Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2018-02-20

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) Fix a memory leak in LPM trie's map_free() callback function, where
the trie structure itself was not freed since initial implementation.
Also a synchronize_rcu() was needed in order to wait for outstanding
programs accessing the trie to complete, from Yonghong.

2) Fix sock_map_alloc()'s error path in order to correctly propagate
the -EINVAL error in case of too large allocation requests. This
was just recently introduced when fixing close hooks via ULP layer,
fix from Eric.

3) Do not use GFP_ATOMIC in __cpu_map_entry_alloc(). Reason is that this
will not work with the recent __ptr_ring_init_queue_alloc() conversion
to kvmalloc_array(), where in case of fallback to vmalloc() that GFP
flag is invalid, from Jason.

4) Fix two recent syzkaller warnings: i) fix bpf_prog_array_copy_to_user()
when a prog query with a big number of ids was performed where we'd
otherwise trigger a warning from allocator side, ii) fix a missing
mlock precharge on arraymaps, from Daniel.

5) Two fixes for bpftool in order to avoid breaking JSON output when used
in batch mode, from Quentin.

6) Move a pr_debug() in libbpf in order to avoid having an otherwise
uninitialized variable in bpf_program__reloc_text(), from Jeremy.
====================

Signed-off-by: David S. Miller <[e-mail]>

kernel/bpf/arraymap.c

···
 static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
-	int numa_node = bpf_map_attr_numa_node(attr);
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
 	u32 elem_size, index_mask, max_entries;
 	bool unpriv = !capable(CAP_SYS_ADMIN);
+	u64 cost, array_size, mask64;
 	struct bpf_array *array;
-	u64 array_size, mask64;
 
 	elem_size = round_up(attr->value_size, 8);
 
···
 		array_size += (u64) max_entries * elem_size;
 
 	/* make sure there is no u32 overflow later in round_up() */
-	if (array_size >= U32_MAX - PAGE_SIZE)
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
+	if (percpu) {
+		cost += (u64)attr->max_entries * elem_size * num_possible_cpus();
+		if (cost >= U32_MAX - PAGE_SIZE)
+			return ERR_PTR(-ENOMEM);
+	}
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
 
 	/* allocate all map elements and zero-initialize them */
 	array = bpf_map_area_alloc(array_size, numa_node);
···
 
 	/* copy mandatory map attributes */
 	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
 	array->elem_size = elem_size;
 
-	if (!percpu)
-		goto out;
-
-	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
-
-	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    bpf_array_alloc_percpu(array)) {
+	if (percpu && bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
-out:
-	array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
 
 	return &array->map;
 }

kernel/bpf/core.c

···
 	 * so always copy 'cnt' prog_ids to the user.
 	 * In a rare race the user will see zero prog_ids
 	 */
-	ids = kcalloc(cnt, sizeof(u32), GFP_USER);
+	ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN);
 	if (!ids)
 		return -ENOMEM;
 	rcu_read_lock();

kernel/bpf/cpumap.c

···
 static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu,
 						       int map_id)
 {
-	gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
 	struct bpf_cpu_map_entry *rcpu;
 	int numa, err;
 

kernel/bpf/lpm_trie.c

···
 	struct lpm_trie_node __rcu **slot;
 	struct lpm_trie_node *node;
 
-	raw_spin_lock(&trie->lock);
+	/* Wait for outstanding programs to complete
+	 * update/lookup/delete/get_next_key and free the trie.
+	 */
+	synchronize_rcu();
 
 	/* Always start at the root and walk down to a node that has no
 	 * children. Then free that node, nullify its reference in the parent
···
 			node = rcu_dereference_protected(*slot,
 					lockdep_is_held(&trie->lock));
 			if (!node)
-				goto unlock;
+				goto out;
 
 			if (rcu_access_pointer(node->child[0])) {
 				slot = &node->child[0];
···
 		}
 	}
 
-unlock:
-	raw_spin_unlock(&trie->lock);
+out:
+	kfree(trie);
 }
 
 static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)

kernel/bpf/sockmap.c

···
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
-	int err = -EINVAL;
 	u64 cost;
+	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
···
 
 	/* make sure page count doesn't overflow */
 	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
+	err = -EINVAL;
 	if (cost >= U32_MAX - PAGE_SIZE)
 		goto free_stab;
 

kernel/trace/bpf_trace.c

···
 		return -EINVAL;
 	if (copy_from_user(&query, uquery, sizeof(query)))
 		return -EFAULT;
+	if (query.ids_len > BPF_TRACE_MAX_PROGS)
+		return -E2BIG;
 
 	mutex_lock(&bpf_event_mutex);
 	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,

tools/bpf/bpftool/main.c

···
 	}
 
 	if (errno && errno != ENOENT) {
-		perror("reading batch file failed");
+		p_err("reading batch file failed: %s", strerror(errno));
 		err = -1;
 	} else {
 		p_info("processed %d lines", lines);

tools/bpf/bpftool/prog.c

···
 			      n < 0 ? strerror(errno) : "short write");
 			goto err_free;
 		}
+
+		if (json_output)
+			jsonw_null(json_wtr);
 	} else {
 		if (member_len == &info.jited_prog_len) {
 			const char *name = NULL;

tools/lib/bpf/libbpf.c

···
 		prog->insns = new_insn;
 		prog->main_prog_cnt = prog->insns_cnt;
 		prog->insns_cnt = new_cnt;
+		pr_debug("added %zd insn from %s to prog %s\n",
+			 text->insns_cnt, text->section_name,
+			 prog->section_name);
 	}
 	insn = &prog->insns[relo->insn_idx];
 	insn->imm += prog->main_prog_cnt - relo->insn_idx;
-	pr_debug("added %zd insn from %s to prog %s\n",
-		 text->insns_cnt, text->section_name, prog->section_name);
 	return 0;
 }