From df8a39defad46b83694ea6dd868d332976d62cc0 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 13 Jan 2015 17:13:44 +0100 Subject: net: rename vlan_tx_* helpers since "tx" is misleading there The same macros are used for rx as well. So rename it. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/openvswitch/datapath.c') diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 4e9a5f035cbc..54854e3ecd83 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -419,7 +419,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, if (!dp_ifindex) return -ENODEV; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; -- cgit v1.2.3 From 053c095a82cf773075e83d7233b5cc19a1f73ece Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 16 Jan 2015 22:09:00 +0100 Subject: netlink: make nlmsg_end() and genlmsg_end() void Contrary to common expectations for an "int" return, these functions return only a positive value -- if used correctly they cannot even return 0 because the message header will necessarily be in the skb. This makes the very common pattern of if (genlmsg_end(...) < 0) { ... } be a whole bunch of dead code. Many places also simply do return nlmsg_end(...); and the caller is expected to deal with it. This also commonly (at least for me) causes errors, because it is very common to write if (my_function(...)) /* error condition */ and if my_function() does "return nlmsg_end()" this is of course wrong. Additionally, there's not a single place in the kernel that actually needs the message length returned, and if anyone needs it later then it'll be very easy to just use skb->len there. Remove this, and make the functions void. This removes a bunch of dead code as described above. The patch adds lines because I did - return nlmsg_end(...); + nlmsg_end(...); + return 0; I could have preserved all the function's return values by returning skb->len, but instead I've audited all the places calling the affected functions and found that none cared. A few places actually compared the return value with <= 0 in dump functionality, but that could just be changed to < 0 with no change in behaviour, so I opted for the more efficient version. One instance of the error I've made numerous times now is also present in net/phonet/pn_netlink.c in the route_dumpit() function - it didn't check for <0 or <=0 and thus broke out of the loop every single time. I've preserved this since it will (I think) have caused the messages to userspace to be formatted differently with just a single message for every SKB returned to userspace. It's possible that this isn't needed for the tools that actually use this, but I don't even know what they are so couldn't test that changing this behaviour would be acceptable. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- drivers/acpi/event.c | 7 +------ drivers/net/ethernet/rocker/rocker.c | 3 ++- drivers/net/vxlan.c | 3 ++- drivers/net/wireless/mac80211_hwsim.c | 3 ++- drivers/scsi/pmcraid.c | 8 +------- drivers/target/target_core_user.c | 4 +--- drivers/thermal/thermal_core.c | 6 +----- fs/dlm/netlink.c | 7 +------ include/net/genetlink.h | 4 ++-- include/net/netlink.h | 6 +----- kernel/taskstats.c | 13 ++----------- net/bridge/br_fdb.c | 3 ++- net/bridge/br_mdb.c | 3 ++- net/bridge/br_netlink.c | 3 ++- net/can/gw.c | 3 ++- net/core/fib_rules.c | 3 ++- net/core/neighbour.c | 12 ++++++++---- net/core/rtnetlink.c | 9 ++++++--- net/decnet/dn_dev.c | 3 ++- net/decnet/dn_route.c | 3 ++- net/decnet/dn_table.c | 3 ++- net/ieee802154/netlink.c | 12 ++---------- net/ieee802154/nl-mac.c | 3 ++- net/ieee802154/nl-phy.c | 3 ++- net/ieee802154/nl802154.c | 6 ++++-- net/ipv4/devinet.c | 8 +++++--- net/ipv4/fib_semantics.c | 3 ++- net/ipv4/inet_diag.c | 9 ++++++--- net/ipv4/ipmr.c | 3 ++- net/ipv4/route.c | 3 ++- net/ipv4/tcp_metrics.c | 3 ++- net/ipv6/addrconf.c | 32 +++++++++++++++++++------------- net/ipv6/addrlabel.c | 5 +++-- net/ipv6/ip6_fib.c | 1 - net/ipv6/ip6mr.c | 3 ++- net/ipv6/route.c | 3 ++- net/l2tp/l2tp_netlink.c | 10 ++++++---- net/netfilter/ipvs/ip_vs_ctl.c | 9 ++++++--- net/netfilter/nf_tables_api.c | 18 ++++++++++++------ net/netlabel/netlabel_cipso_v4.c | 3 ++- net/netlabel/netlabel_mgmt.c | 6 ++++-- net/netlabel/netlabel_unlabeled.c | 3 ++- net/netlink/diag.c | 3 ++- net/netlink/genetlink.c | 6 ++++-- net/nfc/netlink.c | 12 +++++++----- net/openvswitch/datapath.c | 9 ++++++--- net/packet/diag.c | 3 ++- net/phonet/pn_netlink.c | 16 +++++++++++----- net/unix/diag.c | 3 ++- net/wireless/nl80211.c | 27 ++++++++++++++++++--------- net/xfrm/xfrm_user.c | 27 ++++++++++++++++++--------- 51 files changed, 203 insertions(+), 158 deletions(-) (limited to 'net/openvswitch/datapath.c') diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index ef2d730734dc..e24ea4e796e4 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -100,7 +100,6 @@ int acpi_bus_generate_netlink_event(const char *device_class, struct acpi_genl_event *event; void *msg_header; int size; - int result; /* allocate memory */ size = nla_total_size(sizeof(struct acpi_genl_event)) + @@ -137,11 +136,7 @@ int acpi_bus_generate_netlink_event(const char *device_class, event->data = data; /* send multicast genetlink message */ - result = genlmsg_end(skb, msg_header); - if (result < 0) { - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); genlmsg_multicast(&acpi_event_genl_family, skb, 0, 0, GFP_ATOMIC); return 0; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 964d719b150f..d54781e71cd4 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -3674,7 +3674,8 @@ static int rocker_fdb_fill_info(struct sk_buff *skb, if (vid && nla_put_u16(skb, NDA_VLAN, vid)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 6b6b45622a0a..c5f79e7513a6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -363,7 +363,8 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan, if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 494e7335aa64..4a4c6586a8d2 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2557,7 +2557,8 @@ static int mac80211_hwsim_get_radio(struct sk_buff *skb, if (res < 0) goto out_err; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; out_err: genlmsg_cancel(skb, hdr); diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 8c27b6a77ec4..cf222f46eac5 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -1473,13 +1473,7 @@ static int pmcraid_notify_aen( } /* send genetlink multicast message to notify appplications */ - result = genlmsg_end(skb, msg_header); - - if (result < 0) { - pmcraid_err("genlmsg_end failed\n"); - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); result = genlmsg_multicast(&pmcraid_event_family, skb, 0, 0, GFP_ATOMIC); diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 1157b559683b..1a1bcf71ec9d 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -784,9 +784,7 @@ static int tcmu_netlink_event(enum tcmu_genl_cmd cmd, const char *name, int mino if (ret < 0) goto free_skb; - ret = genlmsg_end(skb, msg_header); - if (ret < 0) - goto free_skb; + genlmsg_end(skb, msg_header); ret = genlmsg_multicast(&tcmu_genl_family, skb, 0, TCMU_MCGRP_CONFIG, GFP_KERNEL); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 87e0b0782023..48491d1a81d6 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1759,11 +1759,7 @@ int thermal_generate_netlink_event(struct thermal_zone_device *tz, thermal_event->event = event; /* send multicast genetlink message */ - result = genlmsg_end(skb, msg_header); - if (result < 0) { - nlmsg_free(skb); - return result; - } + genlmsg_end(skb, msg_header); result = genlmsg_multicast(&thermal_event_genl_family, skb, 0, 0, GFP_ATOMIC); diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index e7cfbaf8d0e2..1e6e227134d7 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -56,13 +56,8 @@ static int send_data(struct sk_buff *skb) { struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data); void *data = genlmsg_data(genlhdr); - int rv; - rv = genlmsg_end(skb, data); - if (rv < 0) { - nlmsg_free(skb); - return rv; - } + genlmsg_end(skb, data); return genlmsg_unicast(&init_net, skb, listener_nlportid); } diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 84125088c309..f24aa83b80b6 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -245,9 +245,9 @@ static inline void *genlmsg_put_reply(struct sk_buff *skb, * @skb: socket buffer the message is stored in * @hdr: user specific header */ -static inline int genlmsg_end(struct sk_buff *skb, void *hdr) +static inline void genlmsg_end(struct sk_buff *skb, void *hdr) { - return nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); + nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN); } /** diff --git a/include/net/netlink.h b/include/net/netlink.h index d5869b90bfbb..e010ee8da41d 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -490,14 +490,10 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) * Corrects the netlink message header to include the appeneded * attributes. Only necessary if attributes have been added to * the message. - * - * Returns the total data length of the skb. */ -static inline int nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) +static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; - - return skb->len; } /** diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 670fff88a961..21f82c29c914 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -111,13 +111,8 @@ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); - int rc; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return rc; - } + genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } @@ -134,11 +129,7 @@ static void send_cpu_listeners(struct sk_buff *skb, void *reply = genlmsg_data(genlhdr); int rc, delcount = 0; - rc = genlmsg_end(skb, reply); - if (rc < 0) { - nlmsg_free(skb); - return; - } + genlmsg_end(skb, reply); rc = 0; down_read(&listeners->sem); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 03667e65cc29..08bf04bdac58 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -633,7 +633,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, if (fdb->vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index fed61c971b17..409608960899 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -190,7 +190,8 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb, nla_nest_end(skb, nest2); nla_nest_end(skb, nest); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; end: nla_nest_end(skb, nest); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 163950b10d8c..528cf2790a5f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -263,7 +263,8 @@ static int br_fill_ifinfo(struct sk_buff *skb, } done: - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/can/gw.c b/net/can/gw.c index 295f62e62eb3..a6f448e18ea8 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -575,7 +575,8 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; cancel: nlmsg_cancel(skb, nlh); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 185c341fafbd..44706e81b2e0 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -609,7 +609,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8d614c93f86a..d36d564f149f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1884,7 +1884,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, goto nla_put_failure; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: read_unlock_bh(&tbl->lock); @@ -1917,7 +1918,8 @@ static int neightbl_fill_param_info(struct sk_buff *skb, goto errout; read_unlock_bh(&tbl->lock); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); @@ -2202,7 +2204,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2232,7 +2235,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eadc5c0e2dfa..e13b9dbdf154 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1199,7 +1199,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, af_spec); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2326,7 +2327,8 @@ static int nlmsg_populate_fdb_fill(struct sk_buff *skb, if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -2809,7 +2811,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, nla_nest_end(skb, protinfo); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 4400da7739da..b2c26b081134 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -702,7 +702,8 @@ static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || nla_put_u32(skb, IFA_FLAGS, ifa_flags)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index daccc4a36d80..812e5e6e88fb 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1616,7 +1616,8 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq, nla_put_u32(skb, RTA_IIF, rt->fld.flowidn_iif) < 0) goto errout; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 3f19fcbf126d..1540b506e3e0 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -367,7 +367,8 @@ static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_nest_end(skb, mp_head); } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index fa1464762d0d..c8133c07ceee 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -63,13 +63,9 @@ int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group) struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); - if (genlmsg_end(msg, hdr) < 0) - goto out; + genlmsg_end(msg, hdr); return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC); -out: - nlmsg_free(msg); - return -ENOBUFS; } struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info, @@ -96,13 +92,9 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info) struct nlmsghdr *nlh = nlmsg_hdr(msg); void *hdr = genlmsg_data(nlmsg_data(nlh)); - if (genlmsg_end(msg, hdr) < 0) - goto out; + genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); -out: - nlmsg_free(msg); - return -ENOBUFS; } static const struct genl_ops ieee8021154_ops[] = { diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 3c902e9516fb..9105265920fe 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -136,7 +136,8 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, } wpan_phy_put(phy); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: wpan_phy_put(phy); diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 7baf98b14611..1b9d25f6e898 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -65,7 +65,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, goto nla_put_failure; mutex_unlock(&phy->pib_lock); kfree(buf); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: mutex_unlock(&phy->pib_lock); diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index a25b9bbd077b..a4daf91b8d0a 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -306,7 +306,8 @@ static int nl802154_send_wpan_phy(struct cfg802154_registered_device *rdev, goto nla_put_failure; finish: - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -489,7 +490,8 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, if (nla_put_u8(msg, NL802154_ATTR_LBT_MODE, wpan_dev->lbt)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 214882e7d6de..5f344eb3fc25 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1522,7 +1522,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, preferred, valid)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -1566,7 +1567,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) <= 0) { + RTM_NEWADDR, NLM_F_MULTI) < 0) { rcu_read_unlock(); goto done; } @@ -1749,7 +1750,8 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d2b7b5521b1b..265cb72b7c1b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1091,7 +1091,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_nest_end(skb, mp); } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e34dccbc4d70..81751f12645f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -203,7 +203,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, icsk->icsk_ca_ops->get_info(sk, ext, skb); out: - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; errout: nlmsg_cancel(skb, nlh); @@ -271,7 +272,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, @@ -758,7 +760,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, } #endif - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c8034587859d..9d78427652d2 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2290,7 +2290,8 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, if (err < 0 && err != -ENOENT) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce112d0f2698..f6e43ca5e641 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2390,7 +2390,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index ed9c9a91851c..e5f41bd5ec1b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -886,7 +886,8 @@ static int tcp_metrics_dump_info(struct sk_buff *skb, if (tcp_metrics_fill_info(skb, tm) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7c8bbeb27b7..8975d9501d50 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -489,7 +489,8 @@ static int inet6_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, devconf->proxy_ndp) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -619,7 +620,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) { + -1) < 0) { rcu_read_unlock(); goto done; } @@ -635,7 +636,7 @@ cont: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + -1) < 0) goto done; else h++; @@ -646,7 +647,7 @@ cont: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, - -1) <= 0) + -1) < 0) goto done; else h++; @@ -4047,7 +4048,8 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) goto error; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; error: nlmsg_cancel(skb, nlh); @@ -4076,7 +4078,8 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, @@ -4101,7 +4104,8 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } enum addr_type_t { @@ -4134,7 +4138,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } @@ -4151,7 +4155,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_GETMULTICAST, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } break; @@ -4166,7 +4170,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_GETANYCAST, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } break; @@ -4638,7 +4642,8 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, goto nla_put_failure; nla_nest_end(skb, protoinfo); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -4670,7 +4675,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWLINK, NLM_F_MULTI) <= 0) + RTM_NEWLINK, NLM_F_MULTI) < 0) goto out; cont: idx++; @@ -4747,7 +4752,8 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, ci.valid_time = ntohl(pinfo->valid); if (nla_put(skb, PREFIX_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index fd0dc47f471d..e43e79d0a612 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -490,7 +490,8 @@ static int ip6addrlbl_fill(struct sk_buff *skb, return -EMSGSIZE; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -510,7 +511,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI); - if (err <= 0) + if (err < 0) break; } idx++; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 03c520a4ebeb..53775ee7d376 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w) w->leaf = rt; return 1; } - WARN_ON(res == 0); } w->leaf = NULL; return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 722669754bbf..34b682617f50 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2388,7 +2388,8 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, if (err < 0 && err != -ENOENT) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 34dcbb59df75..c60f15775c53 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2725,7 +2725,8 @@ static int rt6_fill_node(struct net *net, if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 6b16598f31d5..b4e923f77954 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -390,7 +390,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla } out: - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -451,7 +452,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - tunnel, L2TP_CMD_TUNNEL_GET) <= 0) + tunnel, L2TP_CMD_TUNNEL_GET) < 0) goto out; ti++; @@ -752,7 +753,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl goto nla_put_failure; nla_nest_end(skb, nest); - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -816,7 +818,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - session, L2TP_CMD_SESSION_GET) <= 0) + session, L2TP_CMD_SESSION_GET) < 0) break; si++; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b8295a430a56..e55759056361 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2887,7 +2887,8 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb, if (ip_vs_genl_fill_service(skb, svc) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -3079,7 +3080,8 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, if (ip_vs_genl_fill_dest(skb, dest) < 0) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -3215,7 +3217,8 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state, if (ip_vs_genl_fill_daemon(skb, state, mcast_ifn, syncid)) goto nla_put_failure; - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3b3ddb4fb9ee..70f697827b9b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -427,7 +427,8 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -971,7 +972,8 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -1707,7 +1709,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, nla_put(skb, NFTA_RULE_USERDATA, rule->ulen, nft_userdata(rule))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -2361,7 +2364,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, goto nla_put_failure; nla_nest_end(skb, desc); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -3035,7 +3039,8 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, nla_nest_end(skb, nest); - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); @@ -3324,7 +3329,8 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq))) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_trim(skb, nlh); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index c2f2a53a4879..179625353cac 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -641,7 +641,8 @@ static int netlbl_cipsov4_listall_cb(struct cipso_v4_doi *doi_def, void *arg) if (ret_val != 0) goto listall_cb_failure; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index e66e977ef2fa..8b3b789c43c2 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -456,7 +456,8 @@ static int netlbl_mgmt_listall_cb(struct netlbl_dom_map *entry, void *arg) goto listall_cb_failure; cb_arg->seq++; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; listall_cb_failure: genlmsg_cancel(cb_arg->skb, data); @@ -620,7 +621,8 @@ static int netlbl_mgmt_protocols_cb(struct sk_buff *skb, if (ret_val != 0) goto protocols_cb_failure; - return genlmsg_end(skb, data); + genlmsg_end(skb, data); + return 0; protocols_cb_failure: genlmsg_cancel(skb, data); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 78a63c18779e..aec7994f78cf 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1163,7 +1163,8 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, goto list_cb_failure; cb_arg->seq++; - return genlmsg_end(cb_arg->skb, data); + genlmsg_end(cb_arg->skb, data); + return 0; list_cb_failure: genlmsg_cancel(cb_arg->skb, data); diff --git a/net/netlink/diag.c b/net/netlink/diag.c index bb59a7ed0859..3ee63a3cff30 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -91,7 +91,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, sk_diag_put_rings_cfg(sk, skb)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2e11061ef885..f52a7d5734cd 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -756,7 +756,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq, nla_nest_end(skb, nla_grps); } - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); @@ -796,7 +797,8 @@ static int ctrl_fill_mcgrp_info(struct genl_family *family, nla_nest_end(skb, nest); nla_nest_end(skb, nla_grps); - return genlmsg_end(skb, hdr); + genlmsg_end(skb, hdr); + return 0; nla_put_failure: genlmsg_cancel(skb, hdr); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 44989fc8cddf..be387e6219a0 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -102,7 +102,8 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, goto nla_put_failure; } - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -518,7 +519,8 @@ static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, nla_put_u8(msg, NFC_ATTR_RF_MODE, dev->rf_mode)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -908,7 +910,8 @@ static int nfc_genl_send_params(struct sk_buff *msg, nla_put_u16(msg, NFC_ATTR_LLC_PARAM_MIUX, be16_to_cpu(local->miux))) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: @@ -1247,8 +1250,7 @@ static int nfc_genl_send_se(struct sk_buff *msg, struct nfc_dev *dev, nla_put_u8(msg, NFC_ATTR_SE_TYPE, se->type)) goto nla_put_failure; - if (genlmsg_end(msg, hdr) < 0) - goto nla_put_failure; + genlmsg_end(msg, hdr); } return 0; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 8bda3cc12344..f45f1bf4422c 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -799,7 +799,8 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, if (err) goto error; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; error: genlmsg_cancel(skb, ovs_header); @@ -1349,7 +1350,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, if (nla_put_u32(skb, OVS_DP_ATTR_USER_FEATURES, dp->user_features)) goto nla_put_failure; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; nla_put_failure: genlmsg_cancel(skb, ovs_header); @@ -1723,7 +1725,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (err == -EMSGSIZE) goto error; - return genlmsg_end(skb, ovs_header); + genlmsg_end(skb, ovs_header); + return 0; nla_put_failure: err = -EMSGSIZE; diff --git a/net/packet/diag.c b/net/packet/diag.c index 92f2c7107eec..0ed68f0238bf 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -177,7 +177,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, PACKET_DIAG_FILTER)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index b64151ade6b3..54d766842c2b 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -121,7 +121,8 @@ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, ifm->ifa_index = dev->ifindex; if (nla_put_u8(skb, IFA_LOCAL, addr)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -190,7 +191,8 @@ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, if (nla_put_u8(skb, RTA_DST, dst) || nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; nla_put_failure: nlmsg_cancel(skb, nlh); @@ -282,9 +284,13 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (addr_idx++ < addr_start_idx) continue; - if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, RTM_NEWROUTE)) - goto out; + fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, RTM_NEWROUTE); + /* fill_route() used to return > 0 (or negative errors) but + * never 0 - ignore the return value and just go out to + * call dumpit again from outside to preserve the behavior + */ + goto out; } out: diff --git a/net/unix/diag.c b/net/unix/diag.c index 86fa0f3b2caf..ef542fbca9fe 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -155,7 +155,8 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (nla_put_u8(skb, UNIX_DIAG_SHUTDOWN, sk->sk_shutdown)) goto out_nlmsg_trim; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_nlmsg_trim: nlmsg_cancel(skb, nlh); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 380784378df8..4ed9039bd5f9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1721,7 +1721,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, break; } finish: - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -2404,7 +2405,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag goto nla_put_failure; } - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -3825,7 +3827,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, sinfo->assoc_req_ies)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -4555,7 +4558,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, nla_nest_end(msg, pinfoattr); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -5507,7 +5511,8 @@ static int nl80211_send_regdom(struct sk_buff *msg, struct netlink_callback *cb, nla_put_flag(msg, NL80211_ATTR_WIPHY_SELF_MANAGED_REG)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -6577,7 +6582,8 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, nla_nest_end(msg, bss); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; fail_unlock_rcu: rcu_read_unlock(); @@ -6686,7 +6692,8 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, nla_nest_end(msg, infoattr); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -11025,7 +11032,8 @@ static int nl80211_send_scan_msg(struct sk_buff *msg, /* ignore errors and send incomplete event anyway */ nl80211_add_scan_req(msg, rdev); - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); @@ -11048,7 +11056,8 @@ nl80211_send_sched_scan_msg(struct sk_buff *msg, nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex)) goto nla_put_failure; - return genlmsg_end(msg, hdr); + genlmsg_end(msg, hdr); + return 0; nla_put_failure: genlmsg_cancel(msg, hdr); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8128594ab379..7de2ed9ec46d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1019,7 +1019,8 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_set_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1121,7 +1122,8 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1842,7 +1844,8 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_cancel: nlmsg_cancel(skb, nlh); @@ -2282,7 +2285,8 @@ static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, goto out_cancel; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; out_cancel: nlmsg_cancel(skb, nlh); @@ -2490,7 +2494,8 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) @@ -2712,7 +2717,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, return err; } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, @@ -2827,7 +2833,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, } upe->hard = !!hard; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) @@ -2986,7 +2993,8 @@ static int build_report(struct sk_buff *skb, u8 proto, return err; } } - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_report(struct net *net, u8 proto, @@ -3031,7 +3039,8 @@ static int build_mapping(struct sk_buff *skb, struct xfrm_state *x, um->old_sport = x->encap->encap_sport; um->reqid = x->props.reqid; - return nlmsg_end(skb, nlh); + nlmsg_end(skb, nlh); + return 0; } static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, -- cgit v1.2.3 From 5b4237bbc93b1b54d35b037cfc0ece71cd8e358d Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 21 Jan 2015 16:42:48 -0800 Subject: openvswitch: Refactor ovs_nla_fill_match(). Refactor the ovs_nla_fill_match() function into separate netlink serialization functions ovs_nla_put_{unmasked_key,mask}(). Modify ovs_nla_put_flow() to handle attribute nesting and expose the 'is_mask' parameter - all callers need to nest the flow, and callers have better knowledge about whether it is serializing a mask or not. Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/openvswitch/datapath.c | 41 ++++++----------------------------------- net/openvswitch/flow_netlink.c | 38 +++++++++++++++++++++++++++++++++++--- net/openvswitch/flow_netlink.h | 7 +++++-- 3 files changed, 46 insertions(+), 40 deletions(-) (limited to 'net/openvswitch/datapath.c') diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f45f1bf4422c..257b97546b33 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -461,10 +461,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, 0, upcall_info->cmd); upcall->dp_ifindex = dp_ifindex; - nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY); - err = ovs_nla_put_flow(key, key, user_skb); + err = ovs_nla_put_key(key, key, OVS_PACKET_ATTR_KEY, false, user_skb); BUG_ON(err); - nla_nest_end(user_skb, nla); if (upcall_info->userdata) __nla_put(user_skb, OVS_PACKET_ATTR_USERDATA, @@ -675,37 +673,6 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */ } -/* Called with ovs_mutex or RCU read lock. */ -static int ovs_flow_cmd_fill_match(const struct sw_flow *flow, - struct sk_buff *skb) -{ - struct nlattr *nla; - int err; - - /* Fill flow key. */ - nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY); - if (!nla) - return -EMSGSIZE; - - err = ovs_nla_put_flow(&flow->unmasked_key, &flow->unmasked_key, skb); - if (err) - return err; - - nla_nest_end(skb, nla); - - /* Fill flow mask. */ - nla = nla_nest_start(skb, OVS_FLOW_ATTR_MASK); - if (!nla) - return -EMSGSIZE; - - err = ovs_nla_put_flow(&flow->key, &flow->mask->key, skb); - if (err) - return err; - - nla_nest_end(skb, nla); - return 0; -} - /* Called with ovs_mutex or RCU read lock. */ static int ovs_flow_cmd_fill_stats(const struct sw_flow *flow, struct sk_buff *skb) @@ -787,7 +754,11 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, ovs_header->dp_ifindex = dp_ifindex; - err = ovs_flow_cmd_fill_match(flow, skb); + err = ovs_nla_put_unmasked_key(flow, skb); + if (err) + goto error; + + err = ovs_nla_put_mask(flow, skb); if (err) goto error; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d210d1be3470..33751f81bfcb 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1216,12 +1216,12 @@ int ovs_nla_get_flow_metadata(const struct nlattr *attr, return metadata_from_nlattrs(&match, &attrs, a, false, log); } -int ovs_nla_put_flow(const struct sw_flow_key *swkey, - const struct sw_flow_key *output, struct sk_buff *skb) +static int __ovs_nla_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, bool is_mask, + struct sk_buff *skb) { struct ovs_key_ethernet *eth_key; struct nlattr *nla, *encap; - bool is_mask = (swkey != output); if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id)) goto nla_put_failure; @@ -1431,6 +1431,38 @@ nla_put_failure: return -EMSGSIZE; } +int ovs_nla_put_key(const struct sw_flow_key *swkey, + const struct sw_flow_key *output, int attr, bool is_mask, + struct sk_buff *skb) +{ + int err; + struct nlattr *nla; + + nla = nla_nest_start(skb, attr); + if (!nla) + return -EMSGSIZE; + err = __ovs_nla_put_key(swkey, output, is_mask, skb); + if (err) + return err; + nla_nest_end(skb, nla); + + return 0; +} + +/* Called with ovs_mutex or RCU read lock. */ +int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb) +{ + return ovs_nla_put_key(&flow->unmasked_key, &flow->unmasked_key, + OVS_FLOW_ATTR_KEY, false, skb); +} + +/* Called with ovs_mutex or RCU read lock. */ +int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb) +{ + return ovs_nla_put_key(&flow->key, &flow->mask->key, + OVS_FLOW_ATTR_MASK, true, skb); +} + #define MAX_ACTIONS_BUFSIZE (32 * 1024) static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log) diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 577f12be3459..9ed09e66876a 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -43,11 +43,14 @@ size_t ovs_key_attr_size(void); void ovs_match_init(struct sw_flow_match *match, struct sw_flow_key *key, struct sw_flow_mask *mask); -int ovs_nla_put_flow(const struct sw_flow_key *, - const struct sw_flow_key *, struct sk_buff *); +int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, + int attr, bool is_mask, struct sk_buff *); int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *, bool log); +int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb); +int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); + int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, const struct nlattr *mask, bool log); int ovs_nla_put_egress_tunnel_key(struct sk_buff *, -- cgit v1.2.3 From 74ed7ab9264c54471c7f057409d352052820d750 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Wed, 21 Jan 2015 16:42:52 -0800 Subject: openvswitch: Add support for unique flow IDs. Previously, flows were manipulated by userspace specifying a full, unmasked flow key. This adds significant burden onto flow serialization/deserialization, particularly when dumping flows. This patch adds an alternative way to refer to flows using a variable-length "unique flow identifier" (UFID). At flow setup time, userspace may specify a UFID for a flow, which is stored with the flow and inserted into a separate table for lookup, in addition to the standard flow table. Flows created using a UFID must be fetched or deleted using the UFID. All flow dump operations may now be made more terse with OVS_UFID_F_* flags. For example, the OVS_UFID_F_OMIT_KEY flag allows responses to omit the flow key from a datapath operation if the flow has a corresponding UFID. This significantly reduces the time spent assembling and transacting netlink messages. With all OVS_UFID_F_OMIT_* flags enabled, the datapath only returns the UFID and statistics for each flow during flow dump, increasing ovs-vswitchd revalidator performance by 40% or more. Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- Documentation/networking/openvswitch.txt | 13 ++ include/uapi/linux/openvswitch.h | 20 +++ net/openvswitch/datapath.c | 207 +++++++++++++++++++++++-------- net/openvswitch/flow.h | 28 ++++- net/openvswitch/flow_netlink.c | 68 +++++++++- net/openvswitch/flow_netlink.h | 8 +- net/openvswitch/flow_table.c | 187 +++++++++++++++++++++++----- net/openvswitch/flow_table.h | 8 +- 8 files changed, 448 insertions(+), 91 deletions(-) (limited to 'net/openvswitch/datapath.c') diff --git a/Documentation/networking/openvswitch.txt b/Documentation/networking/openvswitch.txt index 37c20ee2455e..b3b9ac61d29d 100644 --- a/Documentation/networking/openvswitch.txt +++ b/Documentation/networking/openvswitch.txt @@ -131,6 +131,19 @@ performs best-effort detection of overlapping wildcarded flows and may reject some but not all of them. However, this behavior may change in future versions. +Unique flow identifiers +----------------------- + +An alternative to using the original match portion of a key as the handle for +flow identification is a unique flow identifier, or "UFID". UFIDs are optional +for both the kernel and user space program. + +User space programs that support UFID are expected to provide it during flow +setup in addition to the flow, then refer to the flow using the UFID for all +future operations. The kernel is not required to index flows by the original +flow key if a UFID is specified. + + Basic rule for evolving flow keys --------------------------------- diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index cd8d933963c2..7a8785a99243 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -459,6 +459,14 @@ struct ovs_key_nd { * a wildcarded match. Omitting attribute is treated as wildcarding all * corresponding fields. Optional for all requests. If not present, * all flow key bits are exact match bits. + * @OVS_FLOW_ATTR_UFID: A value between 1-16 octets specifying a unique + * identifier for the flow. Causes the flow to be indexed by this value rather + * than the value of the %OVS_FLOW_ATTR_KEY attribute. Optional for all + * requests. Present in notifications if the flow was created with this + * attribute. + * @OVS_FLOW_ATTR_UFID_FLAGS: A 32-bit value of OR'd %OVS_UFID_F_* + * flags that provide alternative semantics for flow installation and + * retrieval. Optional for all requests. * * These attributes follow the &struct ovs_header within the Generic Netlink * payload for %OVS_FLOW_* commands. @@ -474,11 +482,23 @@ enum ovs_flow_attr { OVS_FLOW_ATTR_MASK, /* Sequence of OVS_KEY_ATTR_* attributes. */ OVS_FLOW_ATTR_PROBE, /* Flow operation is a feature probe, error * logging should be suppressed. */ + OVS_FLOW_ATTR_UFID, /* Variable length unique flow identifier. */ + OVS_FLOW_ATTR_UFID_FLAGS,/* u32 of OVS_UFID_F_*. */ __OVS_FLOW_ATTR_MAX }; #define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1) +/** + * Omit attributes for notifications. + * + * If a datapath request contains an %OVS_UFID_F_OMIT_* flag, then the datapath + * may omit the corresponding %OVS_FLOW_ATTR_* from the response. + */ +#define OVS_UFID_F_OMIT_KEY (1 << 0) +#define OVS_UFID_F_OMIT_MASK (1 << 1) +#define OVS_UFID_F_OMIT_ACTIONS (1 << 2) + /** * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action. * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 257b97546b33..ae5e77cdc0ca 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -65,6 +65,8 @@ static struct genl_family dp_packet_genl_family; static struct genl_family dp_flow_genl_family; static struct genl_family dp_datapath_genl_family; +static const struct nla_policy flow_policy[]; + static const struct genl_multicast_group ovs_dp_flow_multicast_group = { .name = OVS_FLOW_MCGROUP, }; @@ -662,15 +664,48 @@ static void get_dp_stats(const struct datapath *dp, struct ovs_dp_stats *stats, } } -static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) +static bool should_fill_key(const struct sw_flow_id *sfid, uint32_t ufid_flags) +{ + return ovs_identifier_is_ufid(sfid) && + !(ufid_flags & OVS_UFID_F_OMIT_KEY); +} + +static bool should_fill_mask(uint32_t ufid_flags) +{ + return !(ufid_flags & OVS_UFID_F_OMIT_MASK); +} + +static bool should_fill_actions(uint32_t ufid_flags) { - return NLMSG_ALIGN(sizeof(struct ovs_header)) - + nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_KEY */ - + nla_total_size(ovs_key_attr_size()) /* OVS_FLOW_ATTR_MASK */ + return !(ufid_flags & OVS_UFID_F_OMIT_ACTIONS); +} + +static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, + const struct sw_flow_id *sfid, + uint32_t ufid_flags) +{ + size_t len = NLMSG_ALIGN(sizeof(struct ovs_header)); + + /* OVS_FLOW_ATTR_UFID */ + if (sfid && ovs_identifier_is_ufid(sfid)) + len += nla_total_size(sfid->ufid_len); + + /* OVS_FLOW_ATTR_KEY */ + if (!sfid || should_fill_key(sfid, ufid_flags)) + len += nla_total_size(ovs_key_attr_size()); + + /* OVS_FLOW_ATTR_MASK */ + if (should_fill_mask(ufid_flags)) + len += nla_total_size(ovs_key_attr_size()); + + /* OVS_FLOW_ATTR_ACTIONS */ + if (should_fill_actions(ufid_flags)) + len += nla_total_size(acts->actions_len); + + return len + nla_total_size(sizeof(struct ovs_flow_stats)) /* OVS_FLOW_ATTR_STATS */ + nla_total_size(1) /* OVS_FLOW_ATTR_TCP_FLAGS */ - + nla_total_size(8) /* OVS_FLOW_ATTR_USED */ - + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */ + + nla_total_size(8); /* OVS_FLOW_ATTR_USED */ } /* Called with ovs_mutex or RCU read lock. */ @@ -741,7 +776,7 @@ static int ovs_flow_cmd_fill_actions(const struct sw_flow *flow, /* Called with ovs_mutex or RCU read lock. */ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, struct sk_buff *skb, u32 portid, - u32 seq, u32 flags, u8 cmd) + u32 seq, u32 flags, u8 cmd, u32 ufid_flags) { const int skb_orig_len = skb->len; struct ovs_header *ovs_header; @@ -754,21 +789,31 @@ static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, ovs_header->dp_ifindex = dp_ifindex; - err = ovs_nla_put_unmasked_key(flow, skb); + err = ovs_nla_put_identifier(flow, skb); if (err) goto error; - err = ovs_nla_put_mask(flow, skb); - if (err) - goto error; + if (should_fill_key(&flow->id, ufid_flags)) { + err = ovs_nla_put_masked_key(flow, skb); + if (err) + goto error; + } + + if (should_fill_mask(ufid_flags)) { + err = ovs_nla_put_mask(flow, skb); + if (err) + goto error; + } err = ovs_flow_cmd_fill_stats(flow, skb); if (err) goto error; - err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len); - if (err) - goto error; + if (should_fill_actions(ufid_flags)) { + err = ovs_flow_cmd_fill_actions(flow, skb, skb_orig_len); + if (err) + goto error; + } genlmsg_end(skb, ovs_header); return 0; @@ -780,15 +825,19 @@ error: /* May not be called with RCU read lock. */ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts, + const struct sw_flow_id *sfid, struct genl_info *info, - bool always) + bool always, + uint32_t ufid_flags) { struct sk_buff *skb; + size_t len; if (!always && !ovs_must_notify(&dp_flow_genl_family, info, 0)) return NULL; - skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL); + len = ovs_flow_cmd_msg_size(acts, sfid, ufid_flags); + skb = genlmsg_new_unicast(len, info, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); @@ -799,19 +848,19 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *act static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, int dp_ifindex, struct genl_info *info, u8 cmd, - bool always) + bool always, u32 ufid_flags) { struct sk_buff *skb; int retval; - skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info, - always); + skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), + &flow->id, info, always, ufid_flags); if (IS_ERR_OR_NULL(skb)) return skb; retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, info->snd_portid, info->snd_seq, 0, - cmd); + cmd, ufid_flags); BUG_ON(retval < 0); return skb; } @@ -820,12 +869,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; - struct sw_flow *flow, *new_flow; + struct sw_flow *flow = NULL, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; + struct sw_flow_key key; struct sw_flow_actions *acts; struct sw_flow_match match; + u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int error; bool log = !a[OVS_FLOW_ATTR_PROBE]; @@ -850,13 +901,19 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) } /* Extract key. */ - ovs_match_init(&match, &new_flow->unmasked_key, &mask); + ovs_match_init(&match, &key, &mask); error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) goto err_kfree_flow; - ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask); + ovs_flow_mask_key(&new_flow->key, &key, &mask); + + /* Extract flow identifier. */ + error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], + &key, log); + if (error) + goto err_kfree_flow; /* Validate actions. */ error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, @@ -866,7 +923,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_kfree_flow; } - reply = ovs_flow_cmd_alloc_info(acts, info, false); + reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, + ufid_flags); if (IS_ERR(reply)) { error = PTR_ERR(reply); goto err_kfree_acts; @@ -878,8 +936,12 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = -ENODEV; goto err_unlock_ovs; } + /* Check if this is a duplicate flow */ - flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key); + if (ovs_identifier_is_ufid(&new_flow->id)) + flow = ovs_flow_tbl_lookup_ufid(&dp->table, &new_flow->id); + if (!flow) + flow = ovs_flow_tbl_lookup(&dp->table, &key); if (likely(!flow)) { rcu_assign_pointer(new_flow->sf_acts, acts); @@ -895,7 +957,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, - OVS_FLOW_CMD_NEW); + OVS_FLOW_CMD_NEW, + ufid_flags); BUG_ON(error < 0); } ovs_unlock(); @@ -913,10 +976,15 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = -EEXIST; goto err_unlock_ovs; } - /* The unmasked key has to be the same for flow updates. */ - if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) { - /* Look for any overlapping flow. */ - flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); + /* The flow identifier has to be the same for flow updates. + * Look for any overlapping flow. + */ + if (unlikely(!ovs_flow_cmp(flow, &match))) { + if (ovs_identifier_is_key(&flow->id)) + flow = ovs_flow_tbl_lookup_exact(&dp->table, + &match); + else /* UFID matches but key is different */ + flow = NULL; if (!flow) { error = -ENOENT; goto err_unlock_ovs; @@ -931,7 +999,8 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, - OVS_FLOW_CMD_NEW); + OVS_FLOW_CMD_NEW, + ufid_flags); BUG_ON(error < 0); } ovs_unlock(); @@ -987,8 +1056,11 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; struct sw_flow_actions *old_acts = NULL, *acts = NULL; struct sw_flow_match match; + struct sw_flow_id sfid; + u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int error; bool log = !a[OVS_FLOW_ATTR_PROBE]; + bool ufid_present; /* Extract key. */ error = -EINVAL; @@ -997,6 +1069,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) goto error; } + ufid_present = ovs_nla_get_ufid(&sfid, a[OVS_FLOW_ATTR_UFID], log); ovs_match_init(&match, &key, &mask); error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); @@ -1013,7 +1086,8 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) } /* Can allocate before locking if have acts. */ - reply = ovs_flow_cmd_alloc_info(acts, info, false); + reply = ovs_flow_cmd_alloc_info(acts, &sfid, info, false, + ufid_flags); if (IS_ERR(reply)) { error = PTR_ERR(reply); goto err_kfree_acts; @@ -1027,7 +1101,10 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; } /* Check that the flow exists. */ - flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); + if (ufid_present) + flow = ovs_flow_tbl_lookup_ufid(&dp->table, &sfid); + else + flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (unlikely(!flow)) { error = -ENOENT; goto err_unlock_ovs; @@ -1043,13 +1120,16 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, - OVS_FLOW_CMD_NEW); + OVS_FLOW_CMD_NEW, + ufid_flags); BUG_ON(error < 0); } } else { /* Could not alloc without acts before locking. */ reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, - info, OVS_FLOW_CMD_NEW, false); + info, OVS_FLOW_CMD_NEW, false, + ufid_flags); + if (unlikely(IS_ERR(reply))) { error = PTR_ERR(reply); goto err_unlock_ovs; @@ -1086,17 +1166,22 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) struct sw_flow *flow; struct datapath *dp; struct sw_flow_match match; - int err; + struct sw_flow_id ufid; + u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); + int err = 0; bool log = !a[OVS_FLOW_ATTR_PROBE]; + bool ufid_present; - if (!a[OVS_FLOW_ATTR_KEY]) { + ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); + if (a[OVS_FLOW_ATTR_KEY]) { + ovs_match_init(&match, &key, NULL); + err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, + log); + } else if (!ufid_present) { OVS_NLERR(log, "Flow get message rejected, Key attribute missing."); - return -EINVAL; + err = -EINVAL; } - - ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log); if (err) return err; @@ -1107,14 +1192,17 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) goto unlock; } - flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); + if (ufid_present) + flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid); + else + flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (!flow) { err = -ENOENT; goto unlock; } reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info, - OVS_FLOW_CMD_NEW, true); + OVS_FLOW_CMD_NEW, true, ufid_flags); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; @@ -1133,13 +1221,17 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) struct ovs_header *ovs_header = info->userhdr; struct sw_flow_key key; struct sk_buff *reply; - struct sw_flow *flow; + struct sw_flow *flow = NULL; struct datapath *dp; struct sw_flow_match match; + struct sw_flow_id ufid; + u32 ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); int err; bool log = !a[OVS_FLOW_ATTR_PROBE]; + bool ufid_present; - if (likely(a[OVS_FLOW_ATTR_KEY])) { + ufid_present = ovs_nla_get_ufid(&ufid, a[OVS_FLOW_ATTR_UFID], log); + if (a[OVS_FLOW_ATTR_KEY]) { ovs_match_init(&match, &key, NULL); err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL, log); @@ -1154,12 +1246,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) goto unlock; } - if (unlikely(!a[OVS_FLOW_ATTR_KEY])) { + if (unlikely(!a[OVS_FLOW_ATTR_KEY] && !ufid_present)) { err = ovs_flow_tbl_flush(&dp->table); goto unlock; } - flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); + if (ufid_present) + flow = ovs_flow_tbl_lookup_ufid(&dp->table, &ufid); + else + flow = ovs_flow_tbl_lookup_exact(&dp->table, &match); if (unlikely(!flow)) { err = -ENOENT; goto unlock; @@ -1169,14 +1264,15 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_unlock(); reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, - info, false); + &flow->id, info, false, ufid_flags); if (likely(reply)) { if (likely(!IS_ERR(reply))) { rcu_read_lock(); /*To keep RCU checker happy. */ err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, reply, info->snd_portid, info->snd_seq, 0, - OVS_FLOW_CMD_DEL); + OVS_FLOW_CMD_DEL, + ufid_flags); rcu_read_unlock(); BUG_ON(err < 0); @@ -1195,9 +1291,18 @@ unlock: static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct nlattr *a[__OVS_FLOW_ATTR_MAX]; struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh)); struct table_instance *ti; struct datapath *dp; + u32 ufid_flags; + int err; + + err = genlmsg_parse(cb->nlh, &dp_flow_genl_family, a, + OVS_FLOW_ATTR_MAX, flow_policy); + if (err) + return err; + ufid_flags = ovs_nla_get_ufid_flags(a[OVS_FLOW_ATTR_UFID_FLAGS]); rcu_read_lock(); dp = get_dp_rcu(sock_net(skb->sk), ovs_header->dp_ifindex); @@ -1220,7 +1325,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - OVS_FLOW_CMD_NEW) < 0) + OVS_FLOW_CMD_NEW, ufid_flags) < 0) break; cb->args[0] = bucket; @@ -1236,6 +1341,8 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, [OVS_FLOW_ATTR_PROBE] = { .type = NLA_FLAG }, + [OVS_FLOW_ATTR_UFID] = { .type = NLA_UNSPEC, .len = 1 }, + [OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 }, }; static const struct genl_ops dp_flow_genl_ops[] = { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index d3d0a406562d..a076e445ccc2 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -197,6 +197,16 @@ struct sw_flow_match { struct sw_flow_mask *mask; }; +#define MAX_UFID_LENGTH 16 /* 128 bits */ + +struct sw_flow_id { + u32 ufid_len; + union { + u32 ufid[MAX_UFID_LENGTH / 4]; + struct sw_flow_key *unmasked_key; + }; +}; + struct sw_flow_actions { struct rcu_head rcu; u32 actions_len; @@ -213,13 +223,15 @@ struct flow_stats { struct sw_flow { struct rcu_head rcu; - struct hlist_node hash_node[2]; - u32 hash; + struct { + struct hlist_node node[2]; + u32 hash; + } flow_table, ufid_table; int stats_last_writer; /* NUMA-node id of the last writer on * 'stats[0]'. */ struct sw_flow_key key; - struct sw_flow_key unmasked_key; + struct sw_flow_id id; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; struct flow_stats __rcu *stats[]; /* One for each NUMA node. First one @@ -243,6 +255,16 @@ struct arp_eth_header { unsigned char ar_tip[4]; /* target IP address */ } __packed; +static inline bool ovs_identifier_is_ufid(const struct sw_flow_id *sfid) +{ + return sfid->ufid_len; +} + +static inline bool ovs_identifier_is_key(const struct sw_flow_id *sfid) +{ + return !ovs_identifier_is_ufid(sfid); +} + void ovs_flow_stats_update(struct sw_flow *, __be16 tcp_flags, const struct sk_buff *); void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 33751f81bfcb..8b9a612b39d1 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1180,6 +1180,59 @@ free_newmask: return err; } +static size_t get_ufid_len(const struct nlattr *attr, bool log) +{ + size_t len; + + if (!attr) + return 0; + + len = nla_len(attr); + if (len < 1 || len > MAX_UFID_LENGTH) { + OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)", + nla_len(attr), MAX_UFID_LENGTH); + return 0; + } + + return len; +} + +/* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID, + * or false otherwise. + */ +bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr, + bool log) +{ + sfid->ufid_len = get_ufid_len(attr, log); + if (sfid->ufid_len) + memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len); + + return sfid->ufid_len; +} + +int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, + const struct sw_flow_key *key, bool log) +{ + struct sw_flow_key *new_key; + + if (ovs_nla_get_ufid(sfid, ufid, log)) + return 0; + + /* If UFID was not provided, use unmasked key. */ + new_key = kmalloc(sizeof(*new_key), GFP_KERNEL); + if (!new_key) + return -ENOMEM; + memcpy(new_key, key, sizeof(*key)); + sfid->unmasked_key = new_key; + + return 0; +} + +u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) +{ + return attr ? nla_get_u32(attr) : 0; +} + /** * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key. * @key: Receives extracted in_port, priority, tun_key and skb_mark. @@ -1450,9 +1503,20 @@ int ovs_nla_put_key(const struct sw_flow_key *swkey, } /* Called with ovs_mutex or RCU read lock. */ -int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb) +int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb) +{ + if (ovs_identifier_is_ufid(&flow->id)) + return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len, + flow->id.ufid); + + return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key, + OVS_FLOW_ATTR_KEY, false, skb); +} + +/* Called with ovs_mutex or RCU read lock. */ +int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb) { - return ovs_nla_put_key(&flow->unmasked_key, &flow->unmasked_key, + return ovs_nla_put_key(&flow->mask->key, &flow->key, OVS_FLOW_ATTR_KEY, false, skb); } diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index 9ed09e66876a..5c3d75bff310 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -48,7 +48,8 @@ int ovs_nla_put_key(const struct sw_flow_key *, const struct sw_flow_key *, int ovs_nla_get_flow_metadata(const struct nlattr *, struct sw_flow_key *, bool log); -int ovs_nla_put_unmasked_key(const struct sw_flow *flow, struct sk_buff *skb); +int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb); +int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb); int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, @@ -56,6 +57,11 @@ int ovs_nla_get_match(struct sw_flow_match *, const struct nlattr *key, int ovs_nla_put_egress_tunnel_key(struct sk_buff *, const struct ovs_tunnel_info *); +bool ovs_nla_get_ufid(struct sw_flow_id *, const struct nlattr *, bool log); +int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, + const struct sw_flow_key *key, bool log); +u32 ovs_nla_get_ufid_flags(const struct nlattr *attr); + int ovs_nla_copy_actions(const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log); diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 9a3f41f26da8..5e57628e6584 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -139,6 +139,8 @@ static void flow_free(struct sw_flow *flow) { int node; + if (ovs_identifier_is_key(&flow->id)) + kfree(flow->id.unmasked_key); kfree((struct sw_flow_actions __force *)flow->sf_acts); for_each_node(node) if (flow->stats[node]) @@ -200,18 +202,28 @@ static struct table_instance *table_instance_alloc(int new_size) int ovs_flow_tbl_init(struct flow_table *table) { - struct table_instance *ti; + struct table_instance *ti, *ufid_ti; ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!ti) return -ENOMEM; + ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS); + if (!ufid_ti) + goto free_ti; + rcu_assign_pointer(table->ti, ti); + rcu_assign_pointer(table->ufid_ti, ufid_ti); INIT_LIST_HEAD(&table->mask_list); table->last_rehash = jiffies; table->count = 0; + table->ufid_count = 0; return 0; + +free_ti: + __table_instance_destroy(ti); + return -ENOMEM; } static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) @@ -221,13 +233,16 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) __table_instance_destroy(ti); } -static void table_instance_destroy(struct table_instance *ti, bool deferred) +static void table_instance_destroy(struct table_instance *ti, + struct table_instance *ufid_ti, + bool deferred) { int i; if (!ti) return; + BUG_ON(!ufid_ti); if (ti->keep_flows) goto skip_flows; @@ -236,18 +251,24 @@ static void table_instance_destroy(struct table_instance *ti, bool deferred) struct hlist_head *head = flex_array_get(ti->buckets, i); struct hlist_node *n; int ver = ti->node_ver; + int ufid_ver = ufid_ti->node_ver; - hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { - hlist_del_rcu(&flow->hash_node[ver]); + hlist_for_each_entry_safe(flow, n, head, flow_table.node[ver]) { + hlist_del_rcu(&flow->flow_table.node[ver]); + if (ovs_identifier_is_ufid(&flow->id)) + hlist_del_rcu(&flow->ufid_table.node[ufid_ver]); ovs_flow_free(flow, deferred); } } skip_flows: - if (deferred) + if (deferred) { call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); - else + call_rcu(&ufid_ti->rcu, flow_tbl_destroy_rcu_cb); + } else { __table_instance_destroy(ti); + __table_instance_destroy(ufid_ti); + } } /* No need for locking this function is called from RCU callback or @@ -256,8 +277,9 @@ skip_flows: void ovs_flow_tbl_destroy(struct flow_table *table) { struct table_instance *ti = rcu_dereference_raw(table->ti); + struct table_instance *ufid_ti = rcu_dereference_raw(table->ufid_ti); - table_instance_destroy(ti, false); + table_instance_destroy(ti, ufid_ti, false); } struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, @@ -272,7 +294,7 @@ struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, while (*bucket < ti->n_buckets) { i = 0; head = flex_array_get(ti->buckets, *bucket); - hlist_for_each_entry_rcu(flow, head, hash_node[ver]) { + hlist_for_each_entry_rcu(flow, head, flow_table.node[ver]) { if (i < *last) { i++; continue; @@ -294,16 +316,26 @@ static struct hlist_head *find_bucket(struct table_instance *ti, u32 hash) (hash & (ti->n_buckets - 1))); } -static void table_instance_insert(struct table_instance *ti, struct sw_flow *flow) +static void table_instance_insert(struct table_instance *ti, + struct sw_flow *flow) { struct hlist_head *head; - head = find_bucket(ti, flow->hash); - hlist_add_head_rcu(&flow->hash_node[ti->node_ver], head); + head = find_bucket(ti, flow->flow_table.hash); + hlist_add_head_rcu(&flow->flow_table.node[ti->node_ver], head); +} + +static void ufid_table_instance_insert(struct table_instance *ti, + struct sw_flow *flow) +{ + struct hlist_head *head; + + head = find_bucket(ti, flow->ufid_table.hash); + hlist_add_head_rcu(&flow->ufid_table.node[ti->node_ver], head); } static void flow_table_copy_flows(struct table_instance *old, - struct table_instance *new) + struct table_instance *new, bool ufid) { int old_ver; int i; @@ -318,15 +350,21 @@ static void flow_table_copy_flows(struct table_instance *old, head = flex_array_get(old->buckets, i); - hlist_for_each_entry(flow, head, hash_node[old_ver]) - table_instance_insert(new, flow); + if (ufid) + hlist_for_each_entry(flow, head, + ufid_table.node[old_ver]) + ufid_table_instance_insert(new, flow); + else + hlist_for_each_entry(flow, head, + flow_table.node[old_ver]) + table_instance_insert(new, flow); } old->keep_flows = true; } static struct table_instance *table_instance_rehash(struct table_instance *ti, - int n_buckets) + int n_buckets, bool ufid) { struct table_instance *new_ti; @@ -334,27 +372,38 @@ static struct table_instance *table_instance_rehash(struct table_instance *ti, if (!new_ti) return NULL; - flow_table_copy_flows(ti, new_ti); + flow_table_copy_flows(ti, new_ti, ufid); return new_ti; } int ovs_flow_tbl_flush(struct flow_table *flow_table) { - struct table_instance *old_ti; - struct table_instance *new_ti; + struct table_instance *old_ti, *new_ti; + struct table_instance *old_ufid_ti, *new_ufid_ti; - old_ti = ovsl_dereference(flow_table->ti); new_ti = table_instance_alloc(TBL_MIN_BUCKETS); if (!new_ti) return -ENOMEM; + new_ufid_ti = table_instance_alloc(TBL_MIN_BUCKETS); + if (!new_ufid_ti) + goto err_free_ti; + + old_ti = ovsl_dereference(flow_table->ti); + old_ufid_ti = ovsl_dereference(flow_table->ufid_ti); rcu_assign_pointer(flow_table->ti, new_ti); + rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti); flow_table->last_rehash = jiffies; flow_table->count = 0; + flow_table->ufid_count = 0; - table_instance_destroy(old_ti, true); + table_instance_destroy(old_ti, old_ufid_ti, true); return 0; + +err_free_ti: + __table_instance_destroy(new_ti); + return -ENOMEM; } static u32 flow_hash(const struct sw_flow_key *key, @@ -402,14 +451,15 @@ static bool flow_cmp_masked_key(const struct sw_flow *flow, return cmp_key(&flow->key, key, range->start, range->end); } -bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow, - const struct sw_flow_match *match) +static bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow, + const struct sw_flow_match *match) { struct sw_flow_key *key = match->key; int key_start = flow_key_start(key); int key_end = match->range.end; - return cmp_key(&flow->unmasked_key, key, key_start, key_end); + BUG_ON(ovs_identifier_is_ufid(&flow->id)); + return cmp_key(flow->id.unmasked_key, key, key_start, key_end); } static struct sw_flow *masked_flow_lookup(struct table_instance *ti, @@ -424,8 +474,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, ovs_flow_mask_key(&masked_key, unmasked, mask); hash = flow_hash(&masked_key, &mask->range); head = find_bucket(ti, hash); - hlist_for_each_entry_rcu(flow, head, hash_node[ti->node_ver]) { - if (flow->mask == mask && flow->hash == hash && + hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { + if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; } @@ -468,7 +518,48 @@ struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, /* Always called under ovs-mutex. */ list_for_each_entry(mask, &tbl->mask_list, list) { flow = masked_flow_lookup(ti, match->key, mask); - if (flow && ovs_flow_cmp_unmasked_key(flow, match)) /* Found */ + if (flow && ovs_identifier_is_key(&flow->id) && + ovs_flow_cmp_unmasked_key(flow, match)) + return flow; + } + return NULL; +} + +static u32 ufid_hash(const struct sw_flow_id *sfid) +{ + return jhash(sfid->ufid, sfid->ufid_len, 0); +} + +static bool ovs_flow_cmp_ufid(const struct sw_flow *flow, + const struct sw_flow_id *sfid) +{ + if (flow->id.ufid_len != sfid->ufid_len) + return false; + + return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len); +} + +bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match) +{ + if (ovs_identifier_is_ufid(&flow->id)) + return flow_cmp_masked_key(flow, match->key, &match->range); + + return ovs_flow_cmp_unmasked_key(flow, match); +} + +struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, + const struct sw_flow_id *ufid) +{ + struct table_instance *ti = rcu_dereference_ovsl(tbl->ufid_ti); + struct sw_flow *flow; + struct hlist_head *head; + u32 hash; + + hash = ufid_hash(ufid); + head = find_bucket(ti, hash); + hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) { + if (flow->ufid_table.hash == hash && + ovs_flow_cmp_ufid(flow, ufid)) return flow; } return NULL; @@ -485,9 +576,10 @@ int ovs_flow_tbl_num_masks(const struct flow_table *table) return num; } -static struct table_instance *table_instance_expand(struct table_instance *ti) +static struct table_instance *table_instance_expand(struct table_instance *ti, + bool ufid) { - return table_instance_rehash(ti, ti->n_buckets * 2); + return table_instance_rehash(ti, ti->n_buckets * 2, ufid); } /* Remove 'mask' from the mask list, if it is not needed any more. */ @@ -512,10 +604,15 @@ static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask) void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { struct table_instance *ti = ovsl_dereference(table->ti); + struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti); BUG_ON(table->count == 0); - hlist_del_rcu(&flow->hash_node[ti->node_ver]); + hlist_del_rcu(&flow->flow_table.node[ti->node_ver]); table->count--; + if (ovs_identifier_is_ufid(&flow->id)) { + hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]); + table->ufid_count--; + } /* RCU delete the mask. 'flow->mask' is not NULLed, as it should be * accessible as long as the RCU read lock is held. @@ -589,24 +686,46 @@ static void flow_key_insert(struct flow_table *table, struct sw_flow *flow) struct table_instance *new_ti = NULL; struct table_instance *ti; - flow->hash = flow_hash(&flow->key, &flow->mask->range); + flow->flow_table.hash = flow_hash(&flow->key, &flow->mask->range); ti = ovsl_dereference(table->ti); table_instance_insert(ti, flow); table->count++; /* Expand table, if necessary, to make room. */ if (table->count > ti->n_buckets) - new_ti = table_instance_expand(ti); + new_ti = table_instance_expand(ti, false); else if (time_after(jiffies, table->last_rehash + REHASH_INTERVAL)) - new_ti = table_instance_rehash(ti, ti->n_buckets); + new_ti = table_instance_rehash(ti, ti->n_buckets, false); if (new_ti) { rcu_assign_pointer(table->ti, new_ti); - table_instance_destroy(ti, true); + call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); table->last_rehash = jiffies; } } +/* Must be called with OVS mutex held. */ +static void flow_ufid_insert(struct flow_table *table, struct sw_flow *flow) +{ + struct table_instance *ti; + + flow->ufid_table.hash = ufid_hash(&flow->id); + ti = ovsl_dereference(table->ufid_ti); + ufid_table_instance_insert(ti, flow); + table->ufid_count++; + + /* Expand table, if necessary, to make room. */ + if (table->ufid_count > ti->n_buckets) { + struct table_instance *new_ti; + + new_ti = table_instance_expand(ti, true); + if (new_ti) { + rcu_assign_pointer(table->ufid_ti, new_ti); + call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); + } + } +} + /* Must be called with OVS mutex held. */ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, const struct sw_flow_mask *mask) @@ -617,6 +736,8 @@ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, if (err) return err; flow_key_insert(table, flow); + if (ovs_identifier_is_ufid(&flow->id)) + flow_ufid_insert(table, flow); return 0; } diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 309fa6415689..616eda10d955 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -47,9 +47,11 @@ struct table_instance { struct flow_table { struct table_instance __rcu *ti; + struct table_instance __rcu *ufid_ti; struct list_head mask_list; unsigned long last_rehash; unsigned int count; + unsigned int ufid_count; }; extern struct kmem_cache *flow_stats_cache; @@ -78,8 +80,10 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *, const struct sw_flow_key *); struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl, const struct sw_flow_match *match); -bool ovs_flow_cmp_unmasked_key(const struct sw_flow *flow, - const struct sw_flow_match *match); +struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *, + const struct sw_flow_id *); + +bool ovs_flow_cmp(const struct sw_flow *, const struct sw_flow_match *); void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, const struct sw_flow_mask *mask); -- cgit v1.2.3