Commit 35114fcb authored Aug 06, 2013 by Oleg Nesterov Committed by Linus Torvalds Aug 06, 2013

Revert "ptrace: PTRACE_DETACH should do flush_ptrace_hw_breakpoint(child)"



This reverts commit fab840fc.

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>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

parent 1853a65e

kernel/ptrace.c

+0 −1

Original line number	Diff line number	Diff line
		@@ -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);
		/*

Admin message