Merge branch 'linus' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <[email protected]>

kernel/bpf/btf.c

@@ -1459,7 +1459,8 @@ 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;
 		}

kernel/bpf/cgroup.c

@@ -572,7 +572,7 @@ 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;

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;
@@ -748,7 +748,7 @@ 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);

kernel/bpf/lpm_trie.c

@@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 	}
 
 	if (!node || node->prefixlen != key->prefixlen ||
+	    node->prefixlen != matchlen ||
 	    (node->flags & LPM_TREE_NODE_FLAG_IM)) {
 		ret = -ENOENT;
 		goto out;

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;
+}

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 *);

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_);
 	}
 }
 

kernel/bpf/syscall.c

@@ -713,8 +713,13 @@ 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);
@@ -744,7 +749,10 @@ 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;
 

kernel/bpf/verifier.c

@@ -1617,12 +1617,13 @@ 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 = {};
 
 	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",
@@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off,
 		return -EACCES;
 	}
 
+	env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+
 	return 0;
 }
 
@@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			verbose(env, "cannot write into socket\n");
 			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 {