From patchwork Thu Dec 12 18:42:13 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Paul E. McKenney" X-Patchwork-Id: 13905826 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A273A223C40; Thu, 12 Dec 2024 18:42:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1734028936; cv=none; b=XoripqKk9oy21f1lRmdGT7Sr5SYDUZvK9vzuGfNVlftm2IitfVU/wj9y6iiladDK2iNlB8/lGW4ZApoWEKlqMYoLcIYJNdYFtEBhg6EyJQ4LSSgXo8E98g11hYVppCtg2Qb2tFUw0yeLyYbSTs32L3VcInnuNm784qByVa3uzQ4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1734028936; c=relaxed/simple; bh=uu3fvbyDisEB5DAy3KLp/ZLuYwUsfAY7GhAaSJ6sfRg=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=X0/ubVhTRf26aT1LDSwOCs/jRMJHxhp1rzhjkHas3MjwB80gyKCyvaz435iay8mHFz7c3aV/RLV5X03NXkk7whCXmgbbKsrwJfvRgik13yZBLwwUEKoyCkk8+jjvdLNrzKUQh/3Q6es+PxNfUXW7/w7b9GN2Llcg01CuLeO3Ivk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=HiGw3jWk; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="HiGw3jWk" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 22AF9C4CED0; Thu, 12 Dec 2024 18:42:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1734028936; bh=uu3fvbyDisEB5DAy3KLp/ZLuYwUsfAY7GhAaSJ6sfRg=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=HiGw3jWko8LMxeYVm1lblhLf7HFpdS4AP5ql5PQtJaEBnzwj0lV6DOxCk522+FViN wO3uDYJfJOWoxfOwnpeKFw8UkF7X34MIZPrPJ25ydXfl8qM0QbK1svS0n1QSri/Qou DAKmWcUjlSNWWCcT2uGBbOjhpZvQWRLBssuCLqb7urmnPYYCDFZvKQR0p7TXPruKbn /nt50NRjVTcway0aQDuyxs9Sgmr4GNZVZOa/m+Q3hdedD/CrfriQ1bq8DpwdQcXmRm PyJxwms3i+COuskj1q0pR4HnuakhronwjA24MEA909BP6WSO2azMTTMAlv7GNK1Icv umj2/SGCzh8SQ== Received: by paulmck-ThinkPad-P17-Gen-1.home (Postfix, from userid 1000) id BFB07CE0EE3; Thu, 12 Dec 2024 10:42:15 -0800 (PST) From: "Paul E. McKenney" To: rcu@vger.kernel.org Cc: linux-kernel@vger.kernel.org, kernel-team@meta.com, rostedt@goodmis.org, Frederic Weisbecker , "Paul E . McKenney" Subject: [PATCH rcu 1/2] rcu/nocb: Use switch/case on NOCB timer state machine Date: Thu, 12 Dec 2024 10:42:13 -0800 Message-Id: <20241212184214.2018411-1-paulmck@kernel.org> X-Mailer: git-send-email 2.40.1 In-Reply-To: References: Precedence: bulk X-Mailing-List: rcu@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Frederic Weisbecker It's more convenient to benefit from the fallthrough feature of switch / case to handle the timer state machine. Also a new state is about to be added that will take advantage of it. No intended functional change. Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- kernel/rcu/tree_nocb.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 2605dd234a13c..0923d60c5a338 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -271,22 +271,35 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); - /* - * Bypass wakeup overrides previous deferments. In case of - * callback storms, no need to wake up too early. - */ - if (waketype == RCU_NOCB_WAKE_LAZY && - rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) { - mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush()); - WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); - } else if (waketype == RCU_NOCB_WAKE_BYPASS) { + switch (waketype) { + case RCU_NOCB_WAKE_BYPASS: + /* + * Bypass wakeup overrides previous deferments. In case of + * callback storms, no need to wake up too early. + */ mod_timer(&rdp_gp->nocb_timer, jiffies + 2); WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); - } else { + break; + case RCU_NOCB_WAKE_LAZY: + if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) { + mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush()); + WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); + } + /* + * If the timer is already armed, a non-lazy enqueue may have happened + * in-between. Don't delay it and fall-through. + */ + break; + case RCU_NOCB_WAKE: + fallthrough; + case RCU_NOCB_WAKE_FORCE: if (rdp_gp->nocb_defer_wakeup < RCU_NOCB_WAKE) mod_timer(&rdp_gp->nocb_timer, jiffies + 1); if (rdp_gp->nocb_defer_wakeup < waketype) WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); + break; + default: + WARN_ON_ONCE(1); } raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags); From patchwork Thu Dec 12 18:42:14 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Paul E. McKenney" X-Patchwork-Id: 13905827 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A26DF218594; Thu, 12 Dec 2024 18:42:16 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1734028936; cv=none; b=n68w1Fz9YgBmB7G7NNJlEukhnMTsyPzb/Acs+UdJyGW/vQHrTmkiTJ8IldOBpa9oDNAvjiW+O88lG7MZCaNB4GP3Oh2uripecHx+rIXsKaiOWQA+Iv5R3lJpv1Ec+tdgldkjovw3I7/XJKr5P1idcai+57NAkFHfyGeHjyT9PYg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1734028936; c=relaxed/simple; bh=fwPnm0aiVSfzW+82MVq1yIwL2lTZ/IzUqeBNpXA7rf8=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=Mbbh1i6Zbw/WjVYuMWsxkYjqDAekyMSKUX8se50IDWIpJgSiWNe6osB8c3mvd2Gt3Lsca++rqIkU7BcJS7Izn8OdKeVxXroX6PBV2GZZmRgXVCLIYwPaHBIBlbZoItZO5HVjq2WSy0HStxzg5a3AMpgBuWp2Dq/KMLwIRDwvFBs= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=RTowqtqQ; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="RTowqtqQ" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 3074EC4CED1; Thu, 12 Dec 2024 18:42:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1734028936; bh=fwPnm0aiVSfzW+82MVq1yIwL2lTZ/IzUqeBNpXA7rf8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=RTowqtqQrezQCuLo6anlq5cJSCFGdgcc91vS3NN0ODBjOUD3s8aBxwK3tkdAsD42T BkdonzaW6IIdR3N6s5TBCUidpA8xssWqkLAuPaXr6YxVsk/3rmab0JsADj32NA+W6E SP1eRyfKeUqUHhl0IF4PnWXAaSANy8YL2uk8Q/F0gxo0s1eEKU8vy0s0mf0Zo52oC0 hv0rfaD8OJadmcvGoyA58CFwIbC/PGpBTGcQQ8gEL8wFmRkvVJda7ZbOdBC5EoS/Uv XYw0BGTHokVNr4COJ6DSrypnGl5dx5t1ACID6suihhiJl1HBsmmX+zlD/Eue0ybjmg k9soayfgulyQg== Received: by paulmck-ThinkPad-P17-Gen-1.home (Postfix, from userid 1000) id C4A54CE0F78; Thu, 12 Dec 2024 10:42:15 -0800 (PST) From: "Paul E. McKenney" To: rcu@vger.kernel.org Cc: linux-kernel@vger.kernel.org, kernel-team@meta.com, rostedt@goodmis.org, Frederic Weisbecker , kernel test robot , "Paul E . McKenney" Subject: [PATCH rcu 2/2] rcu/nocb: Fix rcuog wake-up from offline softirq Date: Thu, 12 Dec 2024 10:42:14 -0800 Message-Id: <20241212184214.2018411-2-paulmck@kernel.org> X-Mailer: git-send-email 2.40.1 In-Reply-To: References: Precedence: bulk X-Mailing-List: rcu@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Frederic Weisbecker After a CPU has set itself offline and before it eventually calls rcutree_report_cpu_dead(), there are still opportunities for callbacks to be enqueued, for example from an IRQ. When that happens on NOCB, the rcuog wake-up is deferred through an IPI to an online CPU in order not to call into the scheduler and risk arming the RT-bandwidth after hrtimers have been migrated out and disabled. But performing a synchronized IPI from an IRQ is buggy as reported in the following scenario: WARNING: CPU: 1 PID: 26 at kernel/smp.c:633 smp_call_function_single Modules linked in: rcutorture torture CPU: 1 UID: 0 PID: 26 Comm: migration/1 Not tainted 6.11.0-rc1-00012-g9139f93209d1 #1 Stopper: multi_cpu_stop+0x0/0x320 <- __stop_cpus+0xd0/0x120 RIP: 0010:smp_call_function_single swake_up_one_online __call_rcu_nocb_wake __call_rcu_common ? rcu_torture_one_read call_timer_fn __run_timers run_timer_softirq handle_softirqs irq_exit_rcu ? tick_handle_periodic sysvec_apic_timer_interrupt The periodic tick must be shutdown when the CPU is offline, just like is done for oneshot tick. This must be fixed but this is not enough: softirqs can happen on any hardirq tail and reproduce the above scenario. Fix this with introducing a special deferred rcuog wake up mode when the CPU is offline. This deferred wake up doesn't arm any timer and simply wait for rcu_report_cpu_dead() to be called in order to flush any pending rcuog wake up. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-lkp/202409231644.4c55582d-lkp@intel.com Fixes: 9139f93209d1 ("rcu/nocb: Fix RT throttling hrtimer armed from offline CPU") Signed-off-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- kernel/rcu/tree.h | 1 + kernel/rcu/tree_nocb.h | 14 ++++++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index a9a811d9d7a37..7ed060edd12b1 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -290,6 +290,7 @@ struct rcu_data { #define RCU_NOCB_WAKE_LAZY 2 #define RCU_NOCB_WAKE 3 #define RCU_NOCB_WAKE_FORCE 4 +#define RCU_NOCB_WAKE_OFFLINE 5 #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500)) /* For jiffies_till_first_fqs and */ diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 0923d60c5a338..78841346e1c13 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -295,6 +295,8 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, case RCU_NOCB_WAKE_FORCE: if (rdp_gp->nocb_defer_wakeup < RCU_NOCB_WAKE) mod_timer(&rdp_gp->nocb_timer, jiffies + 1); + fallthrough; + case RCU_NOCB_WAKE_OFFLINE: if (rdp_gp->nocb_defer_wakeup < waketype) WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); break; @@ -562,8 +564,16 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, lazy_len = READ_ONCE(rdp->lazy_len); if (was_alldone) { rdp->qlen_last_fqs_check = len; - // Only lazy CBs in bypass list - if (lazy_len && bypass_len == lazy_len) { + if (cpu_is_offline(rdp->cpu)) { + /* + * Offline CPUs can't call swake_up_one_online() from IRQs. Rely + * on the final deferred wake-up rcutree_report_cpu_dead() + */ + rcu_nocb_unlock(rdp); + wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_OFFLINE, + TPS("WakeEmptyIsDeferredOffline")); + } else if (lazy_len && bypass_len == lazy_len) { + // Only lazy CBs in bypass list rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY, TPS("WakeLazy"));