From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-oi2-f13.google.com (mail-oi2-f13.google.com [74.125.231.205]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3289C345EA7 for ; Sat, 12 Sep 2026 17:18:52 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.231.205 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789233534; cv=none; b=e6+o7NPGV9TPsjRfCbh4DSnWdUAIqOcxsGU4PW2jUTlp/FZpC7JwZXn0UuMUa1P0+rqBblhETIs1O5vv73lLcq8Elg25MJym6Q66oRZnB0AzL0VYWZLhHe97qtN59egcYvXrS6z+Ea926PO7EPRWizt3bGIx4qREyJ5Mf8InPuQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789233534; c=relaxed/simple; bh=jBtZBjDlT8Qi3VYpNIp72jmf1UAXzlM9TkhK/45vnWc=; h=Mime-Version:Content-Type:Date:Message-Id:Cc:Subject:From:To: References:In-Reply-To; b=UYZ3pNaVDiJbtre7wFqrGpdwTChl0Ciz6vaBLZBIN5e7we0/xM+WqQCcFGKawibNPhCELnVvXJH75FzVXnNQZvEAjvLIzLJmeSYHCYlpBsPOF81/6IQb1yG9khKgZMBzLLyEAFWpMYwCQDL3seml/G5y9oCg2bhF6ahKtgXLcvI= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=LLufjg9t; arc=none smtp.client-ip=74.125.231.205 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="LLufjg9t" Received: by mail-oi2-f13.google.com with SMTP id 5614622812f47-4b37a3ed714so388035b6e.0 for ; Sat, 12 Sep 2026 10:18:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1789233531; x=1789838331; darn=vger.kernel.org; h=in-reply-to:references:to:from:subject:cc:message-id:date :content-type:content-transfer-encoding:mime-version:from:to:cc :subject:date:message-id:reply-to:content-type; bh=M1c6suOtzZ2rRuH1TXxQJyOcddxpg3oryXf9dCc4tZI=; b=LLufjg9tkDHfboL43zM8EhB8/3TC5sqvSGrfLsnHpXY5oKIZhyLB12Mpf/1tRBn0Qt aUTmkwDr6K1fXlg42wE3St71lnXgY16DGhmZZsHQvWDX2pFVJrt5xBash1IGri8ujw+K Dos33rufshNrGVyoXmhoAMIEpr8fIqzOJFk56h7oRwrJuSCYgqjWRXrzK1ZwBBeWgsiL mr9G3buIXNvAzpRm2IDzqETuhVXtEVWc5aDnZYcYd8lkAR3CX8wWFuJv8SBGHhH90wdt z0lgJu+7pvtMQKcaKQ+3nUEpjKi4ykmWxRmG4eJoqROjAOq8cGeK8F7PH7wAPuFFmXFw 9uoQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1789233531; x=1789838331; h=in-reply-to:references:to:from:subject:cc:message-id:date :content-type:content-transfer-encoding:mime-version:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=M1c6suOtzZ2rRuH1TXxQJyOcddxpg3oryXf9dCc4tZI=; b=HdAVa+F7fthc6B5eXnCf+MTjhZLx6cnCaWN/0ylUyx96iTOVNaYNPUAt6glMfobY0/ zSvpHQ/RonjNW0nQQiuYStjWB3TIxpU+2hLVyWne0mGpAwcvMzjn5bHPu31/CM6W5Dv9 zk+sdTqPsW+kj4j1jXa/bXTq2SiULvh5oR5IpK57IbKRMhH9j7ZVV/shjVuPYsXoM7WX uxZYcx8pi0YE8SJDbFyT4uz5zbsG4mChVx1zoASfGm+dAZkrvUDiuGpEf+U4DHDLtVUG TGGBEk4qyK7e6RyRu4+UmY/2n89+F5WRSy0iTgFwTVOItjE/6zW/5JxyEiQfuoQGxAz+ 9HcQ== X-Forwarded-Encrypted: i=1; AKwUvBwM5HNN9XNW6pvNxlH5vX61ZiWTVtuWzQa8d7Av959vmeC1CR9rEad92Pl7RzTFNF1Y+OM=@vger.kernel.org X-Gm-Message-State: AFuF++nP0WmYlmVz0guBaQUK4K8ZE1NZEdlPYMj0vN/DFG4ik+QblmXO nxD5Njn82Cd8EAR9ed4pWryq+fsomyA620avOOMhXydCJyXGOgaizeQf X-Gm-Gg: AYBFou3EcoizeE5Y/LFTEhQJ3NprLz4Big41FNriSF/mSIMxFQLqlxD2DlGHbHcjfPq 6p1mvy7nNvcwpeuUmnGqjJUsA8pAoMiKRadaE6tEmrrPhOOoyZHEX0aIHrT+BV/9tI5MA2YrV2U gZ4U+SS9wDDnL7Ia5Y47+OFsPwtbzUSYiAHy+niiG2OzB+rrPlcYLLQtmAcS1fDCZY9m2otEP8E gBfrFr+yGFLla5CpbxWx+Nw96VEAs4xpa1v/71+U23Lgujygm2s5UxeC8GXuaG1vqv2U1dwXfZA +UrIhveizHTNWkVoHv0n9VMJ+cfQfDeBWQ1B0zXYJfALxa8qO4txGslxXH08mTvjsAfKCLgcZXC M0P24gF+hrTwPu3jZj8kYuXCN++awW7p3CpsNzhUX/DWtLHqLf5ahKr1OI/x8cAL34Lo7NxCSPP NT2yDJwSN3ACcylf8ACjC36t5kIqEvme8GBWEvfX4aWkGieEenSWfLawNLBWrssO9m/hlpeHiSi +pi3UT7zS749kByoI/YH7aQEl364pkwRlKvHcGbpUi5+F/2s5vcJ3NdfcffnR8+OA== X-Received: by 2002:a05:6808:3503:b0:4b3:8323:8cd8 with SMTP id 5614622812f47-4c4a751294bmr2617971b6e.5.1789233530981; Sat, 12 Sep 2026 10:18:50 -0700 (PDT) Received: from localhost ([2a03:2880:10ff:72::]) by smtp.gmail.com with ESMTPSA id 5614622812f47-4c3315b19afsm5495263b6e.10.2026.09.12.10.18.48 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Sat, 12 Sep 2026 10:18:49 -0700 (PDT) Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=UTF-8 Date: Sat, 12 Sep 2026 10:18:48 -0700 Message-Id: Cc: "Josef Bacik" , "Frederic Weisbecker" , "Neeraj Upadhyay" , "Joel Fernandes" , "Boqun Feng" , "Thomas Gleixner" , "Peter Zijlstra" , "Steven Rostedt" , "Masami Hiramatsu" , "Mark Rutland" , "Jiri Olsa" , "Alexei Starovoitov" , "Daniel Borkmann" , "Andrii Nakryiko" , , "Catalin Marinas" , "Will Deacon" , "Puranjay Mohan" , "Xu Kuohai" , "Andy Lutomirski" , "Josh Triplett" , "Uladzislau Rezki" , "Mathieu Desnoyers" , "Lai Jiangshan" , "Zqiang" , "Juergen Gross" , "Luis Chamberlain" , "Ihor Solodrai" , , , , , , Subject: Re: [PATCH RFC v2 08/15] bpf, x86: Maintain Tasks RCU trampoline nesting in the BPF trampoline From: "Alexei Starovoitov" To: X-Mailer: aerc References: <20260911-b4-rcu-tasks-preempt-qs-v2-0-eaaa61ed2da4@toxicpanda.com> <20260911-b4-rcu-tasks-preempt-qs-v2-8-eaaa61ed2da4@toxicpanda.com> <14cb8a91-497d-49f5-aa20-c6cb8b9a27fc@paulmck-laptop> In-Reply-To: <14cb8a91-497d-49f5-aa20-c6cb8b9a27fc@paulmck-laptop> On Fri Sep 11, 2026 at 10:10 PM PDT, Paul E. McKenney wrote: > On Fri, Sep 11, 2026 at 08:27:56PM -0700, Alexei Starovoitov wrote: >> On Fri Sep 11, 2026 at 7:08 AM PDT, Josef Bacik wrote: >> > Emit an increment of current->rcu_tramp_nesting once the trampoline's >> > frame is set up and a decrement before the final register restore, so >> > that a task preempted while running fentry/fexit/fmod_ret/LSM programs >> > or the __bpf_tramp_enter()/__bpf_tramp_exit() glue is not treated as >> > Tasks-RCU quiescent. Drop the count around the call to the original >> > function: that may run arbitrarily long without sleeping and must not = pin >> > a Tasks RCU grace period, and the trampoline frame above it is held by >> > im->pcref rather than by Tasks RCU (see bpf_tramp_image_put()). The >> > fmod_ret early-exit branch and the ip_after_call -> ip_epilogue poke b= oth >> > skip the decrement/increment pair around the original call, so the cou= nt >> > stays balanced on every path. >> > >> > The sequence is "mov r11, gs:[current_task]; inc/dec dword [r11 + off]= "; >> > r11 is scratch at every emission point and (u32)¤t_task is a val= id >> > sign-extended %gs-absolute with the current per-CPU layout, the same f= orm >> > the JIT already uses for this_cpu_off. The image is dynamically >> > allocated text, so the instructions outside the bracketed region are >> > covered by the irq-exit IP check. >> > >> > Assisted-by: LLM >> > Signed-off-by: Josef Bacik >> > --- >> > arch/x86/net/bpf_jit_comp.c | 43 ++++++++++++++++++++++++++++++++++++= +++++++ >> > 1 file changed, 43 insertions(+) >> > >> > diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c >> > index 2853e87797a7..a375c1b7bd50 100644 >> > --- a/arch/x86/net/bpf_jit_comp.c >> > +++ b/arch/x86/net/bpf_jit_comp.c >> > @@ -722,6 +722,31 @@ static void emit_indirect_jump(u8 **pprog, int bp= f_reg, u8 *ip) >> > *pprog =3D prog; >> > } >> > =20 >> > +/* >> > + * Tasks RCU trampoline nesting, see rcu_tasks_trampoline_enter(). >> > + * >> > + * mov r11, QWORD PTR gs:[current_task] >> > + * inc/dec DWORD PTR [r11 + offsetof(struct task_struct, rcu_tramp_= nesting)] >> > + * >> > + * r11 (AUX_REG) is scratch in the trampoline at every point this is = emitted. >> > + */ >> > +static void emit_rcu_tasks_tramp_nesting(u8 **pprog, bool enter) >> > +{ >> > +#ifdef CONFIG_TASKS_RCU >> > + u8 *prog =3D *pprog; >> > + >> > + /* mov r11, gs:[abs32] */ >> > + EMIT2(0x65, 0x4C); >> > + EMIT3(0x8B, 0x1C, 0x25); >> > + EMIT((u32)(unsigned long)¤t_task, 4); >> > + /* inc/dec dword ptr [r11 + disp32] */ >> > + EMIT3(0x41, 0xFF, enter ? 0x83 : 0x8B); >> > + EMIT(offsetof(struct task_struct, rcu_tramp_nesting), 4); >> > + >> > + *pprog =3D prog; >> > +#endif >>=20 >> It's not a lot of overhead, but I feel it will be the death by thousand = cuts. >> rcu_read_lock_trace() in bpf_prog_enter_sleepable is doing the same thin= g... >> increamenting a variable inside current. >> Can they be combined? Like treat current->trc_reader_nesting > 0 as >> current->rcu_tramp_nesting > 0 ? >> Or replace one with the other? >> Two current->foo++ operations look redundant. >>=20 >> bpf trampoline is already quite heavy. I'd like to find ways to reduce >> its overhead instead of adding more. > > Replace rcu_read_lock_trace() with Josef's rcu_tasks_trampoline_enter)? If necessary... what I don't understand why we need another rcu_tasks_trampoline_enter-like= counter. Can existing rcu_read_lock_trace() current be used ? It's already doing current->trc_reader_nesting++ so use that as a signal ?