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

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

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 4041f5747e73bf70f8d8dbb412f8e7b7067a8017..a146ee327f6ac15029b64424f0abd07e8d316f67 100644 (file)
--- 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);
        /*