[PATCH 1/1] Revert "ptrace: PTRACE_DETACH should do flush_ptrace_hw_breakpoint(child)"

From: Oleg Nesterov <oleg@redhat.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Felipe Contreras <felipe.contreras@gmail.com>,
	Grazvydas Ignotas <notasas@gmail.com>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Ingo Molnar <mingo@elte.hu>, Denys Vlasenko <dvlasenk@redhat.com>
Subject: [PATCH 1/1] Revert "ptrace: PTRACE_DETACH should do flush_ptrace_hw_breakpoint(child)"
Date: Tue, 6 Aug 2013 17:43:37 +0200	[thread overview]
Message-ID: <20130806154337.GB398@redhat.com> (raw)
In-Reply-To: <20130806154314.GA398@redhat.com>

This reverts commit fab840fc2d542fabcab903db8e03589a6702ba5f.

This commit even has the test-case to prove that the tracee
can be killed by SIGTRAP if the debugger does not remove the
breakpoints before PTRACE_DETACH.

However, this is exactly what wineserver deliberately does,
set_thread_context() calls PTRACE_ATTACH + PTRACE_DETACH just
for PTRACE_POKEUSER(DR*) in between.

So we should revert this fix and document that PTRACE_DETACH
should keep the breakpoints.

Reported-by: Felipe Contreras <felipe.contreras@gmail.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
---
 kernel/ptrace.c |    1 -
 1 files changed, 0 insertions(+), 1 deletions(-)

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4041f57..a146ee3 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -469,7 +469,6 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 	/* Architecture-specific hardware disable .. */
 	ptrace_disable(child);
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
-	flush_ptrace_hw_breakpoint(child);
 
 	write_lock_irq(&tasklist_lock);
 	/*
-- 
1.5.5.1


