Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security

Pull security subsystem updates from James Morris:
 "Highlights:

   - TPM core and driver updates/fixes
   - IPv6 security labeling (CALIPSO)
   - Lots of Apparmor fixes
   - Seccomp: remove 2-phase API, close hole where ptrace can change
     syscall #"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: (156 commits)
  apparmor: fix SECURITY_APPARMOR_HASH_DEFAULT parameter handling
  tpm: Add TPM 2.0 support to the Nuvoton i2c driver (NPCT6xx family)
  tpm: Factor out common startup code
  tpm: use devm_add_action_or_reset
  tpm2_i2c_nuvoton: add irq validity check
  tpm: read burstcount from TPM_STS in one 32-bit transaction
  tpm: fix byte-order for the value read by tpm2_get_tpm_pt
  tpm_tis_core: convert max timeouts from msec to jiffies
  apparmor: fix arg_size computation for when setprocattr is null terminated
  apparmor: fix oops, validate buffer size in apparmor_setprocattr()
  apparmor: do not expose kernel stack
  apparmor: fix module parameters can be changed after policy is locked
  apparmor: fix oops in profile_unpack() when policy_db is not present
  apparmor: don't check for vmalloc_addr if kvzalloc() failed
  apparmor: add missing id bounds check on dfa verification
  apparmor: allow SYS_CAP_RESOURCE to be sufficient to prlimit another task
  apparmor: use list_next_entry instead of list_entry_next
  apparmor: fix refcount race when finding a child profile
  apparmor: fix ref count leak when profile sha1 hash is read
  apparmor: check that xindex is in trans_table bounds
  ...

2 files changed, 92 insertions, 98 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index 45432b54d5c6..00411c82dac5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -361,6 +361,24 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
 	return has_ns_capability_noaudit(t, &init_user_ns, cap);
 }
 
+static bool ns_capable_common(struct user_namespace *ns, int cap, bool audit)
+{
+	int capable;
+
+	if (unlikely(!cap_valid(cap))) {
+		pr_crit("capable() called with invalid cap=%u\n", cap);
+		BUG();
+	}
+
+	capable = audit ? security_capable(current_cred(), ns, cap) :
+			  security_capable_noaudit(current_cred(), ns, cap);
+	if (capable == 0) {
+		current->flags |= PF_SUPERPRIV;
+		return true;
+	}
+	return false;
+}
+
 /**
  * ns_capable - Determine if the current task has a superior capability in effect
  * @ns:  The usernamespace we want the capability in
@@ -374,19 +392,27 @@ bool has_capability_noaudit(struct task_struct *t, int cap)
  */
 bool ns_capable(struct user_namespace *ns, int cap)
 {
-	if (unlikely(!cap_valid(cap))) {
-		pr_crit("capable() called with invalid cap=%u\n", cap);
-		BUG();
-	}
-
-	if (security_capable(current_cred(), ns, cap) == 0) {
-		current->flags |= PF_SUPERPRIV;
-		return true;
-	}
-	return false;
+	return ns_capable_common(ns, cap, true);
 }
 EXPORT_SYMBOL(ns_capable);
 
+/**
+ * ns_capable_noaudit - Determine if the current task has a superior capability
+ * (unaudited) in effect
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool ns_capable_noaudit(struct user_namespace *ns, int cap)
+{
+	return ns_capable_common(ns, cap, false);
+}
+EXPORT_SYMBOL(ns_capable_noaudit);
 
 /**
  * capable - Determine if the current task has a superior capability in effect
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 7002796f14a4..54d15eb2b701 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -173,7 +173,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  *
  * Returns valid seccomp BPF response codes.
  */
-static u32 seccomp_run_filters(struct seccomp_data *sd)
+static u32 seccomp_run_filters(const struct seccomp_data *sd)
 {
 	struct seccomp_data sd_local;
 	u32 ret = SECCOMP_RET_ALLOW;
@@ -554,20 +554,10 @@ void secure_computing_strict(int this_syscall)
 		BUG();
 }
 #else
-int __secure_computing(void)
-{
-	u32 phase1_result = seccomp_phase1(NULL);
-
-	if (likely(phase1_result == SECCOMP_PHASE1_OK))
-		return 0;
-	else if (likely(phase1_result == SECCOMP_PHASE1_SKIP))
-		return -1;
-	else
-		return seccomp_phase2(phase1_result);
-}
 
 #ifdef CONFIG_SECCOMP_FILTER
-static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+			    const bool recheck_after_trace)
 {
 	u32 filter_ret, action;
 	int data;
@@ -599,10 +589,46 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
 		goto skip;
 
 	case SECCOMP_RET_TRACE:
-		return filter_ret;  /* Save the rest for phase 2. */
+		/* We've been put in this state by the ptracer already. */
+		if (recheck_after_trace)
+			return 0;
+
+		/* ENOSYS these calls if there is no tracer attached. */
+		if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
+			syscall_set_return_value(current,
+						 task_pt_regs(current),
+						 -ENOSYS, 0);
+			goto skip;
+		}
+
+		/* Allow the BPF to provide the event message */
+		ptrace_event(PTRACE_EVENT_SECCOMP, data);
+		/*
+		 * The delivery of a fatal signal during event
+		 * notification may silently skip tracer notification.
+		 * Terminating the task now avoids executing a system
+		 * call that may not be intended.
+		 */
+		if (fatal_signal_pending(current))
+			do_exit(SIGSYS);
+		/* Check if the tracer forced the syscall to be skipped. */
+		this_syscall = syscall_get_nr(current, task_pt_regs(current));
+		if (this_syscall < 0)
+			goto skip;
+
+		/*
+		 * Recheck the syscall, since it may have changed. This
+		 * intentionally uses a NULL struct seccomp_data to force
+		 * a reload of all registers. This does not goto skip since
+		 * a skip would have already been reported.
+		 */
+		if (__seccomp_filter(this_syscall, NULL, true))
+			return -1;
+
+		return 0;
 
 	case SECCOMP_RET_ALLOW:
-		return SECCOMP_PHASE1_OK;
+		return 0;
 
 	case SECCOMP_RET_KILL:
 	default:
@@ -614,96 +640,38 @@ static u32 __seccomp_phase1_filter(int this_syscall, struct seccomp_data *sd)
 
 skip:
 	audit_seccomp(this_syscall, 0, action);
-	return SECCOMP_PHASE1_SKIP;
+	return -1;
+}
+#else
+static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd,
+			    const bool recheck_after_trace)
+{
+	BUG();
 }
 #endif
 
-/**
- * seccomp_phase1() - run fast path seccomp checks on the current syscall
- * @arg sd: The seccomp_data or NULL
- *
- * This only reads pt_regs via the syscall_xyz helpers.  The only change
- * it will make to pt_regs is via syscall_set_return_value, and it will
- * only do that if it returns SECCOMP_PHASE1_SKIP.
- *
- * If sd is provided, it will not read pt_regs at all.
- *
- * It may also call do_exit or force a signal; these actions must be
- * safe.
- *
- * If it returns SECCOMP_PHASE1_OK, the syscall passes checks and should
- * be processed normally.
- *
- * If it returns SECCOMP_PHASE1_SKIP, then the syscall should not be
- * invoked.  In this case, seccomp_phase1 will have set the return value
- * using syscall_set_return_value.
- *
- * If it returns anything else, then the return value should be passed
- * to seccomp_phase2 from a context in which ptrace hooks are safe.
- */
-u32 seccomp_phase1(struct seccomp_data *sd)
+int __secure_computing(const struct seccomp_data *sd)
 {
 	int mode = current->seccomp.mode;
-	int this_syscall = sd ? sd->nr :
-		syscall_get_nr(current, task_pt_regs(current));
+	int this_syscall;
 
 	if (config_enabled(CONFIG_CHECKPOINT_RESTORE) &&
 	    unlikely(current->ptrace & PT_SUSPEND_SECCOMP))
-		return SECCOMP_PHASE1_OK;
+		return 0;
+
+	this_syscall = sd ? sd->nr :
+		syscall_get_nr(current, task_pt_regs(current));
 
 	switch (mode) {
 	case SECCOMP_MODE_STRICT:
 		__secure_computing_strict(this_syscall);  /* may call do_exit */
-		return SECCOMP_PHASE1_OK;
-#ifdef CONFIG_SECCOMP_FILTER
+		return 0;
 	case SECCOMP_MODE_FILTER:
-		return __seccomp_phase1_filter(this_syscall, sd);
-#endif
+		return __seccomp_filter(this_syscall, sd, false);
 	default:
 		BUG();
 	}
 }
-
-/**
- * seccomp_phase2() - finish slow path seccomp work for the current syscall
- * @phase1_result: The return value from seccomp_phase1()
- *
- * This must be called from a context in which ptrace hooks can be used.
- *
- * Returns 0 if the syscall should be processed or -1 to skip the syscall.
- */
-int seccomp_phase2(u32 phase1_result)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	u32 action = phase1_result & SECCOMP_RET_ACTION;
-	int data = phase1_result & SECCOMP_RET_DATA;
-
-	BUG_ON(action != SECCOMP_RET_TRACE);
-
-	audit_seccomp(syscall_get_nr(current, regs), 0, action);
-
-	/* Skip these calls if there is no tracer. */
-	if (!ptrace_event_enabled(current, PTRACE_EVENT_SECCOMP)) {
-		syscall_set_return_value(current, regs,
-					 -ENOSYS, 0);
-		return -1;
-	}
-
-	/* Allow the BPF to provide the event message */
-	ptrace_event(PTRACE_EVENT_SECCOMP, data);
-	/*
-	 * The delivery of a fatal signal during event
-	 * notification may silently skip tracer notification.
-	 * Terminating the task now avoids executing a system
-	 * call that may not be intended.
-	 */
-	if (fatal_signal_pending(current))
-		do_exit(SIGSYS);
-	if (syscall_get_nr(current, regs) < 0)
-		return -1;  /* Explicit request to skip. */
-
-	return 0;
-}
 #endif /* CONFIG_HAVE_ARCH_SECCOMP_FILTER */
 
 long prctl_get_seccomp(void)