diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
23 files changed, 252 insertions, 140 deletions
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 21561acfa3ac..46c40db992dd 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4466,13 +4466,19 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv) static void icl_mbus_init(struct drm_i915_private *dev_priv) { - u32 val; + u32 mask, val; - val = MBUS_ABOX_BT_CREDIT_POOL1(16) | - MBUS_ABOX_BT_CREDIT_POOL2(16) | - MBUS_ABOX_B_CREDIT(1) | - MBUS_ABOX_BW_CREDIT(1); + mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK | + MBUS_ABOX_BT_CREDIT_POOL2_MASK | + MBUS_ABOX_B_CREDIT_MASK | + MBUS_ABOX_BW_CREDIT_MASK; + val = I915_READ(MBUS_ABOX_CTL); + val &= ~mask; + val |= MBUS_ABOX_BT_CREDIT_POOL1(16) | + MBUS_ABOX_BT_CREDIT_POOL2(16) | + MBUS_ABOX_B_CREDIT(1) | + MBUS_ABOX_BW_CREDIT(1); I915_WRITE(MBUS_ABOX_CTL, val); } @@ -4968,8 +4974,21 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE); I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE); } else { + u32 val; + I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask); I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask); + + /* Wa_22010178259:tgl */ + val = I915_READ(BW_BUDDY1_CTL); + val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK; + val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8); + I915_WRITE(BW_BUDDY1_CTL, val); + + val = I915_READ(BW_BUDDY2_CTL); + val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK; + val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8); + I915_WRITE(BW_BUDDY2_CTL, val); } } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index c7424e2a04a3..208457005a11 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1360,7 +1360,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp, * lowest possible wakeup latency and so prevent the cpu from going into * deep sleep states. */ - pm_qos_update_request(&i915->pm_qos, 0); + cpu_latency_qos_update_request(&i915->pm_qos, 0); intel_dp_check_edp(intel_dp); @@ -1488,7 +1488,7 @@ done: ret = recv_bytes; out: - pm_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&i915->pm_qos, PM_QOS_DEFAULT_VALUE); if (vdd) edp_panel_vdd_off(intel_dp, false); diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 89c9cf5f38d2..83025052c965 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -852,10 +852,12 @@ void intel_psr_enable(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - if (!crtc_state->has_psr) + if (!CAN_PSR(dev_priv) || dev_priv->psr.dp != intel_dp) return; - if (WARN_ON(!CAN_PSR(dev_priv))) + dev_priv->psr.force_mode_changed = false; + + if (!crtc_state->has_psr) return; WARN_ON(dev_priv->drrs.dp); @@ -1009,6 +1011,8 @@ void intel_psr_update(struct intel_dp *intel_dp, if (!CAN_PSR(dev_priv) || READ_ONCE(psr->dp) != intel_dp) return; + dev_priv->psr.force_mode_changed = false; + mutex_lock(&dev_priv->psr.lock); enable = crtc_state->has_psr && psr_global_enabled(psr->debug); @@ -1534,7 +1538,7 @@ void intel_psr_atomic_check(struct drm_connector *connector, struct drm_crtc_state *crtc_state; if (!CAN_PSR(dev_priv) || !new_state->crtc || - dev_priv->psr.initially_probed) + !dev_priv->psr.force_mode_changed) return; intel_connector = to_intel_connector(connector); @@ -1545,5 +1549,18 @@ void intel_psr_atomic_check(struct drm_connector *connector, crtc_state = drm_atomic_get_new_crtc_state(new_state->state, new_state->crtc); crtc_state->mode_changed = true; - dev_priv->psr.initially_probed = true; +} + +void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv; + + if (!intel_dp) + return; + + dev_priv = dp_to_i915(intel_dp); + if (!CAN_PSR(dev_priv) || intel_dp != dev_priv->psr.dp) + return; + + dev_priv->psr.force_mode_changed = true; } diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h index c58a1d438808..274fc6bb6221 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.h +++ b/drivers/gpu/drm/i915/display/intel_psr.h @@ -40,5 +40,6 @@ bool intel_psr_enabled(struct intel_dp *intel_dp); void intel_psr_atomic_check(struct drm_connector *connector, struct drm_connector_state *old_state, struct drm_connector_state *new_state); +void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp); #endif /* __INTEL_PSR_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 60c984e10c4a..7643a30ba4cd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -423,7 +423,8 @@ eb_validate_vma(struct i915_execbuffer *eb, if (unlikely(entry->flags & eb->invalid_flags)) return -EINVAL; - if (unlikely(entry->alignment && !is_power_of_2(entry->alignment))) + if (unlikely(entry->alignment && + !is_power_of_2_u64(entry->alignment))) return -EINVAL; /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 35985218bd85..5da9f9e534b9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -225,6 +225,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); + cond_resched(); } intel_runtime_pm_put(&i915->runtime_pm, wakeref); } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index ef7c74cff28a..43912e9b683d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, obj = i915_gem_object_create_internal(i915, size); if (IS_ERR(obj)) - return PTR_ERR(obj); + return false; mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL); i915_gem_object_put(obj); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index 8a5054f21bf8..24c99d0838af 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout) fence = i915_active_fence_get(&tl->last_request); if (fence) { + mutex_unlock(&tl->mutex); + timeout = dma_fence_wait_timeout(fence, interruptible, timeout); dma_fence_put(fence); + + /* Retirement is best effort */ + if (!mutex_trylock(&tl->mutex)) { + active_count++; + goto out_active; + } } } if (!retire_requests(tl) || flush_submission(gt)) active_count++; + mutex_unlock(&tl->mutex); - spin_lock(&timelines->lock); +out_active: spin_lock(&timelines->lock); - /* Resume iteration after dropping lock */ + /* Resume list iteration after reacquiring spinlock */ list_safe_reset_next(tl, tn, link); if (atomic_dec_and_test(&tl->active_count)) list_del(&tl->link); - mutex_unlock(&tl->mutex); /* Defer the final release to after the spinlock */ if (refcount_dec_and_test(&tl->kref.refcount)) { diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index fe8a59aaa629..31455eceeb0c 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1600,17 +1600,6 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve, spin_unlock(&old->breadcrumbs.irq_lock); } -static struct i915_request * -last_active(const struct intel_engine_execlists *execlists) -{ - struct i915_request * const *last = READ_ONCE(execlists->active); - - while (*last && i915_request_completed(*last)) - last++; - - return *last; -} - #define for_each_waiter(p__, rq__) \ list_for_each_entry_lockless(p__, \ &(rq__)->sched.waiters_list, \ @@ -1679,11 +1668,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) if (!intel_engine_has_timeslices(engine)) return false; - if (list_is_last(&rq->sched.link, &engine->active.requests)) - return false; - - hint = max(rq_prio(list_next_entry(rq, sched.link)), - engine->execlists.queue_priority_hint); + hint = engine->execlists.queue_priority_hint; + if (!list_is_last(&rq->sched.link, &engine->active.requests)) + hint = max(hint, rq_prio(list_next_entry(rq, sched.link))); return hint >= effective_prio(rq); } @@ -1725,16 +1712,26 @@ static void set_timeslice(struct intel_engine_cs *engine) set_timer_ms(&engine->execlists.timer, active_timeslice(engine)); } +static void start_timeslice(struct intel_engine_cs *engine) +{ + struct intel_engine_execlists *execlists = &engine->execlists; + + execlists->switch_priority_hint = execlists->queue_priority_hint; + + if (timer_pending(&execlists->timer)) + return; + + set_timer_ms(&execlists->timer, timeslice(engine)); +} + static void record_preemption(struct intel_engine_execlists *execlists) { (void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++); } -static unsigned long active_preempt_timeout(struct intel_engine_cs *engine) +static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, + const struct i915_request *rq) { - struct i915_request *rq; - - rq = last_active(&engine->execlists); if (!rq) return 0; @@ -1745,13 +1742,14 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine) return READ_ONCE(engine->props.preempt_timeout_ms); } -static void set_preempt_timeout(struct intel_engine_cs *engine) +static void set_preempt_timeout(struct intel_engine_cs *engine, + const struct i915_request *rq) { if (!intel_engine_has_preempt_reset(engine)) return; set_timer_ms(&engine->execlists.preempt, - active_preempt_timeout(engine)); + active_preempt_timeout(engine, rq)); } static inline void clear_ports(struct i915_request **ports, int count) @@ -1764,6 +1762,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_request **port = execlists->pending; struct i915_request ** const last_port = port + execlists->port_mask; + struct i915_request * const *active; struct i915_request *last; struct rb_node *rb; bool submit = false; @@ -1818,7 +1817,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * i.e. we will retrigger preemption following the ack in case * of trouble. */ - last = last_active(execlists); + active = READ_ONCE(execlists->active); + while ((last = *active) && i915_request_completed(last)) + active++; + if (last) { if (need_preempt(engine, last, rb)) { ENGINE_TRACE(engine, @@ -1888,11 +1890,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * Even if ELSP[1] is occupied and not worthy * of timeslices, our queue might be. */ - if (!execlists->timer.expires && - need_timeslice(engine, last)) - set_timer_ms(&execlists->timer, - timeslice(engine)); - + start_timeslice(engine); return; } } @@ -1927,7 +1925,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.active.lock); - return; /* leave this for another */ + start_timeslice(engine); + return; /* leave this for another sibling */ } ENGINE_TRACE(engine, @@ -2103,7 +2102,7 @@ done: * Skip if we ended up with exactly the same set of requests, * e.g. trying to timeslice a pair of ordered contexts */ - if (!memcmp(execlists->active, execlists->pending, + if (!memcmp(active, execlists->pending, (port - execlists->pending + 1) * sizeof(*port))) { do execlists_schedule_out(fetch_and_zero(port)); @@ -2114,7 +2113,7 @@ done: clear_ports(port + 1, last_port - port); execlists_submit_ports(engine); - set_preempt_timeout(engine); + set_preempt_timeout(engine, *active); } else { skip_submit: ring_set_paused(engine, 0); @@ -4001,26 +4000,6 @@ static int gen12_emit_flush_render(struct i915_request *request, *cs++ = preparser_disable(false); intel_ring_advance(request, cs); - - /* - * Wa_1604544889:tgl - */ - if (IS_TGL_REVID(request->i915, TGL_REVID_A0, TGL_REVID_A0)) { - flags = 0; - flags |= PIPE_CONTROL_CS_STALL; - flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH; - - flags |= PIPE_CONTROL_STORE_DATA_INDEX; - flags |= PIPE_CONTROL_QW_WRITE; - - cs = intel_ring_begin(request, 6); - if (IS_ERR(cs)) - return PTR_ERR(cs); - - cs = gen8_emit_pipe_control(cs, flags, - LRC_PPHWSP_SCRATCH_ADDR); - intel_ring_advance(request, cs); - } } return 0; diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 87716529cd2f..d8d9f1179c2b 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl) static void cacheline_free(struct intel_timeline_cacheline *cl) { + if (!i915_active_acquire_if_busy(&cl->active)) { + __idle_cacheline_free(cl); + return; + } + GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE)); cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE); - if (i915_active_is_idle(&cl->active)) - __idle_cacheline_free(cl); + i915_active_release(&cl->active); } int intel_timeline_init(struct intel_timeline *timeline, diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 4e292d4bf7b9..6c2f8462e0f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -575,24 +575,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - u32 val; - /* Wa_1409142259:tgl */ WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3, GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); - /* Wa_1604555607:tgl */ - val = intel_uncore_read(engine->uncore, FF_MODE2); - val &= ~FF_MODE2_TDS_TIMER_MASK; - val |= FF_MODE2_TDS_TIMER_128; /* - * FIXME: FF_MODE2 register is not readable till TGL B0. We can - * enable verification of WA from the later steppings, which enables - * the read of FF_MODE2. + * Wa_1604555607:gen12 and Wa_1608008084:gen12 + * FF_MODE2 register will return the wrong value when read. The default + * value for this register is zero for all fields and there are no bit + * masks. So instead of doing a RMW we should just write the TDS timer + * value for Wa_1604555607. */ - wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val, - IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 : - FF_MODE2_TDS_TIMER_MASK); + wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, + FF_MODE2_TDS_TIMER_128, 0); } static void @@ -1534,15 +1529,34 @@ err_obj: return ERR_PTR(err); } +static const struct { + u32 start; + u32 end; +} mcr_ranges_gen8[] = { + { .start = 0x5500, .end = 0x55ff }, + { .start = 0x7000, .end = 0x7fff }, + { .start = 0x9400, .end = 0x97ff }, + { .start = 0xb000, .end = 0xb3ff }, + { .start = 0xe000, .end = 0xe7ff }, + {}, +}; + static bool mcr_range(struct drm_i915_private *i915, u32 offset) { + int i; + + if (INTEL_GEN(i915) < 8) + return false; + /* - * Registers in this range are affected by the MCR selector + * Registers in these ranges are affected by the MCR selector * which only controls CPU initiated MMIO. Routing does not * work for CS access so we cannot verify them on this path. */ - if (INTEL_GEN(i915) >= 8 && (offset >= 0xb000 && offset <= 0xb4ff)) - return true; + for (i = 0; mcr_ranges_gen8[i].start; i++) + if (offset >= mcr_ranges_gen8[i].start && + offset <= mcr_ranges_gen8[i].end) + return true; return false; } diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index e1c313da6c00..a62bdf9be682 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -457,7 +457,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected) struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; /* TODO: add more platforms support */ - if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || + IS_COFFEELAKE(dev_priv)) { if (connected) { vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED; diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 867e7629025b..33569b910ed5 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v) /* there's features depending on version! */ v->header.version = 155; v->header.header_size = sizeof(v->header); - v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header); + v->header.vbt_size = sizeof(struct vbt); v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); - v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) - - sizeof(struct bdb_header); + v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header); /* general features */ v->general_features_header.id = BDB_GENERAL_FEATURES; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 487af6ea9972..345c2aa3b491 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; - mutex_lock(&vgpu->vgpu_lock); - WARN(vgpu->active, "vGPU is still active!\n"); + /* + * remove idr first so later clean can judge if need to stop + * service if no active vgpu. + */ + mutex_lock(&gvt->lock); + idr_remove(&gvt->vgpu_idr, vgpu->id); + mutex_unlock(&gvt->lock); + + mutex_lock(&vgpu->vgpu_lock); intel_gvt_debugfs_remove_vgpu(vgpu); intel_vgpu_clean_sched_policy(vgpu); intel_vgpu_clean_submission(vgpu); @@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) mutex_unlock(&vgpu->vgpu_lock); mutex_lock(&gvt->lock); - idr_remove(&gvt->vgpu_idr, vgpu->id); if (idr_is_empty(&gvt->vgpu_idr)) intel_gvt_clean_irq(gvt); intel_gvt_update_vgpu_types(gvt); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index f7385abdd74b..eec1d6a6aa22 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -56,6 +56,7 @@ #include "display/intel_hotplug.h" #include "display/intel_overlay.h" #include "display/intel_pipe_crc.h" +#include "display/intel_psr.h" #include "display/intel_sprite.h" #include "display/intel_vga.h" @@ -330,6 +331,8 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915) intel_init_ipc(i915); + intel_psr_set_force_mode_changed(i915->psr.dp); + return 0; cleanup_gem: @@ -502,8 +505,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) mutex_init(&dev_priv->backlight_lock); mutex_init(&dev_priv->sb_lock); - pm_qos_add_request(&dev_priv->sb_qos, - PM_QOS_CPU_DMA_LATENCY, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE); mutex_init(&dev_priv->av_mutex); mutex_init(&dev_priv->wm.wm_mutex); @@ -568,7 +570,7 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv) vlv_free_s0ix_state(dev_priv); i915_workqueues_cleanup(dev_priv); - pm_qos_remove_request(&dev_priv->sb_qos); + cpu_latency_qos_remove_request(&dev_priv->sb_qos); mutex_destroy(&dev_priv->sb_lock); } @@ -1226,8 +1228,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) } } - pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY, - PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_add_request(&dev_priv->pm_qos, PM_QOS_DEFAULT_VALUE); intel_gt_init_workarounds(dev_priv); @@ -1273,7 +1274,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) err_msi: if (pdev->msi_enabled) pci_disable_msi(pdev); - pm_qos_remove_request(&dev_priv->pm_qos); + cpu_latency_qos_remove_request(&dev_priv->pm_qos); err_mem_regions: intel_memory_regions_driver_release(dev_priv); err_ggtt: @@ -1296,7 +1297,7 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) if (pdev->msi_enabled) pci_disable_msi(pdev); - pm_qos_remove_request(&dev_priv->pm_qos); + cpu_latency_qos_remove_request(&dev_priv->pm_qos); } /** diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 077af22b8340..810e3ccd56ec 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -505,7 +505,7 @@ struct i915_psr { bool dc3co_enabled; u32 dc3co_exit_delay; struct delayed_work idle_work; - bool initially_probed; + bool force_mode_changed; }; #define QUIRK_LVDS_SSC_DISABLE (1<<1) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0f556d80ba36..3b6b913bd27a 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1954,9 +1954,10 @@ out: return i915_vma_get(oa_bo->vma); } -static int emit_oa_config(struct i915_perf_stream *stream, - struct i915_oa_config *oa_config, - struct intel_context *ce) +static struct i915_request * +emit_oa_config(struct i915_perf_stream *stream, + struct i915_oa_config *oa_config, + struct intel_context *ce) { struct i915_request *rq; struct i915_vma *vma; @@ -1964,7 +1965,7 @@ static int emit_oa_config(struct i915_perf_stream *stream, vma = get_oa_vma(stream, oa_config); if (IS_ERR(vma)) - return PTR_ERR(vma); + return ERR_CAST(vma); err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); if (err) @@ -1989,13 +1990,17 @@ static int emit_oa_config(struct i915_perf_stream *stream, err = rq->engine->emit_bb_start(rq, vma->node.start, 0, I915_DISPATCH_SECURE); + if (err) + goto err_add_request; + + i915_request_get(rq); err_add_request: i915_request_add(rq); err_vma_unpin: i915_vma_unpin(vma); err_vma_put: i915_vma_put(vma); - return err; + return err ? ERR_PTR(err) : rq; } static struct intel_context *oa_context(struct i915_perf_stream *stream) @@ -2003,7 +2008,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream) return stream->pinned_ctx ?: stream->engine->kernel_context; } -static int hsw_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +hsw_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; @@ -2406,7 +2412,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream, return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs)); } -static int gen8_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +gen8_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2448,7 +2455,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream) */ ret = lrc_configure_all_contexts(stream, oa_config); if (ret) - return ret; + return ERR_PTR(ret); return emit_oa_config(stream, oa_config, oa_context(stream)); } @@ -2460,7 +2467,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream) 0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS); } -static int gen12_enable_metric_set(struct i915_perf_stream *stream) +static struct i915_request * +gen12_enable_metric_set(struct i915_perf_stream *stream) { struct intel_uncore *uncore = stream->uncore; struct i915_oa_config *oa_config = stream->oa_config; @@ -2491,7 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) */ ret = gen12_configure_all_contexts(stream, oa_config); if (ret) - return ret; + return ERR_PTR(ret); /* * For Gen12, performance counters are context @@ -2501,7 +2509,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream) if (stream->ctx) { ret = gen12_configure_oar_context(stream, true); if (ret) - return ret; + return ERR_PTR(ret); } return emit_oa_config(stream, oa_config, oa_context(stream)); @@ -2696,6 +2704,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = { .read = i915_oa_read, }; +static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream) +{ + struct i915_request *rq; + + rq = stream->perf->ops.enable_metric_set(stream); + if (IS_ERR(rq)) + return PTR_ERR(rq); + + i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); + i915_request_put(rq); + + return 0; +} + /** * i915_oa_stream_init - validate combined props for OA stream and init * @stream: An i915 perf stream @@ -2829,7 +2851,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, stream->ops = &i915_oa_stream_ops; perf->exclusive_stream = stream; - ret = perf->ops.enable_metric_set(stream); + ret = i915_perf_stream_enable_sync(stream); if (ret) { DRM_DEBUG("Unable to enable metric set\n"); goto err_enable; @@ -3147,7 +3169,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, return -EINVAL; if (config != stream->oa_config) { - int err; + struct i915_request *rq; /* * If OA is bound to a specific context, emit the @@ -3158,11 +3180,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream, * When set globally, we use a low priority kernel context, * so it will effectively take effect when idle. */ - err = emit_oa_config(stream, config, oa_context(stream)); - if (err == 0) + rq = emit_oa_config(stream, config, oa_context(stream)); + if (!IS_ERR(rq)) { config = xchg(&stream->oa_config, config); - else - ret = err; + i915_request_put(rq); + } else { + ret = PTR_ERR(rq); + } } i915_oa_config_put(config); diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index 45e581455f5d..a0e22f00f6cf 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -339,7 +339,8 @@ struct i915_oa_ops { * counter reports being sampled. May apply system constraints such as * disabling EU clock gating as required. */ - int (*enable_metric_set)(struct i915_perf_stream *stream); + struct i915_request * + (*enable_metric_set)(struct i915_perf_stream *stream); /** * @disable_metric_set: Remove system constraints associated with using diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 6cc55c103f67..3575fd30756b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7757,6 +7757,7 @@ enum { #define BW_BUDDY1_CTL _MMIO(0x45140) #define BW_BUDDY2_CTL _MMIO(0x45150) #define BW_BUDDY_DISABLE REG_BIT(31) +#define BW_BUDDY_TLB_REQ_TIMER_MASK REG_GENMASK(21, 16) #define BW_BUDDY1_PAGE_MASK _MMIO(0x45144) #define BW_BUDDY2_PAGE_MASK _MMIO(0x45154) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index f56b046a32de..a18b2a244706 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -275,7 +275,7 @@ bool i915_request_retire(struct i915_request *rq) spin_unlock_irq(&rq->lock); remove_from_client(rq); - list_del(&rq->link); + list_del_rcu(&rq->link); intel_context_exit(rq->context); intel_context_unpin(rq->context); @@ -527,19 +527,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) return NOTIFY_DONE; } +static void irq_semaphore_cb(struct irq_work *wrk) +{ + struct i915_request *rq = + container_of(wrk, typeof(*rq), semaphore_work); + + i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE); + i915_request_put(rq); +} + static int __i915_sw_fence_call semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) { - struct i915_request *request = - container_of(fence, typeof(*request), semaphore); + struct i915_request *rq = container_of(fence, typeof(*rq), semaphore); switch (state) { case FENCE_COMPLETE: - i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE); + if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) { + i915_request_get(rq); + init_irq_work(&rq->semaphore_work, irq_semaphore_cb); + irq_work_queue(&rq->semaphore_work); + } break; case FENCE_FREE: - i915_request_put(request); + i915_request_put(rq); break; } @@ -721,6 +733,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) rq->infix = rq->ring->emit; /* end of header; start of user payload */ intel_context_mark_active(ce); + list_add_tail_rcu(&rq->link, &tl->requests); + return rq; err_unwind: @@ -774,16 +788,26 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) struct dma_fence *fence; int err; - GEM_BUG_ON(i915_request_timeline(rq) == - rcu_access_pointer(signal->timeline)); + if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline)) + return 0; + + if (i915_request_started(signal)) + return 0; fence = NULL; rcu_read_lock(); spin_lock_irq(&signal->lock); - if (!i915_request_started(signal) && - !list_is_first(&signal->link, - &rcu_dereference(signal->timeline)->requests)) { - struct i915_request *prev = list_prev_entry(signal, link); + do { + struct list_head *pos = READ_ONCE(signal->link.prev); + struct i915_request *prev; + + /* Confirm signal has not been retired, the link is valid */ + if (unlikely(i915_request_started(signal))) + break; + + /* Is signal the earliest request on its timeline? */ + if (pos == &rcu_dereference(signal->timeline)->requests) + break; /* * Peek at the request before us in the timeline. That @@ -791,20 +815,25 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal) * after acquiring a reference to it, confirm that it is * still part of the signaler's timeline. */ - if (i915_request_get_rcu(prev)) { - if (list_next_entry(prev, link) == signal) - fence = &prev->fence; - else - i915_request_put(prev); + prev = list_entry(pos, typeof(*prev), link); + if (!i915_request_get_rcu(prev)) + break; + + /* After the strong barrier, confirm prev is still attached */ + if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) { + i915_request_put(prev); + break; } - } + + fence = &prev->fence; + } while (0); spin_unlock_irq(&signal->lock); rcu_read_unlock(); if (!fence) return 0; err = 0; - if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) + if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence)) err = i915_sw_fence_await_dma_fence(&rq->submit, fence, 0, I915_FENCE_GFP); @@ -1242,8 +1271,6 @@ __i915_request_add_to_timeline(struct i915_request *rq) 0); } - list_add_tail(&rq->link, &timeline->requests); - /* * Make sure that no request gazumped us - if it was allocated after * our i915_request_alloc() and called __i915_request_add() before @@ -1303,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq, * decide whether to preempt the entire chain so that it is ready to * run at the earliest possible convenience. */ - i915_sw_fence_commit(&rq->semaphore); if (attr && rq->engine->schedule) rq->engine->schedule(rq, attr); + i915_sw_fence_commit(&rq->semaphore); i915_sw_fence_commit(&rq->submit); } diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index f57eadcf3583..fccc339949ec 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -26,6 +26,7 @@ #define I915_REQUEST_H #include <linux/dma-fence.h> +#include <linux/irq_work.h> #include <linux/lockdep.h> #include "gem/i915_gem_context_types.h" @@ -208,6 +209,7 @@ struct i915_request { }; struct list_head execute_cb; struct i915_sw_fence semaphore; + struct irq_work semaphore_work; /* * A list of everyone we wait upon, and everyone who waits upon us. diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index b0ade76bec90..d34141f7dcd8 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -234,6 +234,11 @@ static inline u64 ptr_to_u64(const void *ptr) __idx; \ }) +static inline bool is_power_of_2_u64(u64 n) +{ + return (n != 0 && ((n & (n - 1)) == 0)); +} + static inline void __list_del_many(struct list_head *head, struct list_head *first) { diff --git a/drivers/gpu/drm/i915/intel_sideband.c b/drivers/gpu/drm/i915/intel_sideband.c index cbfb7171d62d..0648eda309e4 100644 --- a/drivers/gpu/drm/i915/intel_sideband.c +++ b/drivers/gpu/drm/i915/intel_sideband.c @@ -60,7 +60,7 @@ static void __vlv_punit_get(struct drm_i915_private *i915) * to the Valleyview P-unit and not all sideband communications. */ if (IS_VALLEYVIEW(i915)) { - pm_qos_update_request(&i915->sb_qos, 0); + cpu_latency_qos_update_request(&i915->sb_qos, 0); on_each_cpu(ping, NULL, 1); } } @@ -68,7 +68,8 @@ static void __vlv_punit_get(struct drm_i915_private *i915) static void __vlv_punit_put(struct drm_i915_private *i915) { if (IS_VALLEYVIEW(i915)) - pm_qos_update_request(&i915->sb_qos, PM_QOS_DEFAULT_VALUE); + cpu_latency_qos_update_request(&i915->sb_qos, + PM_QOS_DEFAULT_VALUE); iosf_mbi_punit_release(); } |