mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-01-12 16:19:53 +00:00
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>
This commit is contained in:
parent
1853a65ec5
commit
35114fcbe0
@ -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);
|
||||
/*
|
||||
|
Loading…
x
Reference in New Issue
Block a user