maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

We have to call waitpid on the lldb side for Mac OS X (even though we've successfully called it 

on the debugserver side) when we kill a process or it leaves a zombie around.

llvm-svn: 201896
This commit is contained in:
Jim Ingham 2014-02-21 22:35:29 +00:00
parent d9e7c22ee4
commit 9d67cc59c4
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
lldb/source/Plugins/Process/gdb-remote/ProcessGDBRemote.cpp
View File

@ -2022,6 +2022,24 @@ ProcessGDBRemote::DoDestroy ()
if (packet_cmd == 'W' || packet_cmd == 'X')
{
#if 0 && defined(__APPLE__)
// For Native processes on Mac OS X, we launch through the Host Platform, then hand the process off
// to debugserver, which becomes the parent process through "PT_ATTACH". Then when we go to kill
// the process on Mac OS X we call ptrace(PT_KILL) to kill it, then we call waitpid which returns
// with no error and the correct status. But amusingly enough that doesn't seem to actually reap
// the process, but instead it is left around as a Zombie. Probably the kernel is in the process of
// switching ownership back to lldb which was the original parent, and gets confused in the handoff.
// Anyway, so call waitpid here to finally reap it.
PlatformSP platform_sp(GetTarget().GetPlatform());
if (platform_sp && platform_sp->IsHost())
{
int status;
::pid_t reap_pid;
reap_pid = waitpid (GetID(), &status, WNOHANG);
if (log)
log->Printf ("Reaped pid: %d, status: %d.\n", reap_pid, status);
}
#endif
SetLastStopPacket (response);
ClearThreadIDList ();
exit_status = response.GetHexU8();