From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.3 required=3.0 tests=DKIM_ADSP_CUSTOM_MED, DKIM_INVALID,DKIM_SIGNED,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 38793C433E3 for ; Mon, 25 May 2020 21:48:14 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id E71D8206C3 for ; Mon, 25 May 2020 21:48:13 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="YkNESquX" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org E71D8206C3 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=gmail.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 8E0C68E0008; Mon, 25 May 2020 17:48:13 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 8419C80061; Mon, 25 May 2020 17:48:13 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 691808E0013; Mon, 25 May 2020 17:48:13 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0130.hostedemail.com [216.40.44.130]) by kanga.kvack.org (Postfix) with ESMTP id 4E2CD8E0008 for ; Mon, 25 May 2020 17:48:13 -0400 (EDT) Received: from smtpin12.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id ECDA4181AC9CB for ; Mon, 25 May 2020 21:48:12 +0000 (UTC) X-FDA: 76856580024.12.trick69_2a96fe9f02c50 X-HE-Tag: trick69_2a96fe9f02c50 X-Filterd-Recvd-Size: 8352 Received: from mail-lf1-f68.google.com (mail-lf1-f68.google.com [209.85.167.68]) by imf07.hostedemail.com (Postfix) with ESMTP for ; Mon, 25 May 2020 21:48:12 +0000 (UTC) Received: by mail-lf1-f68.google.com with SMTP id z206so7533845lfc.6 for ; Mon, 25 May 2020 14:48:12 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=gGk+1Dv1xZWBD45WykPdecLcAYKfFE81IWJLJfIPzl4=; b=YkNESquXqQUg7n7ikcJ7p3fXioH3Tb6MRVXMx68ADYtDErZ6m8ILzBiSS96gBU5/K+ k9UbRIKwDOM3N4BQnVG/G+Tj8CfCAxkECW0eonIxdrxJC0Vx5fF7IWSYNPOe+/8UP+yt fJ4tdGUTbs+yFPo59NDWlvhSlCCqZFyBfIRrLpwmecehEm9mRb6yAqVBUgoerjSRTOBP G8E0yivmIeyNqO+QxWa/lIz721ZFs3qiyu4ayiVW9W+xMQPBkIxhCaKXQGpoxMLXDc1R bvj1/OuViAYkvPW7eieykUzB0ZkLpSny5Svu+2JDtcfZD4la8g0XljN0WF9w2EqxISt2 9RPg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=gGk+1Dv1xZWBD45WykPdecLcAYKfFE81IWJLJfIPzl4=; b=lvEvFMA0m4xSBrSiJHJ+dU/NEFmlUSlFsT50hddO+G+1tCB9x6Q4tx9+J0cAv+Zqzg zwCClUrq17iODz92OgePlL9X9plFw1Pjon83MU32SzrVuqkQatImzIww0jRC1ku2XDMX Y0IjtGlvvkgyANzCZ4pH3yYmneIcFZRm4XmUfhAEAde0VN4xrwv7/u+9MJyDWTHb+AhB hKZjge18dDcTpbR8ME36F0/Lk5yK5BMBqnsyPpuNmKikh8WU1b1ir2N1ZOy6JC8gK08f oWmBCSsRZoY+5bEecjXJhiEicLaNvJZUiNUxCLFfoKDy5zlz/E+YCmfbU1maiHXnn+4e 9Weg== X-Gm-Message-State: AOAM531bjW1NeIEUvqHFN/pF9g87hSDu6zjWKGNxpNexhCrN93zApJIl zCjW4mDE2YrcvVW75VMX0FI= X-Google-Smtp-Source: ABdhPJxnmRdUPLkFsmHymHpSeTqdd/iueRk3nTcSAYw1dqYbXgKIV3RatLW1vOgritqB/JVx2XTE6g== X-Received: by 2002:a19:6b14:: with SMTP id d20mr9822238lfa.202.1590443291199; Mon, 25 May 2020 14:48:11 -0700 (PDT) Received: from pc638.lan (h5ef52e31.seluork.dyn.perspektivbredband.net. [94.245.46.49]) by smtp.gmail.com with ESMTPSA id a6sm2280044lji.29.2020.05.25.14.48.09 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 25 May 2020 14:48:10 -0700 (PDT) From: "Uladzislau Rezki (Sony)" To: LKML , linux-mm@kvack.org Cc: Andrew Morton , "Paul E . McKenney" , "Theodore Y . Ts'o" , Matthew Wilcox , Joel Fernandes , RCU , Uladzislau Rezki , Oleksiy Avramchenko , bigeasy@linutronix.de Subject: [PATCH v2 01/16] rcu/tree: Keep kfree_rcu() awake during lock contention Date: Mon, 25 May 2020 23:47:45 +0200 Message-Id: <20200525214800.93072-2-urezki@gmail.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20200525214800.93072-1-urezki@gmail.com> References: <20200525214800.93072-1-urezki@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: "Joel Fernandes (Google)" On PREEMPT_RT kernels, the krcp spinlock gets converted to an rt-mutex and causes kfree_rcu() callers to sleep. This makes it unusable for callers in purely atomic sections such as non-threaded IRQ handlers and raw spinlock sections. Fix it by converting the spinlock to a raw spinlock. Vetting all code paths, there is no reason to believe that the raw spinlock will hurt RT latencies as it is not held for a long time. Cc: bigeasy@linutronix.de Cc: Uladzislau Rezki Reviewed-by: Uladzislau Rezki Signed-off-by: Joel Fernandes (Google) Signed-off-by: Uladzislau Rezki (Sony) --- kernel/rcu/tree.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 6e120be29332..6e967a9d6704 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2882,7 +2882,7 @@ struct kfree_rcu_cpu { struct kfree_rcu_bulk_data *bhead; struct kfree_rcu_bulk_data *bcached; struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; - spinlock_t lock; + raw_spinlock_t lock; struct delayed_work monitor_work; bool monitor_todo; bool initialized; @@ -2915,12 +2915,12 @@ static void kfree_rcu_work(struct work_struct *wo= rk) krwp =3D container_of(to_rcu_work(work), struct kfree_rcu_cpu_work, rcu_work); krcp =3D krwp->krcp; - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); head =3D krwp->head_free; krwp->head_free =3D NULL; bhead =3D krwp->bhead_free; krwp->bhead_free =3D NULL; - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); =20 /* "bhead" is now private, so traverse locklessly. */ for (; bhead; bhead =3D bnext) { @@ -3023,14 +3023,14 @@ static inline void kfree_rcu_drain_unlock(struct = kfree_rcu_cpu *krcp, krcp->monitor_todo =3D false; if (queue_kfree_rcu_work(krcp)) { // Success! Our job is done here. - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); return; } =20 // Previous RCU batch still in progress, try again later. krcp->monitor_todo =3D true; schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } =20 /* @@ -3043,11 +3043,11 @@ static void kfree_rcu_monitor(struct work_struct = *work) struct kfree_rcu_cpu *krcp =3D container_of(work, struct kfree_rcu_cpu, monitor_work.work); =20 - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } =20 static inline bool @@ -3118,7 +3118,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_call= back_t func) local_irq_save(flags); // For safely calling this_cpu_ptr(). krcp =3D this_cpu_ptr(&krc); if (krcp->initialized) - spin_lock(&krcp->lock); + raw_spin_lock(&krcp->lock); =20 // Queue the object but don't yet schedule the batch. if (debug_rcu_head_queue(head)) { @@ -3149,7 +3149,7 @@ void kfree_call_rcu(struct rcu_head *head, rcu_call= back_t func) =20 unlock_return: if (krcp->initialized) - spin_unlock(&krcp->lock); + raw_spin_unlock(&krcp->lock); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(kfree_call_rcu); @@ -3181,11 +3181,11 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, st= ruct shrink_control *sc) struct kfree_rcu_cpu *krcp =3D per_cpu_ptr(&krc, cpu); =20 count =3D krcp->count; - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (krcp->monitor_todo) kfree_rcu_drain_unlock(krcp, flags); else - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); =20 sc->nr_to_scan -=3D count; freed +=3D count; @@ -3212,15 +3212,15 @@ void __init kfree_rcu_scheduler_running(void) for_each_online_cpu(cpu) { struct kfree_rcu_cpu *krcp =3D per_cpu_ptr(&krc, cpu); =20 - spin_lock_irqsave(&krcp->lock, flags); + raw_spin_lock_irqsave(&krcp->lock, flags); if (!krcp->head || krcp->monitor_todo) { - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); continue; } krcp->monitor_todo =3D true; schedule_delayed_work_on(cpu, &krcp->monitor_work, KFREE_DRAIN_JIFFIES); - spin_unlock_irqrestore(&krcp->lock, flags); + raw_spin_unlock_irqrestore(&krcp->lock, flags); } } =20 @@ -4113,7 +4113,7 @@ static void __init kfree_rcu_batch_init(void) for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp =3D per_cpu_ptr(&krc, cpu); =20 - spin_lock_init(&krcp->lock); + raw_spin_lock_init(&krcp->lock); for (i =3D 0; i < KFREE_N_BATCHES; i++) { INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); krcp->krw_arr[i].krcp =3D krcp; --=20 2.20.1