Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Resolve conflicts with conntrack template fixes.

Conflicts:
	net/netfilter/nf_conntrack_core.c
	net/netfilter/nf_synproxy_core.c
	net/netfilter/xt_CT.c

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

9 files changed, 268 insertions, 55 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cb31229a6fa4..29ace107f236 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -150,15 +150,15 @@ static int __init register_array_map(void)
 }
 late_initcall(register_array_map);
 
-static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
+static struct bpf_map *fd_array_map_alloc(union bpf_attr *attr)
 {
-	/* only bpf_prog file descriptors can be stored in prog_array map */
+	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return ERR_PTR(-EINVAL);
 	return array_map_alloc(attr);
 }
 
-static void prog_array_map_free(struct bpf_map *map)
+static void fd_array_map_free(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
@@ -167,21 +167,21 @@ static void prog_array_map_free(struct bpf_map *map)
 
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
-		BUG_ON(array->prog[i] != NULL);
+		BUG_ON(array->ptrs[i] != NULL);
 	kvfree(array);
 }
 
-static void *prog_array_map_lookup_elem(struct bpf_map *map, void *key)
+static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
 {
 	return NULL;
 }
 
 /* only called from syscall */
-static int prog_array_map_update_elem(struct bpf_map *map, void *key,
-				      void *value, u64 map_flags)
+static int fd_array_map_update_elem(struct bpf_map *map, void *key,
+				    void *value, u64 map_flags)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *prog, *old_prog;
+	void *new_ptr, *old_ptr;
 	u32 index = *(u32 *)key, ufd;
 
 	if (map_flags != BPF_ANY)
@@ -191,57 +191,75 @@ static int prog_array_map_update_elem(struct bpf_map *map, void *key,
 		return -E2BIG;
 
 	ufd = *(u32 *)value;
-	prog = bpf_prog_get(ufd);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
-	if (!bpf_prog_array_compatible(array, prog)) {
-		bpf_prog_put(prog);
-		return -EINVAL;
-	}
+	new_ptr = map->ops->map_fd_get_ptr(map, ufd);
+	if (IS_ERR(new_ptr))
+		return PTR_ERR(new_ptr);
 
-	old_prog = xchg(array->prog + index, prog);
-	if (old_prog)
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, new_ptr);
+	if (old_ptr)
+		map->ops->map_fd_put_ptr(old_ptr);
 
 	return 0;
 }
 
-static int prog_array_map_delete_elem(struct bpf_map *map, void *key)
+static int fd_array_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
-	struct bpf_prog *old_prog;
+	void *old_ptr;
 	u32 index = *(u32 *)key;
 
 	if (index >= array->map.max_entries)
 		return -E2BIG;
 
-	old_prog = xchg(array->prog + index, NULL);
-	if (old_prog) {
-		bpf_prog_put_rcu(old_prog);
+	old_ptr = xchg(array->ptrs + index, NULL);
+	if (old_ptr) {
+		map->ops->map_fd_put_ptr(old_ptr);
 		return 0;
 	} else {
 		return -ENOENT;
 	}
 }
 
+static void *prog_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct bpf_prog *prog = bpf_prog_get(fd);
+	if (IS_ERR(prog))
+		return prog;
+
+	if (!bpf_prog_array_compatible(array, prog)) {
+		bpf_prog_put(prog);
+		return ERR_PTR(-EINVAL);
+	}
+	return prog;
+}
+
+static void prog_fd_array_put_ptr(void *ptr)
+{
+	struct bpf_prog *prog = ptr;
+
+	bpf_prog_put_rcu(prog);
+}
+
 /* decrement refcnt of all bpf_progs that are stored in this map */
-void bpf_prog_array_map_clear(struct bpf_map *map)
+void bpf_fd_array_map_clear(struct bpf_map *map)
 {
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
 	int i;
 
 	for (i = 0; i < array->map.max_entries; i++)
-		prog_array_map_delete_elem(map, &i);
+		fd_array_map_delete_elem(map, &i);
 }
 
 static const struct bpf_map_ops prog_array_ops = {
-	.map_alloc = prog_array_map_alloc,
-	.map_free = prog_array_map_free,
+	.map_alloc = fd_array_map_alloc,
+	.map_free = fd_array_map_free,
 	.map_get_next_key = array_map_get_next_key,
-	.map_lookup_elem = prog_array_map_lookup_elem,
-	.map_update_elem = prog_array_map_update_elem,
-	.map_delete_elem = prog_array_map_delete_elem,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = prog_fd_array_get_ptr,
+	.map_fd_put_ptr = prog_fd_array_put_ptr,
 };
 
 static struct bpf_map_type_list prog_array_type __read_mostly = {
@@ -255,3 +273,60 @@ static int __init register_prog_array_map(void)
 	return 0;
 }
 late_initcall(register_prog_array_map);
+
+static void perf_event_array_map_free(struct bpf_map *map)
+{
+	bpf_fd_array_map_clear(map);
+	fd_array_map_free(map);
+}
+
+static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd)
+{
+	struct perf_event *event;
+	const struct perf_event_attr *attr;
+
+	event = perf_event_get(fd);
+	if (IS_ERR(event))
+		return event;
+
+	attr = perf_event_attrs(event);
+	if (IS_ERR(attr))
+		return (void *)attr;
+
+	if (attr->type != PERF_TYPE_RAW &&
+	    attr->type != PERF_TYPE_HARDWARE) {
+		perf_event_release_kernel(event);
+		return ERR_PTR(-EINVAL);
+	}
+	return event;
+}
+
+static void perf_event_fd_array_put_ptr(void *ptr)
+{
+	struct perf_event *event = ptr;
+
+	perf_event_release_kernel(event);
+}
+
+static const struct bpf_map_ops perf_event_array_ops = {
+	.map_alloc = fd_array_map_alloc,
+	.map_free = perf_event_array_map_free,
+	.map_get_next_key = array_map_get_next_key,
+	.map_lookup_elem = fd_array_map_lookup_elem,
+	.map_update_elem = fd_array_map_update_elem,
+	.map_delete_elem = fd_array_map_delete_elem,
+	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
+	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
+};
+
+static struct bpf_map_type_list perf_event_array_type __read_mostly = {
+	.ops = &perf_event_array_ops,
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+};
+
+static int __init register_perf_event_array_map(void)
+{
+	bpf_register_map_type(&perf_event_array_type);
+	return 0;
+}
+late_initcall(register_perf_event_array_map);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index fafa74161445..67c380cfa9ca 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -450,7 +450,7 @@ select_insn:
 
 		tail_call_cnt++;
 
-		prog = READ_ONCE(array->prog[index]);
+		prog = READ_ONCE(array->ptrs[index]);
 		if (unlikely(!prog))
 			goto out;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a1b14d197a4f..dc9b464fefa9 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -72,7 +72,7 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 		/* prog_array stores refcnt-ed bpf_prog pointers
 		 * release them all when user space closes prog_array_fd
 		 */
-		bpf_prog_array_map_clear(map);
+		bpf_fd_array_map_clear(map);
 
 	bpf_map_put(map);
 	return 0;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cd307df98cb3..ed12e385fb75 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -238,6 +238,14 @@ static const char * const reg_type_str[] = {
 	[CONST_IMM]		= "imm",
 };
 
+static const struct {
+	int map_type;
+	int func_id;
+} func_limit[] = {
+	{BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call},
+	{BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read},
+};
+
 static void print_verifier_state(struct verifier_env *env)
 {
 	enum bpf_reg_type t;
@@ -837,6 +845,28 @@ static int check_func_arg(struct verifier_env *env, u32 regno,
 	return err;
 }
 
+static int check_map_func_compatibility(struct bpf_map *map, int func_id)
+{
+	bool bool_map, bool_func;
+	int i;
+
+	if (!map)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(func_limit); i++) {
+		bool_map = (map->map_type == func_limit[i].map_type);
+		bool_func = (func_id == func_limit[i].func_id);
+		/* only when map & func pair match it can continue.
+		 * don't allow any other map type to be passed into
+		 * the special func;
+		 */
+		if (bool_map != bool_func)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int check_call(struct verifier_env *env, int func_id)
 {
 	struct verifier_state *state = &env->cur_state;
@@ -912,21 +942,9 @@ static int check_call(struct verifier_env *env, int func_id)
 		return -EINVAL;
 	}
 
-	if (map && map->map_type == BPF_MAP_TYPE_PROG_ARRAY &&
-	    func_id != BPF_FUNC_tail_call)
-		/* prog_array map type needs extra care:
-		 * only allow to pass it into bpf_tail_call() for now.
-		 * bpf_map_delete_elem() can be allowed in the future,
-		 * while bpf_map_update_elem() must only be done via syscall
-		 */
-		return -EINVAL;
-
-	if (func_id == BPF_FUNC_tail_call &&
-	    map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
-		/* don't allow any other map type to be passed into
-		 * bpf_tail_call()
-		 */
-		return -EINVAL;
+	err = check_map_func_compatibility(map, func_id);
+	if (err)
+		return err;
 
 	return 0;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d3dae3419b99..e2c6a8886d4d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3212,6 +3212,59 @@ static inline u64 perf_event_count(struct perf_event *event)
 	return __perf_event_count(event);
 }
 
+/*
+ * NMI-safe method to read a local event, that is an event that
+ * is:
+ *   - either for the current task, or for this CPU
+ *   - does not have inherit set, for inherited task events
+ *     will not be local and we cannot read them atomically
+ *   - must not have a pmu::count method
+ */
+u64 perf_event_read_local(struct perf_event *event)
+{
+	unsigned long flags;
+	u64 val;
+
+	/*
+	 * Disabling interrupts avoids all counter scheduling (context
+	 * switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
+	/* If this is a per-task event, it must be for current */
+	WARN_ON_ONCE((event->attach_state & PERF_ATTACH_TASK) &&
+		     event->hw.target != current);
+
+	/* If this is a per-CPU event, it must be for this CPU */
+	WARN_ON_ONCE(!(event->attach_state & PERF_ATTACH_TASK) &&
+		     event->cpu != smp_processor_id());
+
+	/*
+	 * It must not be an event with inherit set, we cannot read
+	 * all child counters from atomic context.
+	 */
+	WARN_ON_ONCE(event->attr.inherit);
+
+	/*
+	 * It must not have a pmu::count method, those are not
+	 * NMI safe.
+	 */
+	WARN_ON_ONCE(event->pmu->count);
+
+	/*
+	 * If the event is currently on this CPU, its either a per-task event,
+	 * or local to this CPU. Furthermore it means its ACTIVE (otherwise
+	 * oncpu == -1).
+	 */
+	if (event->oncpu == smp_processor_id())
+		event->pmu->read(event);
+
+	val = local64_read(&event->count);
+	local_irq_restore(flags);
+
+	return val;
+}
+
 static u64 perf_event_read(struct perf_event *event)
 {
 	/*
@@ -8574,6 +8627,31 @@ void perf_event_delayed_put(struct task_struct *task)
 		WARN_ON_ONCE(task->perf_event_ctxp[ctxn]);
 }
 
+struct perf_event *perf_event_get(unsigned int fd)
+{
+	int err;
+	struct fd f;
+	struct perf_event *event;
+
+	err = perf_fget_light(fd, &f);
+	if (err)
+		return ERR_PTR(err);
+
+	event = f.file->private_data;
+	atomic_long_inc(&event->refcount);
+	fdput(f);
+
+	return event;
+}
+
+const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
+{
+	if (!event)
+		return ERR_PTR(-EINVAL);
+
+	return &event->attr;
+}
+
 /*
  * inherit a event from parent task to child task:
  */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 10e489c448fe..fdea0bee7b5a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -97,6 +97,7 @@ bool kthread_should_park(void)
 {
 	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
 }
+EXPORT_SYMBOL_GPL(kthread_should_park);
 
 /**
  * kthread_freezable_should_stop - should this freezable kthread return now?
@@ -171,6 +172,7 @@ void kthread_parkme(void)
 {
 	__kthread_parkme(to_kthread(current));
 }
+EXPORT_SYMBOL_GPL(kthread_parkme);
 
 static int kthread(void *_create)
 {
@@ -411,6 +413,7 @@ void kthread_unpark(struct task_struct *k)
 	if (kthread)
 		__kthread_unpark(k, kthread);
 }
+EXPORT_SYMBOL_GPL(kthread_unpark);
 
 /**
  * kthread_park - park a thread created by kthread_create().
@@ -441,6 +444,7 @@ int kthread_park(struct task_struct *k)
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(kthread_park);
 
 /**
  * kthread_stop - stop a thread created by kthread_create().
diff --git a/kernel/module.c b/kernel/module.c
index 4d2b82e610e2..b86b7bf1be38 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -602,13 +602,16 @@ const struct kernel_symbol *find_symbol(const char *name,
 }
 EXPORT_SYMBOL_GPL(find_symbol);
 
-/* Search for module by name: must hold module_mutex. */
+/*
+ * Search for module by name: must hold module_mutex (or preempt disabled
+ * for read-only access).
+ */
 static struct module *find_module_all(const char *name, size_t len,
 				      bool even_unformed)
 {
 	struct module *mod;
 
-	module_assert_mutex();
+	module_assert_mutex_or_preempt();
 
 	list_for_each_entry(mod, &modules, list) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
@@ -621,6 +624,7 @@ static struct module *find_module_all(const char *name, size_t len,
 
 struct module *find_module(const char *name)
 {
+	module_assert_mutex();
 	return find_module_all(name, strlen(name), false);
 }
 EXPORT_SYMBOL_GPL(find_module);
diff --git a/kernel/signal.c b/kernel/signal.c
index 836df8dac6cc..0f6bbbe77b46 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2748,12 +2748,15 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 #ifdef SEGV_BNDERR
-		err |= __put_user(from->si_lower, &to->si_lower);
-		err |= __put_user(from->si_upper, &to->si_upper);
+		if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
+			err |= __put_user(from->si_lower, &to->si_lower);
+			err |= __put_user(from->si_upper, &to->si_upper);
+		}
 #endif
 		break;
 	case __SI_CHLD:
@@ -3017,7 +3020,7 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 	int ret = copy_siginfo_from_user32(&info, uinfo);
 	if (unlikely(ret))
 		return ret;
@@ -3061,7 +3064,7 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo,
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 
 	if (copy_siginfo_from_user32(&info, uinfo))
 		return -EFAULT;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 88a041adee90..ef9936df1b04 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -158,6 +158,35 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void)
 	return &bpf_trace_printk_proto;
 }
 
+static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5)
+{
+	struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	struct perf_event *event;
+
+	if (unlikely(index >= array->map.max_entries))
+		return -E2BIG;
+
+	event = (struct perf_event *)array->ptrs[index];
+	if (!event)
+		return -ENOENT;
+
+	/*
+	 * we don't know if the function is run successfully by the
+	 * return value. It can be judged in other places, such as
+	 * eBPF programs.
+	 */
+	return perf_event_read_local(event);
+}
+
+const struct bpf_func_proto bpf_perf_event_read_proto = {
+	.func		= bpf_perf_event_read,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -183,6 +212,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return bpf_get_trace_printk_proto();
 	case BPF_FUNC_get_smp_processor_id:
 		return &bpf_get_smp_processor_id_proto;
+	case BPF_FUNC_perf_event_read:
+		return &bpf_perf_event_read_proto;
 	default:
 		return NULL;
 	}