From nobody Sun Feb 8 18:31:07 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id CAFE7C7EE2F for ; Tue, 6 Jun 2023 08:55:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237328AbjFFIz6 (ORCPT ); Tue, 6 Jun 2023 04:55:58 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44670 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235325AbjFFIzt (ORCPT ); Tue, 6 Jun 2023 04:55:49 -0400 Received: from galois.linutronix.de (Galois.linutronix.de [193.142.43.55]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6C6B2E8 for ; Tue, 6 Jun 2023 01:55:48 -0700 (PDT) From: Sebastian Andrzej Siewior DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020; t=1686041747; 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=Cd+JUiL0ywRxwd2ZYcL8vrhCuZmD85iBs9FdcgWCwPc=; b=E2YAC+kTU9nvRfmyvFVDUWuloG/YvTpHJUW/MMkr8gGPtrs7xX7CR67odfyY3LR9gtvWQB D1TmXGOYD7Iw01LmMuieMr/YXK6HzSI4FbQjmN/U/zVdHj6FWLfYer8RR3G6y9se0nxRsc CWG/GL3QRq8Ex6zWyBrjihfWSsS271qsDhc3s4bS+u58zdB+B2t3+idIgVZ2yRereqOQrF WcDSLnJN/CJhKGtHHHNa73SBQ+/TNSZGODlsBb/ESeq9PE9v2h6k3vtR5IWn2KpYedkmQB TSWH+KI8fqXYPcj5AtLNsYV/2+iIsWgABbMAnIXonHeu+F2JKh/mLkqZu9gTnA== DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020e; t=1686041747; 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=Cd+JUiL0ywRxwd2ZYcL8vrhCuZmD85iBs9FdcgWCwPc=; b=WuR/aNAYTnmyD095A4LuzBzetucWJac5WMktFBXrvgD2zPHMbG6tgZbenLLOt2ptQSxHKf lm2X0eDM1jjzqbAA== To: linux-kernel@vger.kernel.org Cc: "Eric W. Biederman" , Oleg Nesterov , Peter Zijlstra , Thomas Gleixner , Sebastian Andrzej Siewior Subject: [PATCH REPOST 1/2] signal: Add proper comment about the preempt-disable in ptrace_stop(). Date: Tue, 6 Jun 2023 10:55:23 +0200 Message-Id: <20230606085524.2049961-2-bigeasy@linutronix.de> In-Reply-To: <20230606085524.2049961-1-bigeasy@linutronix.de> References: <20230606085524.2049961-1-bigeasy@linutronix.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Commit 53da1d9456fe7 ("fix ptrace slowness") added a preempt-disable section between read_unlock() and the following schedule() invocation without explaining why it is needed. Replace the comment with an explanation why this is needed. Clarify that it is needed for correctness but for performance reasons. Signed-off-by: Sebastian Andrzej Siewior Acked-by: Oleg Nesterov --- kernel/signal.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index 2547fa73bde51..da017a5461163 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2313,10 +2313,21 @@ static int ptrace_stop(int exit_code, int why, unsi= gned long message, do_notify_parent_cldstop(current, false, why); =20 /* - * Don't want to allow preemption here, because - * sys_ptrace() needs this task to be inactive. + * The previous do_notify_parent_cldstop() invocation woke ptracer. + * One a PREEMPTION kernel this can result in preemption requirement + * which will be fulfilled after read_unlock() and the ptracer will be + * put on the CPU. + * The ptracer is in wait_task_inactive(, __TASK_TRACED) waiting for + * this task wait in schedule(). If this task gets preempted then it + * remains enqueued on the runqueue. The ptracer will observe this and + * then sleep for a delay of one HZ tick. In the meantime this task + * gets scheduled, enters schedule() and will wait for the ptracer. * - * XXX: implement read_unlock_no_resched(). + * This preemption point is not bad from correctness point of view but + * extends the runtime by one HZ tick time due to the ptracer's sleep. + * The preempt-disable section ensures that there will be no preemption + * between unlock and schedule() and so improving the performance since + * the ptracer has no reason to sleep. */ preempt_disable(); read_unlock(&tasklist_lock); --=20 2.40.1 From nobody Sun Feb 8 18:31:07 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 23585C77B73 for ; Tue, 6 Jun 2023 08:56:04 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237334AbjFFI4C (ORCPT ); Tue, 6 Jun 2023 04:56:02 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:44672 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236627AbjFFIzu (ORCPT ); Tue, 6 Jun 2023 04:55:50 -0400 Received: from galois.linutronix.de (Galois.linutronix.de [IPv6:2a0a:51c0:0:12e:550::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9E46EEA for ; Tue, 6 Jun 2023 01:55:48 -0700 (PDT) From: Sebastian Andrzej Siewior DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020; t=1686041747; 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=FExOD5E8HJtGy/lm1D7DIYTsTEtzFIwKcZPbLrNzZPE=; b=tftlDy4XknmZgpUOkAK9spHUoXUymEYXhvGp8Mi84sBJhmSus1Q2hCVNc+glOyG0RkYJ4q XjMNM6qo0PSUnDMmWBHEdLb2BUYrAJCRwDEWe122xr8ft93TorEyGBfvd0TY5vqT7NrqvL QTDZiaysFVl/+k8vQwJzwTaE7dQPfFbB7FTkA1NMfxhvzdVA4rGyJVp0Yk0E/d9l08h5X5 Ptlb7RCUo4TiCcrEfmGI59m2HEjZql4d/8zUKlclohrDD1T9S2C7ki/RgNGvqYfcFYy6oG dJFHFGeqprFB5EfAdGTV468f2zKp7jZJMgheWy6523CHjQJDn+ZYq9NkLmYvCQ== DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=linutronix.de; s=2020e; t=1686041747; 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=FExOD5E8HJtGy/lm1D7DIYTsTEtzFIwKcZPbLrNzZPE=; b=Qgdn5lAt6sr9Rgf+wlV5JethHHVroIcnnXwYK0rSnbfsrdjqYsviPU0ZyubGn58uCDQasW NKwkTEQplbPP0fAQ== To: linux-kernel@vger.kernel.org Cc: "Eric W. Biederman" , Oleg Nesterov , Peter Zijlstra , Thomas Gleixner , Sebastian Andrzej Siewior Subject: [PATCH REPOST 2/2] signal: Don't disable preemption in ptrace_stop() on PREEMPT_RT. Date: Tue, 6 Jun 2023 10:55:24 +0200 Message-Id: <20230606085524.2049961-3-bigeasy@linutronix.de> In-Reply-To: <20230606085524.2049961-1-bigeasy@linutronix.de> References: <20230606085524.2049961-1-bigeasy@linutronix.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" On PREEMPT_RT keeping preemption disabled during the invocation of cgroup_enter_frozen() is a problem because the function acquires css_set_lo= ck which is a sleeping lock on PREEMPT_RT and must not be acquired with disabl= ed preemption. The preempt-disabled section is only for performance optimisation reasons and can be avoided. Extend the comment and don't disable preemption before scheduling on PREEMPT_RT. Signed-off-by: Sebastian Andrzej Siewior --- kernel/signal.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/signal.c b/kernel/signal.c index da017a5461163..9e07b3075c72e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2328,11 +2328,16 @@ static int ptrace_stop(int exit_code, int why, unsi= gned long message, * The preempt-disable section ensures that there will be no preemption * between unlock and schedule() and so improving the performance since * the ptracer has no reason to sleep. + * + * This optimisation is not doable on PREEMPT_RT due to the spinlock_t + * within the preempt-disable section. */ - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); read_unlock(&tasklist_lock); cgroup_enter_frozen(); - preempt_enable_no_resched(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable_no_resched(); schedule(); cgroup_leave_frozen(true); =20 --=20 2.40.1