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 22:16:32 +0200 |
| commit | 35114fcbe0b9b0fa3f6653a2a8e4c6b8a9f8cc2d (patch) | |
| tree | 520b0ab0c8aa28c808eabb81e979f01749811018 /kernel/trace | |
| parent | Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus (diff) | |
| download | linux-35114fcbe0b9b0fa3f6653a2a8e4c6b8a9f8cc2d.tar.xz linux-35114fcbe0b9b0fa3f6653a2a8e4c6b8a9f8cc2d.zip | |
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 'kernel/trace')
0 files changed, 0 insertions, 0 deletions