[PATCH net-next 0/4] bpf, sockmap: Fix memleaks and issues of mem charge/uncharge

This patchset fixes memleaks and incorrect charge/uncharge memory, these
issues cause the following info:

WARNING: CPU: 0 PID: 9202 at net/core/stream.c:205 sk_stream_kill_queues+0xc8/0xe0
Call Trace:
 <IRQ>
 inet_csk_destroy_sock+0x55/0x110
 tcp_rcv_state_process+0xe5f/0xe90
 ? sk_filter_trim_cap+0x10d/0x230
 ? tcp_v4_do_rcv+0x161/0x250
 tcp_v4_do_rcv+0x161/0x250
 tcp_v4_rcv+0xc3a/0xce0
 ip_protocol_deliver_rcu+0x3d/0x230
 ip_local_deliver_finish+0x54/0x60
 ip_local_deliver+0xfd/0x110
 ? ip_protocol_deliver_rcu+0x230/0x230
 ip_rcv+0xd6/0x100
 ? ip_local_deliver+0x110/0x110
 __netif_receive_skb_one_core+0x85/0xa0
 process_backlog+0xa4/0x160
 __napi_poll+0x29/0x1b0
 net_rx_action+0x287/0x300
 __do_softirq+0xff/0x2fc
 do_softirq+0x79/0x90
 </IRQ>

WARNING: CPU: 0 PID: 531 at net/ipv4/af_inet.c:154 inet_sock_destruct+0x175/0x1b0
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 ? process_one_work+0x3c0/0x3c0
 worker_thread+0x30/0x350
 ? process_one_work+0x3c0/0x3c0
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x22/0x30
 </TASK>

Wang Yufen (4):
  bpf, sockmap: Fix memleak in sk_psock_queue_msg
  bpf, sockmap: Fix memleak in tcp_bpf_sendmsg while sk msg is full
  bpf, sockmap: Fix more uncharged while msg has more_data
  bpf, sockmap: Fix double uncharge the mem of sk_msg

 include/linux/skmsg.h | 13 ++++---------
 net/ipv4/tcp_bpf.c    | 13 +++++++++----
 2 files changed, 13 insertions(+), 13 deletions(-)

-- 
2.25.1

If tcp_bpf_sendmsg() is running while sk msg is full, sk_msg_alloc()
returns -ENOSPC, tcp_bpf_sendmsg() goto wait for memory. If partial memory
has been alloced by sk_msg_alloc(), that is, msg_tx->sg.size is greater
than osize after sk_msg_alloc(), memleak occurs. To fix we use
sk_msg_trim() to release the allocated memory, then goto wait for memory.

This issue can cause the following info:
WARNING: CPU: 3 PID: 7950 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0
Call Trace:
 <TASK>
 inet_csk_destroy_sock+0x55/0x110
 __tcp_close+0x279/0x470
 tcp_close+0x1f/0x60
 inet_release+0x3f/0x80
 __sock_release+0x3d/0xb0
 sock_close+0x11/0x20
 __fput+0x92/0x250
 task_work_run+0x6a/0xa0
 do_exit+0x33b/0xb60
 do_group_exit+0x2f/0xa0
 get_signal+0xb6/0x950
 arch_do_signal_or_restart+0xac/0x2a0
 exit_to_user_mode_prepare+0xa9/0x200
 syscall_exit_to_user_mode+0x12/0x30
 do_syscall_64+0x46/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae
 </TASK>

WARNING: CPU: 3 PID: 2094 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 kthread+0xe6/0x110
 ret_from_fork+0x22/0x30
 </TASK>

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Wang Yufen <redacted>
---
 net/ipv4/tcp_bpf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 9b9b02052fd3..ac9f491cc139 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c

@@ -421,8 +421,10 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		osize = msg_tx->sg.size;
 		err = sk_msg_alloc(sk, msg_tx, msg_tx->sg.size + copy, msg_tx->sg.end - 1);
 		if (err) {
-			if (err != -ENOSPC)
+			if (err != -ENOSPC) {
+				sk_msg_trim(sk, msg_tx, osize);
 				goto wait_for_memory;
+			}
 			enospc = true;
 			copy = msg_tx->sg.size - osize;
 		}

-- 
2.25.1

If tcp_bpf_sendmsg is running during a tear down operation we may enqueue
data on the ingress msg queue while tear down is trying to free it.

 sk1 (redirect sk2)                         sk2
 -------------------                      ---------------
tcp_bpf_sendmsg()
 tcp_bpf_send_verdict()
  tcp_bpf_sendmsg_redir()
   bpf_tcp_ingress()
                                          sock_map_close()
                                           lock_sock()
    lock_sock() ... blocking
                                           sk_psock_stop
                                            sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
                                           release_sock(sk);
    lock_sock()	
    sk_mem_charge()
    get_page()
    sk_psock_queue_msg()
     sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED);
      drop_sk_msg()
    release_sock()

While drop_sk_msg(), the msg has charged memory form sk by sk_mem_charge
and has sg pages need to put. To fix we use sk_msg_free() and then kfee()
msg.

This issue can cause the following info:
WARNING: CPU: 0 PID: 9202 at net/core/stream.c:205 sk_stream_kill_queues+0xc8/0xe0
Call Trace:
 <IRQ>
 inet_csk_destroy_sock+0x55/0x110
 tcp_rcv_state_process+0xe5f/0xe90
 ? sk_filter_trim_cap+0x10d/0x230
 ? tcp_v4_do_rcv+0x161/0x250
 tcp_v4_do_rcv+0x161/0x250
 tcp_v4_rcv+0xc3a/0xce0
 ip_protocol_deliver_rcu+0x3d/0x230
 ip_local_deliver_finish+0x54/0x60
 ip_local_deliver+0xfd/0x110
 ? ip_protocol_deliver_rcu+0x230/0x230
 ip_rcv+0xd6/0x100
 ? ip_local_deliver+0x110/0x110
 __netif_receive_skb_one_core+0x85/0xa0
 process_backlog+0xa4/0x160
 __napi_poll+0x29/0x1b0
 net_rx_action+0x287/0x300
 __do_softirq+0xff/0x2fc
 do_softirq+0x79/0x90
 </IRQ>

WARNING: CPU: 0 PID: 531 at net/ipv4/af_inet.c:154 inet_sock_destruct+0x175/0x1b0
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 ? process_one_work+0x3c0/0x3c0
 worker_thread+0x30/0x350
 ? process_one_work+0x3c0/0x3c0
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x22/0x30
 </TASK>

Fixes: 9635720b7c88 ("bpf, sockmap: Fix memleak on ingress msg enqueue")
Signed-off-by: Wang Yufen <redacted>
---
 include/linux/skmsg.h | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index fdb5375f0562..c5a2d6f50f25 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h

@@ -304,21 +304,16 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
-static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg)
-{
-	if (msg->skb)
-		sock_drop(psock->sk, msg->skb);
-	kfree(msg);
-}
-
 static inline void sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
 	spin_lock_bh(&psock->ingress_lock);
 	if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
 		list_add_tail(&msg->list, &psock->ingress_msg);
-	else
-		drop_sk_msg(psock, msg);
+	else {
+		sk_msg_free(psock->sk, msg);
+		kfree(msg);
+	}
 	spin_unlock_bh(&psock->ingress_lock);
 }
 

-- 
2.25.1

If tcp_bpf_sendmsg is running during a tear down operation, psock may be
freed.

tcp_bpf_sendmsg()
 tcp_bpf_send_verdict()
  sk_msg_return()
  tcp_bpf_sendmsg_redir()
   unlikely(!psock))
   sk_msg_free()

The mem of msg has been uncharged in tcp_bpf_send_verdict() by
sk_msg_return(), so we need to use sk_msg_free_nocharge while psock
is null.

This issue can cause the following info:
WARNING: CPU: 0 PID: 2136 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 worker_thread+0x30/0x350
 ? process_one_work+0x3c0/0x3c0
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x22/0x30
 </TASK>

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Wang Yufen <redacted>
---
 net/ipv4/tcp_bpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 1f0364e06619..03c037d2a055 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c

@@ -139,7 +139,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
 	int ret;
 
 	if (unlikely(!psock)) {
-		sk_msg_free(sk, msg);
+		sk_msg_free_nocharge(sk, msg);
 		return 0;
 	}
 	ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) :

-- 
2.25.1

In tcp_bpf_send_verdict(), if msg has more data after
tcp_bpf_sendmsg_redir():

tcp_bpf_send_verdict()
 tosend = msg->sg.size  //msg->sg.size = 22220
 case __SK_REDIRECT:
  sk_msg_return()  //uncharged msg->sg.size(22220) sk->sk_forward_alloc
  tcp_bpf_sendmsg_redir() //after tcp_bpf_sendmsg_redir, msg->sg.size=11000
 goto more_data;
 tosend = msg->sg.size  //msg->sg.size = 11000
 case __SK_REDIRECT:
  sk_msg_return()  //uncharged msg->sg.size(11000) to sk->sk_forward_alloc

The msg->sg.size(11000) has been uncharged twice, to fix we can charge the
remaining msg->sg.size before goto more data.

This issue can cause the following info:
WARNING: CPU: 0 PID: 9860 at net/core/stream.c:208 sk_stream_kill_queues+0xd4/0x1a0
Call Trace:
 <TASK>
 inet_csk_destroy_sock+0x55/0x110
 __tcp_close+0x279/0x470
 tcp_close+0x1f/0x60
 inet_release+0x3f/0x80
 __sock_release+0x3d/0xb0
 sock_close+0x11/0x20
 __fput+0x92/0x250
 task_work_run+0x6a/0xa0
 do_exit+0x33b/0xb60
 do_group_exit+0x2f/0xa0
 get_signal+0xb6/0x950
 arch_do_signal_or_restart+0xac/0x2a0
 ? vfs_write+0x237/0x290
 exit_to_user_mode_prepare+0xa9/0x200
 syscall_exit_to_user_mode+0x12/0x30
 do_syscall_64+0x46/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae
 </TASK>

WARNING: CPU: 0 PID: 2136 at net/ipv4/af_inet.c:155 inet_sock_destruct+0x13c/0x260
Call Trace:
 <TASK>
 __sk_destruct+0x24/0x1f0
 sk_psock_destroy+0x19b/0x1c0
 process_one_work+0x1b3/0x3c0
 worker_thread+0x30/0x350
 ? process_one_work+0x3c0/0x3c0
 kthread+0xe6/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x22/0x30
 </TASK>

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Wang Yufen <redacted>
---
 net/ipv4/tcp_bpf.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ac9f491cc139..1f0364e06619 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c

@@ -335,7 +335,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 			cork = true;
 			psock->cork = NULL;
 		}
-		sk_msg_return(sk, msg, tosend);
+		sk_msg_return(sk, msg, msg->sg.size);
 		release_sock(sk);
 
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);

@@ -375,8 +375,11 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 		}
 		if (msg &&
 		    msg->sg.data[msg->sg.start].page_link &&
-		    msg->sg.data[msg->sg.start].length)
+		    msg->sg.data[msg->sg.start].length) {
+			if (eval == __SK_REDIRECT)
+				sk_mem_charge(sk, msg->sg.size);
 			goto more_data;
+		}
 	}
 	return ret;
 }

-- 
2.25.1