lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening PHC | |
Open Source and information security mailing list archives
| ||
|
Date: Mon, 13 Apr 2020 23:09:27 +0300 From: Leşe Doru Călin <lesedorucalin01@...il.com> To: David Miller <davem@...emloft.net> Cc: Alexey Kuznetsov <kuznet@....inr.ac.ru>, Hideaki YOSHIFUJI <yoshfuji@...ux-ipv6.org>, netdev@...r.kernel.org Subject: Re: [PATCH] net: UDP repair mode for retrieving the send queue of corked UDP socket On Sun, Apr 12, 2020 at 08:56:11PM -0700, David Miller wrote: > From: Lese Doru Calin <lesedorucalin01@...il.com> > Date: Wed, 8 Apr 2020 23:59:54 +0300 > > > +static int udp_peek_sndq(struct sock *sk, struct msghdr *msg, int off, int len) > > +{ > > + struct sk_buff *skb; > > + int copied = 0, err = 0, copy; > > Please use reverse christmas tree (longest to shortest) ordering for > local variables. > > > +static int udp6_peek_sndq(struct sock *sk, struct msghdr *msg, int off, int len) > > +{ > > + struct sk_buff *skb; > > + int copied = 0, err = 0, copy; > > Likewise. > > Thank you. I changed it accordingly. I hope it is ok. Best regards, Lese Doru Signed-off-by: Lese Doru Calin <lesedorucalin01@...il.com> --- include/linux/udp.h | 3 +- include/uapi/linux/udp.h | 1 net/ipv4/udp.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/udp.c | 45 +++++++++++++++++++++++++++++++++++ 4 files changed, 108 insertions(+), 1 deletion(-) diff --git a/include/linux/udp.h b/include/linux/udp.h index aa84597bdc33..b22bd70118ce 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -51,7 +51,8 @@ struct udp_sock { * different encapsulation layer set * this */ - gro_enabled:1; /* Can accept GRO packets */ + gro_enabled:1, /* Can accept GRO packets */ + repair:1;/* Receive the send queue */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index 4828794efcf8..2fe78329d6da 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -29,6 +29,7 @@ struct udphdr { /* UDP socket options */ #define UDP_CORK 1 /* Never send partially complete segments */ +#define UDP_REPAIR 19 /* Receive the send queue */ #define UDP_ENCAP 100 /* Set the socket to accept encapsulated packets */ #define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */ #define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32564b350823..306cd70e40cb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1720,6 +1720,28 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, } EXPORT_SYMBOL(__skb_recv_udp); +static int udp_peek_sndq(struct sock *sk, struct msghdr *msg, int off, int len) +{ + int copy, copied = 0, err = 0; + struct sk_buff *skb; + + skb_queue_walk(&sk->sk_write_queue, skb) { + copy = len - copied; + if (copy > skb->len - off) + copy = skb->len - off; + + err = skb_copy_datagram_msg(skb, off, msg, copy); + if (err) + break; + + copied += copy; + + if (len <= copied) + break; + } + return err ?: copied; +} + /* * This should be easy, if there is something there we * return it, otherwise we block. @@ -1729,8 +1751,10 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); + struct udp_sock *up = udp_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; + struct flowi4 *fl4; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); @@ -1739,6 +1763,12 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, if (flags & MSG_ERRQUEUE) return ip_recv_error(sk, msg, len, addr_len); + if (unlikely(up->repair)) { + if (!peeking) + return -EPERM; + goto recv_sndq; + } + try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &off, &err); @@ -1832,6 +1862,18 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; + +recv_sndq: + off = sizeof(struct iphdr) + sizeof(struct udphdr); + if (sin) { + fl4 = &inet->cork.fl.u.ip4; + sin->sin_family = AF_INET; + sin->sin_port = fl4->fl4_dport; + sin->sin_addr.s_addr = fl4->daddr; + memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); + } + return udp_peek_sndq(sk, msg, off, len); } int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -2525,6 +2567,11 @@ void udp_destroy_sock(struct sock *sk) } } +static inline bool udp_can_repair_sock(const struct sock *sk) +{ + return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN); +} + /* * Socket option code for UDP */ @@ -2557,6 +2604,15 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } break; + case UDP_REPAIR: + if (!udp_can_repair_sock(sk)) + err = -EPERM; + else if (val != 0) + up->repair = 1; + else + up->repair = 0; + break; + case UDP_ENCAP: switch (val) { case 0: @@ -2678,6 +2734,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->corkflag; break; + case UDP_REPAIR: + val = up->repair; + break; + case UDP_ENCAP: val = up->encap_type; break; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7d4151747340..ec653f9fce2d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -250,6 +250,28 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be EXPORT_SYMBOL_GPL(udp6_lib_lookup); #endif +static int udp6_peek_sndq(struct sock *sk, struct msghdr *msg, int off, int len) +{ + int copy, copied = 0, err = 0; + struct sk_buff *skb; + + skb_queue_walk(&sk->sk_write_queue, skb) { + copy = len - copied; + if (copy > skb->len - off) + copy = skb->len - off; + + err = skb_copy_datagram_msg(skb, off, msg, copy); + if (err) + break; + + copied += copy; + + if (len <= copied) + break; + } + return err ?: copied; +} + /* do not use the scratch area len for jumbogram: their length execeeds the * scratch area space; note that the IP6CB flags is still in the first * cacheline, so checking for jumbograms is cheap @@ -269,7 +291,9 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); + struct udp_sock *up = udp_sk(sk); struct sk_buff *skb; + struct flowi6 *fl6; unsigned int ulen, copied; int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); @@ -283,6 +307,12 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); + if (unlikely(up->repair)) { + if (!peeking) + return -EPERM; + goto recv_sndq; + } + try_again: off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &off, &err); @@ -394,6 +424,21 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; + +recv_sndq: + off = sizeof(struct ipv6hdr) + sizeof(struct udphdr); + if (msg->msg_name) { + DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); + + fl6 = &inet->cork.fl.u.ip6; + sin6->sin6_family = AF_INET6; + sin6->sin6_port = fl6->fl6_dport; + sin6->sin6_flowinfo = 0; + sin6->sin6_addr = fl6->daddr; + sin6->sin6_scope_id = fl6->flowi6_oif; + *addr_len = sizeof(*sin6); + } + return udp6_peek_sndq(sk, msg, off, len); } DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
Powered by blists - more mailing lists