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()
  ...

2 files changed, 42 insertions, 6 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a268e1595b22..ca8a5cb8e569 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -10,6 +10,7 @@
 
 #include <net/inet_common.h>
 #include <net/tls.h>
+#include <asm/ioctls.h>
 
 void tcp_eat_skb(struct sock *sk, struct sk_buff *skb)
 {
@@ -226,6 +227,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 	int peek = flags & MSG_PEEK;
 	struct sk_psock *psock;
 	struct tcp_sock *tcp;
+	int copied_from_self = 0;
 	int copied = 0;
 	u32 seq;
 
@@ -262,7 +264,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
 	}
 
 msg_bytes_ready:
-	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	copied = __sk_msg_recvmsg(sk, psock, msg, len, flags, &copied_from_self);
 	/* The typical case for EFAULT is the socket was gracefully
 	 * shutdown with a FIN pkt. So check here the other case is
 	 * some error on copy_page_to_iter which would be unexpected.
@@ -277,7 +279,7 @@ msg_bytes_ready:
 			goto out;
 		}
 	}
-	seq += copied;
+	seq += copied_from_self;
 	if (!copied) {
 		long timeo;
 		int data;
@@ -331,6 +333,24 @@ unlock:
 	return copied;
 }
 
+static int tcp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
+{
+	bool slow;
+
+	if (cmd != SIOCINQ)
+		return tcp_ioctl(sk, cmd, karg);
+
+	/* works similar as tcp_ioctl */
+	if (sk->sk_state == TCP_LISTEN)
+		return -EINVAL;
+
+	slow = lock_sock_fast(sk);
+	*karg = sk_psock_msg_inq(sk);
+	unlock_sock_fast(sk, slow);
+
+	return 0;
+}
+
 static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			   int flags, int *addr_len)
 {
@@ -609,6 +629,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
 	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
+	prot[TCP_BPF_BASE].ioctl		= tcp_bpf_ioctl;
 
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 0735d820e413..91233e37cd97 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -5,6 +5,7 @@
 #include <net/sock.h>
 #include <net/udp.h>
 #include <net/inet_common.h>
+#include <asm/ioctls.h>
 
 #include "udp_impl.h"
 
@@ -111,12 +112,26 @@ enum {
 static DEFINE_SPINLOCK(udpv6_prot_lock);
 static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
 
+static int udp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
+{
+	if (cmd != SIOCINQ)
+		return udp_ioctl(sk, cmd, karg);
+
+	/* Since we don't hold a lock, sk_receive_queue may contain data.
+	 * BPF might only be processing this data at the moment. We only
+	 * care about the data in the ingress_msg here.
+	 */
+	*karg = sk_msg_first_len(sk);
+	return 0;
+}
+
 static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 {
-	*prot        = *base;
-	prot->close  = sock_map_close;
-	prot->recvmsg = udp_bpf_recvmsg;
-	prot->sock_is_readable = sk_msg_is_readable;
+	*prot			= *base;
+	prot->close		= sock_map_close;
+	prot->recvmsg		= udp_bpf_recvmsg;
+	prot->sock_is_readable	= sk_msg_is_readable;
+	prot->ioctl		= udp_bpf_ioctl;
 }
 
 static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)