diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
41 files changed, 446 insertions, 177 deletions
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 5dcfa7feffa9..1390729401a0 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1629,6 +1629,8 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder, /* FIXME: initialize from VBT */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; + ret = intel_dsc_compute_params(crtc_state); if (ret) return ret; @@ -2070,7 +2072,14 @@ void icl_dsi_init(struct drm_i915_private *dev_priv) else intel_dsi->ports = BIT(port); + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports; + intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports; + + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports; + intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports; for_each_dsi_port(port, intel_dsi->ports) { diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index 110fc98ec280..f5e1d692976e 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -16,6 +16,7 @@ #include "intel_dsi_dcs_backlight.h" #include "intel_panel.h" #include "intel_pci_config.h" +#include "intel_pps.h" /** * scale - scale values from one range to another @@ -971,26 +972,24 @@ int intel_backlight_device_register(struct intel_connector *connector) if (!name) return -ENOMEM; - bd = backlight_device_register(name, connector->base.kdev, connector, - &intel_backlight_device_ops, &props); - - /* - * Using the same name independent of the drm device or connector - * prevents registration of multiple backlight devices in the - * driver. However, we need to use the default name for backward - * compatibility. Use unique names for subsequent backlight devices as a - * fallback when the default name already exists. - */ - if (IS_ERR(bd) && PTR_ERR(bd) == -EEXIST) { + bd = backlight_device_get_by_name(name); + if (bd) { + put_device(&bd->dev); + /* + * Using the same name independent of the drm device or connector + * prevents registration of multiple backlight devices in the + * driver. However, we need to use the default name for backward + * compatibility. Use unique names for subsequent backlight devices as a + * fallback when the default name already exists. + */ kfree(name); name = kasprintf(GFP_KERNEL, "card%d-%s-backlight", i915->drm.primary->index, connector->base.name); if (!name) return -ENOMEM; - - bd = backlight_device_register(name, connector->base.kdev, connector, - &intel_backlight_device_ops, &props); } + bd = backlight_device_register(name, connector->base.kdev, connector, + &intel_backlight_device_ops, &props); if (IS_ERR(bd)) { drm_err(&i915->drm, @@ -1773,9 +1772,13 @@ void intel_backlight_init_funcs(struct intel_panel *panel) panel->backlight.pwm_funcs = &i9xx_pwm_funcs; } - if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP && - intel_dp_aux_init_backlight_funcs(connector) == 0) - return; + if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP) { + if (intel_dp_aux_init_backlight_funcs(connector) == 0) + return; + + if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK)) + connector->panel.backlight.power = intel_pps_backlight_power; + } /* We're using a standard PWM backlight interface */ panel->backlight.funcs = &pwm_bl_funcs; diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 51dde5bfd956..7d6eb9ad7a02 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -479,6 +479,13 @@ init_bdb_block(struct drm_i915_private *i915, block_size = get_blocksize(block); + /* + * Version number and new block size are considered + * part of the header for MIPI sequenece block v3+. + */ + if (section_id == BDB_MIPI_SEQUENCE && *(const u8 *)block >= 3) + block_size += 5; + entry = kzalloc(struct_size(entry, data, max(min_size, block_size) + 3), GFP_KERNEL); if (!entry) { @@ -1596,6 +1603,8 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, struct intel_panel *panel, enum port port) { + enum port port_bc = DISPLAY_VER(i915) >= 11 ? PORT_B : PORT_C; + if (!panel->vbt.dsi.config->dual_link || i915->vbt.version < 197) { panel->vbt.dsi.bl_ports = BIT(port); if (panel->vbt.dsi.config->cabc_supported) @@ -1609,11 +1618,11 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, panel->vbt.dsi.bl_ports = BIT(PORT_A); break; case DL_DCS_PORT_C: - panel->vbt.dsi.bl_ports = BIT(PORT_C); + panel->vbt.dsi.bl_ports = BIT(port_bc); break; default: case DL_DCS_PORT_A_AND_C: - panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(PORT_C); + panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(port_bc); break; } @@ -1625,12 +1634,12 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, panel->vbt.dsi.cabc_ports = BIT(PORT_A); break; case DL_DCS_PORT_C: - panel->vbt.dsi.cabc_ports = BIT(PORT_C); + panel->vbt.dsi.cabc_ports = BIT(port_bc); break; default: case DL_DCS_PORT_A_AND_C: panel->vbt.dsi.cabc_ports = - BIT(PORT_A) | BIT(PORT_C); + BIT(PORT_A) | BIT(port_bc); break; } } diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 79269d2c476b..3699869ab2db 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -404,15 +404,17 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel int clpchgroup; int j; - if (i < num_groups - 1) - bi_next = &dev_priv->max_bw[i + 1]; - clpchgroup = (sa->deburst * qi.deinterleave / num_channels) << i; - if (i < num_groups - 1 && clpchgroup < clperchgroup) - bi_next->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; - else - bi_next->num_planes = 0; + if (i < num_groups - 1) { + bi_next = &dev_priv->max_bw[i + 1]; + + if (clpchgroup < clperchgroup) + bi_next->num_planes = (ipqdepth - clpchgroup) / + clpchgroup + 1; + else + bi_next->num_planes = 0; + } bi->num_qgv_points = qi.num_points; bi->num_psf_gv_points = qi.num_psf_points; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 32292c0be2bd..3ed7eeacc706 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -389,23 +389,13 @@ static int dg2_max_source_rate(struct intel_dp *intel_dp) return intel_dp_is_edp(intel_dp) ? 810000 : 1350000; } -static bool is_low_voltage_sku(struct drm_i915_private *i915, enum phy phy) -{ - u32 voltage; - - voltage = intel_de_read(i915, ICL_PORT_COMP_DW3(phy)) & VOLTAGE_INFO_MASK; - - return voltage == VOLTAGE_INFO_0_85V; -} - 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 phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - if (intel_phy_is_combo(dev_priv, phy) && - (is_low_voltage_sku(dev_priv, phy) || !intel_dp_is_edp(intel_dp))) + if (intel_phy_is_combo(dev_priv, phy) && !intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -413,23 +403,7 @@ static int icl_max_source_rate(struct intel_dp *intel_dp) static int ehl_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 phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - - if (intel_dp_is_edp(intel_dp) || is_low_voltage_sku(dev_priv, phy)) - return 540000; - - return 810000; -} - -static int dg1_max_source_rate(struct intel_dp *intel_dp) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(i915, dig_port->base.port); - - if (intel_phy_is_combo(i915, phy) && is_low_voltage_sku(i915, phy)) + if (intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -491,7 +465,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) max_rate = dg2_max_source_rate(intel_dp); else if (IS_ALDERLAKE_P(dev_priv) || IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv)) - max_rate = dg1_max_source_rate(intel_dp); + max_rate = 810000; else if (IS_JSL_EHL(dev_priv)) max_rate = ehl_max_source_rate(intel_dp); else @@ -1395,6 +1369,7 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, * DP_DSC_RC_BUF_SIZE for this. */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; /* * Slice Height of 8 works for all currently available panels. So start @@ -5293,8 +5268,6 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, intel_panel_init(intel_connector); - if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK)) - intel_connector->panel.backlight.power = intel_pps_backlight_power; intel_backlight_setup(intel_connector, pipe); intel_edp_add_properties(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 9feaf1a589f3..d213d8ad1ea5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -671,6 +671,28 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, intel_dp_compute_rate(intel_dp, crtc_state->port_clock, &link_bw, &rate_select); + /* + * WaEdpLinkRateDataReload + * + * Parade PS8461E MUX (used on varius TGL+ laptops) needs + * to snoop the link rates reported by the sink when we + * use LINK_RATE_SET in order to operate in jitter cleaning + * mode (as opposed to redriver mode). Unfortunately it + * loses track of the snooped link rates when powered down, + * so we need to make it re-snoop often. Without this high + * link rates are not stable. + */ + if (!link_bw) { + struct intel_connector *connector = intel_dp->attached_connector; + __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; + + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n", + connector->base.base.id, connector->base.name); + + drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES, + sink_rates, sizeof(sink_rates)); + } + if (link_bw) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n", diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c index c8488f5ebd04..e415cd7c0b84 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.c +++ b/drivers/gpu/drm/i915/display/intel_quirks.c @@ -191,6 +191,9 @@ static struct intel_quirk intel_quirks[] = { /* ASRock ITX*/ { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + /* ECS Liva Q2 */ + { 0x3185, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, }; void intel_init_quirks(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 43e1bbc1e303..ca530f0733e0 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -460,7 +460,6 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) u8 i = 0; vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay; - vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay; vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width, pipe_config->dsc.slice_count); diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index b9b1fed99874..35136d26e517 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1933,7 +1933,14 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv) else intel_dsi->ports = BIT(port); + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports; + intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports; + + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports; + intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports; /* Create a DSI host (and a device) for each port. */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dabdfe09f5e5..0bcde53c50c6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1269,6 +1269,10 @@ static void i915_gem_context_release_work(struct work_struct *work) trace_i915_context_free(ctx); GEM_BUG_ON(!i915_gem_context_is_closed(ctx)); + spin_lock(&ctx->i915->gem.contexts.lock); + list_del(&ctx->link); + spin_unlock(&ctx->i915->gem.contexts.lock); + if (ctx->syncobj) drm_syncobj_put(ctx->syncobj); @@ -1521,10 +1525,6 @@ static void context_close(struct i915_gem_context *ctx) ctx->file_priv = ERR_PTR(-EBADF); - spin_lock(&ctx->i915->gem.contexts.lock); - list_del(&ctx->link); - spin_unlock(&ctx->i915->gem.contexts.lock); - client = ctx->client; if (client) { spin_lock(&client->ctx_lock); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index ccec4055fde3..85482a04d158 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -268,7 +268,7 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) */ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj) { - assert_object_held(obj); + assert_object_held_shared(obj); if (!list_empty(&obj->vma.list)) { struct i915_vma *vma; @@ -331,15 +331,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, continue; } - if (!i915_gem_object_trylock(obj, NULL)) { - /* busy, toss it back to the pile */ - if (llist_add(&obj->freed, &i915->mm.free_list)) - queue_delayed_work(i915->wq, &i915->mm.free_work, msecs_to_jiffies(10)); - continue; - } - __i915_gem_object_pages_fini(obj); - i915_gem_object_unlock(obj); __i915_gem_free_object(obj); /* But keep the pointer alive for RCU-protected lookups */ @@ -359,7 +351,7 @@ void i915_gem_flush_free_objects(struct drm_i915_private *i915) static void __i915_gem_free_work(struct work_struct *work) { struct drm_i915_private *i915 = - container_of(work, struct drm_i915_private, mm.free_work.work); + container_of(work, struct drm_i915_private, mm.free_work); i915_gem_flush_free_objects(i915); } @@ -391,7 +383,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) */ if (llist_add(&obj->freed, &i915->mm.free_list)) - queue_delayed_work(i915->wq, &i915->mm.free_work, 0); + queue_work(i915->wq, &i915->mm.free_work); } void __i915_gem_object_flush_frontbuffer(struct drm_i915_gem_object *obj, @@ -731,6 +723,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj) bool lmem_placement = false; int i; + if (!HAS_FLAT_CCS(to_i915(obj->base.dev))) + return false; + for (i = 0; i < obj->mm.n_placements; i++) { /* Compression is not allowed for the objects with smem placement */ if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM) @@ -745,7 +740,7 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj) void i915_gem_init__objects(struct drm_i915_private *i915) { - INIT_DELAYED_WORK(&i915->mm.free_work, __i915_gem_free_work); + INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); } void i915_objects_module_exit(void) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 5cf36a130061..9f6b14ec189a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -335,7 +335,6 @@ struct drm_i915_gem_object { #define I915_BO_READONLY BIT(7) #define I915_TILING_QUIRK_BIT 8 /* unknown swizzling; do not release! */ #define I915_BO_PROTECTED BIT(9) -#define I915_BO_WAS_BOUND_BIT 10 /** * @mem_flags - Mutable placement-related flags * @@ -616,6 +615,8 @@ struct drm_i915_gem_object { * pages were last acquired. */ bool dirty:1; + + u32 tlb; } mm; struct { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 97c820eee115..8357dbdcab5c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -6,14 +6,15 @@ #include <drm/drm_cache.h> +#include "gt/intel_gt.h" +#include "gt/intel_gt_pm.h" + #include "i915_drv.h" #include "i915_gem_object.h" #include "i915_scatterlist.h" #include "i915_gem_lmem.h" #include "i915_gem_mman.h" -#include "gt/intel_gt.h" - void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, struct sg_table *pages, unsigned int sg_page_sizes) @@ -190,6 +191,18 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr) vunmap(ptr); } +static void flush_tlb_invalidate(struct drm_i915_gem_object *obj) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct intel_gt *gt = to_gt(i915); + + if (!obj->mm.tlb) + return; + + intel_gt_invalidate_tlb(gt, obj->mm.tlb); + obj->mm.tlb = 0; +} + struct sg_table * __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) { @@ -215,13 +228,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj) __i915_gem_object_reset_page_iter(obj); obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0; - if (test_and_clear_bit(I915_BO_WAS_BOUND_BIT, &obj->flags)) { - struct drm_i915_private *i915 = to_i915(obj->base.dev); - intel_wakeref_t wakeref; - - with_intel_runtime_pm_if_active(&i915->runtime_pm, wakeref) - intel_gt_invalidate_tlbs(to_gt(i915)); - } + flush_tlb_invalidate(obj); return pages; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index f131dc065f47..6f3ab7ade41a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -297,7 +297,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, i915_tt->is_shmem = true; } - if (HAS_FLAT_CCS(i915) && i915_gem_object_needs_ccs_pages(obj)) + if (i915_gem_object_needs_ccs_pages(obj)) ccs_pages = DIV_ROUND_UP(DIV_ROUND_UP(bo->base.size, NUM_BYTES_PER_CCS_BYTE), PAGE_SIZE); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 633a7e5dba3b..6b5d4ea22b67 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -166,6 +166,21 @@ struct intel_engine_execlists { struct timer_list preempt; /** + * @preempt_target: active request at the time of the preemption request + * + * We force a preemption to occur if the pending contexts have not + * been promoted to active upon receipt of the CS ack event within + * the timeout. This timeout maybe chosen based on the target, + * using a very short timeout if the context is no longer schedulable. + * That short timeout may not be applicable to other contexts, so + * if a context switch should happen within before the preemption + * timeout, we may shoot early at an innocent context. To prevent this, + * we record which context was active at the time of the preemption + * request and only reset that context upon the timeout. + */ + const struct i915_request *preempt_target; + + /** * @ccid: identifier for contexts submitted to this engine */ u32 ccid; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 4b909cb88cdf..c718e6dc40b5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -1241,6 +1241,9 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, if (!rq) return 0; + /* Only allow ourselves to force reset the currently active context */ + engine->execlists.preempt_target = rq; + /* Force a fast reset for terminated contexts (ignoring sysfs!) */ if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq))) return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS; @@ -2427,8 +2430,24 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) GEM_BUG_ON(inactive - post > ARRAY_SIZE(post)); if (unlikely(preempt_timeout(engine))) { + const struct i915_request *rq = *engine->execlists.active; + + /* + * If after the preempt-timeout expired, we are still on the + * same active request/context as before we initiated the + * preemption, reset the engine. + * + * However, if we have processed a CS event to switch contexts, + * but not yet processed the CS event for the pending + * preemption, reset the timer allowing the new context to + * gracefully exit. + */ cancel_timer(&engine->execlists.preempt); - engine->execlists.error_interrupt |= ERROR_PREEMPT; + if (rq == engine->execlists.preempt_target) + engine->execlists.error_interrupt |= ERROR_PREEMPT; + else + set_timer_ms(&engine->execlists.preempt, + active_preempt_timeout(engine, rq)); } if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 68c2b0d8f187..f435e06125aa 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -11,7 +11,9 @@ #include "pxp/intel_pxp.h" #include "i915_drv.h" +#include "i915_perf_oa_regs.h" #include "intel_context.h" +#include "intel_engine_pm.h" #include "intel_engine_regs.h" #include "intel_ggtt_gmch.h" #include "intel_gt.h" @@ -36,8 +38,6 @@ static void __intel_gt_init_early(struct intel_gt *gt) { spin_lock_init(>->irq_lock); - mutex_init(>->tlb_invalidate_lock); - INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -48,6 +48,8 @@ static void __intel_gt_init_early(struct intel_gt *gt) intel_gt_init_reset(gt); intel_gt_init_requests(gt); intel_gt_init_timelines(gt); + mutex_init(>->tlb.invalidate_lock); + seqcount_mutex_init(>->tlb.seqno, >->tlb.invalidate_lock); intel_gt_pm_init_early(gt); intel_uc_init_early(>->uc); @@ -768,6 +770,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915) intel_gt_fini_requests(gt); intel_gt_fini_reset(gt); intel_gt_fini_timelines(gt); + mutex_destroy(>->tlb.invalidate_lock); intel_engines_free(gt); } } @@ -906,7 +909,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, return rb; } -void intel_gt_invalidate_tlbs(struct intel_gt *gt) +static void mmio_invalidate_full(struct intel_gt *gt) { static const i915_reg_t gen8_regs[] = { [RENDER_CLASS] = GEN8_RTCR, @@ -924,13 +927,11 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) struct drm_i915_private *i915 = gt->i915; struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; + intel_engine_mask_t awake, tmp; enum intel_engine_id id; const i915_reg_t *regs; unsigned int num = 0; - if (I915_SELFTEST_ONLY(gt->awake == -ENODEV)) - return; - if (GRAPHICS_VER(i915) == 12) { regs = gen12_regs; num = ARRAY_SIZE(gen12_regs); @@ -945,28 +946,41 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) "Platform does not implement TLB invalidation!")) return; - GEM_TRACE("\n"); - - assert_rpm_wakelock_held(&i915->runtime_pm); - - mutex_lock(>->tlb_invalidate_lock); intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */ + awake = 0; for_each_engine(engine, gt, id) { struct reg_and_bit rb; + if (!intel_engine_pm_is_awake(engine)) + continue; + rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); if (!i915_mmio_reg_offset(rb.reg)) continue; intel_uncore_write_fw(uncore, rb.reg, rb.bit); + awake |= engine->mask; } + GT_TRACE(gt, "invalidated engines %08x\n", awake); + + /* Wa_2207587034:tgl,dg1,rkl,adl-s,adl-p */ + if (awake && + (IS_TIGERLAKE(i915) || + IS_DG1(i915) || + IS_ROCKETLAKE(i915) || + IS_ALDERLAKE_S(i915) || + IS_ALDERLAKE_P(i915))) + intel_uncore_write_fw(uncore, GEN12_OA_TLB_INV_CR, 1); + spin_unlock_irq(&uncore->lock); - for_each_engine(engine, gt, id) { + for_each_engine_masked(engine, gt, awake, tmp) { + struct reg_and_bit rb; + /* * HW architecture suggest typical invalidation time at 40us, * with pessimistic cases up to 100us and a recommendation to @@ -974,12 +988,8 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) */ const unsigned int timeout_us = 100; const unsigned int timeout_ms = 4; - struct reg_and_bit rb; rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num); - if (!i915_mmio_reg_offset(rb.reg)) - continue; - if (__intel_wait_for_register_fw(uncore, rb.reg, rb.bit, 0, timeout_us, timeout_ms, @@ -996,5 +1006,38 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt) * transitions. */ intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL); - mutex_unlock(>->tlb_invalidate_lock); +} + +static bool tlb_seqno_passed(const struct intel_gt *gt, u32 seqno) +{ + u32 cur = intel_gt_tlb_seqno(gt); + + /* Only skip if a *full* TLB invalidate barrier has passed */ + return (s32)(cur - ALIGN(seqno, 2)) > 0; +} + +void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno) +{ + intel_wakeref_t wakeref; + + if (I915_SELFTEST_ONLY(gt->awake == -ENODEV)) + return; + + if (intel_gt_is_wedged(gt)) + return; + + if (tlb_seqno_passed(gt, seqno)) + return; + + with_intel_gt_pm_if_awake(gt, wakeref) { + mutex_lock(>->tlb.invalidate_lock); + if (tlb_seqno_passed(gt, seqno)) + goto unlock; + + mmio_invalidate_full(gt); + + write_seqcount_invalidate(>->tlb.seqno); +unlock: + mutex_unlock(>->tlb.invalidate_lock); + } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 82d6f248d876..40b06adf509a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -101,6 +101,16 @@ void intel_gt_info_print(const struct intel_gt_info *info, void intel_gt_watchdog_work(struct work_struct *work); -void intel_gt_invalidate_tlbs(struct intel_gt *gt); +static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt) +{ + return seqprop_sequence(>->tlb.seqno); +} + +static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt) +{ + return intel_gt_tlb_seqno(gt) | 1; +} + +void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno); #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index bc898df7a48c..a334787a4939 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -55,6 +55,9 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt) for (tmp = 1, intel_gt_pm_get(gt); tmp; \ intel_gt_pm_put(gt), tmp = 0) +#define with_intel_gt_pm_if_awake(gt, wf) \ + for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0) + static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt) { return intel_wakeref_wait_for_idle(>->wakeref); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index 73a8b46e0234..d09a0e845d09 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -545,8 +545,7 @@ static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK); -static const struct attribute *freq_attrs[] = { - &dev_attr_punit_req_freq_mhz.attr, +static const struct attribute *throttle_reason_attrs[] = { &attr_throttle_reason_status.attr, &attr_throttle_reason_pl1.attr, &attr_throttle_reason_pl2.attr, @@ -763,12 +762,20 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) if (!is_object_gt(kobj)) return; - ret = sysfs_create_files(kobj, freq_attrs); + ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr); if (ret) drm_warn(>->i915->drm, - "failed to create gt%u throttle sysfs files (%pe)", + "failed to create gt%u punit_req_freq_mhz sysfs (%pe)", gt->info.id, ERR_PTR(ret)); + if (GRAPHICS_VER(gt->i915) >= 11) { + ret = sysfs_create_files(kobj, throttle_reason_attrs); + if (ret) + drm_warn(>->i915->drm, + "failed to create gt%u throttle sysfs files (%pe)", + gt->info.id, ERR_PTR(ret)); + } + if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(>->uc)) { ret = sysfs_create_files(kobj, media_perf_power_attrs); if (ret) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index df708802889d..3804a583382b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -11,6 +11,7 @@ #include <linux/llist.h> #include <linux/mutex.h> #include <linux/notifier.h> +#include <linux/seqlock.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/workqueue.h> @@ -83,7 +84,22 @@ struct intel_gt { struct intel_uc uc; struct intel_gsc gsc; - struct mutex tlb_invalidate_lock; + struct { + /* Serialize global tlb invalidations */ + struct mutex invalidate_lock; + + /* + * Batch TLB invalidations + * + * After unbinding the PTE, we need to ensure the TLB + * are invalidated prior to releasing the physical pages. + * But we only need one such invalidation for all unbinds, + * so we track how many TLB invalidations have been + * performed since unbind the PTE and only emit an extra + * invalidate if no full barrier has been passed. + */ + seqcount_mutex_t seqno; + } tlb; struct i915_wa_list wa_list; diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c index 14fe65812e42..1d19c073ba2e 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc.c +++ b/drivers/gpu/drm/i915/gt/intel_llc.c @@ -12,6 +12,7 @@ #include "intel_llc.h" #include "intel_mchbar_regs.h" #include "intel_pcode.h" +#include "intel_rps.h" struct ia_constants { unsigned int min_gpu_freq; @@ -55,9 +56,6 @@ static bool get_ia_constants(struct intel_llc *llc, if (!HAS_LLC(i915) || IS_DGFX(i915)) return false; - if (rps->max_freq <= rps->min_freq) - return false; - consts->max_ia_freq = cpu_max_MHz(); consts->min_ring_freq = @@ -65,13 +63,8 @@ static bool get_ia_constants(struct intel_llc *llc, /* convert DDR frequency from units of 266.6MHz to bandwidth */ consts->min_ring_freq = mult_frac(consts->min_ring_freq, 8, 3); - consts->min_gpu_freq = rps->min_freq; - consts->max_gpu_freq = rps->max_freq; - if (GRAPHICS_VER(i915) >= 9) { - /* Convert GT frequency to 50 HZ units */ - consts->min_gpu_freq /= GEN9_FREQ_SCALER; - consts->max_gpu_freq /= GEN9_FREQ_SCALER; - } + consts->min_gpu_freq = intel_rps_get_min_raw_freq(rps); + consts->max_gpu_freq = intel_rps_get_max_raw_freq(rps); return true; } @@ -131,6 +124,12 @@ static void gen6_update_ring_freq(struct intel_llc *llc) return; /* + * Although this is unlikely on any platform during initialization, + * let's ensure we don't get accidentally into infinite loop + */ + if (consts.max_gpu_freq <= consts.min_gpu_freq) + return; + /* * For each potential GPU frequency, load a ring frequency we'd like * to use for memory access. We do this by specifying the IA frequency * the PCU should use as a reference to determine the ring frequency. diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c index 2c35324b5f68..933648cc90ff 100644 --- a/drivers/gpu/drm/i915/gt/intel_migrate.c +++ b/drivers/gpu/drm/i915/gt/intel_migrate.c @@ -638,9 +638,9 @@ static int emit_copy(struct i915_request *rq, return 0; } -static int scatter_list_length(struct scatterlist *sg) +static u64 scatter_list_length(struct scatterlist *sg) { - int len = 0; + u64 len = 0; while (sg && sg_dma_len(sg)) { len += sg_dma_len(sg); @@ -650,28 +650,26 @@ static int scatter_list_length(struct scatterlist *sg) return len; } -static void +static int calculate_chunk_sz(struct drm_i915_private *i915, bool src_is_lmem, - int *src_sz, u32 bytes_to_cpy, u32 ccs_bytes_to_cpy) + u64 bytes_to_cpy, u64 ccs_bytes_to_cpy) { - if (ccs_bytes_to_cpy) { - if (!src_is_lmem) - /* - * When CHUNK_SZ is passed all the pages upto CHUNK_SZ - * will be taken for the blt. in Flat-ccs supported - * platform Smem obj will have more pages than required - * for main meory hence limit it to the required size - * for main memory - */ - *src_sz = min_t(int, bytes_to_cpy, CHUNK_SZ); - } else { /* ccs handling is not required */ - *src_sz = CHUNK_SZ; - } + if (ccs_bytes_to_cpy && !src_is_lmem) + /* + * When CHUNK_SZ is passed all the pages upto CHUNK_SZ + * will be taken for the blt. in Flat-ccs supported + * platform Smem obj will have more pages than required + * for main meory hence limit it to the required size + * for main memory + */ + return min_t(u64, bytes_to_cpy, CHUNK_SZ); + else + return CHUNK_SZ; } -static void get_ccs_sg_sgt(struct sgt_dma *it, u32 bytes_to_cpy) +static void get_ccs_sg_sgt(struct sgt_dma *it, u64 bytes_to_cpy) { - u32 len; + u64 len; do { GEM_BUG_ON(!it->sg || !sg_dma_len(it->sg)); @@ -702,13 +700,13 @@ intel_context_migrate_copy(struct intel_context *ce, { struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst), it_ccs; struct drm_i915_private *i915 = ce->engine->i915; - u32 ccs_bytes_to_cpy = 0, bytes_to_cpy; + u64 ccs_bytes_to_cpy = 0, bytes_to_cpy; enum i915_cache_level ccs_cache_level; u32 src_offset, dst_offset; u8 src_access, dst_access; struct i915_request *rq; - int src_sz, dst_sz; - bool ccs_is_src; + u64 src_sz, dst_sz; + bool ccs_is_src, overwrite_ccs; int err; GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm); @@ -749,6 +747,8 @@ intel_context_migrate_copy(struct intel_context *ce, get_ccs_sg_sgt(&it_ccs, bytes_to_cpy); } + overwrite_ccs = HAS_FLAT_CCS(i915) && !ccs_bytes_to_cpy && dst_is_lmem; + src_offset = 0; dst_offset = CHUNK_SZ; if (HAS_64K_PAGES(ce->engine->i915)) { @@ -788,8 +788,8 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; - calculate_chunk_sz(i915, src_is_lmem, &src_sz, - bytes_to_cpy, ccs_bytes_to_cpy); + src_sz = calculate_chunk_sz(i915, src_is_lmem, + bytes_to_cpy, ccs_bytes_to_cpy); len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem, src_offset, src_sz); @@ -852,6 +852,25 @@ intel_context_migrate_copy(struct intel_context *ce, if (err) goto out_rq; ccs_bytes_to_cpy -= ccs_sz; + } else if (overwrite_ccs) { + err = rq->engine->emit_flush(rq, EMIT_INVALIDATE); + if (err) + goto out_rq; + + /* + * While we can't always restore/manage the CCS state, + * we still need to ensure we don't leak the CCS state + * from the previous user, so make sure we overwrite it + * with something. + */ + err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS, + dst_offset, DIRECT_ACCESS, len); + if (err) + goto out_rq; + + err = rq->engine->emit_flush(rq, EMIT_INVALIDATE); + if (err) + goto out_rq; } /* Arbitration is re-enabled between requests. */ diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index d8b94d638559..6ee8d1127016 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -206,8 +206,12 @@ void ppgtt_bind_vma(struct i915_address_space *vm, void ppgtt_unbind_vma(struct i915_address_space *vm, struct i915_vma_resource *vma_res) { - if (vma_res->allocated) - vm->clear_range(vm, vma_res->start, vma_res->vma_size); + if (!vma_res->allocated) + return; + + vm->clear_range(vm, vma_res->start, vma_res->vma_size); + if (vma_res->tlb) + vma_invalidate_tlb(vm, vma_res->tlb); } static unsigned long pd_count(u64 size, int shift) diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index 6e90032e12e9..aa6aed837194 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -15,6 +15,7 @@ #include "gt/intel_gt_mcr.h" #include "gt/intel_gt_regs.h" +#ifdef CONFIG_64BIT static void _release_bars(struct pci_dev *pdev) { int resno; @@ -111,6 +112,9 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t pci_assign_unassigned_bus_resources(pdev->bus); pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd); } +#else +static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t lmem_size) {} +#endif static int region_lmem_release(struct intel_memory_region *mem) diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index fb3f57ee450b..7bb967034679 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -2126,6 +2126,31 @@ u32 intel_rps_get_max_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->max_freq_softlimit); } +/** + * intel_rps_get_max_raw_freq - returns the max frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the max frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->rp0_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->max_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + u32 intel_rps_get_rp0_frequency(struct intel_rps *rps) { struct intel_guc_slpc *slpc = rps_to_slpc(rps); @@ -2214,6 +2239,31 @@ u32 intel_rps_get_min_frequency(struct intel_rps *rps) return intel_gpu_freq(rps, rps->min_freq_softlimit); } +/** + * intel_rps_get_min_raw_freq - returns the min frequency in some raw format. + * @rps: the intel_rps structure + * + * Returns the min frequency in a raw format. In newer platforms raw is in + * units of 50 MHz. + */ +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps) +{ + struct intel_guc_slpc *slpc = rps_to_slpc(rps); + u32 freq; + + if (rps_uses_slpc(rps)) { + return DIV_ROUND_CLOSEST(slpc->min_freq, + GT_FREQUENCY_MULTIPLIER); + } else { + freq = rps->min_freq; + if (GRAPHICS_VER(rps_to_i915(rps)) >= 9) { + /* Convert GT frequency to 50 MHz units */ + freq /= GEN9_FREQ_SCALER; + } + return freq; + } +} + static int set_min_freq(struct intel_rps *rps, u32 val) { int ret = 0; diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 1e8d56491308..4509dfdc52e0 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -37,8 +37,10 @@ u32 intel_rps_get_cagf(struct intel_rps *rps, u32 rpstat1); u32 intel_rps_read_actual_frequency(struct intel_rps *rps); u32 intel_rps_get_requested_frequency(struct intel_rps *rps); u32 intel_rps_get_min_frequency(struct intel_rps *rps); +u32 intel_rps_get_min_raw_freq(struct intel_rps *rps); int intel_rps_set_min_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_max_frequency(struct intel_rps *rps); +u32 intel_rps_get_max_raw_freq(struct intel_rps *rps); int intel_rps_set_max_frequency(struct intel_rps *rps, u32 val); u32 intel_rps_get_rp0_frequency(struct intel_rps *rps); u32 intel_rps_get_rp1_frequency(struct intel_rps *rps); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 76916aed897a..3e91f44829e9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1438,7 +1438,12 @@ void intel_guc_busyness_park(struct intel_gt *gt) if (!guc_submission_initialized(guc)) return; - cancel_delayed_work(&guc->timestamp.work); + /* + * There is a race with suspend flow where the worker runs after suspend + * and causes an unclaimed register access warning. Cancel the worker + * synchronously here. + */ + cancel_delayed_work_sync(&guc->timestamp.work); /* * Before parking, we should sample engine busyness stats if we need to. @@ -4027,6 +4032,13 @@ static inline void guc_init_lrc_mapping(struct intel_guc *guc) xa_destroy(&guc->context_lookup); /* + * A reset might have occurred while we had a pending stalled request, + * so make sure we clean that up. + */ + guc->stalled_request = NULL; + guc->submission_stall_reason = STALL_NONE; + + /* * Some contexts might have been pinned before we enabled GuC * submission, so we need to add them to the GuC bookeeping. * Also, after a reset the of the GuC we want to make sure that the diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 557f3314291a..3b81a6d35a7b 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -298,7 +298,7 @@ no_enough_resource: } /** - * inte_gvt_free_vgpu_resource - free HW resource owned by a vGPU + * intel_vgpu_free_resource() - free HW resource owned by a vGPU * @vgpu: a vGPU * * This function is used to free the HW resource owned by a vGPU. @@ -328,7 +328,7 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu) } /** - * intel_alloc_vgpu_resource - allocate HW resource for a vGPU + * intel_vgpu_alloc_resource() - allocate HW resource for a vGPU * @vgpu: vGPU * @param: vGPU creation params * diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index b4f69364f9a1..ce0eb03709c3 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2341,7 +2341,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, gvt_vgpu_err("fail to populate guest ggtt entry\n"); /* guest driver may read/write the entry when partial * update the entry in this situation p2m will fail - * settting the shadow entry to point to a scratch page + * setting the shadow entry to point to a scratch page */ ops->set_pfn(&m, gvt->gtt.scratch_mfn); } else diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index beea5895e499..61423da36710 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -905,7 +905,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu, else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX) index = FDI_RX_IMR_TO_PIPE(offset); else { - gvt_vgpu_err("Unsupport registers %x\n", offset); + gvt_vgpu_err("Unsupported registers %x\n", offset); return -EINVAL; } @@ -3052,7 +3052,7 @@ int intel_vgpu_default_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, } /** - * intel_t_default_mmio_write - default MMIO write handler + * intel_vgpu_default_mmio_write() - default MMIO write handler * @vgpu: a vGPU * @offset: access offset * @p_data: write data buffer diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index c85bafe7539e..1c6e941c9666 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -546,7 +546,7 @@ static void switch_mmio(struct intel_vgpu *pre, } /** - * intel_gvt_switch_render_mmio - switch mmio context of specific engine + * intel_gvt_switch_mmio - switch mmio context of specific engine * @pre: the last vGPU that own the engine * @next: the vGPU to switch to * @engine: the engine diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index d25647be25d1..086bbe8945d6 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -247,7 +247,7 @@ struct i915_gem_mm { * List of objects which are pending destruction. */ struct llist_head free_list; - struct delayed_work free_work; + struct work_struct free_work; /** * Count of objects pending destructions. Used to skip needlessly * waiting on an RCU barrier if no objects are waiting to be freed. @@ -1378,7 +1378,7 @@ static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915) * armed the work again. */ while (atomic_read(&i915->mm.free_count)) { - flush_delayed_work(&i915->mm.free_work); + flush_work(&i915->mm.free_work); flush_delayed_work(&i915->bdev.wq); rcu_barrier(); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 702e5b89be22..b605d0ceaefa 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1191,7 +1191,8 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv) intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); - i915_gem_drain_freed_objects(dev_priv); + /* Flush any outstanding work, including i915_gem_context.release_work. */ + i915_gem_drain_workqueue(dev_priv); drm_WARN_ON(&dev_priv->drm, !list_empty(&dev_priv->gem.contexts.list)); } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3168d7007e10..135d04c2d41c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1857,14 +1857,14 @@ #define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8) #define GT0_PERF_LIMIT_REASONS_MASK 0xde3 -#define PROCHOT_MASK REG_BIT(1) -#define THERMAL_LIMIT_MASK REG_BIT(2) -#define RATL_MASK REG_BIT(6) -#define VR_THERMALERT_MASK REG_BIT(7) -#define VR_TDC_MASK REG_BIT(8) -#define POWER_LIMIT_4_MASK REG_BIT(9) -#define POWER_LIMIT_1_MASK REG_BIT(11) -#define POWER_LIMIT_2_MASK REG_BIT(12) +#define PROCHOT_MASK REG_BIT(0) +#define THERMAL_LIMIT_MASK REG_BIT(1) +#define RATL_MASK REG_BIT(5) +#define VR_THERMALERT_MASK REG_BIT(6) +#define VR_TDC_MASK REG_BIT(7) +#define POWER_LIMIT_4_MASK REG_BIT(8) +#define POWER_LIMIT_1_MASK REG_BIT(10) +#define POWER_LIMIT_2_MASK REG_BIT(11) #define CHV_CLK_CTL1 _MMIO(0x101100) #define VLV_CLK_CTL2 _MMIO(0x101104) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index ef3b04c7e153..373582cfd8f3 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -538,8 +538,6 @@ int i915_vma_bind(struct i915_vma *vma, bind_flags); } - set_bit(I915_BO_WAS_BOUND_BIT, &vma->obj->flags); - atomic_or(bind_flags, &vma->flags); return 0; } @@ -1310,6 +1308,19 @@ err_unpin: return err; } +void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb) +{ + /* + * Before we release the pages that were bound by this vma, we + * must invalidate all the TLBs that may still have a reference + * back to our physical address. It only needs to be done once, + * so after updating the PTE to point away from the pages, record + * the most recent TLB invalidation seqno, and if we have not yet + * flushed the TLBs upon release, perform a full invalidation. + */ + WRITE_ONCE(*tlb, intel_gt_next_invalidate_tlb_full(vm->gt)); +} + static void __vma_put_pages(struct i915_vma *vma, unsigned int count) { /* We allocate under vma_get_pages, so beware the shrinker */ @@ -1871,12 +1882,13 @@ int _i915_vma_move_to_active(struct i915_vma *vma, enum dma_resv_usage usage; int idx; - obj->read_domains = 0; if (flags & EXEC_OBJECT_WRITE) { usage = DMA_RESV_USAGE_WRITE; obj->write_domain = I915_GEM_DOMAIN_RENDER; + obj->read_domains = 0; } else { usage = DMA_RESV_USAGE_READ; + obj->write_domain = 0; } dma_fence_array_for_each(curr, idx, fence) @@ -1941,7 +1953,12 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async) vma->vm->skip_pte_rewrite; trace_i915_vma_unbind(vma); - unbind_fence = i915_vma_resource_unbind(vma_res); + if (async) + unbind_fence = i915_vma_resource_unbind(vma_res, + &vma->obj->mm.tlb); + else + unbind_fence = i915_vma_resource_unbind(vma_res, NULL); + vma->resource = NULL; atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR | I915_VMA_GGTT_WRITE), @@ -1949,10 +1966,13 @@ struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async) i915_vma_detach(vma); - if (!async && unbind_fence) { - dma_fence_wait(unbind_fence, false); - dma_fence_put(unbind_fence); - unbind_fence = NULL; + if (!async) { + if (unbind_fence) { + dma_fence_wait(unbind_fence, false); + dma_fence_put(unbind_fence); + unbind_fence = NULL; + } + vma_invalidate_tlb(vma->vm, &vma->obj->mm.tlb); } /* diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h index 88ca0bd9c900..33a58f605d75 100644 --- a/drivers/gpu/drm/i915/i915_vma.h +++ b/drivers/gpu/drm/i915/i915_vma.h @@ -213,6 +213,7 @@ bool i915_vma_misplaced(const struct i915_vma *vma, u64 size, u64 alignment, u64 flags); void __i915_vma_set_map_and_fenceable(struct i915_vma *vma); void i915_vma_revoke_mmap(struct i915_vma *vma); +void vma_invalidate_tlb(struct i915_address_space *vm, u32 *tlb); struct dma_fence *__i915_vma_evict(struct i915_vma *vma, bool async); int __i915_vma_unbind(struct i915_vma *vma); int __must_check i915_vma_unbind(struct i915_vma *vma); diff --git a/drivers/gpu/drm/i915/i915_vma_resource.c b/drivers/gpu/drm/i915/i915_vma_resource.c index 27c55027387a..5a67995ea5fe 100644 --- a/drivers/gpu/drm/i915/i915_vma_resource.c +++ b/drivers/gpu/drm/i915/i915_vma_resource.c @@ -223,10 +223,13 @@ i915_vma_resource_fence_notify(struct i915_sw_fence *fence, * Return: A refcounted pointer to a dma-fence that signals when unbinding is * complete. */ -struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res) +struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res, + u32 *tlb) { struct i915_address_space *vm = vma_res->vm; + vma_res->tlb = tlb; + /* Reference for the sw fence */ i915_vma_resource_get(vma_res); diff --git a/drivers/gpu/drm/i915/i915_vma_resource.h b/drivers/gpu/drm/i915/i915_vma_resource.h index 5d8427caa2ba..06923d1816e7 100644 --- a/drivers/gpu/drm/i915/i915_vma_resource.h +++ b/drivers/gpu/drm/i915/i915_vma_resource.h @@ -67,6 +67,7 @@ struct i915_page_sizes { * taken when the unbind is scheduled. * @skip_pte_rewrite: During ggtt suspend and vm takedown pte rewriting * needs to be skipped for unbind. + * @tlb: pointer for obj->mm.tlb, if async unbind. Otherwise, NULL * * The lifetime of a struct i915_vma_resource is from a binding request to * the actual possible asynchronous unbind has completed. @@ -119,6 +120,8 @@ struct i915_vma_resource { bool immediate_unbind:1; bool needs_wakeref:1; bool skip_pte_rewrite:1; + + u32 *tlb; }; bool i915_vma_resource_hold(struct i915_vma_resource *vma_res, @@ -131,7 +134,8 @@ struct i915_vma_resource *i915_vma_resource_alloc(void); void i915_vma_resource_free(struct i915_vma_resource *vma_res); -struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res); +struct dma_fence *i915_vma_resource_unbind(struct i915_vma_resource *vma_res, + u32 *tlb); void __i915_vma_resource_init(struct i915_vma_resource *vma_res); diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c index 157e166672d7..5595639d0033 100644 --- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c +++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c @@ -1076,7 +1076,8 @@ static int iterate_skl_plus_mmio(struct intel_gvt_mmio_table_iter *iter) MMIO_D(GEN8_HDC_CHICKEN1); MMIO_D(GEN9_WM_CHICKEN3); - if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) + if (IS_KABYLAKE(dev_priv) || + IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv)) MMIO_D(GAMT_CHKN_BIT_REG); if (!IS_BROXTON(dev_priv)) MMIO_D(GEN9_CTX_PREEMPT_REG); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f06babdb3a8c..9fe4b583cc28 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -6561,7 +6561,10 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) enum plane_id plane_id; u8 slices; - skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); + memset(&crtc_state->wm.skl.optimal, 0, + sizeof(crtc_state->wm.skl.optimal)); + if (crtc_state->hw.active) + skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal; memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe])); @@ -6572,6 +6575,9 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) struct skl_ddb_entry *ddb_y = &crtc_state->wm.skl.plane_ddb_y[plane_id]; + if (!crtc_state->hw.active) + continue; + skl_ddb_get_hw_plane_state(dev_priv, crtc->pipe, plane_id, ddb, ddb_y); |