seccomp/cache: Report cache data through /proc/pid/seccomp_cache

Currently the kernel does not provide an infrastructure to translate
architecture numbers to a human-readable name. Translating syscall
numbers to syscall names is possible through FTRACE_SYSCALL
infrastructure but it does not provide support for compat syscalls.

This will create a file for each PID as /proc/pid/seccomp_cache.
The file will be empty when no seccomp filters are loaded, or be
in the format of:
<arch name> <decimal syscall number> <ALLOW | FILTER>
where ALLOW means the cache is guaranteed to allow the syscall,
and filter means the cache will pass the syscall to the BPF filter.

For the docker default profile on x86_64 it looks like:
x86_64 0 ALLOW
x86_64 1 ALLOW
x86_64 2 ALLOW
x86_64 3 ALLOW
[...]
x86_64 132 ALLOW
x86_64 133 ALLOW
x86_64 134 FILTER
x86_64 135 FILTER
x86_64 136 FILTER
x86_64 137 ALLOW
x86_64 138 ALLOW
x86_64 139 FILTER
x86_64 140 ALLOW
x86_64 141 ALLOW
[...]

This file is guarded by CONFIG_SECCOMP_CACHE_DEBUG with a default
of N because I think certain users of seccomp might not want the
application to know which syscalls are definitely usable. For
the same reason, it is also guarded by CAP_SYS_ADMIN.

Suggested-by: Jann Horn <jannh@google.com>
Link: https://lore.kernel.org/lkml/CAG48ez3Ofqp4crXGksLmZY6=fGrF_tWyUCg7PBkAetvbbOPeOA@mail.gmail.com/
Signed-off-by: YiFei Zhu <yifeifz2@illinois.edu>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/94e663fa53136f5a11f432c661794d1ee7060779.1605101222.git.yifeifz2@illinois.edu

1 files changed, 59 insertions, 0 deletions

diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index d8cf468dbe1e..76f524e320b1 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -553,6 +553,9 @@ void seccomp_filter_release(struct task_struct *tsk)
 {
 	struct seccomp_filter *orig = tsk->seccomp.filter;
 
+	/* We are effectively holding the siglock by not having any sighand. */
+	WARN_ON(tsk->sighand != NULL);
+
 	/* Detach task from its filter tree. */
 	tsk->seccomp.filter = NULL;
 	__seccomp_filter_release(orig);
@@ -2335,3 +2338,59 @@ static int __init seccomp_sysctl_init(void)
 device_initcall(seccomp_sysctl_init)
 
 #endif /* CONFIG_SYSCTL */
+
+#ifdef CONFIG_SECCOMP_CACHE_DEBUG
+/* Currently CONFIG_SECCOMP_CACHE_DEBUG implies SECCOMP_ARCH_NATIVE */
+static void proc_pid_seccomp_cache_arch(struct seq_file *m, const char *name,
+					const void *bitmap, size_t bitmap_size)
+{
+	int nr;
+
+	for (nr = 0; nr < bitmap_size; nr++) {
+		bool cached = test_bit(nr, bitmap);
+		char *status = cached ? "ALLOW" : "FILTER";
+
+		seq_printf(m, "%s %d %s\n", name, nr, status);
+	}
+}
+
+int proc_pid_seccomp_cache(struct seq_file *m, struct pid_namespace *ns,
+			   struct pid *pid, struct task_struct *task)
+{
+	struct seccomp_filter *f;
+	unsigned long flags;
+
+	/*
+	 * We don't want some sandboxed process to know what their seccomp
+	 * filters consist of.
+	 */
+	if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (!lock_task_sighand(task, &flags))
+		return -ESRCH;
+
+	f = READ_ONCE(task->seccomp.filter);
+	if (!f) {
+		unlock_task_sighand(task, &flags);
+		return 0;
+	}
+
+	/* prevent filter from being freed while we are printing it */
+	__get_seccomp_filter(f);
+	unlock_task_sighand(task, &flags);
+
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_NATIVE_NAME,
+				    f->cache.allow_native,
+				    SECCOMP_ARCH_NATIVE_NR);
+
+#ifdef SECCOMP_ARCH_COMPAT
+	proc_pid_seccomp_cache_arch(m, SECCOMP_ARCH_COMPAT_NAME,
+				    f->cache.allow_compat,
+				    SECCOMP_ARCH_COMPAT_NR);
+#endif /* SECCOMP_ARCH_COMPAT */
+
+	__put_seccomp_filter(f);
+	return 0;
+}
+#endif /* CONFIG_SECCOMP_CACHE_DEBUG */