Messages in this thread Patch in this message | | | Date | Tue, 6 Aug 2013 17:43:37 +0200 | From | Oleg Nesterov <> | Subject | [PATCH 1/1] 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> --- 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
| |