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

Daniel Borkmann says:

====================
pull-request: bpf 2021-10-26

We've added 12 non-merge commits during the last 7 day(s) which contain
a total of 23 files changed, 118 insertions(+), 98 deletions(-).

The main changes are:

1) Fix potential race window in BPF tail call compatibility check, from Toke Høiland-Jørgensen.

2) Fix memory leak in cgroup fs due to missing cgroup_bpf_offline(), from Quanyang Wang.

3) Fix file descriptor reference counting in generic_map_update_batch(), from Xu Kuohai.

4) Fix bpf_jit_limit knob to the max supported limit by the arch's JIT, from Lorenz Bauer.

5) Fix BPF sockmap ->poll callbacks for UDP and AF_UNIX sockets, from Cong Wang and Yucong Sun.

6) Fix BPF sockmap concurrency issue in TCP on non-blocking sendmsg calls, from Liu Jian.

7) Fix build failure of INODE_STORAGE and TASK_STORAGE maps on !CONFIG_NET, from Tejun Heo.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Fix potential race in tail call compatibility check
  bpf: Move BPF_MAP_TYPE for INODE_STORAGE and TASK_STORAGE outside of CONFIG_NET
  selftests/bpf: Use recv_timeout() instead of retries
  net: Implement ->sock_is_readable() for UDP and AF_UNIX
  skmsg: Extract and reuse sk_msg_is_readable()
  net: Rename ->stream_memory_read to ->sock_is_readable
  tcp_bpf: Fix one concurrency problem in the tcp_bpf_send_verdict function
  cgroup: Fix memory leak caused by missing cgroup_bpf_offline
  bpf: Fix error usage of map_fd and fdget() in generic_map_update_batch()
  bpf: Prevent increasing bpf_jit_limit above max
  bpf: Define bpf_jit_alloc_exec_limit for arm64 JIT
  bpf: Define bpf_jit_alloc_exec_limit for riscv JIT
====================

Link: https://lore.kernel.org/r/20211026201920.11296-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

kernel/bpf/arraymap.c

@@ -1072,6 +1072,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
 	INIT_WORK(&aux->work, prog_array_map_clear_deferred);
 	INIT_LIST_HEAD(&aux->poke_progs);
 	mutex_init(&aux->poke_mutex);
+	spin_lock_init(&aux->owner.lock);
 
 	map = array_map_alloc(attr);
 	if (IS_ERR(map)) {

kernel/bpf/core.c

@@ -524,6 +524,7 @@ int bpf_jit_enable   __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
 int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
 int bpf_jit_harden   __read_mostly;
 long bpf_jit_limit   __read_mostly;
+long bpf_jit_limit_max __read_mostly;
 
 static void
 bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -817,7 +818,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void)
 static int __init bpf_jit_charge_init(void)
 {
 	/* Only used as heuristic here to derive limit. */
-	bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+	bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+	bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
 					    PAGE_SIZE), LONG_MAX);
 	return 0;
 }
@@ -1821,20 +1823,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 bool bpf_prog_array_compatible(struct bpf_array *array,
 			       const struct bpf_prog *fp)
 {
+	bool ret;
+
 	if (fp->kprobe_override)
 		return false;
 
-	if (!array->aux->type) {
+	spin_lock(&array->aux->owner.lock);
+
+	if (!array->aux->owner.type) {
 		/* There's no owner yet where we could check for
 		 * compatibility.
 		 */
-		array->aux->type  = fp->type;
-		array->aux->jited = fp->jited;
-		return true;
+		array->aux->owner.type  = fp->type;
+		array->aux->owner.jited = fp->jited;
+		ret = true;
+	} else {
+		ret = array->aux->owner.type  == fp->type &&
+		      array->aux->owner.jited == fp->jited;
 	}
-
-	return array->aux->type  == fp->type &&
-	       array->aux->jited == fp->jited;
+	spin_unlock(&array->aux->owner.lock);
+	return ret;
 }
 
 static int bpf_check_tail_call(const struct bpf_prog *fp)

kernel/bpf/syscall.c

@@ -543,8 +543,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 
 	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
 		array = container_of(map, struct bpf_array, map);
-		type  = array->aux->type;
-		jited = array->aux->jited;
+		spin_lock(&array->aux->owner.lock);
+		type  = array->aux->owner.type;
+		jited = array->aux->owner.jited;
+		spin_unlock(&array->aux->owner.lock);
 	}
 
 	seq_printf(m,
@@ -1337,12 +1339,11 @@ int generic_map_update_batch(struct bpf_map *map,
 	void __user *values = u64_to_user_ptr(attr->batch.values);
 	void __user *keys = u64_to_user_ptr(attr->batch.keys);
 	u32 value_size, cp, max_count;
-	int ufd = attr->map_fd;
+	int ufd = attr->batch.map_fd;
 	void *key, *value;
 	struct fd f;
 	int err = 0;
 
-	f = fdget(ufd);
 	if (attr->batch.elem_flags & ~BPF_F_LOCK)
 		return -EINVAL;
 
@@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map,
 		return -ENOMEM;
 	}
 
+	f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
 	for (cp = 0; cp < max_count; cp++) {
 		err = -EFAULT;
 		if (copy_from_user(key, keys + cp * map->key_size,
@@ -1386,6 +1388,7 @@ int generic_map_update_batch(struct bpf_map *map,
 
 	kvfree(value);
 	kvfree(key);
+	fdput(f);
 	return err;
 }
 

kernel/cgroup/cgroup.c

@@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb)
 	 * And don't kill the default root.
 	 */
 	if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
-	    !percpu_ref_is_dying(&root->cgrp.self.refcnt))
+	    !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+		cgroup_bpf_offline(&root->cgrp);
 		percpu_ref_kill(&root->cgrp.self.refcnt);
+	}
 	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }