diff options
Diffstat (limited to 'run-command.c')
| -rw-r--r-- | run-command.c | 1144 |
1 files changed, 988 insertions, 156 deletions
diff --git a/run-command.c b/run-command.c index aad03ab705..9e36151bf9 100644 --- a/run-command.c +++ b/run-command.c @@ -3,6 +3,8 @@ #include "exec_cmd.h" #include "sigchain.h" #include "argv-array.h" +#include "thread-utils.h" +#include "strbuf.h" void child_process_init(struct child_process *child) { @@ -11,39 +13,79 @@ void child_process_init(struct child_process *child) argv_array_init(&child->env_array); } +void child_process_clear(struct child_process *child) +{ + argv_array_clear(&child->args); + argv_array_clear(&child->env_array); +} + struct child_to_clean { pid_t pid; + struct child_process *process; struct child_to_clean *next; }; static struct child_to_clean *children_to_clean; static int installed_child_cleanup_handler; -static void cleanup_children(int sig) +static void cleanup_children(int sig, int in_signal) { + struct child_to_clean *children_to_wait_for = NULL; + while (children_to_clean) { struct child_to_clean *p = children_to_clean; children_to_clean = p->next; + + if (p->process && !in_signal) { + struct child_process *process = p->process; + if (process->clean_on_exit_handler) { + trace_printf( + "trace: run_command: running exit handler for pid %" + PRIuMAX, (uintmax_t)p->pid + ); + process->clean_on_exit_handler(process); + } + } + kill(p->pid, sig); - free(p); + + if (p->process && p->process->wait_after_clean) { + p->next = children_to_wait_for; + children_to_wait_for = p; + } else { + if (!in_signal) + free(p); + } + } + + while (children_to_wait_for) { + struct child_to_clean *p = children_to_wait_for; + children_to_wait_for = p->next; + + while (waitpid(p->pid, NULL, 0) < 0 && errno == EINTR) + ; /* spin waiting for process exit or error */ + + if (!in_signal) + free(p); } } static void cleanup_children_on_signal(int sig) { - cleanup_children(sig); + cleanup_children(sig, 1); sigchain_pop(sig); raise(sig); } static void cleanup_children_on_exit(void) { - cleanup_children(SIGTERM); + cleanup_children(SIGTERM, 0); } -static void mark_child_for_cleanup(pid_t pid) +static void mark_child_for_cleanup(pid_t pid, struct child_process *process) { struct child_to_clean *p = xmalloc(sizeof(*p)); p->pid = pid; + p->process = process; p->next = children_to_clean; children_to_clean = p; @@ -75,18 +117,65 @@ static inline void close_pair(int fd[2]) close(fd[1]); } -#ifndef GIT_WINDOWS_NATIVE -static inline void dup_devnull(int to) +int is_executable(const char *name) { - int fd = open("/dev/null", O_RDWR); - if (fd < 0) - die_errno(_("open /dev/null failed")); - if (dup2(fd, to) < 0) - die_errno(_("dup2(%d,%d) failed"), fd, to); - close(fd); + struct stat st; + + if (stat(name, &st) || /* stat, not lstat */ + !S_ISREG(st.st_mode)) + return 0; + +#if defined(GIT_WINDOWS_NATIVE) + /* + * On Windows there is no executable bit. The file extension + * indicates whether it can be run as an executable, and Git + * has special-handling to detect scripts and launch them + * through the indicated script interpreter. We test for the + * file extension first because virus scanners may make + * it quite expensive to open many files. + */ + if (ends_with(name, ".exe")) + return S_IXUSR; + +{ + /* + * Now that we know it does not have an executable extension, + * peek into the file instead. + */ + char buf[3] = { 0 }; + int n; + int fd = open(name, O_RDONLY); + st.st_mode &= ~S_IXUSR; + if (fd >= 0) { + n = read(fd, buf, 2); + if (n == 2) + /* look for a she-bang */ + if (!strcmp(buf, "#!")) + st.st_mode |= S_IXUSR; + close(fd); + } } #endif + return st.st_mode & S_IXUSR; +} +/* + * Search $PATH for a command. This emulates the path search that + * execvp would perform, without actually executing the command so it + * can be used before fork() to prepare to run a command using + * execve() or after execvp() to diagnose why it failed. + * + * The caller should ensure that file contains no directory + * separators. + * + * Returns the path to the command, as found in $PATH or NULL if the + * command could not be found. The caller inherits ownership of the memory + * used to store the resultant path. + * + * This should not be used on Windows, where the $PATH search rules + * are more complicated (e.g., a search for "foo" should find + * "foo.exe"). + */ static char *locate_in_PATH(const char *file) { const char *p = getenv("PATH"); @@ -107,7 +196,7 @@ static char *locate_in_PATH(const char *file) } strbuf_addstr(&buf, file); - if (!access(buf.buf, F_OK)) + if (is_executable(buf.buf)) return strbuf_detach(&buf, NULL); if (!*end) @@ -151,79 +240,275 @@ int sane_execvp(const char *file, char * const argv[]) return -1; } -static const char **prepare_shell_cmd(const char **argv) +static const char **prepare_shell_cmd(struct argv_array *out, const char **argv) { - int argc, nargc = 0; - const char **nargv; - - for (argc = 0; argv[argc]; argc++) - ; /* just counting */ - /* +1 for NULL, +3 for "sh -c" plus extra $0 */ - nargv = xmalloc(sizeof(*nargv) * (argc + 1 + 3)); - - if (argc < 1) + if (!argv[0]) die("BUG: shell command is empty"); if (strcspn(argv[0], "|&;<>()$`\\\"' \t\n*?[#~=%") != strlen(argv[0])) { #ifndef GIT_WINDOWS_NATIVE - nargv[nargc++] = SHELL_PATH; + argv_array_push(out, SHELL_PATH); #else - nargv[nargc++] = "sh"; + argv_array_push(out, "sh"); #endif - nargv[nargc++] = "-c"; - - if (argc < 2) - nargv[nargc++] = argv[0]; - else { - struct strbuf arg0 = STRBUF_INIT; - strbuf_addf(&arg0, "%s \"$@\"", argv[0]); - nargv[nargc++] = strbuf_detach(&arg0, NULL); - } - } + argv_array_push(out, "-c"); - for (argc = 0; argv[argc]; argc++) - nargv[nargc++] = argv[argc]; - nargv[nargc] = NULL; + /* + * If we have no extra arguments, we do not even need to + * bother with the "$@" magic. + */ + if (!argv[1]) + argv_array_push(out, argv[0]); + else + argv_array_pushf(out, "%s \"$@\"", argv[0]); + } - return nargv; + argv_array_pushv(out, argv); + return out->argv; } #ifndef GIT_WINDOWS_NATIVE -static int execv_shell_cmd(const char **argv) +static int child_notifier = -1; + +enum child_errcode { + CHILD_ERR_CHDIR, + CHILD_ERR_DUP2, + CHILD_ERR_CLOSE, + CHILD_ERR_SIGPROCMASK, + CHILD_ERR_ENOENT, + CHILD_ERR_SILENT, + CHILD_ERR_ERRNO +}; + +struct child_err { + enum child_errcode err; + int syserr; /* errno */ +}; + +static void child_die(enum child_errcode err) { - const char **nargv = prepare_shell_cmd(argv); - trace_argv_printf(nargv, "trace: exec:"); - sane_execvp(nargv[0], (char **)nargv); - free(nargv); - return -1; + struct child_err buf; + + buf.err = err; + buf.syserr = errno; + + /* write(2) on buf smaller than PIPE_BUF (min 512) is atomic: */ + xwrite(child_notifier, &buf, sizeof(buf)); + _exit(1); } -#endif -#ifndef GIT_WINDOWS_NATIVE -static int child_err = 2; -static int child_notifier = -1; +static void child_dup2(int fd, int to) +{ + if (dup2(fd, to) < 0) + child_die(CHILD_ERR_DUP2); +} + +static void child_close(int fd) +{ + if (close(fd)) + child_die(CHILD_ERR_CLOSE); +} + +static void child_close_pair(int fd[2]) +{ + child_close(fd[0]); + child_close(fd[1]); +} -static void notify_parent(void) +/* + * parent will make it look like the child spewed a fatal error and died + * this is needed to prevent changes to t0061. + */ +static void fake_fatal(const char *err, va_list params) { + vreportf("fatal: ", err, params); +} + +static void child_error_fn(const char *err, va_list params) +{ + const char msg[] = "error() should not be called in child\n"; + xwrite(2, msg, sizeof(msg) - 1); +} + +static void child_warn_fn(const char *err, va_list params) +{ + const char msg[] = "warn() should not be called in child\n"; + xwrite(2, msg, sizeof(msg) - 1); +} + +static void NORETURN child_die_fn(const char *err, va_list params) +{ + const char msg[] = "die() should not be called in child\n"; + xwrite(2, msg, sizeof(msg) - 1); + _exit(2); +} + +/* this runs in the parent process */ +static void child_err_spew(struct child_process *cmd, struct child_err *cerr) +{ + static void (*old_errfn)(const char *err, va_list params); + + old_errfn = get_error_routine(); + set_error_routine(fake_fatal); + errno = cerr->syserr; + + switch (cerr->err) { + case CHILD_ERR_CHDIR: + error_errno("exec '%s': cd to '%s' failed", + cmd->argv[0], cmd->dir); + break; + case CHILD_ERR_DUP2: + error_errno("dup2() in child failed"); + break; + case CHILD_ERR_CLOSE: + error_errno("close() in child failed"); + break; + case CHILD_ERR_SIGPROCMASK: + error_errno("sigprocmask failed restoring signals"); + break; + case CHILD_ERR_ENOENT: + error_errno("cannot run %s", cmd->argv[0]); + break; + case CHILD_ERR_SILENT: + break; + case CHILD_ERR_ERRNO: + error_errno("cannot exec '%s'", cmd->argv[0]); + break; + } + set_error_routine(old_errfn); +} + +static void prepare_cmd(struct argv_array *out, const struct child_process *cmd) +{ + if (!cmd->argv[0]) + die("BUG: command is empty"); + + /* + * Add SHELL_PATH so in the event exec fails with ENOEXEC we can + * attempt to interpret the command with 'sh'. + */ + argv_array_push(out, SHELL_PATH); + + if (cmd->git_cmd) { + argv_array_push(out, "git"); + argv_array_pushv(out, cmd->argv); + } else if (cmd->use_shell) { + prepare_shell_cmd(out, cmd->argv); + } else { + argv_array_pushv(out, cmd->argv); + } + /* - * execvp failed. If possible, we'd like to let start_command - * know, so failures like ENOENT can be handled right away; but - * otherwise, finish_command will still report the error. + * If there are no '/' characters in the command then perform a path + * lookup and use the resolved path as the command to exec. If there + * are no '/' characters or if the command wasn't found in the path, + * have exec attempt to invoke the command directly. */ - xwrite(child_notifier, "", 1); + if (!strchr(out->argv[1], '/')) { + char *program = locate_in_PATH(out->argv[1]); + if (program) { + free((char *)out->argv[1]); + out->argv[1] = program; + } + } } -static NORETURN void die_child(const char *err, va_list params) +static char **prep_childenv(const char *const *deltaenv) { - vwritef(child_err, "fatal: ", err, params); - exit(128); + extern char **environ; + char **childenv; + struct string_list env = STRING_LIST_INIT_DUP; + struct strbuf key = STRBUF_INIT; + const char *const *p; + int i; + + /* Construct a sorted string list consisting of the current environ */ + for (p = (const char *const *) environ; p && *p; p++) { + const char *equals = strchr(*p, '='); + + if (equals) { + strbuf_reset(&key); + strbuf_add(&key, *p, equals - *p); + string_list_append(&env, key.buf)->util = (void *) *p; + } else { + string_list_append(&env, *p)->util = (void *) *p; + } + } + string_list_sort(&env); + + /* Merge in 'deltaenv' with the current environ */ + for (p = deltaenv; p && *p; p++) { + const char *equals = strchr(*p, '='); + + if (equals) { + /* ('key=value'), insert or replace entry */ + strbuf_reset(&key); + strbuf_add(&key, *p, equals - *p); + string_list_insert(&env, key.buf)->util = (void *) *p; + } else { + /* otherwise ('key') remove existing entry */ + string_list_remove(&env, *p, 0); + } + } + + /* Create an array of 'char *' to be used as the childenv */ + childenv = xmalloc((env.nr + 1) * sizeof(char *)); + for (i = 0; i < env.nr; i++) + childenv[i] = env.items[i].util; + childenv[env.nr] = NULL; + + string_list_clear(&env, 0); + strbuf_release(&key); + return childenv; +} + +struct atfork_state { +#ifndef NO_PTHREADS + int cs; +#endif + sigset_t old; +}; + +#ifndef NO_PTHREADS +static void bug_die(int err, const char *msg) +{ + if (err) { + errno = err; + die_errno("BUG: %s", msg); + } } +#endif -static void error_child(const char *err, va_list params) +static void atfork_prepare(struct atfork_state *as) { - vwritef(child_err, "error: ", err, params); + sigset_t all; + + if (sigfillset(&all)) + die_errno("sigfillset"); +#ifdef NO_PTHREADS + if (sigprocmask(SIG_SETMASK, &all, &as->old)) + die_errno("sigprocmask"); +#else + bug_die(pthread_sigmask(SIG_SETMASK, &all, &as->old), + "blocking all signals"); + bug_die(pthread_setcancelstate(PTHREAD_CANCEL_DISABLE, &as->cs), + "disabling cancellation"); +#endif } + +static void atfork_parent(struct atfork_state *as) +{ +#ifdef NO_PTHREADS + if (sigprocmask(SIG_SETMASK, &as->old, NULL)) + die_errno("sigprocmask"); +#else + bug_die(pthread_setcancelstate(as->cs, NULL), + "re-enabling cancellation"); + bug_die(pthread_sigmask(SIG_SETMASK, &as->old, NULL), + "restoring signal mask"); #endif +} +#endif /* GIT_WINDOWS_NATIVE */ static inline void set_cloexec(int fd) { @@ -232,7 +517,7 @@ static inline void set_cloexec(int fd) fcntl(fd, F_SETFD, flags | FD_CLOEXEC); } -static int wait_or_whine(pid_t pid, const char *argv0) +static int wait_or_whine(pid_t pid, const char *argv0, int in_signal) { int status, code = -1; pid_t waiting; @@ -240,15 +525,17 @@ static int wait_or_whine(pid_t pid, const char *argv0) while ((waiting = waitpid(pid, &status, 0)) < 0 && errno == EINTR) ; /* nothing */ + if (in_signal) + return 0; if (waiting < 0) { failed_errno = errno; - error("waitpid for %s failed: %s", argv0, strerror(errno)); + error_errno("waitpid for %s failed", argv0); } else if (waiting != pid) { error("waitpid is confused (%s)", argv0); } else if (WIFSIGNALED(status)) { code = WTERMSIG(status); - if (code != SIGINT && code != SIGQUIT) + if (code != SIGINT && code != SIGQUIT && code != SIGPIPE) error("%s died of signal %d", argv0, code); /* * This return value is chosen so that code & 0xff @@ -258,13 +545,6 @@ static int wait_or_whine(pid_t pid, const char *argv0) code += 128; } else if (WIFEXITED(status)) { code = WEXITSTATUS(status); - /* - * Convert special exit code when execvp failed. - */ - if (code == 127) { - code = -1; - failed_errno = ENOENT; - } } else { error("waitpid is confused (%s)", argv0); } @@ -336,8 +616,7 @@ int start_command(struct child_process *cmd) fail_pipe: error("cannot create %s pipe for %s: %s", str, cmd->argv[0], strerror(failed_errno)); - argv_array_clear(&cmd->args); - argv_array_clear(&cmd->env_array); + child_process_clear(cmd); errno = failed_errno; return -1; } @@ -350,116 +629,155 @@ fail_pipe: #ifndef GIT_WINDOWS_NATIVE { int notify_pipe[2]; + int null_fd = -1; + char **childenv; + struct argv_array argv = ARGV_ARRAY_INIT; + struct child_err cerr; + struct atfork_state as; + if (pipe(notify_pipe)) notify_pipe[0] = notify_pipe[1] = -1; + if (cmd->no_stdin || cmd->no_stdout || cmd->no_stderr) { + null_fd = open("/dev/null", O_RDWR | O_CLOEXEC); + if (null_fd < 0) + die_errno(_("open /dev/null failed")); + set_cloexec(null_fd); + } + + prepare_cmd(&argv, cmd); + childenv = prep_childenv(cmd->env); + atfork_prepare(&as); + + /* + * NOTE: In order to prevent deadlocking when using threads special + * care should be taken with the function calls made in between the + * fork() and exec() calls. No calls should be made to functions which + * require acquiring a lock (e.g. malloc) as the lock could have been + * held by another thread at the time of forking, causing the lock to + * never be released in the child process. This means only + * Async-Signal-Safe functions are permitted in the child. + */ cmd->pid = fork(); failed_errno = errno; if (!cmd->pid) { + int sig; /* - * Redirect the channel to write syscall error messages to - * before redirecting the process's stderr so that all die() - * in subsequent call paths use the parent's stderr. + * Ensure the default die/error/warn routines do not get + * called, they can take stdio locks and malloc. */ - if (cmd->no_stderr || need_err) { - child_err = dup(2); - set_cloexec(child_err); - } - set_die_routine(die_child); - set_error_routine(error_child); + set_die_routine(child_die_fn); + set_error_routine(child_error_fn); + set_warn_routine(child_warn_fn); close(notify_pipe[0]); set_cloexec(notify_pipe[1]); child_notifier = notify_pipe[1]; - atexit(notify_parent); if (cmd->no_stdin) - dup_devnull(0); + child_dup2(null_fd, 0); else if (need_in) { - dup2(fdin[0], 0); - close_pair(fdin); + child_dup2(fdin[0], 0); + child_close_pair(fdin); } else if (cmd->in) { - dup2(cmd->in, 0); - close(cmd->in); + child_dup2(cmd->in, 0); + child_close(cmd->in); } if (cmd->no_stderr) - dup_devnull(2); + child_dup2(null_fd, 2); else if (need_err) { - dup2(fderr[1], 2); - close_pair(fderr); + child_dup2(fderr[1], 2); + child_close_pair(fderr); } else if (cmd->err > 1) { - dup2(cmd->err, 2); - close(cmd->err); + child_dup2(cmd->err, 2); + child_close(cmd->err); } if (cmd->no_stdout) - dup_devnull(1); + child_dup2(null_fd, 1); else if (cmd->stdout_to_stderr) - dup2(2, 1); + child_dup2(2, 1); else if (need_out) { - dup2(fdout[1], 1); - close_pair(fdout); + child_dup2(fdout[1], 1); + child_close_pair(fdout); } else if (cmd->out > 1) { - dup2(cmd->out, 1); - close(cmd->out); + child_dup2(cmd->out, 1); + child_close(cmd->out); } if (cmd->dir && chdir(cmd->dir)) - die_errno("exec '%s': cd to '%s' failed", cmd->argv[0], - cmd->dir); - if (cmd->env) { - for (; *cmd->env; cmd->env++) { - if (strchr(*cmd->env, '=')) - putenv((char *)*cmd->env); - else - unsetenv(*cmd->env); - } + child_die(CHILD_ERR_CHDIR); + + /* + * restore default signal handlers here, in case + * we catch a signal right before execve below + */ + for (sig = 1; sig < NSIG; sig++) { + /* ignored signals get reset to SIG_DFL on execve */ + if (signal(sig, SIG_DFL) == SIG_IGN) + signal(sig, SIG_IGN); } - if (cmd->git_cmd) - execv_git_cmd(cmd->argv); - else if (cmd->use_shell) - execv_shell_cmd(cmd->argv); - else - sane_execvp(cmd->argv[0], (char *const*) cmd->argv); + + if (sigprocmask(SIG_SETMASK, &as.old, NULL) != 0) + child_die(CHILD_ERR_SIGPROCMASK); + + /* + * Attempt to exec using the command and arguments starting at + * argv.argv[1]. argv.argv[0] contains SHELL_PATH which will + * be used in the event exec failed with ENOEXEC at which point + * we will try to interpret the command using 'sh'. + */ + execve(argv.argv[1], (char *const *) argv.argv + 1, + (char *const *) childenv); + if (errno == ENOEXEC) + execve(argv.argv[0], (char *const *) argv.argv, + (char *const *) childenv); + if (errno == ENOENT) { - if (!cmd->silent_exec_failure) - error("cannot run %s: %s", cmd->argv[0], - strerror(ENOENT)); - exit(127); + if (cmd->silent_exec_failure) + child_die(CHILD_ERR_SILENT); + child_die(CHILD_ERR_ENOENT); } else { - die_errno("cannot exec '%s'", cmd->argv[0]); + child_die(CHILD_ERR_ERRNO); } } + atfork_parent(&as); if (cmd->pid < 0) - error("cannot fork() for %s: %s", cmd->argv[0], - strerror(errno)); + error_errno("cannot fork() for %s", cmd->argv[0]); else if (cmd->clean_on_exit) - mark_child_for_cleanup(cmd->pid); + mark_child_for_cleanup(cmd->pid, cmd); /* - * Wait for child's execvp. If the execvp succeeds (or if fork() + * Wait for child's exec. If the exec succeeds (or if fork() * failed), EOF is seen immediately by the parent. Otherwise, the - * child process sends a single byte. + * child process sends a child_err struct. * Note that use of this infrastructure is completely advisory, * therefore, we keep error checks minimal. */ close(notify_pipe[1]); - if (read(notify_pipe[0], ¬ify_pipe[1], 1) == 1) { + if (xread(notify_pipe[0], &cerr, sizeof(cerr)) == sizeof(cerr)) { /* - * At this point we know that fork() succeeded, but execvp() + * At this point we know that fork() succeeded, but exec() * failed. Errors have been reported to our stderr. */ - wait_or_whine(cmd->pid, cmd->argv[0]); + wait_or_whine(cmd->pid, cmd->argv[0], 0); + child_err_spew(cmd, &cerr); failed_errno = errno; cmd->pid = -1; } close(notify_pipe[0]); + + if (null_fd >= 0) + close(null_fd); + argv_array_clear(&argv); + free(childenv); } #else { int fhin = 0, fhout = 1, fherr = 2; const char **sargv = cmd->argv; + struct argv_array nargv = ARGV_ARRAY_INIT; if (cmd->no_stdin) fhin = open("/dev/null", O_RDWR); @@ -485,21 +803,19 @@ fail_pipe: fhout = dup(cmd->out); if (cmd->git_cmd) - cmd->argv = prepare_git_cmd(cmd->argv); + cmd->argv = prepare_git_cmd(&nargv, cmd->argv); else if (cmd->use_shell) - cmd->argv = prepare_shell_cmd(cmd->argv); + cmd->argv = prepare_shell_cmd(&nargv, cmd->argv); cmd->pid = mingw_spawnvpe(cmd->argv[0], cmd->argv, (char**) cmd->env, cmd->dir, fhin, fhout, fherr); failed_errno = errno; if (cmd->pid < 0 && (!cmd->silent_exec_failure || errno != ENOENT)) - error("cannot spawn %s: %s", cmd->argv[0], strerror(errno)); + error_errno("cannot spawn %s", cmd->argv[0]); if (cmd->clean_on_exit && cmd->pid >= 0) - mark_child_for_cleanup(cmd->pid); - - if (cmd->git_cmd) - free(cmd->argv); + mark_child_for_cleanup(cmd->pid, cmd); + argv_array_clear(&nargv); cmd->argv = sargv; if (fhin != 0) close(fhin); @@ -523,8 +839,7 @@ fail_pipe: close_pair(fderr); else if (cmd->err) close(cmd->err); - argv_array_clear(&cmd->args); - argv_array_clear(&cmd->env_array); + child_process_clear(cmd); errno = failed_errno; return -1; } @@ -549,12 +864,17 @@ fail_pipe: int finish_command(struct child_process *cmd) { - int ret = wait_or_whine(cmd->pid, cmd->argv[0]); - argv_array_clear(&cmd->args); - argv_array_clear(&cmd->env_array); + int ret = wait_or_whine(cmd->pid, cmd->argv[0], 0); + child_process_clear(cmd); return ret; } +int finish_command_in_signal(struct child_process *cmd) +{ + return wait_or_whine(cmd->pid, cmd->argv[0], 1); +} + + int run_command(struct child_process *cmd) { int code; @@ -599,6 +919,16 @@ static void *run_thread(void *data) struct async *async = data; intptr_t ret; + if (async->isolate_sigpipe) { + sigset_t mask; + sigemptyset(&mask); + sigaddset(&mask, SIGPIPE); + if (pthread_sigmask(SIG_BLOCK, &mask, NULL) < 0) { + ret = error("unable to block SIGPIPE in async thread"); + return (void *)ret; + } + } + pthread_setspecific(async_key, async); ret = async->proc(async->proc_in, async->proc_out, async->data); return (void *)ret; @@ -608,7 +938,7 @@ static NORETURN void die_async(const char *err, va_list params) { vreportf("fatal: ", err, params); - if (!pthread_equal(main_thread, pthread_self())) { + if (in_async()) { struct async *async = pthread_getspecific(async_key); if (async->proc_in >= 0) close(async->proc_in); @@ -627,6 +957,18 @@ static int async_die_is_recursing(void) return ret != NULL; } +int in_async(void) +{ + if (!main_thread_set) + return 0; /* no asyncs started yet */ + return !pthread_equal(main_thread, pthread_self()); +} + +static void NORETURN async_exit(int code) +{ + pthread_exit((void *)(intptr_t)code); +} + #else static struct { @@ -666,8 +1008,32 @@ int git_atexit(void (*handler)(void)) } #define atexit git_atexit +static int process_is_async; +int in_async(void) +{ + return process_is_async; +} + +static void NORETURN async_exit(int code) +{ + exit(code); +} + #endif +void check_pipe(int err) +{ + if (err == EPIPE) { + if (in_async()) + async_exit(141); + + signal(SIGPIPE, SIG_DFL); + raise(SIGPIPE); + /* Should never happen, but just in case... */ + exit(141); + } +} + int start_async(struct async *async) { int need_in, need_out; @@ -679,7 +1045,7 @@ int start_async(struct async *async) if (pipe(fdin) < 0) { if (async->out > 0) close(async->out); - return error("cannot create pipe: %s", strerror(errno)); + return error_errno("cannot create pipe"); } async->in = fdin[1]; } @@ -691,7 +1057,7 @@ int start_async(struct async *async) close_pair(fdin); else if (async->in) close(async->in); - return error("cannot create pipe: %s", strerror(errno)); + return error_errno("cannot create pipe"); } async->out = fdout[0]; } @@ -716,7 +1082,7 @@ int start_async(struct async *async) async->pid = fork(); if (async->pid < 0) { - error("fork (async) failed: %s", strerror(errno)); + error_errno("fork (async) failed"); goto error; } if (!async->pid) { @@ -725,10 +1091,11 @@ int start_async(struct async *async) if (need_out) close(fdout[0]); git_atexit_clear(); + process_is_async = 1; exit(!!async->proc(proc_in, proc_out, async->data)); } - mark_child_for_cleanup(async->pid); + mark_child_for_cleanup(async->pid, NULL); if (need_in) close(fdin[0]); @@ -762,7 +1129,7 @@ int start_async(struct async *async) { int err = pthread_create(&async->tid, NULL, run_thread, async); if (err) { - error("cannot create thread: %s", strerror(err)); + error_errno("cannot create thread"); goto error; } } @@ -785,7 +1152,7 @@ error: int finish_async(struct async *async) { #ifdef NO_PTHREADS - return wait_or_whine(async->pid, "child process"); + return wait_or_whine(async->pid, "child process", 0); #else void *ret = (void *)(intptr_t)(-1); @@ -795,13 +1162,21 @@ int finish_async(struct async *async) #endif } -char *find_hook(const char *name) +const char *find_hook(const char *name) { - char *path = git_path("hooks/%s", name); - if (access(path, X_OK) < 0) - path = NULL; - - return path; + static struct strbuf path = STRBUF_INIT; + + strbuf_reset(&path); + strbuf_git_path(&path, "hooks/%s", name); + if (access(path.buf, X_OK) < 0) { +#ifdef STRIP_EXTENSION + strbuf_addstr(&path, STRIP_EXTENSION); + if (access(path.buf, X_OK) >= 0) + return path.buf; +#endif + return NULL; + } + return path.buf; } int run_hook_ve(const char *const *env, const char *name, va_list args) @@ -835,18 +1210,475 @@ int run_hook_le(const char *const *env, const char *name, ...) return ret; } -int capture_command(struct child_process *cmd, struct strbuf *buf, size_t hint) +struct io_pump { + /* initialized by caller */ + int fd; + int type; /* POLLOUT or POLLIN */ + union { + struct { + const char *buf; + size_t len; + } out; + struct { + struct strbuf *buf; + size_t hint; + } in; + } u; + + /* returned by pump_io */ + int error; /* 0 for success, otherwise errno */ + + /* internal use */ + struct pollfd *pfd; +}; + +static int pump_io_round(struct io_pump *slots, int nr, struct pollfd *pfd) +{ + int pollsize = 0; + int i; + + for (i = 0; i < nr; i++) { + struct io_pump *io = &slots[i]; + if (io->fd < 0) + continue; + pfd[pollsize].fd = io->fd; + pfd[pollsize].events = io->type; + io->pfd = &pfd[pollsize++]; + } + + if (!pollsize) + return 0; + + if (poll(pfd, pollsize, -1) < 0) { + if (errno == EINTR) + return 1; + die_errno("poll failed"); + } + + for (i = 0; i < nr; i++) { + struct io_pump *io = &slots[i]; + + if (io->fd < 0) + continue; + + if (!(io->pfd->revents & (POLLOUT|POLLIN|POLLHUP|POLLERR|POLLNVAL))) + continue; + + if (io->type == POLLOUT) { + ssize_t len = xwrite(io->fd, + io->u.out.buf, io->u.out.len); + if (len < 0) { + io->error = errno; + close(io->fd); + io->fd = -1; + } else { + io->u.out.buf += len; + io->u.out.len -= len; + if (!io->u.out.len) { + close(io->fd); + io->fd = -1; + } + } + } + + if (io->type == POLLIN) { + ssize_t len = strbuf_read_once(io->u.in.buf, + io->fd, io->u.in.hint); + if (len < 0) + io->error = errno; + if (len <= 0) { + close(io->fd); + io->fd = -1; + } + } + } + + return 1; +} + +static int pump_io(struct io_pump *slots, int nr) +{ + struct pollfd *pfd; + int i; + + for (i = 0; i < nr; i++) + slots[i].error = 0; + + ALLOC_ARRAY(pfd, nr); + while (pump_io_round(slots, nr, pfd)) + ; /* nothing */ + free(pfd); + + /* There may be multiple errno values, so just pick the first. */ + for (i = 0; i < nr; i++) { + if (slots[i].error) { + errno = slots[i].error; + return -1; + } + } + return 0; +} + + +int pipe_command(struct child_process *cmd, + const char *in, size_t in_len, + struct strbuf *out, size_t out_hint, + struct strbuf *err, size_t err_hint) { - cmd->out = -1; + struct io_pump io[3]; + int nr = 0; + + if (in) + cmd->in = -1; + if (out) + cmd->out = -1; + if (err) + cmd->err = -1; + if (start_command(cmd) < 0) return -1; - if (strbuf_read(buf, cmd->out, hint) < 0) { - close(cmd->out); + if (in) { + io[nr].fd = cmd->in; + io[nr].type = POLLOUT; + io[nr].u.out.buf = in; + io[nr].u.out.len = in_len; + nr++; + } + if (out) { + io[nr].fd = cmd->out; + io[nr].type = POLLIN; + io[nr].u.in.buf = out; + io[nr].u.in.hint = out_hint; + nr++; + } + if (err) { + io[nr].fd = cmd->err; + io[nr].type = POLLIN; + io[nr].u.in.buf = err; + io[nr].u.in.hint = err_hint; + nr++; + } + + if (pump_io(io, nr) < 0) { finish_command(cmd); /* throw away exit code */ return -1; } - close(cmd->out); return finish_command(cmd); } + +enum child_state { + GIT_CP_FREE, + GIT_CP_WORKING, + GIT_CP_WAIT_CLEANUP, +}; + +struct parallel_processes { + void *data; + + int max_processes; + int nr_processes; + + get_next_task_fn get_next_task; + start_failure_fn start_failure; + task_finished_fn task_finished; + + struct { + enum child_state state; + struct child_process process; + struct strbuf err; + void *data; + } *children; + /* + * The struct pollfd is logically part of *children, + * but the system call expects it as its own array. + */ + struct pollfd *pfd; + + unsigned shutdown : 1; + + int output_owner; + struct strbuf buffered_output; /* of finished children */ +}; + +static int default_start_failure(struct strbuf *out, + void *pp_cb, + void *pp_task_cb) +{ + return 0; +} + +static int default_task_finished(int result, + struct strbuf *out, + void *pp_cb, + void *pp_task_cb) +{ + return 0; +} + +static void kill_children(struct parallel_processes *pp, int signo) +{ + int i, n = pp->max_processes; + + for (i = 0; i < n; i++) + if (pp->children[i].state == GIT_CP_WORKING) + kill(pp->children[i].process.pid, signo); +} + +static struct parallel_processes *pp_for_signal; + +static void handle_children_on_signal(int signo) +{ + kill_children(pp_for_signal, signo); + sigchain_pop(signo); + raise(signo); +} + +static void pp_init(struct parallel_processes *pp, + int n, + get_next_task_fn get_next_task, + start_failure_fn start_failure, + task_finished_fn task_finished, + void *data) +{ + int i; + + if (n < 1) + n = online_cpus(); + + pp->max_processes = n; + + trace_printf("run_processes_parallel: preparing to run up to %d tasks", n); + + pp->data = data; + if (!get_next_task) + die("BUG: you need to specify a get_next_task function"); + pp->get_next_task = get_next_task; + + pp->start_failure = start_failure ? start_failure : default_start_failure; + pp->task_finished = task_finished ? task_finished : default_task_finished; + + pp->nr_processes = 0; + pp->output_owner = 0; + pp->shutdown = 0; + pp->children = xcalloc(n, sizeof(*pp->children)); + pp->pfd = xcalloc(n, sizeof(*pp->pfd)); + strbuf_init(&pp->buffered_output, 0); + + for (i = 0; i < n; i++) { + strbuf_init(&pp->children[i].err, 0); + child_process_init(&pp->children[i].process); + pp->pfd[i].events = POLLIN | POLLHUP; + pp->pfd[i].fd = -1; + } + + pp_for_signal = pp; + sigchain_push_common(handle_children_on_signal); +} + +static void pp_cleanup(struct parallel_processes *pp) +{ + int i; + + trace_printf("run_processes_parallel: done"); + for (i = 0; i < pp->max_processes; i++) { + strbuf_release(&pp->children[i].err); + child_process_clear(&pp->children[i].process); + } + + free(pp->children); + free(pp->pfd); + + /* + * When get_next_task added messages to the buffer in its last + * iteration, the buffered output is non empty. + */ + strbuf_write(&pp->buffered_output, stderr); + strbuf_release(&pp->buffered_output); + + sigchain_pop_common(); +} + +/* returns + * 0 if a new task was started. + * 1 if no new jobs was started (get_next_task ran out of work, non critical + * problem with starting a new command) + * <0 no new job was started, user wishes to shutdown early. Use negative code + * to signal the children. + */ +static int pp_start_one(struct parallel_processes *pp) +{ + int i, code; + + for (i = 0; i < pp->max_processes; i++) + if (pp->children[i].state == GIT_CP_FREE) + break; + if (i == pp->max_processes) + die("BUG: bookkeeping is hard"); + + code = pp->get_next_task(&pp->children[i].process, + &pp->children[i].err, + pp->data, + &pp->children[i].data); + if (!code) { + strbuf_addbuf(&pp->buffered_output, &pp->children[i].err); + strbuf_reset(&pp->children[i].err); + return 1; + } + pp->children[i].process.err = -1; + pp->children[i].process.stdout_to_stderr = 1; + pp->children[i].process.no_stdin = 1; + + if (start_command(&pp->children[i].process)) { + code = pp->start_failure(&pp->children[i].err, + pp->data, + &pp->children[i].data); + strbuf_addbuf(&pp->buffered_output, &pp->children[i].err); + strbuf_reset(&pp->children[i].err); + if (code) + pp->shutdown = 1; + return code; + } + + pp->nr_processes++; + pp->children[i].state = GIT_CP_WORKING; + pp->pfd[i].fd = pp->children[i].process.err; + return 0; +} + +static void pp_buffer_stderr(struct parallel_processes *pp, int output_timeout) +{ + int i; + + while ((i = poll(pp->pfd, pp->max_processes, output_timeout)) < 0) { + if (errno == EINTR) + continue; + pp_cleanup(pp); + die_errno("poll"); + } + + /* Buffer output from all pipes. */ + for (i = 0; i < pp->max_processes; i++) { + if (pp->children[i].state == GIT_CP_WORKING && + pp->pfd[i].revents & (POLLIN | POLLHUP)) { + int n = strbuf_read_once(&pp->children[i].err, + pp->children[i].process.err, 0); + if (n == 0) { + close(pp->children[i].process.err); + pp->children[i].state = GIT_CP_WAIT_CLEANUP; + } else if (n < 0) + if (errno != EAGAIN) + die_errno("read"); + } + } +} + +static void pp_output(struct parallel_processes *pp) +{ + int i = pp->output_owner; + if (pp->children[i].state == GIT_CP_WORKING && + pp->children[i].err.len) { + strbuf_write(&pp->children[i].err, stderr); + strbuf_reset(&pp->children[i].err); + } +} + +static int pp_collect_finished(struct parallel_processes *pp) +{ + int i, code; + int n = pp->max_processes; + int result = 0; + + while (pp->nr_processes > 0) { + for (i = 0; i < pp->max_processes; i++) + if (pp->children[i].state == GIT_CP_WAIT_CLEANUP) + break; + if (i == pp->max_processes) + break; + + code = finish_command(&pp->children[i].process); + + code = pp->task_finished(code, + &pp->children[i].err, pp->data, + &pp->children[i].data); + + if (code) + result = code; + if (code < 0) + break; + + pp->nr_processes--; + pp->children[i].state = GIT_CP_FREE; + pp->pfd[i].fd = -1; + child_process_init(&pp->children[i].process); + + if (i != pp->output_owner) { + strbuf_addbuf(&pp->buffered_output, &pp->children[i].err); + strbuf_reset(&pp->children[i].err); + } else { + strbuf_write(&pp->children[i].err, stderr); + strbuf_reset(&pp->children[i].err); + + /* Output all other finished child processes */ + strbuf_write(&pp->buffered_output, stderr); + strbuf_reset(&pp->buffered_output); + + /* + * Pick next process to output live. + * NEEDSWORK: + * For now we pick it randomly by doing a round + * robin. Later we may want to pick the one with + * the most output or the longest or shortest + * running process time. + */ + for (i = 0; i < n; i++) + if (pp->children[(pp->output_owner + i) % n].state == GIT_CP_WORKING) + break; + pp->output_owner = (pp->output_owner + i) % n; + } + } + return result; +} + +int run_processes_parallel(int n, + get_next_task_fn get_next_task, + start_failure_fn start_failure, + task_finished_fn task_finished, + void *pp_cb) +{ + int i, code; + int output_timeout = 100; + int spawn_cap = 4; + struct parallel_processes pp; + + pp_init(&pp, n, get_next_task, start_failure, task_finished, pp_cb); + while (1) { + for (i = 0; + i < spawn_cap && !pp.shutdown && + pp.nr_processes < pp.max_processes; + i++) { + code = pp_start_one(&pp); + if (!code) + continue; + if (code < 0) { + pp.shutdown = 1; + kill_children(&pp, -code); + } + break; + } + if (!pp.nr_processes) + break; + pp_buffer_stderr(&pp, output_timeout); + pp_output(&pp); + code = pp_collect_finished(&pp); + if (code) { + pp.shutdown = 1; + if (code < 0) + kill_children(&pp, -code); + } + } + + pp_cleanup(&pp); + return 0; +} |