diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_reset.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_reset.c | 79 |
1 files changed, 65 insertions, 14 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 6801f8b95c53..aae5a081cb53 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -764,7 +764,7 @@ wa_14015076503_end(struct intel_gt *gt, intel_engine_mask_t engine_mask) HECI_H_GS1_ER_PREP, 0); } -int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) +static int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) { const int retries = engine_mask == ALL_ENGINES ? RESET_MAX_RETRIES : 1; reset_func reset; @@ -879,8 +879,17 @@ static intel_engine_mask_t reset_prepare(struct intel_gt *gt) intel_engine_mask_t awake = 0; enum intel_engine_id id; - /* For GuC mode, ensure submission is disabled before stopping ring */ - intel_uc_reset_prepare(>->uc); + /** + * For GuC mode with submission enabled, ensure submission + * is disabled before stopping ring. + * + * For GuC mode with submission disabled, ensure that GuC is not + * sanitized, do that after engine reset. reset_prepare() + * is followed by engine reset which in this mode requires GuC to + * process any CSB FIFO entries generated by the resets. + */ + if (intel_uc_uses_guc_submission(>->uc)) + intel_uc_reset_prepare(>->uc); for_each_engine(engine, gt, id) { if (intel_engine_pm_get_if_awake(engine)) @@ -978,7 +987,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt) /* Even if the GPU reset fails, it should still stop the engines */ if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - __intel_gt_reset(gt, ALL_ENGINES); + intel_gt_reset_all_engines(gt); for_each_engine(engine, gt, id) engine->submit_request = nop_submit_request; @@ -1004,6 +1013,15 @@ static void __intel_gt_set_wedged(struct intel_gt *gt) GT_TRACE(gt, "end\n"); } +static void set_wedged_work(struct work_struct *w) +{ + struct intel_gt *gt = container_of(w, struct intel_gt, wedge); + intel_wakeref_t wf; + + with_intel_runtime_pm(gt->uncore->rpm, wf) + __intel_gt_set_wedged(gt); +} + void intel_gt_set_wedged(struct intel_gt *gt) { intel_wakeref_t wakeref; @@ -1015,7 +1033,8 @@ void intel_gt_set_wedged(struct intel_gt *gt) mutex_lock(>->reset.mutex); if (GEM_SHOW_DEBUG()) { - struct drm_printer p = drm_debug_printer(__func__); + struct drm_printer p = drm_dbg_printer(>->i915->drm, + DRM_UT_DRIVER, NULL); struct intel_engine_cs *engine; enum intel_engine_id id; @@ -1088,12 +1107,13 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt) /* We must reset pending GPU events before restoring our submission */ ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */ if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - ok = __intel_gt_reset(gt, ALL_ENGINES) == 0; + ok = intel_gt_reset_all_engines(gt) == 0; if (!ok) { /* * Warn CI about the unrecoverable wedged condition. * Time for a reboot. */ + gt_err(gt, "Unrecoverable wedged condition\n"); add_taint_for_CI(gt->i915, TAINT_WARN); return false; } @@ -1132,10 +1152,10 @@ static int do_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) { int err, i; - err = __intel_gt_reset(gt, ALL_ENGINES); + err = intel_gt_reset_all_engines(gt); for (i = 0; err && i < RESET_MAX_RETRIES; i++) { msleep(10 * (i + 1)); - err = __intel_gt_reset(gt, ALL_ENGINES); + err = intel_gt_reset_all_engines(gt); } if (err) return err; @@ -1179,6 +1199,7 @@ void intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask, const char *reason) { + struct intel_display *display = >->i915->display; intel_engine_mask_t awake; int ret; @@ -1214,7 +1235,7 @@ void intel_gt_reset(struct intel_gt *gt, } if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - intel_runtime_pm_disable_interrupts(gt->i915); + intel_irq_suspend(gt->i915); if (do_reset(gt, stalled_mask)) { gt_err(gt, "Failed to reset chip\n"); @@ -1222,10 +1243,13 @@ void intel_gt_reset(struct intel_gt *gt, } if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - intel_runtime_pm_enable_interrupts(gt->i915); + intel_irq_resume(gt->i915); - intel_overlay_reset(gt->i915); + intel_overlay_reset(display); + /* sanitize uC after engine reset */ + if (!intel_uc_uses_guc_submission(>->uc)) + intel_uc_reset_prepare(>->uc); /* * Next we need to restore the context, but we don't use those * yet either... @@ -1241,8 +1265,10 @@ void intel_gt_reset(struct intel_gt *gt, } ret = resume(gt); - if (ret) + if (ret) { + gt_err(gt, "Failed to resume (%d)\n", ret); goto taint; + } finish: reset_finish(gt, awake); @@ -1269,7 +1295,30 @@ error: goto finish; } -static int intel_gt_reset_engine(struct intel_engine_cs *engine) +/** + * intel_gt_reset_all_engines() - Reset all engines in the given gt. + * @gt: the GT to reset all engines for. + * + * This function resets all engines within the given gt. + * + * Returns: + * Zero on success, negative error code on failure. + */ +int intel_gt_reset_all_engines(struct intel_gt *gt) +{ + return __intel_gt_reset(gt, ALL_ENGINES); +} + +/** + * intel_gt_reset_engine() - Reset a specific engine within a gt. + * @engine: engine to be reset. + * + * This function resets the specified engine within a gt. + * + * Returns: + * Zero on success, negative error code on failure. + */ +int intel_gt_reset_engine(struct intel_engine_cs *engine) { return __intel_gt_reset(engine->gt, engine->mask); } @@ -1562,6 +1611,7 @@ void intel_gt_set_wedged_on_init(struct intel_gt *gt) set_bit(I915_WEDGED_ON_INIT, >->reset.flags); /* Wedged on init is non-recoverable */ + gt_err(gt, "Non-recoverable wedged on init\n"); add_taint_for_CI(gt->i915, TAINT_WARN); } @@ -1578,6 +1628,7 @@ void intel_gt_init_reset(struct intel_gt *gt) init_waitqueue_head(>->reset.queue); mutex_init(>->reset.mutex); init_srcu_struct(>->reset.backoff_srcu); + INIT_WORK(>->wedge, set_wedged_work); /* * While undesirable to wait inside the shrinker, complain anyway. @@ -1604,7 +1655,7 @@ static void intel_wedge_me(struct work_struct *work) struct intel_wedge_me *w = container_of(work, typeof(*w), work.work); gt_err(w->gt, "%s timed out, cancelling all in-flight rendering.\n", w->name); - intel_gt_set_wedged(w->gt); + set_wedged_work(&w->gt->wedge); } void __intel_init_wedge(struct intel_wedge_me *w, |