/* * This file implement the Wireless Extensions spy API. * * Authors : Jean Tourrilhes - HPL - * Copyright (c) 1997-2007 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ #include #include #include #include #include #include #include static inline struct iw_spy_data *get_spydata(struct net_device *dev) { /* This is the new way */ if (dev->wireless_data) return dev->wireless_data->spy_data; return NULL; } int iw_handler_set_spy(struct net_device * dev, struct iw_request_info * info, union iwreq_data * wrqu, char * extra) { struct iw_spy_data * spydata = get_spydata(dev); struct sockaddr * address = (struct sockaddr *) extra; /* Make sure driver is not buggy or using the old API */ if (!spydata) return -EOPNOTSUPP; /* Disable spy collection while we copy the addresses. * While we copy addresses, any call to wireless_spy_update() * will NOP. This is OK, as anyway the addresses are changing. */ spydata->spy_number = 0; /* We want to operate without locking, because wireless_spy_update() * most likely will happen in the interrupt handler, and therefore * have its own locking constraints and needs performance. * The rtnl_lock() make sure we don't race with the other iw_handlers. * This make sure wireless_spy_update() "see" that the spy list * is temporarily disabled. */ smp_wmb(); /* Are there are addresses to copy? */ if (wrqu->data.length > 0) { int i; /* Copy addresses */ for (i = 0; i < wrqu->data.length; i++) memcpy(spydata->spy_address[i], address[i].sa_data, ETH_ALEN); /* Reset stats */ memset(spydata->spy_stat, 0, sizeof(struct iw_quality) * IW_MAX_SPY); } /* Make sure above is updated before re-enabling */ smp_wmb(); /* Enable addresses */ spydata->spy_number = wrqu->data.length; return 0; } EXPORT_SYMBOL(iw_handler_set_spy); int iw_handler_get_spy(struct net_device * dev, struct iw_request_info * info, union iwreq_data * wrqu, char * extra) { struct iw_spy_data * spydata = get_spydata(dev); struct sockaddr * address = (struct sockaddr *) extra; int i; /* Make sure driver is not buggy or using the old API */ if (!spydata) return -EOPNOTSUPP; wrqu->data.length = spydata->spy_number; /* Copy addresses. */ for (i = 0; i < spydata->spy_number; i++) { memcpy(address[i].sa_data, spydata->spy_address[i], ETH_ALEN); address[i].sa_family = AF_UNIX; } /* Copy stats to the user buffer (just after). */ if (spydata->spy_number > 0) memcpy(extra + (sizeof(struct sockaddr) *spydata->spy_number), spydata->spy_stat, sizeof(struct iw_quality) * spydata->spy_number); /* Reset updated flags. */ for (i = 0; i < spydata->spy_number; i++) spydata->spy_stat[i].updated &= ~IW_QUAL_ALL_UPDATED; return 0; } EXPORT_SYMBOL(iw_handler_get_spy); /*------------------------------------------------------------------*/ /* * Standard Wireless Handler : set spy threshold */ int iw_handler_set_thrspy(struct net_device * dev, struct iw_request_info *info, union iwreq_data * wrqu, char * extra) { struct iw_spy_data * spydata = get_spydata(dev); struct iw_thrspy * threshold = (struct iw_thrspy *) extra; /* Make sure driver is not buggy or using the old API */ if (!spydata) return -EOPNOTSUPP; /* Just do it */ memcpy(&(spydata->spy_thr_low), &(threshold->low), 2 * sizeof(struct iw_quality)); /* Clear flag */ memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); return 0; } EXPORT_SYMBOL(iw_handler_set_thrspy); /*------------------------------------------------------------------*/ /* * Standard Wireless Handler : get spy threshold */ int iw_handler_get_thrspy(struct net_device * dev, struct iw_request_info *info, union iwreq_data * wrqu, char * extra) { struct iw_spy_data * spydata = get_spydata(dev); struct iw_thrspy * threshold = (struct iw_thrspy *) extra; /* Make sure driver is not buggy or using the old API */ if (!spydata) return -EOPNOTSUPP; /* Just do it */ memcpy(&(threshold->low), &(spydata->spy_thr_low), 2 * sizeof(struct iw_quality)); return 0; } EXPORT_SYMBOL(iw_handler_get_thrspy); /*------------------------------------------------------------------*/ /* * Prepare and send a Spy Threshold event */ static void iw_send_thrspy_event(struct net_device * dev, struct iw_spy_data * spydata, unsigned char * address, struct iw_quality * wstats) { union iwreq_data wrqu; struct iw_thrspy threshold; /* Init */ wrqu.data.length = 1; wrqu.data.flags = 0; /* Copy address */ memcpy(threshold.addr.sa_data, address, ETH_ALEN); threshold.addr.sa_family = ARPHRD_ETHER; /* Copy stats */ memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); /* Copy also thresholds */ memcpy(&(threshold.low), &(spydata->spy_thr_low), 2 * sizeof(struct iw_quality)); /* Send event to user space */ wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); } /* ---------------------------------------------------------------- */ /* * Call for the driver to update the spy data. * For now, the spy data is a simple array. As the size of the array is * small, this is good enough. If we wanted to support larger number of * spy addresses, we should use something more efficient... */ void wireless_spy_update(struct net_device * dev, unsigned char * address, struct iw_quality * wstats) { struct iw_spy_data * spydata = get_spydata(dev); int i; int match = -1; /* Make sure driver is not buggy or using the old API */ if (!spydata) return; /* Update all records that match */ for (i = 0; i < spydata->spy_number; i++) if (ether_addr_equal(address, spydata->spy_address[i])) { memcpy(&(spydata->spy_stat[i]), wstats, sizeof(struct iw_quality)); match = i; } /* Generate an event if we cross the spy threshold. * To avoid event storms, we have a simple hysteresis : we generate * event only when we go under the low threshold or above the * high threshold. */ if (match >= 0) { if (spydata->spy_thr_under[match]) { if (wstats->level > spydata->spy_thr_high.level) { spydata->spy_thr_under[match] = 0; iw_send_thrspy_event(dev, spydata, address, wstats); } } else { if (wstats->level < spydata->spy_thr_low.level) { spydata->spy_thr_under[match] = 1; iw_send_thrspy_event(dev, spydata, address, wstats); } } } } EXPORT_SYMBOL(wireless_spy_update); by bridge driver to send tunnel metadata to bridge ports in vlan tunnel mode. This patch also adds new per port flag IFLA_BRPORT_VLAN_TUNNEL to enable vlan tunnel mode. off by default. One example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). User can configure per-vlan tunnel information which the bridge driver can use to bridge vlan into the corresponding vn-segment. Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03vxlan: support fdb and learning in COLLECT_METADATA modeRoopa Prabhu1-0/+1 Vxlan COLLECT_METADATA mode today solves the per-vni netdev scalability problem in l3 networks. It expects all forwarding information to be present in dst_metadata. This patch series enhances collect metadata mode to include the case where only vni is present in dst_metadata, and the vxlan driver can then use the rest of the forwarding information datbase to make forwarding decisions. There is no change to default COLLECT_METADATA behaviour. These changes only apply to COLLECT_METADATA when used with the bridging use-case with a special dst_metadata tunnel info flag (eg: where vxlan device is part of a bridge). For all this to work, the vxlan driver will need to now support a single fdb table hashed by mac + vni. This series essentially makes this happen. use-case and workflow: vxlan collect metadata device participates in bridging vlan to vn-segments. Bridge driver above the vxlan device, sends the vni corresponding to the vlan in the dst_metadata. vxlan driver will lookup forwarding database with (mac + vni) for the required remote destination information to forward the packet. Changes introduced by this patch: - allow learning and forwarding database state in vxlan netdev in COLLECT_METADATA mode. Current behaviour is not changed by default. tunnel info flag IP_TUNNEL_INFO_BRIDGE is used to support the new bridge friendly mode. - A single fdb table hashed by (mac, vni) to allow fdb entries with multiple vnis in the same fdb table - rx path already has the vni - tx path expects a vni in the packet with dst_metadata - prior to this series, fdb remote_dsts carried remote vni and the vxlan device carrying the fdb table represented the source vni. With the vxlan device now representing multiple vnis, this patch adds a src vni attribute to the fdb entry. The remote vni already uses NDA_VNI attribute. This patch introduces NDA_SRC_VNI netlink attribute to represent the src vni in a multi vni fdb table. iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's. before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metadata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Change to use ife moduleYotam Gigi1-9/+1 Use the encode/decode functionality from the ife module instead of using implementation inside the act_ife. Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net: Introduce ife encapsulation moduleYotam Gigi2-0/+19 This module is responsible for the ife encapsulation protocol encode/decode logics. That module can: - ife_encode: encode skb and reserve space for the ife meta header - ife_decode: decode skb and extract the meta header size - ife_tlv_meta_encode - encodes one tlv entry into the reserved ife header space. - ife_tlv_meta_decode - decodes one tlv entry from the packet - ife_tlv_meta_next - advance to the next tlv Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02net: add LINUX_MIB_PFMEMALLOCDROP counterEric Dumazet1-0/+1 Debugging issues caused by pfmemalloc is often tedious. Add a new SNMP counter to more easily diagnose these problems. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Josef Bacik <jbacik@fb.com> Acked-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02unix: add ioctl to open a unix socket file with O_PATHAndrey Vagin1-0/+2 This ioctl opens a file to which a socket is bound and returns a file descriptor. The caller has to have CAP_NET_ADMIN in the socket network namespace. Currently it is impossible to get a path and a mount point for a socket file. socket_diag reports address, device ID and inode number for unix sockets. An address can contain a relative path or a file may be moved somewhere. And these properties say nothing about a mount namespace and a mount point of a socket file. With the introduced ioctl, we can get a path by reading /proc/self/fd/X and get mnt_id from /proc/self/fdinfo/X. In CRIU we are going to use this ioctl to dump and restore unix socket. Here is an example how it can be used: $ strace -e socket,bind,ioctl ./test /tmp/test_sock socket(AF_UNIX, SOCK_STREAM, 0) = 3 bind(3, {sa_family=AF_UNIX, sun_path="test_sock"}, 11) = 0 ioctl(3, SIOCUNIXFILE, 0) = 4 ^Z $ ss -a | grep test_sock u_str LISTEN 0 1 test_sock 17798 * 0 $ ls -l /proc/760/fd/{3,4} lrwx------ 1 root root 64 Feb 1 09:41 3 -> 'socket:[17798]' l--------- 1 root root 64 Feb 1 09:41 4 -> /tmp/test_sock $ cat /proc/760/fdinfo/4 pos: 0 flags: 012000000 mnt_id: 40 $ cat /proc/self/mountinfo | grep "^40\s" 40 19 0:37 / /tmp rw shared:23 - tmpfs tmpfs rw Signed-off-by: Andrei Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller1-1/+3 All merge conflicts were simple overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>