From patchwork Mon Oct 7 11:35:37 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jeff Xie X-Patchwork-Id: 13824491 Received: from out-186.mta1.migadu.com (out-186.mta1.migadu.com [95.215.58.186]) (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 AAE8A1CACC0 for ; Mon, 7 Oct 2024 11:36:13 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.186 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728300976; cv=none; b=lf0AwUOaP9rhJSiWQ7Etc+1ddQZ/xD6K1hOE9wsG45BJSbAvTduhjSls9B6zIksln0QJBT3/lBPwNHEA224WKURfuybVU+3UBC9DtPjHfq+7odyuweY3NS1k5eZDqEJd9neXI8O1VK28ETLGR99Si7tuXxbAaNEQXqZjrXODANU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1728300976; c=relaxed/simple; bh=P5BPFG8e5ClLH2i6KDp+sSNB6btkuosh3rUzkEErfp8=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=uUvukFfGUVaS0lbmevwkwlRSyYz4nL6t3E+sxvpHOHo0N0B6yGpDwCAivNN0MOv2CxIB6cbDfI1TW2LBADpy/frgoFTn5NK/bkAYXPWyMEqUI+yo96VLLn2xzwmAPi3dai/qr7hx7hepd10Gvbuw9LFB+cb7E5FUD1gEd7fjK6c= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=RYLwNgCB; arc=none smtp.client-ip=95.215.58.186 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="RYLwNgCB" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1728300971; 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; bh=qzZxe9R4Jas3GMKD/rY0M+GDfcweX2HMw86N1Uklvi0=; b=RYLwNgCBMYrdaoidtO0jhIscDgC6nY1KmcddhnIpfslmjqcOMFg0+jfGPluMuCqXZBxuuB Jys7R6acf65s5/fHhvEN4dGloNGqpFLqpc3Ywa8sB84fYpNJY8956oB+vfWFRQ7mLPn5bj RaxOBUz425FwjOP6c0TS5r9sd2XXEBI= From: Jeff Xie To: rostedt@goodmis.org, mhiramat@kernel.org Cc: mathieu.desnoyers@efficios.com, linux-trace-kernel@vger.kernel.org, linux-kernel@vger.kernel.org, xiehuan09@gmail.com, dolinux.peng@gmail.com, chensong_2000@189.cn, Jeff Xie Subject: [PATCH v4] ftrace: Get the true parent ip for function tracer Date: Mon, 7 Oct 2024 19:35:37 +0800 Message-ID: <20241007113537.19686-1-jeff.xie@linux.dev> Precedence: bulk X-Mailing-List: linux-trace-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Migadu-Flow: FLOW_OUT When using both function tracer and function graph simultaneously, it is found that function tracer sometimes captures a fake parent ip (return_to_handler) instead of the true parent ip. This issue is easy to reproduce. Below are my reproduction steps: jeff-labs:~/bin # ./trace-net.sh jeff-labs:~/bin # cat /sys/kernel/debug/tracing/instances/foo/trace | grep return_to_handler trace-net.sh-405 [001] ...2. 31.859501: avc_has_perm+0x4/0x190 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859503: simple_setattr+0x4/0x70 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859503: truncate_pagecache+0x4/0x60 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...2. 31.859505: unmap_mapping_range+0x4/0x140 <-return_to_handler+0x0/0x40 trace-net.sh-405 [001] ...3. 31.859508: _raw_spin_unlock+0x4/0x30 <-return_to_handler+0x0/0x40 [...] The following is my simple trace script: jeff-labs:~/bin # cat ./trace-net.sh TRACE_PATH="/sys/kernel/debug/tracing" set_events() { echo 1 > $1/events/net/enable echo 1 > $1/events/tcp/enable echo 1 > $1/events/sock/enable echo 1 > $1/events/napi/enable echo 1 > $1/events/fib/enable echo 1 > $1/events/neigh/enable } set_events ${TRACE_PATH} echo 1 > ${TRACE_PATH}/options/sym-offset echo 1 > ${TRACE_PATH}/options/funcgraph-tail echo 1 > ${TRACE_PATH}/options/funcgraph-proc echo 1 > ${TRACE_PATH}/options/funcgraph-abstime echo 'tcp_orphan*' > ${TRACE_PATH}/set_ftrace_notrace echo function_graph > ${TRACE_PATH}/current_tracer INSTANCE_FOO=${TRACE_PATH}/instances/foo if [ ! -e $INSTANCE_FOO ]; then mkdir ${INSTANCE_FOO} fi set_events ${INSTANCE_FOO} echo 1 > ${INSTANCE_FOO}/options/sym-offset echo 'tcp_orphan*' > ${INSTANCE_FOO}/set_ftrace_notrace echo function > ${INSTANCE_FOO}/current_tracer echo 1 > ${TRACE_PATH}/tracing_on echo 1 > ${INSTANCE_FOO}/tracing_on echo > ${TRACE_PATH}/trace echo > ${INSTANCE_FOO}/trace Signed-off-by: Jeff Xie Acked-by: Masami Hiramatsu (Google) --- v4: https://lore.kernel.org/linux-trace-kernel/20241005101320.766c1100@rorschach.local.home/ - fixed the crash when accessing the "current" if the arch has not implemented noinstr thanks steve for the testing and the detailed explanation v3: https://lore.kernel.org/linux-trace-kernel/20240910001326.87f27e6b312f1d956cf352a2@kernel.org/ - fixed build error when CONFIG_FUNCTION_GRAPH_TRACER=n suggested by Masami v2: https://lore.kernel.org/linux-trace-kernel/20240821095910.1888d7fa@gandalf.local.home/ - Adding __always_inline to function_get_true_parent_ip suggested by Steve kernel/trace/trace_functions.c | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 3b0cea37e029..46b663d22c37 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -176,6 +176,27 @@ static void function_trace_start(struct trace_array *tr) tracing_reset_online_cpus(&tr->array_buffer); } +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_ARCH_WANTS_NO_INSTR) +static __always_inline unsigned long +function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) +{ + unsigned long true_parent_ip; + int idx = 0; + + true_parent_ip = parent_ip; + if (unlikely(parent_ip == (unsigned long)&return_to_handler)) + true_parent_ip = ftrace_graph_ret_addr(current, &idx, parent_ip, + (unsigned long *)fregs->regs.sp); + return true_parent_ip; +} +#else +static __always_inline unsigned long +function_get_true_parent_ip(unsigned long parent_ip, struct ftrace_regs *fregs) +{ + return parent_ip; +} +#endif + static void function_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) @@ -193,6 +214,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; + parent_ip = function_get_true_parent_ip(parent_ip, fregs); + trace_ctx = tracing_gen_ctx(); cpu = smp_processor_id(); @@ -241,6 +264,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, * recursive protection is performed. */ local_irq_save(flags); + parent_ip = function_get_true_parent_ip(parent_ip, fregs); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); @@ -309,6 +333,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; + parent_ip = function_get_true_parent_ip(parent_ip, fregs); cpu = smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); if (atomic_read(&data->disabled)) @@ -356,6 +381,7 @@ function_stack_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, * recursive protection is performed. */ local_irq_save(flags); + parent_ip = function_get_true_parent_ip(parent_ip, fregs); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled);