From nobody Sat Nov 30 12:37:47 2024 Received: from smtpout.efficios.com (smtpout.efficios.com [167.114.26.122]) (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 9CDF416EB55; Mon, 9 Sep 2024 20:17:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=167.114.26.122 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1725913039; cv=none; b=PhU8F8xW0IRmwCqUjCF4NVBVvmpXOyMQoC0rwxkrq9sNrbMIcC09IH3UVqoIBMTa0JMtLUVJaqogYKCMBZ70DQxRaWyTPCrmLCDHRBFqWS2N9B4u74GZVuKuQXo1n/aq1TDwbWzAZWWDAxfdIP+lgUkAb3AY+VusF2MOCswIjWQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1725913039; c=relaxed/simple; bh=MWuMSBa0wltjyl8Q6xHGNS8TrHMMgd8rkPqmN7QbQzs=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=sRpt3sy1btPMj6z/vzBBvPVCT9KwrtG7ra5tSjYGuHwCHP/Pu4i6egj7VJe3EIKsh582rJh0Az65bNvCPgRhb9XPLcXJe86JinTCml9huiQB7k2f60WTYbcxN27zUyeDaCiZicl256mGFygtSoQSm2ZJFfLPl+PJkTKxYiOEKpo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=efficios.com; spf=pass smtp.mailfrom=efficios.com; dkim=pass (2048-bit key) header.d=efficios.com header.i=@efficios.com header.b=tgLXp5RN; arc=none smtp.client-ip=167.114.26.122 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=efficios.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=efficios.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=efficios.com header.i=@efficios.com header.b="tgLXp5RN" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=efficios.com; s=smtpout1; t=1725913036; bh=MWuMSBa0wltjyl8Q6xHGNS8TrHMMgd8rkPqmN7QbQzs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=tgLXp5RN8e3oKPyxKcUJVJvn95spYGTjLaPySxOBYjhob2svcxRQW7QbugmeXVMI0 tY2YTPeZrUNAsIoHgLjaNxjcot4xAupYjTuCN+JDYLNaPn7eXod2HZVGIfB8yW8oe8 4oMmbWBLWqxRip/JWoqRjwjEIxnz3IFZgTlf1NPczi88jcXSEstP/lu921OfJRz6hR S4QCvJA6I3XCBVCZa0t2zVFG3270S/nRMbNq0UBPLuuGUSzEau6fCmxbGi//RTFItR wg+d+EQ0su8EWmc6vZI6vI6faqcksE4vIubfYoCDKlIduT2aTnN4JqKVxwUJtwjmwY LpoIEMx+P/Y2w== Received: from thinkos.internal.efficios.com (96-127-217-162.qc.cable.ebox.net [96.127.217.162]) by smtpout.efficios.com (Postfix) with ESMTPSA id 4X2dRJ23Pbz1KQX; Mon, 9 Sep 2024 16:17:16 -0400 (EDT) From: Mathieu Desnoyers To: Steven Rostedt , Masami Hiramatsu Cc: linux-kernel@vger.kernel.org, Mathieu Desnoyers , Peter Zijlstra , Alexei Starovoitov , Yonghong Song , "Paul E . McKenney" , Ingo Molnar , Arnaldo Carvalho de Melo , Mark Rutland , Alexander Shishkin , Namhyung Kim , Andrii Nakryiko , bpf@vger.kernel.org, Joel Fernandes , linux-trace-kernel@vger.kernel.org, Michael Jeanson Subject: [PATCH 3/8] tracing/perf: guard syscall probe with preempt_notrace Date: Mon, 9 Sep 2024 16:16:47 -0400 Message-Id: <20240909201652.319406-4-mathieu.desnoyers@efficios.com> X-Mailer: git-send-email 2.39.2 In-Reply-To: <20240909201652.319406-1-mathieu.desnoyers@efficios.com> References: <20240909201652.319406-1-mathieu.desnoyers@efficios.com> Precedence: bulk X-Mailing-List: linux-kernel@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" In preparation for allowing system call enter/exit instrumentation to handle page faults, make sure that perf can handle this change by explicitly disabling preemption within the perf system call tracepoint probes to respect the current expectations within perf ring buffer code. This change does not yet allow perf to take page faults per se within its probe, but allows its existing probes to adapt to the upcoming change. Signed-off-by: Mathieu Desnoyers Cc: Michael Jeanson Cc: Steven Rostedt Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Alexei Starovoitov Cc: Yonghong Song Cc: Paul E. McKenney Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Namhyung Kim Cc: Andrii Nakryiko Cc: bpf@vger.kernel.org Cc: Joel Fernandes --- include/trace/perf.h | 41 +++++++++++++++++++++++++++++++---- kernel/trace/trace_syscalls.c | 12 ++++++++++ 2 files changed, 49 insertions(+), 4 deletions(-) diff --git a/include/trace/perf.h b/include/trace/perf.h index ded997af481e..5650c1bad088 100644 --- a/include/trace/perf.h +++ b/include/trace/perf.h @@ -12,10 +12,10 @@ #undef __perf_task #define __perf_task(t) (__task =3D (t)) =20 -#undef DECLARE_EVENT_CLASS -#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +#undef __DECLARE_EVENT_CLASS +#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ static notrace void \ -perf_trace_##call(void *__data, proto) \ +do_perf_trace_##call(void *__data, proto) \ { \ struct trace_event_call *event_call =3D __data; \ struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\ @@ -55,8 +55,38 @@ perf_trace_##call(void *__data, proto) \ head, __task); \ } =20 +/* + * Define unused __count and __task variables to use @args to pass + * arguments to do_perf_trace_##call. This is needed because the + * macros __perf_count and __perf_task introduce the side-effect to + * store copies into those local variables. + */ +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +perf_trace_##call(void *__data, proto) \ +{ \ + u64 __count __attribute__((unused)); \ + struct task_struct *__task __attribute__((unused)); \ + \ + do_perf_trace_##call(__data, args); \ +} + #undef DECLARE_EVENT_SYSCALL_CLASS -#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, pr= int) \ +__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \ + PARAMS(assign), PARAMS(print)) \ +static notrace void \ +perf_trace_##call(void *__data, proto) \ +{ \ + u64 __count __attribute__((unused)); \ + struct task_struct *__task __attribute__((unused)); \ + \ + guard(preempt_notrace)(); \ + do_perf_trace_##call(__data, args); \ +} =20 /* * This part is compiled out, it is only here as a build time check @@ -76,4 +106,7 @@ static inline void perf_test_probe_##call(void) \ DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args)) =20 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) + +#undef __DECLARE_EVENT_CLASS + #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index abf0e0b7cd0b..a3d8ac00793e 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -594,6 +594,12 @@ static void perf_syscall_enter(void *ignore, struct pt= _regs *regs, long id) int rctx; int size; =20 + /* + * Syscall probe called with preemption enabled, but the ring + * buffer and per-cpu data require preemption to be disabled. + */ + guard(preempt_notrace)(); + syscall_nr =3D trace_get_syscall_nr(current, regs); if (syscall_nr < 0 || syscall_nr >=3D NR_syscalls) return; @@ -694,6 +700,12 @@ static void perf_syscall_exit(void *ignore, struct pt_= regs *regs, long ret) int rctx; int size; =20 + /* + * Syscall probe called with preemption enabled, but the ring + * buffer and per-cpu data require preemption to be disabled. + */ + guard(preempt_notrace)(); + syscall_nr =3D trace_get_syscall_nr(current, regs); if (syscall_nr < 0 || syscall_nr >=3D NR_syscalls) return; --=20 2.39.2