From e05273341c573f7b543f45c06e4a232c5b7c5a59 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Tue, 26 Jun 2012 21:43:19 -0700 Subject: infiniband: netlink: Move away from NLMSG_NEW(). And use nlmsg_data() while we're here too. Signed-off-by: David S. Miller --- drivers/infiniband/core/netlink.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index e497dfbee435..1e691dca1820 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -108,12 +108,14 @@ void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq, unsigned char *prev_tail; prev_tail = skb_tail_pointer(skb); - *nlh = NLMSG_NEW(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), - len, NLM_F_MULTI); + *nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), + len, NLM_F_MULTI); + if (!*nlh) + goto out_nlmsg_trim; (*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail; - return NLMSG_DATA(*nlh); + return nlmsg_data(*nlh); -nlmsg_failure: +out_nlmsg_trim: nlmsg_trim(skb, prev_tail); return NULL; } -- cgit v1.2.3 From a31f2d17b331db970259e875b7223d3aba7e3821 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 29 Jun 2012 06:15:21 +0000 Subject: netlink: add netlink_kernel_cfg parameter to netlink_kernel_create This patch adds the following structure: struct netlink_kernel_cfg { unsigned int groups; void (*input)(struct sk_buff *skb); struct mutex *cb_mutex; }; That can be passed to netlink_kernel_create to set optional configurations for netlink kernel sockets. I've populated this structure by looking for NULL and zero parameters at the existing code. The remaining parameters that always need to be set are still left in the original interface. That includes optional parameters for the netlink socket creation. This allows easy extensibility of this interface in the future. This patch also adapts all callers to use this new interface. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- crypto/crypto_user.c | 7 +++++-- drivers/connector/connector.c | 13 +++++++++---- drivers/infiniband/core/netlink.c | 7 +++++-- drivers/scsi/scsi_netlink.c | 7 +++++-- drivers/scsi/scsi_transport_iscsi.c | 9 ++++++--- drivers/staging/gdm72xx/netlink_k.c | 6 ++++-- include/linux/netlink.h | 15 ++++++++++----- kernel/audit.c | 7 +++++-- lib/kobject_uevent.c | 5 ++++- net/bridge/netfilter/ebt_ulog.c | 6 ++++-- net/core/rtnetlink.c | 9 +++++++-- net/core/sock_diag.c | 8 ++++++-- net/decnet/netfilter/dn_rtmsg.c | 8 +++++--- net/ipv4/fib_frontend.c | 7 +++++-- net/ipv4/netfilter/ipt_ULOG.c | 8 +++++--- net/netfilter/nfnetlink.c | 7 +++++-- net/netlink/af_netlink.c | 16 ++++++++++------ net/netlink/genetlink.c | 10 +++++++--- net/xfrm/xfrm_user.c | 7 +++++-- security/selinux/netlink.c | 6 +++++- 20 files changed, 117 insertions(+), 51 deletions(-) (limited to 'drivers/infiniband') diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 5a37eadb4e56..ba2c611154af 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -496,9 +496,12 @@ static void crypto_netlink_rcv(struct sk_buff *skb) static int __init crypto_user_init(void) { + struct netlink_kernel_cfg cfg = { + .input = crypto_netlink_rcv, + }; + crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, - 0, crypto_netlink_rcv, - NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!crypto_nlsk) return -ENOMEM; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 34e0e9e4d913..116cf8d02834 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -251,15 +251,20 @@ static const struct file_operations cn_file_ops = { .release = single_release }; +static struct cn_dev cdev = { + .input = cn_rx_skb, +}; + static int __devinit cn_init(void) { struct cn_dev *dev = &cdev; - - dev->input = cn_rx_skb; + struct netlink_kernel_cfg cfg = { + .groups = CN_NETLINK_USERS + 0xf, + .input = dev->input, + }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, - CN_NETLINK_USERS + 0xf, - dev->input, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!dev->nls) return -EIO; diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 1e691dca1820..3ae2bfd31015 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -173,8 +173,11 @@ static void ibnl_rcv(struct sk_buff *skb) int __init ibnl_init(void) { - nls = netlink_kernel_create(&init_net, NETLINK_RDMA, 0, ibnl_rcv, - NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = ibnl_rcv, + }; + + nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg); if (!nls) { pr_warn("Failed to create netlink socket\n"); return -ENOMEM; diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c index c77628afbf9f..8818dd681c19 100644 --- a/drivers/scsi/scsi_netlink.c +++ b/drivers/scsi/scsi_netlink.c @@ -486,6 +486,10 @@ void scsi_netlink_init(void) { int error; + struct netlink_kernel_cfg cfg = { + .input = scsi_nl_rcv_msg, + .groups = SCSI_NL_GRP_CNT, + }; INIT_LIST_HEAD(&scsi_nl_drivers); @@ -497,8 +501,7 @@ scsi_netlink_init(void) } scsi_nl_sock = netlink_kernel_create(&init_net, NETLINK_SCSITRANSPORT, - SCSI_NL_GRP_CNT, scsi_nl_rcv_msg, NULL, - THIS_MODULE); + THIS_MODULE, &cfg); if (!scsi_nl_sock) { printk(KERN_ERR "%s: register of receive handler failed\n", __func__); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 1cf640e575da..6042954d8f3b 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2936,7 +2936,10 @@ EXPORT_SYMBOL_GPL(iscsi_unregister_transport); static __init int iscsi_transport_init(void) { int err; - + struct netlink_kernel_cfg cfg = { + .groups = 1, + .input = iscsi_if_rx, + }; printk(KERN_INFO "Loading iSCSI transport class v%s.\n", ISCSI_TRANSPORT_VERSION); @@ -2966,8 +2969,8 @@ static __init int iscsi_transport_init(void) if (err) goto unregister_conn_class; - nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, 1, iscsi_if_rx, - NULL, THIS_MODULE); + nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, + THIS_MODULE, &cfg); if (!nls) { err = -ENOBUFS; goto unregister_session_class; diff --git a/drivers/staging/gdm72xx/netlink_k.c b/drivers/staging/gdm72xx/netlink_k.c index 2489bb5597ca..87c3a07ed80e 100644 --- a/drivers/staging/gdm72xx/netlink_k.c +++ b/drivers/staging/gdm72xx/netlink_k.c @@ -88,13 +88,15 @@ struct sock *netlink_init(int unit, void (*cb)(struct net_device *dev, u16 type, void *msg, int len)) { struct sock *sock; + struct netlink_kernel_cfg cfg = { + .input = netlink_rcv, + }; #if !defined(DEFINE_MUTEX) init_MUTEX(&netlink_mutex); #endif - sock = netlink_kernel_create(&init_net, unit, 0, netlink_rcv, NULL, - THIS_MODULE); + sock = netlink_kernel_create(&init_net, unit, THIS_MODULE, &cfg); if (sock) rcv_cb = cb; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index ed33f0901bc2..6085e4919cb3 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -174,11 +174,16 @@ struct netlink_skb_parms { extern void netlink_table_grab(void); extern void netlink_table_ungrab(void); -extern struct sock *netlink_kernel_create(struct net *net, - int unit,unsigned int groups, - void (*input)(struct sk_buff *skb), - struct mutex *cb_mutex, - struct module *module); +/* optional Netlink kernel configuration parameters */ +struct netlink_kernel_cfg { + unsigned int groups; + void (*input)(struct sk_buff *skb); + struct mutex *cb_mutex; +}; + +extern struct sock *netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg); extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/kernel/audit.c b/kernel/audit.c index 30b252a1fb61..4a3f28d2ca65 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -962,14 +962,17 @@ static void audit_receive(struct sk_buff *skb) static int __init audit_init(void) { int i; + struct netlink_kernel_cfg cfg = { + .input = audit_receive, + }; if (audit_initialized == AUDIT_DISABLED) return 0; printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); - audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0, - audit_receive, NULL, THIS_MODULE); + audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, + THIS_MODULE, &cfg); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 1a91efa6d121..0401d2916d9f 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -373,13 +373,16 @@ EXPORT_SYMBOL_GPL(add_uevent_var); static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; + struct netlink_kernel_cfg cfg = { + .groups = 1, + }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, - 1, NULL, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (!ue_sk->sk) { printk(KERN_ERR "kobject_uevent: unable to create netlink socket!\n"); diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 1bd173218f7b..374bdcd77039 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -282,6 +282,9 @@ static int __init ebt_ulog_init(void) { int ret; int i; + struct netlink_kernel_cfg cfg = { + .groups = EBT_ULOG_MAXNLGROUPS, + }; if (nlbufsiz >= 128*1024) { pr_warning("Netlink buffer has to be <= 128kB," @@ -296,8 +299,7 @@ static int __init ebt_ulog_init(void) } ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - EBT_ULOG_MAXNLGROUPS, NULL, NULL, - THIS_MODULE); + THIS_MODULE, &cfg); if (!ebtulognl) ret = -ENOMEM; else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bc8a1cdaac98..2b325c340b44 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2353,8 +2353,13 @@ static struct notifier_block rtnetlink_dev_notifier = { static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, - rtnetlink_rcv, &rtnl_mutex, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .groups = RTNLGRP_MAX, + .input = rtnetlink_rcv, + .cb_mutex = &rtnl_mutex, + }; + + sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index ff2967acbfae..07a29eb34a41 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -171,8 +171,12 @@ EXPORT_SYMBOL_GPL(sock_diag_nlsk); static int __init sock_diag_init(void) { - sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0, - sock_diag_rcv, NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = sock_diag_rcv, + }; + + sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, + THIS_MODULE, &cfg); return sock_diag_nlsk == NULL ? -ENOMEM : 0; } diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index b8f7f5b8c350..11db0ecf342f 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -125,11 +125,13 @@ static struct nf_hook_ops dnrmg_ops __read_mostly = { static int __init dn_rtmsg_init(void) { int rv = 0; + struct netlink_kernel_cfg cfg = { + .groups = DNRNG_NLGRP_MAX, + .input = dnrmg_receive_user_skb, + }; dnrmg = netlink_kernel_create(&init_net, - NETLINK_DNRTMSG, DNRNG_NLGRP_MAX, - dnrmg_receive_user_skb, - NULL, THIS_MODULE); + NETLINK_DNRTMSG, THIS_MODULE, &cfg); if (dnrmg == NULL) { printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); return -ENOMEM; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index ae528d1b293a..3e11ea225dad 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -976,8 +976,11 @@ static void nl_fib_input(struct sk_buff *skb) static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; - sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, 0, - nl_fib_input, NULL, THIS_MODULE); + struct netlink_kernel_cfg cfg = { + .input = nl_fib_input, + }; + + sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, THIS_MODULE, &cfg); if (sk == NULL) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 99b3f53f16a7..1109f7f6c254 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -381,6 +381,9 @@ static struct nf_logger ipt_ulog_logger __read_mostly = { static int __init ulog_tg_init(void) { int ret, i; + struct netlink_kernel_cfg cfg = { + .groups = ULOG_MAXNLGROUPS, + }; pr_debug("init module\n"); @@ -393,9 +396,8 @@ static int __init ulog_tg_init(void) for (i = 0; i < ULOG_MAXNLGROUPS; i++) setup_timer(&ulog_buffers[i].timer, ulog_timer, i); - nflognl = netlink_kernel_create(&init_net, - NETLINK_NFLOG, ULOG_MAXNLGROUPS, NULL, - NULL, THIS_MODULE); + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, + THIS_MODULE, &cfg); if (!nflognl) return -ENOMEM; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 3e797d1fcb94..700e4616a098 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -203,9 +203,12 @@ static void nfnetlink_rcv(struct sk_buff *skb) static int __net_init nfnetlink_net_init(struct net *net) { struct sock *nfnl; + struct netlink_kernel_cfg cfg = { + .groups = NFNLGRP_MAX, + .input = nfnetlink_rcv, + }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, NFNLGRP_MAX, - nfnetlink_rcv, NULL, THIS_MODULE); + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b3025a603d56..43a124feaad8 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1503,14 +1503,16 @@ static void netlink_data_ready(struct sock *sk, int len) */ struct sock * -netlink_kernel_create(struct net *net, int unit, unsigned int groups, - void (*input)(struct sk_buff *skb), - struct mutex *cb_mutex, struct module *module) +netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; + struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; + unsigned int groups; BUG_ON(!nl_table); @@ -1532,16 +1534,18 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups, sk = sock->sk; sk_change_net(sk, net); - if (groups < 32) + if (!cfg || cfg->groups < 32) groups = 32; + else + groups = cfg->groups; listeners = kzalloc(sizeof(*listeners) + NLGRPSZ(groups), GFP_KERNEL); if (!listeners) goto out_sock_release; sk->sk_data_ready = netlink_data_ready; - if (input) - nlk_sk(sk)->netlink_rcv = input; + if (cfg && cfg->input) + nlk_sk(sk)->netlink_rcv = cfg->input; if (netlink_insert(sk, net, 0)) goto out_sock_release; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2cc7c1ee7690..32761b53015e 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -915,10 +915,14 @@ static struct genl_multicast_group notify_grp = { static int __net_init genl_pernet_init(struct net *net) { + struct netlink_kernel_cfg cfg = { + .input = genl_rcv, + .cb_mutex = &genl_mutex, + }; + /* we'll bump the group number right afterwards */ - net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, 0, - genl_rcv, &genl_mutex, - THIS_MODULE); + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, + THIS_MODULE, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 540762726aaf..e75d8e47f35c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2959,9 +2959,12 @@ static struct xfrm_mgr netlink_mgr = { static int __net_init xfrm_user_net_init(struct net *net) { struct sock *nlsk; + struct netlink_kernel_cfg cfg = { + .groups = XFRMNLGRP_MAX, + .input = xfrm_netlink_rcv, + }; - nlsk = netlink_kernel_create(net, NETLINK_XFRM, XFRMNLGRP_MAX, - xfrm_netlink_rcv, NULL, THIS_MODULE); + nlsk = netlink_kernel_create(net, NETLINK_XFRM, THIS_MODULE, &cfg); if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c index 8a23a35b9c5b..8a77725423e0 100644 --- a/security/selinux/netlink.c +++ b/security/selinux/netlink.c @@ -111,8 +111,12 @@ void selnl_notify_policyload(u32 seqno) static int __init selnl_init(void) { + struct netlink_kernel_cfg cfg = { + .groups = SELNLGRP_MAX, + }; + selnl = netlink_kernel_create(&init_net, NETLINK_SELINUX, - SELNLGRP_MAX, NULL, NULL, THIS_MODULE); + THIS_MODULE, &cfg); if (selnl == NULL) panic("SELinux: Cannot create netlink socket."); netlink_set_nonroot(NETLINK_SELINUX, NL_NONROOT_RECV); -- cgit v1.2.3 From 178709bbfe9d4fe432c272ed65a34b8582703c23 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 2 Jul 2012 22:00:03 -0700 Subject: ipoib: Convert over to dev_lookup_neigh_skb(). Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_main.c | 4 +++- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 22 +++++++++++++--------- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 3974c290b667..bbee4b2d7a13 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -715,7 +715,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); if (likely(skb_dst(skb))) { - n = dst_get_neighbour_noref(skb_dst(skb)); + n = dst_neigh_lookup_skb(skb_dst(skb), skb); if (!n) { ++dev->stats.tx_dropped; dev_kfree_skb_any(skb); @@ -797,6 +797,8 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) } } unlock: + if (n) + neigh_release(n); rcu_read_unlock(); return NETDEV_TX_OK; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 20ebc6fd1bb9..fbb95ee538b2 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -720,16 +720,20 @@ out: rcu_read_lock(); if (dst) - n = dst_get_neighbour_noref(dst); - if (n && !*to_ipoib_neigh(n)) { - struct ipoib_neigh *neigh = ipoib_neigh_alloc(n, - skb->dev); - - if (neigh) { - kref_get(&mcast->ah->ref); - neigh->ah = mcast->ah; - list_add_tail(&neigh->list, &mcast->neigh_list); + n = dst_neigh_lookup_skb(dst, skb); + if (n) { + if (!*to_ipoib_neigh(n)) { + struct ipoib_neigh *neigh; + + neigh = ipoib_neigh_alloc(n, skb->dev); + if (neigh) { + kref_get(&mcast->ah->ref); + neigh->ah = mcast->ah; + list_add_tail(&neigh->list, + &mcast->neigh_list); + } } + neigh_release(n); } rcu_read_unlock(); spin_unlock_irqrestore(&priv->lock, flags); -- cgit v1.2.3 From 534cb283efef9fdbd9f70f4615054d26aa444dd6 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Mon, 2 Jul 2012 22:35:31 -0700 Subject: cxgb3: Convert t3_l2t_get() over to dst_neigh_lookup(). This means passing in a suitable destination address. Signed-off-by: David S. Miller --- drivers/infiniband/hw/cxgb3/iwch_cm.c | 5 +++-- drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c | 11 +++++++---- drivers/net/ethernet/chelsio/cxgb3/l2t.c | 6 ++++-- drivers/net/ethernet/chelsio/cxgb3/l2t.h | 2 +- drivers/scsi/cxgbi/cxgb3i/cxgb3i.c | 3 ++- 5 files changed, 17 insertions(+), 10 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index 740dcc065cf2..77b6b182778a 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -1374,7 +1374,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) goto reject; } dst = &rt->dst; - l2t = t3_l2t_get(tdev, dst, NULL); + l2t = t3_l2t_get(tdev, dst, NULL, &req->peer_ip); if (!l2t) { printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n", __func__); @@ -1942,7 +1942,8 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) goto fail3; } ep->dst = &rt->dst; - ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL); + ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL, + &cm_id->remote_addr.sin_addr.s_addr); if (!ep->l2t) { printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__); err = -ENOMEM; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c index 633c6029e53c..2dbbcbb450d3 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c @@ -63,7 +63,8 @@ static const unsigned int ATID_BASE = 0x10000; static void cxgb_neigh_update(struct neighbour *neigh); static void cxgb_redirect(struct dst_entry *old, struct neighbour *old_neigh, - struct dst_entry *new, struct neighbour *new_neigh); + struct dst_entry *new, struct neighbour *new_neigh, + const void *daddr); static inline int offload_activated(struct t3cdev *tdev) { @@ -970,7 +971,8 @@ static int nb_callback(struct notifier_block *self, unsigned long event, case (NETEVENT_REDIRECT):{ struct netevent_redirect *nr = ctx; cxgb_redirect(nr->old, nr->old_neigh, - nr->new, nr->new_neigh); + nr->new, nr->new_neigh, + nr->daddr); cxgb_neigh_update(nr->new_neigh); break; } @@ -1110,7 +1112,8 @@ static void set_l2t_ix(struct t3cdev *tdev, u32 tid, struct l2t_entry *e) } static void cxgb_redirect(struct dst_entry *old, struct neighbour *old_neigh, - struct dst_entry *new, struct neighbour *new_neigh) + struct dst_entry *new, struct neighbour *new_neigh, + const void *daddr) { struct net_device *olddev, *newdev; struct tid_info *ti; @@ -1139,7 +1142,7 @@ static void cxgb_redirect(struct dst_entry *old, struct neighbour *old_neigh, } /* Add new L2T entry */ - e = t3_l2t_get(tdev, new, newdev); + e = t3_l2t_get(tdev, new, newdev, daddr); if (!e) { printk(KERN_ERR "%s: couldn't allocate new l2t entry!\n", __func__); diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c index 3fa3c8833ed7..8d53438638b2 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c @@ -299,7 +299,7 @@ static inline void reuse_entry(struct l2t_entry *e, struct neighbour *neigh) } struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst, - struct net_device *dev) + struct net_device *dev, const void *daddr) { struct l2t_entry *e = NULL; struct neighbour *neigh; @@ -311,7 +311,7 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst, int smt_idx; rcu_read_lock(); - neigh = dst_get_neighbour_noref(dst); + neigh = dst_neigh_lookup(dst, daddr); if (!neigh) goto done_rcu; @@ -360,6 +360,8 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst, done_unlock: write_unlock_bh(&d->lock); done_rcu: + if (neigh) + neigh_release(neigh); rcu_read_unlock(); return e; } diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.h b/drivers/net/ethernet/chelsio/cxgb3/l2t.h index c4e864369751..8cffcdfd5678 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/l2t.h +++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.h @@ -110,7 +110,7 @@ static inline void set_arp_failure_handler(struct sk_buff *skb, void t3_l2e_free(struct l2t_data *d, struct l2t_entry *e); void t3_l2t_update(struct t3cdev *dev, struct neighbour *neigh); struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst, - struct net_device *dev); + struct net_device *dev, const void *daddr); int t3_l2t_send_slow(struct t3cdev *dev, struct sk_buff *skb, struct l2t_entry *e); void t3_l2t_send_event(struct t3cdev *dev, struct l2t_entry *e); diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c index 36739da8bc15..49692a1ac44a 100644 --- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c @@ -966,7 +966,8 @@ static int init_act_open(struct cxgbi_sock *csk) csk->saddr.sin_addr.s_addr = chba->ipv4addr; csk->rss_qid = 0; - csk->l2t = t3_l2t_get(t3dev, dst, ndev); + csk->l2t = t3_l2t_get(t3dev, dst, ndev, + &csk->daddr.sin_addr.s_addr); if (!csk->l2t) { pr_err("NO l2t available.\n"); return -EINVAL; -- cgit v1.2.3 From 700db99d0140e9da2a31e08ebd3e1b121691aa26 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Thu, 5 Jul 2012 21:08:05 -0700 Subject: ipoib: Need to do dst_neigh_lookup_skb() outside of priv->lock. Otherwise local_bh_enable() complains. Reported-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index fbb95ee538b2..7cecb16d3d48 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -658,9 +658,15 @@ static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb) { struct ipoib_dev_priv *priv = netdev_priv(dev); + struct dst_entry *dst = skb_dst(skb); struct ipoib_mcast *mcast; + struct neighbour *n; unsigned long flags; + n = NULL; + if (dst) + n = dst_neigh_lookup_skb(dst, skb); + spin_lock_irqsave(&priv->lock, flags); if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags) || @@ -715,12 +721,6 @@ void ipoib_mcast_send(struct net_device *dev, void *mgid, struct sk_buff *skb) out: if (mcast && mcast->ah) { - struct dst_entry *dst = skb_dst(skb); - struct neighbour *n = NULL; - - rcu_read_lock(); - if (dst) - n = dst_neigh_lookup_skb(dst, skb); if (n) { if (!*to_ipoib_neigh(n)) { struct ipoib_neigh *neigh; @@ -735,13 +735,14 @@ out: } neigh_release(n); } - rcu_read_unlock(); spin_unlock_irqrestore(&priv->lock, flags); ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN); return; } unlock: + if (n) + neigh_release(n); spin_unlock_irqrestore(&priv->lock, flags); } -- cgit v1.2.3 From 0ff1fb654bec0cff62ddf81a8a8edec4263604a0 Mon Sep 17 00:00:00 2001 From: Hadar Hen Zion Date: Thu, 5 Jul 2012 04:03:46 +0000 Subject: {NET, IB}/mlx4: Add device managed flow steering firmware API The driver is modified to support three operation modes. If supported by firmware use the device managed flow steering API, that which we call device managed steering mode. Else, if the firmware supports the B0 steering mode use it, and finally, if none of the above, use the A0 steering mode. When the steering mode is device managed, the code is modified such that L2 based rules set by the mlx4_en driver for Ethernet unicast and multicast, and the IB stack multicast attach calls done through the mlx4_ib driver are all routed to use the device managed API. When attaching rule using device managed flow steering API, the firmware returns a 64 bit registration id, which is to be provided during detach. Currently the firmware is always programmed during HCA initialization to use standard L2 hashing. Future work should be done to allow configuring the flow-steering hash function with common, non proprietary means. Signed-off-by: Hadar Hen Zion Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 62 +++- drivers/infiniband/hw/mlx4/mlx4_ib.h | 1 + drivers/infiniband/hw/mlx4/qp.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 21 +- drivers/net/ethernet/mellanox/mlx4/fw.c | 91 ++++- drivers/net/ethernet/mellanox/mlx4/fw.h | 3 + drivers/net/ethernet/mellanox/mlx4/main.c | 56 +++- drivers/net/ethernet/mellanox/mlx4/mcg.c | 365 ++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 13 + drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 + drivers/net/ethernet/mellanox/mlx4/port.c | 98 ++++-- drivers/net/ethernet/mellanox/mlx4/profile.c | 12 +- .../net/ethernet/mellanox/mlx4/resource_tracker.c | 6 + include/linux/mlx4/device.h | 108 +++++- 14 files changed, 758 insertions(+), 81 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 3530c41fcd1f..8a3a2037b005 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -718,26 +718,53 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp, return ret; } +struct mlx4_ib_steering { + struct list_head list; + u64 reg_id; + union ib_gid gid; +}; + static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) { int err; struct mlx4_ib_dev *mdev = to_mdev(ibqp->device); struct mlx4_ib_qp *mqp = to_mqp(ibqp); + u64 reg_id; + struct mlx4_ib_steering *ib_steering = NULL; + + if (mdev->dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL); + if (!ib_steering) + return -ENOMEM; + } - err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, - !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), - MLX4_PROT_IB_IPV6); + err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port, + !!(mqp->flags & + MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK), + MLX4_PROT_IB_IPV6, ®_id); if (err) - return err; + goto err_malloc; err = add_gid_entry(ibqp, gid); if (err) goto err_add; + if (ib_steering) { + memcpy(ib_steering->gid.raw, gid->raw, 16); + ib_steering->reg_id = reg_id; + mutex_lock(&mqp->mutex); + list_add(&ib_steering->list, &mqp->steering_rules); + mutex_unlock(&mqp->mutex); + } return 0; err_add: - mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6); + mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + MLX4_PROT_IB_IPV6, reg_id); +err_malloc: + kfree(ib_steering); + return err; } @@ -765,9 +792,30 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid) u8 mac[6]; struct net_device *ndev; struct mlx4_ib_gid_entry *ge; + u64 reg_id = 0; + + if (mdev->dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + struct mlx4_ib_steering *ib_steering; + + mutex_lock(&mqp->mutex); + list_for_each_entry(ib_steering, &mqp->steering_rules, list) { + if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) { + list_del(&ib_steering->list); + break; + } + } + mutex_unlock(&mqp->mutex); + if (&ib_steering->list == &mqp->steering_rules) { + pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n"); + return -EINVAL; + } + reg_id = ib_steering->reg_id; + kfree(ib_steering); + } - err = mlx4_multicast_detach(mdev->dev, - &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6); + err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, + MLX4_PROT_IB_IPV6, reg_id); if (err) return err; diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index ff36655d23d3..42df4f7a6a5b 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -163,6 +163,7 @@ struct mlx4_ib_qp { u8 state; int mlx_type; struct list_head gid_list; + struct list_head steering_rules; }; struct mlx4_ib_srq { diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 8d4ed24aef93..6af19f6c2b11 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -495,6 +495,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, spin_lock_init(&qp->sq.lock); spin_lock_init(&qp->rq.lock); INIT_LIST_HEAD(&qp->gid_list); + INIT_LIST_HEAD(&qp->steering_rules); qp->state = IB_QPS_RESET; if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 44ff7cdb15e5..eb5ed8e39873 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -463,7 +463,8 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) err = mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - MLX4_PROT_ETH); + MLX4_PROT_ETH, + mclist->reg_id); if (err) en_err(priv, "Fail to detach multicast address\n"); @@ -475,11 +476,14 @@ static void mlx4_en_do_set_multicast(struct work_struct *work) if (mclist->action == MCLIST_ADD) { /* attach the address */ memcpy(&mc_list[10], mclist->addr, ETH_ALEN); + /* needed for B0 steering support */ mc_list[5] = priv->port; err = mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, - mc_list, 0, - MLX4_PROT_ETH); + mc_list, + priv->port, 0, + MLX4_PROT_ETH, + &mclist->reg_id); if (err) en_err(priv, "Fail to attach multicast address\n"); @@ -827,9 +831,10 @@ int mlx4_en_start_port(struct net_device *dev) /* Attach rx QP to bradcast address */ memset(&mc_list[10], 0xff, ETH_ALEN); - mc_list[5] = priv->port; + mc_list[5] = priv->port; /* needed for B0 steering support */ if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - 0, MLX4_PROT_ETH)) + priv->port, 0, MLX4_PROT_ETH, + &priv->broadcast_id)) mlx4_warn(mdev, "Failed Attaching Broadcast\n"); /* Must redo promiscuous mode setup. */ @@ -886,14 +891,14 @@ void mlx4_en_stop_port(struct net_device *dev) /* Detach All multicasts */ memset(&mc_list[10], 0xff, ETH_ALEN); - mc_list[5] = priv->port; + mc_list[5] = priv->port; /* needed for B0 steering support */ mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list, - MLX4_PROT_ETH); + MLX4_PROT_ETH, priv->broadcast_id); list_for_each_entry(mclist, &priv->curr_list, list) { memcpy(&mc_list[10], mclist->addr, ETH_ALEN); mc_list[5] = priv->port; mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, - mc_list, MLX4_PROT_ETH); + mc_list, MLX4_PROT_ETH, mclist->reg_id); } mlx4_en_clear_list(dev); list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 40e048bac024..1d70657058a5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -123,7 +123,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) static const char * const fname[] = { [0] = "RSS support", [1] = "RSS Toeplitz Hash Function support", - [2] = "RSS XOR Hash Function support" + [2] = "RSS XOR Hash Function support", + [3] = "Device manage flow steering support" }; int i; @@ -391,6 +392,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_RSVD_XRC_OFFSET 0x66 #define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68 +#define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76 +#define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80 #define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET 0x82 #define QUERY_DEV_CAP_AUX_ENTRY_SZ_OFFSET 0x84 @@ -474,6 +477,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->num_ports = field & 0xf; MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MSG_SZ_OFFSET); dev_cap->max_msg_sz = 1 << (field & 0x1f); + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET); + if (field & 0x80) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN; + dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f; + MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET); + dev_cap->fs_max_num_qp_per_entry = field; MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET); dev_cap->stat_rate_support = stat_rate; MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET); @@ -1061,6 +1070,15 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) +#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 +#define INIT_HCA_FS_PARAM_OFFSET 0x1d0 +#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) +#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) +#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b) +#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21) +#define INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22) +#define INIT_HCA_FS_IB_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x25) +#define INIT_HCA_FS_IB_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x26) #define INIT_HCA_TPT_OFFSET 0x0f0 #define INIT_HCA_DMPT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x00) #define INIT_HCA_LOG_MPT_SZ_OFFSET (INIT_HCA_TPT_OFFSET + 0x0b) @@ -1119,14 +1137,44 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) MLX4_PUT(inbox, param->rdmarc_base, INIT_HCA_RDMARC_BASE_OFFSET); MLX4_PUT(inbox, param->log_rd_per_qp, INIT_HCA_LOG_RD_OFFSET); - /* multicast attributes */ - - MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET); - MLX4_PUT(inbox, param->log_mc_entry_sz, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); - MLX4_PUT(inbox, param->log_mc_hash_sz, INIT_HCA_LOG_MC_HASH_SZ_OFFSET); - if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0) - MLX4_PUT(inbox, (u8) (1 << 3), INIT_HCA_UC_STEERING_OFFSET); - MLX4_PUT(inbox, param->log_mc_table_sz, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + /* steering attributes */ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |= + cpu_to_be32(1 << + INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN); + + MLX4_PUT(inbox, param->mc_base, INIT_HCA_FS_BASE_OFFSET); + MLX4_PUT(inbox, param->log_mc_entry_sz, + INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_table_sz, + INIT_HCA_FS_LOG_TABLE_SZ_OFFSET); + /* Enable Ethernet flow steering + * with udp unicast and tcp unicast + */ + MLX4_PUT(inbox, param->fs_hash_enable_bits, + INIT_HCA_FS_ETH_BITS_OFFSET); + MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR, + INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET); + /* Enable IPoIB flow steering + * with udp unicast and tcp unicast + */ + MLX4_PUT(inbox, param->fs_hash_enable_bits, + INIT_HCA_FS_IB_BITS_OFFSET); + MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR, + INIT_HCA_FS_IB_NUM_ADDRS_OFFSET); + } else { + MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET); + MLX4_PUT(inbox, param->log_mc_entry_sz, + INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_hash_sz, + INIT_HCA_LOG_MC_HASH_SZ_OFFSET); + MLX4_PUT(inbox, param->log_mc_table_sz, + INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0) + MLX4_PUT(inbox, (u8) (1 << 3), + INIT_HCA_UC_STEERING_OFFSET); + } /* TPT attributes */ @@ -1188,15 +1236,24 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev, MLX4_GET(param->rdmarc_base, outbox, INIT_HCA_RDMARC_BASE_OFFSET); MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET); - /* multicast attributes */ + /* steering attributes */ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { - MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET); - MLX4_GET(param->log_mc_entry_sz, outbox, - INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); - MLX4_GET(param->log_mc_hash_sz, outbox, - INIT_HCA_LOG_MC_HASH_SZ_OFFSET); - MLX4_GET(param->log_mc_table_sz, outbox, - INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET); + MLX4_GET(param->log_mc_entry_sz, outbox, + INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET); + MLX4_GET(param->log_mc_table_sz, outbox, + INIT_HCA_FS_LOG_TABLE_SZ_OFFSET); + } else { + MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET); + MLX4_GET(param->log_mc_entry_sz, outbox, + INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET); + MLX4_GET(param->log_mc_hash_sz, outbox, + INIT_HCA_LOG_MC_HASH_SZ_OFFSET); + MLX4_GET(param->log_mc_table_sz, outbox, + INIT_HCA_LOG_MC_TABLE_SZ_OFFSET); + } /* TPT attributes */ diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index 64c0399e4b78..83fcbbf1b169 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -78,6 +78,8 @@ struct mlx4_dev_cap { u16 wavelength[MLX4_MAX_PORTS + 1]; u64 trans_code[MLX4_MAX_PORTS + 1]; u16 stat_rate_support; + int fs_log_max_ucast_qp_range_size; + int fs_max_num_qp_per_entry; u64 flags; u64 flags2; int reserved_uars; @@ -165,6 +167,7 @@ struct mlx4_init_hca_param { u8 log_mpt_sz; u8 log_uar_sz; u8 uar_page_sz; /* log pg sz in 4k chunks */ + u8 fs_hash_enable_bits; }; struct mlx4_init_ib_param { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f8125a82c0cb..42645166bae2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -91,7 +91,9 @@ module_param_named(log_num_mgm_entry_size, MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num" " of qp per mcg, for example:" " 10 gives 248.range: 9<=" - " log_num_mgm_entry_size <= 12"); + " log_num_mgm_entry_size <= 12." + " Not in use with device managed" + " flow steering"); #define MLX4_VF (1 << 0) @@ -274,20 +276,27 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER && - dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) { - dev->caps.steering_mode = MLX4_STEERING_MODE_B0; + if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) { + dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED; + dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry; + dev->caps.fs_log_max_ucast_qp_range_size = + dev_cap->fs_log_max_ucast_qp_range_size; } else { - dev->caps.steering_mode = MLX4_STEERING_MODE_A0; + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER && + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) { + dev->caps.steering_mode = MLX4_STEERING_MODE_B0; + } else { + dev->caps.steering_mode = MLX4_STEERING_MODE_A0; - if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || - dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) - mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags " - "set to use B0 steering. Falling back to A0 steering mode.\n"); + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER || + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) + mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags " + "set to use B0 steering. Falling back to A0 steering mode.\n"); + } + dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); } mlx4_dbg(dev, "Steering mode is: %s\n", mlx4_steering_mode_str(dev->caps.steering_mode)); - dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev); /* Sense port always allowed on supported devices for ConnectX1 and 2 */ if (dev->pdev->device != 0x1003) @@ -982,9 +991,11 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap, } /* - * It's not strictly required, but for simplicity just map the - * whole multicast group table now. The table isn't very big - * and it's a lot easier than trying to track ref counts. + * For flow steering device managed mode it is required to use + * mlx4_init_icm_table. For B0 steering mode it's not strictly + * required, but for simplicity just map the whole multicast + * group table now. The table isn't very big and it's a lot + * easier than trying to track ref counts. */ err = mlx4_init_icm_table(dev, &priv->mcg_table.table, init_hca->mc_base, @@ -1220,7 +1231,26 @@ static int mlx4_init_hca(struct mlx4_dev *dev) goto err_stop_fw; } + priv->fs_hash_mode = MLX4_FS_L2_HASH; + + switch (priv->fs_hash_mode) { + case MLX4_FS_L2_HASH: + init_hca.fs_hash_enable_bits = 0; + break; + + case MLX4_FS_L2_L3_L4_HASH: + /* Enable flow steering with + * udp unicast and tcp unicast + */ + init_hca.fs_hash_enable_bits = + MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN; + break; + } + profile = default_profile; + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + profile.num_mcg = MLX4_FS_NUM_MCG; icm_size = mlx4_make_profile(dev, &profile, &dev_cap, &init_hca); diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 3c59a33a98a5..768a2a4530e8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -41,6 +41,7 @@ #define MGM_QPN_MASK 0x00FFFFFF #define MGM_BLCK_LB_BIT 30 +#define MLX4_MAC_MASK 0xffffffffffffULL static const u8 zero_gid[16]; /* automatically initialized to 0 */ @@ -54,7 +55,12 @@ struct mlx4_mgm { int mlx4_get_mgm_entry_size(struct mlx4_dev *dev) { - return min((1 << mlx4_log_num_mgm_entry_size), MLX4_MAX_MGM_ENTRY_SIZE); + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE; + else + return min((1 << mlx4_log_num_mgm_entry_size), + MLX4_MAX_MGM_ENTRY_SIZE); } int mlx4_get_qp_per_mgm(struct mlx4_dev *dev) @@ -643,6 +649,311 @@ static int find_entry(struct mlx4_dev *dev, u8 port, return err; } +struct mlx4_net_trans_rule_hw_ctrl { + __be32 ctrl; + __be32 vf_vep_port; + __be32 qpn; + __be32 reserved; +}; + +static void trans_rule_ctrl_to_hw(struct mlx4_net_trans_rule *ctrl, + struct mlx4_net_trans_rule_hw_ctrl *hw) +{ + static const u8 __promisc_mode[] = { + [MLX4_FS_PROMISC_NONE] = 0x0, + [MLX4_FS_PROMISC_UPLINK] = 0x1, + [MLX4_FS_PROMISC_FUNCTION_PORT] = 0x2, + [MLX4_FS_PROMISC_ALL_MULTI] = 0x3, + }; + + u32 dw = 0; + + dw = ctrl->queue_mode == MLX4_NET_TRANS_Q_LIFO ? 1 : 0; + dw |= ctrl->exclusive ? (1 << 2) : 0; + dw |= ctrl->allow_loopback ? (1 << 3) : 0; + dw |= __promisc_mode[ctrl->promisc_mode] << 8; + dw |= ctrl->priority << 16; + + hw->ctrl = cpu_to_be32(dw); + hw->vf_vep_port = cpu_to_be32(ctrl->port); + hw->qpn = cpu_to_be32(ctrl->qpn); +} + +struct mlx4_net_trans_rule_hw_ib { + u8 size; + u8 rsvd1; + __be16 id; + u32 rsvd2; + __be32 qpn; + __be32 qpn_mask; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +} __packed; + +struct mlx4_net_trans_rule_hw_eth { + u8 size; + u8 rsvd; + __be16 id; + u8 rsvd1[6]; + u8 dst_mac[6]; + u16 rsvd2; + u8 dst_mac_msk[6]; + u16 rsvd3; + u8 src_mac[6]; + u16 rsvd4; + u8 src_mac_msk[6]; + u8 rsvd5; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +} __packed; + +struct mlx4_net_trans_rule_hw_tcp_udp { + u8 size; + u8 rsvd; + __be16 id; + __be16 rsvd1[3]; + __be16 dst_port; + __be16 rsvd2; + __be16 dst_port_msk; + __be16 rsvd3; + __be16 src_port; + __be16 rsvd4; + __be16 src_port_msk; +} __packed; + +struct mlx4_net_trans_rule_hw_ipv4 { + u8 size; + u8 rsvd; + __be16 id; + __be32 rsvd1; + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +} __packed; + +struct _rule_hw { + union { + struct { + u8 size; + u8 rsvd; + __be16 id; + }; + struct mlx4_net_trans_rule_hw_eth eth; + struct mlx4_net_trans_rule_hw_ib ib; + struct mlx4_net_trans_rule_hw_ipv4 ipv4; + struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp; + }; +}; + +static int parse_trans_rule(struct mlx4_dev *dev, struct mlx4_spec_list *spec, + struct _rule_hw *rule_hw) +{ + static const u16 __sw_id_hw[] = { + [MLX4_NET_TRANS_RULE_ID_ETH] = 0xE001, + [MLX4_NET_TRANS_RULE_ID_IB] = 0xE005, + [MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003, + [MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002, + [MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004, + [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006 + }; + + static const size_t __rule_hw_sz[] = { + [MLX4_NET_TRANS_RULE_ID_ETH] = + sizeof(struct mlx4_net_trans_rule_hw_eth), + [MLX4_NET_TRANS_RULE_ID_IB] = + sizeof(struct mlx4_net_trans_rule_hw_ib), + [MLX4_NET_TRANS_RULE_ID_IPV6] = 0, + [MLX4_NET_TRANS_RULE_ID_IPV4] = + sizeof(struct mlx4_net_trans_rule_hw_ipv4), + [MLX4_NET_TRANS_RULE_ID_TCP] = + sizeof(struct mlx4_net_trans_rule_hw_tcp_udp), + [MLX4_NET_TRANS_RULE_ID_UDP] = + sizeof(struct mlx4_net_trans_rule_hw_tcp_udp) + }; + if (spec->id > MLX4_NET_TRANS_RULE_NUM) { + mlx4_err(dev, "Invalid network rule id. id = %d\n", spec->id); + return -EINVAL; + } + memset(rule_hw, 0, __rule_hw_sz[spec->id]); + rule_hw->id = cpu_to_be16(__sw_id_hw[spec->id]); + rule_hw->size = __rule_hw_sz[spec->id] >> 2; + + switch (spec->id) { + case MLX4_NET_TRANS_RULE_ID_ETH: + memcpy(rule_hw->eth.dst_mac, spec->eth.dst_mac, ETH_ALEN); + memcpy(rule_hw->eth.dst_mac_msk, spec->eth.dst_mac_msk, + ETH_ALEN); + memcpy(rule_hw->eth.src_mac, spec->eth.src_mac, ETH_ALEN); + memcpy(rule_hw->eth.src_mac_msk, spec->eth.src_mac_msk, + ETH_ALEN); + if (spec->eth.ether_type_enable) { + rule_hw->eth.ether_type_enable = 1; + rule_hw->eth.ether_type = spec->eth.ether_type; + } + rule_hw->eth.vlan_id = spec->eth.vlan_id; + rule_hw->eth.vlan_id_msk = spec->eth.vlan_id_msk; + break; + + case MLX4_NET_TRANS_RULE_ID_IB: + rule_hw->ib.qpn = spec->ib.r_qpn; + rule_hw->ib.qpn_mask = spec->ib.qpn_msk; + memcpy(&rule_hw->ib.dst_gid, &spec->ib.dst_gid, 16); + memcpy(&rule_hw->ib.dst_gid_msk, &spec->ib.dst_gid_msk, 16); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV6: + return -EOPNOTSUPP; + + case MLX4_NET_TRANS_RULE_ID_IPV4: + rule_hw->ipv4.src_ip = spec->ipv4.src_ip; + rule_hw->ipv4.src_ip_msk = spec->ipv4.src_ip_msk; + rule_hw->ipv4.dst_ip = spec->ipv4.dst_ip; + rule_hw->ipv4.dst_ip_msk = spec->ipv4.dst_ip_msk; + break; + + case MLX4_NET_TRANS_RULE_ID_TCP: + case MLX4_NET_TRANS_RULE_ID_UDP: + rule_hw->tcp_udp.dst_port = spec->tcp_udp.dst_port; + rule_hw->tcp_udp.dst_port_msk = spec->tcp_udp.dst_port_msk; + rule_hw->tcp_udp.src_port = spec->tcp_udp.src_port; + rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk; + break; + + default: + return -EINVAL; + } + + return __rule_hw_sz[spec->id]; +} + +static void mlx4_err_rule(struct mlx4_dev *dev, char *str, + struct mlx4_net_trans_rule *rule) +{ +#define BUF_SIZE 256 + struct mlx4_spec_list *cur; + char buf[BUF_SIZE]; + int len = 0; + + mlx4_err(dev, "%s", str); + len += snprintf(buf + len, BUF_SIZE - len, + "port = %d prio = 0x%x qp = 0x%x ", + rule->port, rule->priority, rule->qpn); + + list_for_each_entry(cur, &rule->list, list) { + switch (cur->id) { + case MLX4_NET_TRANS_RULE_ID_ETH: + len += snprintf(buf + len, BUF_SIZE - len, + "dmac = %pM ", &cur->eth.dst_mac); + if (cur->eth.ether_type) + len += snprintf(buf + len, BUF_SIZE - len, + "ethertype = 0x%x ", + be16_to_cpu(cur->eth.ether_type)); + if (cur->eth.vlan_id) + len += snprintf(buf + len, BUF_SIZE - len, + "vlan-id = %d ", + be16_to_cpu(cur->eth.vlan_id)); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV4: + if (cur->ipv4.src_ip) + len += snprintf(buf + len, BUF_SIZE - len, + "src-ip = %pI4 ", + &cur->ipv4.src_ip); + if (cur->ipv4.dst_ip) + len += snprintf(buf + len, BUF_SIZE - len, + "dst-ip = %pI4 ", + &cur->ipv4.dst_ip); + break; + + case MLX4_NET_TRANS_RULE_ID_TCP: + case MLX4_NET_TRANS_RULE_ID_UDP: + if (cur->tcp_udp.src_port) + len += snprintf(buf + len, BUF_SIZE - len, + "src-port = %d ", + be16_to_cpu(cur->tcp_udp.src_port)); + if (cur->tcp_udp.dst_port) + len += snprintf(buf + len, BUF_SIZE - len, + "dst-port = %d ", + be16_to_cpu(cur->tcp_udp.dst_port)); + break; + + case MLX4_NET_TRANS_RULE_ID_IB: + len += snprintf(buf + len, BUF_SIZE - len, + "dst-gid = %pI6\n", cur->ib.dst_gid); + len += snprintf(buf + len, BUF_SIZE - len, + "dst-gid-mask = %pI6\n", + cur->ib.dst_gid_msk); + break; + + case MLX4_NET_TRANS_RULE_ID_IPV6: + break; + + default: + break; + } + } + len += snprintf(buf + len, BUF_SIZE - len, "\n"); + mlx4_err(dev, "%s", buf); + + if (len >= BUF_SIZE) + mlx4_err(dev, "Network rule error message was truncated, print buffer is too small.\n"); +} + +int mlx4_flow_attach(struct mlx4_dev *dev, + struct mlx4_net_trans_rule *rule, u64 *reg_id) +{ + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_spec_list *cur; + u32 size = 0; + int ret; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + memset(mailbox->buf, 0, sizeof(struct mlx4_net_trans_rule_hw_ctrl)); + trans_rule_ctrl_to_hw(rule, mailbox->buf); + + size += sizeof(struct mlx4_net_trans_rule_hw_ctrl); + + list_for_each_entry(cur, &rule->list, list) { + ret = parse_trans_rule(dev, cur, mailbox->buf + size); + if (ret < 0) { + mlx4_free_cmd_mailbox(dev, mailbox); + return -EINVAL; + } + size += ret; + } + + ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id); + if (ret == -ENOMEM) + mlx4_err_rule(dev, + "mcg table is full. Fail to register network rule.\n", + rule); + else if (ret) + mlx4_err_rule(dev, "Fail to register network rule.\n", rule); + + mlx4_free_cmd_mailbox(dev, mailbox); + + return ret; +} +EXPORT_SYMBOL_GPL(mlx4_flow_attach); + +int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) +{ + int err; + + err = mlx4_QP_FLOW_STEERING_DETACH(dev, reg_id); + if (err) + mlx4_err(dev, "Fail to detach network rule. registration id = 0x%llx\n", + reg_id); + return err; +} +EXPORT_SYMBOL_GPL(mlx4_flow_detach); + int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int block_mcast_loopback, enum mlx4_protocol prot, enum mlx4_steer_type steer) @@ -895,7 +1206,8 @@ static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp, } int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - int block_mcast_loopback, enum mlx4_protocol prot) + u8 port, int block_mcast_loopback, + enum mlx4_protocol prot, u64 *reg_id) { switch (dev->caps.steering_mode) { @@ -914,6 +1226,42 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], block_mcast_loopback, prot, MLX4_MC_STEER); + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + struct mlx4_spec_list spec = { {NULL} }; + __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .promisc_mode = MLX4_FS_PROMISC_NONE, + .priority = MLX4_DOMAIN_NIC, + }; + + rule.allow_loopback = ~block_mcast_loopback; + rule.port = port; + rule.qpn = qp->qpn; + INIT_LIST_HEAD(&rule.list); + + switch (prot) { + case MLX4_PROT_ETH: + spec.id = MLX4_NET_TRANS_RULE_ID_ETH; + memcpy(spec.eth.dst_mac, &gid[10], ETH_ALEN); + memcpy(spec.eth.dst_mac_msk, &mac_mask, ETH_ALEN); + break; + + case MLX4_PROT_IB_IPV6: + spec.id = MLX4_NET_TRANS_RULE_ID_IB; + memcpy(spec.ib.dst_gid, gid, 16); + memset(&spec.ib.dst_gid_msk, 0xff, 16); + break; + default: + return -EINVAL; + } + list_add_tail(&spec.list, &rule.list); + + return mlx4_flow_attach(dev, &rule, reg_id); + } + default: return -EINVAL; } @@ -921,7 +1269,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], EXPORT_SYMBOL_GPL(mlx4_multicast_attach); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - enum mlx4_protocol prot) + enum mlx4_protocol prot, u64 reg_id) { switch (dev->caps.steering_mode) { case MLX4_STEERING_MODE_A0: @@ -938,6 +1286,9 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], return mlx4_qp_detach_common(dev, qp, gid, prot, MLX4_MC_STEER); + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return mlx4_flow_detach(dev, reg_id); + default: return -EINVAL; } @@ -1042,6 +1393,10 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int err; + /* No need for mcg_table when fw managed the mcg table*/ + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) + return 0; err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms, dev->caps.num_amgms - 1, 0, 0); if (err) @@ -1054,5 +1409,7 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) void mlx4_cleanup_mcg_table(struct mlx4_dev *dev) { - mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap); + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index c07e882e8369..0084967be19e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -54,6 +54,17 @@ #define DRV_VERSION "1.1" #define DRV_RELDATE "Dec, 2011" +#define MLX4_FS_UDP_UC_EN (1 << 1) +#define MLX4_FS_TCP_UC_EN (1 << 2) +#define MLX4_FS_NUM_OF_L2_ADDR 8 +#define MLX4_FS_MGM_LOG_ENTRY_SIZE 7 +#define MLX4_FS_NUM_MCG (1 << 17) + +enum { + MLX4_FS_L2_HASH = 0, + MLX4_FS_L2_L3_L4_HASH, +}; + #define MLX4_NUM_UP 8 #define MLX4_NUM_TC 8 #define MLX4_RATELIMIT_UNITS 3 /* 100 Mbps */ @@ -704,6 +715,7 @@ struct mlx4_set_port_rqp_calc_context { struct mlx4_mac_entry { u64 mac; + u64 reg_id; }; struct mlx4_port_info { @@ -777,6 +789,7 @@ struct mlx4_priv { struct mutex bf_mutex; struct io_mapping *bf_mapping; int reserved_mtts; + int fs_hash_mode; }; static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 1bb00cd22d42..2d6dabe7f55d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -414,6 +414,7 @@ struct mlx4_en_mc_list { struct list_head list; enum mlx4_en_mclist_act action; u8 addr[ETH_ALEN]; + u64 reg_id; }; struct mlx4_en_frag_info { @@ -503,6 +504,7 @@ struct mlx4_en_priv { u64 stats_bitmap; struct list_head mc_list; struct list_head curr_list; + u64 broadcast_id; struct mlx4_en_stat_out_mbox hw_stats; int vids[128]; bool wol; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 58de7237f57a..a51d1b9bf1d1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -75,21 +75,54 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table) table->total = 0; } -static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) +static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, + u64 mac, int *qpn, u64 *reg_id) { - struct mlx4_qp qp; - u8 gid[16] = {0}; __be64 be_mac; int err; - qp.qpn = *qpn; - - mac &= 0xffffffffffffULL; + mac &= MLX4_MAC_MASK; be_mac = cpu_to_be64(mac << 16); - memcpy(&gid[10], &be_mac, ETH_ALEN); - gid[5] = port; - err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH); + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: { + struct mlx4_qp qp; + u8 gid[16] = {0}; + + qp.qpn = *qpn; + memcpy(&gid[10], &be_mac, ETH_ALEN); + gid[5] = port; + + err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH); + break; + } + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + struct mlx4_spec_list spec_eth = { {NULL} }; + __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16); + + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + .promisc_mode = MLX4_FS_PROMISC_NONE, + .priority = MLX4_DOMAIN_NIC, + }; + + rule.port = port; + rule.qpn = *qpn; + INIT_LIST_HEAD(&rule.list); + + spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH; + memcpy(spec_eth.eth.dst_mac, &be_mac, ETH_ALEN); + memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN); + list_add_tail(&spec_eth.list, &rule.list); + + err = mlx4_flow_attach(dev, &rule, reg_id); + break; + } + default: + return -EINVAL; + } if (err) mlx4_warn(dev, "Failed Attaching Unicast\n"); @@ -97,19 +130,30 @@ static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) } static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port, - u64 mac, int qpn) + u64 mac, int qpn, u64 reg_id) { - struct mlx4_qp qp; - u8 gid[16] = {0}; - __be64 be_mac; + switch (dev->caps.steering_mode) { + case MLX4_STEERING_MODE_B0: { + struct mlx4_qp qp; + u8 gid[16] = {0}; + __be64 be_mac; - qp.qpn = qpn; - mac &= 0xffffffffffffULL; - be_mac = cpu_to_be64(mac << 16); - memcpy(&gid[10], &be_mac, ETH_ALEN); - gid[5] = port; + qp.qpn = qpn; + mac &= MLX4_MAC_MASK; + be_mac = cpu_to_be64(mac << 16); + memcpy(&gid[10], &be_mac, ETH_ALEN); + gid[5] = port; - mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH); + mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH); + break; + } + case MLX4_STEERING_MODE_DEVICE_MANAGED: { + mlx4_flow_detach(dev, reg_id); + break; + } + default: + mlx4_err(dev, "Invalid steering mode.\n"); + } } static int validate_index(struct mlx4_dev *dev, @@ -144,6 +188,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) struct mlx4_mac_entry *entry; int index = 0; int err = 0; + u64 reg_id; mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n", (unsigned long long) mac); @@ -167,7 +212,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) goto qp_err; } - err = mlx4_uc_steer_add(dev, port, mac, qpn); + err = mlx4_uc_steer_add(dev, port, mac, qpn, ®_id); if (err) goto steer_err; @@ -177,6 +222,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn) goto alloc_err; } entry->mac = mac; + entry->reg_id = reg_id; err = radix_tree_insert(&info->mac_tree, *qpn, entry); if (err) goto insert_err; @@ -186,7 +232,7 @@ insert_err: kfree(entry); alloc_err: - mlx4_uc_steer_release(dev, port, mac, *qpn); + mlx4_uc_steer_release(dev, port, mac, *qpn, reg_id); steer_err: mlx4_qp_release_range(dev, *qpn, 1); @@ -212,7 +258,8 @@ void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn) mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx," " qpn %d\n", port, (unsigned long long) mac, qpn); - mlx4_uc_steer_release(dev, port, entry->mac, qpn); + mlx4_uc_steer_release(dev, port, entry->mac, + qpn, entry->reg_id); mlx4_qp_release_range(dev, qpn, 1); radix_tree_delete(&info->mac_tree, qpn); kfree(entry); @@ -363,11 +410,14 @@ int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac) entry = radix_tree_lookup(&info->mac_tree, qpn); if (!entry) return -EINVAL; - mlx4_uc_steer_release(dev, port, entry->mac, qpn); + mlx4_uc_steer_release(dev, port, entry->mac, + qpn, entry->reg_id); mlx4_unregister_mac(dev, port, entry->mac); entry->mac = new_mac; + entry->reg_id = 0; mlx4_register_mac(dev, port, new_mac); - err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn); + err = mlx4_uc_steer_add(dev, port, entry->mac, + &qpn, &entry->reg_id); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c index b83bc928d52a..9ee4725363d5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/profile.c +++ b/drivers/net/ethernet/mellanox/mlx4/profile.c @@ -237,13 +237,19 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, init_hca->mtt_base = profile[i].start; break; case MLX4_RES_MCG: - dev->caps.num_mgms = profile[i].num >> 1; - dev->caps.num_amgms = profile[i].num >> 1; init_hca->mc_base = profile[i].start; init_hca->log_mc_entry_sz = ilog2(mlx4_get_mgm_entry_size(dev)); init_hca->log_mc_table_sz = profile[i].log_num; - init_hca->log_mc_hash_sz = profile[i].log_num - 1; + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + dev->caps.num_mgms = profile[i].num; + } else { + init_hca->log_mc_hash_sz = + profile[i].log_num - 1; + dev->caps.num_mgms = profile[i].num >> 1; + dev->caps.num_amgms = profile[i].num >> 1; + } break; default: break; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index a8ca960f4620..5a6f3555d806 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2744,6 +2744,9 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + return -EOPNOTSUPP; return mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, @@ -2757,6 +2760,9 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { + if (dev->caps.steering_mode != + MLX4_STEERING_MODE_DEVICE_MANAGED) + return -EOPNOTSUPP; return mlx4_cmd(dev, vhcr->in_param, 0, 0, MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7f5c9ee42f96..e45fc20bd01f 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -70,14 +70,17 @@ enum { MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1) }; -/* Driver supports 2 diffrent device methods to manage traffic steering: +/* Driver supports 3 diffrent device methods to manage traffic steering: + * -device managed - High level API for ib and eth flow steering. FW is + * managing flow steering tables. * - B0 steering mode - Common low level API for ib and (if supported) eth. * - A0 steering mode - Limited low level API for eth. In case of IB, * B0 mode is in use. */ enum { MLX4_STEERING_MODE_A0, - MLX4_STEERING_MODE_B0 + MLX4_STEERING_MODE_B0, + MLX4_STEERING_MODE_DEVICE_MANAGED }; static inline const char *mlx4_steering_mode_str(int steering_mode) @@ -88,6 +91,10 @@ static inline const char *mlx4_steering_mode_str(int steering_mode) case MLX4_STEERING_MODE_B0: return "B0 steering"; + + case MLX4_STEERING_MODE_DEVICE_MANAGED: + return "Device managed flow steering"; + default: return "Unrecognize steering mode"; } @@ -125,7 +132,8 @@ enum { enum { MLX4_DEV_CAP_FLAG2_RSS = 1LL << 0, MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1, - MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2 + MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2, + MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3 }; #define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90) @@ -319,6 +327,7 @@ struct mlx4_caps { int reserved_mcgs; int num_qp_per_mgm; int steering_mode; + int fs_log_max_ucast_qp_range_size; int num_pds; int reserved_pds; int max_xrcds; @@ -647,9 +656,94 @@ int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], enum mlx4_protocol prot); int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - int block_mcast_loopback, enum mlx4_protocol protocol); + u8 port, int block_mcast_loopback, + enum mlx4_protocol protocol, u64 *reg_id); int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], - enum mlx4_protocol protocol); + enum mlx4_protocol protocol, u64 reg_id); + +enum { + MLX4_DOMAIN_UVERBS = 0x1000, + MLX4_DOMAIN_ETHTOOL = 0x2000, + MLX4_DOMAIN_RFS = 0x3000, + MLX4_DOMAIN_NIC = 0x5000, +}; + +enum mlx4_net_trans_rule_id { + MLX4_NET_TRANS_RULE_ID_ETH = 0, + MLX4_NET_TRANS_RULE_ID_IB, + MLX4_NET_TRANS_RULE_ID_IPV6, + MLX4_NET_TRANS_RULE_ID_IPV4, + MLX4_NET_TRANS_RULE_ID_TCP, + MLX4_NET_TRANS_RULE_ID_UDP, + MLX4_NET_TRANS_RULE_NUM, /* should be last */ +}; + +enum mlx4_net_trans_promisc_mode { + MLX4_FS_PROMISC_NONE = 0, + MLX4_FS_PROMISC_UPLINK, + MLX4_FS_PROMISC_FUNCTION_PORT, + MLX4_FS_PROMISC_ALL_MULTI, +}; + +struct mlx4_spec_eth { + u8 dst_mac[6]; + u8 dst_mac_msk[6]; + u8 src_mac[6]; + u8 src_mac_msk[6]; + u8 ether_type_enable; + __be16 ether_type; + __be16 vlan_id_msk; + __be16 vlan_id; +}; + +struct mlx4_spec_tcp_udp { + __be16 dst_port; + __be16 dst_port_msk; + __be16 src_port; + __be16 src_port_msk; +}; + +struct mlx4_spec_ipv4 { + __be32 dst_ip; + __be32 dst_ip_msk; + __be32 src_ip; + __be32 src_ip_msk; +}; + +struct mlx4_spec_ib { + __be32 r_qpn; + __be32 qpn_msk; + u8 dst_gid[16]; + u8 dst_gid_msk[16]; +}; + +struct mlx4_spec_list { + struct list_head list; + enum mlx4_net_trans_rule_id id; + union { + struct mlx4_spec_eth eth; + struct mlx4_spec_ib ib; + struct mlx4_spec_ipv4 ipv4; + struct mlx4_spec_tcp_udp tcp_udp; + }; +}; + +enum mlx4_net_trans_hw_rule_queue { + MLX4_NET_TRANS_Q_FIFO, + MLX4_NET_TRANS_Q_LIFO, +}; + +struct mlx4_net_trans_rule { + struct list_head list; + enum mlx4_net_trans_hw_rule_queue queue_mode; + bool exclusive; + bool allow_loopback; + enum mlx4_net_trans_promisc_mode promisc_mode; + u8 port; + u16 priority; + u32 qpn; +}; + int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port); int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port); @@ -692,4 +786,8 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); +int mlx4_flow_attach(struct mlx4_dev *dev, + struct mlx4_net_trans_rule *rule, u64 *reg_id); +int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id); + #endif /* MLX4_DEVICE_H */ -- cgit v1.2.3 From 6700c2709c08d74ae2c3c29b84a30da012dbc7f1 Mon Sep 17 00:00:00 2001 From: David S. Miller Date: Tue, 17 Jul 2012 03:29:28 -0700 Subject: net: Pass optional SKB and SK arguments to dst_ops->{update_pmtu,redirect}() This will be used so that we can compose a full flow key. Even though we have a route in this context, we need more. In the future the routes will be without destination address, source address, etc. keying. One ipv4 route will cover entire subnets, etc. In this environment we have to have a way to possess persistent storage for redirects and PMTU information. This persistent storage will exist in the FIB tables, and that's why we'll need to be able to rebuild a full lookup flow key here. Using that flow key will do a fib_lookup() and create/update the persistent entry. Signed-off-by: David S. Miller --- drivers/infiniband/ulp/ipoib/ipoib_cm.c | 2 +- include/net/dst_ops.h | 6 ++++-- net/bridge/br_netfilter.c | 6 ++++-- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 2 +- net/decnet/dn_route.c | 12 ++++++++---- net/ipv4/inet_connection_sock.c | 2 +- net/ipv4/ip_gre.c | 2 +- net/ipv4/ipip.c | 2 +- net/ipv4/route.c | 21 +++++++++++++-------- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/xfrm4_policy.c | 10 ++++++---- net/ipv6/inet6_connection_sock.c | 2 +- net/ipv6/ip6_tunnel.c | 6 +++--- net/ipv6/route.c | 21 +++++++++++++-------- net/ipv6/sit.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/xfrm6_policy.c | 10 ++++++---- net/netfilter/ipvs/ip_vs_xmit.c | 4 ++-- net/sctp/input.c | 2 +- net/sctp/transport.c | 2 +- 21 files changed, 71 insertions(+), 49 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 014504d8e43c..1ca732201f33 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1397,7 +1397,7 @@ void ipoib_cm_skb_too_long(struct net_device *dev, struct sk_buff *skb, int e = skb_queue_empty(&priv->cm.skb_queue); if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); skb_queue_tail(&priv->cm.skb_queue, skb); if (e) diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 085931fa7ce0..d079fc61c123 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,8 +24,10 @@ struct dst_ops { struct net_device *dev, int how); struct dst_entry * (*negative_advice)(struct dst_entry *); void (*link_failure)(struct sk_buff *); - void (*update_pmtu)(struct dst_entry *dst, u32 mtu); - void (*redirect)(struct dst_entry *dst, struct sk_buff *skb); + void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); + void (*redirect)(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); int (*local_out)(struct sk_buff *skb); struct neighbour * (*neigh_lookup)(const struct dst_entry *dst, struct sk_buff *skb, diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 81f76c402cf2..68e8f364bbf8 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -111,11 +111,13 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb) pppoe_proto(skb) == htons(PPP_IPV6) && \ brnf_filter_pppoe_tagged) -static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) +static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { } -static void fake_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void fake_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 683902fcc8ed..ab4f44c9bb21 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -193,7 +193,7 @@ static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) - dst->ops->redirect(dst, skb); + dst->ops->redirect(dst, sk, skb); } /* diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3ee0342e1cec..56840b249f3b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -134,7 +134,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) - dst->ops->redirect(dst, skb); + dst->ops->redirect(dst, sk, skb); } if (type == ICMPV6_PKT_TOOBIG) { diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index e9c4e2e864c6..47de90d8fe94 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -117,8 +117,10 @@ static void dn_dst_destroy(struct dst_entry *); static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); -static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); -static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb); +static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb , u32 mtu); +static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); @@ -266,7 +268,8 @@ static int dn_dst_gc(struct dst_ops *ops) * We update both the mtu and the advertised mss (i.e. the segment size we * advertise to the other end). */ -static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) +static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; @@ -294,7 +297,8 @@ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static void dn_dst_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 200d21809379..3ea465286a39 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -840,7 +840,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0c3123566d76..42c44b1403c9 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -833,7 +833,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index c2d0e6d8baaf..2c2c35bace76 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -519,7 +519,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if ((old_iph->frag_off & htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index aad21819316d..b35d3bfc66cd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -148,8 +148,10 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); -static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); -static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb); +static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); static int rt_garbage_collect(struct dst_ops *ops); static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -1273,7 +1275,7 @@ static void rt_del(unsigned int hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } -static void ip_do_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; @@ -1506,7 +1508,8 @@ out: kfree_skb(skb); return 0; } -static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct rtable *rt = (struct rtable *) dst; @@ -1531,7 +1534,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, iph->daddr, iph->saddr, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { - ip_rt_update_pmtu(&rt->dst, mtu); + ip_rt_update_pmtu(&rt->dst, NULL, skb, mtu); ip_rt_put(rt); } } @@ -1559,7 +1562,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net, protocol, flow_flags, iph->daddr, iph->saddr, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { - ip_do_redirect(&rt->dst, skb); + ip_do_redirect(&rt->dst, NULL, skb); ip_rt_put(rt); } } @@ -2587,11 +2590,13 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { } -static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b8e7e0595407..d9caf5c07aae 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -319,7 +319,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) - dst->ops->redirect(dst, skb); + dst->ops->redirect(dst, sk, skb); } /* diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 737131cef375..fcf7678bc009 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -194,20 +194,22 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops) return (dst_entries_get_slow(ops) > ops->gc_thresh * 2); } -static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->update_pmtu(path, sk, skb, mtu); } -static void xfrm4_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->redirect(path, skb); + path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 62539a4b2dc7..4a0c4d2d8b05 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -269,7 +269,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu); return inet6_csk_route_socket(sk); } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 61d106597296..db3284667968 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -609,10 +609,10 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info); + skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), NULL, skb2, rel_info); } if (rel_type == ICMP_REDIRECT) - skb_dst(skb2)->ops->redirect(skb_dst(skb2), skb2); + skb_dst(skb2)->ops->redirect(skb_dst(skb2), NULL, skb2); icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -952,7 +952,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { *pmtu = mtu; err = -EMSGSIZE; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2a4c8d48977f..31af1ed6c1dc 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -78,8 +78,10 @@ static int ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu); -static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb); +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu); +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); #ifdef CONFIG_IPV6_ROUTE_INFO static struct rt6_info *rt6_add_route_info(struct net *net, @@ -187,11 +189,13 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) return mtu ? : dst->dev->mtu; } -static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { } -static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { } @@ -1071,7 +1075,8 @@ static void ip6_link_failure(struct sk_buff *skb) } } -static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu) +static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct rt6_info *rt6 = (struct rt6_info*)dst; @@ -1108,7 +1113,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - ip6_rt_update_pmtu(dst, ntohl(mtu)); + ip6_rt_update_pmtu(dst, NULL, skb, ntohl(mtu)); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); @@ -1136,7 +1141,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - rt6_do_redirect(dst, skb); + rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); @@ -1639,7 +1644,7 @@ static int ip6_route_del(struct fib6_config *cfg) return err; } -static void rt6_do_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct netevent_redirect netevent; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index fbf1622fdeef..3bd1bfc01f85 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -807,7 +807,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr && skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len > mtu) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index ecdf241cad02..c9dabdd832d7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -367,7 +367,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); if (dst) - dst->ops->redirect(dst,skb); + dst->ops->redirect(dst, sk, skb); } if (type == ICMPV6_PKT_TOOBIG) { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f5a9cb8257b9..ef39812107b1 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -207,20 +207,22 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops) return dst_entries_get_fast(ops) > ops->gc_thresh * 2; } -static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) +static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, mtu); + path->ops->update_pmtu(path, sk, skb, mtu); } -static void xfrm6_redirect(struct dst_entry *dst, struct sk_buff *skb) +static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->redirect(path, skb); + path->ops->redirect(path, sk, skb); } static void xfrm6_dst_destroy(struct dst_entry *dst) diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 71d6ecb65926..65b616ae1716 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -797,7 +797,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); df |= (old_iph->frag_off & htons(IP_DF)); @@ -913,7 +913,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error_put; } if (skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && !skb_is_gso(skb)) { diff --git a/net/sctp/input.c b/net/sctp/input.c index a67bc31f49fd..c201b26879a1 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -432,7 +432,7 @@ void sctp_icmp_redirect(struct sock *sk, struct sctp_transport *t, return; dst = sctp_transport_dst_check(t); if (dst) - dst->ops->redirect(dst, skb); + dst->ops->redirect(dst, sk, skb); } /* diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e69e1a2175a4..a6b7ee9ce28a 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -249,7 +249,7 @@ void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 p t->af_specific->get_dst(t, &t->saddr, &t->fl, sk); if (dst) { - dst->ops->update_pmtu(dst, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu); dst = sctp_transport_dst_check(t); if (!dst) -- cgit v1.2.3 From d9236c3f10490cd0b3fd4516af12ba62dcbae0b0 Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Wed, 18 Jul 2012 22:33:51 +0000 Subject: {NET,IB}/mlx4: Add rmap support to mlx4_assign_eq Enable callers of mlx4_assign_eq to supply a pointer to cpu_rmap. If supplied, the assigned IRQ is tracked using rmap infrastructure. Signed-off-by: Amir Vadai Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 3 ++- drivers/net/ethernet/mellanox/mlx4/en_cq.c | 3 ++- drivers/net/ethernet/mellanox/mlx4/eq.c | 12 +++++++++++- include/linux/mlx4/device.h | 4 +++- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 8a3a2037b005..a07b774e7864 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1159,7 +1159,8 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev) sprintf(name, "mlx4-ib-%d-%d@%s", i, j, dev->pdev->bus->name); /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(dev, name, &ibdev->eq_table[eq])) { + if (mlx4_assign_eq(dev, name, NULL, + &ibdev->eq_table[eq])) { /* Use legacy (same as mlx4_en driver) */ pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq); ibdev->eq_table[eq] = diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 908a460d8db6..0ef615684021 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -91,7 +91,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, sprintf(name, "%s-%d", priv->dev->name, cq->ring); /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(mdev->dev, name, &cq->vector)) { + if (mlx4_assign_eq(mdev->dev, name, NULL, + &cq->vector)) { cq->vector = (cq->ring + 1 + priv->port) % mdev->dev->caps.num_comp_vectors; mlx4_warn(mdev, "Failed Assigning an EQ to " diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index bce98d9c0039..cd48337cbfc0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -39,6 +39,7 @@ #include #include +#include #include "mlx4.h" #include "fw.h" @@ -1060,7 +1061,8 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) } EXPORT_SYMBOL(mlx4_test_interrupts); -int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector) +int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, + int *vector) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -1074,6 +1076,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector) snprintf(priv->eq_table.irq_names + vec * MLX4_IRQNAME_SIZE, MLX4_IRQNAME_SIZE, "%s", name); +#ifdef CONFIG_RFS_ACCEL + if (rmap) { + err = irq_cpu_rmap_add(rmap, + priv->eq_table.eq[vec].irq); + if (err) + mlx4_warn(dev, "Failed adding irq rmap\n"); + } +#endif err = request_irq(priv->eq_table.eq[vec].irq, mlx4_msi_x_interrupt, 0, &priv->eq_table.irq_names[vec<<5], diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 6f0d133cc7ad..4d7761f8c3f6 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -36,6 +36,7 @@ #include #include #include +#include #include @@ -784,7 +785,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr, int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr); int mlx4_SYNC_TPT(struct mlx4_dev *dev); int mlx4_test_interrupts(struct mlx4_dev *dev); -int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector); +int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, + int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); -- cgit v1.2.3