bpf, sockmap: Fix some issues with using apply_bytes
Subsystems (8)
v2 cover bpf, sockmap: Fix some issues with using apply_bytes
Patch 1~3 fixes three issues with using apply_bytes when redirecting. Patch 4 adds ingress tests for txmsg with apply_bytes in selftests.
---
Changes in v2:
*Patch 2: Clear psock->flags explicitly before releasing the sock lock
Pengcheng Yang (4):
bpf, sockmap: Fix repeated calls to sock_put() when msg has more_data bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes bpf, sockmap: Fix data loss caused by using apply_bytes on ingress
redirect
selftests/bpf: Add ingress tests for txmsg with apply_bytes
include/linux/skmsg.h | 1 + net/core/skmsg.c | 1 + net/ipv4/tcp_bpf.c | 10 ++++++++-- net/tls/tls_sw.c | 1 + tools/testing/selftests/bpf/test_sockmap.c | 18 ++++++++++++++++++ 5 files changed, 29 insertions(+), 2 deletions(-)
Signature · 1 line
1.8.3.1
PATCH v2 1/4 bpf, sockmap: Fix repeated calls to sock_put() when msg has more_data
In tcp_bpf_send_verdict() redirection, the eval variable is assigned to __SK_REDIRECT after the apply_bytes data is sent, if msg has more_data, sock_put() will be called multiple times.
We should reset the eval variable to __SK_NONE every time more_data starts.
This causes:
IPv4: Attempt to release TCP socket in state 1 00000000b4c925d7
------------[ cut here ]------------ refcount_t: addition on 0; use-after-free. WARNING: CPU: 5 PID: 4482 at lib/refcount.c:25 refcount_warn_saturate+0x7d/0x110 Modules linked in: CPU: 5 PID: 4482 Comm: sockhash_bypass Kdump: loaded Not tainted 6.0.0 #1 Hardware name: Red Hat KVM, BIOS 1.11.0-2.el7 04/01/2014 Call Trace: <TASK> __tcp_transmit_skb+0xa1b/0xb90 ? __alloc_skb+0x8c/0x1a0 ? __kmalloc_node_track_caller+0x184/0x320 tcp_write_xmit+0x22a/0x1110 __tcp_push_pending_frames+0x32/0xf0 do_tcp_sendpages+0x62d/0x640 tcp_bpf_push+0xae/0x2c0 tcp_bpf_sendmsg_redir+0x260/0x410 ? preempt_count_add+0x70/0xa0 tcp_bpf_send_verdict+0x386/0x4b0 tcp_bpf_sendmsg+0x21b/0x3b0 sock_sendmsg+0x58/0x70 __sys_sendto+0xfa/0x170 ? xfd_validate_state+0x1d/0x80 ? switch_fpu_return+0x59/0xe0 __x64_sys_sendto+0x24/0x30 do_syscall_64+0x37/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd
--- net/ipv4/tcp_bpf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/ipv4/tcp_bpf.c +2 -1
@@ -279,7 +279,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,bool cork = false, enospc =sk_msg_full (msg);struct sock *sk_redir;u32 tosend, origsize, sent, delta =0 ; -u32 eval = __SK_NONE; +u32 eval;int ret; more_data:
@@ -310,6 +310,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, tosend = msg->sg.size;if (psock->apply_bytes && psock->apply_bytes < tosend) tosend = psock->apply_bytes; + eval = __SK_NONE;switch (psock->eval) {case __SK_PASS:
Signature · 1 line
1.8.3.1
PATCH v2 2/4 bpf, sockmap: Fix missing BPF_F_INGRESS flag when using apply_bytes
In reply to Pengcheng YangWhen redirecting, we use sk_msg_to_ingress() to get the BPF_F_INGRESS flag from the msg->flags. If apply_bytes is used and it is larger than the current data being processed, sk_psock_msg_verdict() will not be called when sendmsg() is called again. At this time, the msg->flags is 0, and we lost the BPF_F_INGRESS flag.
So we need to save the BPF_F_INGRESS flag in sk_psock and assign it to msg->flags before redirection.
--- include/linux/skmsg.h | 1 + net/core/skmsg.c | 1 + net/ipv4/tcp_bpf.c | 2 ++ net/tls/tls_sw.c | 1 + 4 files changed, 5 insertions(+)
include/linux/skmsg.h +1 -0
@@ -82,6 +82,7 @@ struct sk_psock {u32 apply_bytes;u32 cork_bytes;u32 eval; +u32 flags;struct sk_msg *cork;struct sk_psock_progs progs;#if IS_ENABLED (CONFIG_BPF_STREAM_PARSER )
net/core/skmsg.c +1 -0
@@ -888,6 +888,7 @@ int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock,if (psock->sk_redir)sock_put (psock->sk_redir); psock->sk_redir = msg->sk_redir; + psock->flags = msg->flags;if (!psock->sk_redir) { ret = __SK_DROP; goto out;
net/ipv4/tcp_bpf.c +2 -0
@@ -323,12 +323,14 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,break ;case __SK_REDIRECT: sk_redir = psock->sk_redir; + msg->flags = psock->flags;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 ; + psock->flags =0 ; }if (psock->cork) { cork = true;
net/tls/tls_sw.c +1 -0
@@ -838,6 +838,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,break ;case __SK_REDIRECT: sk_redir = psock->sk_redir; + msg->flags = psock->flags;memcpy (&msg_redir, msg,sizeof (*msg));if (msg->apply_bytes < send) msg->apply_bytes =0 ;
Signature · 1 line
1.8.3.1
PATCH v2 3/4 bpf, sockmap: Fix data loss caused by using apply_bytes on ingress redirect
In reply to Pengcheng YangUse apply_bytes on ingress redirect, when apply_bytes is less than the length of msg data, some data may be skipped and lost in bpf_tcp_ingress().
If there is still data in the scatterlist that has not been consumed, we cannot move the msg iter.
--- net/ipv4/tcp_bpf.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
net/ipv4/tcp_bpf.c +4 -1
@@ -45,8 +45,11 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, tmp->sg.end = i;if (apply) { apply_bytes -= size; -if (!apply_bytes) +if (!apply_bytes) { +if (sge->length) +sk_msg_iter_var_prev (i);break ; + } } }while (i != msg->sg.end);
Signature · 1 line
1.8.3.1
PATCH v2 4/4 selftests/bpf: Add ingress tests for txmsg with apply_bytes
In reply to Pengcheng YangCurrently, the ingress redirect is not covered in "txmsg test apply".
--- tools/testing/selftests/bpf/test_sockmap.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
tools/testing/selftests/bpf/test_sockmap.c +18 -0
@@ -1649,24 +1649,42 @@ static void test_txmsg_apply(int cgrp, struct sockmap_options *opt) { txmsg_pass =1 ; txmsg_redir =0 ; + txmsg_ingress =0 ; txmsg_apply =1 ; txmsg_cork =0 ;test_send_one (opt, cgrp); txmsg_pass =0 ; txmsg_redir =1 ; + txmsg_ingress =0 ; + txmsg_apply =1 ; + txmsg_cork =0 ; +test_send_one (opt, cgrp); + + txmsg_pass =0 ; + txmsg_redir =1 ; + txmsg_ingress =1 ; txmsg_apply =1 ; txmsg_cork =0 ;test_send_one (opt, cgrp); txmsg_pass =1 ; txmsg_redir =0 ; + txmsg_ingress =0 ; + txmsg_apply =1024 ; + txmsg_cork =0 ; +test_send_large (opt, cgrp); + + txmsg_pass =0 ; + txmsg_redir =1 ; + txmsg_ingress =0 ; txmsg_apply =1024 ; txmsg_cork =0 ;test_send_large (opt, cgrp); txmsg_pass =0 ; txmsg_redir =1 ; + txmsg_ingress =1 ; txmsg_apply =1024 ; txmsg_cork =0 ;test_send_large (opt, cgrp);
Signature · 1 line
1.8.3.1
Quoted 6 lines · Pengcheng Yang
Patch 1~3 fixes three issues with using
apply_byteswhen redirecting. Patch 4 adds ingress tests for txmsg withapply_bytesin selftests.---
Changes in v2:
*Patch 2: Clearpsock->flagsexplicitly before releasing the sock lock
Yeah I think its slightly nicer Thanks for fixing this.
For the series.