From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751925AbcFNLcR (ORCPT ); Tue, 14 Jun 2016 07:32:17 -0400 Received: from terminus.zytor.com ([198.137.202.10]:34366 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750808AbcFNLcN (ORCPT ); Tue, 14 Jun 2016 07:32:13 -0400 Date: Tue, 14 Jun 2016 04:31:07 -0700 From: tip-bot for Masami Hiramatsu Message-ID: Cc: luto@kernel.org, ananth@linux.vnet.ibm.com, linux-kernel@vger.kernel.org, brgerst@gmail.com, acme@redhat.com, mingo@kernel.org, bp@alien8.de, peterz@infradead.org, eranian@google.com, alexander.shishkin@linux.intel.com, dvlasenk@redhat.com, tglx@linutronix.de, vincent.weaver@maine.edu, hpa@zytor.com, jolsa@redhat.com, torvalds@linux-foundation.org, mhiramat@kernel.org, rostedt@goodmis.org Reply-To: linux-kernel@vger.kernel.org, ananth@linux.vnet.ibm.com, luto@kernel.org, acme@redhat.com, brgerst@gmail.com, dvlasenk@redhat.com, peterz@infradead.org, eranian@google.com, alexander.shishkin@linux.intel.com, mingo@kernel.org, bp@alien8.de, rostedt@goodmis.org, mhiramat@kernel.org, torvalds@linux-foundation.org, hpa@zytor.com, vincent.weaver@maine.edu, jolsa@redhat.com, tglx@linutronix.de In-Reply-To: <20160611140648.25885.37482.stgit@devbox> References: <20160611140648.25885.37482.stgit@devbox> To: linux-tip-commits@vger.kernel.org Subject: [tip:perf/urgent] kprobes/x86: Clear TF bit in fault on single-stepping Git-Commit-ID: dcfc47248d3f7d28df6f531e6426b933de94370d X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: dcfc47248d3f7d28df6f531e6426b933de94370d Gitweb: http://git.kernel.org/tip/dcfc47248d3f7d28df6f531e6426b933de94370d Author: Masami Hiramatsu AuthorDate: Sat, 11 Jun 2016 23:06:53 +0900 Committer: Ingo Molnar CommitDate: Tue, 14 Jun 2016 12:00:54 +0200 kprobes/x86: Clear TF bit in fault on single-stepping Fix kprobe_fault_handler() to clear the TF (trap flag) bit of the flags register in the case of a fault fixup on single-stepping. If we put a kprobe on the instruction which caused a page fault (e.g. actual mov instructions in copy_user_*), that fault happens on the single-stepping buffer. In this case, kprobes resets running instance so that the CPU can retry execution on the original ip address. However, current code forgets to reset the TF bit. Since this fault happens with TF bit set for enabling single-stepping, when it retries, it causes a debug exception and kprobes can not handle it because it already reset itself. On the most of x86-64 platform, it can be easily reproduced by using kprobe tracer. E.g. # cd /sys/kernel/debug/tracing # echo p copy_user_enhanced_fast_string+5 > kprobe_events # echo 1 > events/kprobes/enable And you'll see a kernel panic on do_debug(), since the debug trap is not handled by kprobes. To fix this problem, we just need to clear the TF bit when resetting running kprobe. Signed-off-by: Masami Hiramatsu Reviewed-by: Ananth N Mavinakayanahalli Acked-by: Steven Rostedt Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: systemtap@sourceware.org Cc: stable@vger.kernel.org # All the way back to ancient kernels Link: http://lkml.kernel.org/r/20160611140648.25885.37482.stgit@devbox [ Updated the comments. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes/core.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 38cf7a7..7847e5c 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else