From f75cfbaddeef943aed479b80415c3dcc63ff4247 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 21 Apr 2016 13:13:56 +0300 Subject: MAINTAINERS: net: add entry for TI Ethernet Switch drivers Add record for TI Ethernet Switch Driver CPSW/CPDMA/MDIO HW (am33/am43/am57/dr7/davinci) to ensure that related patches will go through dedicated linux-omap list. Also add Mugunthan as maintainer and myself as the reviewer. Cc: "David S. Miller" Cc: Tony Lindgren Cc: Mugunthan V N Cc: Richard Cochran Signed-off-by: Grygorii Strashko Acked-by: Mugunthan V N Acked-by: Tony Lindgren Signed-off-by: David S. Miller diff --git a/MAINTAINERS b/MAINTAINERS index 1d5b4be..8491336 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11071,6 +11071,15 @@ S: Maintained F: drivers/clk/ti/ F: include/linux/clk/ti.h +TI ETHERNET SWITCH DRIVER (CPSW) +M: Mugunthan V N +R: Grygorii Strashko +L: linux-omap@vger.kernel.org +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/ti/cpsw* +F: drivers/net/ethernet/ti/davinci* + TI FLASH MEDIA INTERFACE DRIVER M: Alex Dubov S: Maintained -- cgit v0.10.2 From 7ceb2afbd6aee4643056b47156baad6841db8e78 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:43 +0200 Subject: switchdev: Adding complete operation to deferred switchdev ops When using switchdev deferred operation (SWITCHDEV_F_DEFER), the operation is executed in different context and the application doesn't have any way to get the operation real status. Adding a completion callback fixes that. This patch adds fields to switchdev_attr and switchdev_obj "complete_priv" field which is used by the "complete" callback. Application can set a complete function which will be called once the operation executed. Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d451122..51d77b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -54,6 +54,8 @@ struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ @@ -75,6 +77,8 @@ struct switchdev_obj { struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2b9b98f..b7e01d8 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -305,6 +305,8 @@ static void switchdev_port_attr_set_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); + if (attr->complete) + attr->complete(dev, err, attr->complete_priv); } static int switchdev_port_attr_set_defer(struct net_device *dev, @@ -434,6 +436,8 @@ static void switchdev_port_obj_add_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_add_defer(struct net_device *dev, @@ -502,6 +506,8 @@ static void switchdev_port_obj_del_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_del_defer(struct net_device *dev, -- cgit v0.10.2 From 6dd684c0feb207f30180570bad24264b922d9476 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:44 +0200 Subject: bridge: mdb: Common function for mdb entry translation There is duplicate code that translates br_mdb_entry to br_ip let's wrap it in a common function. Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 253bc77..b258120 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -61,6 +61,19 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags |= MDB_FLAGS_OFFLOAD; } +static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) +{ + memset(ip, 0, sizeof(struct br_ip)); + ip->vid = entry->vid; + ip->proto = entry->addr.proto; + if (ip->proto == htons(ETH_P_IP)) + ip->u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip->u.ip6 = entry->addr.u.ip6; +#endif +} + static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { @@ -509,15 +522,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); ret = br_mdb_add_group(br, p, &ip, entry->state, pg); @@ -584,15 +589,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || br->multicast_disabled) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); -- cgit v0.10.2 From 45ebcce56823d14d196dbdecd26783b3d5f464a6 Mon Sep 17 00:00:00 2001 From: Elad Raz Date: Thu, 21 Apr 2016 12:52:45 +0200 Subject: bridge: mdb: Marking port-group as offloaded There is a race-condition when updating the mdb offload flag without using the mulicast_lock. This reverts commit 9e8430f8d60d98 ("bridge: mdb: Passing the port-group pointer to br_mdb module"). This patch marks offloaded MDB entry as "offload" by changing the port- group flags and marks it as MDB_PG_FLAGS_OFFLOAD. When switchdev PORT_MDB succeeded and adds a multicast group, a completion callback is been invoked "br_mdb_complete". The completion function locks the multicast_lock and finds the right net_bridge_port_group and marks it as offloaded. Fixes: 9e8430f8d60d98 ("bridge: mdb: Passing the port-group pointer to br_mdb module") Reported-by: Nikolay Aleksandrov Signed-off-by: Elad Raz Signed-off-by: Jiri Pirko Reviewed-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index b258120..7dbc80d 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -256,9 +256,45 @@ static inline size_t rtnl_mdb_nlmsg_size(void) + nla_total_size(sizeof(struct br_mdb_entry)); } -static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, - int type, struct net_bridge_port_group *pg) +struct br_mdb_complete_info { + struct net_bridge_port *port; + struct br_ip ip; +}; + +static void br_mdb_complete(struct net_device *dev, int err, void *priv) { + struct br_mdb_complete_info *data = priv; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port *port = data->port; + struct net_bridge *br = port->br; + + if (err) + goto err; + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, &data->ip); + if (!mp) + goto out; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + p->flags |= MDB_PG_FLAGS_OFFLOAD; + } +out: + spin_unlock_bh(&br->multicast_lock); +err: + kfree(priv); +} + +static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, + struct br_mdb_entry *entry, int type) +{ + struct br_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_PORT_MDB, @@ -281,9 +317,14 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, mdb.obj.orig_dev = port_dev; if (port_dev && type == RTM_NEWMDB) { - err = switchdev_port_obj_add(port_dev, &mdb.obj); - if (!err && pg) - pg->flags |= MDB_PG_FLAGS_OFFLOAD; + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (complete_info) { + complete_info->port = p; + __mdb_entry_to_br_ip(entry, &complete_info->ip); + mdb.obj.complete_priv = complete_info; + mdb.obj.complete = br_mdb_complete; + switchdev_port_obj_add(port_dev, &mdb.obj); + } } else if (port_dev && type == RTM_DELMDB) { switchdev_port_obj_del(port_dev, &mdb.obj); } @@ -304,21 +345,21 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type) +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags) { struct br_mdb_entry entry; memset(&entry, 0, sizeof(entry)); - entry.ifindex = pg->port->dev->ifindex; - entry.addr.proto = pg->addr.proto; - entry.addr.u.ip4 = pg->addr.u.ip4; + entry.ifindex = port->dev->ifindex; + entry.addr.proto = group->proto; + entry.addr.u.ip4 = group->u.ip4; #if IS_ENABLED(CONFIG_IPV6) - entry.addr.u.ip6 = pg->addr.u.ip6; + entry.addr.u.ip6 = group->u.ip6; #endif - entry.vid = pg->addr.vid; - __mdb_entry_fill_flags(&entry, pg->flags); - __br_mdb_notify(dev, &entry, type, pg); + entry.vid = group->vid; + __mdb_entry_fill_flags(&entry, flags); + __br_mdb_notify(dev, port, &entry, type); } static int nlmsg_populate_rtr_fill(struct sk_buff *skb, @@ -463,8 +504,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, } static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group, unsigned char state, - struct net_bridge_port_group **pg) + struct br_ip *group, unsigned char state) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; @@ -495,7 +535,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); - *pg = p; if (state == MDB_TEMPORARY) mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -503,8 +542,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } static int __br_mdb_add(struct net *net, struct net_bridge *br, - struct br_mdb_entry *entry, - struct net_bridge_port_group **pg) + struct br_mdb_entry *entry) { struct br_ip ip; struct net_device *dev; @@ -525,7 +563,7 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); - ret = br_mdb_add_group(br, p, &ip, entry->state, pg); + ret = br_mdb_add_group(br, p, &ip, entry->state); spin_unlock_bh(&br->multicast_lock); return ret; } @@ -533,7 +571,6 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - struct net_bridge_port_group *pg; struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; @@ -563,15 +600,15 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (br_vlan_enabled(br) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (err) break; - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } } else { - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } return err; @@ -659,12 +696,12 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } } else { err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a4c15df..191ea66 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,7 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->flags); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -705,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, p, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -1461,7 +1462,8 @@ br_multicast_leave_group(struct net_bridge *br, hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->flags); if (!mp->ports && !mp->mglist && netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1b5d145..d9da857 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -560,8 +560,8 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, unsigned char flags); void br_mdb_init(void); void br_mdb_uninit(void); -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type); +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags); void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, int type); -- cgit v0.10.2 From 72f2a05b8f367ee0d75584a6fbec7dbe7c144f27 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:01 +0200 Subject: macsec: add missing NULL check after kmalloc Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Dan Carpenter Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 84d3e5c..f691030 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1622,8 +1622,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); - if (init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, - secy->icv_len)) { + if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), + secy->key_len, secy->icv_len)) { rtnl_unlock(); return -ENOMEM; } -- cgit v0.10.2 From c10c63ea739bce3b8a6ab85c7bb472d900c9b070 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:02 +0200 Subject: macsec: take rtnl lock before for_each_netdev Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Johannes Berg Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index f691030..5f3ea80 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2268,8 +2268,6 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!hdr) return -EMSGSIZE; - rtnl_lock(); - if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2429,14 +2427,11 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, nla_nest_end(skb, rxsc_list); - rtnl_unlock(); - genlmsg_end(skb, hdr); return 0; nla_put_failure: - rtnl_unlock(); genlmsg_cancel(skb, hdr); return -EMSGSIZE; } @@ -2450,6 +2445,7 @@ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) dev_idx = cb->args[0]; d = 0; + rtnl_lock(); for_each_netdev(net, dev) { struct macsec_secy *secy; @@ -2467,6 +2463,7 @@ next: } done: + rtnl_unlock(); cb->args[0] = d; return skb->len; } -- cgit v0.10.2 From 497f358aa4c0d99b75ec204407389920d5e33ec5 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:03 +0200 Subject: macsec: don't put a NULL rxsa The "deliver:" path of macsec_handle_frame can be called with rx_sa == NULL. Check rx_sa != NULL before calling macsec_rxsa_put(). Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 5f3ea80..2a2136b 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1161,7 +1161,8 @@ deliver: macsec_extra_len(macsec_skb_cb(skb)->has_sci)); macsec_reset_skb(skb, secy->netdev); - macsec_rxsa_put(rx_sa); + if (rx_sa) + macsec_rxsa_put(rx_sa); count_rx(dev, skb->len); rcu_read_unlock(); -- cgit v0.10.2 From c3b7d0bd7ac2c501d4806db71ddd383c184968e8 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:04 +0200 Subject: macsec: fix rx_sa refcounting with decrypt callback The decrypt callback macsec_decrypt_done needs a reference on the rx_sa and releases it before returning, but macsec_handle_frame already put that reference after macsec_decrypt returned NULL. Set rx_sa to NULL when the decrypt callback runs so that macsec_handle_frame knows it must not release the reference. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 2a2136b..1fd2b14 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -880,12 +880,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) - return NULL; + return ERR_PTR(-ENOMEM); req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC); if (!req) { kfree_skb(skb); - return NULL; + return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; @@ -905,7 +905,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); - return NULL; + return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ @@ -921,14 +921,14 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { - return NULL; + return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); - skb = NULL; + skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; @@ -1146,8 +1146,10 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); - if (!skb) { - macsec_rxsa_put(rx_sa); + if (IS_ERR(skb)) { + /* the decrypt callback needs the reference */ + if (PTR_ERR(skb) != -EINPROGRESS) + macsec_rxsa_put(rx_sa); rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; -- cgit v0.10.2 From 96cfc5052c5d434563873caa7707b32b9e389b16 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:05 +0200 Subject: macsec: add consistency check to netlink dumps Use genl_dump_check_consistent in dump_secy. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Suggested-by: Johannes Berg Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 1fd2b14..41fbe55 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2271,6 +2271,8 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!hdr) return -EMSGSIZE; + genl_dump_check_consistent(cb, hdr, &macsec_fam); + if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2439,6 +2441,8 @@ nla_put_failure: return -EMSGSIZE; } +static int macsec_generation = 1; /* protected by RTNL */ + static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2449,6 +2453,9 @@ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) d = 0; rtnl_lock(); + + cb->seq = macsec_generation; + for_each_netdev(net, dev) { struct macsec_secy *secy; @@ -2920,6 +2927,8 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); + macsec_generation++; + unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); if (list_empty(&rxd->secys)) @@ -3066,6 +3075,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) goto del_dev; + macsec_generation++; + dev_hold(real_dev); return 0; -- cgit v0.10.2 From 960d5848dbf1245cc3a310109897937207411c0c Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:06 +0200 Subject: macsec: fix memory leaks around rx_handler (un)registration We leak a struct macsec_rxh_data when we unregister the rx_handler in macsec_dellink. We also leak a struct macsec_rxh_data in register_macsec_dev if we fail to register the rx_handler. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 41fbe55..826c6c9 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2931,8 +2931,10 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); - if (list_empty(&rxd->secys)) + if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); + kfree(rxd); + } macsec_del_dev(macsec); } @@ -2954,8 +2956,10 @@ static int register_macsec_dev(struct net_device *real_dev, err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); - if (err < 0) + if (err < 0) { + kfree(rxd); return err; + } } list_add_tail_rcu(&macsec->secys, &rxd->secys); -- cgit v0.10.2 From 38787fc209580f9b5918e93e71da7c960dbb5d8d Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:07 +0200 Subject: macsec: fix SA leak if initialization fails Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Reported-by: Lance Richardson Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 826c6c9..b37d348 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1627,6 +1627,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len)) { + kfree(rx_sa); rtnl_unlock(); return -ENOMEM; } @@ -1771,6 +1772,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); if (!tx_sa || init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len)) { + kfree(tx_sa); rtnl_unlock(); return -ENOMEM; } -- cgit v0.10.2 From 748164802c1bd2c52937d20782b07d8c68dd9a4f Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:08 +0200 Subject: macsec: add missing macsec prefix in uapi I accidentally forgot some MACSEC_ prefixes in if_macsec.h. Fixes: dece8d2b78d1 ("uapi: add MACsec bits") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index b37d348..9f63cc7 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -2232,7 +2232,8 @@ static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) return 1; if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci) || - nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || @@ -3096,7 +3097,7 @@ unregister: static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) { - u64 csid = DEFAULT_CIPHER_ID; + u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = DEFAULT_ICV_LEN; int flag; bool es, scb, sci; @@ -3111,8 +3112,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); switch (csid) { - case DEFAULT_CIPHER_ID: - case DEFAULT_CIPHER_ALT: + case MACSEC_DEFAULT_CIPHER_ID: + case MACSEC_DEFAULT_CIPHER_ALT: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_MAX_ICV_LEN) return -EINVAL; @@ -3185,7 +3186,8 @@ static int macsec_fill_info(struct sk_buff *skb, if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || - nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 26b0d1e..4c58d99 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -19,8 +19,8 @@ #define MACSEC_MAX_KEY_LEN 128 -#define DEFAULT_CIPHER_ID 0x0080020001000001ULL -#define DEFAULT_CIPHER_ALT 0x0080C20001000001ULL +#define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL +#define MACSEC_DEFAULT_CIPHER_ALT 0x0080C20001000001ULL #define MACSEC_MIN_ICV_LEN 8 #define MACSEC_MAX_ICV_LEN 32 -- cgit v0.10.2 From 4b1fb9352f351faa067a914907d58a6fe38ac048 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 22 Apr 2016 11:28:09 +0200 Subject: macsec: fix netlink attribute validation macsec_validate_attr should check IFLA_MACSEC_REPLAY_PROTECT (not IFLA_MACSEC_PROTECT) to verify that the replay protection and replay window arguments are correct. Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver") Signed-off-by: Sabrina Dubroca Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9f63cc7..c638561 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3147,8 +3147,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) return -EINVAL; - if ((data[IFLA_MACSEC_PROTECT] && - nla_get_u8(data[IFLA_MACSEC_PROTECT])) && + if ((data[IFLA_MACSEC_REPLAY_PROTECT] && + nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; -- cgit v0.10.2 From 3c201b5a84edd6ee2f9a8548efaa813980839b46 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Thu, 21 Apr 2016 14:11:50 +0200 Subject: net: stmmac: socfpga: Remove re-registration of reset controller Both socfpga_dwmac_parse_data() in dwmac-socfpga.c and stmmac_dvr_probe() in stmmac_main.c functions call devm_reset_control_get() to register an reset controller for the stmmac. This results in an attempt to register two reset controllers for the same non-shared reset line. The first attempt to register the reset controller works fine. The second attempt fails with warning from the reset controller core, see below. The warning is produced because the reset line is non-shared and thus it is allowed to have only up-to one reset controller associated with that reset line, not two or more. The solution has multiple parts. First, the original socfpga_dwmac_init() is tweaked to use reset controller pointer from the stmmac_priv (private data of the stmmac core) instead of the local instance, which was used before. The local re-registration of the reset controller is removed. Next, the socfpga_dwmac_init() is moved after stmmac_dvr_probe() in the probe function. This order is legal according to Altera and it makes the code much easier, since there is no need to temporarily register and unregister the reset controller ; the reset controller is already registered by the stmmac_dvr_probe(). Finally, plat_dat->exit and socfpga_dwmac_exit() is no longer necessary, since the functionality is already performed by the stmmac core. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 1 at drivers/reset/core.c:187 __of_reset_control_get+0x218/0x270 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.6.0-rc4-next-20160419-00015-gabb2477-dirty #4 Hardware name: Altera SOCFPGA [] (unwind_backtrace) from [] (show_stack+0x10/0x14) [] (show_stack) from [] (dump_stack+0x94/0xa8) [] (dump_stack) from [] (__warn+0xec/0x104) [] (__warn) from [] (warn_slowpath_null+0x20/0x28) [] (warn_slowpath_null) from [] (__of_reset_control_get+0x218/0x270) [] (__of_reset_control_get) from [] (__devm_reset_control_get+0x54/0x90) [] (__devm_reset_control_get) from [] (stmmac_dvr_probe+0x1b4/0x8e8) [] (stmmac_dvr_probe) from [] (socfpga_dwmac_probe+0x1b8/0x28c) [] (socfpga_dwmac_probe) from [] (platform_drv_probe+0x4c/0xb0) [] (platform_drv_probe) from [] (driver_probe_device+0x224/0x2bc) [] (driver_probe_device) from [] (__driver_attach+0xac/0xb0) [] (__driver_attach) from [] (bus_for_each_dev+0x6c/0xa0) [] (bus_for_each_dev) from [] (bus_add_driver+0x1a4/0x21c) [] (bus_add_driver) from [] (driver_register+0x78/0xf8) [] (driver_register) from [] (do_one_initcall+0x40/0x170) [] (do_one_initcall) from [] (kernel_init_freeable+0x1dc/0x27c) [] (kernel_init_freeable) from [] (kernel_init+0x8/0x114) [] (kernel_init) from [] (ret_from_fork+0x14/0x3c) ---[ end trace 059d2fbe87608fa9 ]--- Signed-off-by: Marek Vasut Cc: Matthew Gerlach Cc: Dinh Nguyen Cc: David S. Miller Tested-by: Dinh Nguyen Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 44022b1..afb90d1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -49,7 +49,6 @@ struct socfpga_dwmac { u32 reg_shift; struct device *dev; struct regmap *sys_mgr_base_addr; - struct reset_control *stmmac_rst; void __iomem *splitter_base; bool f2h_ptp_ref_clk; }; @@ -92,15 +91,6 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * struct device_node *np_splitter; struct resource res_splitter; - dwmac->stmmac_rst = devm_reset_control_get(dev, - STMMAC_RESOURCE_NAME); - if (IS_ERR(dwmac->stmmac_rst)) { - dev_info(dev, "Could not get reset control!\n"); - if (PTR_ERR(dwmac->stmmac_rst) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dwmac->stmmac_rst = NULL; - } - dwmac->interface = of_get_phy_mode(np); sys_mgr_base_addr = syscon_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon"); @@ -194,30 +184,23 @@ static int socfpga_dwmac_setup(struct socfpga_dwmac *dwmac) return 0; } -static void socfpga_dwmac_exit(struct platform_device *pdev, void *priv) -{ - struct socfpga_dwmac *dwmac = priv; - - /* On socfpga platform exit, assert and hold reset to the - * enet controller - the default state after a hard reset. - */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); -} - static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) { - struct socfpga_dwmac *dwmac = priv; + struct socfpga_dwmac *dwmac = priv; struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *stpriv = NULL; int ret = 0; - if (ndev) - stpriv = netdev_priv(ndev); + if (!ndev) + return -EINVAL; + + stpriv = netdev_priv(ndev); + if (!stpriv) + return -EINVAL; /* Assert reset to the enet controller before changing the phy mode */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_assert(stpriv->stmmac_rst); /* Setup the phy mode in the system manager registers according to * devicetree configuration @@ -227,8 +210,8 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) /* Deassert reset for the phy configuration to be sampled by * the enet controller, and operation to start in requested mode */ - if (dwmac->stmmac_rst) - reset_control_deassert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_deassert(stpriv->stmmac_rst); /* Before the enet controller is suspended, the phy is suspended. * This causes the phy clock to be gated. The enet controller is @@ -245,7 +228,7 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) * control register 0, and can be modified by the phy driver * framework. */ - if (stpriv && stpriv->phydev) + if (stpriv->phydev) phy_resume(stpriv->phydev); return ret; @@ -285,14 +268,13 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = dwmac; plat_dat->init = socfpga_dwmac_init; - plat_dat->exit = socfpga_dwmac_exit; plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; - ret = socfpga_dwmac_init(pdev, plat_dat->bsp_priv); - if (ret) - return ret; + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (!ret) + ret = socfpga_dwmac_init(pdev, dwmac); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct of_device_id socfpga_dwmac_match[] = { -- cgit v0.10.2 From 45c78e0219405af1b0f31b06952dfd9bcf7ad1f6 Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 21 Apr 2016 13:25:20 -0400 Subject: qlcnic: Update version to 5.3.64 Just updating the version as many fixes got accumulated over 5.3.63 Signed-off-by: Manish Chopra Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 55007f1..caf6ddb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 63 -#define QLCNIC_LINUX_VERSIONID "5.3.63" +#define _QLCNIC_LINUX_SUBVERSION 64 +#define QLCNIC_LINUX_VERSIONID "5.3.64" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) -- cgit v0.10.2 From c3f9bf628bc7edda298897d952f5e761137229c9 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Fri, 22 Apr 2016 00:33:00 +0300 Subject: net/mlx5_core: Fix soft lockup in steering error flow In the error flow of adding flow rule to auto-grouped flow table, we call to tree_remove_node. tree_remove_node locks the node's parent, however the node's parent is already locked by mlx5_add_flow_rule and this causes a deadlock. After this patch, if we failed to add the flow rule, we unlock the flow table before calling to tree_remove_node. fixes: f0d22d187473 ('net/mlx5_core: Introduce flow steering autogrouped flow table') Signed-off-by: Maor Gottlieb Reported-by: Amir Vadai Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5121be4..3c7e3e5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1065,33 +1065,6 @@ unlock_fg: return rule; } -static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u8 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_rule *rule; - struct mlx5_flow_group *g; - - g = create_autogroup(ft, match_criteria_enable, match_criteria); - if (IS_ERR(g)) - return (void *)g; - - rule = add_rule_fg(g, match_value, - action, flow_tag, dest); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - tree_get_node(&g->node); - tree_remove_node(&g->node); - } - return rule; -} - static struct mlx5_flow_rule * _mlx5_add_flow_rule(struct mlx5_flow_table *ft, u8 match_criteria_enable, @@ -1119,8 +1092,23 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, goto unlock; } - rule = add_rule_to_auto_fg(ft, match_criteria_enable, match_criteria, - match_value, action, flow_tag, dest); + g = create_autogroup(ft, match_criteria_enable, match_criteria); + if (IS_ERR(g)) { + rule = (void *)g; + goto unlock; + } + + rule = add_rule_fg(g, match_value, + action, flow_tag, dest); + if (IS_ERR(rule)) { + /* Remove assumes refcount > 0 and autogroup creates a group + * with a refcount = 0. + */ + unlock_ref_node(&ft->node); + tree_get_node(&g->node); + tree_remove_node(&g->node); + return rule; + } unlock: unlock_ref_node(&ft->node); return rule; -- cgit v0.10.2 From 6e4c21894673baabdbef03c3ac2458a28246128b Mon Sep 17 00:00:00 2001 From: Rana Shahout Date: Fri, 22 Apr 2016 00:33:01 +0300 Subject: net/mlx5e: Fix MLX5E_100BASE_T define Bit 25 of eth_proto_capability in PTYS register is 1000Base-TT and not 100Base-T. Fixes: f62b8bb8f2d3 ('net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality') Signed-off-by: Rana Shahout Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 879e627..e80ce94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -609,7 +609,7 @@ enum mlx5e_link_mode { MLX5E_100GBASE_KR4 = 22, MLX5E_100GBASE_LR4 = 23, MLX5E_100BASE_TX = 24, - MLX5E_100BASE_T = 25, + MLX5E_1000BASE_T = 25, MLX5E_10GBASE_T = 26, MLX5E_25GBASE_CR = 27, MLX5E_25GBASE_KR = 28, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 68834b7..3476ab8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -138,10 +138,10 @@ static const struct { [MLX5E_100BASE_TX] = { .speed = 100, }, - [MLX5E_100BASE_T] = { - .supported = SUPPORTED_100baseT_Full, - .advertised = ADVERTISED_100baseT_Full, - .speed = 100, + [MLX5E_1000BASE_T] = { + .supported = SUPPORTED_1000baseT_Full, + .advertised = ADVERTISED_1000baseT_Full, + .speed = 1000, }, [MLX5E_10GBASE_T] = { .supported = SUPPORTED_10000baseT_Full, -- cgit v0.10.2 From 64dbbdfef245f67504ec403a5aebfcc7b92bd8c1 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Fri, 22 Apr 2016 00:33:02 +0300 Subject: net/mlx5_core: Add ConnectX-5 to list of supported devices Add the upcoming ConnectX-5 devices (PF and VF) to the list of supported devices by the mlx5 driver. Signed-off-by: Majd Dibbiny Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3f3b2fa..ddd352a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1459,6 +1459,8 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4 VF */ { PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */ { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ + { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5 */ + { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ { 0, } }; -- cgit v0.10.2 From 046339eaab26804f52f6604877f5674f70815b26 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:03 +0300 Subject: net/mlx5e: Device's mtu field is u16 and not int For set/query MTU port firmware commands the MTU field is 16 bits, here I changed all the "int mtu" parameters of the functions wrapping those firmware commands to be u16. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5acf346..99eb1c1 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -671,8 +671,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port, struct mlx5_ib_dev *dev = to_mdev(ibdev); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *rep; - int max_mtu; - int oper_mtu; + u16 max_mtu; + u16 oper_mtu; int err; u8 ib_link_width_oper; u8 vl_hw_cap; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e0adb60..2fbbc62 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1408,7 +1408,7 @@ static int mlx5e_set_dev_port_mtu(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - int hw_mtu; + u16 hw_mtu; int err; err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1); @@ -2004,7 +2004,7 @@ static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; - int max_mtu; + u16 max_mtu; int err = 0; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index ae378c5..53cc1e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -247,8 +247,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status); -static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, - int *max_mtu, int *oper_mtu, u8 port) +static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu, + u16 *max_mtu, u16 *oper_mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -268,7 +268,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, *admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu); } -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -283,14 +283,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) } EXPORT_SYMBOL_GPL(mlx5_set_port_mtu); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port); } EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index a1d145a..b30250a 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -54,9 +54,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port); int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, -- cgit v0.10.2 From d8edd2469ace550db707798180d1c84d81f93bca Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:04 +0300 Subject: net/mlx5e: Fix minimum MTU Minimum MTU that can be set in Connectx4 device is 68. This fixes the case where a user wants to set invalid MTU, the driver will fail to satisfy this request and the interface will stay down. It is better to report an error and continue working with old mtu. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2fbbc62..93e4ef4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1999,22 +1999,27 @@ static int mlx5e_set_features(struct net_device *netdev, return err; } +#define MXL5_HW_MIN_MTU 64 +#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN) + static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; u16 max_mtu; + u16 min_mtu; int err = 0; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); max_mtu = MLX5E_HW2SW_MTU(max_mtu); + min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU); - if (new_mtu > max_mtu) { + if (new_mtu > max_mtu || new_mtu < min_mtu) { netdev_err(netdev, - "%s: Bad MTU (%d) > (%d) Max\n", - __func__, new_mtu, max_mtu); + "%s: Bad MTU (%d), valid range is: [%d..%d]\n", + __func__, new_mtu, min_mtu, max_mtu); return -EINVAL; } -- cgit v0.10.2 From cd255efff9baadd654d6160e52d17ae7c568c9d3 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Fri, 22 Apr 2016 00:33:05 +0300 Subject: net/mlx5e: Use vport MTU rather than physical port MTU Set and report vport MTU rather than physical MTU, Driver will set both vport and physical port mtu and will rely on the query of vport mtu. SRIOV VFs have to report their MTU to their vport manager (PF), and this will allow them to work with any MTU they need without failing the request. Also for some cases where the PF is not a port owner, PF can work with MTU less than the physical port mtu if set physical port mtu didn't take effect. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 93e4ef4..85773f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1404,24 +1404,50 @@ static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) return 0; } -static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu) { - struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - u16 hw_mtu; + u16 hw_mtu = MLX5E_SW2HW_MTU(mtu); int err; - err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1); + err = mlx5_set_port_mtu(mdev, hw_mtu, 1); if (err) return err; - mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + /* Update vport context MTU */ + mlx5_modify_nic_vport_mtu(mdev, hw_mtu); + return 0; +} + +static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u16 hw_mtu = 0; + int err; + + err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu); + if (err || !hw_mtu) /* fallback to port oper mtu */ + mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + + *mtu = MLX5E_HW2SW_MTU(hw_mtu); +} + +static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + u16 mtu; + int err; + + err = mlx5e_set_mtu(priv, netdev->mtu); + if (err) + return err; - if (MLX5E_HW2SW_MTU(hw_mtu) != netdev->mtu) - netdev_warn(netdev, "%s: Port MTU %d is different than netdev mtu %d\n", - __func__, MLX5E_HW2SW_MTU(hw_mtu), netdev->mtu); + mlx5e_query_mtu(priv, &mtu); + if (mtu != netdev->mtu) + netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n", + __func__, mtu, netdev->mtu); - netdev->mtu = MLX5E_HW2SW_MTU(hw_mtu); + netdev->mtu = mtu; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index bd51840..b69dadc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -196,6 +196,46 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev, } EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_address); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = mlx5_vzalloc(outlen); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out, outlen); + if (!err) + *mtu = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.mtu); + + kvfree(out); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mtu); + +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); + void *in; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1); + MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, mtu); + + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); + int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, u32 vport, enum mlx5_list_type list_type, diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index bd93e63..301da4a 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -45,6 +45,8 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, u16 vport, u8 *addr); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); -- cgit v0.10.2 From 78228cbdeb0aa5c96e2a721e7e0d6953b416b5a3 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Fri, 22 Apr 2016 00:33:06 +0300 Subject: net/mlx5_core: Remove static from local variable The static is not required and breaks re-entrancy if it will be required. Fixes: 2530236303d9 ("net/mlx5_core: Flow steering tree initialization") Signed-off-by: Eli Cohen Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3c7e3e5..89cce97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1276,7 +1276,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; int prio; - static struct fs_prio *fs_prio; + struct fs_prio *fs_prio; struct mlx5_flow_namespace *ns; if (!root_ns) -- cgit v0.10.2 From 5fc7197d3a256d9c5de3134870304b24892a4908 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Fri, 22 Apr 2016 00:33:07 +0300 Subject: net/mlx5: Add pci shutdown callback This patch introduces kexec support for mlx5. When switching kernels, kexec() calls shutdown, which unloads the driver and cleans its resources. In addition, remove unregister netdev from shutdown flow. This will allow a clean shutdown, even if some netdev clients did not release their reference from this netdev. Releasing The HW resources only is enough as the kernel is shutting down Signed-off-by: Majd Dibbiny Signed-off-by: Tariq Toukan Signed-off-by: Haggai Abramovsky Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 85773f8..67d548b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2633,7 +2633,16 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) schedule_work(&priv->set_rx_mode_work); mlx5e_disable_async_events(priv); flush_scheduled_work(); - unregister_netdev(netdev); + if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) { + netif_device_detach(netdev); + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_close_locked(netdev); + mutex_unlock(&priv->state_lock); + } else { + unregister_netdev(netdev); + } + mlx5e_tc_cleanup(priv); mlx5e_vxlan_cleanup(priv); mlx5e_destroy_flow_tables(priv); @@ -2646,7 +2655,9 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn); mlx5_core_dealloc_pd(priv->mdev, priv->pdn); mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); - free_netdev(netdev); + + if (!test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) + free_netdev(netdev); } static void *mlx5e_get_netdev(void *vpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index ddd352a..6892746 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -966,7 +966,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) int err; mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_UP) { + if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", __func__); goto out; @@ -1133,7 +1133,8 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) if (err) pr_info("failed request module on %s\n", MLX5_IB_MOD); - dev->interface_state = MLX5_INTERFACE_STATE_UP; + clear_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); out: mutex_unlock(&dev->intf_state_mutex); @@ -1207,7 +1208,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) } mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_DOWN) { + if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", __func__); goto out; @@ -1241,7 +1242,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cmd_cleanup(dev); out: - dev->interface_state = MLX5_INTERFACE_STATE_DOWN; + clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); mutex_unlock(&dev->intf_state_mutex); return err; } @@ -1452,6 +1454,18 @@ static const struct pci_error_handlers mlx5_err_handler = { .resume = mlx5_pci_resume }; +static void shutdown(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + + dev_info(&pdev->dev, "Shutdown was called\n"); + /* Notify mlx5 clients that the kernel is being shut down */ + set_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &dev->intf_state); + mlx5_unload_one(dev, priv); + mlx5_pci_disable_device(dev); +} + static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1011) }, /* Connect-IB */ { PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF}, /* Connect-IB VF */ @@ -1471,6 +1485,7 @@ static struct pci_driver mlx5_core_driver = { .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, + .shutdown = shutdown, .err_handler = &mlx5_err_handler, .sriov_configure = mlx5_core_sriov_configure, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index dcd5ac8..369c837 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -519,8 +519,9 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN, - MLX5_INTERFACE_STATE_UP, + MLX5_INTERFACE_STATE_DOWN = BIT(0), + MLX5_INTERFACE_STATE_UP = BIT(1), + MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), }; enum mlx5_pci_status { @@ -544,7 +545,7 @@ struct mlx5_core_dev { enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; - enum mlx5_interface_state interface_state; + unsigned long intf_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); -- cgit v0.10.2 From 391a20333b8393ef2e13014e6e59d192c5594471 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 21 Apr 2016 22:23:31 +0200 Subject: ipv4/fib: don't warn when primary address is missing if in_dev is dead After commit fbd40ea0180a ("ipv4: Don't do expensive useless work during inetdev destroy.") when deleting an interface, fib_del_ifaddr() can be executed without any primary address present on the dead interface. The above is safe, but triggers some "bug: prim == NULL" warnings. This commit avoids warning if the in_dev is dead Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8a9246d..63566ec 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { - pr_warn("%s: bug: prim == NULL\n", __func__); + /* if the device has been deleted, we don't perform + * address promotion + */ + if (!in_dev->dead) + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { -- cgit v0.10.2 From 841645b5f2dfceac69b78fcd0c9050868d41ea61 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 25 Apr 2016 15:33:55 -0400 Subject: ipv6: Revert optional address flusing on ifdown. This reverts the following three commits: 70af921db6f8835f4b11c65731116560adb00c14 799977d9aafbf0ca0b9c39b04cbfb16db71302c9 f1705ec197e705b79ea40fe7a2cc5acfa1d3bfac The feature was ill conceived, has terrible semantics, and has added nothing but regressions to the already fragile ipv6 stack. Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional") Signed-off-by: David S. Miller diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index b183e2b..e0ac252 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1568,15 +1568,6 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) -keep_addr_on_down - INTEGER - Keep all IPv6 addresses on an interface down event. If set static - global addresses with no expiration time are not flushed. - >0 : enabled - 0 : system default - <0 : disabled - - Default: 0 (addresses are removed) - max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 7edc14f..4b2267e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,7 +62,6 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; - __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 3958760..ec117b6 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,7 +176,6 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, - DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cec53..d77ba39 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,7 +216,6 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, - .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -261,7 +260,6 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, - .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3176,81 +3174,6 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) -/* If the host route is cached on the addr struct make sure it is associated - * with the proper table. e.g., enslavement can change and if so the cached - * host route needs to move to the new table. - */ -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - if (ifp->rt) { - u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - - if (tb_id != ifp->rt->rt6i_table->tb6_id) { - ip6_del_rt(ifp->rt); - ifp->rt = NULL; - } - } -} -#else -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ -} -#endif - -static int fixup_permanent_addr(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - l3mdev_check_host_rt(idev, ifp); - - if (!ifp->rt) { - struct rt6_info *rt; - - rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (unlikely(IS_ERR(rt))) - return PTR_ERR(rt); - - ifp->rt = rt; - } - - if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, - idev->dev, 0, 0); - } - - addrconf_dad_start(ifp); - - return 0; -} - -static void addrconf_permanent_addr(struct net_device *dev) -{ - struct inet6_ifaddr *ifp, *tmp; - struct inet6_dev *idev; - - idev = __in6_dev_get(dev); - if (!idev) - return; - - write_lock_bh(&idev->lock); - - list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { - if ((ifp->flags & IFA_F_PERMANENT) && - fixup_permanent_addr(idev, ifp) < 0) { - write_unlock_bh(&idev->lock); - ipv6_del_addr(ifp); - write_lock_bh(&idev->lock); - - net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", - idev->dev->name, &ifp->addr); - } - } - - write_unlock_bh(&idev->lock); -} - static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3337,9 +3260,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); - switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3448,20 +3368,11 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event) ipv6_mc_unmap(idev); } -static bool addr_is_local(const struct in6_addr *addr) -{ - return ipv6_addr_type(addr) & - (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); -} - static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa, *tmp; - struct list_head del_list; - int _keep_addr; - bool keep_addr; + struct inet6_ifaddr *ifa; int state, i; ASSERT_RTNL(); @@ -3488,16 +3399,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* aggregate the system setting and interface setting */ - _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; - if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; - - /* combine the user config with event to determine if permanent - * addresses are to be removed from address hash table - */ - keep_addr = !(how || _keep_addr <= 0); - /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3506,16 +3407,9 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { + hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - /* combined flag + permanent flag decide if - * address is retained on a down event - */ - if (!keep_addr || - !(ifa->flags & IFA_F_PERMANENT) || - addr_is_local(&ifa->addr)) { - hlist_del_init_rcu(&ifa->addr_lst); - goto restart; - } + goto restart; } } spin_unlock_bh(&addrconf_hash_lock); @@ -3549,54 +3443,31 @@ restart: write_lock_bh(&idev->lock); } - /* re-combine the user config with event to determine if permanent - * addresses are to be removed from the interface list - */ - keep_addr = (!how && _keep_addr > 0); - - INIT_LIST_HEAD(&del_list); - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + while (!list_empty(&idev->addr_list)) { + ifa = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); addrconf_del_dad_work(ifa); - write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - - if (keep_addr && (ifa->flags & IFA_F_PERMANENT) && - !addr_is_local(&ifa->addr)) { - /* set state to skip the notifier below */ - state = INET6_IFADDR_STATE_DEAD; - ifa->state = 0; - if (!(ifa->flags & IFA_F_NODAD)) - ifa->flags |= IFA_F_TENTATIVE; - } else { - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + list_del(&ifa->if_list); - list_del(&ifa->if_list); - list_add(&ifa->if_list, &del_list); - } + write_unlock_bh(&idev->lock); + spin_lock_bh(&ifa->lock); + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } + in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); - /* now clean up addresses to be removed */ - while (!list_empty(&del_list)) { - ifa = list_first_entry(&del_list, - struct inet6_ifaddr, if_list); - list_del(&ifa->if_list); - - in6_ifa_put(ifa); - } - /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4861,7 +4732,6 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; - array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5950,14 +5820,6 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { - .procname = "keep_addr_on_down", - .data = &ipv6_devconf.keep_addr_on_down, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - - }, - { /* sentinel */ } }, -- cgit v0.10.2 From 3d6d30d60abb19ba9a20e53ce65b18a9c148fcd1 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Fri, 22 Apr 2016 13:09:13 +0200 Subject: cxgbi: fix uninitialized flowi6 ip6_route_output looks into different fields in the passed flowi6 structure, yet cxgbi passes garbage in nearly all those fields. Zero the structure out first. Fixes: fc8d0590d9142 ("libcxgbi: Add ipv6 api to driver") Signed-off-by: Jiri Benc Signed-off-by: David S. Miller diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index f3bb7af..ead83a2 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -688,6 +688,7 @@ static struct rt6_info *find_route_ipv6(const struct in6_addr *saddr, { struct flowi6 fl; + memset(&fl, 0, sizeof(fl)); if (saddr) memcpy(&fl.saddr, saddr, sizeof(struct in6_addr)); if (daddr) -- cgit v0.10.2 From 9f5db53507b6607dc1b5d59547097966c0e71047 Mon Sep 17 00:00:00 2001 From: Ivan Babrou Date: Sat, 23 Apr 2016 12:58:03 +0000 Subject: net: dummy: remove note about being Y by default Signed-off-by: Ivan Babrou Signed-off-by: David S. Miller diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index a24c18e..befd67d 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -62,9 +62,8 @@ config DUMMY this device is consigned into oblivion) with a configurable IP address. It is most commonly used in order to make your currently inactive SLIP address seem like a real address for local programs. - If you use SLIP or PPP, you might want to say Y here. Since this - thing often comes in handy, the default is Y. It won't enlarge your - kernel either. What a deal. Read about it in the Network + If you use SLIP or PPP, you might want to say Y here. It won't + enlarge your kernel. What a deal. Read about it in the Network Administrator's Guide, available from . -- cgit v0.10.2 From fc96256c906362e845d848d0f6a6354450059e81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 23 Apr 2016 11:35:46 -0700 Subject: net/mlx4_en: fix spurious timestamping callbacks When multiple skb are TX-completed in a row, we might incorrectly keep a timestamp of a prior skb and cause extra work. Fixes: ec693d47010e8 ("net/mlx4_en: Add HW timestamping (TS) support") Signed-off-by: Eric Dumazet Cc: Willem de Bruijn Reviewed-by: Eran Ben Elisha Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index c0d7b72..a386f04 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -405,7 +405,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, u32 packets = 0; u32 bytes = 0; int factor = priv->cqe_factor; - u64 timestamp = 0; int done = 0; int budget = priv->tx_work_limit; u32 last_nr_txbb; @@ -445,9 +444,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, new_index = be16_to_cpu(cqe->wqe_index) & size_mask; do { + u64 timestamp = 0; + txbbs_skipped += last_nr_txbb; ring_index = (ring_index + last_nr_txbb) & size_mask; - if (ring->tx_info[ring_index].ts_requested) + + if (unlikely(ring->tx_info[ring_index].ts_requested)) timestamp = mlx4_en_get_cqe_ts(cqe); /* free next descriptor */ -- cgit v0.10.2 From 6a923934c33c750a595868af6bef5f1a1fa90054 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 26 Apr 2016 11:47:41 -0400 Subject: Revert "ipv6: Revert optional address flusing on ifdown." This reverts commit 841645b5f2dfceac69b78fcd0c9050868d41ea61. Ok, this puts the feature back. I've decided to apply David A.'s bug fix and run with that rather than make everyone wait another whole release for this feature. Signed-off-by: David S. Miller diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e0ac252..b183e2b 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1568,6 +1568,15 @@ temp_prefered_lft - INTEGER Preferred lifetime (in seconds) for temporary addresses. Default: 86400 (1 day) +keep_addr_on_down - INTEGER + Keep all IPv6 addresses on an interface down event. If set static + global addresses with no expiration time are not flushed. + >0 : enabled + 0 : system default + <0 : disabled + + Default: 0 (addresses are removed) + max_desync_factor - INTEGER Maximum value for DESYNC_FACTOR, which is a random value that ensures that clients don't synchronize with each diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4b2267e..7edc14f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -62,6 +62,7 @@ struct ipv6_devconf { struct in6_addr secret; } stable_secret; __s32 use_oif_addrs_only; + __s32 keep_addr_on_down; void *sysctl; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index ec117b6..3958760 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -176,6 +176,7 @@ enum { DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN, DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, DEVCONF_DROP_UNSOLICITED_NA, + DEVCONF_KEEP_ADDR_ON_DOWN, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d77ba39..23cec53 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -216,6 +216,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -260,6 +261,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { }, .use_oif_addrs_only = 0, .ignore_routes_with_linkdown = 0, + .keep_addr_on_down = 0, }; /* Check if a valid qdisc is available */ @@ -3174,6 +3176,81 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) +/* If the host route is cached on the addr struct make sure it is associated + * with the proper table. e.g., enslavement can change and if so the cached + * host route needs to move to the new table. + */ +static void l3mdev_check_host_rt(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + if (ifp->rt) { + u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; + + if (tb_id != ifp->rt->rt6i_table->tb6_id) { + ip6_del_rt(ifp->rt); + ifp->rt = NULL; + } + } +} +#else +static void l3mdev_check_host_rt(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ +} +#endif + +static int fixup_permanent_addr(struct inet6_dev *idev, + struct inet6_ifaddr *ifp) +{ + l3mdev_check_host_rt(idev, ifp); + + if (!ifp->rt) { + struct rt6_info *rt; + + rt = addrconf_dst_alloc(idev, &ifp->addr, false); + if (unlikely(IS_ERR(rt))) + return PTR_ERR(rt); + + ifp->rt = rt; + } + + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + idev->dev, 0, 0); + } + + addrconf_dad_start(ifp); + + return 0; +} + +static void addrconf_permanent_addr(struct net_device *dev) +{ + struct inet6_ifaddr *ifp, *tmp; + struct inet6_dev *idev; + + idev = __in6_dev_get(dev); + if (!idev) + return; + + write_lock_bh(&idev->lock); + + list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { + if ((ifp->flags & IFA_F_PERMANENT) && + fixup_permanent_addr(idev, ifp) < 0) { + write_unlock_bh(&idev->lock); + ipv6_del_addr(ifp); + write_lock_bh(&idev->lock); + + net_info_ratelimited("%s: Failed to add prefix route for address %pI6c; dropping\n", + idev->dev->name, &ifp->addr); + } + } + + write_unlock_bh(&idev->lock); +} + static int addrconf_notify(struct notifier_block *this, unsigned long event, void *ptr) { @@ -3260,6 +3337,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3368,11 +3448,20 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event) ipv6_mc_unmap(idev); } +static bool addr_is_local(const struct in6_addr *addr) +{ + return ipv6_addr_type(addr) & + (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); +} + static int addrconf_ifdown(struct net_device *dev, int how) { struct net *net = dev_net(dev); struct inet6_dev *idev; - struct inet6_ifaddr *ifa; + struct inet6_ifaddr *ifa, *tmp; + struct list_head del_list; + int _keep_addr; + bool keep_addr; int state, i; ASSERT_RTNL(); @@ -3399,6 +3488,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) } + /* aggregate the system setting and interface setting */ + _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + /* combine the user config with event to determine if permanent + * addresses are to be removed from address hash table + */ + keep_addr = !(how || _keep_addr <= 0); + /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { struct hlist_head *h = &inet6_addr_lst[i]; @@ -3407,9 +3506,16 @@ static int addrconf_ifdown(struct net_device *dev, int how) restart: hlist_for_each_entry_rcu(ifa, h, addr_lst) { if (ifa->idev == idev) { - hlist_del_init_rcu(&ifa->addr_lst); addrconf_del_dad_work(ifa); - goto restart; + /* combined flag + permanent flag decide if + * address is retained on a down event + */ + if (!keep_addr || + !(ifa->flags & IFA_F_PERMANENT) || + addr_is_local(&ifa->addr)) { + hlist_del_init_rcu(&ifa->addr_lst); + goto restart; + } } } spin_unlock_bh(&addrconf_hash_lock); @@ -3443,31 +3549,54 @@ restart: write_lock_bh(&idev->lock); } - while (!list_empty(&idev->addr_list)) { - ifa = list_first_entry(&idev->addr_list, - struct inet6_ifaddr, if_list); - addrconf_del_dad_work(ifa); + /* re-combine the user config with event to determine if permanent + * addresses are to be removed from the interface list + */ + keep_addr = (!how && _keep_addr > 0); - list_del(&ifa->if_list); + INIT_LIST_HEAD(&del_list); + list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); - spin_lock_bh(&ifa->lock); - state = ifa->state; - ifa->state = INET6_IFADDR_STATE_DEAD; + + if (keep_addr && (ifa->flags & IFA_F_PERMANENT) && + !addr_is_local(&ifa->addr)) { + /* set state to skip the notifier below */ + state = INET6_IFADDR_STATE_DEAD; + ifa->state = 0; + if (!(ifa->flags & IFA_F_NODAD)) + ifa->flags |= IFA_F_TENTATIVE; + } else { + state = ifa->state; + ifa->state = INET6_IFADDR_STATE_DEAD; + + list_del(&ifa->if_list); + list_add(&ifa->if_list, &del_list); + } + spin_unlock_bh(&ifa->lock); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } - in6_ifa_put(ifa); write_lock_bh(&idev->lock); } write_unlock_bh(&idev->lock); + /* now clean up addresses to be removed */ + while (!list_empty(&del_list)) { + ifa = list_first_entry(&del_list, + struct inet6_ifaddr, if_list); + list_del(&ifa->if_list); + + in6_ifa_put(ifa); + } + /* Step 5: Discard anycast and multicast list */ if (how) { ipv6_ac_destroy_dev(idev); @@ -4732,6 +4861,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_USE_OIF_ADDRS_ONLY] = cnf->use_oif_addrs_only; array[DEVCONF_DROP_UNICAST_IN_L2_MULTICAST] = cnf->drop_unicast_in_l2_multicast; array[DEVCONF_DROP_UNSOLICITED_NA] = cnf->drop_unsolicited_na; + array[DEVCONF_KEEP_ADDR_ON_DOWN] = cnf->keep_addr_on_down; } static inline size_t inet6_ifla6_size(void) @@ -5820,6 +5950,14 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "keep_addr_on_down", + .data = &ipv6_devconf.keep_addr_on_down, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + + }, + { /* sentinel */ } }, -- cgit v0.10.2 From 38bd10c447f8e8980753149a8a65108159871df5 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 21 Apr 2016 20:56:12 -0700 Subject: net: ipv6: Delete host routes on an ifdown It was a simple idea -- save IPv6 configured addresses on a link down so that IPv6 behaves similar to IPv4. As always the devil is in the details and the IPv6 stack as too many behavioral differences from IPv4 making the simple idea more complicated than it needs to be. The current implementation for keeping IPv6 addresses can panic or spit out a warning in one of many paths: 1. IPv6 route gets an IPv4 route as its 'next' which causes a panic in rt6_fill_node while handling a route dump request. 2. rt->dst.obsolete is set to DST_OBSOLETE_DEAD hitting the WARN_ON in fib6_del 3. Panic in fib6_purge_rt because rt6i_ref count is not 1. The root cause of all these is references related to the host route for an address that is retained. So, this patch deletes the host route every time the ifdown loop runs. Since the host route is deleted and will be re-generated an up there is no longer a need for the l3mdev fix up. On the 'admin up' side move addrconf_permanent_addr into the NETDEV_UP event handling so that it runs only once versus on UP and CHANGE events. All of the current panics and warnings appear to be related to addresses on the loopback device, but given the catastrophic nature when a bug is triggered this patch takes the conservative approach and evicts all host routes rather than trying to determine when it can be re-used and when it can not. That can be a later optimizaton if desired. Signed-off-by: David Ahern Signed-off-by: David S. Miller diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cec53..8ec4b30 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3176,35 +3176,9 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) -/* If the host route is cached on the addr struct make sure it is associated - * with the proper table. e.g., enslavement can change and if so the cached - * host route needs to move to the new table. - */ -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - if (ifp->rt) { - u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - - if (tb_id != ifp->rt->rt6i_table->tb6_id) { - ip6_del_rt(ifp->rt); - ifp->rt = NULL; - } - } -} -#else -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ -} -#endif - static int fixup_permanent_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - l3mdev_check_host_rt(idev, ifp); - if (!ifp->rt) { struct rt6_info *rt; @@ -3304,6 +3278,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; if (event == NETDEV_UP) { + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + if (!addrconf_qdisc_ok(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", @@ -3337,9 +3314,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); - switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3556,6 +3530,8 @@ restart: INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + struct rt6_info *rt = NULL; + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); @@ -3568,6 +3544,9 @@ restart: ifa->state = 0; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; + + rt = ifa->rt; + ifa->rt = NULL; } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; @@ -3578,6 +3557,9 @@ restart: spin_unlock_bh(&ifa->lock); + if (rt) + ip6_del_rt(rt); + if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); @@ -5343,10 +5325,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); - + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + } rt_genid_bump_ipv6(net); break; } -- cgit v0.10.2 From 8358b02bf67d3a5d8a825070e1aa73f25fb2e4c7 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 26 Apr 2016 22:26:26 +0200 Subject: bpf: fix double-fdput in replace_map_fd_with_map_ptr() When bpf(BPF_PROG_LOAD, ...) was invoked with a BPF program whose bytecode references a non-map file descriptor as a map file descriptor, the error handling code called fdput() twice instead of once (in __bpf_map_get() and in replace_map_fd_with_map_ptr()). If the file descriptor table of the current task is shared, this causes f_count to be decremented too much, allowing the struct file to be freed while it is still in use (use-after-free). This can be exploited to gain root privileges by an unprivileged user. This bug was introduced in commit 0246e64d9a5f ("bpf: handle pseudo BPF_LD_IMM64 insn"), but is only exploitable since commit 1be7f75d1668 ("bpf: enable non-root eBPF programs") because previously, CAP_SYS_ADMIN was required to reach the vulnerable code. (posted publicly according to request by maintainer) Signed-off-by: Jann Horn Signed-off-by: Linus Torvalds Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 618ef77..db2574e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2030,7 +2030,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) if (IS_ERR(map)) { verbose("fd %d is not pointing to valid bpf_map\n", insn->imm); - fdput(f); return PTR_ERR(map); } -- cgit v0.10.2