Merge tag 'seccomp-next' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux into next

Author: James Morris

include/linux/ptrace.h

@@ -34,6 +34,7 @@
 #define PT_TRACE_SECCOMP	PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP)
 
 #define PT_EXITKILL		(PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT)
+#define PT_SUSPEND_SECCOMP	(PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT)
 
 /* single stepping state bits (used on ARM and PA-RISC) */
 #define PT_SINGLESTEP_BIT	31

include/linux/seccomp.h

@@ -78,7 +78,7 @@ static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3)
 
 static inline int seccomp_mode(struct seccomp *s)
 {
-	return 0;
+	return SECCOMP_MODE_DISABLED;
 }
 #endif /* CONFIG_SECCOMP */
 

include/uapi/linux/ptrace.h

@@ -89,9 +89,11 @@ struct ptrace_peeksiginfo_args {
 #define PTRACE_O_TRACESECCOMP	(1 << PTRACE_EVENT_SECCOMP)
 
 /* eventless options */
-#define PTRACE_O_EXITKILL	(1 << 20)
+#define PTRACE_O_EXITKILL		(1 << 20)
+#define PTRACE_O_SUSPEND_SECCOMP	(1 << 21)
 
-#define PTRACE_O_MASK		(0x000000ff | PTRACE_O_EXITKILL)
+#define PTRACE_O_MASK		(\
+	0x000000ff | PTRACE_O_EXITKILL | PTRACE_O_SUSPEND_SECCOMP)
 
 #include <asm/ptrace.h>
 

kernel/ptrace.c

@@ -556,6 +556,19 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data)
 	if (data & ~(unsigned long)PTRACE_O_MASK)
 		return -EINVAL;
 
+	if (unlikely(data & PTRACE_O_SUSPEND_SECCOMP)) {
+		if (!config_enabled(CONFIG_CHECKPOINT_RESTORE) ||
+		    !config_enabled(CONFIG_SECCOMP))
+			return -EINVAL;
+
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+
+		if (seccomp_mode(&current->seccomp) != SECCOMP_MODE_DISABLED ||
+		    current->ptrace & PT_SUSPEND_SECCOMP)
+			return -EPERM;
+	}
+
 	/* Avoid intermediate state when all opts are cleared */
 	flags = child->ptrace;
 	flags &= ~(PTRACE_O_MASK << PT_OPT_FLAG_SHIFT);

kernel/seccomp.c

@@ -175,17 +175,16 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  */
 static u32 seccomp_run_filters(struct seccomp_data *sd)
 {
-	struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
 	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
+	/* Make sure cross-thread synced filter points somewhere sane. */
+	struct seccomp_filter *f =
+			lockless_dereference(current->seccomp.filter);
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
 	if (unlikely(WARN_ON(f == NULL)))
 		return SECCOMP_RET_KILL;
 
-	/* Make sure cross-thread synced filter points somewhere sane. */
-	smp_read_barrier_depends();
-
 	if (!sd) {
 		populate_seccomp_data(&sd_local);
 		sd = &sd_local;
@@ -549,7 +548,11 @@ void secure_computing_strict(int this_syscall)
 {
 	int mode = current->seccomp.mode;
 
-	if (mode == 0)
+	if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
+		return;
+
+	if (mode == SECCOMP_MODE_DISABLED)
 		return;
 	else if (mode == SECCOMP_MODE_STRICT)
 		__secure_computing_strict(this_syscall);
@@ -650,6 +653,10 @@ u32 seccomp_phase1(struct seccomp_data *sd)
 	int this_syscall = sd ? sd->nr :
 		syscall_get_nr(current, task_pt_regs(current));
 
+	if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
+	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
+		return SECCOMP_PHASE1_OK;
+
 	switch (mode) {
 	case SECCOMP_MODE_STRICT:
 		__secure_computing_strict(this_syscall);  /* may call do_exit */