Merge remote-tracking branch 'net-next/master' into mac80211-next

Merge net-next to resolve a conflict and to get the mac80211
rhashtable fixes so further patches can be applied on top.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

27 files changed, 410 insertions, 158 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 7019c1f05cab..bd3921b1514b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1530,7 +1530,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 
 		/* "typedef void new_void", "const void"...etc */
 		if (!btf_type_is_void(next_type) &&
-		    !btf_type_is_fwd(next_type)) {
+		    !btf_type_is_fwd(next_type) &&
+		    !btf_type_is_func_proto(next_type)) {
 			btf_verifier_log_type(env, v->t, "Invalid type_id");
 			return -EINVAL;
 		}
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index d78cfec5807d..4e807973aa80 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -573,7 +573,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	bpf_compute_and_save_data_end(skb, &saved_data_end);
 
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
-				 bpf_prog_run_save_cb);
+				 __bpf_prog_run_save_cb);
 	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
 	skb->sk = save_sk;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 937776531998..fed15cf94dca 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 	}
 
 	if (htab_is_prealloc(htab)) {
-		pcpu_freelist_push(&htab->freelist, &l->fnode);
+		__pcpu_freelist_push(&htab->freelist, &l->fnode);
 	} else {
 		atomic_dec(&htab->count);
 		l->htab = htab;
@@ -739,7 +739,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 		} else {
 			struct pcpu_freelist_node *l;
 
-			l = pcpu_freelist_pop(&htab->freelist);
+			l = __pcpu_freelist_pop(&htab->freelist);
 			if (!l)
 				return ERR_PTR(-E2BIG);
 			l_new = container_of(l, struct htab_elem, fnode);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 39dba8c90331..ba635209ae9a 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -35,6 +35,7 @@ static DECLARE_RWSEM(bpf_devs_lock);
 struct bpf_offload_dev {
 	const struct bpf_prog_offload_ops *ops;
 	struct list_head netdevs;
+	void *priv;
 };
 
 struct bpf_offload_netdev {
@@ -669,7 +670,7 @@ unlock:
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
 
 struct bpf_offload_dev *
-bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
+bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv)
 {
 	struct bpf_offload_dev *offdev;
 	int err;
@@ -688,6 +689,7 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops)
 		return ERR_PTR(-ENOMEM);
 
 	offdev->ops = ops;
+	offdev->priv = priv;
 	INIT_LIST_HEAD(&offdev->netdevs);
 
 	return offdev;
@@ -700,3 +702,9 @@ void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
 	kfree(offdev);
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);
+
+void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev)
+{
+	return offdev->priv;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_priv);
diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c
index 673fa6fe2d73..0c1b4ba9e90e 100644
--- a/kernel/bpf/percpu_freelist.c
+++ b/kernel/bpf/percpu_freelist.c
@@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s)
 	free_percpu(s->freelist);
 }
 
-static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
-					struct pcpu_freelist_node *node)
+static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head,
+					 struct pcpu_freelist_node *node)
 {
 	raw_spin_lock(&head->lock);
 	node->next = head->first;
@@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head,
 	raw_spin_unlock(&head->lock);
 }
 
-void pcpu_freelist_push(struct pcpu_freelist *s,
+void __pcpu_freelist_push(struct pcpu_freelist *s,
 			struct pcpu_freelist_node *node)
 {
 	struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist);
 
-	__pcpu_freelist_push(head, node);
+	___pcpu_freelist_push(head, node);
+}
+
+void pcpu_freelist_push(struct pcpu_freelist *s,
+			struct pcpu_freelist_node *node)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__pcpu_freelist_push(s, node);
+	local_irq_restore(flags);
 }
 
 void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
@@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 	for_each_possible_cpu(cpu) {
 again:
 		head = per_cpu_ptr(s->freelist, cpu);
-		__pcpu_freelist_push(head, buf);
+		___pcpu_freelist_push(head, buf);
 		i++;
 		buf += elem_size;
 		if (i == nr_elems)
@@ -74,14 +84,12 @@ again:
 	local_irq_restore(flags);
 }
 
-struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s)
 {
 	struct pcpu_freelist_head *head;
 	struct pcpu_freelist_node *node;
-	unsigned long flags;
 	int orig_cpu, cpu;
 
-	local_irq_save(flags);
 	orig_cpu = cpu = raw_smp_processor_id();
 	while (1) {
 		head = per_cpu_ptr(s->freelist, cpu);
@@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
 		node = head->first;
 		if (node) {
 			head->first = node->next;
-			raw_spin_unlock_irqrestore(&head->lock, flags);
+			raw_spin_unlock(&head->lock);
 			return node;
 		}
 		raw_spin_unlock(&head->lock);
 		cpu = cpumask_next(cpu, cpu_possible_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = 0;
-		if (cpu == orig_cpu) {
-			local_irq_restore(flags);
+		if (cpu == orig_cpu)
 			return NULL;
-		}
 	}
 }
+
+struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s)
+{
+	struct pcpu_freelist_node *ret;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ret = __pcpu_freelist_pop(s);
+	local_irq_restore(flags);
+	return ret;
+}
diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h
index 3049aae8ea1e..c3960118e617 100644
--- a/kernel/bpf/percpu_freelist.h
+++ b/kernel/bpf/percpu_freelist.h
@@ -22,8 +22,12 @@ struct pcpu_freelist_node {
 	struct pcpu_freelist_node *next;
 };
 
+/* pcpu_freelist_* do spin_lock_irqsave. */
 void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
 struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *);
+/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */
+void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *);
+struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *);
 void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size,
 			    u32 nr_elems);
 int pcpu_freelist_init(struct pcpu_freelist *);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d43b14535827..950ab2f28922 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry)
 	struct stack_map_irq_work *work;
 
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read(work->sem);
+	up_read_non_owner(work->sem);
 	work->sem = NULL;
 }
 
@@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	} else {
 		work->sem = &current->mm->mmap_sem;
 		irq_work_queue(&work->irq_work);
+		/*
+		 * The irq_work will release the mmap_sem with
+		 * up_read_non_owner(). The rwsem_release() is called
+		 * here to release the lock from lockdep's perspective.
+		 */
+		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
 	}
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0834958f1dc4..ec7c552af76b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -740,8 +740,13 @@ static int map_lookup_elem(union bpf_attr *attr)
 
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_lookup_elem(map, key, value);
-	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
-		   map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
+		goto done;
+	}
+
+	preempt_disable();
+	this_cpu_inc(bpf_prog_active);
+	if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	    map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
 		err = bpf_percpu_hash_copy(map, key, value);
 	} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
 		err = bpf_percpu_array_copy(map, key, value);
@@ -777,7 +782,10 @@ static int map_lookup_elem(union bpf_attr *attr)
 		}
 		rcu_read_unlock();
 	}
+	this_cpu_dec(bpf_prog_active);
+	preempt_enable();
 
+done:
 	if (err)
 		goto free_value;
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b63bc77af2d1..1b9496c41383 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -331,10 +331,19 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type)
 	       type == PTR_TO_PACKET_META;
 }
 
+static bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCK_COMMON ||
+		type == PTR_TO_TCP_SOCK;
+}
+
 static bool reg_type_may_be_null(enum bpf_reg_type type)
 {
 	return type == PTR_TO_MAP_VALUE_OR_NULL ||
-	       type == PTR_TO_SOCKET_OR_NULL;
+	       type == PTR_TO_SOCKET_OR_NULL ||
+	       type == PTR_TO_SOCK_COMMON_OR_NULL ||
+	       type == PTR_TO_TCP_SOCK_OR_NULL;
 }
 
 static bool type_is_refcounted(enum bpf_reg_type type)
@@ -377,6 +386,12 @@ static bool is_release_function(enum bpf_func_id func_id)
 	return func_id == BPF_FUNC_sk_release;
 }
 
+static bool is_acquire_function(enum bpf_func_id func_id)
+{
+	return func_id == BPF_FUNC_sk_lookup_tcp ||
+		func_id == BPF_FUNC_sk_lookup_udp;
+}
+
 /* string representation of 'enum bpf_reg_type' */
 static const char * const reg_type_str[] = {
 	[NOT_INIT]		= "?",
@@ -392,6 +407,10 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_FLOW_KEYS]	= "flow_keys",
 	[PTR_TO_SOCKET]		= "sock",
 	[PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
+	[PTR_TO_SOCK_COMMON]	= "sock_common",
+	[PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
+	[PTR_TO_TCP_SOCK]	= "tcp_sock",
+	[PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
 };
 
 static char slot_type_char[] = {
@@ -618,13 +637,10 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
 }
 
 /* release function corresponding to acquire_reference_state(). Idempotent. */
-static int __release_reference_state(struct bpf_func_state *state, int ptr_id)
+static int release_reference_state(struct bpf_func_state *state, int ptr_id)
 {
 	int i, last_idx;
 
-	if (!ptr_id)
-		return -EFAULT;
-
 	last_idx = state->acquired_refs - 1;
 	for (i = 0; i < state->acquired_refs; i++) {
 		if (state->refs[i].id == ptr_id) {
@@ -636,21 +652,7 @@ static int __release_reference_state(struct bpf_func_state *state, int ptr_id)
 			return 0;
 		}
 	}
-	return -EFAULT;
-}
-
-/* variation on the above for cases where we expect that there must be an
- * outstanding reference for the specified ptr_id.
- */
-static int release_reference_state(struct bpf_verifier_env *env, int ptr_id)
-{
-	struct bpf_func_state *state = cur_func(env);
-	int err;
-
-	err = __release_reference_state(state, ptr_id);
-	if (WARN_ON_ONCE(err != 0))
-		verbose(env, "verifier internal error: can't release reference\n");
-	return err;
+	return -EINVAL;
 }
 
 static int transfer_reference_state(struct bpf_func_state *dst,
@@ -1209,6 +1211,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type)
 	case CONST_PTR_TO_MAP:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
+	case PTR_TO_SOCK_COMMON:
+	case PTR_TO_SOCK_COMMON_OR_NULL:
+	case PTR_TO_TCP_SOCK:
+	case PTR_TO_TCP_SOCK_OR_NULL:
 		return true;
 	default:
 		return false;
@@ -1640,12 +1646,14 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
 	return 0;
 }
 
-static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
-			     int size, enum bpf_access_type t)
+static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
+			     u32 regno, int off, int size,
+			     enum bpf_access_type t)
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = &regs[regno];
-	struct bpf_insn_access_aux info;
+	struct bpf_insn_access_aux info = {};
+	bool valid;
 
 	if (reg->smin_value < 0) {
 		verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
@@ -1653,13 +1661,31 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
 		return -EACCES;
 	}
 
-	if (!bpf_sock_is_valid_access(off, size, t, &info)) {
-		verbose(env, "invalid bpf_sock access off=%d size=%d\n",
-			off, size);
-		return -EACCES;
+	switch (reg->type) {
+	case PTR_TO_SOCK_COMMON:
+		valid = bpf_sock_common_is_valid_access(off, size, t, &info);
+		break;
+	case PTR_TO_SOCKET:
+		valid = bpf_sock_is_valid_access(off, size, t, &info);
+		break;
+	case PTR_TO_TCP_SOCK:
+		valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
+		break;
+	default:
+		valid = false;
 	}
 
-	return 0;
+
+	if (valid) {
+		env->insn_aux_data[insn_idx].ctx_field_size =
+			info.ctx_field_size;
+		return 0;
+	}
+
+	verbose(env, "R%d invalid %s access off=%d size=%d\n",
+		regno, reg_type_str[reg->type], off, size);
+
+	return -EACCES;
 }
 
 static bool __is_pointer_value(bool allow_ptr_leaks,
@@ -1685,8 +1711,14 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
 {
 	const struct bpf_reg_state *reg = reg_state(env, regno);
 
-	return reg->type == PTR_TO_CTX ||
-	       reg->type == PTR_TO_SOCKET;
+	return reg->type == PTR_TO_CTX;
+}
+
+static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = reg_state(env, regno);
+
+	return type_is_sk_pointer(reg->type);
 }
 
 static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
@@ -1797,6 +1829,12 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 	case PTR_TO_SOCKET:
 		pointer_desc = "sock ";
 		break;
+	case PTR_TO_SOCK_COMMON:
+		pointer_desc = "sock_common ";
+		break;
+	case PTR_TO_TCP_SOCK:
+		pointer_desc = "tcp_sock ";
+		break;
 	default:
 		break;
 	}
@@ -2000,11 +2038,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			 * PTR_TO_PACKET[_META,_END]. In the latter
 			 * case, we know the offset is zero.
 			 */
-			if (reg_type == SCALAR_VALUE)
+			if (reg_type == SCALAR_VALUE) {
 				mark_reg_unknown(env, regs, value_regno);
-			else
+			} else {
 				mark_reg_known_zero(env, regs,
 						    value_regno);
+				if (reg_type_may_be_null(reg_type))
+					regs[value_regno].id = ++env->id_gen;
+			}
 			regs[value_regno].type = reg_type;
 		}
 
@@ -2050,12 +2091,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		err = check_flow_keys_access(env, off, size);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
-	} else if (reg->type == PTR_TO_SOCKET) {
+	} else if (type_is_sk_pointer(reg->type)) {
 		if (t == BPF_WRITE) {
-			verbose(env, "cannot write into socket\n");
+			verbose(env, "R%d cannot write into %s\n",
+				regno, reg_type_str[reg->type]);
 			return -EACCES;
 		}
-		err = check_sock_access(env, regno, off, size, t);
+		err = check_sock_access(env, insn_idx, regno, off, size, t);
 		if (!err && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
 	} else {
@@ -2099,7 +2141,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg) ||
-	    is_flow_key_reg(env, insn->dst_reg)) {
+	    is_flow_key_reg(env, insn->dst_reg) ||
+	    is_sk_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
 			insn->dst_reg,
 			reg_type_str[reg_state(env, insn->dst_reg)->type]);
@@ -2366,6 +2409,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		err = check_ctx_reg(env, reg, regno);
 		if (err < 0)
 			return err;
+	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
+		expected_type = PTR_TO_SOCK_COMMON;
+		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
+		if (!type_is_sk_pointer(type))
+			goto err_type;
 	} else if (arg_type == ARG_PTR_TO_SOCKET) {
 		expected_type = PTR_TO_SOCKET;
 		if (type != expected_type)
@@ -2780,7 +2828,7 @@ static int release_reference(struct bpf_verifier_env *env,
 	for (i = 0; i <= vstate->curframe; i++)
 		release_reg_references(env, vstate->frame[i], meta->ptr_id);
 
-	return release_reference_state(env, meta->ptr_id);
+	return release_reference_state(cur_func(env), meta->ptr_id);
 }
 
 static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
@@ -3046,8 +3094,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		}
 	} else if (is_release_function(func_id)) {
 		err = release_reference(env, &meta);
-		if (err)
+		if (err) {
+			verbose(env, "func %s#%d reference has not been acquired before\n",
+				func_id_name(func_id), func_id);
 			return err;
+		}
 	}
 
 	regs = cur_regs(env);
@@ -3096,12 +3147,23 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 			regs[BPF_REG_0].id = ++env->id_gen;
 		}
 	} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
-		int id = acquire_reference_state(env, insn_idx);
-		if (id < 0)
-			return id;
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
-		regs[BPF_REG_0].id = id;
+		if (is_acquire_function(func_id)) {
+			int id = acquire_reference_state(env, insn_idx);
+
+			if (id < 0)
+				return id;
+			/* For release_reference() */
+			regs[BPF_REG_0].id = id;
+		} else {
+			/* For mark_ptr_or_null_reg() */
+			regs[BPF_REG_0].id = ++env->id_gen;
+		}
+	} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else {
 		verbose(env, "unknown return type %d of func %s#%d\n",
 			fn->ret_type, func_id_name(func_id), func_id);
@@ -3361,6 +3423,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
 	case PTR_TO_PACKET_END:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
+	case PTR_TO_SOCK_COMMON:
+	case PTR_TO_SOCK_COMMON_OR_NULL:
+	case PTR_TO_TCP_SOCK:
+	case PTR_TO_TCP_SOCK_OR_NULL:
 		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
 			dst, reg_type_str[ptr_reg->type]);
 		return -EACCES;
@@ -4594,6 +4660,10 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 			}
 		} else if (reg->type == PTR_TO_SOCKET_OR_NULL) {
 			reg->type = PTR_TO_SOCKET;
+		} else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) {
+			reg->type = PTR_TO_SOCK_COMMON;
+		} else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
+			reg->type = PTR_TO_TCP_SOCK;
 		}
 		if (is_null || !(reg_is_refcounted(reg) ||
 				 reg_may_point_to_spin_lock(reg))) {
@@ -4618,7 +4688,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 	int i, j;
 
 	if (reg_is_refcounted_or_null(&regs[regno]) && is_null)
-		__release_reference_state(state, id);
+		release_reference_state(state, id);
 
 	for (i = 0; i < MAX_BPF_REG; i++)
 		mark_ptr_or_null_reg(state, &regs[i], id, is_null);
@@ -5787,6 +5857,10 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
 	case PTR_TO_FLOW_KEYS:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
+	case PTR_TO_SOCK_COMMON:
+	case PTR_TO_SOCK_COMMON_OR_NULL:
+	case PTR_TO_TCP_SOCK:
+	case PTR_TO_TCP_SOCK_OR_NULL:
 		/* Only valid matches are exact, which memcmp() above
 		 * would have accepted
 		 */
@@ -6107,6 +6181,10 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type)
 	case PTR_TO_CTX:
 	case PTR_TO_SOCKET:
 	case PTR_TO_SOCKET_OR_NULL:
+	case PTR_TO_SOCK_COMMON:
+	case PTR_TO_SOCK_COMMON_OR_NULL:
+	case PTR_TO_TCP_SOCK:
+	case PTR_TO_TCP_SOCK_OR_NULL:
 		return false;
 	default:
 		return true;
@@ -7109,8 +7187,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 			convert_ctx_access = ops->convert_ctx_access;
 			break;
 		case PTR_TO_SOCKET:
+		case PTR_TO_SOCK_COMMON:
 			convert_ctx_access = bpf_sock_convert_ctx_access;
 			break;
+		case PTR_TO_TCP_SOCK:
+			convert_ctx_access = bpf_tcp_sock_convert_ctx_access;
+			break;
 		default:
 			continue;
 		}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 91d5c38eb7e5..d1c6d152da89 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { }
 
 #ifdef CONFIG_HOTPLUG_SMT
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
-EXPORT_SYMBOL_GPL(cpu_smt_control);
-
-static bool cpu_smt_available __read_mostly;
 
 void __init cpu_smt_disable(bool force)
 {
@@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force)
 
 /*
  * The decision whether SMT is supported can only be done after the full
- * CPU identification. Called from architecture code before non boot CPUs
- * are brought up.
- */
-void __init cpu_smt_check_topology_early(void)
-{
-	if (!topology_smt_supported())
-		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
-}
-
-/*
- * If SMT was disabled by BIOS, detect it here, after the CPUs have been
- * brought online. This ensures the smt/l1tf sysfs entries are consistent
- * with reality. cpu_smt_available is set to true during the bringup of non
- * boot CPUs when a SMT sibling is detected. Note, this may overwrite
- * cpu_smt_control's previous setting.
+ * CPU identification. Called from architecture code.
  */
 void __init cpu_smt_check_topology(void)
 {
-	if (!cpu_smt_available)
+	if (!topology_smt_supported())
 		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
 }
 
@@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable);
 
 static inline bool cpu_smt_allowed(unsigned int cpu)
 {
-	if (topology_is_primary_thread(cpu))
+	if (cpu_smt_control == CPU_SMT_ENABLED)
 		return true;
 
-	/*
-	 * If the CPU is not a 'primary' thread and the booted_once bit is
-	 * set then the processor has SMT support. Store this information
-	 * for the late check of SMT support in cpu_smt_check_topology().
-	 */
-	if (per_cpu(cpuhp_state, cpu).booted_once)
-		cpu_smt_available = true;
-
-	if (cpu_smt_control == CPU_SMT_ENABLED)
+	if (topology_is_primary_thread(cpu))
 		return true;
 
 	/*
@@ -2090,10 +2065,8 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
 		 */
 		cpuhp_offline_cpu_device(cpu);
 	}
-	if (!ret) {
+	if (!ret)
 		cpu_smt_control = ctrlval;
-		arch_smt_update();
-	}
 	cpu_maps_update_done();
 	return ret;
 }
@@ -2104,7 +2077,6 @@ static int cpuhp_smt_enable(void)
 
 	cpu_maps_update_begin();
 	cpu_smt_control = CPU_SMT_ENABLED;
-	arch_smt_update();
 	for_each_present_cpu(cpu) {
 		/* Skip online CPUs and CPUs on offline nodes */
 		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3cd13a30f732..26d6edab051a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
-	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-
-	if (ret || !write)
-		return ret;
-
+	int ret;
+	int perf_cpu = sysctl_perf_cpu_time_max_percent;
 	/*
 	 * If throttling is disabled don't allow the write:
 	 */
-	if (sysctl_perf_cpu_time_max_percent == 100 ||
-	    sysctl_perf_cpu_time_max_percent == 0)
+	if (write && (perf_cpu == 100 || perf_cpu == 0))
 		return -EINVAL;
 
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (ret || !write)
+		return ret;
+
 	max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ);
 	perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 	update_perf_cpu_limits();
@@ -4963,6 +4963,11 @@ static void __perf_event_period(struct perf_event *event,
 	}
 }
 
+static int perf_event_check_period(struct perf_event *event, u64 value)
+{
+	return event->pmu->check_period(event, value);
+}
+
 static int perf_event_period(struct perf_event *event, u64 __user *arg)
 {
 	u64 value;
@@ -4979,6 +4984,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
 	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
 		return -EINVAL;
 
+	if (perf_event_check_period(event, value))
+		return -EINVAL;
+
 	event_function_call(event, __perf_event_period, &value);
 
 	return 0;
@@ -9391,6 +9399,11 @@ static int perf_pmu_nop_int(struct pmu *pmu)
 	return 0;
 }
 
+static int perf_event_nop_int(struct perf_event *event, u64 value)
+{
+	return 0;
+}
+
 static DEFINE_PER_CPU(unsigned int, nop_txn_flags);
 
 static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags)
@@ -9691,6 +9704,9 @@ got_cpu_context:
 		pmu->pmu_disable = perf_pmu_nop_void;
 	}
 
+	if (!pmu->check_period)
+		pmu->check_period = perf_event_nop_int;
+
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 4a9937076331..5ab4fe3b1dcc 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	size = sizeof(struct ring_buffer);
 	size += nr_pages * sizeof(void *);
 
+	if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER)
+		goto fail;
+
 	rb = kzalloc(size, GFP_KERNEL);
 	if (!rb)
 		goto fail;
diff --git a/kernel/exit.c b/kernel/exit.c
index 3fb7be001964..2639a30a8aa5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p)
 	return NULL;
 }
 
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+						struct list_head *dead)
 	__releases(&tasklist_lock)
 	__acquires(&tasklist_lock)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(father);
 	struct task_struct *reaper = pid_ns->child_reaper;
+	struct task_struct *p, *n;
 
 	if (likely(reaper != father))
 		return reaper;
@@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father)
 		panic("Attempted to kill init! exitcode=0x%08x\n",
 			father->signal->group_exit_code ?: father->exit_code);
 	}
+
+	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+
 	zap_pid_ns_processes(pid_ns);
 	write_lock_irq(&tasklist_lock);
 
@@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father,
 		exit_ptrace(father, dead);
 
 	/* Can drop and reacquire tasklist_lock */
-	reaper = find_child_reaper(father);
+	reaper = find_child_reaper(father, dead);
 	if (list_empty(&father->children))
 		return;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index fdd312da0992..a0514e01c3eb 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2221,11 +2221,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 	 * decrement the counter at queue_unlock() when some error has
 	 * occurred and we don't end up adding the task to the list.
 	 */
-	hb_waiters_inc(hb);
+	hb_waiters_inc(hb); /* implies smp_mb(); (A) */
 
 	q->lock_ptr = &hb->lock;
 
-	spin_lock(&hb->lock); /* implies smp_mb(); (A) */
+	spin_lock(&hb->lock);
 	return hb;
 }
 
@@ -2861,35 +2861,39 @@ retry_private:
 	 * and BUG when futex_unlock_pi() interleaves with this.
 	 *
 	 * Therefore acquire wait_lock while holding hb->lock, but drop the
-	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
-	 * serializes against futex_unlock_pi() as that does the exact same
-	 * lock handoff sequence.
+	 * latter before calling __rt_mutex_start_proxy_lock(). This
+	 * interleaves with futex_unlock_pi() -- which does a similar lock
+	 * handoff -- such that the latter can observe the futex_q::pi_state
+	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
 	spin_unlock(q.lock_ptr);
+	/*
+	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
+	 * such that futex_unlock_pi() is guaranteed to observe the waiter when
+	 * it sees the futex_q::pi_state.
+	 */
 	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
 	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
 
 	if (ret) {
 		if (ret == 1)
 			ret = 0;
-
-		spin_lock(q.lock_ptr);
-		goto no_block;
+		goto cleanup;
 	}
 
-
 	if (unlikely(to))
 		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
 
 	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
 
+cleanup:
 	spin_lock(q.lock_ptr);
 	/*
-	 * If we failed to acquire the lock (signal/timeout), we must
+	 * If we failed to acquire the lock (deadlock/signal/timeout), we must
 	 * first acquire the hb->lock before removing the lock from the
-	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
-	 * wait lists consistent.
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait
+	 * lists consistent.
 	 *
 	 * In particular; it is important that futex_unlock_pi() can not
 	 * observe this inconsistency.
@@ -3013,6 +3017,10 @@ retry:
 		 * there is no point where we hold neither; and therefore
 		 * wake_futex_pi() must observe a state consistent with what we
 		 * observed.
+		 *
+		 * In particular; this forces __rt_mutex_start_proxy() to
+		 * complete such that we're guaranteed to observe the
+		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 581edcc63c26..978d63a8261c 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1726,12 +1726,33 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 	rt_mutex_set_owner(lock, NULL);
 }
 
+/**
+ * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: does _NOT_ remove the @waiter on failure; must either call
+ * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this.
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for PI-futex support.
+ */
 int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
+	lockdep_assert_held(&lock->wait_lock);
+
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 
@@ -1749,9 +1770,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		ret = 0;
 	}
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
@@ -1763,12 +1781,18 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
  *
+ * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock
+ * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that.
+ *
+ * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter
+ * on failure.
+ *
  * Returns:
  *  0 - task blocked on lock
  *  1 - acquired the lock for task, caller should wake it up
  * <0 - error
  *
- * Special API call for FUTEX_REQUEUE_PI support.
+ * Special API call for PI-futex support.
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
@@ -1778,6 +1802,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 
 	raw_spin_lock_irq(&lock->wait_lock);
 	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	if (unlikely(ret))
+		remove_waiter(lock, waiter);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
@@ -1845,7 +1871,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
  * @lock:		the rt_mutex we were woken on
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or
+ * rt_mutex_wait_proxy_lock().
  *
  * Unless we acquired the lock; we're still enqueued on the wait-list and can
  * in fact still be granted ownership until we're removed. Therefore we can
diff --git a/kernel/relay.c b/kernel/relay.c
index 04f248644e06..9e0f52375487 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan,
 	dentry = chan->cb->create_buf_file(tmpname, chan->parent,
 					   S_IRUSR, buf,
 					   &chan->is_global);
+	if (IS_ERR(dentry))
+		dentry = NULL;
 
 	kfree(tmpname);
 
@@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 		dentry = chan->cb->create_buf_file(NULL, NULL,
 						   S_IRUSR, buf,
 						   &chan->is_global);
-		if (WARN_ON(dentry))
+		if (IS_ERR_OR_NULL(dentry))
 			goto free_buf;
 	}
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 50aa2aba69bd..310d0637fe4b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 
 #ifdef CONFIG_SCHED_SMT
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index fe24de3fbc93..c3484785b179 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -124,6 +124,7 @@
  * sampling of the aggregate task states would be.
  */
 
+#include "../workqueue_internal.h"
 #include <linux/sched/loadavg.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
@@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 			groupc->tasks[t]++;
 
 	write_seqcount_end(&groupc->seq);
-
-	if (!delayed_work_pending(&group->clock_work))
-		schedule_delayed_work(&group->clock_work, PSI_FREQ);
 }
 
 static struct psi_group *iterate_groups(struct task_struct *task, void **iter)
@@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
 	struct psi_group *group;
+	bool wake_clock = true;
 	void *iter = NULL;
 
 	if (!task->pid)
@@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set)
 	task->psi_flags &= ~clear;
 	task->psi_flags |= set;
 
-	while ((group = iterate_groups(task, &iter)))
+	/*
+	 * Periodic aggregation shuts off if there is a period of no
+	 * task changes, so we wake it back up if necessary. However,
+	 * don't do this if the task change is the aggregation worker
+	 * itself going to sleep, or we'll ping-pong forever.
+	 */
+	if (unlikely((clear & TSK_RUNNING) &&
+		     (task->flags & PF_WQ_WORKER) &&
+		     wq_worker_last_func(task) == psi_update_work))
+		wake_clock = false;
+
+	while ((group = iterate_groups(task, &iter))) {
 		psi_group_change(group, cpu, clear, set);
+		if (wake_clock && !delayed_work_pending(&group->clock_work))
+			schedule_delayed_work(&group->clock_work, PSI_FREQ);
+	}
 }
 
 void psi_memstall_tick(struct task_struct *task, int cpu)
diff --git a/kernel/signal.c b/kernel/signal.c
index e1d7ad8e6ab1..57b7771e20d7 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in
 }
 EXPORT_SYMBOL_GPL(dequeue_signal);
 
+static int dequeue_synchronous_signal(kernel_siginfo_t *info)
+{
+	struct task_struct *tsk = current;
+	struct sigpending *pending = &tsk->pending;
+	struct sigqueue *q, *sync = NULL;
+
+	/*
+	 * Might a synchronous signal be in the queue?
+	 */
+	if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK))
+		return 0;
+
+	/*
+	 * Return the first synchronous signal in the queue.
+	 */
+	list_for_each_entry(q, &pending->list, list) {
+		/* Synchronous signals have a postive si_code */
+		if ((q->info.si_code > SI_USER) &&
+		    (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) {
+			sync = q;
+			goto next;
+		}
+	}
+	return 0;
+next:
+	/*
+	 * Check if there is another siginfo for the same signal.
+	 */
+	list_for_each_entry_continue(q, &pending->list, list) {
+		if (q->info.si_signo == sync->info.si_signo)
+			goto still_pending;
+	}
+
+	sigdelset(&pending->signal, sync->info.si_signo);
+	recalc_sigpending();
+still_pending:
+	list_del_init(&sync->list);
+	copy_siginfo(info, &sync->info);
+	__sigqueue_free(sync);
+	return info->si_signo;
+}
+
 /*
  * Tell a process that it has a new active signal..
  *
@@ -1057,10 +1099,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 
 	result = TRACE_SIGNAL_DELIVERED;
 	/*
-	 * Skip useless siginfo allocation for SIGKILL SIGSTOP,
-	 * and kernel threads.
+	 * Skip useless siginfo allocation for SIGKILL and kernel threads.
 	 */
-	if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD))
+	if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
 		goto out_set;
 
 	/*
@@ -2394,6 +2435,14 @@ relock:
 		goto relock;
 	}
 
+	/* Has this task already been marked for death? */
+	if (signal_group_exit(signal)) {
+		ksig->info.si_signo = signr = SIGKILL;
+		sigdelset(&current->pending.signal, SIGKILL);
+		recalc_sigpending();
+		goto fatal;
+	}
+
 	for (;;) {
 		struct k_sigaction *ka;
 
@@ -2407,7 +2456,15 @@ relock:
 			goto relock;
 		}
 
-		signr = dequeue_signal(current, &current->blocked, &ksig->info);
+		/*
+		 * Signals generated by the execution of an instruction
+		 * need to be delivered before any other pending signals
+		 * so that the instruction pointer in the signal stack
+		 * frame points to the faulting instruction.
+		 */
+		signr = dequeue_synchronous_signal(&ksig->info);
+		if (!signr)
+			signr = dequeue_signal(current, &current->blocked, &ksig->info);
 
 		if (!signr)
 			break; /* will return 0 */
@@ -2489,6 +2546,7 @@ relock:
 			continue;
 		}
 
+	fatal:
 		spin_unlock_irq(&sighand->siglock);
 
 		/*
diff --git a/kernel/smp.c b/kernel/smp.c
index 163c451af42e..f4cf1b0bb3b8 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,8 +584,6 @@ void __init smp_init(void)
 		num_nodes, (num_nodes > 1 ? "s" : ""),
 		num_cpus,  (num_cpus  > 1 ? "s" : ""));
 
-	/* Final decision about SMT support */
-	cpu_smt_check_topology();
 	/* Any cleanup work */
 	smp_cpus_done(setup_max_cpus);
 }
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 8b068adb9da1..f1a86a0d881d 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1204,22 +1204,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *
 
 int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 {
-	int err;
-
-	mutex_lock(&bpf_event_mutex);
-	err = __bpf_probe_register(btp, prog);
-	mutex_unlock(&bpf_event_mutex);
-	return err;
+	return __bpf_probe_register(btp, prog);
 }
 
 int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog)
 {
-	int err;
-
-	mutex_lock(&bpf_event_mutex);
-	err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
-	mutex_unlock(&bpf_event_mutex);
-	return err;
+	return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog);
 }
 
 int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c521b7347482..c4238b441624 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3384,6 +3384,8 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 	const char tgid_space[] = "          ";
 	const char space[] = "  ";
 
+	print_event_info(buf, m);
+
 	seq_printf(m, "#                          %s  _-----=> irqs-off\n",
 		   tgid ? tgid_space : space);
 	seq_printf(m, "#                          %s / _----=> need-resched\n",
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d5fb09ebba8b..9eaf07f99212 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -861,22 +861,14 @@ static const struct file_operations kprobe_profile_ops = {
 static nokprobe_inline int
 fetch_store_strlen(unsigned long addr)
 {
-	mm_segment_t old_fs;
 	int ret, len = 0;
 	u8 c;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	pagefault_disable();
-
 	do {
-		ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1);
+		ret = probe_mem_read(&c, (u8 *)addr + len, 1);
 		len++;
 	} while (c && ret == 0 && len < MAX_STRING_SIZE);
 
-	pagefault_enable();
-	set_fs(old_fs);
-
 	return (ret < 0) ? ret : len;
 }
 
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 5c56afc17cf8..4737bb8c07a3 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs,
 		if (unlikely(arg->dynamic))
 			*dl = make_data_loc(maxlen, dyndata - base);
 		ret = process_fetch_insn(arg->code, regs, dl, base);
-		if (unlikely(ret < 0 && arg->dynamic))
+		if (unlikely(ret < 0 && arg->dynamic)) {
 			*dl = make_data_loc(0, dyndata - base);
-		else
+		} else {
 			dyndata += ret;
+			maxlen -= ret;
+		}
 	}
 }
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index e335576b9411..9bde07c06362 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -5,7 +5,7 @@
  * Copyright (C) IBM Corporation, 2010-2012
  * Author:	Srikar Dronamraju <srikar@linux.vnet.ibm.com>
  */
-#define pr_fmt(fmt)	"trace_kprobe: " fmt
+#define pr_fmt(fmt)	"trace_uprobe: " fmt
 
 #include <linux/ctype.h>
 #include <linux/module.h>
@@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base)
 	if (ret >= 0) {
 		if (ret == maxlen)
 			dst[ret - 1] = '\0';
+		else
+			/*
+			 * Include the terminating null byte. In this case it
+			 * was copied by strncpy_from_user but not accounted
+			 * for in ret.
+			 */
+			ret++;
 		*(u32 *)dest = make_data_loc(ret, (void *)dst - base);
 	}
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 392be4b252f6..fc5d23d752a5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -910,6 +910,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 }
 
 /**
+ * wq_worker_last_func - retrieve worker's last work function
+ *
+ * Determine the last function a worker executed. This is called from
+ * the scheduler to get a worker's last known identity.
+ *
+ * CONTEXT:
+ * spin_lock_irq(rq->lock)
+ *
+ * Return:
+ * The last work function %current executed as a worker, NULL if it
+ * hasn't executed any work yet.
+ */
+work_func_t wq_worker_last_func(struct task_struct *task)
+{
+	struct worker *worker = kthread_data(task);
+
+	return worker->last_func;
+}
+
+/**
  * worker_set_flags - set worker flags and adjust nr_running accordingly
  * @worker: self
  * @flags: flags to set
@@ -2184,6 +2204,9 @@ __acquires(&pool->lock)
 	if (unlikely(cpu_intensive))
 		worker_clr_flags(worker, WORKER_CPU_INTENSIVE);
 
+	/* tag the worker for identification in schedule() */
+	worker->last_func = worker->current_func;
+
 	/* we're done with it, release */
 	hash_del(&worker->hentry);
 	worker->current_work = NULL;
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index 66fbb5a9e633..cb68b03ca89a 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -53,6 +53,9 @@ struct worker {
 
 	/* used only by rescuers to point to the target workqueue */
 	struct workqueue_struct	*rescue_wq;	/* I: the workqueue to rescue */
+
+	/* used by the scheduler to determine a worker's last known identity */
+	work_func_t		last_func;
 };
 
 /**
@@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void)
 
 /*
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
- * sched/core.c and workqueue.c.
+ * sched/ and workqueue.c.
  */
 void wq_worker_waking_up(struct task_struct *task, int cpu);
 struct task_struct *wq_worker_sleeping(struct task_struct *task);
+work_func_t wq_worker_last_func(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */