From patchwork Thu Jun 13 10:20:22 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sebastian Andrzej Siewior X-Patchwork-Id: 13696573 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id D0175C27C75 for ; Thu, 13 Jun 2024 10:28:34 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 2DA6C10EA1D; Thu, 13 Jun 2024 10:28:32 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; secure) header.d=linutronix.de header.i=@linutronix.de header.b="QqbLWHkr"; dkim=permerror (0-bit key) header.d=linutronix.de header.i=@linutronix.de header.b="myP2UD1Z"; dkim-atps=neutral Received: from galois.linutronix.de (Galois.linutronix.de [193.142.43.55]) by gabe.freedesktop.org (Postfix) with ESMTPS id 541F910EA0C; Thu, 13 Jun 2024 10:28:28 +0000 (UTC) From: Sebastian Andrzej Siewior DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020; t=1718274505; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=QUNTO0UfshytQe0+4dGuteCafLmjnva+iste5V2OTf4=; b=QqbLWHkr1BWTqXGIiBPt+yLA8vCXKFgte4XcdwO2UKml4VtY2bjhgMh7a49NCiTLkHdePi Hv9Q8+GV7fj8GuNt//nUVHuKt7gyMnb0v8O4yFNDolTmo9wCRCHPSdWksloON++K84mL6o 4tZwzQzMFK0pwHBdFzAeeqB6bVio2cXipU5qS2KDKkUwFudKMmYc8qxULAlJgxKRuI1X0F oWvfEldCovxUWs62mAPL6HPA3Ffzh32S2sjc84CSqf4Qcql+znS/qotyNYD2X73wWakKju WIzoYcGMF3dWAfL6ZofjdA7aakkn53aIaNxQ4f9qbodSqkiBvbPPScR1kR069Q== DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020e; t=1718274505; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=QUNTO0UfshytQe0+4dGuteCafLmjnva+iste5V2OTf4=; b=myP2UD1ZqWtoCezXP9b6/jBpepupf8ZB6So7XzXlGTeY8I9yDsOcP+a7NdK7rmS30wBqhl mP1xeRzwKlIkJmDg== To: intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org Cc: Jani Nikula , Joonas Lahtinen , Rodrigo Vivi , Thomas Gleixner , Tvrtko Ursulin , Sebastian Andrzej Siewior , Clark Williams , Maarten Lankhorst Subject: [PATCH v2 5/8] drm/i915/gt: Use spin_lock_irq() instead of local_irq_disable() + spin_lock() Date: Thu, 13 Jun 2024 12:20:22 +0200 Message-ID: <20240613102818.4056866-6-bigeasy@linutronix.de> In-Reply-To: <20240613102818.4056866-1-bigeasy@linutronix.de> References: <20240613102818.4056866-1-bigeasy@linutronix.de> MIME-Version: 1.0 X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" execlists_dequeue() is invoked from a function which uses local_irq_disable() to disable interrupts so the spin_lock() behaves like spin_lock_irq(). This breaks PREEMPT_RT because local_irq_disable() + spin_lock() is not the same as spin_lock_irq(). execlists_dequeue_irq() and execlists_dequeue() has each one caller only. If intel_engine_cs::active::lock is acquired and released with the _irq suffix then it behaves almost as if execlists_dequeue() would be invoked with disabled interrupts. The difference is the last part of the function which is then invoked with enabled interrupts. I can't tell if this makes a difference. From looking at it, it might work to move the last unlock at the end of the function as I didn't find anything that would acquire the lock again. Reported-by: Clark Williams Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Maarten Lankhorst --- .../drm/i915/gt/intel_execlists_submission.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 21829439e6867..ed29a2dd6ea0a 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -1303,7 +1303,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * and context switches) submission. */ - spin_lock(&sched_engine->lock); + spin_lock_irq(&sched_engine->lock); /* * If the queue is higher priority than the last @@ -1403,7 +1403,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) * Even if ELSP[1] is occupied and not worthy * of timeslices, our queue might be. */ - spin_unlock(&sched_engine->lock); + spin_unlock_irq(&sched_engine->lock); return; } } @@ -1429,7 +1429,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) if (last && !can_merge_rq(last, rq)) { spin_unlock(&ve->base.sched_engine->lock); - spin_unlock(&engine->sched_engine->lock); + spin_unlock_irq(&engine->sched_engine->lock); return; /* leave this for another sibling */ } @@ -1591,7 +1591,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine) */ sched_engine->queue_priority_hint = queue_prio(sched_engine); i915_sched_engine_reset_on_empty(sched_engine); - spin_unlock(&sched_engine->lock); + spin_unlock_irq(&sched_engine->lock); /* * We can skip poking the HW if we ended up with exactly the same set @@ -1617,13 +1617,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine) } } -static void execlists_dequeue_irq(struct intel_engine_cs *engine) -{ - local_irq_disable(); /* Suspend interrupts across request submission */ - execlists_dequeue(engine); - local_irq_enable(); /* flush irq_work (e.g. breadcrumb enabling) */ -} - static void clear_ports(struct i915_request **ports, int count) { memset_p((void **)ports, NULL, count); @@ -2478,7 +2471,7 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) } if (!engine->execlists.pending[0]) { - execlists_dequeue_irq(engine); + execlists_dequeue(engine); start_timeslice(engine); }