ash: dowait: remove incorrect looping

Prev code:

         rpid = 1;
         do {
                 pid = waitone(block, jp);
                 rpid &= !!pid; <<<<<<<<<<<<<<<<<< HERE
                 if (!pid || (jp && jp->state != JOBRUNNING))
                         block = DOWAIT_NONBLOCK;
         } while (pid >= 0);
         return rpid;

If we got pid == 0, it happens in exactly one case:
we did waitpid(WNOHANG), got 0 ("children exist but none yet
changed its state"), then waited for a signal and got one,
which wasn't SIGCHLD.

The above behavior is requested by only one caller: waitcmd()
- the "wait" builtin.

"wait" builtin is required to be interruptible by signals and
to set exitcode to (128 + sig).

Therefore, if we got pid == 0, we don't need to wait
for any more processes. We need to return to waitcmd()
and let it set $? accordingly.

Instead, we do yet another loop.

I'm not saying that we know
that there are no more processes that finished.

I'm saying we don't care at this point: we know
that we are "wait" builtin and we got interrupted by a signal.

Fix this by not looping if "pid == 0" indicates we got a signal.
ONLY loop if we got a pid > 0 and we either do not wait for a specific job,
or this scpecific job is still RUNNING.

function                                             old     new   delta
dowait                                               546     530     -16

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
This commit is contained in:
Denys Vlasenko committed 2026-10-05 17:40:47 +02:00
1 parent e054f9fb4b
commit 3920b0a994
1 file changed
+14 -12
+14 -12
View File
@@ -4351,6 +4351,9 @@ waitproc(int block, int *status)
if (err) /* waitpid() returned PID or error? */
break; /* return it */
/* We are here only if DOWAIT_NONBLOCK or DOWAIT_CHILD_OR_SIG */
err = -!block;
if (err) /* block == DOWAIT_NONBLOCK (0)? */
break; /* return -1 */
@@ -4493,7 +4496,6 @@ static int waitone(int block, struct job *job)
static int dowait(int block, struct job *jp)
{
smallint gotchld = *(volatile smallint *)&gotsigchld;
int rpid;
int pid;
if (jp && jp->state != JOBRUNNING)
@@ -4502,8 +4504,6 @@ static int dowait(int block, struct job *jp)
if (block == DOWAIT_NONBLOCK && !gotchld)
return 1;
rpid = 1;
/* In what cases we loop here:
* = If we waited in blocking mode and got pid > 0,
* but the job we waiting for is still running
@@ -4514,22 +4514,24 @@ static int dowait(int block, struct job *jp)
* we should see whether more processes have terminated,
* we have to wait in non-blocking mode again.
* The users are
* showjobs() -> dowait(DOWAIT_NONBLOCK)
* waitforjob(NULL) -> dowait(DOWAIT_NONBLOCK)
* showjobs() -> dowait(DOWAIT_NONBLOCK, NULL)
* waitforjob(NULL) -> dowait(DOWAIT_NONBLOCK, NULL)
* waitcmd() does its own looping while it sees at least one JOBRUNNING
* job, it does not need us to loop here - only to do
* one nonblocking wait and if it gives nothing, wait for signals.
*/
do {
pid = waitone(block, jp);
rpid &= !!pid;
if (pid == 0)
return 0; /* got a signal */
if (jp && jp->state != JOBRUNNING) {
/* no more running procs in this job, stop waiting */
return 1; /* did not get a signal */
}
/* if we saw a process changing state, wait again (is there more?) */
} while (pid > 0);
if (!pid || (jp && jp->state != JOBRUNNING))
block = DOWAIT_NONBLOCK;
} while (pid >= 0); //WRONG? should be "pid > 0"
/* Return: 0 if seen a signal, 1 otherwise */
return rpid;
return 1; /* did not get a signal */
}
/*