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/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

arch/arm64/net/bpf_jit_comp.c

@@ -1136,6 +1136,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	return prog;
 }
 
+u64 bpf_jit_alloc_exec_limit(void)
+{
+	return BPF_JIT_REGION_SIZE;
+}
+
 void *bpf_jit_alloc_exec(unsigned long size)
 {
 	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,

arch/riscv/net/bpf_jit_core.c

@@ -166,6 +166,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	return prog;
 }
 
+u64 bpf_jit_alloc_exec_limit(void)
+{
+	return BPF_JIT_REGION_SIZE;
+}
+
 void *bpf_jit_alloc_exec(unsigned long size)
 {
 	return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,

include/linux/bpf.h

@@ -929,8 +929,11 @@ struct bpf_array_aux {
 	 * stored in the map to make sure that all callers and callees have
 	 * the same prog type and JITed flag.
 	 */
-	enum bpf_prog_type type;
-	bool jited;
+	struct {
+		spinlock_t lock;
+		enum bpf_prog_type type;
+		bool jited;
+	} owner;
 	/* Programs with direct jumps into programs part of this array. */
 	struct list_head poke_progs;
 	struct bpf_map *map;

include/linux/bpf_types.h

@@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
-#ifdef CONFIG_NET
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 #ifdef CONFIG_BPF_LSM
 BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
+#ifdef CONFIG_NET
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
 BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)

include/linux/filter.h

@@ -1051,6 +1051,7 @@ extern int bpf_jit_enable;
 extern int bpf_jit_harden;
 extern int bpf_jit_kallsyms;
 extern long bpf_jit_limit;
+extern long bpf_jit_limit_max;
 
 typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
 

include/linux/skmsg.h

@@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
 			     struct sk_msg *msg, u32 bytes);
 int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 		   int len, int flags);
+bool sk_msg_is_readable(struct sock *sk);
 
 static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
 {

include/net/sock.h

@@ -1208,7 +1208,7 @@ struct proto {
 #endif
 
 	bool			(*stream_memory_free)(const struct sock *sk, int wake);
-	bool			(*stream_memory_read)(const struct sock *sk);
+	bool			(*sock_is_readable)(struct sock *sk);
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
 	void			(*leave_memory_pressure)(struct sock *sk);
@@ -2820,4 +2820,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs);
 
 int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
 
+static inline bool sk_is_readable(struct sock *sk)
+{
+	if (sk->sk_prot->sock_is_readable)
+		return sk->sk_prot->sock_is_readable(sk);
+	return false;
+}
 #endif	/* _SOCK_H */

include/net/tls.h

@@ -375,7 +375,7 @@ void tls_sw_release_resources_rx(struct sock *sk);
 void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
-bool tls_sw_stream_read(const struct sock *sk);
+bool tls_sw_sock_is_readable(struct sock *sk);
 ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
 			   struct pipe_inode_info *pipe,
 			   size_t len, unsigned int flags);

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)