Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

All conflicts seemed rather trivial, with some guidance from
Saeed Mameed on the tc_ct.c one.

Signed-off-by: David S. Miller <davem@davemloft.net>

30 files changed, 461 insertions, 281 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 4c3007f428b1..30721f2c2d10 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3776,7 +3776,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 				return false;
 
 			t = btf_type_skip_modifiers(btf, t->type, NULL);
-			if (!btf_type_is_int(t)) {
+			if (!btf_type_is_small_int(t)) {
 				bpf_log(log,
 					"ret type %s not allowed for fmod_ret\n",
 					btf_kind_str[BTF_INFO_KIND(t->info)]);
@@ -3798,7 +3798,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 	/* skip modifiers */
 	while (btf_type_is_modifier(t))
 		t = btf_type_by_id(btf, t->type);
-	if (btf_type_is_int(t) || btf_type_is_enum(t))
+	if (btf_type_is_small_int(t) || btf_type_is_enum(t))
 		/* accessing a scalar */
 		return true;
 	if (!btf_type_is_ptr(t)) {
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 78cf061f8179..310241ca7991 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -19,18 +19,21 @@ struct bpf_netns_link {
 	 * with netns_bpf_mutex held.
 	 */
 	struct net *net;
+	struct list_head node; /* node in list of links attached to net */
 };
 
 /* Protects updates to netns_bpf */
 DEFINE_MUTEX(netns_bpf_mutex);
 
 /* Must be called with netns_bpf_mutex held. */
-static void __net_exit bpf_netns_link_auto_detach(struct bpf_link *link)
+static void netns_bpf_run_array_detach(struct net *net,
+				       enum netns_bpf_attach_type type)
 {
-	struct bpf_netns_link *net_link =
-		container_of(link, struct bpf_netns_link, link);
+	struct bpf_prog_array *run_array;
 
-	net_link->net = NULL;
+	run_array = rcu_replace_pointer(net->bpf.run_array[type], NULL,
+					lockdep_is_held(&netns_bpf_mutex));
+	bpf_prog_array_free(run_array);
 }
 
 static void bpf_netns_link_release(struct bpf_link *link)
@@ -40,22 +43,18 @@ static void bpf_netns_link_release(struct bpf_link *link)
 	enum netns_bpf_attach_type type = net_link->netns_type;
 	struct net *net;
 
-	/* Link auto-detached by dying netns. */
-	if (!net_link->net)
-		return;
-
 	mutex_lock(&netns_bpf_mutex);
 
-	/* Recheck after potential sleep. We can race with cleanup_net
-	 * here, but if we see a non-NULL struct net pointer pre_exit
-	 * has not happened yet and will block on netns_bpf_mutex.
+	/* We can race with cleanup_net, but if we see a non-NULL
+	 * struct net pointer, pre_exit has not run yet and wait for
+	 * netns_bpf_mutex.
 	 */
 	net = net_link->net;
 	if (!net)
 		goto out_unlock;
 
-	net->bpf.links[type] = NULL;
-	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+	netns_bpf_run_array_detach(net, type);
+	list_del(&net_link->node);
 
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
@@ -76,6 +75,7 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 	struct bpf_netns_link *net_link =
 		container_of(link, struct bpf_netns_link, link);
 	enum netns_bpf_attach_type type = net_link->netns_type;
+	struct bpf_prog_array *run_array;
 	struct net *net;
 	int ret = 0;
 
@@ -93,8 +93,11 @@ static int bpf_netns_link_update_prog(struct bpf_link *link,
 		goto out_unlock;
 	}
 
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	WRITE_ONCE(run_array->items[0].prog, new_prog);
+
 	old_prog = xchg(&link->prog, new_prog);
-	rcu_assign_pointer(net->bpf.progs[type], new_prog);
 	bpf_prog_put(old_prog);
 
 out_unlock:
@@ -142,14 +145,38 @@ static const struct bpf_link_ops bpf_netns_link_ops = {
 	.show_fdinfo = bpf_netns_link_show_fdinfo,
 };
 
+/* Must be called with netns_bpf_mutex held. */
+static int __netns_bpf_prog_query(const union bpf_attr *attr,
+				  union bpf_attr __user *uattr,
+				  struct net *net,
+				  enum netns_bpf_attach_type type)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	struct bpf_prog_array *run_array;
+	u32 prog_cnt = 0, flags = 0;
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array)
+		prog_cnt = bpf_prog_array_length(run_array);
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
+		return -EFAULT;
+	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		return -EFAULT;
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		return 0;
+
+	return bpf_prog_array_copy_to_user(run_array, prog_ids,
+					   attr->query.prog_cnt);
+}
+
 int netns_bpf_prog_query(const union bpf_attr *attr,
 			 union bpf_attr __user *uattr)
 {
-	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
-	u32 prog_id, prog_cnt = 0, flags = 0;
 	enum netns_bpf_attach_type type;
-	struct bpf_prog *attached;
 	struct net *net;
+	int ret;
 
 	if (attr->query.query_flags)
 		return -EINVAL;
@@ -162,36 +189,25 @@ int netns_bpf_prog_query(const union bpf_attr *attr,
 	if (IS_ERR(net))
 		return PTR_ERR(net);
 
-	rcu_read_lock();
-	attached = rcu_dereference(net->bpf.progs[type]);
-	if (attached) {
-		prog_cnt = 1;
-		prog_id = attached->aux->id;
-	}
-	rcu_read_unlock();
+	mutex_lock(&netns_bpf_mutex);
+	ret = __netns_bpf_prog_query(attr, uattr, net, type);
+	mutex_unlock(&netns_bpf_mutex);
 
 	put_net(net);
-
-	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
-		return -EFAULT;
-	if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
-		return -EFAULT;
-
-	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
-		return 0;
-
-	if (copy_to_user(prog_ids, &prog_id, sizeof(u32)))
-		return -EFAULT;
-
-	return 0;
+	return ret;
 }
 
 int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
+	struct bpf_prog_array *run_array;
 	enum netns_bpf_attach_type type;
+	struct bpf_prog *attached;
 	struct net *net;
 	int ret;
 
+	if (attr->target_fd || attr->attach_flags || attr->replace_bpf_fd)
+		return -EINVAL;
+
 	type = to_netns_bpf_attach_type(attr->attach_type);
 	if (type < 0)
 		return -EINVAL;
@@ -200,19 +216,47 @@ int netns_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	mutex_lock(&netns_bpf_mutex);
 
 	/* Attaching prog directly is not compatible with links */
-	if (net->bpf.links[type]) {
+	if (!list_empty(&net->bpf.links[type])) {
 		ret = -EEXIST;
 		goto out_unlock;
 	}
 
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
-		ret = flow_dissector_bpf_prog_attach(net, prog);
+		ret = flow_dissector_bpf_prog_attach_check(net, prog);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
+	if (ret)
+		goto out_unlock;
+
+	attached = net->bpf.progs[type];
+	if (attached == prog) {
+		/* The same program cannot be attached twice */
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	run_array = rcu_dereference_protected(net->bpf.run_array[type],
+					      lockdep_is_held(&netns_bpf_mutex));
+	if (run_array) {
+		WRITE_ONCE(run_array->items[0].prog, prog);
+	} else {
+		run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+		if (!run_array) {
+			ret = -ENOMEM;
+			goto out_unlock;
+		}
+		run_array->items[0].prog = prog;
+		rcu_assign_pointer(net->bpf.run_array[type], run_array);
+	}
+
+	net->bpf.progs[type] = prog;
+	if (attached)
+		bpf_prog_put(attached);
+
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
 
@@ -221,63 +265,74 @@ out_unlock:
 
 /* Must be called with netns_bpf_mutex held. */
 static int __netns_bpf_prog_detach(struct net *net,
-				   enum netns_bpf_attach_type type)
+				   enum netns_bpf_attach_type type,
+				   struct bpf_prog *old)
 {
 	struct bpf_prog *attached;
 
 	/* Progs attached via links cannot be detached */
-	if (net->bpf.links[type])
+	if (!list_empty(&net->bpf.links[type]))
 		return -EINVAL;
 
-	attached = rcu_dereference_protected(net->bpf.progs[type],
-					     lockdep_is_held(&netns_bpf_mutex));
-	if (!attached)
+	attached = net->bpf.progs[type];
+	if (!attached || attached != old)
 		return -ENOENT;
-	RCU_INIT_POINTER(net->bpf.progs[type], NULL);
+	netns_bpf_run_array_detach(net, type);
+	net->bpf.progs[type] = NULL;
 	bpf_prog_put(attached);
 	return 0;
 }
 
-int netns_bpf_prog_detach(const union bpf_attr *attr)
+int netns_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
 {
 	enum netns_bpf_attach_type type;
+	struct bpf_prog *prog;
 	int ret;
 
+	if (attr->target_fd)
+		return -EINVAL;
+
 	type = to_netns_bpf_attach_type(attr->attach_type);
 	if (type < 0)
 		return -EINVAL;
 
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
 	mutex_lock(&netns_bpf_mutex);
-	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type);
+	ret = __netns_bpf_prog_detach(current->nsproxy->net_ns, type, prog);
 	mutex_unlock(&netns_bpf_mutex);
 
+	bpf_prog_put(prog);
+
 	return ret;
 }
 
 static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 				 enum netns_bpf_attach_type type)
 {
-	struct bpf_prog *prog;
+	struct bpf_netns_link *net_link =
+		container_of(link, struct bpf_netns_link, link);
+	struct bpf_prog_array *run_array;
 	int err;
 
 	mutex_lock(&netns_bpf_mutex);
 
 	/* Allow attaching only one prog or link for now */
-	if (net->bpf.links[type]) {
+	if (!list_empty(&net->bpf.links[type])) {
 		err = -E2BIG;
 		goto out_unlock;
 	}
 	/* Links are not compatible with attaching prog directly */
-	prog = rcu_dereference_protected(net->bpf.progs[type],
-					 lockdep_is_held(&netns_bpf_mutex));
-	if (prog) {
+	if (net->bpf.progs[type]) {
 		err = -EEXIST;
 		goto out_unlock;
 	}
 
 	switch (type) {
 	case NETNS_BPF_FLOW_DISSECTOR:
-		err = flow_dissector_bpf_prog_attach(net, link->prog);
+		err = flow_dissector_bpf_prog_attach_check(net, link->prog);
 		break;
 	default:
 		err = -EINVAL;
@@ -286,7 +341,15 @@ static int netns_bpf_link_attach(struct net *net, struct bpf_link *link,
 	if (err)
 		goto out_unlock;
 
-	net->bpf.links[type] = link;
+	run_array = bpf_prog_array_alloc(1, GFP_KERNEL);
+	if (!run_array) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+	run_array->items[0].prog = link->prog;
+	rcu_assign_pointer(net->bpf.run_array[type], run_array);
+
+	list_add_tail(&net_link->node, &net->bpf.links[type]);
 
 out_unlock:
 	mutex_unlock(&netns_bpf_mutex);
@@ -345,23 +408,34 @@ out_put_net:
 	return err;
 }
 
+static int __net_init netns_bpf_pernet_init(struct net *net)
+{
+	int type;
+
+	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++)
+		INIT_LIST_HEAD(&net->bpf.links[type]);
+
+	return 0;
+}
+
 static void __net_exit netns_bpf_pernet_pre_exit(struct net *net)
 {
 	enum netns_bpf_attach_type type;
-	struct bpf_link *link;
+	struct bpf_netns_link *net_link;
 
 	mutex_lock(&netns_bpf_mutex);
 	for (type = 0; type < MAX_NETNS_BPF_ATTACH_TYPE; type++) {
-		link = net->bpf.links[type];
-		if (link)
-			bpf_netns_link_auto_detach(link);
-		else
-			__netns_bpf_prog_detach(net, type);
+		netns_bpf_run_array_detach(net, type);
+		list_for_each_entry(net_link, &net->bpf.links[type], node)
+			net_link->net = NULL; /* auto-detach link */
+		if (net->bpf.progs[type])
+			bpf_prog_put(net->bpf.progs[type]);
 	}
 	mutex_unlock(&netns_bpf_mutex);
 }
 
 static struct pernet_operations netns_bpf_pernet_ops __net_initdata = {
+	.init = netns_bpf_pernet_init,
 	.pre_exit = netns_bpf_pernet_pre_exit,
 };
 
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 3625c4fcc65c..90b29c5b1da7 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -20,11 +20,14 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map)
 /* The caller must hold the reuseport_lock */
 void bpf_sk_reuseport_detach(struct sock *sk)
 {
-	struct sock __rcu **socks;
+	uintptr_t sk_user_data;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	socks = sk->sk_user_data;
-	if (socks) {
+	sk_user_data = (uintptr_t)sk->sk_user_data;
+	if (sk_user_data & SK_USER_DATA_BPF) {
+		struct sock __rcu **socks;
+
+		socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK);
 		WRITE_ONCE(sk->sk_user_data, NULL);
 		/*
 		 * Do not move this NULL assignment outside of
@@ -250,6 +253,7 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	struct sock *free_osk = NULL, *osk, *nsk;
 	struct sock_reuseport *reuse;
 	u32 index = *(u32 *)key;
+	uintptr_t sk_user_data;
 	struct socket *socket;
 	int err, fd;
 
@@ -303,7 +307,9 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
 	if (err)
 		goto put_file_unlock;
 
-	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY |
+		SK_USER_DATA_BPF;
+	WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data);
 	rcu_assign_pointer(array->ptrs[index], nsk);
 	free_osk = osk;
 	err = 0;
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 13a8d3967e07..002f8a5c9e51 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -132,15 +132,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 {
 	struct bpf_ringbuf *rb;
 
-	if (!data_sz || !PAGE_ALIGNED(data_sz))
-		return ERR_PTR(-EINVAL);
-
-#ifdef CONFIG_64BIT
-	/* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
-	if (data_sz > RINGBUF_MAX_DATA_SZ)
-		return ERR_PTR(-E2BIG);
-#endif
-
 	rb = bpf_ringbuf_area_alloc(data_sz, numa_node);
 	if (!rb)
 		return ERR_PTR(-ENOMEM);
@@ -166,9 +157,16 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-EINVAL);
 
 	if (attr->key_size || attr->value_size ||
-	    attr->max_entries == 0 || !PAGE_ALIGNED(attr->max_entries))
+	    !is_power_of_2(attr->max_entries) ||
+	    !PAGE_ALIGNED(attr->max_entries))
 		return ERR_PTR(-EINVAL);
 
+#ifdef CONFIG_64BIT
+	/* on 32-bit arch, it's impossible to overflow record's hdr->pgoff */
+	if (attr->max_entries > RINGBUF_MAX_DATA_SZ)
+		return ERR_PTR(-E2BIG);
+#endif
+
 	rb_map = kzalloc(sizeof(*rb_map), GFP_USER);
 	if (!rb_map)
 		return ERR_PTR(-ENOMEM);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8da159936bab..0fd80ac81f70 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2121,7 +2121,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	    !bpf_capable())
 		return -EPERM;
 
-	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN))
+	if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (is_perfmon_prog_type(type) && !perfmon_capable())
 		return -EPERM;
@@ -2893,13 +2893,11 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (ptype) {
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_SK_SKB:
-		return sock_map_get_from_fd(attr, NULL);
+		return sock_map_prog_detach(attr, ptype);
 	case BPF_PROG_TYPE_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		return netns_bpf_prog_detach(attr);
+		return netns_bpf_prog_detach(attr, ptype);
 	case BPF_PROG_TYPE_CGROUP_DEVICE:
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
@@ -3139,7 +3137,8 @@ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
 	return NULL;
 }
 
-static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
+static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog,
+					      const struct cred *f_cred)
 {
 	const struct bpf_map *map;
 	struct bpf_insn *insns;
@@ -3165,7 +3164,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 		    code == (BPF_JMP | BPF_CALL_ARGS)) {
 			if (code == (BPF_JMP | BPF_CALL_ARGS))
 				insns[i].code = BPF_JMP | BPF_CALL;
-			if (!bpf_dump_raw_ok())
+			if (!bpf_dump_raw_ok(f_cred))
 				insns[i].imm = 0;
 			continue;
 		}
@@ -3221,7 +3220,8 @@ static int set_info_rec_size(struct bpf_prog_info *info)
 	return 0;
 }
 
-static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
+static int bpf_prog_get_info_by_fd(struct file *file,
+				   struct bpf_prog *prog,
 				   const union bpf_attr *attr,
 				   union bpf_attr __user *uattr)
 {
@@ -3290,11 +3290,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 		struct bpf_insn *insns_sanitized;
 		bool fault;
 
-		if (prog->blinded && !bpf_dump_raw_ok()) {
+		if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) {
 			info.xlated_prog_insns = 0;
 			goto done;
 		}
-		insns_sanitized = bpf_insn_prepare_dump(prog);
+		insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred);
 		if (!insns_sanitized)
 			return -ENOMEM;
 		uinsns = u64_to_user_ptr(info.xlated_prog_insns);
@@ -3328,7 +3328,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	if (info.jited_prog_len && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			uinsns = u64_to_user_ptr(info.jited_prog_insns);
 			ulen = min_t(u32, info.jited_prog_len, ulen);
 
@@ -3363,7 +3363,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_ksyms;
 	info.nr_jited_ksyms = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			unsigned long ksym_addr;
 			u64 __user *user_ksyms;
 			u32 i;
@@ -3394,7 +3394,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	ulen = info.nr_jited_func_lens;
 	info.nr_jited_func_lens = prog->aux->func_cnt ? : 1;
 	if (ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			u32 __user *user_lens;
 			u32 func_len, i;
 
@@ -3451,7 +3451,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	else
 		info.nr_jited_line_info = 0;
 	if (info.nr_jited_line_info && ulen) {
-		if (bpf_dump_raw_ok()) {
+		if (bpf_dump_raw_ok(file->f_cred)) {
 			__u64 __user *user_linfo;
 			u32 i;
 
@@ -3497,7 +3497,8 @@ done:
 	return 0;
 }
 
-static int bpf_map_get_info_by_fd(struct bpf_map *map,
+static int bpf_map_get_info_by_fd(struct file *file,
+				  struct bpf_map *map,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3540,7 +3541,8 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map,
 	return 0;
 }
 
-static int bpf_btf_get_info_by_fd(struct btf *btf,
+static int bpf_btf_get_info_by_fd(struct file *file,
+				  struct btf *btf,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3555,7 +3557,8 @@ static int bpf_btf_get_info_by_fd(struct btf *btf,
 	return btf_get_info_by_fd(btf, attr, uattr);
 }
 
-static int bpf_link_get_info_by_fd(struct bpf_link *link,
+static int bpf_link_get_info_by_fd(struct file *file,
+				  struct bpf_link *link,
 				  const union bpf_attr *attr,
 				  union bpf_attr __user *uattr)
 {
@@ -3608,15 +3611,15 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 		return -EBADFD;
 
 	if (f.file->f_op == &bpf_prog_fops)
-		err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_prog_get_info_by_fd(f.file, f.file->private_data, attr,
 					      uattr);
 	else if (f.file->f_op == &bpf_map_fops)
-		err = bpf_map_get_info_by_fd(f.file->private_data, attr,
+		err = bpf_map_get_info_by_fd(f.file, f.file->private_data, attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
-		err = bpf_btf_get_info_by_fd(f.file->private_data, attr, uattr);
+		err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
 	else if (f.file->f_op == &bpf_link_fops)
-		err = bpf_link_get_info_by_fd(f.file->private_data,
+		err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
 					      attr, uattr);
 	else
 		err = -EINVAL;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b608185e1ffd..3c1efc9d08fd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -399,8 +399,7 @@ static bool reg_type_not_null(enum bpf_reg_type type)
 	return type == PTR_TO_SOCKET ||
 		type == PTR_TO_TCP_SOCK ||
 		type == PTR_TO_MAP_VALUE ||
-		type == PTR_TO_SOCK_COMMON ||
-	        type == PTR_TO_BTF_ID;
+		type == PTR_TO_SOCK_COMMON;
 }
 
 static bool reg_type_may_be_null(enum bpf_reg_type type)
@@ -9896,7 +9895,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	int i, j, subprog_start, subprog_end = 0, len, subprog;
 	struct bpf_insn *insn;
 	void *old_bpf_func;
-	int err;
+	int err, num_exentries;
 
 	if (env->subprog_cnt <= 1)
 		return 0;
@@ -9971,6 +9970,14 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
 		func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
+		num_exentries = 0;
+		insn = func[i]->insnsi;
+		for (j = 0; j < func[i]->len; j++, insn++) {
+			if (BPF_CLASS(insn->code) == BPF_LDX &&
+			    BPF_MODE(insn->code) == BPF_PROBE_MEM)
+				num_exentries++;
+		}
+		func[i]->aux->num_exentries = num_exentries;
 		func[i] = bpf_int_jit_compile(func[i]);
 		if (!func[i]->jited) {
 			err = -ENOTSUPP;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 1ea181a58465..dd247747ec14 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6439,18 +6439,8 @@ void cgroup_sk_alloc_disable(void)
 
 void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 {
-	if (cgroup_sk_alloc_disabled)
-		return;
-
-	/* Socket clone path */
-	if (skcd->val) {
-		/*
-		 * We might be cloning a socket which is left in an empty
-		 * cgroup and the cgroup might have already been rmdir'd.
-		 * Don't use cgroup_get_live().
-		 */
-		cgroup_get(sock_cgroup_ptr(skcd));
-		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	if (cgroup_sk_alloc_disabled) {
+		skcd->no_refcnt = 1;
 		return;
 	}
 
@@ -6475,10 +6465,27 @@ void cgroup_sk_alloc(struct sock_cgroup_data *skcd)
 	rcu_read_unlock();
 }
 
+void cgroup_sk_clone(struct sock_cgroup_data *skcd)
+{
+	if (skcd->val) {
+		if (skcd->no_refcnt)
+			return;
+		/*
+		 * We might be cloning a socket which is left in an empty
+		 * cgroup and the cgroup might have already been rmdir'd.
+		 * Don't use cgroup_get_live().
+		 */
+		cgroup_get(sock_cgroup_ptr(skcd));
+		cgroup_bpf_get(sock_cgroup_ptr(skcd));
+	}
+}
+
 void cgroup_sk_free(struct sock_cgroup_data *skcd)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(skcd);
 
+	if (skcd->no_refcnt)
+		return;
 	cgroup_bpf_put(cgrp);
 	cgroup_put(cgrp);
 }
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index bc8d25f2ac8a..9e5934780f41 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -587,6 +587,7 @@ static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
 		arch_kgdb_ops.disable_hw_break(regs);
 
 acquirelock:
+	rcu_read_lock();
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
 	 * single stepping.
@@ -646,6 +647,7 @@ return_normal:
 			atomic_dec(&slaves_in_kgdb);
 			dbg_touch_watchdogs();
 			local_irq_restore(flags);
+			rcu_read_unlock();
 			return 0;
 		}
 		cpu_relax();
@@ -664,6 +666,7 @@ return_normal:
 		raw_spin_unlock(&dbg_master_lock);
 		dbg_touch_watchdogs();
 		local_irq_restore(flags);
+		rcu_read_unlock();
 
 		goto acquirelock;
 	}
@@ -787,6 +790,7 @@ kgdb_restore:
 	raw_spin_unlock(&dbg_master_lock);
 	dbg_touch_watchdogs();
 	local_irq_restore(flags);
+	rcu_read_unlock();
 
 	return kgdb_info[cpu].ret_state;
 }
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 924bc9298a42..683a799618ad 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -542,6 +542,44 @@ static int kdb_search_string(char *searched, char *searchfor)
 	return 0;
 }
 
+static void kdb_msg_write(const char *msg, int msg_len)
+{
+	struct console *c;
+
+	if (msg_len == 0)
+		return;
+
+	if (dbg_io_ops) {
+		const char *cp = msg;
+		int len = msg_len;
+
+		while (len--) {
+			dbg_io_ops->write_char(*cp);
+			cp++;
+		}
+	}
+
+	for_each_console(c) {
+		if (!(c->flags & CON_ENABLED))
+			continue;
+		if (c == dbg_io_ops->cons)
+			continue;
+		/*
+		 * Set oops_in_progress to encourage the console drivers to
+		 * disregard their internal spin locks: in the current calling
+		 * context the risk of deadlock is a bigger problem than risks
+		 * due to re-entering the console driver. We operate directly on
+		 * oops_in_progress rather than using bust_spinlocks() because
+		 * the calls bust_spinlocks() makes on exit are not appropriate
+		 * for this calling context.
+		 */
+		++oops_in_progress;
+		c->write(c, msg, msg_len);
+		--oops_in_progress;
+		touch_nmi_watchdog();
+	}
+}
+
 int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 {
 	int diag;
@@ -553,7 +591,6 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap)
 	int this_cpu, old_cpu;
 	char *cp, *cp2, *cphold = NULL, replaced_byte = ' ';
 	char *moreprompt = "more> ";
-	struct console *c;
 	unsigned long uninitialized_var(flags);
 
 	/* Serialize kdb_printf if multiple cpus try to write at once.
@@ -687,22 +724,11 @@ kdb_printit:
 	 */
 	retlen = strlen(kdb_buffer);
 	cp = (char *) printk_skip_headers(kdb_buffer);
-	if (!dbg_kdb_mode && kgdb_connected) {
+	if (!dbg_kdb_mode && kgdb_connected)
 		gdbstub_msg_write(cp, retlen - (cp - kdb_buffer));
-	} else {
-		if (dbg_io_ops && !dbg_io_ops->is_console) {
-			len = retlen - (cp - kdb_buffer);
-			cp2 = cp;
-			while (len--) {
-				dbg_io_ops->write_char(*cp2);
-				cp2++;
-			}
-		}
-		for_each_console(c) {
-			c->write(c, cp, retlen - (cp - kdb_buffer));
-			touch_nmi_watchdog();
-		}
-	}
+	else
+		kdb_msg_write(cp, retlen - (cp - kdb_buffer));
+
 	if (logging) {
 		saved_loglevel = console_loglevel;
 		console_loglevel = CONSOLE_LOGLEVEL_SILENT;
@@ -751,19 +777,7 @@ kdb_printit:
 			moreprompt = "more> ";
 
 		kdb_input_flush();
-
-		if (dbg_io_ops && !dbg_io_ops->is_console) {
-			len = strlen(moreprompt);
-			cp = moreprompt;
-			while (len--) {
-				dbg_io_ops->write_char(*cp);
-				cp++;
-			}
-		}
-		for_each_console(c) {
-			c->write(c, moreprompt, strlen(moreprompt));
-			touch_nmi_watchdog();
-		}
+		kdb_msg_write(moreprompt, strlen(moreprompt));
 
 		if (logging)
 			printk("%s", moreprompt);
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index a0ce3c1494fd..1da3f44f2565 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -71,15 +71,16 @@ config SWIOTLB
 # in the pagetables
 #
 config DMA_NONCOHERENT_MMAP
+	default y if !MMU
 	bool
 
 config DMA_COHERENT_POOL
+	select GENERIC_ALLOCATOR
 	bool
 
 config DMA_REMAP
 	bool
 	depends on MMU
-	select GENERIC_ALLOCATOR
 	select DMA_NONCOHERENT_MMAP
 
 config DMA_DIRECT_REMAP
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 0a4881e59aa7..95866b647581 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -109,14 +109,15 @@ static inline bool dma_should_free_from_pool(struct device *dev,
 	return false;
 }
 
-struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
+static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp, unsigned long attrs)
 {
-	size_t alloc_size = PAGE_ALIGN(size);
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
 	u64 phys_limit;
 
+	WARN_ON_ONCE(!PAGE_ALIGNED(size));
+
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
@@ -124,14 +125,14 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	gfp &= ~__GFP_ZERO;
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_limit);
-	page = dma_alloc_contiguous(dev, alloc_size, gfp);
+	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		dma_free_contiguous(dev, page, alloc_size);
+		dma_free_contiguous(dev, page, size);
 		page = NULL;
 	}
 again:
 	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(alloc_size));
+		page = alloc_pages_node(node, gfp, get_order(size));
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, size);
 		page = NULL;
@@ -157,9 +158,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 {
 	struct page *page;
 	void *ret;
+	int err;
+
+	size = PAGE_ALIGN(size);
 
 	if (dma_should_alloc_from_pool(dev, gfp, attrs)) {
-		ret = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, gfp);
+		ret = dma_alloc_from_pool(dev, size, &page, gfp);
 		if (!ret)
 			return NULL;
 		goto done;
@@ -183,14 +187,20 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	     dma_alloc_need_uncached(dev, attrs)) ||
 	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
 		/* remove any dirty cache lines on the kernel alias */
-		arch_dma_prep_coherent(page, PAGE_ALIGN(size));
+		arch_dma_prep_coherent(page, size);
 
 		/* create a coherent mapping */
-		ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size),
+		ret = dma_common_contiguous_remap(page, size,
 				dma_pgprot(dev, PAGE_KERNEL, attrs),
 				__builtin_return_address(0));
 		if (!ret)
 			goto out_free_pages;
+		if (force_dma_unencrypted(dev)) {
+			err = set_memory_decrypted((unsigned long)ret,
+						   1 << get_order(size));
+			if (err)
+				goto out_free_pages;
+		}
 		memset(ret, 0, size);
 		goto done;
 	}
@@ -207,8 +217,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted(dev))
-		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_decrypted((unsigned long)ret,
+					   1 << get_order(size));
+		if (err)
+			goto out_free_pages;
+	}
 
 	memset(ret, 0, size);
 
@@ -217,7 +231,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		arch_dma_prep_coherent(page, size);
 		ret = arch_dma_set_uncached(ret, size);
 		if (IS_ERR(ret))
-			goto out_free_pages;
+			goto out_encrypt_pages;
 	}
 done:
 	if (force_dma_unencrypted(dev))
@@ -225,6 +239,15 @@ done:
 	else
 		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	return ret;
+
+out_encrypt_pages:
+	if (force_dma_unencrypted(dev)) {
+		err = set_memory_encrypted((unsigned long)page_address(page),
+					   1 << get_order(size));
+		/* If memory cannot be re-encrypted, it must be leaked */
+		if (err)
+			return NULL;
+	}
 out_free_pages:
 	dma_free_contiguous(dev, page, size);
 	return NULL;
@@ -459,7 +482,6 @@ int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
-#ifdef CONFIG_MMU
 bool dma_direct_can_mmap(struct device *dev)
 {
 	return dev_is_dma_coherent(dev) ||
@@ -485,19 +507,6 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 	return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
 			user_count << PAGE_SHIFT, vma->vm_page_prot);
 }
-#else /* CONFIG_MMU */
-bool dma_direct_can_mmap(struct device *dev)
-{
-	return false;
-}
-
-int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size,
-		unsigned long attrs)
-{
-	return -ENXIO;
-}
-#endif /* CONFIG_MMU */
 
 int dma_direct_supported(struct device *dev, u64 mask)
 {
@@ -530,3 +539,9 @@ size_t dma_direct_max_mapping_size(struct device *dev)
 		return swiotlb_max_mapping_size(dev);
 	return SIZE_MAX;
 }
+
+bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return !dev_is_dma_coherent(dev) ||
+		is_swiotlb_buffer(dma_to_phys(dev, dma_addr));
+}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 98e3d873792e..a8c18c9a796f 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -397,6 +397,16 @@ size_t dma_max_mapping_size(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dma_max_mapping_size);
 
+bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (dma_is_direct(ops))
+		return dma_direct_need_sync(dev, dma_addr);
+	return ops->sync_single_for_cpu || ops->sync_single_for_device;
+}
+EXPORT_SYMBOL_GPL(dma_need_sync);
+
 unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 8cfa01243ed2..39ca26fa41b5 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -239,12 +239,16 @@ void *dma_alloc_from_pool(struct device *dev, size_t size,
 	}
 
 	val = gen_pool_alloc(pool, size);
-	if (val) {
+	if (likely(val)) {
 		phys_addr_t phys = gen_pool_virt_to_phys(pool, val);
 
 		*ret_page = pfn_to_page(__phys_to_pfn(phys));
 		ptr = (void *)val;
 		memset(ptr, 0, size);
+	} else {
+		WARN_ONCE(1, "DMA coherent pool depleted, increase size "
+			     "(recommended min coherent_pool=%zuK)\n",
+			  gen_pool_size(pool) >> 9);
 	}
 	if (gen_pool_avail(pool) < atomic_pool_size)
 		schedule_work(&atomic_pool_work);
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index e739a6eea6e7..78b23f089cf1 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -24,7 +24,8 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 {
 	void *vaddr;
 
-	vaddr = vmap(pages, size >> PAGE_SHIFT, VM_DMA_COHERENT, prot);
+	vaddr = vmap(pages, PAGE_ALIGN(size) >> PAGE_SHIFT,
+		     VM_DMA_COHERENT, prot);
 	if (vaddr)
 		find_vm_area(vaddr)->pages = pages;
 	return vaddr;
@@ -37,7 +38,7 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller)
 {
-	int count = size >> PAGE_SHIFT;
+	int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	struct page **pages;
 	void *vaddr;
 	int i;
diff --git a/kernel/fork.c b/kernel/fork.c
index 142b23645d82..efc5493203ae 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1977,7 +1977,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 * to stop root fork bombs.
 	 */
 	retval = -EAGAIN;
-	if (nr_threads >= max_threads)
+	if (data_race(nr_threads >= max_threads))
 		goto bad_fork_cleanup_count;
 
 	delayacct_tsk_init(p);	/* Must remain after dup_task_struct() */
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 16c8c605f4b0..bb14e64f62a4 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -644,19 +644,20 @@ static inline int kallsyms_for_perf(void)
  * Otherwise, require CAP_SYSLOG (assuming kptr_restrict isn't set to
  * block even that).
  */
-int kallsyms_show_value(void)
+bool kallsyms_show_value(const struct cred *cred)
 {
 	switch (kptr_restrict) {
 	case 0:
 		if (kallsyms_for_perf())
-			return 1;
+			return true;
 	/* fallthrough */
 	case 1:
-		if (has_capability_noaudit(current, CAP_SYSLOG))
-			return 1;
+		if (security_capable(cred, &init_user_ns, CAP_SYSLOG,
+				     CAP_OPT_NOAUDIT) == 0)
+			return true;
 	/* fallthrough */
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -673,7 +674,11 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 	reset_iter(iter, 0);
 
-	iter->show_value = kallsyms_show_value();
+	/*
+	 * Instead of checking this on every s_show() call, cache
+	 * the result here at open time.
+	 */
+	iter->show_value = kallsyms_show_value(file->f_cred);
 	return 0;
 }
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index bb05fd52de85..09cc78df53c6 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -181,34 +181,19 @@ void kimage_file_post_load_cleanup(struct kimage *image)
 static int
 kimage_validate_signature(struct kimage *image)
 {
-	const char *reason;
 	int ret;
 
 	ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf,
 					   image->kernel_buf_len);
-	switch (ret) {
-	case 0:
-		break;
+	if (ret) {
 
-		/* Certain verification errors are non-fatal if we're not
-		 * checking errors, provided we aren't mandating that there
-		 * must be a valid signature.
-		 */
-	case -ENODATA:
-		reason = "kexec of unsigned image";
-		goto decide;
-	case -ENOPKG:
-		reason = "kexec of image with unsupported crypto";
-		goto decide;
-	case -ENOKEY:
-		reason = "kexec of image with unavailable key";
-	decide:
 		if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) {
-			pr_notice("%s rejected\n", reason);
+			pr_notice("Enforced kernel signature verification failed (%d).\n", ret);
 			return ret;
 		}
 
-		/* If IMA is guaranteed to appraise a signature on the kexec
+		/*
+		 * If IMA is guaranteed to appraise a signature on the kexec
 		 * image, permit it even if the kernel is otherwise locked
 		 * down.
 		 */
@@ -216,17 +201,10 @@ kimage_validate_signature(struct kimage *image)
 		    security_locked_down(LOCKDOWN_KEXEC))
 			return -EPERM;
 
-		return 0;
-
-		/* All other errors are fatal, including nomem, unparseable
-		 * signatures and signature check failures - even if signatures
-		 * aren't required.
-		 */
-	default:
-		pr_notice("kernel signature verification failed (%d).\n", ret);
+		pr_debug("kernel signature verification failed (%d).\n", ret);
 	}
 
-	return ret;
+	return 0;
 }
 #endif
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 4a904cc56d68..2e97febeef77 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2448,7 +2448,7 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 	else
 		kprobe_type = "k";
 
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(pi->file->f_cred))
 		addr = NULL;
 
 	if (sym)
@@ -2540,7 +2540,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	 * If /proc/kallsyms is not showing kernel address, we won't
 	 * show them here either.
 	 */
-	if (!kallsyms_show_value())
+	if (!kallsyms_show_value(m->file->f_cred))
 		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
 			   (void *)ent->start_addr);
 	else
diff --git a/kernel/module.c b/kernel/module.c
index e8a198588f26..aa183c9ac0a2 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1510,8 +1510,7 @@ static inline bool sect_empty(const Elf_Shdr *sect)
 }
 
 struct module_sect_attr {
-	struct module_attribute mattr;
-	char *name;
+	struct bin_attribute battr;
 	unsigned long address;
 };
 
@@ -1521,13 +1520,18 @@ struct module_sect_attrs {
 	struct module_sect_attr attrs[];
 };
 
-static ssize_t module_sect_show(struct module_attribute *mattr,
-				struct module_kobject *mk, char *buf)
+static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
+				struct bin_attribute *battr,
+				char *buf, loff_t pos, size_t count)
 {
 	struct module_sect_attr *sattr =
-		container_of(mattr, struct module_sect_attr, mattr);
-	return sprintf(buf, "0x%px\n", kptr_restrict < 2 ?
-		       (void *)sattr->address : NULL);
+		container_of(battr, struct module_sect_attr, battr);
+
+	if (pos != 0)
+		return -EINVAL;
+
+	return sprintf(buf, "0x%px\n",
+		       kallsyms_show_value(file->f_cred) ? (void *)sattr->address : NULL);
 }
 
 static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
@@ -1535,7 +1539,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
 	unsigned int section;
 
 	for (section = 0; section < sect_attrs->nsections; section++)
-		kfree(sect_attrs->attrs[section].name);
+		kfree(sect_attrs->attrs[section].battr.attr.name);
 	kfree(sect_attrs);
 }
 
@@ -1544,42 +1548,41 @@ static void add_sect_attrs(struct module *mod, const struct load_info *info)
 	unsigned int nloaded = 0, i, size[2];
 	struct module_sect_attrs *sect_attrs;
 	struct module_sect_attr *sattr;
-	struct attribute **gattr;
+	struct bin_attribute **gattr;
 
 	/* Count loaded sections and allocate structures */
 	for (i = 0; i < info->hdr->e_shnum; i++)
 		if (!sect_empty(&info->sechdrs[i]))
 			nloaded++;
 	size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded),
-			sizeof(sect_attrs->grp.attrs[0]));
-	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.attrs[0]);
+			sizeof(sect_attrs->grp.bin_attrs[0]));
+	size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]);
 	sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL);
 	if (sect_attrs == NULL)
 		return;
 
 	/* Setup section attributes. */
 	sect_attrs->grp.name = "sections";
-	sect_attrs->grp.attrs = (void *)sect_attrs + size[0];
+	sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0];
 
 	sect_attrs->nsections = 0;
 	sattr = &sect_attrs->attrs[0];
-	gattr = &sect_attrs->grp.attrs[0];
+	gattr = &sect_attrs->grp.bin_attrs[0];
 	for (i = 0; i < info->hdr->e_shnum; i++) {
 		Elf_Shdr *sec = &info->sechdrs[i];
 		if (sect_empty(sec))
 			continue;
+		sysfs_bin_attr_init(&sattr->battr);
 		sattr->address = sec->sh_addr;
-		sattr->name = kstrdup(info->secstrings + sec->sh_name,
-					GFP_KERNEL);
-		if (sattr->name == NULL)
+		sattr->battr.attr.name =
+			kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
+		if (sattr->battr.attr.name == NULL)
 			goto out;
 		sect_attrs->nsections++;
-		sysfs_attr_init(&sattr->mattr.attr);
-		sattr->mattr.show = module_sect_show;
-		sattr->mattr.store = NULL;
-		sattr->mattr.attr.name = sattr->name;
-		sattr->mattr.attr.mode = S_IRUSR;
-		*(gattr++) = &(sattr++)->mattr.attr;
+		sattr->battr.read = module_sect_read;
+		sattr->battr.size = 3 /* "0x", "\n" */ + (BITS_PER_LONG / 4);
+		sattr->battr.attr.mode = 0400;
+		*(gattr++) = &(sattr++)->battr;
 	}
 	*gattr = NULL;
 
@@ -1669,7 +1672,7 @@ static void add_notes_attrs(struct module *mod, const struct load_info *info)
 			continue;
 		if (info->sechdrs[i].sh_type == SHT_NOTE) {
 			sysfs_bin_attr_init(nattr);
-			nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
+			nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name;
 			nattr->attr.mode = S_IRUGO;
 			nattr->size = info->sechdrs[i].sh_size;
 			nattr->private = (void *) info->sechdrs[i].sh_addr;
@@ -2783,7 +2786,9 @@ static void dynamic_debug_remove(struct module *mod, struct _ddebug *debug)
 
 void * __weak module_alloc(unsigned long size)
 {
-	return vmalloc_exec(size);
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 bool __weak module_init_section(const char *name)
@@ -4377,7 +4382,7 @@ static int modules_open(struct inode *inode, struct file *file)
 
 	if (!err) {
 		struct seq_file *m = file->private_data;
-		m->private = kallsyms_show_value() ? NULL : (void *)8ul;
+		m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul;
 	}
 
 	return err;
diff --git a/kernel/padata.c b/kernel/padata.c
index 29fc5d87a4cd..4373f7adaa40 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -335,7 +335,7 @@ static void padata_reorder(struct parallel_data *pd)
 	 *
 	 * Ensure reorder queue is read after pd->lock is dropped so we see
 	 * new objects from another task in padata_do_serial.  Pairs with
-	 * smp_mb__after_atomic in padata_do_serial.
+	 * smp_mb in padata_do_serial.
 	 */
 	smp_mb();
 
@@ -418,7 +418,7 @@ void padata_do_serial(struct padata_priv *padata)
 	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
 	 * in padata_reorder.
 	 */
-	smp_mb__after_atomic();
+	smp_mb();
 
 	padata_reorder(pd);
 }
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 16dd1e6b7c09..9eb39c20082c 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -723,7 +723,7 @@ kfree_perf_init(void)
 		schedule_timeout_uninterruptible(1);
 	}
 
-	pr_alert("kfree object size=%lu\n", kfree_mult * sizeof(struct kfree_obj));
+	pr_alert("kfree object size=%zu\n", kfree_mult * sizeof(struct kfree_obj));
 
 	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
 			       GFP_KERNEL);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c716eadc7617..6c6569e0586c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -250,7 +250,7 @@ static noinstr void rcu_dynticks_eqs_enter(void)
 	 * next idle sojourn.
 	 */
 	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
@@ -274,13 +274,13 @@ static noinstr void rcu_dynticks_eqs_exit(void)
 	 * and we also must force ordering with the next RCU read-side
 	 * critical section.
 	 */
-	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	seq = arch_atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
 	// RCU is now watching.  Better not be in an extended quiescent state!
 	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
-		atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
+		arch_atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks);
 		smp_mb__after_atomic(); /* _exit after clearing mask. */
 	}
 }
@@ -313,7 +313,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
+	return !(arch_atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR);
 }
 
 /*
@@ -633,6 +633,10 @@ static noinstr void rcu_eqs_enter(bool user)
 	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	instrumentation_end();
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
 	// RCU is watching here ...
@@ -692,6 +696,7 @@ noinstr void rcu_nmi_exit(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
+	instrumentation_begin();
 	/*
 	 * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks.
 	 * (We are exiting an NMI handler, so RCU better be paying attention
@@ -705,7 +710,6 @@ noinstr void rcu_nmi_exit(void)
 	 * leave it in non-RCU-idle state.
 	 */
 	if (rdp->dynticks_nmi_nesting != 1) {
-		instrumentation_begin();
 		trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2,
 				  atomic_read(&rdp->dynticks));
 		WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */
@@ -714,13 +718,15 @@ noinstr void rcu_nmi_exit(void)
 		return;
 	}
 
-	instrumentation_begin();
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
 	if (!in_nmi())
 		rcu_prepare_for_idle();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
 
 	// RCU is watching here ...
@@ -838,6 +844,10 @@ static void noinstr rcu_eqs_exit(bool user)
 	rcu_dynticks_eqs_exit();
 	// ... but is watching here.
 	instrumentation_begin();
+
+	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
@@ -983,13 +993,21 @@ noinstr void rcu_nmi_enter(void)
 		if (!in_nmi())
 			rcu_cleanup_after_idle();
 
+		instrumentation_begin();
+		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
+		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
+		// instrumentation for the noinstr rcu_dynticks_eqs_exit()
+		instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
+
 		incby = 1;
 	} else if (!in_nmi()) {
 		instrumentation_begin();
 		rcu_irq_enter_check_tick();
 		instrumentation_end();
+	} else  {
+		instrumentation_begin();
 	}
-	instrumentation_begin();
+
 	trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="),
 			  rdp->dynticks_nmi_nesting,
 			  rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks));
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8f360326861e..ca5db40392d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1637,7 +1637,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	/*
@@ -2293,8 +2293,15 @@ void sched_ttwu_pending(void *arg)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -2322,7 +2329,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	__smp_call_single_queue(cpu, &p->wake_entry);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2369,7 +2376,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	 * the soon-to-be-idle CPU as the current CPU is likely busy.
 	 * nr_running is checked to avoid unnecessary task stacking.
 	 */
-	if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1)
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
 		return true;
 
 	return false;
@@ -2378,6 +2385,9 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -2528,7 +2538,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2550,7 +2559,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2614,8 +2622,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * which potentially sends an IPI instead of spinning on p->on_cpu to
 	 * let the waker make forward progress. This is safe because IRQs are
 	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
 	 */
-	if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ))
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
 		goto unlock;
 
 	/*
@@ -2635,6 +2656,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2642,7 +2665,7 @@ unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
@@ -2763,7 +2786,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
-	p->wake_entry_type = CSD_TYPE_TTWU;
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 #endif
 }
 
@@ -4533,7 +4556,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 504d2f51b0d6..f63f337c7147 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2692,6 +2692,7 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
+	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cbcb2f71599b..658aa7a2ae6f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -806,7 +806,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 		}
 	}
 
-	sa->runnable_avg = cpu_scale;
+	sa->runnable_avg = sa->util_avg;
 
 	if (p->sched_class != &fair_sched_class) {
 		/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 05deb81bb3e3..1ae95b9150d3 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -96,6 +96,15 @@ void __cpuidle default_idle_call(void)
 	}
 }
 
+static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev)
+{
+	if (current_clr_polling_and_test())
+		return -EBUSY;
+
+	return cpuidle_enter_s2idle(drv, dev);
+}
+
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      int next_state)
 {
@@ -171,11 +180,9 @@ static void cpuidle_idle_call(void)
 		if (idle_should_enter_s2idle()) {
 			rcu_idle_enter();
 
-			entered_state = cpuidle_enter_s2idle(drv, dev);
-			if (entered_state > 0) {
-				local_irq_enable();
+			entered_state = call_cpuidle_s2idle(drv, dev);
+			if (entered_state > 0)
 				goto exit_idle;
-			}
 
 			rcu_idle_exit();
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1d4e94c1e5fe..877fb08eb1b0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1682,7 +1682,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
 #define WF_MIGRATED		0x04		/* Internal use, task got migrated */
-#define WF_ON_RQ		0x08		/* Wakee is on_rq */
+#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
diff --git a/kernel/signal.c b/kernel/signal.c
index 5ca48cc5da76..ee22ec78fd6d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2529,9 +2529,6 @@ bool get_signal(struct ksignal *ksig)
 	struct signal_struct *signal = current->signal;
 	int signr;
 
-	if (unlikely(current->task_works))
-		task_work_run();
-
 	if (unlikely(uprobe_deny_signal()))
 		return false;
 
@@ -2544,6 +2541,13 @@ bool get_signal(struct ksignal *ksig)
 
 relock:
 	spin_lock_irq(&sighand->siglock);
+	current->jobctl &= ~JOBCTL_TASK_WORK;
+	if (unlikely(current->task_works)) {
+		spin_unlock_irq(&sighand->siglock);
+		task_work_run();
+		goto relock;
+	}
+
 	/*
 	 * Every stopped thread goes here after wakeup. Check to see if
 	 * we should notify the parent, prepare_signal(SIGCONT) encodes
diff --git a/kernel/smp.c b/kernel/smp.c
index 472c2b274c65..aa17eedff5be 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -669,24 +669,6 @@ void __init smp_init(void)
 {
 	int num_nodes, num_cpus;
 
-	/*
-	 * Ensure struct irq_work layout matches so that
-	 * flush_smp_call_function_queue() can do horrible things.
-	 */
-	BUILD_BUG_ON(offsetof(struct irq_work, llnode) !=
-		     offsetof(struct __call_single_data, llist));
-	BUILD_BUG_ON(offsetof(struct irq_work, func) !=
-		     offsetof(struct __call_single_data, func));
-	BUILD_BUG_ON(offsetof(struct irq_work, flags) !=
-		     offsetof(struct __call_single_data, flags));
-
-	/*
-	 * Assert the CSD_TYPE_TTWU layout is similar enough
-	 * for task_struct to be on the @call_single_queue.
-	 */
-	BUILD_BUG_ON(offsetof(struct task_struct, wake_entry_type) - offsetof(struct task_struct, wake_entry) !=
-		     offsetof(struct __call_single_data, flags) - offsetof(struct __call_single_data, llist));
-
 	idle_threads_init();
 	cpuhp_threads_init();
 
diff --git a/kernel/task_work.c b/kernel/task_work.c
index 825f28259a19..5c0848ca1287 100644
--- a/kernel/task_work.c
+++ b/kernel/task_work.c
@@ -25,9 +25,10 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * 0 if succeeds or -ESRCH.
  */
 int
-task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
+task_work_add(struct task_struct *task, struct callback_head *work, int notify)
 {
 	struct callback_head *head;
+	unsigned long flags;
 
 	do {
 		head = READ_ONCE(task->task_works);
@@ -36,8 +37,19 @@ task_work_add(struct task_struct *task, struct callback_head *work, bool notify)
 		work->next = head;
 	} while (cmpxchg(&task->task_works, head, work) != head);
 
-	if (notify)
+	switch (notify) {
+	case TWA_RESUME:
 		set_notify_resume(task);
+		break;
+	case TWA_SIGNAL:
+		if (lock_task_sighand(task, &flags)) {
+			task->jobctl |= JOBCTL_TASK_WORK;
+			signal_wake_up(task, 0);
+			unlock_task_sighand(task, &flags);
+		}
+		break;
+	}
+
 	return 0;
 }