bpf, sockmap: Fix FIONREAD for sockmap

A socket using sockmap has its own independent receive queue: ingress_msg.
This queue may contain data from its own protocol stack or from other
sockets.

Therefore, for sockmap, relying solely on copied_seq and rcv_nxt to
calculate FIONREAD is not enough.

This patch adds a new msg_tot_len field in the psock structure to record
the data length in ingress_msg. Additionally, we implement new ioctl
interfaces for TCP and UDP to intercept FIONREAD operations.

Note that we intentionally do not include sk_receive_queue data in the
FIONREAD result. Data in sk_receive_queue has not yet been processed by
the BPF verdict program, and may be redirected to other sockets or
dropped. Including it would create semantic ambiguity since this data
may never be readable by the user.

Unix and VSOCK sockets have similar issues, but fixing them is outside
the scope of this patch as it would require more intrusive changes.

Previous work by John Fastabend made some efforts towards FIONREAD support:
commit e5c6de5fa025 ("bpf, sockmap: Incorrectly handling copied_seq")
Although the current patch is based on the previous work by John Fastabend,
it is acceptable for our Fixes tag to point to the same commit.

                                                      FD1:read()
                                                      --  FD1->copied_seq++
                                                          |  [read data]
                                                          |
                                   [enqueue data]         v
                  [sockmap]     -> ingress to self ->  ingress_msg queue
FD1 native stack  ------>                                 ^
-- FD1->rcv_nxt++               -> redirect to other      | [enqueue data]
                                       |                  |
                                       |             ingress to FD1
                                       v                  ^
                                      ...                 |  [sockmap]
                                                     FD2 native stack

Fixes: 04919bed948dc ("tcp: Introduce tcp_read_skb()")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20260124113314.113584-3-jiayuan.chen@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 39 insertions, 4 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 5c698fd7fbf8..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)
 {
@@ -332,6 +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)
 {
@@ -610,6 +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)