From 35790c0421121364883a167bab8a2e37e1f67f78 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 May 2010 00:34:04 -0700 Subject: [PATCH 1/3] tcp: fix MD5 (RFC2385) support TCP MD5 support uses percpu data for temporary storage. It currently disables preemption so that same storage cannot be reclaimed by another thread on same cpu. We also have to make sure a softirq handler wont try to use also same context. Various bug reports demonstrated corruptions. Fix is to disable preemption and BH. Reported-by: Bhaskar Dutta Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 21 +++------------------ net/ipv4/tcp.c | 34 ++++++++++++++++++++++++---------- 2 files changed, 27 insertions(+), 28 deletions(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 75be5a28815d..aa04b9a5093b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1197,30 +1197,15 @@ extern int tcp_v4_md5_do_del(struct sock *sk, extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *); extern void tcp_free_md5sig_pool(void); -extern struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu); -extern void __tcp_put_md5sig_pool(void); +extern struct tcp_md5sig_pool *tcp_get_md5sig_pool(void); +extern void tcp_put_md5sig_pool(void); + extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, struct tcphdr *); extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, struct sk_buff *, unsigned header_len); extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key); -static inline -struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) -{ - int cpu = get_cpu(); - struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu); - if (!ret) - put_cpu(); - return ret; -} - -static inline void tcp_put_md5sig_pool(void) -{ - __tcp_put_md5sig_pool(); - put_cpu(); -} - /* write queue abstraction */ static inline void tcp_write_queue_purge(struct sock *sk) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0f8caf64caa3..296150b2a62f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2839,7 +2839,6 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool * __percpu *pool) if (p->md5_desc.tfm) crypto_free_hash(p->md5_desc.tfm); kfree(p); - p = NULL; } } free_percpu(pool); @@ -2937,25 +2936,40 @@ retry: EXPORT_SYMBOL(tcp_alloc_md5sig_pool); -struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu) + +/** + * tcp_get_md5sig_pool - get md5sig_pool for this user + * + * We use percpu structure, so if we succeed, we exit with preemption + * and BH disabled, to make sure another thread or softirq handling + * wont try to get same context. + */ +struct tcp_md5sig_pool *tcp_get_md5sig_pool(void) { struct tcp_md5sig_pool * __percpu *p; - spin_lock_bh(&tcp_md5sig_pool_lock); + + local_bh_disable(); + + spin_lock(&tcp_md5sig_pool_lock); p = tcp_md5sig_pool; if (p) tcp_md5sig_users++; - spin_unlock_bh(&tcp_md5sig_pool_lock); - return (p ? *per_cpu_ptr(p, cpu) : NULL); + spin_unlock(&tcp_md5sig_pool_lock); + + if (p) + return *per_cpu_ptr(p, smp_processor_id()); + + local_bh_enable(); + return NULL; } +EXPORT_SYMBOL(tcp_get_md5sig_pool); -EXPORT_SYMBOL(__tcp_get_md5sig_pool); - -void __tcp_put_md5sig_pool(void) +void tcp_put_md5sig_pool(void) { + local_bh_enable(); tcp_free_md5sig_pool(); } - -EXPORT_SYMBOL(__tcp_put_md5sig_pool); +EXPORT_SYMBOL(tcp_put_md5sig_pool); int tcp_md5_hash_header(struct tcp_md5sig_pool *hp, struct tcphdr *th) From 55fa0cfd7c3ac2ae34cac7dca2e3fbcfe661e6c3 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 9 May 2010 16:56:07 +0000 Subject: [PATCH 2/3] sctp: delete active ICMP proto unreachable timer when free transport transport may be free before ICMP proto unreachable timer expire, so we should delete active ICMP proto unreachable timer when transport is going away. Signed-off-by: Wei Yongjun Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/sctp/transport.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 4a368038d46f..165d54e07fcd 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -173,6 +173,10 @@ void sctp_transport_free(struct sctp_transport *transport) del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); + /* Delete the ICMP proto unreachable timer if it's active. */ + if (timer_pending(&transport->proto_unreach_timer) && + del_timer(&transport->proto_unreach_timer)) + sctp_association_put(transport->asoc); sctp_transport_put(transport); } From c02db8c6290bb992442fec1407643c94cc414375 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Sun, 16 May 2010 01:05:45 -0700 Subject: [PATCH 3/3] rtnetlink: make SR-IOV VF interface symmetric Now we have a set of nested attributes: IFLA_VFINFO_LIST (NESTED) IFLA_VF_INFO (NESTED) IFLA_VF_MAC IFLA_VF_VLAN IFLA_VF_TX_RATE This allows a single set to operate on multiple attributes if desired. Among other things, it means a dump can be replayed to set state. The current interface has yet to be released, so this seems like something to consider for 2.6.34. Signed-off-by: Chris Wright Signed-off-by: David S. Miller --- include/linux/if_link.h | 23 +++++- net/core/rtnetlink.c | 159 +++++++++++++++++++++++++++------------- 2 files changed, 129 insertions(+), 53 deletions(-) diff --git a/include/linux/if_link.h b/include/linux/if_link.h index c9bf92cd7653..d94963b379d9 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -79,10 +79,7 @@ enum { IFLA_NET_NS_PID, IFLA_IFALIAS, IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ - IFLA_VF_MAC, /* Hardware queue specific attributes */ - IFLA_VF_VLAN, - IFLA_VF_TX_RATE, /* TX Bandwidth Allocation */ - IFLA_VFINFO, + IFLA_VFINFO_LIST, __IFLA_MAX }; @@ -203,6 +200,24 @@ enum macvlan_mode { /* SR-IOV virtual function managment section */ +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, + IFLA_VF_TX_RATE, /* TX Bandwidth Allocation */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + struct ifla_vf_mac { __u32 vf; __u8 mac[32]; /* MAX_ADDR_LEN */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fe776c9ddeca..31e85d327aa2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -602,12 +602,19 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; }; +/* All VF info */ static inline int rtnl_vfinfo_size(const struct net_device *dev) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) - return dev_num_vf(dev->dev.parent) * - sizeof(struct ifla_vf_info); - else + if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { + + int num_vfs = dev_num_vf(dev->dev.parent); + size_t size = nlmsg_total_size(sizeof(struct nlattr)); + size += nlmsg_total_size(num_vfs * sizeof(struct nlattr)); + size += num_vfs * (sizeof(struct ifla_vf_mac) + + sizeof(struct ifla_vf_vlan) + + sizeof(struct ifla_vf_tx_rate)); + return size; + } else return 0; } @@ -629,7 +636,7 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_NUM_VF */ - + nla_total_size(rtnl_vfinfo_size(dev)) /* IFLA_VFINFO */ + + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ } @@ -700,14 +707,37 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { int i; - struct ifla_vf_info ivi; - NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); - for (i = 0; i < dev_num_vf(dev->dev.parent); i++) { + struct nlattr *vfinfo, *vf; + int num_vfs = dev_num_vf(dev->dev.parent); + + NLA_PUT_U32(skb, IFLA_NUM_VF, num_vfs); + vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); + if (!vfinfo) + goto nla_put_failure; + for (i = 0; i < num_vfs; i++) { + struct ifla_vf_info ivi; + struct ifla_vf_mac vf_mac; + struct ifla_vf_vlan vf_vlan; + struct ifla_vf_tx_rate vf_tx_rate; if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) break; - NLA_PUT(skb, IFLA_VFINFO, sizeof(ivi), &ivi); + vf_mac.vf = vf_vlan.vf = vf_tx_rate.vf = ivi.vf; + memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); + vf_vlan.vlan = ivi.vlan; + vf_vlan.qos = ivi.qos; + vf_tx_rate.rate = ivi.tx_rate; + vf = nla_nest_start(skb, IFLA_VF_INFO); + if (!vf) { + nla_nest_cancel(skb, vfinfo); + goto nla_put_failure; + } + NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac); + NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan); + NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate); + nla_nest_end(skb, vf); } + nla_nest_end(skb, vfinfo); } if (dev->rtnl_link_ops) { if (rtnl_link_fill(skb, dev) < 0) @@ -769,12 +799,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINKINFO] = { .type = NLA_NESTED }, [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, - [IFLA_VF_MAC] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_mac) }, - [IFLA_VF_VLAN] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_vlan) }, - [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, - .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, }; EXPORT_SYMBOL(ifla_policy); @@ -783,6 +808,19 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; +static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = { + [IFLA_VF_INFO] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { + [IFLA_VF_MAC] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_tx_rate) }, +}; + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; @@ -812,6 +850,52 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return 0; } +static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) +{ + int rem, err = -EINVAL; + struct nlattr *vf; + const struct net_device_ops *ops = dev->netdev_ops; + + nla_for_each_nested(vf, attr, rem) { + switch (nla_type(vf)) { + case IFLA_VF_MAC: { + struct ifla_vf_mac *ivm; + ivm = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, + ivm->mac); + break; + } + case IFLA_VF_VLAN: { + struct ifla_vf_vlan *ivv; + ivv = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, + ivv->vlan, + ivv->qos); + break; + } + case IFLA_VF_TX_RATE: { + struct ifla_vf_tx_rate *ivt; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_tx_rate) + err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, + ivt->rate); + break; + } + default: + err = -EINVAL; + break; + } + if (err) + break; + } + return err; +} + static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { @@ -942,40 +1026,17 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, write_unlock_bh(&dev_base_lock); } - if (tb[IFLA_VF_MAC]) { - struct ifla_vf_mac *ivm; - ivm = nla_data(tb[IFLA_VF_MAC]); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_mac) - err = ops->ndo_set_vf_mac(dev, ivm->vf, ivm->mac); - if (err < 0) - goto errout; - modified = 1; - } - - if (tb[IFLA_VF_VLAN]) { - struct ifla_vf_vlan *ivv; - ivv = nla_data(tb[IFLA_VF_VLAN]); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_vlan) - err = ops->ndo_set_vf_vlan(dev, ivv->vf, - ivv->vlan, - ivv->qos); - if (err < 0) - goto errout; - modified = 1; - } - err = 0; - - if (tb[IFLA_VF_TX_RATE]) { - struct ifla_vf_tx_rate *ivt; - ivt = nla_data(tb[IFLA_VF_TX_RATE]); - err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, ivt->rate); - if (err < 0) - goto errout; - modified = 1; + if (tb[IFLA_VFINFO_LIST]) { + struct nlattr *attr; + int rem; + nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) { + if (nla_type(attr) != IFLA_VF_INFO) + goto errout; + err = do_setvfinfo(dev, attr); + if (err < 0) + goto errout; + modified = 1; + } } err = 0;