selftests/bpf: Test packet range of pointers sharing an idgrafted

Add tests where two packet pointers share an id and tightening one
pointer's umax from its var_off would put it less than their constant
distance from the other's umax: with an index & 0x38 capped at 50, the
base pointer keeps umax 50, so the pointer 8 bytes further on must keep
umax 58, even though its known bits allow at most 56.

These refused a valid program or accepted an out-of-bounds access before
the fix:

- check the advanced copy, load through the base: valid, was refused;
- check the base, load the byte at base + 1 through a copy advanced by
  8: was accepted;
- check base + 4, load 4 bytes at base + 2 through base + 8: reads two
  bytes past the checked range, was accepted;
- the same as the second with data_meta pointers checked against data:
  was accepted.

These pass with and without the fix and cover nearby paths:

- subtract an unknown scalar from a checked pointer and load below it
  (the range is kept across a new id);
- reach a load through two paths whose checks cover 8 and 7 bytes after
  the loaded pointer; the second path must not be pruned by the first;
- spill a copy of a pointer, check the pointer, fill the copy and load
  one byte past the checked range: the load is refused, and the copy
  has the range of the check.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20261001145255.855630-2-alexei.starovoitov@gmail.com
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>

1 files changed, 159 insertions, 0 deletions

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 <linux/module.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/binfmts.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+
+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/<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");