diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt')
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gt.c | 108 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gt.h | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gt_types.h | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/uc/intel_guc.h | 5 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 114 |
6 files changed, 215 insertions, 18 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f98f0fb21efb..35d0fcd3a86c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -29,6 +29,8 @@ void __intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) { spin_lock_init(>->irq_lock); + mutex_init(>->tlb_invalidate_lock); + INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -912,3 +914,109 @@ void intel_gt_info_print(const struct intel_gt_info *info, intel_sseu_dump(&info->sseu, p); } + +struct reg_and_bit { + i915_reg_t reg; + u32 bit; +}; + +static struct reg_and_bit +get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8, + const i915_reg_t *regs, const unsigned int num) +{ + const unsigned int class = engine->class; + struct reg_and_bit rb = { }; + + if (drm_WARN_ON_ONCE(&engine->i915->drm, + class >= num || !regs[class].reg)) + return rb; + + rb.reg = regs[class]; + if (gen8 && class == VIDEO_DECODE_CLASS) + rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */ + else + rb.bit = engine->instance; + + rb.bit = BIT(rb.bit); + + return rb; +} + +void intel_gt_invalidate_tlbs(struct intel_gt *gt) +{ + static const i915_reg_t gen8_regs[] = { + [RENDER_CLASS] = GEN8_RTCR, + [VIDEO_DECODE_CLASS] = GEN8_M1TCR, /* , GEN8_M2TCR */ + [VIDEO_ENHANCEMENT_CLASS] = GEN8_VTCR, + [COPY_ENGINE_CLASS] = GEN8_BTCR, + }; + static const i915_reg_t gen12_regs[] = { + [RENDER_CLASS] = GEN12_GFX_TLB_INV_CR, + [VIDEO_DECODE_CLASS] = GEN12_VD_TLB_INV_CR, + [VIDEO_ENHANCEMENT_CLASS] = GEN12_VE_TLB_INV_CR, + [COPY_ENGINE_CLASS] = GEN12_BLT_TLB_INV_CR, + }; + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct intel_engine_cs *engine; + 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); + } else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) { + regs = gen8_regs; + num = ARRAY_SIZE(gen8_regs); + } else if (GRAPHICS_VER(i915) < 8) { + return; + } + + if (drm_WARN_ONCE(&i915->drm, !num, + "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); + + for_each_engine(engine, gt, id) { + /* + * HW architecture suggest typical invalidation time at 40us, + * with pessimistic cases up to 100us and a recommendation to + * cap at 1ms. We go a bit higher just in case. + */ + 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; + + intel_uncore_write_fw(uncore, rb.reg, rb.bit); + if (__intel_wait_for_register_fw(uncore, + rb.reg, rb.bit, 0, + timeout_us, timeout_ms, + NULL)) + drm_err_ratelimited(>->i915->drm, + "%s TLB invalidation did not complete in %ums!\n", + engine->name, timeout_ms); + } + + /* + * Use delayed put since a) we mostly expect a flurry of TLB + * invalidations so it is good to avoid paying the forcewake cost and + * b) it works around a bug in Icelake which cannot cope with too rapid + * transitions. + */ + intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL); + 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 3ace129eb2af..a913fb6ffec3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -91,4 +91,6 @@ 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); + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 14216cc471b1..f20687796490 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -73,6 +73,8 @@ struct intel_gt { struct intel_uc uc; + struct mutex tlb_invalidate_lock; + struct i915_wa_list wa_list; struct intel_gt_timelines { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index f9240d4baa69..3aabe164c329 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -206,6 +206,11 @@ struct intel_guc { * context usage for overflows. */ struct delayed_work work; + + /** + * @shift: Right shift value for the gpm timestamp + */ + u32 shift; } timestamp; #ifdef CONFIG_DRM_I915_SELFTEST diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 13b27b8ff74e..ba21ace973da 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -110,7 +110,7 @@ static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) { u32 request[] = { GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 2), + SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), id, }; 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 e7517206af82..154ad726e266 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1113,6 +1113,19 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) if (new_start == lower_32_bits(*prev_start)) return; + /* + * When gt is unparked, we update the gt timestamp and start the ping + * worker that updates the gt_stamp every POLL_TIME_CLKS. As long as gt + * is unparked, all switched in contexts will have a start time that is + * within +/- POLL_TIME_CLKS of the most recent gt_stamp. + * + * If neither gt_stamp nor new_start has rolled over, then the + * gt_stamp_hi does not need to be adjusted, however if one of them has + * rolled over, we need to adjust gt_stamp_hi accordingly. + * + * The below conditions address the cases of new_start rollover and + * gt_stamp_last rollover respectively. + */ if (new_start < gt_stamp_last && (new_start - gt_stamp_last) <= POLL_TIME_CLKS) gt_stamp_hi++; @@ -1124,17 +1137,45 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) *prev_start = ((u64)gt_stamp_hi << 32) | new_start; } -static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) +/* + * GuC updates shared memory and KMD reads it. Since this is not synchronized, + * we run into a race where the value read is inconsistent. Sometimes the + * inconsistency is in reading the upper MSB bytes of the last_in value when + * this race occurs. 2 types of cases are seen - upper 8 bits are zero and upper + * 24 bits are zero. Since these are non-zero values, it is non-trivial to + * determine validity of these values. Instead we read the values multiple times + * until they are consistent. In test runs, 3 attempts results in consistent + * values. The upper bound is set to 6 attempts and may need to be tuned as per + * any new occurences. + */ +static void __get_engine_usage_record(struct intel_engine_cs *engine, + u32 *last_in, u32 *id, u32 *total) { struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine); + int i = 0; + + do { + *last_in = READ_ONCE(rec->last_switch_in_stamp); + *id = READ_ONCE(rec->current_context_index); + *total = READ_ONCE(rec->total_runtime); + + if (READ_ONCE(rec->last_switch_in_stamp) == *last_in && + READ_ONCE(rec->current_context_index) == *id && + READ_ONCE(rec->total_runtime) == *total) + break; + } while (++i < 6); +} + +static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) +{ struct intel_engine_guc_stats *stats = &engine->stats.guc; struct intel_guc *guc = &engine->gt->uc.guc; - u32 last_switch = rec->last_switch_in_stamp; - u32 ctx_id = rec->current_context_index; - u32 total = rec->total_runtime; + u32 last_switch, ctx_id, total; lockdep_assert_held(&guc->timestamp.lock); + __get_engine_usage_record(engine, &last_switch, &ctx_id, &total); + stats->running = ctx_id != ~0U && last_switch; if (stats->running) __extend_last_switch(guc, &stats->start_gt_clk, last_switch); @@ -1149,23 +1190,51 @@ static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) } } -static void guc_update_pm_timestamp(struct intel_guc *guc, - struct intel_engine_cs *engine, - ktime_t *now) +static u32 gpm_timestamp_shift(struct intel_gt *gt) +{ + intel_wakeref_t wakeref; + u32 reg, shift; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + reg = intel_uncore_read(gt->uncore, RPM_CONFIG0); + + shift = (reg & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >> + GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT; + + return 3 - shift; +} + +static u64 gpm_timestamp(struct intel_gt *gt) +{ + u32 lo, hi, old_hi, loop = 0; + + hi = intel_uncore_read(gt->uncore, MISC_STATUS1); + do { + lo = intel_uncore_read(gt->uncore, MISC_STATUS0); + old_hi = hi; + hi = intel_uncore_read(gt->uncore, MISC_STATUS1); + } while (old_hi != hi && loop++ < 2); + + return ((u64)hi << 32) | lo; +} + +static void guc_update_pm_timestamp(struct intel_guc *guc, ktime_t *now) { - u32 gt_stamp_now, gt_stamp_hi; + struct intel_gt *gt = guc_to_gt(guc); + u32 gt_stamp_lo, gt_stamp_hi; + u64 gpm_ts; lockdep_assert_held(&guc->timestamp.lock); gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp); - gt_stamp_now = intel_uncore_read(engine->uncore, - RING_TIMESTAMP(engine->mmio_base)); + gpm_ts = gpm_timestamp(gt) >> guc->timestamp.shift; + gt_stamp_lo = lower_32_bits(gpm_ts); *now = ktime_get(); - if (gt_stamp_now < lower_32_bits(guc->timestamp.gt_stamp)) + if (gt_stamp_lo < lower_32_bits(guc->timestamp.gt_stamp)) gt_stamp_hi++; - guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_now; + guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_lo; } /* @@ -1208,8 +1277,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) if (!in_reset && intel_gt_pm_get_if_awake(gt)) { stats_saved = *stats; gt_stamp_saved = guc->timestamp.gt_stamp; + /* + * Update gt_clks, then gt timestamp to simplify the 'gt_stamp - + * start_gt_clk' calculation below for active engines. + */ guc_update_engine_gt_clks(engine); - guc_update_pm_timestamp(guc, engine, now); + guc_update_pm_timestamp(guc, now); intel_gt_pm_put_async(gt); if (i915_reset_count(gpu_error) != reset_count) { *stats = stats_saved; @@ -1241,8 +1314,8 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) spin_lock_irqsave(&guc->timestamp.lock, flags); + guc_update_pm_timestamp(guc, &unused); for_each_engine(engine, gt, id) { - guc_update_pm_timestamp(guc, engine, &unused); guc_update_engine_gt_clks(engine); engine->stats.guc.prev_total = 0; } @@ -1259,10 +1332,11 @@ static void __update_guc_busyness_stats(struct intel_guc *guc) ktime_t unused; spin_lock_irqsave(&guc->timestamp.lock, flags); - for_each_engine(engine, gt, id) { - guc_update_pm_timestamp(guc, engine, &unused); + + guc_update_pm_timestamp(guc, &unused); + for_each_engine(engine, gt, id) guc_update_engine_gt_clks(engine); - } + spin_unlock_irqrestore(&guc->timestamp.lock, flags); } @@ -1335,10 +1409,15 @@ void intel_guc_busyness_park(struct intel_gt *gt) void intel_guc_busyness_unpark(struct intel_gt *gt) { struct intel_guc *guc = >->uc.guc; + unsigned long flags; + ktime_t unused; if (!guc_submission_initialized(guc)) return; + spin_lock_irqsave(&guc->timestamp.lock, flags); + guc_update_pm_timestamp(guc, &unused); + spin_unlock_irqrestore(&guc->timestamp.lock, flags); mod_delayed_work(system_highpri_wq, &guc->timestamp.work, guc->timestamp.ping_delay); } @@ -1783,6 +1862,7 @@ int intel_guc_submission_init(struct intel_guc *guc) spin_lock_init(&guc->timestamp.lock); INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ; + guc->timestamp.shift = gpm_timestamp_shift(gt); return 0; } |