seccomp: add SECCOMP_RET_ERRNO

This change adds the SECCOMP_RET_ERRNO as a valid return value from a
seccomp filter.  Additionally, it makes the first use of the lower
16-bits for storing a filter-supplied errno.  16-bits is more than
enough for the errno-base.h calls.

Returning errors instead of immediately terminating processes that
violate seccomp policy allow for broader use of this functionality
for kernel attack surface reduction.  For example, a linux container
could maintain a whitelist of pre-existing system calls but drop
all new ones with errnos.  This would keep a logically static attack
surface while providing errnos that may allow for graceful failure
without the downside of do_exit() on a bad call.

This change also changes the signature of __secure_computing.  It
appears the only direct caller is the arm entry code and it clobbers
any possible return value (register) immediately.
Signed-off-by: Will Drewry <wad@chromium.org>
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Eric Paris <eparis@redhat.com>

v18: - fix up comments and rebase
     - fix bad var name which was fixed in later revs
     - remove _int() and just change the __secure_computing signature
v16-v17: ...
v15: - use audit_seccomp and add a skip label. (eparis@redhat.com)
     - clean up and pad out return codes (indan@nul.nu)
v14: - no change/rebase
v13: - rebase on to 88ebdda6
v12: - move to WARN_ON if filter is NULL
       (oleg@redhat.com, luto@mit.edu, keescook@chromium.org)
     - return immediately for filter==NULL (keescook@chromium.org)
     - change evaluation to only compare the ACTION so that layered
       errnos don't result in the lowest one being returned.
       (keeschook@chromium.org)
v11: - check for NULL filter (keescook@chromium.org)
v10: - change loaders to fn
 v9: - n/a
 v8: - update Kconfig to note new need for syscall_set_return_value.
     - reordered such that TRAP behavior follows on later.
     - made the for loop a little less indent-y
 v7: - introduced
Signed-off-by: James Morris <james.l.morris@oracle.com>

arch/Kconfig

@@ -220,8 +220,10 @@ config HAVE_ARCH_SECCOMP_FILTER
 	bool
 	help
 	  This symbol should be selected by an architecure if it provides
-	  asm/syscall.h, specifically syscall_get_arguments() and
-	  syscall_get_arch().
+	  asm/syscall.h, specifically syscall_get_arguments(),
+	  syscall_get_arch(), and syscall_set_return_value().  Additionally,
+	  its system call entry path must respect a return value of -1 from
+	  __secure_computing() and/or secure_computing().
 
 config SECCOMP_FILTER
 	def_bool y

include/linux/seccomp.h

@@ -12,13 +12,14 @@
 
 /*
  * All BPF programs must return a 32-bit value.
- * The bottom 16-bits are reserved for future use.
+ * The bottom 16-bits are for optional return data.
  * The upper 16-bits are ordered from least permissive values to most.
  *
  * The ordering ensures that a min_t() over composed return values always
  * selects the least permissive choice.
  */
 #define SECCOMP_RET_KILL	0x00000000U /* kill the task immediately */
+#define SECCOMP_RET_ERRNO	0x00050000U /* returns an errno */
 #define SECCOMP_RET_ALLOW	0x7fff0000U /* allow */
 
 /* Masks for the return value sections. */
@@ -64,11 +65,12 @@ struct seccomp {
 	struct seccomp_filter *filter;
 };
 
-extern void __secure_computing(int);
-static inline void secure_computing(int this_syscall)
+extern int __secure_computing(int);
+static inline int secure_computing(int this_syscall)
 {
 	if (unlikely(test_thread_flag(TIF_SECCOMP)))
-		__secure_computing(this_syscall);
+		return  __secure_computing(this_syscall);
+	return 0;
 }
 
 extern long prctl_get_seccomp(void);

kernel/seccomp.c

@@ -199,15 +199,20 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 static u32 seccomp_run_filters(int syscall)
 {
 	struct seccomp_filter *f;
-	u32 ret = SECCOMP_RET_KILL;
+	u32 ret = SECCOMP_RET_ALLOW;
+
+	/* Ensure unexpected behavior doesn't result in failing open. */
+	if (WARN_ON(current->seccomp.filter == NULL))
+		return SECCOMP_RET_KILL;
+
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
-	 * value always takes priority.
+	 * value always takes priority (ignoring the DATA).
 	 */
 	for (f = current->seccomp.filter; f; f = f->prev) {
-		ret = sk_run_filter(NULL, f->insns);
-		if (ret != SECCOMP_RET_ALLOW)
-			break;
+		u32 cur_ret = sk_run_filter(NULL, f->insns);
+		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+			ret = cur_ret;
 	}
 	return ret;
 }
@@ -346,11 +351,13 @@ static int mode1_syscalls_32[] = {
 };
 #endif
 
-void __secure_computing(int this_syscall)
+int __secure_computing(int this_syscall)
 {
 	int mode = current->seccomp.mode;
 	int exit_sig = 0;
 	int *syscall;
+	u32 ret = SECCOMP_RET_KILL;
+	int data;
 
 	switch (mode) {
 	case SECCOMP_MODE_STRICT:
@@ -361,14 +368,26 @@ void __secure_computing(int this_syscall)
 #endif
 		do {
 			if (*syscall == this_syscall)
-				return;
+				return 0;
 		} while (*++syscall);
 		exit_sig = SIGKILL;
 		break;
 #ifdef CONFIG_SECCOMP_FILTER
 	case SECCOMP_MODE_FILTER:
-		if (seccomp_run_filters(this_syscall) == SECCOMP_RET_ALLOW)
-			return;
+		ret = seccomp_run_filters(this_syscall);
+		data = ret & SECCOMP_RET_DATA;
+		switch (ret & SECCOMP_RET_ACTION) {
+		case SECCOMP_RET_ERRNO:
+			/* Set the low-order 16-bits as a errno. */
+			syscall_set_return_value(current, task_pt_regs(current),
+						 -data, 0);
+			goto skip;
+		case SECCOMP_RET_ALLOW:
+			return 0;
+		case SECCOMP_RET_KILL:
+		default:
+			break;
+		}
 		exit_sig = SIGSYS;
 		break;
 #endif
@@ -379,8 +398,11 @@ void __secure_computing(int this_syscall)
 #ifdef SECCOMP_DEBUG
 	dump_stack();
 #endif
-	audit_seccomp(this_syscall, exit_code, SECCOMP_RET_KILL);
+	audit_seccomp(this_syscall, exit_sig, ret);
 	do_exit(exit_sig);
+skip:
+	audit_seccomp(this_syscall, exit_sig, ret);
+	return -1;
 }
 
 long prctl_get_seccomp(void)