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/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

arch/arm64/net/bpf_jit_comp.c

···
 	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

···
 	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

···
 	 * 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

···
 #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

···
 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

···
 			     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

···
 #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);
···
 
 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

···
 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

···
 	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

···
 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)
···
 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;
 }
···
 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

···
 
 	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,
···
 	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;
 
···
 		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,
···
 
 	kvfree(value);
 	kvfree(key);
+	fdput(f);
 	return err;
 }
 

kernel/cgroup/cgroup.c

···
 	 * 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);
 }

net/core/skmsg.c

···
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
 
+bool sk_msg_is_readable(struct sock *sk)
+{
+	struct sk_psock *psock;
+	bool empty = true;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (likely(psock))
+		empty = list_empty(&psock->ingress_msg);
+	rcu_read_unlock();
+	return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
 static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 						  struct sk_buff *skb)
 {

net/core/sysctl_net_core.c

···
 		.mode		= 0600,
 		.proc_handler	= proc_dolongvec_minmax_bpf_restricted,
 		.extra1		= &long_one,
-		.extra2		= &long_max,
+		.extra2		= &bpf_jit_limit_max,
 	},
 #endif
 	{

net/ipv4/tcp.c

···
 {
 	if (tcp_epollin_ready(sk, target))
 		return true;
-
-	if (sk->sk_prot->stream_memory_read)
-		return sk->sk_prot->stream_memory_read(sk);
-	return false;
+	return sk_is_readable(sk);
 }
 
 /*

net/ipv4/tcp_bpf.c

···
 EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 
 #ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
-	struct sk_psock *psock;
-	bool empty = true;
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (likely(psock))
-		empty = list_empty(&psock->ingress_msg);
-	rcu_read_unlock();
-	return !empty;
-}
-
 static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 			     long timeo)
 {
···
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
+	u32 eval = __SK_NONE;
 	int ret;
 
 more_data:
···
 	case __SK_REDIRECT:
 		sk_redir = psock->sk_redir;
 		sk_msg_apply_bytes(psock, tosend);
+		if (!psock->apply_bytes) {
+			/* Clean up before releasing the sock lock. */
+			eval = psock->eval;
+			psock->eval = __SK_NONE;
+			psock->sk_redir = NULL;
+		}
 		if (psock->cork) {
 			cork = true;
 			psock->cork = NULL;
 		}
 		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
+
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+		if (eval == __SK_REDIRECT)
+			sock_put(sk_redir);
+
 		lock_sock(sk);
 		if (unlikely(ret < 0)) {
 			int free = sk_msg_free_nocharge(sk, msg);
···
 	prot[TCP_BPF_BASE].unhash		= sock_map_unhash;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
-	prot[TCP_BPF_BASE].stream_memory_read	= tcp_bpf_stream_read;
+	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
 
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;

net/ipv4/udp.c

···
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
+	/* psock ingress_msg queue should not contain any bad checksum frames */
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 	return mask;
 
 }

net/ipv4/udp_bpf.c

···
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = udp_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)

net/tls/tls_main.c

···
 
 	prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_BASE][TLS_SW].recvmsg		  = tls_sw_recvmsg;
-	prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+	prot[TLS_BASE][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_BASE][TLS_SW].close		  = tls_sk_proto_close;
 
 	prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
 	prot[TLS_SW][TLS_SW].recvmsg		= tls_sw_recvmsg;
-	prot[TLS_SW][TLS_SW].stream_memory_read	= tls_sw_stream_read;
+	prot[TLS_SW][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_SW][TLS_SW].close		= tls_sk_proto_close;
 
 #ifdef CONFIG_TLS_DEVICE

net/tls/tls_sw.c

···
 	return copied ? : err;
 }
 
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);

net/unix/af_unix.c

···
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
···
 
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */

net/unix/unix_bpf.c

···
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void unix_stream_bpf_rebuild_protos(struct proto *prot,
···
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 	prot->unhash  = sock_map_unhash;
 }
 

tools/testing/selftests/bpf/prog_tests/sockmap_listen.c

···
 	int err, n;
 	u32 key;
 	char b;
-	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
···
 		goto close_peer1;
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
-	n = read(c0, &b, 1);
-	if (n < 0) {
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
+	n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	if (n < 0)
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_peer1:
 	xclose(p1);
···
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	int sfd[2];
 	u32 key;
···
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
-	if (n < 0) {
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	if (n < 0)
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close:
 	xclose(c1);
···
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	u32 key;
 	char b;
···
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
-	if (n < 0) {
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	if (n < 0)
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_cli1:
 	xclose(c1);
···
 	const char *log_prefix = redir_mode_str(mode);
 	int c0, c1, p0, p1;
 	unsigned int pass;
-	int retries = 100;
 	int err, n;
 	int sfd[2];
 	u32 key;
···
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
-	if (n < 0) {
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	if (n < 0)
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close_cli1:
 	xclose(c1);
···
 	int sfd[2];
 	u32 key;
 	char b;
-	int retries = 100;
 
 	zero_verdict_count(verd_mapfd);
 
···
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 
-again:
-	n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
-	if (n < 0) {
-		if (errno == EAGAIN && retries--) {
-			usleep(1000);
-			goto again;
-		}
-		FAIL_ERRNO("%s: read", log_prefix);
-	}
+	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+	if (n < 0)
+		FAIL_ERRNO("%s: recv_timeout", log_prefix);
 	if (n == 0)
-		FAIL("%s: incomplete read", log_prefix);
+		FAIL("%s: incomplete recv", log_prefix);
 
 close:
 	xclose(c1);