Merge tag 'seccomp-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux into next

MAINTAINERS

@@ -7953,6 +7953,16 @@ S:	Maintained
 F:	drivers/mmc/host/sdhci.*
 F:	drivers/mmc/host/sdhci-pltfm.[ch]
 
+SECURE COMPUTING
+M:	Kees Cook <keescook@chromium.org>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git seccomp
+S:	Supported
+F:	kernel/seccomp.c
+F:	include/uapi/linux/seccomp.h
+F:	include/linux/seccomp.h
+K:	\bsecure_computing
+K:	\bTIF_SECCOMP\b
+
 SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)
 M:	Anton Vorontsov <anton@enomsg.org>
 L:	linuxppc-dev@lists.ozlabs.org

arch/Kconfig

@@ -321,6 +321,7 @@ config HAVE_ARCH_SECCOMP_FILTER
 	  - secure_computing is called from a ptrace_event()-safe context
 	  - secure_computing return value is checked and a return value of -1
 	    results in the system call being skipped immediately.
+	  - seccomp syscall wired up
 
 config SECCOMP_FILTER
 	def_bool y

arch/arm/include/uapi/asm/unistd.h

@@ -409,6 +409,7 @@
 #define __NR_sched_setattr		(__NR_SYSCALL_BASE+380)
 #define __NR_sched_getattr		(__NR_SYSCALL_BASE+381)
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
+#define __NR_seccomp			(__NR_SYSCALL_BASE+383)
 
 /*
  * This may need to be greater than __NR_last_syscall+1 in order to

arch/arm/kernel/calls.S

@@ -392,6 +392,7 @@
 /* 380 */	CALL(sys_sched_setattr)
 		CALL(sys_sched_getattr)
 		CALL(sys_renameat2)
+		CALL(sys_seccomp)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/mips/include/uapi/asm/unistd.h

@@ -372,16 +372,17 @@
 #define __NR_sched_setattr		(__NR_Linux + 349)
 #define __NR_sched_getattr		(__NR_Linux + 350)
 #define __NR_renameat2			(__NR_Linux + 351)
+#define __NR_seccomp			(__NR_Linux + 352)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		351
+#define __NR_Linux_syscalls		352
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		351
+#define __NR_O32_Linux_syscalls		352
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -701,16 +702,17 @@
 #define __NR_sched_setattr		(__NR_Linux + 309)
 #define __NR_sched_getattr		(__NR_Linux + 310)
 #define __NR_renameat2			(__NR_Linux + 311)
+#define __NR_seccomp			(__NR_Linux + 312)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		311
+#define __NR_Linux_syscalls		312
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		311
+#define __NR_64_Linux_syscalls		312
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1034,15 +1036,16 @@
 #define __NR_sched_setattr		(__NR_Linux + 313)
 #define __NR_sched_getattr		(__NR_Linux + 314)
 #define __NR_renameat2			(__NR_Linux + 315)
+#define __NR_seccomp			(__NR_Linux + 316)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		315
+#define __NR_Linux_syscalls		316
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		315
+#define __NR_N32_Linux_syscalls		316
 
 #endif /* _UAPI_ASM_UNISTD_H */

arch/mips/kernel/scall32-o32.S

@@ -578,3 +578,4 @@ EXPORT(sys_call_table)
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 4350 */
 	PTR	sys_renameat2
+	PTR	sys_seccomp

arch/mips/kernel/scall64-64.S

@@ -431,4 +431,5 @@ EXPORT(sys_call_table)
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 5310 */
 	PTR	sys_renameat2
+	PTR	sys_seccomp
 	.size	sys_call_table,.-sys_call_table

arch/mips/kernel/scall64-n32.S

@@ -424,4 +424,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr
 	PTR	sys_renameat2			/* 6315 */
+	PTR	sys_seccomp
 	.size	sysn32_call_table,.-sysn32_call_table

arch/mips/kernel/scall64-o32.S

@@ -557,4 +557,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 4350 */
 	PTR	sys_renameat2
+	PTR	sys_seccomp
 	.size	sys32_call_table,.-sys32_call_table

arch/x86/syscalls/syscall_32.tbl

@@ -360,3 +360,4 @@
 351	i386	sched_setattr		sys_sched_setattr
 352	i386	sched_getattr		sys_sched_getattr
 353	i386	renameat2		sys_renameat2
+354	i386	seccomp			sys_seccomp

arch/x86/syscalls/syscall_64.tbl

@@ -323,6 +323,7 @@
 314	common	sched_setattr		sys_sched_setattr
 315	common	sched_getattr		sys_sched_getattr
 316	common	renameat2		sys_renameat2
+317	common	seccomp			sys_seccomp
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

fs/exec.c

@@ -1216,7 +1216,7 @@ EXPORT_SYMBOL(install_exec_creds);
 /*
  * determine how safe it is to execute the proposed program
  * - the caller must hold ->cred_guard_mutex to protect against
- *   PTRACE_ATTACH
+ *   PTRACE_ATTACH or seccomp thread-sync
  */
 static void check_unsafe_exec(struct linux_binprm *bprm)
 {
@@ -1234,7 +1234,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * This isn't strictly necessary, but it makes it harder for LSMs to
 	 * mess up.
 	 */
-	if (current->no_new_privs)
+	if (task_no_new_privs(current))
 		bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
 
 	t = p;
@@ -1272,7 +1272,7 @@ int prepare_binprm(struct linux_binprm *bprm)
 	bprm->cred->egid = current_egid();
 
 	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
-	    !current->no_new_privs &&
+	    !task_no_new_privs(current) &&
 	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
 	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
 		/* Set-uid? */

include/linux/sched.h

@@ -1307,13 +1307,12 @@ struct task_struct {
 				 * execve */
 	unsigned in_iowait:1;
 
-	/* task may not gain privileges */
-	unsigned no_new_privs:1;
-
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
 
+	unsigned long atomic_flags; /* Flags needing atomic access. */
+
 	pid_t pid;
 	pid_t tgid;
 
@@ -1967,6 +1966,19 @@ static inline void memalloc_noio_restore(unsigned int flags)
 	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
 }
 
+/* Per-process atomic flags. */
+#define PFA_NO_NEW_PRIVS 0x00000001	/* May not gain new privileges. */
+
+static inline bool task_no_new_privs(struct task_struct *p)
+{
+	return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
+static inline void task_set_no_new_privs(struct task_struct *p)
+{
+	set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
 /*
  * task->jobctl flags
  */

include/linux/seccomp.h

@@ -3,6 +3,8 @@
 
 #include <uapi/linux/seccomp.h>
 
+#define SECCOMP_FILTER_FLAG_MASK	(SECCOMP_FILTER_FLAG_TSYNC)
+
 #ifdef CONFIG_SECCOMP
 
 #include <linux/thread_info.h>
@@ -14,11 +16,11 @@ struct seccomp_filter;
  *
  * @mode:  indicates one of the valid values above for controlled
  *         system calls available to a process.
- * @filter: The metadata and ruleset for determining what system calls
- *          are allowed for a task.
+ * @filter: must always point to a valid seccomp-filter or NULL as it is
+ *          accessed without locking during system call entry.
  *
  *          @filter must only be accessed from the context of current as there
- *          is no locking.
+ *          is no read locking.
  */
 struct seccomp {
 	int mode;

include/linux/syscalls.h

@@ -866,4 +866,6 @@ asmlinkage long sys_process_vm_writev(pid_t pid,
 asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
 			 unsigned long idx1, unsigned long idx2);
 asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
+asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
+			    const char __user *uargs);
 #endif

include/uapi/asm-generic/unistd.h

@@ -699,9 +699,11 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
 __SYSCALL(__NR_sched_getattr, sys_sched_getattr)
 #define __NR_renameat2 276
 __SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
 
 #undef __NR_syscalls
-#define __NR_syscalls 277
+#define __NR_syscalls 278
 
 /*
  * All syscalls below here should go away really,

include/uapi/linux/seccomp.h

@@ -10,6 +10,13 @@
 #define SECCOMP_MODE_STRICT	1 /* uses hard-coded filter. */
 #define SECCOMP_MODE_FILTER	2 /* uses user-supplied filter. */
 
+/* Valid operations for seccomp syscall. */
+#define SECCOMP_SET_MODE_STRICT	0
+#define SECCOMP_SET_MODE_FILTER	1
+
+/* Valid flags for SECCOMP_SET_MODE_FILTER */
+#define SECCOMP_FILTER_FLAG_TSYNC	1
+
 /*
  * All BPF programs must return a 32-bit value.
  * The bottom 16-bits are for optional return data.

kernel/fork.c

@@ -315,6 +315,15 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 		goto free_ti;
 
 	tsk->stack = ti;
+#ifdef CONFIG_SECCOMP
+	/*
+	 * We must handle setting up seccomp filters once we're under
+	 * the sighand lock in case orig has changed between now and
+	 * then. Until then, filter must be NULL to avoid messing up
+	 * the usage counts on the error path calling free_task.
+	 */
+	tsk->seccomp.filter = NULL;
+#endif
 
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
@@ -1081,6 +1090,39 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	return 0;
 }
 
+static void copy_seccomp(struct task_struct *p)
+{
+#ifdef CONFIG_SECCOMP
+	/*
+	 * Must be called with sighand->lock held, which is common to
+	 * all threads in the group. Holding cred_guard_mutex is not
+	 * needed because this new task is not yet running and cannot
+	 * be racing exec.
+	 */
+	BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+	/* Ref-count the new filter user, and assign it. */
+	get_seccomp_filter(current);
+	p->seccomp = current->seccomp;
+
+	/*
+	 * Explicitly enable no_new_privs here in case it got set
+	 * between the task_struct being duplicated and holding the
+	 * sighand lock. The seccomp state and nnp must be in sync.
+	 */
+	if (task_no_new_privs(current))
+		task_set_no_new_privs(p);
+
+	/*
+	 * If the parent gained a seccomp mode after copying thread
+	 * flags and between before we held the sighand lock, we have
+	 * to manually enable the seccomp thread flag here.
+	 */
+	if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
+		set_tsk_thread_flag(p, TIF_SECCOMP);
+#endif
+}
+
 SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
 {
 	current->clear_child_tid = tidptr;
@@ -1196,7 +1238,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	ftrace_graph_init_task(p);
-	get_seccomp_filter(p);
 
 	rt_mutex_init_task(p);
 
@@ -1436,6 +1477,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	spin_lock(&current->sighand->siglock);
 
+	/*
+	 * Copy seccomp details explicitly here, in case they were changed
+	 * before holding sighand lock.
+	 */
+	copy_seccomp(p);
+
 	/*
 	 * Process group and session signals need to be delivered to just the
 	 * parent before the fork or both the parent and the child after the

kernel/seccomp.c

@@ -18,15 +18,17 @@
 #include <linux/compat.h>
 #include <linux/sched.h>
 #include <linux/seccomp.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
 
 /* #define SECCOMP_DEBUG 1 */
 
 #ifdef CONFIG_SECCOMP_FILTER
 #include <asm/syscall.h>
 #include <linux/filter.h>
+#include <linux/pid.h>
 #include <linux/ptrace.h>
 #include <linux/security.h>
-#include <linux/slab.h>
 #include <linux/tracehook.h>
 #include <linux/uaccess.h>
 
@@ -172,21 +174,24 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
  */
 static u32 seccomp_run_filters(int syscall)
 {
-	struct seccomp_filter *f;
+	struct seccomp_filter *f = ACCESS_ONCE(current->seccomp.filter);
 	struct seccomp_data sd;
 	u32 ret = SECCOMP_RET_ALLOW;
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
-	if (WARN_ON(current->seccomp.filter == NULL))
+	if (unlikely(WARN_ON(f == NULL)))
 		return SECCOMP_RET_KILL;
 
+	/* Make sure cross-thread synced filter points somewhere sane. */
+	smp_read_barrier_depends();
+
 	populate_seccomp_data(&sd);
 
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
-	for (f = current->seccomp.filter; f; f = f->prev) {
+	for (; f; f = f->prev) {
 		u32 cur_ret = SK_RUN_FILTER(f->prog, (void *)&sd);
 
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
@@ -194,29 +199,159 @@ static u32 seccomp_run_filters(int syscall)
 	}
 	return ret;
 }
+#endif /* CONFIG_SECCOMP_FILTER */
+
+static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode)
+{
+	BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+	if (current->seccomp.mode && current->seccomp.mode != seccomp_mode)
+		return false;
+
+	return true;
+}
+
+static inline void seccomp_assign_mode(struct task_struct *task,
+				       unsigned long seccomp_mode)
+{
+	BUG_ON(!spin_is_locked(&task->sighand->siglock));
+
+	task->seccomp.mode = seccomp_mode;
+	/*
+	 * Make sure TIF_SECCOMP cannot be set before the mode (and
+	 * filter) is set.
+	 */
+	smp_mb__before_atomic();
+	set_tsk_thread_flag(task, TIF_SECCOMP);
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+/* Returns 1 if the parent is an ancestor of the child. */
+static int is_ancestor(struct seccomp_filter *parent,
+		       struct seccomp_filter *child)
+{
+	/* NULL is the root ancestor. */
+	if (parent == NULL)
+		return 1;
+	for (; child; child = child->prev)
+		if (child == parent)
+			return 1;
+	return 0;
+}
 
 /**
- * seccomp_attach_filter: Attaches a seccomp filter to current.
+ * seccomp_can_sync_threads: checks if all threads can be synchronized
+ *
+ * Expects sighand and cred_guard_mutex locks to be held.
+ *
+ * Returns 0 on success, -ve on error, or the pid of a thread which was
+ * either not in the correct seccomp mode or it did not have an ancestral
+ * seccomp filter.
+ */
+static inline pid_t seccomp_can_sync_threads(void)
+{
+	struct task_struct *thread, *caller;
+
+	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
+	BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+	/* Validate all threads being eligible for synchronization. */
+	caller = current;
+	for_each_thread(caller, thread) {
+		pid_t failed;
+
+		/* Skip current, since it is initiating the sync. */
+		if (thread == caller)
+			continue;
+
+		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
+		    (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
+		     is_ancestor(thread->seccomp.filter,
+				 caller->seccomp.filter)))
+			continue;
+
+		/* Return the first thread that cannot be synchronized. */
+		failed = task_pid_vnr(thread);
+		/* If the pid cannot be resolved, then return -ESRCH */
+		if (unlikely(WARN_ON(failed == 0)))
+			failed = -ESRCH;
+		return failed;
+	}
+
+	return 0;
+}
+
+/**
+ * seccomp_sync_threads: sets all threads to use current's filter
+ *
+ * Expects sighand and cred_guard_mutex locks to be held, and for
+ * seccomp_can_sync_threads() to have returned success already
+ * without dropping the locks.
+ *
+ */
+static inline void seccomp_sync_threads(void)
+{
+	struct task_struct *thread, *caller;
+
+	BUG_ON(!mutex_is_locked(&current->signal->cred_guard_mutex));
+	BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+	/* Synchronize all threads. */
+	caller = current;
+	for_each_thread(caller, thread) {
+		/* Skip current, since it needs no changes. */
+		if (thread == caller)
+			continue;
+
+		/* Get a task reference for the new leaf node. */
+		get_seccomp_filter(caller);
+		/*
+		 * Drop the task reference to the shared ancestor since
+		 * current's path will hold a reference.  (This also
+		 * allows a put before the assignment.)
+		 */
+		put_seccomp_filter(thread);
+		smp_store_release(&thread->seccomp.filter,
+				  caller->seccomp.filter);
+		/*
+		 * Opt the other thread into seccomp if needed.
+		 * As threads are considered to be trust-realm
+		 * equivalent (see ptrace_may_access), it is safe to
+		 * allow one thread to transition the other.
+		 */
+		if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) {
+			/*
+			 * Don't let an unprivileged task work around
+			 * the no_new_privs restriction by creating
+			 * a thread that sets it up, enters seccomp,
+			 * then dies.
+			 */
+			if (task_no_new_privs(caller))
+				task_set_no_new_privs(thread);
+
+			seccomp_assign_mode(thread, SECCOMP_MODE_FILTER);
+		}
+	}
+}
+
+/**
+ * seccomp_prepare_filter: Prepares a seccomp filter for use.
  * @fprog: BPF program to install
  *
- * Returns 0 on success or an errno on failure.
+ * Returns filter on success or an ERR_PTR on failure.
  */
-static long seccomp_attach_filter(struct sock_fprog *fprog)
+static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog)
 {
 	struct seccomp_filter *filter;
-	unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
-	unsigned long total_insns = fprog->len;
+	unsigned long fp_size;
 	struct sock_filter *fp;
 	int new_len;
 	long ret;
 
 	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
-		return -EINVAL;
-
-	for (filter = current->seccomp.filter; filter; filter = filter->prev)
-		total_insns += filter->prog->len + 4;  /* include a 4 instr penalty */
-	if (total_insns > MAX_INSNS_PER_PATH)
-		return -ENOMEM;
+		return ERR_PTR(-EINVAL);
+	BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter));
+	fp_size = fprog->len * sizeof(struct sock_filter);
 
 	/*
 	 * Installing a seccomp filter requires that the task has
@@ -224,14 +359,14 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	 * This avoids scenarios where unprivileged tasks can affect the
 	 * behavior of privileged children.
 	 */
-	if (!current->no_new_privs &&
+	if (!task_no_new_privs(current) &&
 	    security_capable_noaudit(current_cred(), current_user_ns(),
 				     CAP_SYS_ADMIN) != 0)
-		return -EACCES;
+		return ERR_PTR(-EACCES);
 
 	fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
 	if (!fp)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	/* Copy the instructions from fprog. */
 	ret = -EFAULT;
@@ -275,13 +410,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 
 	sk_filter_select_runtime(filter->prog);
 
-	/*
-	 * If there is an existing filter, make it the prev and don't drop its
-	 * task reference.
-	 */
-	filter->prev = current->seccomp.filter;
-	current->seccomp.filter = filter;
-	return 0;
+	return filter;
 
 free_filter_prog:
 	kfree(filter->prog);
@@ -289,19 +418,20 @@ free_filter:
 	kfree(filter);
 free_prog:
 	kfree(fp);
-	return ret;
+	return ERR_PTR(ret);
 }
 
 /**
- * seccomp_attach_user_filter - attaches a user-supplied sock_fprog
+ * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog
  * @user_filter: pointer to the user data containing a sock_fprog.
  *
  * Returns 0 on success and non-zero otherwise.
  */
-static long seccomp_attach_user_filter(char __user *user_filter)
+static struct seccomp_filter *
+seccomp_prepare_user_filter(const char __user *user_filter)
 {
 	struct sock_fprog fprog;
-	long ret = -EFAULT;
+	struct seccomp_filter *filter = ERR_PTR(-EFAULT);
 
 #ifdef CONFIG_COMPAT
 	if (is_compat_task()) {
@@ -314,9 +444,56 @@ static long seccomp_attach_user_filter(char __user *user_filter)
 #endif
 	if (copy_from_user(&fprog, user_filter, sizeof(fprog)))
 		goto out;
-	ret = seccomp_attach_filter(&fprog);
+	filter = seccomp_prepare_filter(&fprog);
 out:
-	return ret;
+	return filter;
+}
+
+/**
+ * seccomp_attach_filter: validate and attach filter
+ * @flags:  flags to change filter behavior
+ * @filter: seccomp filter to add to the current process
+ *
+ * Caller must be holding current->sighand->siglock lock.
+ *
+ * Returns 0 on success, -ve on error.
+ */
+static long seccomp_attach_filter(unsigned int flags,
+				  struct seccomp_filter *filter)
+{
+	unsigned long total_insns;
+	struct seccomp_filter *walker;
+
+	BUG_ON(!spin_is_locked(&current->sighand->siglock));
+
+	/* Validate resulting filter length. */
+	total_insns = filter->prog->len;
+	for (walker = current->seccomp.filter; walker; walker = walker->prev)
+		total_insns += walker->prog->len + 4;  /* 4 instr penalty */
+	if (total_insns > MAX_INSNS_PER_PATH)
+		return -ENOMEM;
+
+	/* If thread sync has been requested, check that it is possible. */
+	if (flags & SECCOMP_FILTER_FLAG_TSYNC) {
+		int ret;
+
+		ret = seccomp_can_sync_threads();
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * If there is an existing filter, make it the prev and don't drop its
+	 * task reference.
+	 */
+	filter->prev = current->seccomp.filter;
+	current->seccomp.filter = filter;
+
+	/* Now that the new filter is in place, synchronize to all threads. */
+	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+		seccomp_sync_threads();
+
+	return 0;
 }
 
 /* get_seccomp_filter - increments the reference count of the filter on @tsk */
@@ -329,6 +506,14 @@ void get_seccomp_filter(struct task_struct *tsk)
 	atomic_inc(&orig->usage);
 }
 
+static inline void seccomp_filter_free(struct seccomp_filter *filter)
+{
+	if (filter) {
+		sk_filter_free(filter->prog);
+		kfree(filter);
+	}
+}
+
 /* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
 void put_seccomp_filter(struct task_struct *tsk)
 {
@@ -337,8 +522,7 @@ void put_seccomp_filter(struct task_struct *tsk)
 	while (orig && atomic_dec_and_test(&orig->usage)) {
 		struct seccomp_filter *freeme = orig;
 		orig = orig->prev;
-		sk_filter_free(freeme->prog);
-		kfree(freeme);
+		seccomp_filter_free(freeme);
 	}
 }
 
@@ -382,12 +566,17 @@ static int mode1_syscalls_32[] = {
 
 int __secure_computing(int this_syscall)
 {
-	int mode = current->seccomp.mode;
 	int exit_sig = 0;
 	int *syscall;
 	u32 ret;
 
-	switch (mode) {
+	/*
+	 * Make sure that any changes to mode from another thread have
+	 * been seen after TIF_SECCOMP was seen.
+	 */
+	rmb();
+
+	switch (current->seccomp.mode) {
 	case SECCOMP_MODE_STRICT:
 		syscall = mode1_syscalls;
 #ifdef CONFIG_COMPAT
@@ -473,47 +662,152 @@ long prctl_get_seccomp(void)
 }
 
 /**
- * prctl_set_seccomp: configures current->seccomp.mode
- * @seccomp_mode: requested mode to use
- * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
- *
- * This function may be called repeatedly with a @seccomp_mode of
- * SECCOMP_MODE_FILTER to install additional filters.  Every filter
- * successfully installed will be evaluated (in reverse order) for each system
- * call the task makes.
+ * seccomp_set_mode_strict: internal function for setting strict seccomp
  *
  * Once current->seccomp.mode is non-zero, it may not be changed.
  *
  * Returns 0 on success or -EINVAL on failure.
  */
-long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+static long seccomp_set_mode_strict(void)
 {
+	const unsigned long seccomp_mode = SECCOMP_MODE_STRICT;
 	long ret = -EINVAL;
 
-	if (current->seccomp.mode &&
-	    current->seccomp.mode != seccomp_mode)
+	spin_lock_irq(&current->sighand->siglock);
+
+	if (!seccomp_may_assign_mode(seccomp_mode))
 		goto out;
 
+#ifdef TIF_NOTSC
+	disable_TSC();
+#endif
+	seccomp_assign_mode(current, seccomp_mode);
+	ret = 0;
+
+out:
+	spin_unlock_irq(&current->sighand->siglock);
+
+	return ret;
+}
+
+#ifdef CONFIG_SECCOMP_FILTER
+/**
+ * seccomp_set_mode_filter: internal function for setting seccomp filter
+ * @flags:  flags to change filter behavior
+ * @filter: struct sock_fprog containing filter
+ *
+ * This function may be called repeatedly to install additional filters.
+ * Every filter successfully installed will be evaluated (in reverse order)
+ * for each system call the task makes.
+ *
+ * Once current->seccomp.mode is non-zero, it may not be changed.
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+static long seccomp_set_mode_filter(unsigned int flags,
+				    const char __user *filter)
+{
+	const unsigned long seccomp_mode = SECCOMP_MODE_FILTER;
+	struct seccomp_filter *prepared = NULL;
+	long ret = -EINVAL;
+
+	/* Validate flags. */
+	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
+		return -EINVAL;
+
+	/* Prepare the new filter before holding any locks. */
+	prepared = seccomp_prepare_user_filter(filter);
+	if (IS_ERR(prepared))
+		return PTR_ERR(prepared);
+
+	/*
+	 * Make sure we cannot change seccomp or nnp state via TSYNC
+	 * while another thread is in the middle of calling exec.
+	 */
+	if (flags & SECCOMP_FILTER_FLAG_TSYNC &&
+	    mutex_lock_killable(&current->signal->cred_guard_mutex))
+		goto out_free;
+
+	spin_lock_irq(&current->sighand->siglock);
+
+	if (!seccomp_may_assign_mode(seccomp_mode))
+		goto out;
+
+	ret = seccomp_attach_filter(flags, prepared);
+	if (ret)
+		goto out;
+	/* Do not free the successfully attached filter. */
+	prepared = NULL;
+
+	seccomp_assign_mode(current, seccomp_mode);
+out:
+	spin_unlock_irq(&current->sighand->siglock);
+	if (flags & SECCOMP_FILTER_FLAG_TSYNC)
+		mutex_unlock(&current->signal->cred_guard_mutex);
+out_free:
+	seccomp_filter_free(prepared);
+	return ret;
+}
+#else
+static inline long seccomp_set_mode_filter(unsigned int flags,
+					   const char __user *filter)
+{
+	return -EINVAL;
+}
+#endif
+
+/* Common entry point for both prctl and syscall. */
+static long do_seccomp(unsigned int op, unsigned int flags,
+		       const char __user *uargs)
+{
+	switch (op) {
+	case SECCOMP_SET_MODE_STRICT:
+		if (flags != 0 || uargs != NULL)
+			return -EINVAL;
+		return seccomp_set_mode_strict();
+	case SECCOMP_SET_MODE_FILTER:
+		return seccomp_set_mode_filter(flags, uargs);
+	default:
+		return -EINVAL;
+	}
+}
+
+SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags,
+			 const char __user *, uargs)
+{
+	return do_seccomp(op, flags, uargs);
+}
+
+/**
+ * prctl_set_seccomp: configures current->seccomp.mode
+ * @seccomp_mode: requested mode to use
+ * @filter: optional struct sock_fprog for use with SECCOMP_MODE_FILTER
+ *
+ * Returns 0 on success or -EINVAL on failure.
+ */
+long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
+{
+	unsigned int op;
+	char __user *uargs;
+
 	switch (seccomp_mode) {
 	case SECCOMP_MODE_STRICT:
-		ret = 0;
-#ifdef TIF_NOTSC
-		disable_TSC();
-#endif
+		op = SECCOMP_SET_MODE_STRICT;
+		/*
+		 * Setting strict mode through prctl always ignored filter,
+		 * so make sure it is always NULL here to pass the internal
+		 * check in do_seccomp().
+		 */
+		uargs = NULL;
 		break;
-#ifdef CONFIG_SECCOMP_FILTER
 	case SECCOMP_MODE_FILTER:
-		ret = seccomp_attach_user_filter(filter);
-		if (ret)
-			goto out;
+		op = SECCOMP_SET_MODE_FILTER;
+		uargs = filter;
 		break;
-#endif
 	default:
-		goto out;
+		return -EINVAL;
 	}
 
-	current->seccomp.mode = seccomp_mode;
-	set_thread_flag(TIF_SECCOMP);
-out:
-	return ret;
+	/* prctl interface doesn't have flags, so they are always zero. */
+	return do_seccomp(op, 0, uargs);
 }

kernel/sys.c

@@ -1990,12 +1990,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (arg2 != 1 || arg3 || arg4 || arg5)
 			return -EINVAL;
 
-		current->no_new_privs = 1;
+		task_set_no_new_privs(current);
 		break;
 	case PR_GET_NO_NEW_PRIVS:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
-		return current->no_new_privs ? 1 : 0;
+		return task_no_new_privs(current) ? 1 : 0;
 	case PR_GET_THP_DISABLE:
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;

kernel/sys_ni.c

@@ -213,3 +213,6 @@ cond_syscall(compat_sys_open_by_handle_at);
 
 /* compare kernel pointers */
 cond_syscall(sys_kcmp);
+
+/* operate on Secure Computing state */
+cond_syscall(sys_seccomp);

security/apparmor/domain.c

@@ -621,7 +621,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 	 * There is no exception for unconfined as change_hat is not
 	 * available.
 	 */
-	if (current->no_new_privs)
+	if (task_no_new_privs(current))
 		return -EPERM;
 
 	/* released below */
@@ -776,7 +776,7 @@ int aa_change_profile(const char *ns_name, const char *hname, bool onexec,
 	 * no_new_privs is set because this aways results in a reduction
 	 * of permissions.
 	 */
-	if (current->no_new_privs && !unconfined(profile)) {
+	if (task_no_new_privs(current) && !unconfined(profile)) {
 		put_cred(cred);
 		return -EPERM;
 	}