From nobody Sat Nov 30 12:30:29 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 4BA1A13B2B0; 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=FAI/Qod+cyisxosoHZy6qf2JJwgxrCpvbaD/4QKRNjKlUwbhciO97dvZcBKxcvCgTOoG+e9KOIH6XUf6frcrOWS08ElTYepLjYhR7HL5BCBF2W5tpW2RieV/qFnRtV5s8SmcNzV45eyGrDk6DFHnTamA6LYD8QBKwjD2SmmBNcQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1725913039; c=relaxed/simple; bh=L37e79fW1nnCbz9UeSvSJbvkQXXomU2axg08VtYxoxM=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=L7OCzeOTinDn12yAnUs1peqJ3qXyG5WMIoW/gehFjNxV0Gli0vHe2PTkLYjOGkqapZSC+N+iOG7cT1+jtn7BrAuwFgn/VygSYKCH+n/sYf5oRIFtSs7rzvGFqnp/oZIbZoB4LoPBJNcAuFfAYdFcAYuCqVXCtk/LKhwPdRdw+zw= 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=jKHrHzdw; 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="jKHrHzdw" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=efficios.com; s=smtpout1; t=1725913036; bh=L37e79fW1nnCbz9UeSvSJbvkQXXomU2axg08VtYxoxM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=jKHrHzdwGa3ovEllgxT42j052GD5O3KKyIdpKwu9v5VjrJ1R4hXwzsoQ4EgAzmWEv JlUHBiR9Vf22xx7w1o/KaN6FMo9QPOKXEVasYZLtB/SHFKJxgsJpGGxtbQY52T7PK0 Nas6395QhbGqu+bCjaqMW35sZXRhRsIrAFI+kOcaj0hjDDaA5f4TSfdDWDltPgk7oU excMBgg17dytQXt/jayw4ejiXWMPpkNN+RsCsIFtzBrTf4opPeTiN+nDUvY5HzifGN y2GXN4bqpffPOxzr9gpWrQYzj9HmuHEPoicNosB2ZmV969aXfAQFtzsnyXudc/hziT NPl8Z1r8x55ZQ== 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 4X2dRH6VQCz1Ksw; Mon, 9 Sep 2024 16:17:15 -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 2/8] tracing/ftrace: guard syscall probe with preempt_notrace Date: Mon, 9 Sep 2024 16:16:46 -0400 Message-Id: <20240909201652.319406-3-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 ftrace can handle this change by explicitly disabling preemption within the ftrace system call tracepoint probes to respect the current expectations within ftrace ring buffer code. This change does not yet allow ftrace 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 Acked-by: Masami Hiramatsu (Google) --- include/trace/trace_events.h | 38 ++++++++++++++++++++++++++++------- kernel/trace/trace_syscalls.c | 12 +++++++++++ 2 files changed, 43 insertions(+), 7 deletions(-) diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h index 8bcbb9ee44de..0228d9ed94a3 100644 --- a/include/trace/trace_events.h +++ b/include/trace/trace_events.h @@ -263,6 +263,9 @@ static struct trace_event_fields trace_event_fields_##c= all[] =3D { \ tstruct \ {} }; =20 +#undef DECLARE_EVENT_SYSCALL_CLASS +#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS + #undef DEFINE_EVENT_PRINT #define DEFINE_EVENT_PRINT(template, name, proto, args, print) =20 @@ -396,11 +399,11 @@ static inline notrace int trace_event_get_offsets_##c= all( \ =20 #include "stages/stage6_event_callback.h" =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 \ -trace_event_raw_event_##call(void *__data, proto) \ +do_trace_event_raw_event_##call(void *__data, proto) \ { \ struct trace_event_file *trace_file =3D __data; \ struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\ @@ -425,15 +428,34 @@ trace_event_raw_event_##call(void *__data, proto) \ \ trace_event_buffer_commit(&fbuffer); \ } + +#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 \ +trace_event_raw_event_##call(void *__data, proto) \ +{ \ + do_trace_event_raw_event_##call(__data, args); \ +} + +#undef DECLARE_EVENT_SYSCALL_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 \ +trace_event_raw_event_##call(void *__data, proto) \ +{ \ + guard(preempt_notrace)(); \ + do_trace_event_raw_event_##call(__data, args); \ +} + /* * The ftrace_test_probe is compiled out, it is only here as a build time = check * to make sure that if the tracepoint handling changes, the ftrace probe = will * fail to compile unless it too is updated. */ =20 -#undef DECLARE_EVENT_SYSCALL_CLASS -#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS - #undef DEFINE_EVENT #define DEFINE_EVENT(template, call, proto, args) \ static inline void ftrace_test_probe_##call(void) \ @@ -443,6 +465,8 @@ static inline void ftrace_test_probe_##call(void) \ =20 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE) =20 +#undef __DECLARE_EVENT_CLASS + #include "stages/stage7_class_define.h" =20 #undef DECLARE_EVENT_CLASS diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 067f8e2b930f..abf0e0b7cd0b 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -299,6 +299,12 @@ static void ftrace_syscall_enter(void *data, struct pt= _regs *regs, long id) int syscall_nr; 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; @@ -338,6 +344,12 @@ static void ftrace_syscall_exit(void *data, struct pt_= regs *regs, long ret) struct trace_event_buffer fbuffer; int syscall_nr; =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