diff options
author | Oleg Nesterov <oleg@redhat.com> | 2013-08-06 17:43:37 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-08-06 13:16:32 -0700 |
commit | 35114fcbe0b9b0fa3f6653a2a8e4c6b8a9f8cc2d (patch) | |
tree | 520b0ab0c8aa28c808eabb81e979f01749811018 /arch/x86 | |
parent | 1853a65ec5bd07c18f4a43e6709486c81400afa6 (diff) | |
download | linux-35114fcbe0b9b0fa3f6653a2a8e4c6b8a9f8cc2d.tar.bz2 |
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>
Diffstat (limited to 'arch/x86')
0 files changed, 0 insertions, 0 deletions