN2(dev_priv)) { + if (!IS_GEN(dev_priv, 2)) { attrs->gamma0 = I915_READ(OGAMC0); attrs->gamma1 = I915_READ(OGAMC1); attrs->gamma2 = I915_READ(OGAMC2); @@ -1270,7 +1270,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, update_reg_attrs(overlay, overlay->regs); if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) { - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) goto out_unlock; if (overlay->active) { diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c index e6cd7b55c018..ee3e0842d542 100644 --- a/drivers/gpu/drm/i915/intel_panel.c +++ b/drivers/gpu/drm/i915/intel_panel.c @@ -563,7 +563,7 @@ static void i9xx_set_backlight(const struct drm_connector_state *conn_state, u32 pci_write_config_byte(dev_priv->drm.pdev, LBPC, lbpc); } - if (IS_GEN4(dev_priv)) { + if (IS_GEN(dev_priv, 4)) { mask = BACKLIGHT_DUTY_CYCLE_MASK; } else { level <<= 1; @@ -929,7 +929,7 @@ static void i9xx_enable_backlight(const struct intel_crtc_state *crtc_state, * 855gm only, but checking for gen2 is safe, as 855gm is the only gen2 * that has backlight. */ - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) I915_WRITE(BLC_HIST_CTL, BLM_HISTOGRAM_ENABLE); } @@ -1557,7 +1557,7 @@ static int i9xx_setup_backlight(struct intel_connector *connector, enum pipe unu ctl = I915_READ(BLC_PWM_CTL); - if (IS_GEN2(dev_priv) || IS_I915GM(dev_priv) || IS_I945GM(dev_priv)) + if (IS_GEN(dev_priv, 2) || IS_I915GM(dev_priv) || IS_I945GM(dev_priv)) panel->backlight.combination_mode = ctl & BLM_LEGACY_MODE; if (IS_PINEVIEW(dev_priv)) @@ -1886,7 +1886,7 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel) panel->backlight.get = vlv_get_backlight; panel->backlight.hz_to_pwm = vlv_hz_to_pwm; } - } else if (IS_GEN4(dev_priv)) { + } else if (IS_GEN(dev_priv, 4)) { panel->backlight.setup = i965_setup_backlight; panel->backlight.enable = i965_enable_backlight; panel->backlight.disable = i965_disable_backlight; diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c index f3c9010e332a..bdabcfab8090 100644 --- a/drivers/gpu/drm/i915/intel_pipe_crc.c +++ b/drivers/gpu/drm/i915/intel_pipe_crc.c @@ -427,13 +427,13 @@ static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv, enum intel_pipe_crc_source *source, u32 *val, bool set_wa) { - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) return i8xx_pipe_crc_ctl_reg(source, val); else if (INTEL_GEN(dev_priv) < 5) return i9xx_pipe_crc_ctl_reg(dev_priv, pipe, source, val); else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) return vlv_pipe_crc_ctl_reg(dev_priv, pipe, source, val); - else if (IS_GEN5(dev_priv) || IS_GEN6(dev_priv)) + else if (IS_GEN_RANGE(dev_priv, 5, 6)) return ilk_pipe_crc_ctl_reg(source, val); else return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val, set_wa); @@ -544,13 +544,13 @@ static int intel_is_valid_crc_source(struct drm_i915_private *dev_priv, const enum intel_pipe_crc_source source) { - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) return i8xx_crc_source_valid(dev_priv, source); else if (INTEL_GEN(dev_priv) < 5) return i9xx_crc_source_valid(dev_priv, source); else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) return vlv_crc_source_valid(dev_priv, source); - else if (IS_GEN5(dev_priv) || IS_GEN6(dev_priv)) + else if (IS_GEN_RANGE(dev_priv, 5, 6)) return ilk_crc_source_valid(dev_priv, source); else return ivb_crc_source_valid(dev_priv, source); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 897a791662c5..83b01cde8113 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -1399,10 +1399,9 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state) return 0; } -static int g4x_compute_intermediate_wm(struct drm_device *dev, - struct intel_crtc *crtc, - struct intel_crtc_state *new_crtc_state) +static int g4x_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); struct g4x_wm_state *intermediate = &new_crtc_state->wm.g4x.intermediate; const struct g4x_wm_state *optimal = &new_crtc_state->wm.g4x.optimal; struct intel_atomic_state *intel_state = @@ -2032,10 +2031,9 @@ static void vlv_atomic_update_fifo(struct intel_atomic_state *state, #undef VLV_FIFO -static int vlv_compute_intermediate_wm(struct drm_device *dev, - struct intel_crtc *crtc, - struct intel_crtc_state *new_crtc_state) +static int vlv_compute_intermediate_wm(struct intel_crtc_state *new_crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc); struct vlv_wm_state *intermediate = &new_crtc_state->wm.vlv.intermediate; const struct vlv_wm_state *optimal = &new_crtc_state->wm.vlv.optimal; struct intel_atomic_state *intel_state = @@ -2273,7 +2271,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) if (IS_I945GM(dev_priv)) wm_info = &i945_wm_info; - else if (!IS_GEN2(dev_priv)) + else if (!IS_GEN(dev_priv, 2)) wm_info = &i915_wm_info; else wm_info = &i830_a_wm_info; @@ -2287,7 +2285,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) crtc->base.primary->state->fb; int cpp; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) cpp = 4; else cpp = fb->format->cpp[0]; @@ -2302,7 +2300,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) planea_wm = wm_info->max_wm; } - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) wm_info = &i830_bc_wm_info; fifo_size = dev_priv->display.get_fifo_size(dev_priv, PLANE_B); @@ -2314,7 +2312,7 @@ static void i9xx_update_wm(struct intel_crtc *unused_crtc) crtc->base.primary->state->fb; int cpp; - if (IS_GEN2(dev_priv)) + if (IS_GEN(dev_priv, 2)) cpp = 4; else cpp = fb->format->cpp[0]; @@ -2626,13 +2624,12 @@ static unsigned int ilk_fbc_wm_reg_max(const struct drm_i915_private *dev_priv) } /* Calculate the maximum primary/sprite plane watermark */ -static unsigned int ilk_plane_wm_max(const struct drm_device *dev, +static unsigned int ilk_plane_wm_max(const struct drm_i915_private *dev_priv, int level, const struct intel_wm_config *config, enum intel_ddb_partitioning ddb_partitioning, bool is_sprite) { - struct drm_i915_private *dev_priv = to_i915(dev); unsigned int fifo_size = ilk_display_fifo_size(dev_priv); /* if sprites aren't enabled, sprites get nothing */ @@ -2668,7 +2665,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_device *dev, } /* Calculate the maximum cursor plane watermark */ -static unsigned int ilk_cursor_wm_max(const struct drm_device *dev, +static unsigned int ilk_cursor_wm_max(const struct drm_i915_private *dev_priv, int level, const struct intel_wm_config *config) { @@ -2677,19 +2674,19 @@ static unsigned int ilk_cursor_wm_max(const struct drm_device *dev, return 64; /* otherwise just report max that registers can hold */ - return ilk_cursor_wm_reg_max(to_i915(dev), level); + return ilk_cursor_wm_reg_max(dev_priv, level); } -static void ilk_compute_wm_maximums(const struct drm_device *dev, +static void ilk_compute_wm_maximums(const struct drm_i915_private *dev_priv, int level, const struct intel_wm_config *config, enum intel_ddb_partitioning ddb_partitioning, struct ilk_wm_maximums *max) { - max->pri = ilk_plane_wm_max(dev, level, config, ddb_partitioning, false); - max->spr = ilk_plane_wm_max(dev, level, config, ddb_partitioning, true); - max->cur = ilk_cursor_wm_max(dev, level, config); - max->fbc = ilk_fbc_wm_reg_max(to_i915(dev)); + max->pri = ilk_plane_wm_max(dev_priv, level, config, ddb_partitioning, false); + max->spr = ilk_plane_wm_max(dev_priv, level, config, ddb_partitioning, true); + max->cur = ilk_cursor_wm_max(dev_priv, level, config); + max->fbc = ilk_fbc_wm_reg_max(dev_priv); } static void ilk_compute_wm_reg_maximums(const struct drm_i915_private *dev_priv, @@ -2926,7 +2923,7 @@ static void intel_fixup_spr_wm_latency(struct drm_i915_private *dev_priv, uint16_t wm[5]) { /* ILK sprite LP0 latency is 1300 ns */ - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) wm[0] = 13; } @@ -2934,7 +2931,7 @@ static void intel_fixup_cur_wm_latency(struct drm_i915_private *dev_priv, uint16_t wm[5]) { /* ILK cursor LP0 latency is 1300 ns */ - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) wm[0] = 13; } @@ -3061,7 +3058,7 @@ static void ilk_setup_wm_latency(struct drm_i915_private *dev_priv) intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency); intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency); - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { snb_wm_latency_quirk(dev_priv); snb_wm_lp3_irq_quirk(dev_priv); } @@ -3073,7 +3070,7 @@ static void skl_setup_wm_latency(struct drm_i915_private *dev_priv) intel_print_wm_latency(dev_priv, "Gen9 Plane", dev_priv->wm.skl_latency); } -static bool ilk_validate_pipe_wm(struct drm_device *dev, +static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv, struct intel_pipe_wm *pipe_wm) { /* LP0 watermark maximums depend on this pipe alone */ @@ -3085,7 +3082,7 @@ static bool ilk_validate_pipe_wm(struct drm_device *dev, struct ilk_wm_maximums max; /* LP0 watermarks always use 1/2 DDB partitioning */ - ilk_compute_wm_maximums(dev, 0, &config, INTEL_DDB_PART_1_2, &max); + ilk_compute_wm_maximums(dev_priv, 0, &config, INTEL_DDB_PART_1_2, &max); /* At least LP0 must be valid */ if (!ilk_validate_wm_level(0, &max, &pipe_wm->wm[0])) { @@ -3150,7 +3147,7 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate) if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) pipe_wm->linetime = hsw_compute_linetime_wm(cstate); - if (!ilk_validate_pipe_wm(dev, pipe_wm)) + if (!ilk_validate_pipe_wm(dev_priv, pipe_wm)) return -EINVAL; ilk_compute_wm_reg_maximums(dev_priv, 1, &max); @@ -3180,17 +3177,17 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *cstate) * state and the new state. These can be programmed to the hardware * immediately. */ -static int ilk_compute_intermediate_wm(struct drm_device *dev, - struct intel_crtc *intel_crtc, - struct intel_crtc_state *newstate) +static int ilk_compute_intermediate_wm(struct intel_crtc_state *newstate) { + struct intel_crtc *intel_crtc = to_intel_crtc(newstate->base.crtc); + struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev); struct intel_pipe_wm *a = &newstate->wm.ilk.intermediate; struct intel_atomic_state *intel_state = to_intel_atomic_state(newstate->base.state); const struct intel_crtc_state *oldstate = intel_atomic_get_old_crtc_state(intel_state, intel_crtc); const struct intel_pipe_wm *b = &oldstate->wm.ilk.optimal; - int level, max_level = ilk_wm_max_level(to_i915(dev)); + int level, max_level = ilk_wm_max_level(dev_priv); /* * Start with the final, target watermarks, then combine with the @@ -3223,7 +3220,7 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev, * there's no safe way to transition from the old state to * the new state, so we need to fail the atomic transaction. */ - if (!ilk_validate_pipe_wm(dev, a)) + if (!ilk_validate_pipe_wm(dev_priv, a)) return -EINVAL; /* @@ -3239,7 +3236,7 @@ static int ilk_compute_intermediate_wm(struct drm_device *dev, /* * Merge the watermarks from all active pipes for a specific level. */ -static void ilk_merge_wm_level(struct drm_device *dev, +static void ilk_merge_wm_level(struct drm_i915_private *dev_priv, int level, struct intel_wm_level *ret_wm) { @@ -3247,7 +3244,7 @@ static void ilk_merge_wm_level(struct drm_device *dev, ret_wm->enable = true; - for_each_intel_crtc(dev, intel_crtc) { + for_each_intel_crtc(&dev_priv->drm, intel_crtc) { const struct intel_pipe_wm *active = &intel_crtc->wm.active.ilk; const struct intel_wm_level *wm = &active->wm[level]; @@ -3272,12 +3269,11 @@ static void ilk_merge_wm_level(struct drm_device *dev, /* * Merge all low power watermarks for all active pipes. */ -static void ilk_wm_merge(struct drm_device *dev, +static void ilk_wm_merge(struct drm_i915_private *dev_priv, const struct intel_wm_config *config, const struct ilk_wm_maximums *max, struct intel_pipe_wm *merged) { - struct drm_i915_private *dev_priv = to_i915(dev); int level, max_level = ilk_wm_max_level(dev_priv); int last_enabled_level = max_level; @@ -3293,7 +3289,7 @@ static void ilk_wm_merge(struct drm_device *dev, for (level = 1; level <= max_level; level++) { struct intel_wm_level *wm = &merged->wm[level]; - ilk_merge_wm_level(dev, level, wm); + ilk_merge_wm_level(dev_priv, level, wm); if (level > last_enabled_level) wm->enable = false; @@ -3318,7 +3314,7 @@ static void ilk_wm_merge(struct drm_device *dev, * What we should check here is whether FBC can be * enabled sometime later. */ - if (IS_GEN5(dev_priv) && !merged->fbc_wm_enabled && + if (IS_GEN(dev_priv, 5) && !merged->fbc_wm_enabled && intel_fbc_is_active(dev_priv)) { for (level = 2; level <= max_level; level++) { struct intel_wm_level *wm = &merged->wm[level]; @@ -3335,22 +3331,20 @@ static int ilk_wm_lp_to_level(int wm_lp, const struct intel_pipe_wm *pipe_wm) } /* The value we need to program into the WM_LPx latency field */ -static unsigned int ilk_wm_lp_latency(struct drm_device *dev, int level) +static unsigned int ilk_wm_lp_latency(struct drm_i915_private *dev_priv, + int level) { - struct drm_i915_private *dev_priv = to_i915(dev); - if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) return 2 * level; else return dev_priv->wm.pri_latency[level]; } -static void ilk_compute_wm_results(struct drm_device *dev, +static void ilk_compute_wm_results(struct drm_i915_private *dev_priv, const struct intel_pipe_wm *merged, enum intel_ddb_partitioning partitioning, struct ilk_wm_values *results) { - struct drm_i915_private *dev_priv = to_i915(dev); struct intel_crtc *intel_crtc; int level, wm_lp; @@ -3370,7 +3364,7 @@ static void ilk_compute_wm_results(struct drm_device *dev, * disabled. Doing otherwise could cause underruns. */ results->wm_lp[wm_lp - 1] = - (ilk_wm_lp_latency(dev, level) << WM1_LP_LATENCY_SHIFT) | + (ilk_wm_lp_latency(dev_priv, level) << WM1_LP_LATENCY_SHIFT) | (r->pri_val << WM1_LP_SR_SHIFT) | r->cur_val; @@ -3396,7 +3390,7 @@ static void ilk_compute_wm_results(struct drm_device *dev, } /* LP0 register values */ - for_each_intel_crtc(dev, intel_crtc) { + for_each_intel_crtc(&dev_priv->drm, intel_crtc) { enum pipe pipe = intel_crtc->pipe; const struct intel_wm_level *r = &intel_crtc->wm.active.ilk.wm[0]; @@ -3415,11 +3409,12 @@ static void ilk_compute_wm_results(struct drm_device *dev, /* Find the result with the highest level enabled. Check for enable_fbc_wm in * case both are at the same level. Prefer r1 in case they're the same. */ -static struct intel_pipe_wm *ilk_find_best_result(struct drm_device *dev, - struct intel_pipe_wm *r1, - struct intel_pipe_wm *r2) +static struct intel_pipe_wm * +ilk_find_best_result(struct drm_i915_private *dev_priv, + struct intel_pipe_wm *r1, + struct intel_pipe_wm *r2) { - int level, max_level = ilk_wm_max_level(to_i915(dev)); + int level, max_level = ilk_wm_max_level(dev_priv); int level1 = 0, level2 = 0; for (level = 1; level <= max_level; level++) { @@ -3756,9 +3751,9 @@ bool intel_can_enable_sagv(struct drm_atomic_state *state) if (!intel_has_sagv(dev_priv)) return false; - if (IS_GEN9(dev_priv)) + if (IS_GEN(dev_priv, 9)) sagv_block_time_us = 30; - else if (IS_GEN10(dev_priv)) + else if (IS_GEN(dev_priv, 10)) sagv_block_time_us = 20; else sagv_block_time_us = 10; @@ -3951,68 +3946,68 @@ 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); } /* @@ -4306,102 +4301,6 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate, return total_data_rate; } -static uint16_t -skl_ddb_min_alloc(const struct drm_plane_state *pstate, const int plane) -{ - struct drm_framebuffer *fb = pstate->fb; - struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate); - uint32_t src_w, src_h; - uint32_t min_scanlines = 8; - uint8_t plane_bpp; - - if (WARN_ON(!fb)) - return 0; - - /* For packed formats, and uv-plane, return 0 */ - if (plane == 1 && fb->format->format != DRM_FORMAT_NV12) - return 0; - - /* For Non Y-tile return 8-blocks */ - if (fb->modifier != I915_FORMAT_MOD_Y_TILED && - fb->modifier != I915_FORMAT_MOD_Yf_TILED && - fb->modifier != I915_FORMAT_MOD_Y_TILED_CCS && - fb->modifier != I915_FORMAT_MOD_Yf_TILED_CCS) - return 8; - - /* - * Src coordinates are already rotated by 270 degrees for - * the 90/270 degree plane rotation cases (to match the - * GTT mapping), hence no need to account for rotation here. - */ - src_w = drm_rect_width(&intel_pstate->base.src) >> 16; - src_h = drm_rect_height(&intel_pstate->base.src) >> 16; - - /* Halve UV plane width and height for NV12 */ - if (plane == 1) { - src_w /= 2; - src_h /= 2; - } - - plane_bpp = fb->format->cpp[plane]; - - if (drm_rotation_90_or_270(pstate->rotation)) { - switch (plane_bpp) { - case 1: - min_scanlines = 32; - break; - case 2: - min_scanlines = 16; - break; - case 4: - min_scanlines = 8; - break; - case 8: - min_scanlines = 4; - break; - default: - WARN(1, "Unsupported pixel depth %u for rotation", - plane_bpp); - min_scanlines = 32; - } - } - - return DIV_ROUND_UP((4 * src_w * plane_bpp), 512) * min_scanlines/4 + 3; -} - -static void -skl_ddb_calc_min(const struct intel_crtc_state *cstate, int num_active, - uint16_t *minimum, uint16_t *uv_minimum) -{ - const struct drm_plane_state *pstate; - struct drm_plane *plane; - - drm_atomic_crtc_state_for_each_plane_state(plane, pstate, &cstate->base) { - enum plane_id plane_id = to_intel_plane(plane)->id; - struct intel_plane_state *plane_state = to_intel_plane_state(pstate); - - if (plane_id == PLANE_CURSOR) - continue; - - /* slave plane must be invisible and calculated from master */ - if (!pstate->visible || WARN_ON(plane_state->slave)) - continue; - - if (!plane_state->linked_plane) { - minimum[plane_id] = skl_ddb_min_alloc(pstate, 0); - uv_minimum[plane_id] = skl_ddb_min_alloc(pstate, 1); - } else { - enum plane_id y_plane_id = - plane_state->linked_plane->id; - - minimum[y_plane_id] = skl_ddb_min_alloc(pstate, 0); - minimum[plane_id] = skl_ddb_min_alloc(pstate, 1); - } - } - - minimum[PLANE_CURSOR] = skl_cursor_allocation(num_active); -} - static int skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, struct skl_ddb_allocation *ddb /* out */) @@ -4410,21 +4309,22 @@ 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] = {}; - uint16_t uv_minimum[I915_MAX_PLANES] = {}; + struct skl_plane_wm *wm; + uint16_t alloc_size, start = 0; + uint16_t total[I915_MAX_PLANES] = {}; + uint16_t uv_total[I915_MAX_PLANES] = {}; u64 total_data_rate; enum plane_id plane_id; int num_active; u64 plane_data_rate[I915_MAX_PLANES] = {}; u64 uv_plane_data_rate[I915_MAX_PLANES] = {}; - uint16_t total_min_blocks = 0; + uint16_t blocks = 0; + int level; /* 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; @@ -4450,81 +4350,135 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate, if (alloc_size == 0) return 0; - skl_ddb_calc_min(cstate, num_active, minimum, uv_minimum); + /* Allocate fixed number of blocks for cursor. */ + total[PLANE_CURSOR] = skl_cursor_allocation(num_active); + alloc_size -= total[PLANE_CURSOR]; + cstate->wm.skl.plane_ddb_y[PLANE_CURSOR].start = + alloc->end - total[PLANE_CURSOR]; + cstate->wm.skl.plane_ddb_y[PLANE_CURSOR].end = alloc->end; + + if (total_data_rate == 0) + return 0; /* - * 1. Allocate the mininum required blocks for each active plane - * and allocate the cursor, it doesn't require extra allocation - * proportional to the data rate. + * Find the highest watermark level for which we can satisfy the block + * requirement of active planes. */ + for (level = ilk_wm_max_level(dev_priv); level >= 0; level--) { + blocks = 0; + for_each_plane_id_on_crtc(intel_crtc, plane_id) { + if (plane_id == PLANE_CURSOR) + continue; - for_each_plane_id_on_crtc(intel_crtc, plane_id) { - total_min_blocks += minimum[plane_id]; - total_min_blocks += uv_minimum[plane_id]; + wm = &cstate->wm.skl.optimal.planes[plane_id]; + blocks += wm->wm[level].plane_res_b; + blocks += wm->uv_wm[level].plane_res_b; + } + + if (blocks < alloc_size) { + alloc_size -= blocks; + break; + } } - if (total_min_blocks > alloc_size) { + if (level < 0) { DRM_DEBUG_KMS("Requested display configuration exceeds system DDB limitations"); - DRM_DEBUG_KMS("minimum required %d/%d\n", total_min_blocks, - alloc_size); + DRM_DEBUG_KMS("minimum required %d/%d\n", blocks, + alloc_size); return -EINVAL; } - alloc_size -= total_min_blocks; - ddb->plane[pipe][PLANE_CURSOR].start = alloc->end - minimum[PLANE_CURSOR]; - ddb->plane[pipe][PLANE_CURSOR].end = alloc->end; - /* - * 2. Distribute the remaining space in proportion to the amount of - * data each plane needs to fetch from memory. - * - * FIXME: we may not allocate every single block here. + * Grant each plane the blocks it requires at the highest achievable + * watermark level, plus an extra share of the leftover blocks + * proportional to its relative data rate. */ - if (total_data_rate == 0) - return 0; - - start = alloc->start; for_each_plane_id_on_crtc(intel_crtc, plane_id) { - u64 data_rate, uv_data_rate; - uint16_t plane_blocks, uv_plane_blocks; + u64 rate; + u16 extra; if (plane_id == PLANE_CURSOR) continue; - data_rate = plane_data_rate[plane_id]; - /* - * allocation for (packed formats) or (uv-plane part of planar format): - * promote the expression to 64 bits to avoid overflowing, the - * result is < available as data_rate / total_data_rate < 1 + * We've accounted for all active planes; remaining planes are + * all disabled. */ - plane_blocks = minimum[plane_id]; - plane_blocks += div64_u64(alloc_size * data_rate, total_data_rate); + if (total_data_rate == 0) + break; - /* 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; - } + wm = &cstate->wm.skl.optimal.planes[plane_id]; - start += plane_blocks; + rate = plane_data_rate[plane_id]; + extra = min_t(u16, alloc_size, + DIV64_U64_ROUND_UP(alloc_size * rate, + total_data_rate)); + total[plane_id] = wm->wm[level].plane_res_b + extra; + alloc_size -= extra; + total_data_rate -= rate; - /* Allocate DDB for UV plane for planar format/NV12 */ - uv_data_rate = uv_plane_data_rate[plane_id]; + if (total_data_rate == 0) + break; + + rate = uv_plane_data_rate[plane_id]; + extra = min_t(u16, alloc_size, + DIV64_U64_ROUND_UP(alloc_size * rate, + total_data_rate)); + uv_total[plane_id] = wm->uv_wm[level].plane_res_b + extra; + alloc_size -= extra; + total_data_rate -= rate; + } + WARN_ON(alloc_size != 0 || total_data_rate != 0); + + /* Set the actual DDB start/end points for each plane */ + start = alloc->start; + for_each_plane_id_on_crtc(intel_crtc, plane_id) { + struct skl_ddb_entry *plane_alloc, *uv_plane_alloc; + + if (plane_id == PLANE_CURSOR) + continue; - uv_plane_blocks = uv_minimum[plane_id]; - uv_plane_blocks += div64_u64(alloc_size * uv_data_rate, total_data_rate); + plane_alloc = &cstate->wm.skl.plane_ddb_y[plane_id]; + uv_plane_alloc = &cstate->wm.skl.plane_ddb_uv[plane_id]; /* Gen11+ uses a separate plane for UV watermarks */ - WARN_ON(INTEL_GEN(dev_priv) >= 11 && uv_plane_blocks); + WARN_ON(INTEL_GEN(dev_priv) >= 11 && uv_total[plane_id]); + + /* Leave disabled planes at (0,0) */ + if (total[plane_id]) { + plane_alloc->start = start; + start += total[plane_id]; + plane_alloc->end = start; + } - if (uv_data_rate) { - ddb->uv_plane[pipe][plane_id].start = start; - ddb->uv_plane[pipe][plane_id].end = - start + uv_plane_blocks; + if (uv_total[plane_id]) { + uv_plane_alloc->start = start; + start += uv_total[plane_id]; + uv_plane_alloc->end = start; } + } - start += uv_plane_blocks; + /* + * When we calculated watermark values we didn't know how high + * of a level we'd actually be able to hit, so we just marked + * all levels as "enabled." Go back now and disable the ones + * that aren't actually possible. + */ + for (level++; level <= ilk_wm_max_level(dev_priv); level++) { + for_each_plane_id_on_crtc(intel_crtc, plane_id) { + wm = &cstate->wm.skl.optimal.planes[plane_id]; + memset(&wm->wm[level], 0, sizeof(wm->wm[level])); + } + } + + /* + * Go back and disable the transition watermark if it turns out we + * don't have enough DDB blocks for it. + */ + for_each_plane_id_on_crtc(intel_crtc, plane_id) { + wm = &cstate->wm.skl.optimal.planes[plane_id]; + if (wm->trans_wm.plane_res_b > total[plane_id]) + memset(&wm->trans_wm, 0, sizeof(wm->trans_wm)); } return 0; @@ -4617,12 +4571,12 @@ 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 +4584,8 @@ 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 +4610,10 @@ 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); @@ -4706,7 +4657,7 @@ skl_compute_plane_wm_params(const struct drm_i915_private *dev_priv, wp->plane_blocks_per_line = div_fixed16(interm_pbpl, wp->y_min_scanlines); - } else if (wp->x_tiled && IS_GEN9(dev_priv)) { + } else if (wp->x_tiled && IS_GEN(dev_priv, 9)) { interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, wp->dbuf_block_size); wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl); @@ -4724,16 +4675,15 @@ 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, - const struct intel_plane_state *intel_pstate, - uint16_t ddb_allocation, - int level, - const struct skl_wm_params *wp, - const struct skl_wm_level *result_prev, - struct skl_wm_level *result /* out */) +static void skl_compute_plane_wm(const struct intel_crtc_state *cstate, + const struct intel_plane_state *intel_pstate, + int level, + const struct skl_wm_params *wp, + const struct skl_wm_level *result_prev, + struct skl_wm_level *result /* out */) { - const struct drm_plane_state *pstate = &intel_pstate->base; + struct drm_i915_private *dev_priv = + to_i915(intel_pstate->base.plane->dev); uint32_t latency = dev_priv->wm.skl_latency[level]; uint_fixed_16_16_t method1, method2; uint_fixed_16_16_t selected_result; @@ -4741,13 +4691,6 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, struct intel_atomic_state *state = to_intel_atomic_state(cstate->base.state); 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; - } /* Display WA #1141: kbl,cfl */ if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv) || @@ -4772,15 +4715,8 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, wp->dbuf_block_size < 1) && (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) { selected_result = method2; - } else if (ddb_allocation >= - fixed16_to_u32_round_up(wp->plane_blocks_per_line)) { - if (IS_GEN9(dev_priv) && - !IS_GEMINILAKE(dev_priv)) - selected_result = min_fixed16(method1, method2); - else - selected_result = method2; } else if (latency >= wp->linetime_us) { - if (IS_GEN9(dev_priv) && + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv)) selected_result = min_fixed16(method1, method2); else @@ -4794,121 +4730,67 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, res_lines = div_round_up_fixed16(selected_result, wp->plane_blocks_per_line); - /* Display WA #1125: skl,bxt,kbl,glk */ - if (level == 0 && wp->rc_surface) - res_blocks += fixed16_to_u32_round_up(wp->y_tile_minimum); - - /* Display WA #1126: skl,bxt,kbl,glk */ - if (level >= 1 && level <= 7) { - if (wp->y_tiled) { - res_blocks += fixed16_to_u32_round_up( - wp->y_tile_minimum); - res_lines += wp->y_min_scanlines; - } else { - res_blocks++; - } - - /* - * Make sure result blocks for higher latency levels are atleast - * as high as level below the current level. - * Assumption in DDB algorithm optimization for special cases. - * Also covers Display WA #1125 for RC. - */ - if (result_prev->plane_res_b > res_blocks) - res_blocks = result_prev->plane_res_b; - } - - if (INTEL_GEN(dev_priv) >= 11) { - if (wp->y_tiled) { - uint32_t extra_lines; - uint_fixed_16_16_t fp_min_disp_buf_needed; - - if (res_lines % wp->y_min_scanlines == 0) - extra_lines = wp->y_min_scanlines; - else - extra_lines = wp->y_min_scanlines * 2 - - res_lines % wp->y_min_scanlines; - - fp_min_disp_buf_needed = mul_u32_fixed16(res_lines + - extra_lines, - wp->plane_blocks_per_line); - min_disp_buf_needed = fixed16_to_u32_round_up( - fp_min_disp_buf_needed); - } else { - min_disp_buf_needed = DIV_ROUND_UP(res_blocks * 11, 10); - } - } else { - min_disp_buf_needed = res_blocks; - } - - 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. - */ - if (level) { - return 0; - } else { - struct drm_plane *plane = pstate->plane; + if (IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) { + /* Display WA #1125: skl,bxt,kbl */ + if (level == 0 && wp->rc_surface) + res_blocks += + fixed16_to_u32_round_up(wp->y_tile_minimum); + + /* Display WA #1126: skl,bxt,kbl */ + if (level >= 1 && level <= 7) { + if (wp->y_tiled) { + res_blocks += + fixed16_to_u32_round_up(wp->y_tile_minimum); + res_lines += wp->y_min_scanlines; + } else { + res_blocks++; + } - DRM_DEBUG_KMS("Requested display configuration exceeds system watermark limitations\n"); - DRM_DEBUG_KMS("[PLANE:%d:%s] blocks required = %u/%u, lines required = %u/31\n", - plane->base.id, plane->name, - res_blocks, ddb_allocation, res_lines); - return -EINVAL; + /* + * Make sure result blocks for higher latency levels are + * atleast as high as level below the current level. + * Assumption in DDB algorithm optimization for special + * cases. Also covers Display WA #1125 for RC. + */ + if (result_prev->plane_res_b > res_blocks) + res_blocks = result_prev->plane_res_b; } } /* The number of lines are ignored for the level 0 watermark. */ + if (level > 0 && res_lines > 31) + return; + + /* + * If res_lines is valid, assume we can use this watermark level + * for now. We'll come back and disable it after we calculate the + * DDB allocation if it turns out we don't actually have enough + * blocks to satisfy it. + */ result->plane_res_b = res_blocks; result->plane_res_l = res_lines; result->plane_en = true; - - return 0; } -static int -skl_compute_wm_levels(const struct drm_i915_private *dev_priv, - struct skl_ddb_allocation *ddb, - const struct intel_crtc_state *cstate, +static void +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, - intel_pstate, - ddb_blocks, - level, - wm_params, - result_prev, - result); - if (ret) - return ret; + skl_compute_plane_wm(cstate, intel_pstate, level, wm_params, + result_prev, result); result_prev = result; } - - if (intel_pstate->base.fb->format->format == DRM_FORMAT_NV12) - wm->is_planar = true; - - return 0; } static uint32_t @@ -4935,10 +4817,8 @@ 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) { struct drm_device *dev = cstate->base.crtc->dev; const struct drm_i915_private *dev_priv = to_i915(dev); @@ -4946,16 +4826,13 @@ 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 +4850,7 @@ 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, @@ -4989,110 +4866,124 @@ 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; - } - -exit: - trans_wm->plane_en = false; + /* + * Just assume we can enable the transition watermark. After + * computing the DDB we'll come back and disable it if that + * assumption turns out to be false. + */ + wm->trans_wm.plane_res_b = res_blocks + 1; + wm->trans_wm.plane_en = true; } -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]; 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); - - if (ret) - return ret; - - skl_compute_transition_wm(cstate, &wm_params, &wm->wm[0], - ddb_blocks, &wm->trans_wm); + skl_compute_wm_levels(crtc_state, plane_state, &wm_params, wm->wm); + skl_compute_transition_wm(crtc_state, &wm_params, wm); 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) +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) { - enum plane_id plane_id = to_intel_plane(pstate->base.plane)->id; + struct skl_plane_wm *wm = &crtc_state->wm.skl.optimal.planes[plane_id]; + struct skl_wm_params wm_params; + int ret; - return __skl_build_plane_wm_single(ddb, pipe_wm, plane_id, cstate, pstate, 0); + wm->is_planar = true; + + /* uv plane watermarks must also be validated for NV12/Planar */ + ret = skl_compute_plane_wm_params(crtc_state, plane_state, + &wm_params, 1); + if (ret) + return ret; + + skl_compute_wm_levels(crtc_state, plane_state, &wm_params, wm->uv_wm); + + return 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(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(pstate->base.plane); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); + 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; - struct skl_plane_wm *wm = &pipe_wm->planes[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; - - /* uv plane watermarks must also be validated for NV12/Planar */ - ddb_blocks = skl_ddb_entry_size(&ddb->uv_plane[pipe][plane_id]); + if (!intel_wm_plane_visible(crtc_state, plane_state)) + return 0; - ret = skl_compute_plane_wm_params(dev_priv, cstate, pstate, &wm_params, 1); + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane_id, 0); if (ret) return ret; - return skl_compute_wm_levels(dev_priv, ddb, cstate, pstate, - ddb_blocks, &wm_params, wm, wm->uv_wm); + 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_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 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; - 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 (ret) - return 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; - return __skl_build_plane_wm_single(ddb, pipe_wm, uv_plane_id, - cstate, pstate, 1); + 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 +4999,12 @@ 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 +5019,9 @@ 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 +5036,22 @@ 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 +5060,32 @@ 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 +5093,30 @@ 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, @@ -5241,16 +5140,14 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, return false; } -static int skl_update_pipe_wm(struct drm_crtc_state *cstate, +static int skl_update_pipe_wm(struct intel_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(cstate, pipe_wm); if (ret) return ret; @@ -5263,78 +5160,67 @@ static int skl_update_pipe_wm(struct drm_crtc_state *cstate, } static uint32_t -pipes_modified(struct drm_atomic_state *state) +pipes_modified(struct intel_atomic_state *state) { - struct drm_crtc *crtc; - struct drm_crtc_state *cstate; + struct intel_crtc *crtc; + struct intel_crtc_state *cstate; uint32_t i, ret = 0; - for_each_new_crtc_in_state(state, crtc, cstate, i) - ret |= drm_crtc_mask(crtc); + for_each_new_intel_crtc_in_state(state, crtc, cstate, i) + ret |= drm_crtc_mask(&crtc->base); return ret; } 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; } static int -skl_compute_ddb(struct drm_atomic_state *state) +skl_compute_ddb(struct intel_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; + const struct drm_i915_private *dev_priv = to_i915(state->base.dev); + struct skl_ddb_allocation *ddb = &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(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 +5229,29 @@ 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); } @@ -5380,14 +5259,12 @@ skl_print_wm_changes(const struct drm_atomic_state *state) } static int -skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed) +skl_ddb_add_affected_pipes(struct intel_atomic_state *state, bool *changed) { - struct drm_device *dev = state->dev; + struct drm_device *dev = state->base.dev; const struct drm_i915_private *dev_priv = to_i915(dev); - const struct drm_crtc *crtc; - const struct drm_crtc_state *cstate; - struct intel_crtc *intel_crtc; - struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct intel_crtc *crtc; + struct intel_crtc_state *crtc_state; uint32_t realloc_pipes = pipes_modified(state); int ret, i; @@ -5406,7 +5283,7 @@ skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed) * since any racing commits that want to update them would need to * hold _all_ CRTC state mutexes. */ - for_each_new_crtc_in_state(state, crtc, cstate, i) + for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) (*changed) = true; if (!*changed) @@ -5420,20 +5297,20 @@ skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed) */ if (dev_priv->wm.distrust_bios_wm) { ret = drm_modeset_lock(&dev->mode_config.connection_mutex, - state->acquire_ctx); + state->base.acquire_ctx); if (ret) return ret; - intel_state->active_pipe_changes = ~0; + state->active_pipe_changes = ~0; /* - * We usually only initialize intel_state->active_crtcs if we + * We usually only initialize state->active_crtcs if we * we're doing a modeset; make sure this field is always * initialized during the sanitization process that happens * on the first commit too. */ - if (!intel_state->modeset) - intel_state->active_crtcs = dev_priv->active_crtcs; + if (!state->modeset) + state->active_crtcs = dev_priv->active_crtcs; } /* @@ -5449,33 +5326,91 @@ skl_ddb_add_affected_pipes(struct drm_atomic_state *state, bool *changed) * any other display updates race with this transaction, so we need * to grab the lock on *all* CRTC's. */ - if (intel_state->active_pipe_changes || intel_state->modeset) { + if (state->active_pipe_changes || state->modeset) { realloc_pipes = ~0; - intel_state->wm_results.dirty_pipes = ~0; + state->wm_results.dirty_pipes = ~0; } /* * We're not recomputing for the pipes not included in the commit, so * make sure we start with the current state. */ - for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) { - struct intel_crtc_state *cstate; + for_each_intel_crtc_mask(dev, crtc, realloc_pipes) { + crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + } + + 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; - cstate = intel_atomic_get_crtc_state(state, intel_crtc); - if (IS_ERR(cstate)) - return PTR_ERR(cstate); + 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) +skl_compute_wm(struct intel_atomic_state *state) { - struct drm_crtc *crtc; - struct drm_crtc_state *cstate; - struct intel_atomic_state *intel_state = to_intel_atomic_state(state); - struct skl_ddb_values *results = &intel_state->wm_results; + struct intel_crtc *crtc; + struct intel_crtc_state *cstate; + struct intel_crtc_state *old_crtc_state; + struct skl_ddb_values *results = &state->wm_results; struct skl_pipe_wm *pipe_wm; bool changed = false; int ret, i; @@ -5487,42 +5422,34 @@ skl_compute_wm(struct drm_atomic_state *state) if (ret || !changed) return ret; - ret = skl_compute_ddb(state); - if (ret) - return ret; - /* * Calculate WM's for all pipes that are part of this transaction. - * Note that the DDB allocation above may have added more CRTC's that + * Note that skl_ddb_add_affected_pipes may have added more CRTC's that * weren't otherwise being modified (and set bits in dirty_pipes) if * pipe allocations had to change. - * - * FIXME: Now that we're doing this in the atomic check phase, we - * should allow skl_update_pipe_wm() to return failure in cases where - * no suitable watermark values can be found. */ - for_each_new_crtc_in_state(state, crtc, cstate, i) { - struct intel_crtc_state *intel_cstate = - to_intel_crtc_state(cstate); + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + cstate, i) { const struct skl_pipe_wm *old_pipe_wm = - &to_intel_crtc_state(crtc->state)->wm.skl.optimal; + &old_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); + pipe_wm = &cstate->wm.skl.optimal; + ret = skl_update_pipe_wm(cstate, old_pipe_wm, pipe_wm, &changed); if (ret) return ret; - if (changed) - results->dirty_pipes |= drm_crtc_mask(crtc); - - if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0) - /* This pipe's WM's did not change */ - continue; + ret = skl_wm_add_affected_planes(state, crtc); + if (ret) + return ret; - intel_cstate->update_wm_pre = true; + if (changed) + results->dirty_pipes |= drm_crtc_mask(&crtc->base); } + ret = skl_compute_ddb(state); + if (ret) + return ret; + skl_print_wm_changes(state); return 0; @@ -5534,23 +5461,12 @@ 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 +5476,6 @@ 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; @@ -5571,21 +5485,16 @@ 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); } -static void ilk_compute_wm_config(struct drm_device *dev, +static void ilk_compute_wm_config(struct drm_i915_private *dev_priv, struct intel_wm_config *config) { struct intel_crtc *crtc; /* Compute the currently _active_ config */ - for_each_intel_crtc(dev, crtc) { + for_each_intel_crtc(&dev_priv->drm, crtc) { const struct intel_pipe_wm *wm = &crtc->wm.active.ilk; if (!wm->pipe_enabled) @@ -5599,25 +5508,24 @@ static void ilk_compute_wm_config(struct drm_device *dev, static void ilk_program_watermarks(struct drm_i915_private *dev_priv) { - struct drm_device *dev = &dev_priv->drm; struct intel_pipe_wm lp_wm_1_2 = {}, lp_wm_5_6 = {}, *best_lp_wm; struct ilk_wm_maximums max; struct intel_wm_config config = {}; struct ilk_wm_values results = {}; enum intel_ddb_partitioning partitioning; - ilk_compute_wm_config(dev, &config); + ilk_compute_wm_config(dev_priv, &config); - ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_1_2, &max); - ilk_wm_merge(dev, &config, &max, &lp_wm_1_2); + ilk_compute_wm_maximums(dev_priv, 1, &config, INTEL_DDB_PART_1_2, &max); + ilk_wm_merge(dev_priv, &config, &max, &lp_wm_1_2); /* 5/6 split only in single pipe config on IVB+ */ if (INTEL_GEN(dev_priv) >= 7 && config.num_pipes_active == 1 && config.sprites_enabled) { - ilk_compute_wm_maximums(dev, 1, &config, INTEL_DDB_PART_5_6, &max); - ilk_wm_merge(dev, &config, &max, &lp_wm_5_6); + ilk_compute_wm_maximums(dev_priv, 1, &config, INTEL_DDB_PART_5_6, &max); + ilk_wm_merge(dev_priv, &config, &max, &lp_wm_5_6); - best_lp_wm = ilk_find_best_result(dev, &lp_wm_1_2, &lp_wm_5_6); + best_lp_wm = ilk_find_best_result(dev_priv, &lp_wm_1_2, &lp_wm_5_6); } else { best_lp_wm = &lp_wm_1_2; } @@ -5625,7 +5533,7 @@ static void ilk_program_watermarks(struct drm_i915_private *dev_priv) partitioning = (best_lp_wm == &lp_wm_1_2) ? INTEL_DDB_PART_1_2 : INTEL_DDB_PART_5_6; - ilk_compute_wm_results(dev, best_lp_wm, partitioning, &results); + ilk_compute_wm_results(dev_priv, best_lp_wm, partitioning, &results); ilk_write_wm_values(dev_priv, &results); } @@ -5665,19 +5573,18 @@ static inline void skl_wm_level_from_reg_val(uint32_t val, PLANE_WM_LINES_MASK; } -void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc, +void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc, struct skl_pipe_wm *out) { - 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 drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; int level, max_level; enum plane_id plane_id; uint32_t val; max_level = ilk_wm_max_level(dev_priv); - for_each_plane_id_on_crtc(intel_crtc, plane_id) { + for_each_plane_id_on_crtc(crtc, plane_id) { struct skl_plane_wm *wm = &out->planes[plane_id]; for (level = 0; level <= max_level; level++) { @@ -5697,54 +5604,43 @@ void skl_pipe_wm_get_hw_state(struct drm_crtc *crtc, skl_wm_level_from_reg_val(val, &wm->trans_wm); } - if (!intel_crtc->active) + if (!crtc->active) return; out->linetime = I915_READ(PIPE_WM_LINETIME(pipe)); } -void skl_wm_get_hw_state(struct drm_device *dev) +void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); struct skl_ddb_values *hw = &dev_priv->wm.skl_hw; struct skl_ddb_allocation *ddb = &dev_priv->wm.skl_hw.ddb; - struct drm_crtc *crtc; - struct intel_crtc *intel_crtc; + struct intel_crtc *crtc; struct intel_crtc_state *cstate; skl_ddb_get_hw_state(dev_priv, ddb); - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - intel_crtc = to_intel_crtc(crtc); - cstate = to_intel_crtc_state(crtc->state); + for_each_intel_crtc(&dev_priv->drm, crtc) { + cstate = to_intel_crtc_state(crtc->base.state); skl_pipe_wm_get_hw_state(crtc, &cstate->wm.skl.optimal); - if (intel_crtc->active) - hw->dirty_pipes |= drm_crtc_mask(crtc); + if (crtc->active) + hw->dirty_pipes |= drm_crtc_mask(&crtc->base); } 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)); } } -static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) +static void ilk_pipe_wm_get_hw_state(struct intel_crtc *crtc) { - struct drm_device *dev = crtc->dev; + struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); struct ilk_wm_values *hw = &dev_priv->wm.hw; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); + struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->base.state); struct intel_pipe_wm *active = &cstate->wm.ilk.optimal; - enum pipe pipe = intel_crtc->pipe; + enum pipe pipe = crtc->pipe; static const i915_reg_t wm0_pipe_reg[] = { [PIPE_A] = WM0_PIPEA_ILK, [PIPE_B] = WM0_PIPEB_ILK, @@ -5757,7 +5653,7 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) memset(active, 0, sizeof(*active)); - active->pipe_enabled = intel_crtc->active; + active->pipe_enabled = crtc->active; if (active->pipe_enabled) { u32 tmp = hw->wm_pipe[pipe]; @@ -5785,7 +5681,7 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) active->wm[level].enable = true; } - intel_crtc->wm.active.ilk = *active; + crtc->wm.active.ilk = *active; } #define _FW_WM(value, plane) \ @@ -5895,9 +5791,8 @@ static void vlv_read_wm_values(struct drm_i915_private *dev_priv, #undef _FW_WM #undef _FW_WM_VLV -void g4x_wm_get_hw_state(struct drm_device *dev) +void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); struct g4x_wm_values *wm = &dev_priv->wm.g4x; struct intel_crtc *crtc; @@ -5905,7 +5800,7 @@ void g4x_wm_get_hw_state(struct drm_device *dev) wm->cxsr = I915_READ(FW_BLC_SELF) & FW_BLC_SELF_EN; - for_each_intel_crtc(dev, crtc) { + for_each_intel_crtc(&dev_priv->drm, crtc) { struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct g4x_wm_state *active = &crtc->wm.active.g4x; @@ -6036,9 +5931,8 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv) mutex_unlock(&dev_priv->wm.wm_mutex); } -void vlv_wm_get_hw_state(struct drm_device *dev) +void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); struct vlv_wm_values *wm = &dev_priv->wm.vlv; struct intel_crtc *crtc; u32 val; @@ -6082,7 +5976,7 @@ void vlv_wm_get_hw_state(struct drm_device *dev) mutex_unlock(&dev_priv->pcu_lock); } - for_each_intel_crtc(dev, crtc) { + for_each_intel_crtc(&dev_priv->drm, crtc) { struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct vlv_wm_state *active = &crtc->wm.active.vlv; @@ -6199,15 +6093,14 @@ static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv) */ } -void ilk_wm_get_hw_state(struct drm_device *dev) +void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct drm_i915_private *dev_priv = to_i915(dev); struct ilk_wm_values *hw = &dev_priv->wm.hw; - struct drm_crtc *crtc; + struct intel_crtc *crtc; ilk_init_lp_watermarks(dev_priv); - for_each_crtc(dev, crtc) + for_each_intel_crtc(&dev_priv->drm, crtc) ilk_pipe_wm_get_hw_state(crtc); hw->wm_lp[0] = I915_READ(WM1_LP_ILK); @@ -7018,7 +6911,7 @@ static void gen9_enable_rps(struct drm_i915_private *dev_priv) intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); /* Program defaults and thresholds for RPS */ - if (IS_GEN9(dev_priv)) + if (IS_GEN(dev_priv, 9)) I915_WRITE(GEN6_RC_VIDEO_FREQ, GEN9_FREQUENCY(dev_priv->gt_pm.rps.rp1_freq)); @@ -7254,9 +7147,9 @@ static void gen6_enable_rc6(struct drm_i915_private *dev_priv) rc6vids = 0; ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS, &rc6vids); - if (IS_GEN6(dev_priv) && ret) { + if (IS_GEN(dev_priv, 6) && ret) { DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n"); - } else if (IS_GEN6(dev_priv) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) { + } else if (IS_GEN(dev_priv, 6) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) { DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n", GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450); rc6vids &= 0xffff00; @@ -7381,7 +7274,7 @@ static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv) val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE); - switch (INTEL_INFO(dev_priv)->sseu.eu_total) { + switch (RUNTIME_INFO(dev_priv)->sseu.eu_total) { case 8: /* (2 * 4) config */ rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT); @@ -7956,7 +7849,7 @@ unsigned long i915_chipset_val(struct drm_i915_private *dev_priv) { unsigned long val; - if (!IS_GEN5(dev_priv)) + if (!IS_GEN(dev_priv, 5)) return 0; spin_lock_irq(&mchdev_lock); @@ -8040,7 +7933,7 @@ static void __i915_update_gfx_val(struct drm_i915_private *dev_priv) void i915_update_gfx_val(struct drm_i915_private *dev_priv) { - if (!IS_GEN5(dev_priv)) + if (!IS_GEN(dev_priv, 5)) return; spin_lock_irq(&mchdev_lock); @@ -8091,7 +7984,7 @@ unsigned long i915_gfx_val(struct drm_i915_private *dev_priv) { unsigned long val; - if (!IS_GEN5(dev_priv)) + if (!IS_GEN(dev_priv, 5)) return 0; spin_lock_irq(&mchdev_lock); @@ -8379,7 +8272,7 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) intel_freq_opcode(dev_priv, 450)); /* After setting max-softlimit, find the overclock max freq */ - if (IS_GEN6(dev_priv) || + if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv)) { u32 params = 0; @@ -9449,9 +9342,9 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) dev_priv->display.init_clock_gating = ivb_init_clock_gating; else if (IS_VALLEYVIEW(dev_priv)) dev_priv->display.init_clock_gating = vlv_init_clock_gating; - else if (IS_GEN6(dev_priv)) + else if (IS_GEN(dev_priv, 6)) dev_priv->display.init_clock_gating = gen6_init_clock_gating; - else if (IS_GEN5(dev_priv)) + else if (IS_GEN(dev_priv, 5)) dev_priv->display.init_clock_gating = ilk_init_clock_gating; else if (IS_G4X(dev_priv)) dev_priv->display.init_clock_gating = g4x_init_clock_gating; @@ -9459,11 +9352,11 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) dev_priv->display.init_clock_gating = i965gm_init_clock_gating; else if (IS_I965G(dev_priv)) dev_priv->display.init_clock_gating = i965g_init_clock_gating; - else if (IS_GEN3(dev_priv)) + else if (IS_GEN(dev_priv, 3)) dev_priv->display.init_clock_gating = gen3_init_clock_gating; else if (IS_I85X(dev_priv) || IS_I865G(dev_priv)) dev_priv->display.init_clock_gating = i85x_init_clock_gating; - else if (IS_GEN2(dev_priv)) + else if (IS_GEN(dev_priv, 2)) dev_priv->display.init_clock_gating = i830_init_clock_gating; else { MISSING_CASE(INTEL_DEVID(dev_priv)); @@ -9477,7 +9370,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv) /* For cxsr */ if (IS_PINEVIEW(dev_priv)) i915_pineview_get_mem_freq(dev_priv); - else if (IS_GEN5(dev_priv)) + else if (IS_GEN(dev_priv, 5)) i915_ironlake_get_mem_freq(dev_priv); /* For FIFO watermark updates */ @@ -9489,9 +9382,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv) } else if (HAS_PCH_SPLIT(dev_priv)) { ilk_setup_wm_latency(dev_priv); - if ((IS_GEN5(dev_priv) && dev_priv->wm.pri_latency[1] && + if ((IS_GEN(dev_priv, 5) && dev_priv->wm.pri_latency[1] && dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || - (!IS_GEN5(dev_priv) && dev_priv->wm.pri_latency[0] && + (!IS_GEN(dev_priv, 5) && dev_priv->wm.pri_latency[0] && dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { dev_priv->display.compute_pipe_wm = ilk_compute_pipe_wm; dev_priv->display.compute_intermediate_wm = @@ -9532,12 +9425,12 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->display.update_wm = NULL; } else dev_priv->display.update_wm = pineview_update_wm; - } else if (IS_GEN4(dev_priv)) { + } else if (IS_GEN(dev_priv, 4)) { dev_priv->display.update_wm = i965_update_wm; - } else if (IS_GEN3(dev_priv)) { + } else if (IS_GEN(dev_priv, 3)) { dev_priv->display.update_wm = i9xx_update_wm; dev_priv->display.get_fifo_size = i9xx_get_fifo_size; - } else if (IS_GEN2(dev_priv)) { + } else if (IS_GEN(dev_priv, 2)) { if (INTEL_INFO(dev_priv)->num_pipes == 1) { dev_priv->display.update_wm = i845_update_wm; dev_priv->display.get_fifo_size = i845_get_fifo_size; diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c index 54fa17a5596a..dce39f06b682 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) @@ -237,6 +261,32 @@ static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp) return val; } +static u16 intel_dp_get_su_x_granulartiy(struct intel_dp *intel_dp) +{ + u16 val; + ssize_t r; + + /* + * Returning the default X granularity if granularity not required or + * if DPCD read fails + */ + if (!(intel_dp->psr_dpcd[1] & DP_PSR2_SU_GRANULARITY_REQUIRED)) + return 4; + + r = drm_dp_dpcd_read(&intel_dp->aux, DP_PSR2_SU_X_GRANULARITY, &val, 2); + if (r != 2) + DRM_DEBUG_KMS("Unable to read DP_PSR2_SU_X_GRANULARITY\n"); + + /* + * Spec says that if the value read is 0 the default granularity should + * be used instead. + */ + if (r != 2 || val == 0) + val = 4; + + return val; +} + void intel_psr_init_dpcd(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = @@ -250,10 +300,16 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp) DRM_DEBUG_KMS("eDP panel supports PSR version %x\n", intel_dp->psr_dpcd[0]); + if (drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_NO_PSR)) { + DRM_DEBUG_KMS("PSR support not currently available for this panel\n"); + return; + } + if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) { DRM_DEBUG_KMS("Panel lacks power state control, PSR cannot be enabled\n"); return; } + dev_priv->psr.sink_support = true; dev_priv->psr.sink_sync_latency = intel_dp_get_sink_sync_latency(intel_dp); @@ -285,6 +341,8 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp) if (dev_priv->psr.sink_psr2_support) { dev_priv->psr.colorimetry_support = intel_dp_get_colorimetry_status(intel_dp); + dev_priv->psr.su_x_granularity = + intel_dp_get_su_x_granulartiy(intel_dp); } } } @@ -364,13 +422,15 @@ static void intel_psr_enable_sink(struct intel_dp *intel_dp) if (dev_priv->psr.psr2_enabled) { drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG, DP_ALPM_ENABLE); - dpcd_val |= DP_PSR_ENABLE_PSR2; + dpcd_val |= DP_PSR_ENABLE_PSR2 | DP_PSR_IRQ_HPD_WITH_CRC_ERRORS; + } else { + if (dev_priv->psr.link_standby) + dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE; + + if (INTEL_GEN(dev_priv) >= 8) + dpcd_val |= DP_PSR_CRC_VERIFICATION; } - if (dev_priv->psr.link_standby) - dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE; - if (!dev_priv->psr.psr2_enabled && INTEL_GEN(dev_priv) >= 8) - dpcd_val |= DP_PSR_CRC_VERIFICATION; drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val); drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0); @@ -444,9 +504,6 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp) idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1); val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT; - /* FIXME: selective update is probably totally broken because it doesn't - * mesh at all with our frontbuffer tracking. And the hw alone isn't - * good enough. */ val |= EDP_PSR2_ENABLE | EDP_SU_TRACK_ENABLE; if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) val |= EDP_Y_COORDINATE_ENABLE; @@ -482,10 +539,20 @@ 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; - } else if (IS_GEN9(dev_priv)) { + } else if (IS_GEN(dev_priv, 9)) { psr_max_h = 3640; psr_max_v = 2304; } @@ -497,6 +564,18 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp, return false; } + /* + * HW sends SU blocks of size four scan lines, which means the starting + * X coordinate and Y granularity requirements will always be met. We + * only need to validate the SU block width is a multiple of + * x granularity. + */ + if (crtc_hdisplay % dev_priv->psr.su_x_granularity) { + DRM_DEBUG_KMS("PSR2 not enabled, hdisplay(%d) not multiple of %d\n", + crtc_hdisplay, dev_priv->psr.su_x_granularity); + return false; + } + return true; } @@ -527,10 +606,8 @@ 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; } @@ -609,17 +686,14 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp, if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) hsw_psr_setup_aux(intel_dp); - if (dev_priv->psr.psr2_enabled) { + if (dev_priv->psr.psr2_enabled && (IS_GEN(dev_priv, 9) && + !IS_GEMINILAKE(dev_priv))) { i915_reg_t reg = gen9_chicken_trans_reg(dev_priv, cpu_transcoder); u32 chicken = I915_READ(reg); - if (IS_GEN9(dev_priv) && !IS_GEMINILAKE(dev_priv)) - chicken |= (PSR2_VSC_ENABLE_PROG_HEADER - | PSR2_ADD_VERTICAL_LINE_COUNT); - - else - chicken &= ~VSC_DATA_SEL_SOFTWARE_CONTROL; + chicken |= PSR2_VSC_ENABLE_PROG_HEADER | + PSR2_ADD_VERTICAL_LINE_COUNT; I915_WRITE(reg, chicken); } @@ -687,6 +761,7 @@ 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 +1008,16 @@ 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 +1028,9 @@ 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 +1069,6 @@ 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 +1081,7 @@ 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 +1106,6 @@ 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 +1118,7 @@ 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 +1132,7 @@ 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 +1149,8 @@ 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 +1164,22 @@ 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 +1217,7 @@ 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 +1235,27 @@ 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..6e2661e86d18 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -69,19 +69,28 @@ unsigned int intel_ring_update_space(struct intel_ring *ring) static int gen2_render_ring_flush(struct i915_request *rq, u32 mode) { + unsigned int num_store_dw; u32 cmd, *cs; cmd = MI_FLUSH; - + num_store_dw = 0; if (mode & EMIT_INVALIDATE) cmd |= MI_READ_FLUSH; + if (mode & EMIT_FLUSH) + num_store_dw = 4; - cs = intel_ring_begin(rq, 2); + cs = intel_ring_begin(rq, 2 + 3 * num_store_dw); if (IS_ERR(cs)) return PTR_ERR(cs); *cs++ = cmd; - *cs++ = MI_NOOP; + while (num_store_dw--) { + *cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; + *cs++ = i915_scratch_offset(rq->i915); + *cs++ = 0; + } + *cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH; + intel_ring_advance(rq, cs); return 0; @@ -124,7 +133,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) cmd = MI_FLUSH; if (mode & EMIT_INVALIDATE) { cmd |= MI_EXE_FLUSH; - if (IS_G4X(rq->i915) || IS_GEN5(rq->i915)) + if (IS_G4X(rq->i915) || IS_GEN(rq->i915, 5)) cmd |= MI_INVALIDATE_ISP; } @@ -150,8 +159,7 @@ 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 +167,7 @@ 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; } @@ -210,10 +217,9 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) * really our business. That leaves only stall at scoreboard. */ static int -intel_emit_post_sync_nonzero_flush(struct i915_request *rq) +gen6_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); @@ -246,13 +252,12 @@ 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; /* Force SNB workarounds for PIPE_CONTROL flushes */ - ret = intel_emit_post_sync_nonzero_flush(rq); + ret = gen6_emit_post_sync_nonzero_flush(rq); if (ret) return ret; @@ -295,6 +300,37 @@ gen6_render_ring_flush(struct i915_request *rq, u32 mode) return 0; } +static void gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) +{ + /* First we do the gen6_emit_post_sync_nonzero_flush w/a */ + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = PIPE_CONTROL_CS_STALL | PIPE_CONTROL_STALL_AT_SCOREBOARD; + *cs++ = 0; + *cs++ = 0; + + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = PIPE_CONTROL_QW_WRITE; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = 0; + + /* Finally we can flush and with it emit the breadcrumb */ + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE | + PIPE_CONTROL_QW_WRITE | + PIPE_CONTROL_CS_STALL); + *cs++ = intel_hws_seqno_address(rq->engine) | PIPE_CONTROL_GLOBAL_GTT; + *cs++ = rq->global_seqno; + + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; + + rq->tail = intel_ring_offset(rq, cs); + assert_ring_tail_valid(rq->ring, rq->tail); +} +static const int gen6_rcs_emit_breadcrumb_sz = 14; + static int gen7_render_ring_cs_stall_wa(struct i915_request *rq) { @@ -316,8 +352,7 @@ 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; /* @@ -375,11 +410,86 @@ gen7_render_ring_flush(struct i915_request *rq, u32 mode) return 0; } -static void ring_setup_phys_status_page(struct intel_engine_cs *engine) +static void gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) +{ + *cs++ = GFX_OP_PIPE_CONTROL(4); + *cs++ = (PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | + PIPE_CONTROL_DEPTH_CACHE_FLUSH | + PIPE_CONTROL_DC_FLUSH_ENABLE | + PIPE_CONTROL_FLUSH_ENABLE | + PIPE_CONTROL_QW_WRITE | + PIPE_CONTROL_GLOBAL_GTT_IVB | + PIPE_CONTROL_CS_STALL); + *cs++ = intel_hws_seqno_address(rq->engine); + *cs++ = rq->global_seqno; + + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; + + rq->tail = intel_ring_offset(rq, cs); + assert_ring_tail_valid(rq->ring, rq->tail); +} +static const int gen7_rcs_emit_breadcrumb_sz = 6; + +static void gen6_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) +{ + *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW; + *cs++ = intel_hws_seqno_address(rq->engine) | MI_FLUSH_DW_USE_GTT; + *cs++ = rq->global_seqno; + *cs++ = MI_USER_INTERRUPT; + + rq->tail = intel_ring_offset(rq, cs); + assert_ring_tail_valid(rq->ring, rq->tail); +} +static const int gen6_xcs_emit_breadcrumb_sz = 4; + +#define GEN7_XCS_WA 32 +static void gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs) +{ + int i; + + *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW; + *cs++ = intel_hws_seqno_address(rq->engine) | MI_FLUSH_DW_USE_GTT; + *cs++ = rq->global_seqno; + + for (i = 0; i < GEN7_XCS_WA; i++) { + *cs++ = MI_STORE_DWORD_INDEX; + *cs++ = I915_GEM_HWS_INDEX_ADDR; + *cs++ = rq->global_seqno; + } + + *cs++ = MI_FLUSH_DW; + *cs++ = 0; + *cs++ = 0; + + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; + + rq->tail = intel_ring_offset(rq, cs); + assert_ring_tail_valid(rq->ring, rq->tail); +} +static const int gen7_xcs_emit_breadcrumb_sz = 8 + GEN7_XCS_WA * 3; +#undef GEN7_XCS_WA + +static void set_hwstam(struct intel_engine_cs *engine, u32 mask) +{ + /* + * Keep the render interrupt unmasked as this papers over + * lost interrupts following a reset. + */ + if (engine->class == RENDER_CLASS) { + if (INTEL_GEN(engine->i915) >= 6) + mask &= ~BIT(0); + else + mask &= ~I915_USER_INTERRUPT; + } + + intel_engine_set_hwsp_writemask(engine, mask); +} + +static void set_hws_pga(struct intel_engine_cs *engine, phys_addr_t phys) { struct drm_i915_private *dev_priv = engine->i915; - struct page *page = virt_to_page(engine->status_page.page_addr); - phys_addr_t phys = PFN_PHYS(page_to_pfn(page)); u32 addr; addr = lower_32_bits(phys); @@ -389,15 +499,25 @@ static void ring_setup_phys_status_page(struct intel_engine_cs *engine) I915_WRITE(HWS_PGA, addr); } -static void intel_ring_setup_status_page(struct intel_engine_cs *engine) +static void ring_setup_phys_status_page(struct intel_engine_cs *engine) +{ + struct page *page = virt_to_page(engine->status_page.page_addr); + phys_addr_t phys = PFN_PHYS(page_to_pfn(page)); + + set_hws_pga(engine, phys); + set_hwstam(engine, ~0u); +} + +static void set_hwsp(struct intel_engine_cs *engine, u32 offset) { struct drm_i915_private *dev_priv = engine->i915; - i915_reg_t mmio; + i915_reg_t hwsp; - /* The ring status page addresses are no longer next to the rest of + /* + * The ring status page addresses are no longer next to the rest of * the ring registers as of gen7. */ - if (IS_GEN7(dev_priv)) { + if (IS_GEN(dev_priv, 7)) { switch (engine->id) { /* * No more rings exist on Gen7. Default case is only to shut up @@ -406,56 +526,55 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine) default: GEM_BUG_ON(engine->id); case RCS: - mmio = RENDER_HWS_PGA_GEN7; + hwsp = RENDER_HWS_PGA_GEN7; break; case BCS: - mmio = BLT_HWS_PGA_GEN7; + hwsp = BLT_HWS_PGA_GEN7; break; case VCS: - mmio = BSD_HWS_PGA_GEN7; + hwsp = BSD_HWS_PGA_GEN7; break; case VECS: - mmio = VEBOX_HWS_PGA_GEN7; + hwsp = VEBOX_HWS_PGA_GEN7; break; } - } else if (IS_GEN6(dev_priv)) { - mmio = RING_HWS_PGA_GEN6(engine->mmio_base); + } else if (IS_GEN(dev_priv, 6)) { + hwsp = RING_HWS_PGA_GEN6(engine->mmio_base); } else { - mmio = RING_HWS_PGA(engine->mmio_base); + hwsp = RING_HWS_PGA(engine->mmio_base); } - if (INTEL_GEN(dev_priv) >= 6) { - u32 mask = ~0u; + I915_WRITE(hwsp, offset); + POSTING_READ(hwsp); +} - /* - * Keep the render interrupt unmasked as this papers over - * lost interrupts following a reset. - */ - if (engine->id == RCS) - mask &= ~BIT(0); +static void flush_cs_tlb(struct intel_engine_cs *engine) +{ + struct drm_i915_private *dev_priv = engine->i915; + i915_reg_t instpm = RING_INSTPM(engine->mmio_base); - I915_WRITE(RING_HWSTAM(engine->mmio_base), mask); - } + if (!IS_GEN_RANGE(dev_priv, 6, 7)) + return; - I915_WRITE(mmio, engine->status_page.ggtt_offset); - POSTING_READ(mmio); + /* ring should be idle before issuing a sync flush*/ + WARN_ON((I915_READ_MODE(engine) & MODE_IDLE) == 0); - /* Flush the TLB for this page */ - if (IS_GEN(dev_priv, 6, 7)) { - i915_reg_t reg = RING_INSTPM(engine->mmio_base); + I915_WRITE(instpm, + _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE | + INSTPM_SYNC_FLUSH)); + if (intel_wait_for_register(dev_priv, + instpm, INSTPM_SYNC_FLUSH, 0, + 1000)) + DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n", + engine->name); +} - /* ring should be idle before issuing a sync flush*/ - WARN_ON((I915_READ_MODE(engine) & MODE_IDLE) == 0); +static void ring_setup_status_page(struct intel_engine_cs *engine) +{ + set_hwsp(engine, engine->status_page.ggtt_offset); + set_hwstam(engine, ~0u); - I915_WRITE(reg, - _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE | - INSTPM_SYNC_FLUSH)); - if (intel_wait_for_register(dev_priv, - reg, INSTPM_SYNC_FLUSH, 0, - 1000)) - DRM_ERROR("%s: wait for SyncFlush to complete for TLB invalidation timed out\n", - engine->name); - } + flush_cs_tlb(engine); } static bool stop_ring(struct intel_engine_cs *engine) @@ -525,7 +644,7 @@ static int init_ring_common(struct intel_engine_cs *engine) if (HWS_NEEDS_PHYSICAL(dev_priv)) ring_setup_phys_status_page(engine); else - intel_ring_setup_status_page(engine); + ring_setup_status_page(engine); intel_engine_reset_breadcrumbs(engine); @@ -546,10 +665,11 @@ 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 +694,12 @@ 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: @@ -585,10 +711,6 @@ out: static struct i915_request *reset_prepare(struct intel_engine_cs *engine) { intel_engine_stop_cs(engine); - - if (engine->irq_seqno_barrier) - engine->irq_seqno_barrier(engine); - return i915_gem_find_active_request(engine); } @@ -642,7 +764,7 @@ 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; @@ -660,10 +782,8 @@ 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)) + if (IS_GEN_RANGE(dev_priv, 4, 6)) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH)); /* We need to disable the AsyncFlip performance optimisations in order @@ -672,22 +792,22 @@ static int init_render_ring(struct intel_engine_cs *engine) * * WaDisableAsyncFlipPerfMode:snb,ivb,hsw,vlv */ - if (IS_GEN(dev_priv, 6, 7)) + if (IS_GEN_RANGE(dev_priv, 6, 7)) I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(ASYNC_FLIP_PERF_DISABLE)); /* Required for the hardware to program scanline values for waiting */ /* WaEnableFlushTlbInvalidationMode:snb */ - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) I915_WRITE(GFX_MODE, _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT)); /* WaBCSVCSTlbInvalidationMode:ivb,vlv,hsw */ - if (IS_GEN7(dev_priv)) + if (IS_GEN(dev_priv, 7)) I915_WRITE(GFX_MODE_GEN7, _MASKED_BIT_ENABLE(GFX_TLB_INVALIDATE_EXPLICIT) | _MASKED_BIT_ENABLE(GFX_REPLAY_MODE)); - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { /* From the Sandybridge PRM, volume 1 part 3, page 24: * "If this bit is set, STCunit will have LRA as replacement * policy. [...] This bit must be reset. LRA replacement @@ -697,7 +817,7 @@ static int init_render_ring(struct intel_engine_cs *engine) _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB)); } - if (IS_GEN(dev_priv, 6, 7)) + if (IS_GEN_RANGE(dev_priv, 6, 7)) I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING)); if (INTEL_GEN(dev_priv) >= 6) @@ -706,33 +826,6 @@ static int init_render_ring(struct intel_engine_cs *engine) return 0; } -static u32 *gen6_signal(struct i915_request *rq, u32 *cs) -{ - struct drm_i915_private *dev_priv = rq->i915; - struct intel_engine_cs *engine; - enum intel_engine_id id; - int num_rings = 0; - - for_each_engine(engine, dev_priv, id) { - i915_reg_t mbox_reg; - - if (!(BIT(engine->hw_id) & GEN6_SEMAPHORES_MASK)) - continue; - - mbox_reg = rq->engine->semaphore.mbox.signal[engine->hw_id]; - if (i915_mmio_reg_valid(mbox_reg)) { - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(mbox_reg); - *cs++ = rq->global_seqno; - num_rings++; - } - } - if (num_rings & 1) - *cs++ = MI_NOOP; - - return cs; -} - static void cancel_requests(struct intel_engine_cs *engine) { struct i915_request *request; @@ -743,9 +836,18 @@ 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); @@ -763,92 +865,41 @@ static void i9xx_submit_request(struct i915_request *request) static void i9xx_emit_breadcrumb(struct i915_request *rq, u32 *cs) { + *cs++ = MI_FLUSH; + *cs++ = MI_STORE_DWORD_INDEX; - *cs++ = I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT; + *cs++ = I915_GEM_HWS_INDEX_ADDR; *cs++ = rq->global_seqno; + *cs++ = MI_USER_INTERRUPT; + *cs++ = MI_NOOP; rq->tail = intel_ring_offset(rq, cs); assert_ring_tail_valid(rq->ring, rq->tail); } +static const int i9xx_emit_breadcrumb_sz = 6; -static const int i9xx_emit_breadcrumb_sz = 4; - -static void gen6_sema_emit_breadcrumb(struct i915_request *rq, u32 *cs) +#define GEN5_WA_STORES 8 /* must be at least 1! */ +static void gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs) { - return i9xx_emit_breadcrumb(rq, rq->engine->semaphore.signal(rq, cs)); -} - -static int -gen6_ring_sync_to(struct i915_request *rq, struct i915_request *signal) -{ - u32 dw1 = MI_SEMAPHORE_MBOX | - MI_SEMAPHORE_COMPARE | - MI_SEMAPHORE_REGISTER; - u32 wait_mbox = signal->engine->semaphore.mbox.wait[rq->engine->hw_id]; - u32 *cs; - - WARN_ON(wait_mbox == MI_SEMAPHORE_SYNC_INVALID); - - cs = intel_ring_begin(rq, 4); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - *cs++ = dw1 | wait_mbox; - /* Throughout all of the GEM code, seqno passed implies our current - * seqno is >= the last seqno executed. However for hardware the - * comparison is strictly greater than. - */ - *cs++ = signal->global_seqno - 1; - *cs++ = 0; - *cs++ = MI_NOOP; - intel_ring_advance(rq, cs); + int i; - return 0; -} + *cs++ = MI_FLUSH; -static void -gen5_seqno_barrier(struct intel_engine_cs *engine) -{ - /* MI_STORE are internally buffered by the GPU and not flushed - * either by MI_FLUSH or SyncFlush or any other combination of - * MI commands. - * - * "Only the submission of the store operation is guaranteed. - * The write result will be complete (coherent) some time later - * (this is practically a finite period but there is no guaranteed - * latency)." - * - * Empirically, we observe that we need a delay of at least 75us to - * be sure that the seqno write is visible by the CPU. - */ - usleep_range(125, 250); -} + BUILD_BUG_ON(GEN5_WA_STORES < 1); + for (i = 0; i < GEN5_WA_STORES; i++) { + *cs++ = MI_STORE_DWORD_INDEX; + *cs++ = I915_GEM_HWS_INDEX_ADDR; + *cs++ = rq->global_seqno; + } -static void -gen6_seqno_barrier(struct intel_engine_cs *engine) -{ - struct drm_i915_private *dev_priv = engine->i915; + *cs++ = MI_USER_INTERRUPT; - /* Workaround to force correct ordering between irq and seqno writes on - * ivb (and maybe also on snb) by reading from a CS register (like - * ACTHD) before reading the status page. - * - * Note that this effectively stalls the read by the time it takes to - * do a memory transaction, which more or less ensures that the write - * from the GPU has sufficient time to invalidate the CPU cacheline. - * Alternatively we could delay the interrupt from the CS ring to give - * the write time to land, but that would incur a delay after every - * batch i.e. much more frequent than a delay when waiting for the - * interrupt (with the same net latency). - * - * Also note that to prevent whole machine hangs on gen7, we have to - * take the spinlock to guard against concurrent cacheline access. - */ - spin_lock_irq(&dev_priv->uncore.lock); - POSTING_READ_FW(RING_ACTHD(engine->mmio_base)); - spin_unlock_irq(&dev_priv->uncore.lock); + rq->tail = intel_ring_offset(rq, cs); + assert_ring_tail_valid(rq->ring, rq->tail); } +static const int gen5_emit_breadcrumb_sz = GEN5_WA_STORES * 3 + 2; +#undef GEN5_WA_STORES static void gen5_irq_enable(struct intel_engine_cs *engine) @@ -923,6 +974,10 @@ gen6_irq_enable(struct intel_engine_cs *engine) I915_WRITE_IMR(engine, ~(engine->irq_enable_mask | engine->irq_keep_mask)); + + /* Flush/delay to ensure the RING_IMR is active before the GT IMR */ + POSTING_READ_FW(RING_IMR(engine->mmio_base)); + gen5_enable_gt_irq(dev_priv, engine->irq_enable_mask); } @@ -941,6 +996,10 @@ hsw_vebox_irq_enable(struct intel_engine_cs *engine) struct drm_i915_private *dev_priv = engine->i915; I915_WRITE_IMR(engine, ~engine->irq_enable_mask); + + /* Flush/delay to ensure the RING_IMR is active before the GT IMR */ + POSTING_READ_FW(RING_IMR(engine->mmio_base)); + gen6_unmask_pm_irq(dev_priv, engine->irq_enable_mask); } @@ -973,7 +1032,7 @@ 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 +1040,9 @@ 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 +1499,6 @@ 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 +1523,12 @@ 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 +1602,7 @@ 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); @@ -1564,10 +1615,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) struct intel_engine_cs *engine = rq->engine; enum intel_engine_id id; const int num_rings = - /* Use an extended w/a on gen7 if signalling from other rings */ - (HAS_LEGACY_SEMAPHORES(i915) && IS_GEN7(i915)) ? - INTEL_INFO(i915)->num_rings - 1 : - 0; + IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_rings - 1 : 0; bool force_restore = false; int len; u32 *cs; @@ -1580,7 +1628,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN; len = 4; - if (IS_GEN7(i915)) + if (IS_GEN(i915, 7)) len += 2 + (num_rings ? 4*num_rings + 6 : 0); if (flags & MI_FORCE_RESTORE) { GEM_BUG_ON(flags & MI_RESTORE_INHIBIT); @@ -1594,7 +1642,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) return PTR_ERR(cs); /* WaProgramMiArbOnOffAroundMiSetContext:ivb,vlv,hsw,bdw,chv */ - if (IS_GEN7(i915)) { + if (IS_GEN(i915, 7)) { *cs++ = MI_ARB_ON_OFF | MI_ARB_DISABLE; if (num_rings) { struct intel_engine_cs *signaller; @@ -1641,7 +1689,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) */ *cs++ = MI_NOOP; - if (IS_GEN7(i915)) { + if (IS_GEN(i915, 7)) { if (num_rings) { struct intel_engine_cs *signaller; i915_reg_t last_reg = {}; /* keep gcc quiet */ @@ -1660,7 +1708,7 @@ 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; @@ -1812,17 +1860,19 @@ static int ring_request_alloc(struct i915_request *request) GEM_BUG_ON(!request->hw_context->pin_count); - /* Flush enough space to reduce the likelihood of waiting after + /* + * Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just * have to repeat work. */ request->reserved_space += LEGACY_REQUEST_SIZE; - ret = intel_ring_wait_for_space(request->ring, request->reserved_space); + ret = switch_context(request); if (ret) return ret; - ret = switch_context(request); + /* Unconditionally invalidate GPU caches and TLBs. */ + ret = request->engine->emit_flush(request, EMIT_INVALIDATE); if (ret) return ret; @@ -1864,22 +1914,6 @@ static noinline int wait_for_space(struct intel_ring *ring, unsigned int bytes) return 0; } -int intel_ring_wait_for_space(struct intel_ring *ring, unsigned int bytes) -{ - GEM_BUG_ON(bytes > ring->effective_size); - if (unlikely(bytes > ring->effective_size - ring->emit)) - bytes += ring->size - ring->emit; - - if (unlikely(bytes > ring->space)) { - int ret = wait_for_space(ring, bytes); - if (unlikely(ret)) - return ret; - } - - GEM_BUG_ON(ring->space < bytes); - return 0; -} - u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords) { struct intel_ring *ring = rq->ring; @@ -2112,77 +2146,15 @@ static int gen6_ring_flush(struct i915_request *rq, u32 mode) return gen6_flush_dw(rq, mode, MI_INVALIDATE_TLB); } -static void intel_ring_init_semaphores(struct drm_i915_private *dev_priv, - struct intel_engine_cs *engine) -{ - int i; - - if (!HAS_LEGACY_SEMAPHORES(dev_priv)) - return; - - GEM_BUG_ON(INTEL_GEN(dev_priv) < 6); - engine->semaphore.sync_to = gen6_ring_sync_to; - engine->semaphore.signal = gen6_signal; - - /* - * The current semaphore is only applied on pre-gen8 - * platform. And there is no VCS2 ring on the pre-gen8 - * platform. So the semaphore between RCS and VCS2 is - * initialized as INVALID. - */ - for (i = 0; i < GEN6_NUM_SEMAPHORES; i++) { - static const struct { - u32 wait_mbox; - i915_reg_t mbox_reg; - } sem_data[GEN6_NUM_SEMAPHORES][GEN6_NUM_SEMAPHORES] = { - [RCS_HW] = { - [VCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_RV, .mbox_reg = GEN6_VRSYNC }, - [BCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_RB, .mbox_reg = GEN6_BRSYNC }, - [VECS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_RVE, .mbox_reg = GEN6_VERSYNC }, - }, - [VCS_HW] = { - [RCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VR, .mbox_reg = GEN6_RVSYNC }, - [BCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VB, .mbox_reg = GEN6_BVSYNC }, - [VECS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VVE, .mbox_reg = GEN6_VEVSYNC }, - }, - [BCS_HW] = { - [RCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_BR, .mbox_reg = GEN6_RBSYNC }, - [VCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_BV, .mbox_reg = GEN6_VBSYNC }, - [VECS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_BVE, .mbox_reg = GEN6_VEBSYNC }, - }, - [VECS_HW] = { - [RCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VER, .mbox_reg = GEN6_RVESYNC }, - [VCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VEV, .mbox_reg = GEN6_VVESYNC }, - [BCS_HW] = { .wait_mbox = MI_SEMAPHORE_SYNC_VEB, .mbox_reg = GEN6_BVESYNC }, - }, - }; - u32 wait_mbox; - i915_reg_t mbox_reg; - - if (i == engine->hw_id) { - wait_mbox = MI_SEMAPHORE_SYNC_INVALID; - mbox_reg = GEN6_NOSYNC; - } else { - wait_mbox = sem_data[engine->hw_id][i].wait_mbox; - mbox_reg = sem_data[engine->hw_id][i].mbox_reg; - } - - engine->semaphore.mbox.wait[i] = wait_mbox; - engine->semaphore.mbox.signal[i] = mbox_reg; - } -} - static void intel_ring_init_irq(struct drm_i915_private *dev_priv, struct intel_engine_cs *engine) { if (INTEL_GEN(dev_priv) >= 6) { engine->irq_enable = gen6_irq_enable; engine->irq_disable = gen6_irq_disable; - engine->irq_seqno_barrier = gen6_seqno_barrier; } else if (INTEL_GEN(dev_priv) >= 5) { engine->irq_enable = gen5_irq_enable; engine->irq_disable = gen5_irq_disable; - engine->irq_seqno_barrier = gen5_seqno_barrier; } else if (INTEL_GEN(dev_priv) >= 3) { engine->irq_enable = i9xx_irq_enable; engine->irq_disable = i9xx_irq_disable; @@ -2214,7 +2186,6 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv, GEM_BUG_ON(INTEL_GEN(dev_priv) >= 8); intel_ring_init_irq(dev_priv, engine); - intel_ring_init_semaphores(dev_priv, engine); engine->init_hw = init_ring_common; engine->reset.prepare = reset_prepare; @@ -2226,15 +2197,9 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv, engine->emit_breadcrumb = i9xx_emit_breadcrumb; engine->emit_breadcrumb_sz = i9xx_emit_breadcrumb_sz; - if (HAS_LEGACY_SEMAPHORES(dev_priv)) { - int num_rings; - - engine->emit_breadcrumb = gen6_sema_emit_breadcrumb; - - num_rings = INTEL_INFO(dev_priv)->num_rings - 1; - engine->emit_breadcrumb_sz += num_rings * 3; - if (num_rings & 1) - engine->emit_breadcrumb_sz++; + if (IS_GEN(dev_priv, 5)) { + engine->emit_breadcrumb = gen5_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen5_emit_breadcrumb_sz; } engine->set_default_submission = i9xx_set_default_submission; @@ -2261,12 +2226,17 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT; - if (INTEL_GEN(dev_priv) >= 6) { + if (INTEL_GEN(dev_priv) >= 7) { engine->init_context = intel_rcs_ctx_init; engine->emit_flush = gen7_render_ring_flush; - if (IS_GEN6(dev_priv)) - engine->emit_flush = gen6_render_ring_flush; - } else if (IS_GEN5(dev_priv)) { + engine->emit_breadcrumb = gen7_rcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen7_rcs_emit_breadcrumb_sz; + } else if (IS_GEN(dev_priv, 6)) { + engine->init_context = intel_rcs_ctx_init; + engine->emit_flush = gen6_render_ring_flush; + engine->emit_breadcrumb = gen6_rcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen6_rcs_emit_breadcrumb_sz; + } else if (IS_GEN(dev_priv, 5)) { engine->emit_flush = gen4_render_ring_flush; } else { if (INTEL_GEN(dev_priv) < 4) @@ -2296,13 +2266,21 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine) if (INTEL_GEN(dev_priv) >= 6) { /* gen6 bsd needs a special wa for tail updates */ - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) engine->set_default_submission = gen6_bsd_set_default_submission; engine->emit_flush = gen6_bsd_ring_flush; engine->irq_enable_mask = GT_BSD_USER_INTERRUPT; + + if (IS_GEN(dev_priv, 6)) { + engine->emit_breadcrumb = gen6_xcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen6_xcs_emit_breadcrumb_sz; + } else { + engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen7_xcs_emit_breadcrumb_sz; + } } else { engine->emit_flush = bsd_ring_flush; - if (IS_GEN5(dev_priv)) + if (IS_GEN(dev_priv, 5)) engine->irq_enable_mask = ILK_BSD_USER_INTERRUPT; else engine->irq_enable_mask = I915_BSD_USER_INTERRUPT; @@ -2315,11 +2293,21 @@ int intel_init_blt_ring_buffer(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + GEM_BUG_ON(INTEL_GEN(dev_priv) < 6); + intel_ring_default_vfuncs(dev_priv, engine); engine->emit_flush = gen6_ring_flush; engine->irq_enable_mask = GT_BLT_USER_INTERRUPT; + if (IS_GEN(dev_priv, 6)) { + engine->emit_breadcrumb = gen6_xcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen6_xcs_emit_breadcrumb_sz; + } else { + engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen7_xcs_emit_breadcrumb_sz; + } + return intel_init_ring_buffer(engine); } @@ -2327,6 +2315,8 @@ int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; + GEM_BUG_ON(INTEL_GEN(dev_priv) < 7); + intel_ring_default_vfuncs(dev_priv, engine); engine->emit_flush = gen6_ring_flush; @@ -2334,5 +2324,8 @@ int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine) engine->irq_enable = hsw_vebox_irq_enable; engine->irq_disable = hsw_vebox_irq_disable; + engine->emit_breadcrumb = gen7_xcs_emit_breadcrumb; + engine->emit_breadcrumb_sz = gen7_xcs_emit_breadcrumb_sz; + return intel_init_ring_buffer(engine); } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 8a2270b209b0..3c1366c58cf3 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; @@ -93,12 +94,12 @@ hangcheck_action_to_str(const enum intel_engine_hangcheck_action a) #define I915_MAX_SUBSLICES 8 #define instdone_slice_mask(dev_priv__) \ - (IS_GEN7(dev_priv__) ? \ - 1 : INTEL_INFO(dev_priv__)->sseu.slice_mask) + (IS_GEN(dev_priv__, 7) ? \ + 1 : RUNTIME_INFO(dev_priv__)->sseu.slice_mask) #define instdone_subslice_mask(dev_priv__) \ - (IS_GEN7(dev_priv__) ? \ - 1 : INTEL_INFO(dev_priv__)->sseu.subslice_mask[0]) + (IS_GEN(dev_priv__, 7) ? \ + 1 : RUNTIME_INFO(dev_priv__)->sseu.subslice_mask[0]) #define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \ for ((slice__) = 0, (subslice__) = 0; \ @@ -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; @@ -380,9 +365,6 @@ struct intel_engine_cs { struct drm_i915_gem_object *default_state; void *pinned_default_state; - unsigned long irq_posted; -#define ENGINE_IRQ_BREADCRUMB 0 - /* Rather than have every client wait upon all user interrupts, * with the herd waking after every interrupt and each doing the * heavyweight seqno dance, we delegate the task (of being the @@ -451,7 +433,9 @@ 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 */ @@ -514,69 +498,8 @@ struct intel_engine_cs { */ void (*cancel_requests)(struct intel_engine_cs *engine); - /* Some chipsets are not quite as coherent as advertised and need - * an expensive kick to force a true read of the up-to-date seqno. - * However, the up-to-date seqno is not always required and the last - * seen value is good enough. Note that the seqno will always be - * monotonic, even if not coherent. - */ - void (*irq_seqno_barrier)(struct intel_engine_cs *engine); void (*cleanup)(struct intel_engine_cs *engine); - /* GEN8 signal/wait table - never trust comments! - * signal to signal to signal to signal to signal to - * RCS VCS BCS VECS VCS2 - * -------------------------------------------------------------------- - * RCS | NOP (0x00) | VCS (0x08) | BCS (0x10) | VECS (0x18) | VCS2 (0x20) | - * |------------------------------------------------------------------- - * VCS | RCS (0x28) | NOP (0x30) | BCS (0x38) | VECS (0x40) | VCS2 (0x48) | - * |------------------------------------------------------------------- - * BCS | RCS (0x50) | VCS (0x58) | NOP (0x60) | VECS (0x68) | VCS2 (0x70) | - * |------------------------------------------------------------------- - * VECS | RCS (0x78) | VCS (0x80) | BCS (0x88) | NOP (0x90) | VCS2 (0x98) | - * |------------------------------------------------------------------- - * VCS2 | RCS (0xa0) | VCS (0xa8) | BCS (0xb0) | VECS (0xb8) | NOP (0xc0) | - * |------------------------------------------------------------------- - * - * Generalization: - * f(x, y) := (x->id * NUM_RINGS * seqno_size) + (seqno_size * y->id) - * ie. transpose of g(x, y) - * - * sync from sync from sync from sync from sync from - * RCS VCS BCS VECS VCS2 - * -------------------------------------------------------------------- - * RCS | NOP (0x00) | VCS (0x28) | BCS (0x50) | VECS (0x78) | VCS2 (0xa0) | - * |------------------------------------------------------------------- - * VCS | RCS (0x08) | NOP (0x30) | BCS (0x58) | VECS (0x80) | VCS2 (0xa8) | - * |------------------------------------------------------------------- - * BCS | RCS (0x10) | VCS (0x38) | NOP (0x60) | VECS (0x88) | VCS2 (0xb0) | - * |------------------------------------------------------------------- - * VECS | RCS (0x18) | VCS (0x40) | BCS (0x68) | NOP (0x90) | VCS2 (0xb8) | - * |------------------------------------------------------------------- - * VCS2 | RCS (0x20) | VCS (0x48) | BCS (0x70) | VECS (0x98) | NOP (0xc0) | - * |------------------------------------------------------------------- - * - * Generalization: - * g(x, y) := (y->id * NUM_RINGS * seqno_size) + (seqno_size * x->id) - * ie. transpose of f(x, y) - */ - struct { -#define GEN6_SEMAPHORE_LAST VECS_HW -#define GEN6_NUM_SEMAPHORES (GEN6_SEMAPHORE_LAST + 1) -#define GEN6_SEMAPHORES_MASK GENMASK(GEN6_SEMAPHORE_LAST, 0) - struct { - /* our mbox written by others */ - u32 wait[GEN6_NUM_SEMAPHORES]; - /* mboxes this ring signals to */ - i915_reg_t signal[GEN6_NUM_SEMAPHORES]; - } mbox; - - /* AKA wait() */ - int (*sync_to)(struct i915_request *rq, - struct i915_request *signal); - u32 *(*signal)(struct i915_request *rq, u32 *cs); - } semaphore; - struct intel_engine_execlists execlists; /* Contexts are pinned whilst they are active on the GPU. The last @@ -821,7 +744,6 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv); int __must_check intel_ring_cacheline_align(struct i915_request *rq); -int intel_ring_wait_for_space(struct intel_ring *ring, unsigned int bytes); u32 __must_check *intel_ring_begin(struct i915_request *rq, unsigned int n); static inline void intel_ring_advance(struct i915_request *rq, u32 *cs) @@ -902,16 +824,12 @@ intel_ring_set_tail(struct intel_ring *ring, unsigned int tail) return tail; } -void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno); +void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno); 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); @@ -920,6 +838,8 @@ int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine); int intel_engine_stop_cs(struct intel_engine_cs *engine); void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine); +void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask); + u64 intel_engine_get_active_head(const struct intel_engine_cs *engine); u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine); @@ -964,15 +884,6 @@ static inline bool intel_engine_has_started(struct intel_engine_cs *engine, void intel_engine_get_instdone(struct intel_engine_cs *engine, struct intel_instdone *instdone); -/* - * Arbitrary size for largest possible 'add request' sequence. The code paths - * are complex and variable. Empirical measurement shows that the worst case - * is BDW at 192 bytes (6 + 6 + 36 dwords), then ILK at 136 bytes. However, - * we need to allocate double the largest single packet within that emission - * to account for tail wraparound (so 6 + 6 + 72 dwords for BDW). - */ -#define MIN_SPACE_FOR_ADD_REQUEST 336 - static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine) { return engine->status_page.ggtt_offset + I915_GEM_HWS_INDEX_ADDR; @@ -1072,7 +983,7 @@ static inline u32 *gen8_emit_pipe_control(u32 *batch, u32 flags, u32 offset) } static inline u32 * -gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset) +gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags) { /* We're using qword write, offset should be aligned to 8 bytes. */ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); @@ -1082,8 +993,7 @@ gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset) * following the batch. */ *cs++ = GFX_OP_PIPE_CONTROL(6); - *cs++ = PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | - PIPE_CONTROL_QW_WRITE; + *cs++ = flags | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB; *cs++ = gtt_offset; *cs++ = 0; *cs++ = value; @@ -1109,7 +1019,7 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset) return cs; } -void intel_engines_sanitize(struct drm_i915_private *i915); +void intel_engines_sanitize(struct drm_i915_private *i915, bool force); bool intel_engine_is_idle(struct intel_engine_cs *engine); bool intel_engines_are_idle(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 1c2de9b69a19..9e9501f82f06 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: @@ -507,7 +509,7 @@ static bool hsw_power_well_enabled(struct drm_i915_private *dev_priv, * BIOS's own request bits, which are forced-on for these power wells * when exiting DC5/6. */ - if (IS_GEN9(dev_priv) && !IS_GEN9_LP(dev_priv) && + if (IS_GEN(dev_priv, 9) && !IS_GEN9_LP(dev_priv) && (id == SKL_DISP_PW_1 || id == SKL_DISP_PW_MISC_IO)) val |= I915_READ(regs->bios); @@ -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 ( \ @@ -3056,7 +3058,7 @@ static uint32_t get_allowed_dc_mask(const struct drm_i915_private *dev_priv, * suspend/resume, so allow it unconditionally. */ mask = DC_STATE_EN_DC9; - } else if (IS_GEN10(dev_priv) || IS_GEN9_BC(dev_priv)) { + } else if (IS_GEN(dev_priv, 10) || IS_GEN9_BC(dev_priv)) { max_dc = 2; mask = 0; } else if (IS_GEN9_LP(dev_priv)) { diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index abe193815ccc..f70d2c607902 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); @@ -1067,7 +1087,7 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state, dvscntr = DVS_ENABLE | DVS_GAMMA_ENABLE; - if (IS_GEN6(dev_priv)) + if (IS_GEN(dev_priv, 6)) dvscntr |= DVS_TRICKLE_FEED_DISABLE; switch (fb->format->format) { @@ -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; @@ -1957,7 +1983,7 @@ static bool skl_plane_has_planar(struct drm_i915_private *dev_priv, if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv)) return false; - if (IS_GEN9(dev_priv) && !IS_GEMINILAKE(dev_priv) && pipe == PIPE_C) + if (IS_GEN(dev_priv, 9) && !IS_GEMINILAKE(dev_priv) && pipe == PIPE_C) return false; if (plane_id != PLANE_PRIMARY && plane_id != PLANE_SPRITE0) @@ -2137,7 +2163,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv, plane->check_plane = g4x_sprite_check; modifiers = i9xx_plane_format_modifiers; - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { formats = snb_plane_formats; num_formats = ARRAY_SIZE(snb_plane_formats); diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c index b34c318b238d..731b82afe636 100644 --- a/drivers/gpu/drm/i915/intel_uc.c +++ b/drivers/gpu/drm/i915/intel_uc.c @@ -71,7 +71,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *i915) { int guc_log_level; - if (!HAS_GUC(i915) || !intel_uc_is_using_guc()) + if (!HAS_GUC(i915) || !intel_uc_is_using_guc(i915)) guc_log_level = GUC_LOG_LEVEL_DISABLED; else if (IS_ENABLED(CONFIG_DRM_I915_DEBUG) || IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) @@ -112,11 +112,11 @@ static void sanitize_options_early(struct drm_i915_private *i915) DRM_DEBUG_DRIVER("enable_guc=%d (submission:%s huc:%s)\n", i915_modparams.enable_guc, - yesno(intel_uc_is_using_guc_submission()), - yesno(intel_uc_is_using_huc())); + yesno(intel_uc_is_using_guc_submission(i915)), + yesno(intel_uc_is_using_huc(i915))); /* Verify GuC firmware availability */ - if (intel_uc_is_using_guc() && !intel_uc_fw_is_selected(guc_fw)) { + if (intel_uc_is_using_guc(i915) && !intel_uc_fw_is_selected(guc_fw)) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "enable_guc", i915_modparams.enable_guc, !HAS_GUC(i915) ? "no GuC hardware" : @@ -124,7 +124,7 @@ static void sanitize_options_early(struct drm_i915_private *i915) } /* Verify HuC firmware availability */ - if (intel_uc_is_using_huc() && !intel_uc_fw_is_selected(huc_fw)) { + if (intel_uc_is_using_huc(i915) && !intel_uc_fw_is_selected(huc_fw)) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "enable_guc", i915_modparams.enable_guc, !HAS_HUC(i915) ? "no HuC hardware" : @@ -136,7 +136,7 @@ static void sanitize_options_early(struct drm_i915_private *i915) i915_modparams.guc_log_level = __get_default_guc_log_level(i915); - if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc()) { + if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc(i915)) { DRM_WARN("Incompatible option detected: %s=%d, %s!\n", "guc_log_level", i915_modparams.guc_log_level, !HAS_GUC(i915) ? "no GuC hardware" : @@ -354,7 +354,7 @@ int intel_uc_init_hw(struct drm_i915_private *i915) /* WaEnableuKernelHeaderValidFix:skl */ /* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */ - if (IS_GEN9(i915)) + if (IS_GEN(i915, 9)) attempts = 3; else attempts = 1; diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h index 25d73ada74ae..870faf9011b9 100644 --- a/drivers/gpu/drm/i915/intel_uc.h +++ b/drivers/gpu/drm/i915/intel_uc.h @@ -41,19 +41,19 @@ void intel_uc_fini(struct drm_i915_private *dev_priv); int intel_uc_suspend(struct drm_i915_private *dev_priv); int intel_uc_resume(struct drm_i915_private *dev_priv); -static inline bool intel_uc_is_using_guc(void) +static inline bool intel_uc_is_using_guc(struct drm_i915_private *i915) { GEM_BUG_ON(i915_modparams.enable_guc < 0); return i915_modparams.enable_guc > 0; } -static inline bool intel_uc_is_using_guc_submission(void) +static inline bool intel_uc_is_using_guc_submission(struct drm_i915_private *i915) { GEM_BUG_ON(i915_modparams.enable_guc < 0); return i915_modparams.enable_guc & ENABLE_GUC_SUBMISSION; } -static inline bool intel_uc_is_using_huc(void) +static inline bool intel_uc_is_using_huc(struct drm_i915_private *i915) { GEM_BUG_ON(i915_modparams.enable_guc < 0); return i915_modparams.enable_guc & ENABLE_GUC_LOAD_HUC; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 9289515108c3..fff468f17d2d 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -528,7 +528,7 @@ check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) ret |= vlv_check_for_unclaimed_mmio(dev_priv); - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) + if (IS_GEN_RANGE(dev_priv, 6, 7)) ret |= gen6_check_for_fifo_debug(dev_priv); return ret; @@ -556,7 +556,7 @@ static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, dev_priv->uncore.funcs.force_wake_get(dev_priv, restore_forcewake); - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) + if (IS_GEN_RANGE(dev_priv, 6, 7)) dev_priv->uncore.fifo_count = fifo_free_entries(dev_priv); spin_unlock_irq(&dev_priv->uncore.lock); @@ -1398,7 +1398,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) <= 5 || intel_vgpu_active(dev_priv)) return; - if (IS_GEN6(dev_priv)) { + if (IS_GEN(dev_priv, 6)) { dev_priv->uncore.fw_reset = 0; dev_priv->uncore.fw_set = FORCEWAKE_KERNEL; dev_priv->uncore.fw_clear = 0; @@ -1437,7 +1437,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) FORCEWAKE_MEDIA_VEBOX_GEN11(i), FORCEWAKE_ACK_MEDIA_VEBOX_GEN11(i)); } - } else if (IS_GEN10(dev_priv) || IS_GEN9(dev_priv)) { + } else if (IS_GEN_RANGE(dev_priv, 9, 10)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_fallback; dev_priv->uncore.funcs.force_wake_put = fw_domains_put; @@ -1503,7 +1503,7 @@ static void intel_uncore_fw_domains_init(struct drm_i915_private *dev_priv) fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE, FORCEWAKE_ACK); } - } else if (IS_GEN6(dev_priv)) { + } else if (IS_GEN(dev_priv, 6)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; dev_priv->uncore.funcs.force_wake_put = fw_domains_put; @@ -1567,13 +1567,13 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) dev_priv->uncore.pmic_bus_access_nb.notifier_call = i915_pmic_bus_access_notifier; - if (IS_GEN(dev_priv, 2, 4) || intel_vgpu_active(dev_priv)) { + if (IS_GEN_RANGE(dev_priv, 2, 4) || intel_vgpu_active(dev_priv)) { ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen2); ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen2); - } else if (IS_GEN5(dev_priv)) { + } else if (IS_GEN(dev_priv, 5)) { ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen5); ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen5); - } else if (IS_GEN(dev_priv, 6, 7)) { + } else if (IS_GEN_RANGE(dev_priv, 6, 7)) { ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen6); if (IS_VALLEYVIEW(dev_priv)) { @@ -1582,7 +1582,7 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) } else { ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen6); } - } else if (IS_GEN8(dev_priv)) { + } else if (IS_GEN(dev_priv, 8)) { if (IS_CHERRYVIEW(dev_priv)) { ASSIGN_FW_DOMAINS_TABLE(__chv_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, fwtable); @@ -1592,7 +1592,7 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, gen8); ASSIGN_READ_MMIO_VFUNCS(dev_priv, gen6); } - } else if (IS_GEN(dev_priv, 9, 10)) { + } else if (IS_GEN_RANGE(dev_priv, 9, 10)) { ASSIGN_FW_DOMAINS_TABLE(__gen9_fw_ranges); ASSIGN_WRITE_MMIO_VFUNCS(dev_priv, fwtable); ASSIGN_READ_MMIO_VFUNCS(dev_priv, fwtable); @@ -1931,6 +1931,103 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv, return gen6_hw_domain_reset(dev_priv, hw_mask); } +static u32 gen11_lock_sfc(struct drm_i915_private *dev_priv, + struct intel_engine_cs *engine) +{ + u8 vdbox_sfc_access = RUNTIME_INFO(dev_priv)->vdbox_sfc_access; + i915_reg_t sfc_forced_lock, sfc_forced_lock_ack; + u32 sfc_forced_lock_bit, sfc_forced_lock_ack_bit; + i915_reg_t sfc_usage; + u32 sfc_usage_bit; + u32 sfc_reset_bit; + + switch (engine->class) { + case VIDEO_DECODE_CLASS: + if ((BIT(engine->instance) & vdbox_sfc_access) == 0) + return 0; + + sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine); + sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT; + + sfc_forced_lock_ack = GEN11_VCS_SFC_LOCK_STATUS(engine); + sfc_forced_lock_ack_bit = GEN11_VCS_SFC_LOCK_ACK_BIT; + + sfc_usage = GEN11_VCS_SFC_LOCK_STATUS(engine); + sfc_usage_bit = GEN11_VCS_SFC_USAGE_BIT; + sfc_reset_bit = GEN11_VCS_SFC_RESET_BIT(engine->instance); + break; + + case VIDEO_ENHANCEMENT_CLASS: + sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine); + sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT; + + sfc_forced_lock_ack = GEN11_VECS_SFC_LOCK_ACK(engine); + sfc_forced_lock_ack_bit = GEN11_VECS_SFC_LOCK_ACK_BIT; + + sfc_usage = GEN11_VECS_SFC_USAGE(engine); + sfc_usage_bit = GEN11_VECS_SFC_USAGE_BIT; + sfc_reset_bit = GEN11_VECS_SFC_RESET_BIT(engine->instance); + break; + + default: + return 0; + } + + /* + * Tell the engine that a software reset is going to happen. The engine + * will then try to force lock the SFC (if currently locked, it will + * remain so until we tell the engine it is safe to unlock; if currently + * unlocked, it will ignore this and all new lock requests). If SFC + * ends up being locked to the engine we want to reset, we have to reset + * it as well (we will unlock it once the reset sequence is completed). + */ + I915_WRITE_FW(sfc_forced_lock, + I915_READ_FW(sfc_forced_lock) | sfc_forced_lock_bit); + + if (__intel_wait_for_register_fw(dev_priv, + sfc_forced_lock_ack, + sfc_forced_lock_ack_bit, + sfc_forced_lock_ack_bit, + 1000, 0, NULL)) { + DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n"); + return 0; + } + + if (I915_READ_FW(sfc_usage) & sfc_usage_bit) + return sfc_reset_bit; + + return 0; +} + +static void gen11_unlock_sfc(struct drm_i915_private *dev_priv, + struct intel_engine_cs *engine) +{ + u8 vdbox_sfc_access = RUNTIME_INFO(dev_priv)->vdbox_sfc_access; + i915_reg_t sfc_forced_lock; + u32 sfc_forced_lock_bit; + + switch (engine->class) { + case VIDEO_DECODE_CLASS: + if ((BIT(engine->instance) & vdbox_sfc_access) == 0) + return; + + sfc_forced_lock = GEN11_VCS_SFC_FORCED_LOCK(engine); + sfc_forced_lock_bit = GEN11_VCS_SFC_FORCED_LOCK_BIT; + break; + + case VIDEO_ENHANCEMENT_CLASS: + sfc_forced_lock = GEN11_VECS_SFC_FORCED_LOCK(engine); + sfc_forced_lock_bit = GEN11_VECS_SFC_FORCED_LOCK_BIT; + break; + + default: + return; + } + + I915_WRITE_FW(sfc_forced_lock, + I915_READ_FW(sfc_forced_lock) & ~sfc_forced_lock_bit); +} + /** * gen11_reset_engines - reset individual engines * @dev_priv: i915 device @@ -1947,7 +2044,6 @@ static int gen6_reset_engines(struct drm_i915_private *dev_priv, static int gen11_reset_engines(struct drm_i915_private *dev_priv, unsigned int engine_mask) { - struct intel_engine_cs *engine; const u32 hw_engine_mask[I915_NUM_ENGINES] = { [RCS] = GEN11_GRDOM_RENDER, [BCS] = GEN11_GRDOM_BLT, @@ -1958,21 +2054,30 @@ static int gen11_reset_engines(struct drm_i915_private *dev_priv, [VECS] = GEN11_GRDOM_VECS, [VECS2] = GEN11_GRDOM_VECS2, }; + struct intel_engine_cs *engine; + unsigned int tmp; u32 hw_mask; + int ret; BUILD_BUG_ON(VECS2 + 1 != I915_NUM_ENGINES); if (engine_mask == ALL_ENGINES) { hw_mask = GEN11_GRDOM_FULL; } else { - unsigned int tmp; - hw_mask = 0; - for_each_engine_masked(engine, dev_priv, engine_mask, tmp) + for_each_engine_masked(engine, dev_priv, engine_mask, tmp) { hw_mask |= hw_engine_mask[engine->id]; + hw_mask |= gen11_lock_sfc(dev_priv, engine); + } } - return gen6_hw_domain_reset(dev_priv, hw_mask); + ret = gen6_hw_domain_reset(dev_priv, hw_mask); + + if (engine_mask != ALL_ENGINES) + for_each_engine_masked(engine, dev_priv, engine_mask, tmp) + gen11_unlock_sfc(dev_priv, engine); + + return ret; } /** @@ -2173,7 +2278,7 @@ static reset_func intel_get_gpu_reset(struct drm_i915_private *dev_priv) return gen8_reset_engines; else if (INTEL_GEN(dev_priv) >= 6) return gen6_reset_engines; - else if (IS_GEN5(dev_priv)) + else if (IS_GEN(dev_priv, 5)) return ironlake_do_reset; else if (IS_G4X(dev_priv)) return g4x_do_reset; @@ -2256,7 +2361,7 @@ bool intel_has_gpu_reset(struct drm_i915_private *dev_priv) bool intel_has_reset_engine(struct drm_i915_private *dev_priv) { - return (dev_priv->info.has_reset_engine && + return (INTEL_INFO(dev_priv)->has_reset_engine && i915_modparams.reset >= 2); } @@ -2321,7 +2426,7 @@ intel_uncore_forcewake_for_read(struct drm_i915_private *dev_priv, } else if (INTEL_GEN(dev_priv) >= 6) { fw_domains = __gen6_reg_read_fw_domains(offset); } else { - WARN_ON(!IS_GEN(dev_priv, 2, 5)); + WARN_ON(!IS_GEN_RANGE(dev_priv, 2, 5)); fw_domains = 0; } @@ -2341,12 +2446,12 @@ intel_uncore_forcewake_for_write(struct drm_i915_private *dev_priv, fw_domains = __gen11_fwtable_reg_write_fw_domains(offset); } else if (HAS_FWTABLE(dev_priv) && !IS_VALLEYVIEW(dev_priv)) { fw_domains = __fwtable_reg_write_fw_domains(offset); - } else if (IS_GEN8(dev_priv)) { + } else if (IS_GEN(dev_priv, 8)) { fw_domains = __gen8_reg_write_fw_domains(offset); - } else if (IS_GEN(dev_priv, 6, 7)) { + } else if (IS_GEN_RANGE(dev_priv, 6, 7)) { fw_domains = FORCEWAKE_RENDER; } else { - WARN_ON(!IS_GEN(dev_priv, 2, 5)); + WARN_ON(!IS_GEN_RANGE(dev_priv, 2, 5)); fw_domains = 0; } 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 <[email protected]> + * Manasi Navare <[email protected]> + */ + +#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_wopcm.c b/drivers/gpu/drm/i915/intel_wopcm.c index 92cb82dd0c07..f82a415ea2ba 100644 --- a/drivers/gpu/drm/i915/intel_wopcm.c +++ b/drivers/gpu/drm/i915/intel_wopcm.c @@ -130,11 +130,11 @@ static inline int check_hw_restriction(struct drm_i915_private *i915, { int err = 0; - if (IS_GEN9(i915)) + if (IS_GEN(i915, 9)) err = gen9_check_dword_gap(guc_wopcm_base, guc_wopcm_size); if (!err && - (IS_GEN9(i915) || IS_CNL_REVID(i915, CNL_REVID_A0, CNL_REVID_A0))) + (IS_GEN(i915, 9) || IS_CNL_REVID(i915, CNL_REVID_A0, CNL_REVID_A0))) err = gen9_check_huc_fw_fits(guc_wopcm_size, huc_fw_size); return err; @@ -163,7 +163,7 @@ int intel_wopcm_init(struct intel_wopcm *wopcm) u32 guc_wopcm_rsvd; int err; - if (!USES_GUC(dev_priv)) + if (!USES_GUC(i915)) return 0; GEM_BUG_ON(!wopcm->size); diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index ca1f78a42b17..480c53a2ecb5 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(RUNTIME_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(RUNTIME_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; + const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu; + 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 +798,218 @@ 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; + + 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); -static void whitelist_reg(struct whitelist *w, i915_reg_t reg) + 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); } -static void bdw_whitelist_build(struct whitelist *w) +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv) { + wa_list_apply(dev_priv, &dev_priv->gt_wa_list); } -static void chv_whitelist_build(struct whitelist *w) +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 gen9_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; +} + +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 +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 +1021,7 @@ 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 +1029,12 @@ 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 +1042,7 @@ 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 +1050,18 @@ 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 +1070,21 @@ 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 +1102,178 @@ 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))); +} + +static void rcs_engine_wa_init(struct intel_engine_cs *engine) +{ + 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); + + /* + * 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_GEN(i915, 9) || 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_GEN(i915, 9)) { + /* 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; - intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL); + /* 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_whitelist_workarounds_apply(struct intel_engine_cs *engine) +void intel_engine_init_workarounds(struct intel_engine_cs *engine) { - struct whitelist w; + 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); +} - whitelist_apply(engine, whitelist_build(engine, &w)); +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/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 26c065c8d2c0..6c10734e948d 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -972,7 +972,6 @@ static int gpu_write(struct i915_vma *vma, { struct i915_request *rq; struct i915_vma *batch; - int flags = 0; int err; GEM_BUG_ON(!intel_engine_can_store_dword(engine)); @@ -981,14 +980,14 @@ static int gpu_write(struct i915_vma *vma, if (err) return err; - rq = i915_request_alloc(engine, ctx); - if (IS_ERR(rq)) - return PTR_ERR(rq); - batch = gpu_write_dw(vma, dword * sizeof(u32), value); - if (IS_ERR(batch)) { - err = PTR_ERR(batch); - goto err_request; + if (IS_ERR(batch)) + return PTR_ERR(batch); + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_batch; } err = i915_vma_move_to_active(batch, rq, 0); @@ -996,21 +995,21 @@ static int gpu_write(struct i915_vma *vma, goto err_request; i915_gem_object_set_active_reference(batch->obj); - i915_vma_unpin(batch); - i915_vma_close(batch); - err = engine->emit_bb_start(rq, - batch->node.start, batch->node.size, - flags); + err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); if (err) goto err_request; - err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE); + err = engine->emit_bb_start(rq, + batch->node.start, batch->node.size, + 0); +err_request: if (err) i915_request_skip(rq, err); - -err_request: i915_request_add(rq); +err_batch: + i915_vma_unpin(batch); + i915_vma_close(batch); return err; } @@ -1703,7 +1702,6 @@ int i915_gem_huge_page_mock_selftests(void) }; struct drm_i915_private *dev_priv; struct i915_hw_ppgtt *ppgtt; - struct pci_dev *pdev; int err; dev_priv = mock_gem_device(); @@ -1713,9 +1711,6 @@ int i915_gem_huge_page_mock_selftests(void) /* Pretend to be a device which supports the 48b PPGTT */ mkwrite_device_info(dev_priv)->ppgtt = INTEL_PPGTT_FULL_4LVL; - pdev = dev_priv->drm.pdev; - dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(39)); - mutex_lock(&dev_priv->drm.struct_mutex); ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV)); if (IS_ERR(ppgtt)) { diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c index d0aa19d17653..bdcc53e15e75 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem.c @@ -121,7 +121,7 @@ static void pm_resume(struct drm_i915_private *i915) */ intel_runtime_pm_get(i915); - intel_engines_sanitize(i915); + intel_engines_sanitize(i915, false); i915_gem_sanitize(i915); i915_gem_resume(i915); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c index 7d82043aff10..d00cdf3c2939 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c @@ -627,7 +627,7 @@ static int igt_ctx_exec(void *arg) ncontexts++; } pr_info("Submitted %lu contexts (across %u engines), filling %lu dwords\n", - ncontexts, INTEL_INFO(i915)->num_rings, ndwords); + ncontexts, RUNTIME_INFO(i915)->num_rings, ndwords); dw = 0; list_for_each_entry(obj, &objects, st_link) { @@ -732,7 +732,7 @@ static int igt_ctx_readonly(void *arg) } } pr_info("Submitted %lu dwords (across %u engines)\n", - ndwords, INTEL_INFO(i915)->num_rings); + ndwords, RUNTIME_INFO(i915)->num_rings); dw = 0; list_for_each_entry(obj, &objects, st_link) { @@ -1064,7 +1064,7 @@ static int igt_vm_isolation(void *arg) count += this; } pr_info("Checked %lu scratch offsets across %d engines\n", - count, INTEL_INFO(i915)->num_rings); + count, RUNTIME_INFO(i915)->num_rings); out_rpm: intel_runtime_pm_put(i915); diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index c3999dd2021e..be7ecb66ad11 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -238,6 +238,7 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj, u32 *cpu; GEM_BUG_ON(view.partial.size > nreal); + cond_resched(); err = i915_gem_object_set_to_gtt_domain(obj, true); if (err) { 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..0e70df0230b8 --- /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 move_to_active(struct i915_vma *vma, + struct i915_request *rq, + unsigned int flags) +{ + int err; + + err = i915_vma_move_to_active(vma, rq, flags); + if (err) + return err; + + if (!i915_gem_object_has_active_reference(vma->obj)) { + i915_gem_object_get(vma->obj); + i915_gem_object_set_active_reference(vma->obj); + } + + return 0; +} + +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_address_space *vm = &ctx->ppgtt->vm; + struct i915_request *rq = NULL; + struct i915_vma *hws, *vma; + u32 *batch; + int err; + + vma = i915_vma_instance(spin->obj, vm, NULL); + if (IS_ERR(vma)) + return ERR_CAST(vma); + + hws = i915_vma_instance(spin->hws, vm, NULL); + if (IS_ERR(hws)) + return ERR_CAST(hws); + + err = i915_vma_pin(vma, 0, 0, PIN_USER); + if (err) + return ERR_PTR(err); + + err = i915_vma_pin(hws, 0, 0, PIN_USER); + if (err) + goto unpin_vma; + + rq = i915_request_alloc(engine, ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto unpin_hws; + } + + err = move_to_active(vma, rq, 0); + if (err) + goto cancel_rq; + + err = move_to_active(hws, rq, 0); + if (err) + goto cancel_rq; + + 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 = engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0); + +cancel_rq: + if (err) { + i915_request_skip(rq, err); + i915_request_add(rq); + } +unpin_hws: + i915_vma_unpin(hws); +unpin_vma: + i915_vma_unpin(vma); + return err ? ERR_PTR(err) : 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..797cf5e6d6d4 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" @@ -102,52 +103,87 @@ static u64 hws_address(const struct i915_vma *hws, return hws->node.start + offset_in_page(sizeof(u32)*rq->fence.context); } -static int emit_recurse_batch(struct hang *h, - struct i915_request *rq) +static int move_to_active(struct i915_vma *vma, + struct i915_request *rq, + unsigned int flags) +{ + int err; + + err = i915_vma_move_to_active(vma, rq, flags); + if (err) + return err; + + if (!i915_gem_object_has_active_reference(vma->obj)) { + i915_gem_object_get(vma->obj); + i915_gem_object_set_active_reference(vma->obj); + } + + return 0; +} + +static struct i915_request * +hang_create_request(struct hang *h, struct intel_engine_cs *engine) { struct drm_i915_private *i915 = h->i915; struct i915_address_space *vm = - rq->gem_context->ppgtt ? - &rq->gem_context->ppgtt->vm : - &i915->ggtt.vm; + h->ctx->ppgtt ? &h->ctx->ppgtt->vm : &i915->ggtt.vm; + struct i915_request *rq = NULL; struct i915_vma *hws, *vma; unsigned int flags; u32 *batch; int err; + if (i915_gem_object_is_active(h->obj)) { + struct drm_i915_gem_object *obj; + void *vaddr; + + obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + vaddr = i915_gem_object_pin_map(obj, + i915_coherent_map_type(h->i915)); + if (IS_ERR(vaddr)) { + i915_gem_object_put(obj); + return ERR_CAST(vaddr); + } + + i915_gem_object_unpin_map(h->obj); + i915_gem_object_put(h->obj); + + h->obj = obj; + h->batch = vaddr; + } + vma = i915_vma_instance(h->obj, vm, NULL); if (IS_ERR(vma)) - return PTR_ERR(vma); + return ERR_CAST(vma); hws = i915_vma_instance(h->hws, vm, NULL); if (IS_ERR(hws)) - return PTR_ERR(hws); + return ERR_CAST(hws); err = i915_vma_pin(vma, 0, 0, PIN_USER); if (err) - return err; + return ERR_PTR(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) + rq = i915_request_alloc(engine, h->ctx); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); 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); + err = move_to_active(vma, rq, 0); if (err) - goto unpin_hws; + goto cancel_rq; - if (!i915_gem_object_has_active_reference(hws->obj)) { - i915_gem_object_get(hws->obj); - i915_gem_object_set_active_reference(hws->obj); - } + err = move_to_active(hws, rq, 0); + if (err) + goto cancel_rq; batch = h->batch; if (INTEL_GEN(i915) >= 8) { @@ -212,52 +248,16 @@ static int emit_recurse_batch(struct hang *h, err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags); +cancel_rq: + if (err) { + i915_request_skip(rq, err); + i915_request_add(rq); + } unpin_hws: i915_vma_unpin(hws); unpin_vma: i915_vma_unpin(vma); - return err; -} - -static struct i915_request * -hang_create_request(struct hang *h, struct intel_engine_cs *engine) -{ - struct i915_request *rq; - int err; - - if (i915_gem_object_is_active(h->obj)) { - struct drm_i915_gem_object *obj; - void *vaddr; - - obj = i915_gem_object_create_internal(h->i915, PAGE_SIZE); - if (IS_ERR(obj)) - return ERR_CAST(obj); - - vaddr = i915_gem_object_pin_map(obj, - i915_coherent_map_type(h->i915)); - if (IS_ERR(vaddr)) { - i915_gem_object_put(obj); - return ERR_CAST(vaddr); - } - - i915_gem_object_unpin_map(h->obj); - i915_gem_object_put(h->obj); - - h->obj = obj; - h->batch = vaddr; - } - - rq = i915_request_alloc(engine, h->ctx); - if (IS_ERR(rq)) - return rq; - - err = emit_recurse_batch(h, rq); - if (err) { - i915_request_add(rq); - return ERR_PTR(err); - } - - return rq; + return err ? ERR_PTR(err) : rq; } static u32 hws_seqno(const struct hang *h, const struct i915_request *rq) @@ -308,6 +308,7 @@ 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 +329,14 @@ 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 +354,6 @@ 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 +362,7 @@ 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 +377,7 @@ 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; @@ -413,6 +385,30 @@ static int igt_global_reset(void *arg) return err; } +static int igt_wedged_reset(void *arg) +{ + struct drm_i915_private *i915 = arg; + + /* Check that we can recover a wedged device with a GPU reset */ + + igt_global_reset_lock(i915); + mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); + + i915_gem_set_wedged(i915); + GEM_BUG_ON(!i915_terminally_wedged(&i915->gpu_error)); + + set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); + i915_reset(i915, ALL_ENGINES, NULL); + GEM_BUG_ON(test_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags)); + + intel_runtime_pm_put(i915); + mutex_unlock(&i915->drm.struct_mutex); + igt_global_reset_unlock(i915); + + return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0; +} + static bool wait_for_idle(struct intel_engine_cs *engine) { return wait_for(intel_engine_is_idle(engine), IGT_IDLE_TIMEOUT) == 0; @@ -936,7 +932,7 @@ 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 +984,7 @@ 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 +1062,7 @@ 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 +1182,7 @@ 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 +1262,7 @@ 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 +1393,7 @@ 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; @@ -1476,10 +1472,182 @@ err_unlock: return err; } +static void __preempt_begin(void) +{ + preempt_disable(); +} + +static void __preempt_end(void) +{ + preempt_enable(); +} + +static void __softirq_begin(void) +{ + local_bh_disable(); +} + +static void __softirq_end(void) +{ + local_bh_enable(); +} + +static void __hardirq_begin(void) +{ + local_irq_disable(); +} + +static void __hardirq_end(void) +{ + local_irq_enable(); +} + +struct atomic_section { + const char *name; + void (*critical_section_begin)(void); + void (*critical_section_end)(void); +}; + +static int __igt_atomic_reset_engine(struct intel_engine_cs *engine, + const struct atomic_section *p, + const char *mode) +{ + struct tasklet_struct * const t = &engine->execlists.tasklet; + int err; + + GEM_TRACE("i915_reset_engine(%s:%s) under %s\n", + engine->name, mode, p->name); + + tasklet_disable_nosync(t); + p->critical_section_begin(); + + err = i915_reset_engine(engine, NULL); + + p->critical_section_end(); + tasklet_enable(t); + + if (err) + pr_err("i915_reset_engine(%s:%s) failed under %s\n", + engine->name, mode, p->name); + + return err; +} + +static int igt_atomic_reset_engine(struct intel_engine_cs *engine, + const struct atomic_section *p) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_request *rq; + struct hang h; + int err; + + err = __igt_atomic_reset_engine(engine, p, "idle"); + if (err) + return err; + + err = hang_init(&h, i915); + if (err) + return err; + + rq = hang_create_request(&h, engine); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto out; + } + + i915_request_get(rq); + i915_request_add(rq); + + if (wait_until_running(&h, rq)) { + err = __igt_atomic_reset_engine(engine, p, "active"); + } else { + pr_err("%s(%s): Failed to start request %llx, at %x\n", + __func__, engine->name, + rq->fence.seqno, hws_seqno(&h, rq)); + err = -EIO; + } + + if (err == 0) { + struct igt_wedge_me w; + + igt_wedge_on_timeout(&w, i915, HZ / 20 /* 50ms timeout*/) + i915_request_wait(rq, + I915_WAIT_LOCKED, + MAX_SCHEDULE_TIMEOUT); + if (i915_terminally_wedged(&i915->gpu_error)) + err = -EIO; + } + + i915_request_put(rq); +out: + hang_fini(&h); + return err; +} + +static void force_reset(struct drm_i915_private *i915) +{ + i915_gem_set_wedged(i915); + set_bit(I915_RESET_HANDOFF, &i915->gpu_error.flags); + i915_reset(i915, 0, NULL); +} + +static int igt_atomic_reset(void *arg) +{ + static const struct atomic_section phases[] = { + { "preempt", __preempt_begin, __preempt_end }, + { "softirq", __softirq_begin, __softirq_end }, + { "hardirq", __hardirq_begin, __hardirq_end }, + { } + }; + struct drm_i915_private *i915 = arg; + int err = 0; + + /* Check that the resets are usable from atomic context */ + + if (USES_GUC_SUBMISSION(i915)) + return 0; /* guc is dead; long live the guc */ + + igt_global_reset_lock(i915); + mutex_lock(&i915->drm.struct_mutex); + intel_runtime_pm_get(i915); + + /* Flush any requests before we get started and check basics */ + force_reset(i915); + if (i915_terminally_wedged(&i915->gpu_error)) + goto unlock; + + if (intel_has_reset_engine(i915)) { + struct intel_engine_cs *engine; + enum intel_engine_id id; + + for_each_engine(engine, i915, id) { + const typeof(*phases) *p; + + for (p = phases; p->name; p++) { + err = igt_atomic_reset_engine(engine, p); + if (err) + goto out; + } + } + } + +out: + /* As we poke around the guts, do a full reset before continuing. */ + force_reset(i915); + +unlock: + intel_runtime_pm_put(i915); + mutex_unlock(&i915->drm.struct_mutex); + igt_global_reset_unlock(i915); + + return err; +} + int intel_hangcheck_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_global_reset), /* attempt to recover GPU first */ + SUBTEST(igt_wedged_reset), SUBTEST(igt_hang_sanitycheck), SUBTEST(igt_reset_idle_engine), SUBTEST(igt_reset_active_engine), @@ -1490,6 +1658,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915) SUBTEST(igt_reset_evict_ppgtt), SUBTEST(igt_reset_evict_fence), SUBTEST(igt_handle_error), + SUBTEST(igt_atomic_reset), }; bool saved_hangcheck; int err; diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c index 94fc0e5c8766..00caaa00f02f 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); @@ -719,7 +522,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags) pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n", count, flags, - INTEL_INFO(smoke->i915)->num_rings, smoke->ncontext); + RUNTIME_INFO(smoke->i915)->num_rings, smoke->ncontext); return 0; } @@ -747,7 +550,7 @@ static int smoke_random(struct preempt_smoke *smoke, unsigned int flags) pr_info("Submitted %lu random:%x requests across %d engines and %d contexts\n", count, flags, - INTEL_INFO(smoke->i915)->num_rings, smoke->ncontext); + RUNTIME_INFO(smoke->i915)->num_rings, smoke->ncontext); return 0; } diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c index d1a0923d2f38..c2b3cd8fcc34 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 +315,149 @@ 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); + intel_runtime_pm_get(i915); + + ok = verify_gt_engine_wa(i915, "before reset"); + if (!ok) + goto out; + + set_bit(I915_RESET_HANDOFF, &error->flags); + i915_reset(i915, ALL_ENGINES, "live_workarounds"); + + ok = verify_gt_engine_wa(i915, "after reset"); + +out: + intel_runtime_pm_put(i915); + 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); + intel_runtime_pm_get(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; + } + + i915_reset_engine(engine, "live_workarounds"); + + 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; + + rq = igt_spinner_create_request(&spin, ctx, engine, MI_NOOP); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + igt_spinner_fini(&spin); + goto err; + } + + i915_request_add(rq); + + if (!igt_wait_for_spinner(&spin, rq)) { + pr_err("Spinner failed to start\n"); + igt_spinner_fini(&spin); + ret = -ETIMEDOUT; + goto err; + } + + i915_reset_engine(engine, "live_workarounds"); + + igt_spinner_end(&spin); + igt_spinner_fini(&spin); + + ok = verify_gt_engine_wa(i915, "after busy reset"); + if (!ok) { + ret = -ESRCH; + goto err; + } + } + +err: + intel_runtime_pm_put(i915); + 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; diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c index d0c44c18db42..50e1a0b1af7e 100644 --- a/drivers/gpu/drm/i915/selftests/mock_engine.c +++ b/drivers/gpu/drm/i915/selftests/mock_engine.c @@ -148,8 +148,6 @@ static struct intel_ring *mock_ring(struct intel_engine_cs *engine) const unsigned long sz = PAGE_SIZE / 2; struct mock_ring *ring; - BUILD_BUG_ON(MIN_SPACE_FOR_ADD_REQUEST > sz); - ring = kzalloc(sizeof(*ring) + sz, GFP_KERNEL); if (!ring) return NULL; diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 43ed8b28aeaa..baa3c38919de 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -147,7 +147,7 @@ struct drm_i915_private *mock_gem_device(void) pdev->class = PCI_BASE_CLASS_DISPLAY << 16; pdev->dev.release = release_dev; dev_set_name(&pdev->dev, "mock"); - dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) /* hack to disable iommu for the fake device; force identity mapping */ diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 0a7252aecfa5..bb71db63c99c 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -334,7 +334,7 @@ int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, } EXPORT_SYMBOL_GPL(sysfs_create_file_ns); -int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr) +int sysfs_create_files(struct kobject *kobj, const struct attribute * const *ptr) { int err = 0; int i; @@ -493,7 +493,7 @@ bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr) return ret; } -void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr) +void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *ptr) { int i; for (i = 0; ptr[i]; i++) diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 3314e91f6eb3..c223c87ef119 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -314,6 +314,10 @@ # define DP_PSR_SETUP_TIME_SHIFT 1 # define DP_PSR2_SU_Y_COORDINATE_REQUIRED (1 << 4) /* eDP 1.4a */ # define DP_PSR2_SU_GRANULARITY_REQUIRED (1 << 5) /* eDP 1.4b */ + +#define DP_PSR2_SU_X_GRANULARITY 0x072 /* eDP 1.4b */ +#define DP_PSR2_SU_Y_GRANULARITY 0x074 /* eDP 1.4b */ + /* * 0x80-0x8f describe downstream port capabilities, but there are two layouts * based on whether DP_DETAILED_CAP_INFO_AVAILABLE was set. If it was not, @@ -1123,7 +1127,8 @@ drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) u8 drm_dp_dsc_sink_max_slice_count(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE], bool is_edp); u8 drm_dp_dsc_sink_line_buf_depth(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]); -u8 drm_dp_dsc_sink_max_color_depth(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE]); +int drm_dp_dsc_sink_supported_input_bpcs(const u8 dsc_dpc[DP_DSC_RECEIVER_CAP_SIZE], + u8 dsc_bpc[3]); static inline bool drm_dp_sink_supports_dsc(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) @@ -1364,6 +1369,13 @@ enum drm_dp_quirk { * to 16 bits. So will give a constant value (0x8000) for compatability. */ DP_DPCD_QUIRK_CONSTANT_N, + /** + * @DP_DPCD_QUIRK_NO_PSR: + * + * The device does not support PSR even if reports that it supports or + * driver still need to implement proper handling for such device. + */ + DP_DPCD_QUIRK_NO_PSR, }; /** diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h new file mode 100644 index 000000000000..d03f1b83421a --- /dev/null +++ b/include/drm/drm_dsc.h @@ -0,0 +1,485 @@ +/* SPDX-License-Identifier: MIT + * Copyright (C) 2018 Intel Corp. + * + * Authors: + * Manasi Navare <[email protected]> + */ + +#ifndef DRM_DSC_H_ +#define DRM_DSC_H_ + +#include <drm/drm_dp_helper.h> + +/* VESA Display Stream Compression DSC 1.2 constants */ +#define DSC_NUM_BUF_RANGES 15 +#define DSC_MUX_WORD_SIZE_8_10_BPC 48 +#define DSC_MUX_WORD_SIZE_12_BPC 64 +#define DSC_RC_PIXELS_PER_GROUP 3 +#define DSC_SCALE_DECREMENT_INTERVAL_MAX 4095 +#define DSC_RANGE_BPG_OFFSET_MASK 0x3f + +/* DSC Rate Control Constants */ +#define DSC_RC_MODEL_SIZE_CONST 8192 +#define DSC_RC_EDGE_FACTOR_CONST 6 +#define DSC_RC_TGT_OFFSET_HI_CONST 3 +#define DSC_RC_TGT_OFFSET_LO_CONST 3 + +/* DSC PPS constants and macros */ +#define DSC_PPS_VERSION_MAJOR_SHIFT 4 +#define DSC_PPS_BPC_SHIFT 4 +#define DSC_PPS_MSB_SHIFT 8 +#define DSC_PPS_LSB_MASK (0xFF << 0) +#define DSC_PPS_BPP_HIGH_MASK (0x3 << 8) +#define DSC_PPS_VBR_EN_SHIFT 2 +#define DSC_PPS_SIMPLE422_SHIFT 3 +#define DSC_PPS_CONVERT_RGB_SHIFT 4 +#define DSC_PPS_BLOCK_PRED_EN_SHIFT 5 +#define DSC_PPS_INIT_XMIT_DELAY_HIGH_MASK (0x3 << 8) +#define DSC_PPS_SCALE_DEC_INT_HIGH_MASK (0xF << 8) +#define DSC_PPS_RC_TGT_OFFSET_HI_SHIFT 4 +#define DSC_PPS_RC_RANGE_MINQP_SHIFT 11 +#define DSC_PPS_RC_RANGE_MAXQP_SHIFT 6 +#define DSC_PPS_NATIVE_420_SHIFT 1 +#define DSC_1_2_MAX_LINEBUF_DEPTH_BITS 16 +#define DSC_1_2_MAX_LINEBUF_DEPTH_VAL 0 +#define DSC_1_1_MAX_LINEBUF_DEPTH_BITS 13 + +/* Configuration for a single Rate Control model range */ +struct drm_dsc_rc_range_parameters { + /* Min Quantization Parameters allowed for this range */ + u8 range_min_qp; + /* Max Quantization Parameters allowed for this range */ + u8 range_max_qp; + /* Bits/group offset to apply to target for this group */ + u8 range_bpg_offset; +}; + +struct drm_dsc_config { + /* Bits / component for previous reconstructed line buffer */ + u8 line_buf_depth; + /* Bits per component to code (must be 8, 10, or 12) */ + u8 bits_per_component; + /* + * Flag indicating to do RGB - YCoCg conversion + * and back (should be 1 for RGB input) + */ + bool convert_rgb; + u8 slice_count; + /* Slice Width */ + u16 slice_width; + /* Slice Height */ + u16 slice_height; + /* + * 4:2:2 enable mode (from PPS, 4:2:2 conversion happens + * outside of DSC encode/decode algorithm) + */ + bool enable422; + /* Picture Width */ + u16 pic_width; + /* Picture Height */ + u16 pic_height; + /* Offset to bits/group used by RC to determine QP adjustment */ + u8 rc_tgt_offset_high; + /* Offset to bits/group used by RC to determine QP adjustment */ + u8 rc_tgt_offset_low; + /* Bits/pixel target << 4 (ie., 4 fractional bits) */ + u16 bits_per_pixel; + /* + * Factor to determine if an edge is present based + * on the bits produced + */ + u8 rc_edge_factor; + /* Slow down incrementing once the range reaches this value */ + u8 rc_quant_incr_limit1; + /* Slow down incrementing once the range reaches this value */ + u8 rc_quant_incr_limit0; + /* Number of pixels to delay the initial transmission */ + u16 initial_xmit_delay; + /* Number of pixels to delay the VLD on the decoder,not including SSM */ + u16 initial_dec_delay; + /* Block prediction enable */ + bool block_pred_enable; + /* Bits/group offset to use for first line of the slice */ + u8 first_line_bpg_offset; + /* Value to use for RC model offset at slice start */ + u16 initial_offset; + /* Thresholds defining each of the buffer ranges */ + u16 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; + /* Parameters for each of the RC ranges */ + struct drm_dsc_rc_range_parameters rc_range_params[DSC_NUM_BUF_RANGES]; + /* Total size of RC model */ + u16 rc_model_size; + /* Minimum QP where flatness information is sent */ + u8 flatness_min_qp; + /* Maximum QP where flatness information is sent */ + u8 flatness_max_qp; + /* Initial value for scale factor */ + u8 initial_scale_value; + /* Decrement scale factor every scale_decrement_interval groups */ + u16 scale_decrement_interval; + /* Increment scale factor every scale_increment_interval groups */ + u16 scale_increment_interval; + /* Non-first line BPG offset to use */ + u16 nfl_bpg_offset; + /* BPG offset used to enforce slice bit */ + u16 slice_bpg_offset; + /* Final RC linear transformation offset value */ + u16 final_offset; + /* Enable on-off VBR (ie., disable stuffing bits) */ + bool vbr_enable; + /* Mux word size (in bits) for SSM mode */ + u8 mux_word_size; + /* + * The (max) size in bytes of the "chunks" that are + * used in slice multiplexing + */ + u16 slice_chunk_size; + /* Rate Control buffer siz in bits */ + u16 rc_bits; + /* DSC Minor Version */ + u8 dsc_version_minor; + /* DSC Major version */ + u8 dsc_version_major; + /* Native 4:2:2 support */ + bool native_422; + /* Native 4:2:0 support */ + bool native_420; + /* Additional bits/grp for seconnd line of slice for native 4:2:0 */ + u8 second_line_bpg_offset; + /* Num of bits deallocated for each grp that is not in second line of slice */ + u16 nsl_bpg_offset; + /* Offset adj fr second line in Native 4:2:0 mode */ + u16 second_line_offset_adj; +}; + +/** + * struct picture_parameter_set - Represents 128 bytes of Picture Parameter Set + * + * The VESA DSC standard defines picture parameter set (PPS) which display + * stream compression encoders must communicate to decoders. + * The PPS is encapsulated in 128 bytes (PPS 0 through PPS 127). The fields in + * this structure are as per Table 4.1 in Vesa DSC specification v1.1/v1.2. + * The PPS fields that span over more than a byte should be stored in Big Endian + * format. + */ +struct drm_dsc_picture_parameter_set { + /** + * @dsc_version: + * PPS0[3:0] - dsc_version_minor: Contains Minor version of DSC + * PPS0[7:4] - dsc_version_major: Contains major version of DSC + */ + u8 dsc_version; + /** + * @pps_identifier: + * PPS1[7:0] - Application specific identifier that can be + * used to differentiate between different PPS tables. + */ + u8 pps_identifier; + /** + * @pps_reserved: + * PPS2[7:0]- RESERVED Byte + */ + u8 pps_reserved; + /** + * @pps_3: + * PPS3[3:0] - linebuf_depth: Contains linebuffer bit depth used to + * generate the bitstream. (0x0 - 16 bits for DSC 1.2, 0x8 - 8 bits, + * 0xA - 10 bits, 0xB - 11 bits, 0xC - 12 bits, 0xD - 13 bits, + * 0xE - 14 bits for DSC1.2, 0xF - 14 bits for DSC 1.2. + * PPS3[7:4] - bits_per_component: Bits per component for the original + * pixels of the encoded picture. + * 0x0 = 16bpc (allowed only when dsc_version_minor = 0x2) + * 0x8 = 8bpc, 0xA = 10bpc, 0xC = 12bpc, 0xE = 14bpc (also + * allowed only when dsc_minor_version = 0x2) + */ + u8 pps_3; + /** + * @pps_4: + * PPS4[1:0] -These are the most significant 2 bits of + * compressed BPP bits_per_pixel[9:0] syntax element. + * PPS4[2] - vbr_enable: 0 = VBR disabled, 1 = VBR enabled + * PPS4[3] - simple_422: Indicates if decoder drops samples to + * reconstruct the 4:2:2 picture. + * PPS4[4] - Convert_rgb: Indicates if DSC color space conversion is + * active. + * PPS4[5] - blobk_pred_enable: Indicates if BP is used to code any + * groups in picture + * PPS4[7:6] - Reseved bits + */ + u8 pps_4; + /** + * @bits_per_pixel_low: + * PPS5[7:0] - This indicates the lower significant 8 bits of + * the compressed BPP bits_per_pixel[9:0] element. + */ + u8 bits_per_pixel_low; + /** + * @pic_height: + * PPS6[7:0], PPS7[7:0] -pic_height: Specifies the number of pixel rows + * within the raster. + */ + __be16 pic_height; + /** + * @pic_width: + * PPS8[7:0], PPS9[7:0] - pic_width: Number of pixel columns within + * the raster. + */ + __be16 pic_width; + /** + * @slice_height: + * PPS10[7:0], PPS11[7:0] - Slice height in units of pixels. + */ + __be16 slice_height; + /** + * @slice_width: + * PPS12[7:0], PPS13[7:0] - Slice width in terms of pixels. + */ + __be16 slice_width; + /** + * @chunk_size: + * PPS14[7:0], PPS15[7:0] - Size in units of bytes of the chunks + * that are used for slice multiplexing. + */ + __be16 chunk_size; + /** + * @initial_xmit_delay_high: + * PPS16[1:0] - Most Significant two bits of initial transmission delay. + * It specifies the number of pixel times that the encoder waits before + * transmitting data from its rate buffer. + * PPS16[7:2] - Reserved + */ + u8 initial_xmit_delay_high; + /** + * @initial_xmit_delay_low: + * PPS17[7:0] - Least significant 8 bits of initial transmission delay. + */ + u8 initial_xmit_delay_low; + /** + * @initial_dec_delay: + * + * PPS18[7:0], PPS19[7:0] - Initial decoding delay which is the number + * of pixel times that the decoder accumulates data in its rate buffer + * before starting to decode and output pixels. + */ + __be16 initial_dec_delay; + /** + * @pps20_reserved: + * + * PPS20[7:0] - Reserved + */ + u8 pps20_reserved; + /** + * @initial_scale_value: + * PPS21[5:0] - Initial rcXformScale factor used at beginning + * of a slice. + * PPS21[7:6] - Reserved + */ + u8 initial_scale_value; + /** + * @scale_increment_interval: + * PPS22[7:0], PPS23[7:0] - Number of group times between incrementing + * the rcXformScale factor at end of a slice. + */ + __be16 scale_increment_interval; + /** + * @scale_decrement_interval_high: + * PPS24[3:0] - Higher 4 bits indicating number of group times between + * decrementing the rcXformScale factor at beginning of a slice. + * PPS24[7:4] - Reserved + */ + u8 scale_decrement_interval_high; + /** + * @scale_decrement_interval_low: + * PPS25[7:0] - Lower 8 bits of scale decrement interval + */ + u8 scale_decrement_interval_low; + /** + * @pps26_reserved: + * PPS26[7:0] + */ + u8 pps26_reserved; + /** + * @first_line_bpg_offset: + * PPS27[4:0] - Number of additional bits that are allocated + * for each group on first line of a slice. + * PPS27[7:5] - Reserved + */ + u8 first_line_bpg_offset; + /** + * @nfl_bpg_offset: + * PPS28[7:0], PPS29[7:0] - Number of bits including frac bits + * deallocated for each group for groups after the first line of slice. + */ + __be16 nfl_bpg_offset; + /** + * @slice_bpg_offset: + * PPS30, PPS31[7:0] - Number of bits that are deallocated for each + * group to enforce the slice constraint. + */ + __be16 slice_bpg_offset; + /** + * @initial_offset: + * PPS32,33[7:0] - Initial value for rcXformOffset + */ + __be16 initial_offset; + /** + * @final_offset: + * PPS34,35[7:0] - Maximum end-of-slice value for rcXformOffset + */ + __be16 final_offset; + /** + * @flatness_min_qp: + * PPS36[4:0] - Minimum QP at which flatness is signaled and + * flatness QP adjustment is made. + * PPS36[7:5] - Reserved + */ + u8 flatness_min_qp; + /** + * @flatness_max_qp: + * PPS37[4:0] - Max QP at which flatness is signalled and + * the flatness adjustment is made. + * PPS37[7:5] - Reserved + */ + u8 flatness_max_qp; + /** + * @rc_model_size: + * PPS38,39[7:0] - Number of bits within RC Model. + */ + __be16 rc_model_size; + /** + * @rc_edge_factor: + * PPS40[3:0] - Ratio of current activity vs, previous + * activity to determine presence of edge. + * PPS40[7:4] - Reserved + */ + u8 rc_edge_factor; + /** + * @rc_quant_incr_limit0: + * PPS41[4:0] - QP threshold used in short term RC + * PPS41[7:5] - Reserved + */ + u8 rc_quant_incr_limit0; + /** + * @rc_quant_incr_limit1: + * PPS42[4:0] - QP threshold used in short term RC + * PPS42[7:5] - Reserved + */ + u8 rc_quant_incr_limit1; + /** + * @rc_tgt_offset: + * PPS43[3:0] - Lower end of the variability range around the target + * bits per group that is allowed by short term RC. + * PPS43[7:4]- Upper end of the variability range around the target + * bits per group that i allowed by short term rc. + */ + u8 rc_tgt_offset; + /** + * @rc_buf_thresh: + * PPS44[7:0] - PPS57[7:0] - Specifies the thresholds in RC model for + * the 15 ranges defined by 14 thresholds. + */ + u8 rc_buf_thresh[DSC_NUM_BUF_RANGES - 1]; + /** + * @rc_range_parameters: + * PPS58[7:0] - PPS87[7:0] + * Parameters that correspond to each of the 15 ranges. + */ + __be16 rc_range_parameters[DSC_NUM_BUF_RANGES]; + /** + * @native_422_420: + * PPS88[0] - 0 = Native 4:2:2 not used + * 1 = Native 4:2:2 used + * PPS88[1] - 0 = Native 4:2:0 not use + * 1 = Native 4:2:0 used + * PPS88[7:2] - Reserved 6 bits + */ + u8 native_422_420; + /** + * @second_line_bpg_offset: + * PPS89[4:0] - Additional bits/group budget for the + * second line of a slice in Native 4:2:0 mode. + * Set to 0 if DSC minor version is 1 or native420 is 0. + * PPS89[7:5] - Reserved + */ + u8 second_line_bpg_offset; + /** + * @nsl_bpg_offset: + * PPS90[7:0], PPS91[7:0] - Number of bits that are deallocated + * for each group that is not in the second line of a slice. + */ + __be16 nsl_bpg_offset; + /** + * @second_line_offset_adj: + * PPS92[7:0], PPS93[7:0] - Used as offset adjustment for the second + * line in Native 4:2:0 mode. + */ + __be16 second_line_offset_adj; + /** + * @pps_long_94_reserved: + * PPS 94, 95, 96, 97 - Reserved + */ + u32 pps_long_94_reserved; + /** + * @pps_long_98_reserved: + * PPS 98, 99, 100, 101 - Reserved + */ + u32 pps_long_98_reserved; + /** + * @pps_long_102_reserved: + * PPS 102, 103, 104, 105 - Reserved + */ + u32 pps_long_102_reserved; + /** + * @pps_long_106_reserved: + * PPS 106, 107, 108, 109 - reserved + */ + u32 pps_long_106_reserved; + /** + * @pps_long_110_reserved: + * PPS 110, 111, 112, 113 - reserved + */ + u32 pps_long_110_reserved; + /** + * @pps_long_114_reserved: + * PPS 114 - 117 - reserved + */ + u32 pps_long_114_reserved; + /** + * @pps_long_118_reserved: + * PPS 118 - 121 - reserved + */ + u32 pps_long_118_reserved; + /** + * @pps_long_122_reserved: + * PPS 122- 125 - reserved + */ + u32 pps_long_122_reserved; + /** + * @pps_short_126_reserved: + * PPS 126, 127 - reserved + */ + __be16 pps_short_126_reserved; +} __packed; + +/** + * struct drm_dsc_pps_infoframe - DSC infoframe carrying the Picture Parameter + * Set Metadata + * + * This structure represents the DSC PPS infoframe required to send the Picture + * Parameter Set metadata required before enabling VESA Display Stream + * Compression. This is based on the DP Secondary Data Packet structure and + * comprises of SDP Header as defined in drm_dp_helper.h and PPS payload. + * + * @pps_header: Header for PPS as per DP SDP header format + * @pps_payload: PPS payload fields as per DSC specification Table 4-1 + */ +struct drm_dsc_pps_infoframe { + struct dp_sdp_header pps_header; + struct drm_dsc_picture_parameter_set pps_payload; +} __packed; + +void drm_dsc_dp_pps_header_init(struct drm_dsc_pps_infoframe *pps_sdp); +void drm_dsc_pps_infoframe_pack(struct drm_dsc_pps_infoframe *pps_sdp, + const struct drm_dsc_config *dsc_cfg); + +#endif /* _DRM_DSC_H_ */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 987cefa337de..786816cf4aa5 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -234,7 +234,7 @@ int __must_check sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns); int __must_check sysfs_create_files(struct kobject *kobj, - const struct attribute **attr); + const struct attribute * const *attr); int __must_check sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr, umode_t mode); struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj, @@ -243,7 +243,7 @@ void sysfs_unbreak_active_protection(struct kernfs_node *kn); void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr, const void *ns); bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr); -void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr); +void sysfs_remove_files(struct kobject *kobj, const struct attribute * const *attr); int __must_check sysfs_create_bin_file(struct kobject *kobj, const struct bin_attribute *attr); @@ -342,7 +342,7 @@ static inline int sysfs_create_file_ns(struct kobject *kobj, } static inline int sysfs_create_files(struct kobject *kobj, - const struct attribute **attr) + const struct attribute * const *attr) { return 0; } @@ -377,7 +377,7 @@ static inline bool sysfs_remove_file_self(struct kobject *kobj, } static inline void sysfs_remove_files(struct kobject *kobj, - const struct attribute **attr) + const struct attribute * const *attr) { } |