Avoid calling proc_exit() in processes forked by system().

The SIGTERM handler for the startup process immediately calls
proc_exit() for the duration of the restore_command, i.e., a call
to system().  This system() call forks a new process to execute the
shell command, and this child process inherits the parent's signal
handlers.  If both the parent and child processes receive SIGTERM,
both will attempt to call proc_exit().  This can end badly.  For
example, both processes will try to remove themselves from the
PGPROC shared array.

To fix this problem, this commit adds a check in
StartupProcShutdownHandler() to see whether MyProcPid == getpid().
If they match, this is the parent process, and we can proc_exit()
like before.  If they do not match, this is a child process, and we
just emit a message to STDERR (in a signal safe manner) and
_exit(), thereby skipping any problematic exit callbacks.

This commit also adds checks in proc_exit(), ProcKill(), and
AuxiliaryProcKill() that verify they are not being called within
such child processes.

Suggested-by: Andres Freund
Reviewed-by: Thomas Munro, Andres Freund
Discussion: https://postgr.es/m/Y9nGDSgIm83FHcad%40paquier.xyz
Discussion: https://postgr.es/m/20230223231503.GA743455%40nathanxps13
Backpatch-through: 11

diff --git a/src/backend/postmaster/startup.c b/src/backend/postmaster/startup.c
index d897cafb272c38ff509ca85b719940e49f23007d..ec372b135686460de7934a0d39b753637fbfe940 100644 (file)
--- a/src/backend/postmaster/startup.c
+++ b/src/backend/postmaster/startup.c
@@ -132,7 +132,20 @@ StartupProcShutdownHandler(SIGNAL_ARGS)
        int                     save_errno = errno;
 
        if (in_restore_command)
-               proc_exit(1);
+       {
+               /*
+                * If we are in a child process (e.g., forked by system() in
+                * RestoreArchivedFile()), we don't want to call any exit callbacks.
+                * The parent will take care of that.
+                */
+               if (MyProcPid == (int) getpid())
+                       proc_exit(1);
+               else
+               {
+                       write_stderr_signal_safe("StartupProcShutdownHandler() called in child process\n");
+                       _exit(1);
+               }
+       }
        else
                shutdown_requested = true;
        WakeupRecovery();

diff --git a/src/backend/storage/ipc/ipc.c b/src/backend/storage/ipc/ipc.c
index a85a1c6de5dbfe40024fa29c9606516f781edd35..b249048f61ff38806382866470f01b1227afc883 100644 (file)
--- a/src/backend/storage/ipc/ipc.c
+++ b/src/backend/storage/ipc/ipc.c
@@ -103,6 +103,10 @@ static int on_proc_exit_index,
 void
 proc_exit(int code)
 {
+       /* not safe if forked by system(), etc. */
+       if (MyProcPid != (int) getpid())
+               elog(PANIC, "proc_exit() called in child process");
+
        /* Clean up everything that must be cleaned up */
        proc_exit_prepare(code);
 

diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 9ff26c45c2eaa5e13e6c1d61bc08ff441a1427b1..6742f5f7440834ae65e0c0a9fb40b68b52da7699 100644 (file)
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -805,6 +805,10 @@ ProcKill(int code, Datum arg)
 
        Assert(MyProc != NULL);
 
+       /* not safe if forked by system(), etc. */
+       if (MyProc->pid != (int) getpid())
+               elog(PANIC, "ProcKill() called in child process");
+
        /* Make sure we're out of the sync rep lists */
        SyncRepCleanupAtProcExit();
 
@@ -929,6 +933,10 @@ AuxiliaryProcKill(int code, Datum arg)
 
        Assert(proctype >= 0 && proctype < NUM_AUXILIARY_PROCS);
 
+       /* not safe if forked by system(), etc. */
+       if (MyProc->pid != (int) getpid())
+               elog(PANIC, "AuxiliaryProcKill() called in child process");
+
        auxproc = &AuxiliaryProcs[proctype];
 
        Assert(MyProc == auxproc);

diff --git a/src/backend/utils/error/elog.c b/src/backend/utils/error/elog.c
index 9dc7163a40a0382e3ea325c0f200f090020194b2..a4e1697e3fea418f3e734ef195385e3360b9406d 100644 (file)
--- a/src/backend/utils/error/elog.c
+++ b/src/backend/utils/error/elog.c
@@ -3703,6 +3703,34 @@ write_stderr(const char *fmt,...)
 }
 
 
+/*
+ * Write a message to STDERR using only async-signal-safe functions.  This can
+ * be used to safely emit a message from a signal handler.
+ *
+ * TODO: It is likely possible to safely do a limited amount of string
+ * interpolation (e.g., %s and %d), but that is not presently supported.
+ */
+void
+write_stderr_signal_safe(const char *str)
+{
+       int                     nwritten = 0;
+       int                     ntotal = strlen(str);
+
+       while (nwritten < ntotal)
+       {
+               int                     rc;
+
+               rc = write(STDERR_FILENO, str + nwritten, ntotal - nwritten);
+
+               /* Just give up on error.  There isn't much else we can do. */
+               if (rc == -1)
+                       return;
+
+               nwritten += rc;
+       }
+}
+
+
 /*
  * is_log_level_output -- is elevel logically >= log_min_level?
  *

diff --git a/src/include/utils/elog.h b/src/include/utils/elog.h
index 7a9ba7f2fffb52f0c0b32e5b1aeb6188de1ff78b..70b3e1cdbd82ecd07790bddff2bc42e99b24cff4 100644 (file)
--- a/src/include/utils/elog.h
+++ b/src/include/utils/elog.h
@@ -413,4 +413,10 @@ extern void set_syslog_parameters(const char *ident, int facility);
  */
 extern void write_stderr(const char *fmt,...) pg_attribute_printf(1, 2);
 
+/*
+ * Write a message to STDERR using only async-signal-safe functions.  This can
+ * be used to safely emit a message from a signal handler.
+ */
+extern void write_stderr_signal_safe(const char *fmt);
+
 #endif                                                 /* ELOG_H */