Fix bug #12829 with aborts on MS-Windows when several child processes die.

 nt/inc/sys/wait.h: New file, with prototype of waitpid and
 definitions of macros it needs.
 nt/inc/ms-w32.h (wait): Don't define, 'wait' is not used anymore.
 (sys_wait): Remove prototype.
 nt/config.nt (HAVE_SYS_WAIT_H): Define to 1.

 src/w32proc.c (create_child): Don't clip the PID of the child
 process to fit into an Emacs integer, as this is no longer a
 restriction.
 (waitpid): Rename from sys_wait.  Emulate a Posix 'waitpid' by
 reaping only the process specified by PID argument, if that is
 positive.  Use PID instead of dead_child to know which process to
 reap.  Wait for the child to die only if WNOHANG is not in
 OPTIONS.
 (sys_select): Don't set dead_child.
 src/sysdep.c (wait_for_termination_1): Remove the WINDOWSNT portion,
 as it is no longer needed.
 src/process.c (waitpid, WUNTRACED) [!WNOHANG]: Remove definitions,
 no longer needed.
 (record_child_status_change): Remove the setting of
 record_at_most_one_child for the !WNOHANG case.

4 files changed, 112 insertions, 62 deletions

diff --git a/src/ChangeLog b/src/ChangeLog
index 1194fe099fa..45d48ba41cc 100644
--- a/src/ChangeLog
+++ b/src/ChangeLog
@@ -1,3 +1,23 @@
+2012-11-17  Eli Zaretskii  <eliz@gnu.org>
+
+        * w32proc.c (create_child): Don't clip the PID of the child
+        process to fit into an Emacs integer, as this is no longer a
+        restriction.
+        (waitpid): Rename from sys_wait.  Emulate a Posix 'waitpid' by
+        reaping only the process specified by PID argument, if that is
+        positive.  Use PID instead of dead_child to know which process to
+        reap.  Wait for the child to die only if WNOHANG is not in
+        OPTIONS.
+        (sys_select): Don't set dead_child.
+
+        * sysdep.c (wait_for_termination_1): Remove the WINDOWSNT portion,
+        as it is no longer needed.
+
+        * process.c (waitpid, WUNTRACED) [!WNOHANG]: Remove definitions,
+        no longer needed.
+        (record_child_status_change): Remove the setting of
+        record_at_most_one_child for the !WNOHANG case.
+
 2012-11-17  Paul Eggert  <eggert@cs.ucla.edu>
 
         Fix problems in ns port found by static checking.
diff --git a/src/process.c b/src/process.c
index 785282fba36..5fe6a6540f3 100644
--- a/src/process.c
+++ b/src/process.c
@@ -130,18 +130,6 @@ extern int sys_select (int, SELECT_TYPE *, SELECT_TYPE *, SELECT_TYPE *,
                        EMACS_TIME *, void *);
 #endif
 
-/* This is for DOS_NT ports.  FIXME: Remove this old portability cruft
-   by having DOS_NT ports implement waitpid instead of wait.  Nowadays
-   POSIXish hosts all define waitpid, WNOHANG, and WUNTRACED, as these
-   have been standard since POSIX.1-1988.  */
-#ifndef WNOHANG
-# undef waitpid
-# define waitpid(pid, status, options) wait (status)
-#endif
-#ifndef WUNTRACED
-# define WUNTRACED 0
-#endif
-
 /* Work around GCC 4.7.0 bug with strict overflow checking; see
    <http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52904>.
    These lines can be removed once the GCC bug is fixed.  */
@@ -6295,17 +6283,9 @@ record_child_status_change (pid_t pid, int w)
 {
 #ifdef SIGCHLD
 
-# ifdef WNOHANG
   /* On POSIXish hosts, record at most one child only if we already
      know one child that has exited.  */
   bool record_at_most_one_child = 0 <= pid;
-# else
-  /* On DOS_NT (the only porting target that lacks WNOHANG),
-     record the status of at most one child process, since the SIGCHLD
-     handler must return right away.  If any more processes want to
-     signal us, we will get another signal.  */
-  bool record_at_most_one_child = 1;
-# endif
 
   Lisp_Object tail;
 
diff --git a/src/sysdep.c b/src/sysdep.c
index a7f3de2f1b1..06dc41b511e 100644
--- a/src/sysdep.c
+++ b/src/sysdep.c
@@ -289,10 +289,6 @@ wait_for_termination_1 (pid_t pid, int interruptible)
 {
   while (1)
     {
-#ifdef WINDOWSNT
-      wait (0);
-      break;
-#else /* not WINDOWSNT */
       int status;
       int wait_result = waitpid (pid, &status, 0);
       if (wait_result < 0)
@@ -306,7 +302,8 @@ wait_for_termination_1 (pid_t pid, int interruptible)
           break;
         }
 
-#endif /* not WINDOWSNT */
+      /* Note: the MS-Windows emulation of waitpid calls QUIT
+         internally.  */
       if (interruptible)
         QUIT;
     }
diff --git a/src/w32proc.c b/src/w32proc.c
index 10dd23003b8..fd6a498290a 100644
--- a/src/w32proc.c
+++ b/src/w32proc.c
@@ -789,7 +789,6 @@ alarm (int seconds)
 /* Child process management list.  */
 int child_proc_count = 0;
 child_process child_procs[ MAX_CHILDREN ];
-child_process *dead_child = NULL;
 
 static DWORD WINAPI reader_thread (void *arg);
 
@@ -1042,9 +1041,6 @@ create_child (char *exe, char *cmdline, char *env, int is_gui_app,
   if (cp->pid < 0)
     cp->pid = -cp->pid;
 
-  /* pid must fit in a Lisp_Int */
-  cp->pid = cp->pid & INTMASK;
-
   *pPid = cp->pid;
 
   return TRUE;
@@ -1120,55 +1116,110 @@ reap_subprocess (child_process *cp)
     delete_child (cp);
 }
 
-/* Wait for any of our existing child processes to die
-   When it does, close its handle
-   Return the pid and fill in the status if non-NULL.  */
+/* Wait for a child process specified by PID, or for any of our
+   existing child processes (if PID is nonpositive) to die.  When it
+   does, close its handle.  Return the pid of the process that died
+   and fill in STATUS if non-NULL.  */
 
-int
-sys_wait (int *status)
+pid_t
+waitpid (pid_t pid, int *status, int options)
 {
   DWORD active, retval;
   int nh;
-  int pid;
   child_process *cp, *cps[MAX_CHILDREN];
   HANDLE wait_hnd[MAX_CHILDREN];
+  DWORD timeout_ms;
+  int dont_wait = (options & WNOHANG) != 0;
 
   nh = 0;
-  if (dead_child != NULL)
+  /* According to Posix:
+
+     PID = -1 means status is requested for any child process.
+
+     PID > 0 means status is requested for a single child process
+     whose pid is PID.
+
+     PID = 0 means status is requested for any child process whose
+     process group ID is equal to that of the calling process.  But
+     since Windows has only a limited support for process groups (only
+     for console processes and only for the purposes of passing
+     Ctrl-BREAK signal to them), and since we have no documented way
+     of determining whether a given process belongs to our group, we
+     treat 0 as -1.
+
+     PID < -1 means status is requested for any child process whose
+     process group ID is equal to the absolute value of PID.  Again,
+     since we don't support process groups, we treat that as -1.  */
+  if (pid > 0)
     {
-      /* We want to wait for a specific child */
-      wait_hnd[nh] = dead_child->procinfo.hProcess;
-      cps[nh] = dead_child;
-      if (!wait_hnd[nh]) emacs_abort ();
-      nh++;
-      active = 0;
-      goto get_result;
+      int our_child = 0;
+
+      /* We are requested to wait for a specific child.  */
+      for (cp = child_procs + (child_proc_count-1); cp >= child_procs; cp--)
+        {
+          /* Some child_procs might be sockets; ignore them.  Also
+             ignore subprocesses whose output is not yet completely
+             read.  */
+          if (CHILD_ACTIVE (cp)
+              && cp->procinfo.hProcess
+              && cp->pid == pid)
+            {
+              our_child = 1;
+              break;
+            }
+        }
+      if (our_child)
+        {
+          if (cp->fd < 0 || (fd_info[cp->fd].flags & FILE_AT_EOF) != 0)
+            {
+              wait_hnd[nh] = cp->procinfo.hProcess;
+              cps[nh] = cp;
+              nh++;
+            }
+          else if (dont_wait)
+            {
+              /* PID specifies our subprocess, but its status is not
+                 yet available.  */
+              return 0;
+            }
+        }
+      if (nh == 0)
+        {
+          /* No such child process, or nothing to wait for, so fail.  */
+          errno = ECHILD;
+          return -1;
+        }
     }
   else
     {
       for (cp = child_procs + (child_proc_count-1); cp >= child_procs; cp--)
-        /* some child_procs might be sockets; ignore them */
-        if (CHILD_ACTIVE (cp) && cp->procinfo.hProcess
-            && (cp->fd < 0 || (fd_info[cp->fd].flags & FILE_AT_EOF) != 0))
-          {
-            wait_hnd[nh] = cp->procinfo.hProcess;
-            cps[nh] = cp;
-            nh++;
-          }
+        {
+          if (CHILD_ACTIVE (cp)
+              && cp->procinfo.hProcess
+              && (cp->fd < 0 || (fd_info[cp->fd].flags & FILE_AT_EOF) != 0))
+            {
+              wait_hnd[nh] = cp->procinfo.hProcess;
+              cps[nh] = cp;
+              nh++;
+            }
+        }
+      if (nh == 0)
+        {
+          /* Nothing to wait on, so fail.  */
+          errno = ECHILD;
+          return -1;
+        }
     }
 
-  if (nh == 0)
-    {
-      /* Nothing to wait on, so fail */
-      errno = ECHILD;
-      return -1;
-    }
+  if (dont_wait)
+    timeout_ms = 0;
+  else
+    timeout_ms = 1000;  /* check for quit about once a second. */
 
   do
     {
-      /* Check for quit about once a second. */
       QUIT;
-      active = WaitForMultipleObjects (nh, wait_hnd, FALSE, 1000);
+      active = WaitForMultipleObjects (nh, wait_hnd, FALSE, timeout_ms);
     } while (active == WAIT_TIMEOUT);
 
   if (active == WAIT_FAILED)
@@ -1198,8 +1249,10 @@ get_result:
     }
   if (retval == STILL_ACTIVE)
     {
-      /* Should never happen */
+      /* Should never happen.  */
       DebPrint (("Wait.WaitForMultipleObjects returned an active process\n"));
+      if (pid > 0 && dont_wait)
+        return 0;
       errno = EINVAL;
       return -1;
     }
@@ -1213,6 +1266,8 @@ get_result:
   else
     retval <<= 8;
 
+  if (pid > 0 && active != 0)
+    emacs_abort ();
   cp = cps[active];
   pid = cp->pid;
 #ifdef FULL_DEBUG
@@ -2001,9 +2056,7 @@ count_children:
               DebPrint (("select calling SIGCHLD handler for pid %d\n",
                          cp->pid));
 #endif
-              dead_child = cp;
               sig_handlers[SIGCHLD] (SIGCHLD);
-              dead_child = NULL;
             }
         }
       else if (fdindex[active] == -1)