From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena Schedulers on the default cid mapping treat [0, nr_online_cids) as the online set and restart on hotplug. Schedulers that install their own mapping with scx_bpf_cid_override() have no way to learn which cids are online: the count no longer identifies members and the CPU-form cpumask is unusable from cid programs. This is an obvious hole in the cid API. Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's arena, allocated alongside the per-CPU scratch masks and populated after the cid mapping is finalized and before ops.init(), for child schedulers too. The pointer stays valid through ops.exit() with no reference to take. It is the arena offset as a void pointer, the same form struct_ops arena arguments arrive in. The verifier types the void return as a scalar for the program's arena cast. The mask follows the SCX hotplug notifications: seeded from cpu_active_mask and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask only inside a hotplug transition. Updates walk the scheduler list under the lock that also serializes unlinking. Reads are live, not atomic snapshots. Root initialization excludes hotplug. v2: Reworded the getter kerneldoc (Andrea Righi). Signed-off-by: Tejun Heo Reviewed-by: Andrea Righi --- fs/binfmt_script.c | 159 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 159 insertions(+) create mode 100644 fs/binfmt_script.c (limited to 'fs/binfmt_script.c') diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c new file mode 100644 index 000000000..637daf6e4 --- /dev/null +++ b/fs/binfmt_script.c @@ -0,0 +1,159 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/binfmt_script.c + * + * Copyright (C) 1996 Martin von Löwis + * original #!-checking implemented by tytso. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline const char *next_non_spacetab(const char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline const char *next_terminator(const char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + +static int load_script(struct linux_binprm *bprm) +{ + const char *i_name, *i_sep, *i_arg, *i_end, *buf_end; + struct file *file; + int retval; + + /* Not ours to exec if we don't start with "#!". */ + if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) + return -ENOEXEC; + + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + i_end = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!i_end) { + i_end = next_non_spacetab(bprm->buf + 2, buf_end); + if (!i_end) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(i_end, buf_end)) + return -ENOEXEC; + i_end = buf_end; + } + /* Trim any trailing spaces/tabs from i_end */ + while (spacetab(i_end[-1])) + i_end--; + + /* Skip over leading spaces/tabs */ + i_name = next_non_spacetab(bprm->buf+2, i_end); + if (!i_name || (i_name == i_end)) + return -ENOEXEC; /* No interpreter name found */ + + /* Is there an optional argument? */ + i_arg = NULL; + i_sep = next_terminator(i_name, i_end); + if (i_sep && (*i_sep != '\0')) + i_arg = next_non_spacetab(i_sep, i_end); + + /* + * If the script filename will be inaccessible after exec, typically + * because it is a "/dev/fd//.." path against an O_CLOEXEC fd, give + * up now (on the assumption that the interpreter will want to load + * this file). + */ + if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) + return -ENOENT; + + /* + * OK, we've parsed out the interpreter name and + * (optional) argument. + * Splice in (1) the interpreter's name for argv[0] + * (2) (optional) argument to interpreter + * (3) filename of shell script (replace argv[0]) + * + * This is done in reverse order, because of how the + * user environment and arguments are stored. + */ + retval = remove_arg_zero(bprm); + if (retval) + return retval; + retval = copy_string_kernel(bprm->interp, bprm); + if (retval < 0) + return retval; + bprm->argc++; + *((char *)i_end) = '\0'; + if (i_arg) { + *((char *)i_sep) = '\0'; + retval = copy_string_kernel(i_arg, bprm); + if (retval < 0) + return retval; + bprm->argc++; + } + retval = copy_string_kernel(i_name, bprm); + if (retval) + return retval; + bprm->argc++; + retval = bprm_change_interp(i_name, bprm); + if (retval < 0) + return retval; + + /* + * OK, now restart the process with the interpreter's dentry. + */ + file = open_exec(i_name); + if (IS_ERR(file)) + return PTR_ERR(file); + + bprm->interpreter = file; + return 0; +} + +static struct linux_binfmt script_format = { + .module = THIS_MODULE, + .load_binary = load_script, +}; + +static int __init init_script_binfmt(void) +{ + register_binfmt(&script_format); + return 0; +} + +static void __exit exit_script_binfmt(void) +{ + unregister_binfmt(&script_format); +} + +core_initcall(init_script_binfmt); +module_exit(exit_script_binfmt); +MODULE_DESCRIPTION("Kernel support for scripts starting with #!"); +MODULE_LICENSE("GPL"); -- cgit v1.3.1