Merge tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Support associating BPF program with struct_ops (Amery Hung)

 - Switch BPF local storage to rqspinlock and remove recursion detection
   counters which were causing false positives (Amery Hung)

 - Fix live registers marking for indirect jumps (Anton Protopopov)

 - Introduce execution context detection BPF helpers (Changwoo Min)

 - Improve verifier precision for 32bit sign extension pattern
   (Cupertino Miranda)

 - Optimize BTF type lookup by sorting vmlinux BTF and doing binary
   search (Donglin Peng)

 - Allow states pruning for misc/invalid slots in iterator loops (Eduard
   Zingerman)

 - In preparation for ASAN support in BPF arenas teach libbpf to move
   global BPF variables to the end of the region and enable arena kfuncs
   while holding locks (Emil Tsalapatis)

 - Introduce support for implicit arguments in kfuncs and migrate a
   number of them to new API. This is a prerequisite for cgroup
   sub-schedulers in sched-ext (Ihor Solodrai)

 - Fix incorrect copied_seq calculation in sockmap (Jiayuan Chen)

 - Fix ORC stack unwind from kprobe_multi (Jiri Olsa)

 - Speed up fentry attach by using single ftrace direct ops in BPF
   trampolines (Jiri Olsa)

 - Require frozen map for calculating map hash (KP Singh)

 - Fix lock entry creation in TAS fallback in rqspinlock (Kumar
   Kartikeya Dwivedi)

 - Allow user space to select cpu in lookup/update operations on per-cpu
   array and hash maps (Leon Hwang)

 - Make kfuncs return trusted pointers by default (Matt Bobrowski)

 - Introduce "fsession" support where single BPF program is executed
   upon entry and exit from traced kernel function (Menglong Dong)

 - Allow bpf_timer and bpf_wq use in all programs types (Mykyta
   Yatsenko, Andrii Nakryiko, Kumar Kartikeya Dwivedi, Alexei
   Starovoitov)

 - Make KF_TRUSTED_ARGS the default for all kfuncs and clean up their
   definition across the tree (Puranjay Mohan)

 - Allow BPF arena calls from non-sleepable context (Puranjay Mohan)

 - Improve register id comparison logic in the verifier and extend
   linked registers with negative offsets (Puranjay Mohan)

 - In preparation for BPF-OOM introduce kfuncs to access memcg events
   (Roman Gushchin)

 - Use CFI compatible destructor kfunc type (Sami Tolvanen)

 - Add bitwise tracking for BPF_END in the verifier (Tianci Cao)

 - Add range tracking for BPF_DIV and BPF_MOD in the verifier (Yazhou
   Tang)

 - Make BPF selftests work with 64k page size (Yonghong Song)

* tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (268 commits)
  selftests/bpf: Fix outdated test on storage->smap
  selftests/bpf: Choose another percpu variable in bpf for btf_dump test
  selftests/bpf: Remove test_task_storage_map_stress_lookup
  selftests/bpf: Update task_local_storage/task_storage_nodeadlock test
  selftests/bpf: Update task_local_storage/recursion test
  selftests/bpf: Update sk_storage_omem_uncharge test
  bpf: Switch to bpf_selem_unlink_nofail in bpf_local_storage_{map_free, destroy}
  bpf: Support lockless unlink when freeing map or local storage
  bpf: Prepare for bpf_selem_unlink_nofail()
  bpf: Remove unused percpu counter from bpf_local_storage_map_free
  bpf: Remove cgroup local storage percpu counter
  bpf: Remove task local storage percpu counter
  bpf: Change local_storage->lock and b->lock to rqspinlock
  bpf: Convert bpf_selem_unlink to failable
  bpf: Convert bpf_selem_link_map to failable
  bpf: Convert bpf_selem_unlink_map to failable
  bpf: Select bpf_local_storage_map_bucket based on bpf_local_storage
  selftests/xsk: fix number of Tx frags in invalid packet
  selftests/xsk: properly handle batch ending in the middle of a packet
  bpf: Prevent reentrance into call_rcu_tasks_trace()
  ...

1 files changed, 68 insertions, 2 deletions

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 49847888c287..829b281d6c9c 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -97,6 +97,8 @@ struct sk_psock {
 	struct sk_buff_head		ingress_skb;
 	struct list_head		ingress_msg;
 	spinlock_t			ingress_lock;
+	/** @msg_tot_len: Total bytes queued in ingress_msg list. */
+	u32				msg_tot_len;
 	unsigned long			state;
 	struct list_head		link;
 	spinlock_t			link_lock;
@@ -141,6 +143,8 @@ 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);
+int __sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+		     int len, int flags, int *copied_from_self);
 bool sk_msg_is_readable(struct sock *sk);
 
 static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
@@ -319,6 +323,27 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
+static inline u32 sk_psock_get_msg_len_nolock(struct sk_psock *psock)
+{
+	/* Used by ioctl to read msg_tot_len only; lock-free for performance */
+	return READ_ONCE(psock->msg_tot_len);
+}
+
+static inline void sk_psock_msg_len_add_locked(struct sk_psock *psock, int diff)
+{
+	/* Use WRITE_ONCE to ensure correct read in sk_psock_get_msg_len_nolock().
+	 * ingress_lock should be held to prevent concurrent updates to msg_tot_len
+	 */
+	WRITE_ONCE(psock->msg_tot_len, psock->msg_tot_len + diff);
+}
+
+static inline void sk_psock_msg_len_add(struct sk_psock *psock, int diff)
+{
+	spin_lock_bh(&psock->ingress_lock);
+	sk_psock_msg_len_add_locked(psock, diff);
+	spin_unlock_bh(&psock->ingress_lock);
+}
+
 static inline bool sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
@@ -327,6 +352,7 @@ static inline bool sk_psock_queue_msg(struct sk_psock *psock,
 	spin_lock_bh(&psock->ingress_lock);
 	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 		list_add_tail(&msg->list, &psock->ingress_msg);
+		sk_psock_msg_len_add_locked(psock, msg->sg.size);
 		ret = true;
 	} else {
 		sk_msg_free(psock->sk, msg);
@@ -343,18 +369,25 @@ static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock)
 
 	spin_lock_bh(&psock->ingress_lock);
 	msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
-	if (msg)
+	if (msg) {
 		list_del(&msg->list);
+		sk_psock_msg_len_add_locked(psock, -msg->sg.size);
+	}
 	spin_unlock_bh(&psock->ingress_lock);
 	return msg;
 }
 
+static inline struct sk_msg *sk_psock_peek_msg_locked(struct sk_psock *psock)
+{
+	return list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
+}
+
 static inline struct sk_msg *sk_psock_peek_msg(struct sk_psock *psock)
 {
 	struct sk_msg *msg;
 
 	spin_lock_bh(&psock->ingress_lock);
-	msg = list_first_entry_or_null(&psock->ingress_msg, struct sk_msg, list);
+	msg = sk_psock_peek_msg_locked(psock);
 	spin_unlock_bh(&psock->ingress_lock);
 	return msg;
 }
@@ -521,6 +554,39 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
 	return !!psock->saved_data_ready;
 }
 
+/* for tcp only, sk is locked */
+static inline ssize_t sk_psock_msg_inq(struct sock *sk)
+{
+	struct sk_psock *psock;
+	ssize_t inq = 0;
+
+	psock = sk_psock_get(sk);
+	if (likely(psock)) {
+		inq = sk_psock_get_msg_len_nolock(psock);
+		sk_psock_put(sk, psock);
+	}
+	return inq;
+}
+
+/* for udp only, sk is not locked */
+static inline ssize_t sk_msg_first_len(struct sock *sk)
+{
+	struct sk_psock *psock;
+	struct sk_msg *msg;
+	ssize_t inq = 0;
+
+	psock = sk_psock_get(sk);
+	if (likely(psock)) {
+		spin_lock_bh(&psock->ingress_lock);
+		msg = sk_psock_peek_msg_locked(psock);
+		if (msg)
+			inq = msg->sg.size;
+		spin_unlock_bh(&psock->ingress_lock);
+		sk_psock_put(sk, psock);
+	}
+	return inq;
+}
+
 #if IS_ENABLED(CONFIG_NET_SOCK_MSG)
 
 #define BPF_F_STRPARSER	(1UL << 1)