From 6d4e8f62e93b575a1da2cd2b4abeb9dce56e1e52 Mon Sep 17 00:00:00 2001 From: Paul Eggert Date: Fri, 23 Nov 2012 14:20:31 -0800 Subject: Fix a race condition with glib (Bug#8855). This is a backport from the trunk, consisting of: 2012-11-17 Eli Zaretskii * 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. 2012-11-03 Paul Eggert Fix a race condition that causes Emacs to mess up glib (Bug#8855). This is a backport from the trunk. The symptom is a diagnostic "GLib-WARNING **: In call to g_spawn_sync(), exit status of a child process was requested but SIGCHLD action was set to SIG_IGN and ECHILD was received by waitpid(), so exit status can't be returned." The diagnostic is partly wrong, as the SIGCHLD action is not set to SIG_IGN. The real bug is a race condition between Emacs and glib: Emacs does a waitpid (-1, ...) and reaps glib's subprocess by mistake, so that glib can't find it. Work around the bug by invoking waitpid only on subprocesses that Emacs itself creates. * src/process.c (create_process, record_child_status_change): Don't use special value -1 in pid field, as the caller now must know the pid rather than having the callee infer it. The inference was sometimes incorrect anyway, due to another race. (create_process): Set new 'alive' member if child is created. (process_status_retrieved): New function. (record_child_status_change): Use it. Accept negative 1st argument, which means to wait for the processes that Emacs already knows about. Move special-case code for DOS_NT (which lacks WNOHANG) here, from caller. Keep track of processes that have already been waited for, by testing and clearing new 'alive' member. (CAN_HANDLE_MULTIPLE_CHILDREN): Remove, as record_child_status_change now does this internally. (handle_child_signal): Let record_child_status_change do all the work, since we do not want to reap all exited child processes, only the child processes that Emacs itself created. * src/process.h (Lisp_Process): New boolean member 'alive'. --- src/process.c | 191 +++++++++++++++++++++++++++------------------------------- 1 file changed, 88 insertions(+), 103 deletions(-) (limited to 'src/process.c') diff --git a/src/process.c b/src/process.c index 77e99ead01f..c095d13293b 100644 --- a/src/process.c +++ b/src/process.c @@ -130,14 +130,6 @@ extern int sys_select (int, SELECT_TYPE *, SELECT_TYPE *, SELECT_TYPE *, EMACS_TIME *, void *); #endif -#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 . These lines can be removed once the GCC bug is fixed. */ @@ -795,9 +787,8 @@ get_process (register Lisp_Object name) #ifdef SIGCHLD /* Fdelete_process promises to immediately forget about the process, but in reality, Emacs needs to remember those processes until they have been - treated by the SIGCHLD handler; otherwise this handler would consider the - process as being synchronous and say that the synchronous process is - dead. */ + treated by the SIGCHLD handler and waitpid has been invoked on them; + otherwise they might fill up the kernel's process table. */ static Lisp_Object deleted_pid_list; #endif @@ -1704,16 +1695,7 @@ create_process (Lisp_Object process, char **new_argv, Lisp_Object current_dir) if (inchannel > max_process_desc) max_process_desc = inchannel; - /* Until we store the proper pid, enable the SIGCHLD handler - to recognize an unknown pid as standing for this process. - It is very important not to let this `marker' value stay - in the table after this function has returned; if it does - it might cause call-process to hang and subsequent asynchronous - processes to get their return values scrambled. */ - XPROCESS (process)->pid = -1; - - /* This must be called after the above line because it may signal an - error. */ + /* This may signal an error. */ setup_process_coding_systems (process); encoded_current_dir = ENCODE_FILE (current_dir); @@ -1880,6 +1862,8 @@ create_process (Lisp_Object process, char **new_argv, Lisp_Object current_dir) #endif XPROCESS (process)->pid = pid; + if (0 <= pid) + XPROCESS (process)->alive = 1; /* Stop blocking signals in the parent. */ #ifdef SIGCHLD @@ -6273,9 +6257,35 @@ process has been transmitted to the serial port. */) return process; } -/* On receipt of a signal that a child status has changed, loop asking - about children with changed statuses until the system says there - are no more. +/* If the status of the process DESIRED has changed, return true and + set *STATUS to its exit status; otherwise, return false. + If HAVE is nonnegative, assume that HAVE = waitpid (HAVE, STATUS, ...) + has already been invoked, and do not invoke waitpid again. */ + +static bool +process_status_retrieved (pid_t desired, pid_t have, int *status) +{ + if (have < 0) + { + /* Invoke waitpid only with a known process ID; do not invoke + waitpid with a nonpositive argument. Otherwise, Emacs might + reap an unwanted process by mistake. For example, invoking + waitpid (-1, ...) can mess up glib by reaping glib's subprocesses, + so that another thread running glib won't find them. */ + do + have = waitpid (desired, status, WNOHANG | WUNTRACED); + while (have < 0 && errno == EINTR); + } + + return have == desired; +} + +/* If PID is nonnegative, the child process PID with wait status W has + changed its status; record this and return true. + + If PID is negative, ignore W, and look for known child processes + of Emacs whose status have changed. For each one found, record its new + status. All we do is change the status; we do not run sentinels or print notifications. That is saved for the next time keyboard input is @@ -6298,13 +6308,15 @@ process has been transmitted to the serial port. */) ** Malloc WARNING: This should never call malloc either directly or indirectly; if it does, that is a bug */ -/* Record the changed status of the child process PID with wait status W. */ void record_child_status_change (pid_t pid, int w) { #ifdef SIGCHLD - Lisp_Object proc; - struct Lisp_Process *p; + + /* 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; + Lisp_Object tail; /* Find the process that signaled us, and record its status. */ @@ -6312,68 +6324,69 @@ record_child_status_change (pid_t pid, int w) /* The process can have been deleted by Fdelete_process. */ for (tail = deleted_pid_list; CONSP (tail); tail = XCDR (tail)) { + bool all_pids_are_fixnums + = (MOST_NEGATIVE_FIXNUM <= TYPE_MINIMUM (pid_t) + && TYPE_MAXIMUM (pid_t) <= MOST_POSITIVE_FIXNUM); Lisp_Object xpid = XCAR (tail); - if ((INTEGERP (xpid) && pid == XINT (xpid)) - || (FLOATP (xpid) && pid == XFLOAT_DATA (xpid))) + if (all_pids_are_fixnums ? INTEGERP (xpid) : NUMBERP (xpid)) { - XSETCAR (tail, Qnil); - return; + pid_t deleted_pid; + if (INTEGERP (xpid)) + deleted_pid = XINT (xpid); + else + deleted_pid = XFLOAT_DATA (xpid); + if (process_status_retrieved (deleted_pid, pid, &w)) + { + XSETCAR (tail, Qnil); + if (record_at_most_one_child) + return; + } } } /* Otherwise, if it is asynchronous, it is in Vprocess_alist. */ - p = 0; for (tail = Vprocess_alist; CONSP (tail); tail = XCDR (tail)) { - proc = XCDR (XCAR (tail)); - p = XPROCESS (proc); - if (EQ (p->type, Qreal) && p->pid == pid) - break; - p = 0; - } - - /* Look for an asynchronous process whose pid hasn't been filled - in yet. */ - if (! p) - for (tail = Vprocess_alist; CONSP (tail); tail = XCDR (tail)) - { - proc = XCDR (XCAR (tail)); - p = XPROCESS (proc); - if (p->pid == -1) - break; - p = 0; - } + Lisp_Object proc = XCDR (XCAR (tail)); + struct Lisp_Process *p = XPROCESS (proc); + if (p->alive && process_status_retrieved (p->pid, pid, &w)) + { + /* Change the status of the process that was found. */ + p->tick = ++process_tick; + p->raw_status = w; + p->raw_status_new = 1; - /* Change the status of the process that was found. */ - if (p) - { - int clear_desc_flag = 0; + /* If process has terminated, stop waiting for its output. */ + if (WIFSIGNALED (w) || WIFEXITED (w)) + { + int clear_desc_flag = 0; + p->alive = 0; + if (p->infd >= 0) + clear_desc_flag = 1; - p->tick = ++process_tick; - p->raw_status = w; - p->raw_status_new = 1; + /* clear_desc_flag avoids a compiler bug in Microsoft C. */ + if (clear_desc_flag) + { + FD_CLR (p->infd, &input_wait_mask); + FD_CLR (p->infd, &non_keyboard_wait_mask); + } + } - /* If process has terminated, stop waiting for its output. */ - if ((WIFSIGNALED (w) || WIFEXITED (w)) - && p->infd >= 0) - clear_desc_flag = 1; + /* Tell wait_reading_process_output that it needs to wake up and + look around. */ + if (input_available_clear_time) + *input_available_clear_time = make_emacs_time (0, 0); - /* We use clear_desc_flag to avoid a compiler bug in Microsoft C. */ - if (clear_desc_flag) - { - FD_CLR (p->infd, &input_wait_mask); - FD_CLR (p->infd, &non_keyboard_wait_mask); + if (record_at_most_one_child) + return; } - - /* Tell wait_reading_process_output that it needs to wake up and - look around. */ - if (input_available_clear_time) - *input_available_clear_time = make_emacs_time (0, 0); } - /* There was no asynchronous process found for that pid: we have - a synchronous process. */ - else + + if (0 <= pid) { + /* The caller successfully waited for a pid but no asynchronous + process was found for it, so this is a synchronous process. */ + synch_process_alive = 0; /* Report the status of the synchronous process. */ @@ -6392,38 +6405,10 @@ record_child_status_change (pid_t pid, int w) #ifdef SIGCHLD -/* On some systems, the SIGCHLD handler must return right away. If - any more processes want to signal us, we will get another signal. - Otherwise, loop around to use up all the processes that have - something to tell us. */ -#if (defined WINDOWSNT \ - || (defined USG && !defined GNU_LINUX \ - && !(defined HPUX && defined WNOHANG))) -enum { CAN_HANDLE_MULTIPLE_CHILDREN = 0 }; -#else -enum { CAN_HANDLE_MULTIPLE_CHILDREN = 1 }; -#endif - static void handle_child_signal (int sig) { - do - { - pid_t pid; - int status; - - do - pid = waitpid (-1, &status, WNOHANG | WUNTRACED); - while (pid < 0 && errno == EINTR); - - /* PID == 0 means no processes found, PID == -1 means a real failure. - Either way, we have done all our job. */ - if (pid <= 0) - break; - - record_child_status_change (pid, status); - } - while (CAN_HANDLE_MULTIPLE_CHILDREN); + record_child_status_change (-1, 0); } static void -- cgit v1.2.1