From 1ddc3229ad3c40840c24a699ada5cfeb4319b578 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 10 Mar 2021 16:28:58 +0800 Subject: skbuff: remove some unnecessary operation in skb_segment_list() gro list uses skb_shinfo(skb)->frag_list to link two skb together, and NAPI_GRO_CB(p)->last->next is used when there are more skb, see skb_gro_receive_list(). gso expects that each segmented skb is linked together using skb->next, so only the first skb->next need to set to skb_shinfo(skb)-> frag_list when doing gso list segment. It is the same reason that nskb->next does not need to be set to list_skb before goto the error handling, because nskb->next already pointers to list_skb. And nskb is also the last skb at the end of loop, so remove tail variable and use nskb instead. Signed-off-by: Yunsheng Lin Signed-off-by: David S. Miller --- net/core/skbuff.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'net/core/skbuff.c') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c421c8f80925..e8320b5d651a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3732,13 +3732,13 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; - struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int err; skb_push(skb, -skb_network_offset(skb) + offset); skb_shinfo(skb)->frag_list = NULL; + skb->next = list_skb; do { nskb = list_skb; @@ -3756,17 +3756,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, } } - if (!tail) - skb->next = nskb; - else - tail->next = nskb; - - if (unlikely(err)) { - nskb->next = list_skb; + if (unlikely(err)) goto err_linearize; - } - - tail = nskb; delta_len += nskb->len; delta_truesize += nskb->truesize; @@ -3793,7 +3784,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_gso_reset(skb); - skb->prev = tail; + skb->prev = nskb; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) -- cgit v1.2.3-58-ga151 From 0739cd28f2645e814586c7536ba5da9825cb8029 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Tue, 30 Mar 2021 19:32:24 -0700 Subject: net: Introduce skb_send_sock() for sock_map We only have skb_send_sock_locked() which requires callers to use lock_sock(). Introduce a variant skb_send_sock() which locks on its own, callers do not need to lock it any more. This will save us from adding a ->sendmsg_locked for each protocol. To reuse the code, pass function pointers to __skb_send_sock() and build skb_send_sock() and skb_send_sock_locked() on top. Signed-off-by: Cong Wang Signed-off-by: Alexei Starovoitov Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20210331023237.41094-4-xiyou.wangcong@gmail.com --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 55 +++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 49 insertions(+), 7 deletions(-) (limited to 'net/core/skbuff.c') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c8def85fcc22..dbf820a50a39 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3626,6 +3626,7 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e8320b5d651a..3ad9e8425ab2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2500,9 +2500,32 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, } EXPORT_SYMBOL_GPL(skb_splice_bits); -/* Send skb data on a socket. Socket must be locked. */ -int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, - int len) +static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t size) +{ + struct socket *sock = sk->sk_socket; + + if (!sock) + return -EINVAL; + return kernel_sendmsg(sock, msg, vec, num, size); +} + +static int sendpage_unlocked(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct socket *sock = sk->sk_socket; + + if (!sock) + return -EINVAL; + return kernel_sendpage(sock, page, offset, size, flags); +} + +typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t size); +typedef int (*sendpage_func)(struct sock *sk, struct page *page, int offset, + size_t size, int flags); +static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, + int len, sendmsg_func sendmsg, sendpage_func sendpage) { unsigned int orig_len = len; struct sk_buff *head = skb; @@ -2522,7 +2545,8 @@ do_frag_list: memset(&msg, 0, sizeof(msg)); msg.msg_flags = MSG_DONTWAIT; - ret = kernel_sendmsg_locked(sk, &msg, &kv, 1, slen); + ret = INDIRECT_CALL_2(sendmsg, kernel_sendmsg_locked, + sendmsg_unlocked, sk, &msg, &kv, 1, slen); if (ret <= 0) goto error; @@ -2553,9 +2577,11 @@ do_frag_list: slen = min_t(size_t, len, skb_frag_size(frag) - offset); while (slen) { - ret = kernel_sendpage_locked(sk, skb_frag_page(frag), - skb_frag_off(frag) + offset, - slen, MSG_DONTWAIT); + ret = INDIRECT_CALL_2(sendpage, kernel_sendpage_locked, + sendpage_unlocked, sk, + skb_frag_page(frag), + skb_frag_off(frag) + offset, + slen, MSG_DONTWAIT); if (ret <= 0) goto error; @@ -2587,8 +2613,23 @@ out: error: return orig_len == len ? ret : orig_len - len; } + +/* Send skb data on a socket. Socket must be locked. */ +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len) +{ + return __skb_send_sock(sk, skb, offset, len, kernel_sendmsg_locked, + kernel_sendpage_locked); +} EXPORT_SYMBOL_GPL(skb_send_sock_locked); +/* Send skb data on a socket. Socket must be unlocked. */ +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len) +{ + return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, + sendpage_unlocked); +} + /** * skb_store_bits - store bits from kernel buffer to skb * @skb: destination buffer -- cgit v1.2.3-58-ga151 From 17c3df7078e3742bd9e907f3006a9e3469383007 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 14 Apr 2021 12:48:48 +0200 Subject: skbuff: revert "skbuff: remove some unnecessary operation in skb_segment_list()" the commit 1ddc3229ad3c ("skbuff: remove some unnecessary operation in skb_segment_list()") introduces an issue very similar to the one already fixed by commit 53475c5dd856 ("net: fix use-after-free when UDP GRO with shared fraglist"). If the GSO skb goes though skb_clone() and pskb_expand_head() before entering skb_segment_list(), the latter will unshare the frag_list skbs and will release the old list. With the reverted commit in place, when skb_segment_list() completes, skb->next points to the just released list, and later on the kernel will hit UaF. Note that since commit e0e3070a9bc9 ("udp: properly complete L4 GRO over UDP tunnel packet") the critical scenario can be reproduced also receiving UDP over vxlan traffic with: NIC (NETIF_F_GRO_FRAGLIST enabled) -> vxlan -> UDP sink Attaching a packet socket to the NIC will cause skb_clone() and the tunnel decapsulation will call pskb_expand_head(). Fixes: 1ddc3229ad3c ("skbuff: remove some unnecessary operation in skb_segment_list()") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/core/skbuff.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'net/core/skbuff.c') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ad9e8425ab2..14010c0eec48 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3773,13 +3773,13 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int delta_truesize = 0; unsigned int delta_len = 0; + struct sk_buff *tail = NULL; struct sk_buff *nskb, *tmp; int err; skb_push(skb, -skb_network_offset(skb) + offset); skb_shinfo(skb)->frag_list = NULL; - skb->next = list_skb; do { nskb = list_skb; @@ -3797,8 +3797,17 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, } } - if (unlikely(err)) + if (!tail) + skb->next = nskb; + else + tail->next = nskb; + + if (unlikely(err)) { + nskb->next = list_skb; goto err_linearize; + } + + tail = nskb; delta_len += nskb->len; delta_truesize += nskb->truesize; @@ -3825,7 +3834,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_gso_reset(skb); - skb->prev = nskb; + skb->prev = tail; if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) -- cgit v1.2.3-58-ga151