tree 520b0ab0c8aa28c808eabb81e979f01749811018
parent 1853a65ec5bd07c18f4a43e6709486c81400afa6
author Oleg Nesterov <oleg@redhat.com> 1375803817 +0200
committer Linus Torvalds <torvalds@linux-foundation.org> 1375820192 -0700

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>