diff options
Diffstat (limited to 'net')
144 files changed, 1501 insertions, 843 deletions
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 70417e9b932d..314bbc8010fb 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -114,6 +114,7 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) dst = (ax25_address *)(bp + 1); src = (ax25_address *)(bp + 8); + ax25_route_lock_use(); route = ax25_get_route(dst, NULL); if (route) { digipeat = route->digipeat; @@ -206,9 +207,8 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) ax25_queue_xmit(skb, dev); put: - if (route) - ax25_put_route(route); + ax25_route_lock_unuse(); return NETDEV_TX_OK; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index a0eff323af12..66f74c85cf6b 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -40,7 +40,7 @@ #include <linux/export.h> static ax25_route *ax25_route_list; -static DEFINE_RWLOCK(ax25_route_lock); +DEFINE_RWLOCK(ax25_route_lock); void ax25_rt_device_down(struct net_device *dev) { @@ -335,6 +335,7 @@ const struct seq_operations ax25_rt_seqops = { * Find AX.25 route * * Only routes with a reference count of zero can be destroyed. + * Must be called with ax25_route_lock read locked. */ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) { @@ -342,7 +343,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) ax25_route *ax25_def_rt = NULL; ax25_route *ax25_rt; - read_lock(&ax25_route_lock); /* * Bind to the physical interface we heard them on, or the default * route if none is found; @@ -365,11 +365,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev) if (ax25_spe_rt != NULL) ax25_rt = ax25_spe_rt; - if (ax25_rt != NULL) - ax25_hold_route(ax25_rt); - - read_unlock(&ax25_route_lock); - return ax25_rt; } @@ -400,9 +395,12 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) ax25_route *ax25_rt; int err = 0; - if ((ax25_rt = ax25_get_route(addr, NULL)) == NULL) + ax25_route_lock_use(); + ax25_rt = ax25_get_route(addr, NULL); + if (!ax25_rt) { + ax25_route_lock_unuse(); return -EHOSTUNREACH; - + } if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) { err = -EHOSTUNREACH; goto put; @@ -437,8 +435,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) } put: - ax25_put_route(ax25_rt); - + ax25_route_lock_unuse(); return err; } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..ef0dec20c7d8 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..415d494cbe22 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -20,7 +20,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/gfp.h> @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5db5a0a4c959..b85ca809e509 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -221,6 +221,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 7acfc83087d5..7ee4fea93637 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -13,39 +13,24 @@ extern char bpfilter_umh_start; extern char bpfilter_umh_end; -static struct umh_info info; -/* since ip_getsockopt() can run in parallel, serialize access to umh */ -static DEFINE_MUTEX(bpfilter_lock); - -static void shutdown_umh(struct umh_info *info) +static void shutdown_umh(void) { struct task_struct *tsk; - if (!info->pid) + if (bpfilter_ops.stop) return; - tsk = get_pid_task(find_vpid(info->pid), PIDTYPE_PID); + + tsk = get_pid_task(find_vpid(bpfilter_ops.info.pid), PIDTYPE_PID); if (tsk) { force_sig(SIGKILL, tsk); put_task_struct(tsk); } - fput(info->pipe_to_umh); - fput(info->pipe_from_umh); - info->pid = 0; } static void __stop_umh(void) { - if (IS_ENABLED(CONFIG_INET)) { - bpfilter_process_sockopt = NULL; - shutdown_umh(&info); - } -} - -static void stop_umh(void) -{ - mutex_lock(&bpfilter_lock); - __stop_umh(); - mutex_unlock(&bpfilter_lock); + if (IS_ENABLED(CONFIG_INET)) + shutdown_umh(); } static int __bpfilter_process_sockopt(struct sock *sk, int optname, @@ -63,10 +48,10 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, req.cmd = optname; req.addr = (long __force __user)optval; req.len = optlen; - mutex_lock(&bpfilter_lock); - if (!info.pid) + if (!bpfilter_ops.info.pid) goto out; - n = __kernel_write(info.pipe_to_umh, &req, sizeof(req), &pos); + n = __kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req), + &pos); if (n != sizeof(req)) { pr_err("write fail %zd\n", n); __stop_umh(); @@ -74,7 +59,8 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, goto out; } pos = 0; - n = kernel_read(info.pipe_from_umh, &reply, sizeof(reply), &pos); + n = kernel_read(bpfilter_ops.info.pipe_from_umh, &reply, sizeof(reply), + &pos); if (n != sizeof(reply)) { pr_err("read fail %zd\n", n); __stop_umh(); @@ -83,37 +69,59 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname, } ret = reply.status; out: - mutex_unlock(&bpfilter_lock); return ret; } -static int __init load_umh(void) +static int start_umh(void) { int err; /* fork usermode process */ - info.cmdline = "bpfilter_umh"; err = fork_usermode_blob(&bpfilter_umh_start, &bpfilter_umh_end - &bpfilter_umh_start, - &info); + &bpfilter_ops.info); if (err) return err; - pr_info("Loaded bpfilter_umh pid %d\n", info.pid); + bpfilter_ops.stop = false; + pr_info("Loaded bpfilter_umh pid %d\n", bpfilter_ops.info.pid); /* health check that usermode process started correctly */ if (__bpfilter_process_sockopt(NULL, 0, NULL, 0, 0) != 0) { - stop_umh(); + shutdown_umh(); return -EFAULT; } - if (IS_ENABLED(CONFIG_INET)) - bpfilter_process_sockopt = &__bpfilter_process_sockopt; return 0; } +static int __init load_umh(void) +{ + int err; + + mutex_lock(&bpfilter_ops.lock); + if (!bpfilter_ops.stop) { + err = -EFAULT; + goto out; + } + err = start_umh(); + if (!err && IS_ENABLED(CONFIG_INET)) { + bpfilter_ops.sockopt = &__bpfilter_process_sockopt; + bpfilter_ops.start = &start_umh; + } +out: + mutex_unlock(&bpfilter_ops.lock); + return err; +} + static void __exit fini_umh(void) { - stop_umh(); + mutex_lock(&bpfilter_ops.lock); + if (IS_ENABLED(CONFIG_INET)) { + shutdown_umh(); + bpfilter_ops.start = NULL; + bpfilter_ops.sockopt = NULL; + } + mutex_unlock(&bpfilter_ops.lock); } module_init(load_umh); module_exit(fini_umh); diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S index 40311d10d2f2..9ea6100dca87 100644 --- a/net/bpfilter/bpfilter_umh_blob.S +++ b/net/bpfilter/bpfilter_umh_blob.S @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ - .section .init.rodata, "a" + .section .rodata, "a" .global bpfilter_umh_start bpfilter_umh_start: .incbin "net/bpfilter/bpfilter_umh" diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index fe3c758791ca..9e14767500ea 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1128,6 +1128,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, err = -ENOMEM; goto err_unlock; } + if (swdev_notify) + fdb->added_by_user = 1; fdb->added_by_external_learn = 1; fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { @@ -1147,6 +1149,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (swdev_notify) + fdb->added_by_user = 1; + if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 5372e2042adf..48ddc60b4fbd 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -36,10 +36,10 @@ static inline int should_deliver(const struct net_bridge_port *p, int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { + skb_push(skb, ETH_HLEN); if (!is_skb_forwardable(skb->dev, skb)) goto drop; - skb_push(skb, ETH_HLEN); br_drop_fake_rtable(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && @@ -65,6 +65,7 @@ EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + skb->tstamp = 0; return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, net, sk, skb, NULL, skb->dev, br_dev_queue_push_xmit); @@ -97,12 +98,11 @@ static void __br_forward(const struct net_bridge_port *to, net = dev_net(indev); } else { if (unlikely(netpoll_tx_running(to->br->dev))) { - if (!is_skb_forwardable(skb->dev, skb)) { + skb_push(skb, ETH_HLEN); + if (!is_skb_forwardable(skb->dev, skb)) kfree_skb(skb); - } else { - skb_push(skb, ETH_HLEN); + else br_netpoll_send_skb(to, skb); - } return; } br_hook = NF_BR_LOCAL_OUT; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index d21a23698410..c93c35bb73dd 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -265,7 +265,7 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); int ret; - if (neigh->hh.hh_len) { + if ((neigh->nud_state & NUD_CONNECTED) && neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; ret = br_handle_frame_finish(net, sk, skb); diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 94039f588f1d..564710f88f93 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb) IPSTATS_MIB_INDISCARDS); goto drop; } + hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb)) goto drop; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d240b3e7919f..eabf8bf28a3f 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -107,6 +107,7 @@ struct br_tunnel_info { /* private vlan flags */ enum { BR_VLFLAG_PER_PORT_STATS = BIT(0), + BR_VLFLAG_ADDED_BY_SWITCHDEV = BIT(1), }; /** diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 4a2f31157ef5..96abf8feb9dc 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -80,16 +80,18 @@ static bool __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, - u16 vid, u16 flags, struct netlink_ext_ack *extack) + struct net_bridge_vlan *v, u16 flags, + struct netlink_ext_ack *extack) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q add. */ - err = br_switchdev_port_vlan_add(dev, vid, flags, extack); + err = br_switchdev_port_vlan_add(dev, v->vid, flags, extack); if (err == -EOPNOTSUPP) - return vlan_vid_add(dev, br->vlan_proto, vid); + return vlan_vid_add(dev, br->vlan_proto, v->vid); + v->priv_flags |= BR_VLFLAG_ADDED_BY_SWITCHDEV; return err; } @@ -121,19 +123,17 @@ static void __vlan_del_list(struct net_bridge_vlan *v) } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, - u16 vid) + const struct net_bridge_vlan *v) { int err; /* Try switchdev op first. In case it is not supported, fallback to * 8021q del. */ - err = br_switchdev_port_vlan_del(dev, vid); - if (err == -EOPNOTSUPP) { - vlan_vid_del(dev, br->vlan_proto, vid); - return 0; - } - return err; + err = br_switchdev_port_vlan_del(dev, v->vid); + if (!(v->priv_flags & BR_VLFLAG_ADDED_BY_SWITCHDEV)) + vlan_vid_del(dev, br->vlan_proto, v->vid); + return err == -EOPNOTSUPP ? 0 : err; } /* Returns a master vlan, if it didn't exist it gets created. In all cases a @@ -242,7 +242,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, * This ensures tagged traffic enters the bridge when * promiscuous mode is disabled by br_manage_promisc(). */ - err = __vlan_vid_add(dev, br, v->vid, flags, extack); + err = __vlan_vid_add(dev, br, v, flags, extack); if (err) goto out; @@ -305,7 +305,7 @@ out_fdb_insert: out_filt: if (p) { - __vlan_vid_del(dev, br, v->vid); + __vlan_vid_del(dev, br, v); if (masterv) { if (v->stats && masterv->stats != v->stats) free_percpu(v->stats); @@ -338,7 +338,7 @@ static int __vlan_del(struct net_bridge_vlan *v) __vlan_delete_pvid(vg, v->vid); if (p) { - err = __vlan_vid_del(p->dev, p->br, v->vid); + err = __vlan_vid_del(p->dev, p->br, v); if (err) goto out; } else { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 491828713e0b..6693e209efe8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1137,14 +1137,16 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = vmalloc(tmp.entries_size); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; @@ -2291,9 +2293,12 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; + if (tmp.nentries) { + ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + if (ret < 0) + goto out_unlock; + } + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 08cbed7d940e..419e8edf23ba 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) return false; + ip6h = ipv6_hdr(skb); thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) return false; diff --git a/net/can/bcm.c b/net/can/bcm.c index 0af8f0db892a..79bb8afa9c0c 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -67,6 +67,9 @@ */ #define MAX_NFRAMES 256 +/* limit timers to 400 days for sending/timeouts */ +#define BCM_TIMER_SEC_MAX (400 * 24 * 60 * 60) + /* use of last_frames[index].flags */ #define RX_RECV 0x40 /* received data for this element */ #define RX_THR 0x80 /* element not been sent due to throttle feature */ @@ -140,6 +143,22 @@ static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); } +/* check limitations for timeval provided by user */ +static bool bcm_is_invalid_tv(struct bcm_msg_head *msg_head) +{ + if ((msg_head->ival1.tv_sec < 0) || + (msg_head->ival1.tv_sec > BCM_TIMER_SEC_MAX) || + (msg_head->ival1.tv_usec < 0) || + (msg_head->ival1.tv_usec >= USEC_PER_SEC) || + (msg_head->ival2.tv_sec < 0) || + (msg_head->ival2.tv_sec > BCM_TIMER_SEC_MAX) || + (msg_head->ival2.tv_usec < 0) || + (msg_head->ival2.tv_usec >= USEC_PER_SEC)) + return true; + + return false; +} + #define CFSIZ(flags) ((flags & CAN_FD_FRAME) ? CANFD_MTU : CAN_MTU) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) @@ -873,6 +892,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (msg_head->nframes < 1 || msg_head->nframes > MAX_NFRAMES) return -EINVAL; + /* check timeval limitations */ + if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) + return -EINVAL; + /* check the given can_id */ op = bcm_find_op(&bo->tx_ops, msg_head, ifindex); if (op) { @@ -1053,6 +1076,10 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, (!(msg_head->can_id & CAN_RTR_FLAG)))) return -EINVAL; + /* check timeval limitations */ + if ((msg_head->flags & SETTIMER) && bcm_is_invalid_tv(msg_head)) + return -EINVAL; + /* check the given can_id */ op = bcm_find_op(&bo->rx_ops, msg_head, ifindex); if (op) { diff --git a/net/can/gw.c b/net/can/gw.c index faa3da88a127..53859346dc9a 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -416,13 +416,29 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); - /* check for checksum updates when the CAN frame has been modified */ + /* Has the CAN frame been modified? */ if (modidx) { - if (gwj->mod.csumfunc.crc8) + /* get available space for the processed CAN frame type */ + int max_len = nskb->len - offsetof(struct can_frame, data); + + /* dlc may have changed, make sure it fits to the CAN frame */ + if (cf->can_dlc > max_len) + goto out_delete; + + /* check for checksum updates in classic CAN length only */ + if (gwj->mod.csumfunc.crc8) { + if (cf->can_dlc > 8) + goto out_delete; + (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + } + + if (gwj->mod.csumfunc.xor) { + if (cf->can_dlc > 8) + goto out_delete; - if (gwj->mod.csumfunc.xor) (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + } } /* clear the skb timestamp if not configured the other way */ @@ -434,6 +450,14 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) gwj->dropped_frames++; else gwj->handled_frames++; + + return; + + out_delete: + /* delete frame due to misconfiguration */ + gwj->deleted_frames++; + kfree_skb(nskb); + return; } static inline int cgw_register_filter(struct net *net, struct cgw_job *gwj) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d5718284db57..3661cdd927f1 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3206,9 +3206,10 @@ void ceph_con_keepalive(struct ceph_connection *con) dout("con_keepalive %p\n", con); mutex_lock(&con->mutex); clear_standby(con); + con_flag_set(con, CON_FLAG_KEEPALIVE_PENDING); mutex_unlock(&con->mutex); - if (con_flag_test_and_set(con, CON_FLAG_KEEPALIVE_PENDING) == 0 && - con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) + + if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); diff --git a/net/core/dev.c b/net/core/dev.c index 82f20022259d..8e276e0192a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8712,6 +8712,9 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* napi_busy_loop stats accounting wants this */ + dev_net_set(dev, &init_net); + /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. diff --git a/net/core/filter.c b/net/core/filter.c index 447dd1bad31f..7a54dc11ac2d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2020,18 +2020,19 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { - /* skb->mac_len is not set on normal egress */ - unsigned int mlen = skb->network_header - skb->mac_header; + unsigned int mlen = skb_network_offset(skb); - __skb_pull(skb, mlen); + if (mlen) { + __skb_pull(skb, mlen); - /* At ingress, the mac header has already been pulled once. - * At egress, skb_pospull_rcsum has to be done in case that - * the skb is originated from ingress (i.e. a forwarded skb) - * to ensure that rcsum starts at net header. - */ - if (!skb_at_tc_ingress(skb)) - skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + /* At ingress, the mac header has already been pulled once. + * At egress, skb_pospull_rcsum has to be done in case that + * the skb is originated from ingress (i.e. a forwarded skb) + * to ensure that rcsum starts at net header. + */ + if (!skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); + } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? @@ -4111,14 +4112,20 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; case SO_MAX_PACING_RATE: /* 32bit version */ + if (val != ~0U) + cmpxchg(&sk->sk_pacing_status, + SK_PACING_NONE, + SK_PACING_NEEDED); sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val; sk->sk_pacing_rate = min(sk->sk_pacing_rate, sk->sk_max_pacing_rate); @@ -4132,7 +4139,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, sk->sk_rcvlowat = val ? : 1; break; case SO_MARK: - sk->sk_mark = val; + if (sk->sk_mark != val) { + sk->sk_mark = val; + sk_dst_reset(sk); + } break; default: ret = -EINVAL; @@ -4203,7 +4213,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: - if (val <= 0 || tp->data_segs_out > 0) + if (val <= 0 || tp->data_segs_out > tp->syn_data) ret = -EINVAL; else tp->snd_cwnd = val; @@ -5309,7 +5319,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_trace_printk: if (capable(CAP_SYS_ADMIN)) return bpf_get_trace_printk_proto(); - /* else: fall through */ + /* else, fall through */ default: return NULL; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 3e85437f7106..a648568c5e8f 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -63,6 +63,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, lwt->name ? : "<unknown>"); ret = BPF_OK; } else { + skb_reset_mac_header(skb); ret = skb_do_redirect(skb); if (ret == 0) ret = BPF_REDIRECT; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 763a7b08df67..4230400b9a30 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -18,6 +18,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> +#include <linux/kmemleak.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> @@ -443,12 +444,14 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) return NULL; - if (size <= PAGE_SIZE) + if (size <= PAGE_SIZE) { buckets = kzalloc(size, GFP_ATOMIC); - else + } else { buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); + kmemleak_alloc(buckets, size, 1, GFP_ATOMIC); + } if (!buckets) { kfree(ret); return NULL; @@ -468,10 +471,12 @@ static void neigh_hash_free_rcu(struct rcu_head *head) size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); struct neighbour __rcu **buckets = nht->hash_buckets; - if (size <= PAGE_SIZE) + if (size <= PAGE_SIZE) { kfree(buckets); - else + } else { + kmemleak_free(buckets); free_pages((unsigned long)buckets, get_order(size)); + } kfree(nht); } @@ -1002,7 +1007,7 @@ static void neigh_probe(struct neighbour *neigh) if (neigh->ops->solicit) neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); - kfree_skb(skb); + consume_skb(skb); } /* Called when a timer expires for a neighbour entry. */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 37317ffec146..26d848484912 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5270,7 +5270,6 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long chunk; struct sk_buff *skb; struct page *page; - gfp_t gfp_head; int i; *errcode = -EMSGSIZE; @@ -5280,12 +5279,8 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, if (npages > MAX_SKB_FRAGS) return NULL; - gfp_head = gfp_mask; - if (gfp_head & __GFP_DIRECT_RECLAIM) - gfp_head |= __GFP_RETRY_MAYFAIL; - *errcode = -ENOBUFS; - skb = alloc_skb(header_len, gfp_head); + skb = alloc_skb(header_len, gfp_mask); if (!skb) return NULL; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index d6d5c20d7044..8c826603bf36 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -545,8 +545,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - if (psock->parser.enabled) - strp_done(&psock->parser.strp); + strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index d0b3e69c6b39..0962f9201baa 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -56,7 +56,7 @@ #include <net/dn_neigh.h> #include <net/dn_fib.h> -#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn)) +#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn)) static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00}; static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00}; diff --git a/net/dsa/master.c b/net/dsa/master.c index 71bb15f491c8..54f5551fb799 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -205,6 +205,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -218,6 +220,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a3fcc1d01615..a1c9fe155057 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) @@ -639,7 +642,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +662,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) diff --git a/net/ipv4/bpfilter/sockopt.c b/net/ipv4/bpfilter/sockopt.c index 5e04ed25bc0e..1e976bb93d99 100644 --- a/net/ipv4/bpfilter/sockopt.c +++ b/net/ipv4/bpfilter/sockopt.c @@ -1,28 +1,54 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/module.h> #include <linux/uaccess.h> #include <linux/bpfilter.h> #include <uapi/linux/bpf.h> #include <linux/wait.h> #include <linux/kmod.h> +#include <linux/fs.h> +#include <linux/file.h> -int (*bpfilter_process_sockopt)(struct sock *sk, int optname, - char __user *optval, - unsigned int optlen, bool is_set); -EXPORT_SYMBOL_GPL(bpfilter_process_sockopt); +struct bpfilter_umh_ops bpfilter_ops; +EXPORT_SYMBOL_GPL(bpfilter_ops); + +static void bpfilter_umh_cleanup(struct umh_info *info) +{ + mutex_lock(&bpfilter_ops.lock); + bpfilter_ops.stop = true; + fput(info->pipe_to_umh); + fput(info->pipe_from_umh); + info->pid = 0; + mutex_unlock(&bpfilter_ops.lock); +} static int bpfilter_mbox_request(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set) { - if (!bpfilter_process_sockopt) { - int err = request_module("bpfilter"); + int err; + mutex_lock(&bpfilter_ops.lock); + if (!bpfilter_ops.sockopt) { + mutex_unlock(&bpfilter_ops.lock); + err = request_module("bpfilter"); + mutex_lock(&bpfilter_ops.lock); if (err) - return err; - if (!bpfilter_process_sockopt) - return -ECHILD; + goto out; + if (!bpfilter_ops.sockopt) { + err = -ECHILD; + goto out; + } + } + if (bpfilter_ops.stop) { + err = bpfilter_ops.start(); + if (err) + goto out; } - return bpfilter_process_sockopt(sk, optname, optval, optlen, is_set); + err = bpfilter_ops.sockopt(sk, optname, optval, optlen, is_set); +out: + mutex_unlock(&bpfilter_ops.lock); + return err; } int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, @@ -41,3 +67,15 @@ int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, return bpfilter_mbox_request(sk, optname, optval, len, false); } + +static int __init bpfilter_sockopt_init(void) +{ + mutex_init(&bpfilter_ops.lock); + bpfilter_ops.stop = true; + bpfilter_ops.info.cmdline = "bpfilter_umh"; + bpfilter_ops.info.cleanup = &bpfilter_umh_cleanup; + + return 0; +} + +module_init(bpfilter_sockopt_init); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 04ba321ae5ce..e258a00b4a3d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1826,7 +1826,7 @@ put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return err < 0 ? err : skb->len; + return skb->len ? : err; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6df95be96311..fe4f6a624238 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -203,7 +203,7 @@ static void fib_flush(struct net *net) struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) - flushed += fib_table_flush(net, tb); + flushed += fib_table_flush(net, tb, false); } if (flushed) @@ -1463,7 +1463,7 @@ static void ip_fib_net_exit(struct net *net) hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); - fib_table_flush(net, tb); + fib_table_flush(net, tb, true); fib_free_table(tb); } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 237c9f72b265..a573e37e0615 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1856,7 +1856,7 @@ void fib_table_flush_external(struct fib_table *tb) } /* Caller must hold RTNL. */ -int fib_table_flush(struct net *net, struct fib_table *tb) +int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; @@ -1904,8 +1904,17 @@ int fib_table_flush(struct net *net, struct fib_table *tb) hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; - if (!fi || !(fi->fib_flags & RTNH_F_DEAD) || - tb->tb_id != fa->tb_id) { + if (!fi || tb->tb_id != fa->tb_id || + (!(fi->fib_flags & RTNH_F_DEAD) && + !fib_props[fa->fa_type].error)) { + slen = fa->fa_slen; + continue; + } + + /* Do not flush error routes if network namespace is + * not being dismantled + */ + if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 0c9f171fb085..437070d1ffb1 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -1020,10 +1020,11 @@ static int gue_err(struct sk_buff *skb, u32 info) { int transport_offset = skb_transport_offset(skb); struct guehdr *guehdr; - size_t optlen; + size_t len, optlen; int ret; - if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr)) + len = sizeof(struct udphdr) + sizeof(struct guehdr); + if (!pskb_may_pull(skb, len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; @@ -1058,6 +1059,10 @@ static int gue_err(struct sk_buff *skb, u32 info) optlen = guehdr->hlen << 2; + if (!pskb_may_pull(skb, len + optlen)) + return -EINVAL; + + guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) return -EINVAL; @@ -1065,7 +1070,8 @@ static int gue_err(struct sk_buff *skb, u32 info) * recursion. Besides, this kind of encapsulation can't even be * configured currently. Discard this. */ - if (guehdr->proto_ctype == IPPROTO_UDP) + if (guehdr->proto_ctype == IPPROTO_UDP || + guehdr->proto_ctype == IPPROTO_UDPLITE) return -EOPNOTSUPP; skb_set_transport_header(skb, -(int)sizeof(struct icmphdr)); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index a4bf22ee3aed..7c4a41dc04bb 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -25,6 +25,7 @@ #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> +#include <net/erspan.h> #include <net/icmp.h> #include <net/route.h> @@ -119,6 +120,22 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, hdr_len += 4; } tpi->hdr_len = hdr_len; + + /* ERSPAN ver 1 and 2 protocol sets GRE key field + * to 0 and sets the configured key in the + * inner erspan header field + */ + if (greh->protocol == htons(ETH_P_ERSPAN) || + greh->protocol == htons(ETH_P_ERSPAN2)) { + struct erspan_base_hdr *ershdr; + + if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) + return -EINVAL; + + ershdr = (struct erspan_base_hdr *)options; + tpi->key = cpu_to_be32(get_session_id(ershdr)); + } + return hdr_len; } EXPORT_SYMBOL(gre_parse_header); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d1d09f3e5f9e..3978f807fa8b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -268,20 +268,11 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int len; itn = net_generic(net, erspan_net_id); - len = gre_hdr_len + sizeof(*ershdr); - - /* Check based hdr len */ - if (unlikely(!pskb_may_pull(skb, len))) - return PACKET_REJECT; iph = ip_hdr(skb); ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; - /* The original GRE header does not have key field, - * Use ERSPAN 10-bit session ID as key. - */ - tpi->key = cpu_to_be32(get_session_id(ershdr)); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); @@ -569,8 +560,7 @@ err_free_skb: dev->stats.tx_dropped++; } -static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, - __be16 proto) +static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; @@ -578,10 +568,10 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, struct erspan_metadata *md; struct rtable *rt = NULL; bool truncate = false; + __be16 df, proto; struct flowi4 fl; int tunnel_hlen; int version; - __be16 df; int nhoff; int thoff; @@ -626,18 +616,20 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); + proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); + proto = htons(ETH_P_ERSPAN2); } else { goto err_free_rt; } gre_build_header(skb, 8, TUNNEL_SEQ, - htons(ETH_P_ERSPAN), 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(tunnel->o_seqno++)); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -721,12 +713,13 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; + __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { - erspan_fb_xmit(skb, dev, skb->protocol); + erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } @@ -742,19 +735,22 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, } /* Push ERSPAN header */ - if (tunnel->erspan_ver == 1) + if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); - else if (tunnel->erspan_ver == 2) + proto = htons(ETH_P_ERSPAN); + } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); - else + proto = htons(ETH_P_ERSPAN2); + } else { goto free_skb; + } tunnel->parms.o_flags &= ~TUNNEL_KEY; - __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_ERSPAN)); + __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: @@ -1459,12 +1455,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((t->erspan_ver == 1 || t->erspan_ver == 2) && + !t->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 26921f6b3b92..51d8efba6de2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -488,6 +488,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto drop; } + iph = ip_hdr(skb); skb->transport_header = skb->network_header + iph->ihl*4; /* Remove any debris in the socket control block */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index fffcc130900e..82f341e84fae 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -148,19 +148,17 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { + __be16 _ports[2], *ports; struct sockaddr_in sin; - __be16 *ports; - int end; - - end = skb_transport_offset(skb) + 4; - if (end > 0 && !pskb_may_pull(skb, end)) - return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (!ports) + return; sin.sin_family = AF_INET; sin.sin_addr.s_addr = ip_hdr(skb)->daddr; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index c4f5602308ed..054d01c16dc6 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -644,13 +644,19 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ + struct ip_tunnel_info *tun_info; if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } - if (skb->protocol == htons(ETH_P_IP)) { + tun_info = skb_tunnel_info(skb); + if (tun_info && (tun_info->mode & IP_TUNNEL_INFO_TX) && + ip_tunnel_info_af(tun_info) == AF_INET && + tun_info->key.u.ipv4.dst) + dst = tun_info->key.u.ipv4.dst; + else if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); dst = rt_nexthop(rt, inner_iph->daddr); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d7b43e700023..68a21bf75dd0 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -74,6 +74,33 @@ drop: return 0; } +static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + + skb->dev = tunnel->dev; + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + static int vti_rcv(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; @@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb) return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); } +static int vti_rcv_ipip(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0); +} + static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = vti_rcv_ipip, + .err_handler = vti4_err, + .priority = 0, +}; + static int __net_init vti_init_net(struct net *net) { int err; @@ -603,6 +644,13 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; + msg = "ipip tunnel"; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: cant't register tunnel\n",__func__); + goto xfrm_tunnel_failed; + } + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) @@ -612,6 +660,8 @@ static int __init vti_init(void) rtnl_link_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); +xfrm_tunnel_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index b61977db9b7f..2a909e5f9ba0 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -846,9 +846,9 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { +#ifdef CONFIG_PROC_FS struct clusterip_net *cn = clusterip_pernet(net); -#ifdef CONFIG_PROC_FS mutex_lock(&cn->mutex); proc_remove(cn->procdir); cn->procdir = NULL; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 27e2f6837062..2079145a3b7c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1186,7 +1186,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { - if (sk->sk_state != TCP_ESTABLISHED) { + if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { err = -EINVAL; goto out_err; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f87dbc78b6bc..71a29e9c0620 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -226,7 +226,7 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) { dst_negative_advice(sk); - } else if (!tp->syn_data && !tp->syn_fastopen) { + } else { sk_rethink_txhash(sk); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3fb0ed5e4789..5c3cd5d84a6f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -847,15 +847,23 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) + if (hlen + cork->gso_size > cork->fragsize) { + kfree_skb(skb); return -EINVAL; - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + } + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); return -EINVAL; - if (sk->sk_no_check_tx) + } + if (sk->sk_no_check_tx) { + kfree_skb(skb); return -EINVAL; + } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) + dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); return -EIO; + } skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; @@ -1918,7 +1926,7 @@ void udp_lib_rehash(struct sock *sk, u16 newhash) } EXPORT_SYMBOL(udp_lib_rehash); -static void udp_v4_rehash(struct sock *sk) +void udp_v4_rehash(struct sock *sk) { u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 322672655419..6b2fa77eeb1c 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -10,6 +10,7 @@ int __udp4_lib_rcv(struct sk_buff *, struct udp_table *, int); int __udp4_lib_err(struct sk_buff *, u32, struct udp_table *); int udp_v4_get_port(struct sock *sk, unsigned short snum); +void udp_v4_rehash(struct sock *sk); int udp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 39c7f17d916f..3c94b8f0ff27 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -53,6 +53,7 @@ struct proto udplite_prot = { .sendpage = udp_sendpage, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8eeec6eb2bd3..84c358804355 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3495,8 +3495,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ - pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", - dev->name); + pr_debug("ADDRCONF(NETDEV_UP): %s: link is not ready\n", + dev->name); break; } @@ -5120,6 +5120,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, if (idev) { err = in6_dump_addrs(idev, skb, cb, s_ip_idx, &fillargs); + if (err > 0) + err = 0; } goto put_tgt_net; } @@ -5154,7 +5156,7 @@ put_tgt_net: if (fillargs.netnsid >= 0) put_net(tgt_net); - return err < 0 ? err : skb->len; + return skb->len ? : err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0bfb6cc0a30a..d99753b5e39b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -310,6 +310,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, /* Check if the address belongs to the host. */ if (addr_type == IPV6_ADDR_MAPPED) { + struct net_device *dev = NULL; int chk_addr_ret; /* Binding to v4-mapped address on a v6-only socket @@ -320,9 +321,20 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, goto out; } + rcu_read_lock(); + if (sk->sk_bound_dev_if) { + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); + if (!dev) { + err = -ENODEV; + goto out_unlock; + } + } + /* Reproduce AF_INET checks to make the bindings consistent */ v4addr = addr->sin6_addr.s6_addr32[3]; - chk_addr_ret = inet_addr_type(net, v4addr); + chk_addr_ret = inet_addr_type_dev_table(net, dev, v4addr); + rcu_read_unlock(); + if (!inet_can_nonlocal_bind(net, inet) && v4addr != htonl(INADDR_ANY) && chk_addr_ret != RTN_LOCAL && diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index bde08aa549f3..ee4a4e54d016 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -341,6 +341,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; + ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; @@ -700,17 +701,15 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports; - int end; + __be16 _ports[2], *ports; - end = skb_transport_offset(skb) + 4; - if (end <= 0 || pskb_may_pull(skb, end)) { + ports = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_ports), &_ports); + if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ - ports = (__be16 *)skb_transport_header(skb); - sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index bd675c61deb1..b858bd5280bf 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -90,10 +90,11 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { int transport_offset = skb_transport_offset(skb); struct guehdr *guehdr; - size_t optlen; + size_t len, optlen; int ret; - if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr)) + len = sizeof(struct udphdr) + sizeof(struct guehdr); + if (!pskb_may_pull(skb, len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; @@ -128,9 +129,21 @@ static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, optlen = guehdr->hlen << 2; + if (!pskb_may_pull(skb, len + optlen)) + return -EINVAL; + + guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) return -EINVAL; + /* Handling exceptions for direct UDP encapsulation in GUE would lead to + * recursion. Besides, this kind of encapsulation can't even be + * configured currently. Discard this. + */ + if (guehdr->proto_ctype == IPPROTO_UDP || + guehdr->proto_ctype == IPPROTO_UDPLITE) + return -EOPNOTSUPP; + skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr)); ret = gue6_err_proto_handler(guehdr->proto_ctype, skb, opt, type, code, offset, info); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 5d7aa2c2770c..bbcdfd299692 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -423,10 +423,10 @@ static int icmp6_iif(const struct sk_buff *skb) static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr) { - struct net *net = dev_net(skb->dev); struct inet6_dev *idev = NULL; struct ipv6hdr *hdr = ipv6_hdr(skb); struct sock *sk; + struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct dst_entry *dst; @@ -437,12 +437,16 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, int iif = 0; int addr_type = 0; int len; - u32 mark = IP6_REPLY_MARK(net, skb->mark); + u32 mark; if ((u8 *)hdr < skb->head || (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb)) return; + if (!skb->dev) + return; + net = dev_net(skb->dev); + mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules * i.e. RFC 1885 2.4(e) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 09d0826742f8..801a9a0c217e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -534,13 +534,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, struct ip6_tnl *tunnel; u8 ver; - if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) - return PACKET_REJECT; - ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; - tpi->key = cpu_to_be32(get_session_id(ershdr)); tunnel = ip6gre_tunnel_lookup(skb->dev, &ipv6h->saddr, &ipv6h->daddr, tpi->key, @@ -922,6 +918,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, __u8 dsfield = false; struct flowi6 fl6; int err = -EINVAL; + __be16 proto; __u32 mtu; int nhoff; int thoff; @@ -1035,8 +1032,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, } /* Push GRE header. */ - gre_build_header(skb, 8, TUNNEL_SEQ, - htons(ETH_P_ERSPAN), 0, htonl(t->o_seqno++)); + proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) + : htons(ETH_P_ERSPAN2); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) @@ -1169,6 +1167,10 @@ static void ip6gre_tnl_copy_tnl_parm(struct ip6_tnl *t, t->parms.i_flags = p->i_flags; t->parms.o_flags = p->o_flags; t->parms.fwmark = p->fwmark; + t->parms.erspan_ver = p->erspan_ver; + t->parms.index = p->index; + t->parms.dir = p->dir; + t->parms.hwid = p->hwid; dst_cache_reset(&t->dst_cache); } @@ -2025,9 +2027,9 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - struct ip6gre_net *ign = net_generic(dev_net(dev), ip6gre_net_id); + struct ip6_tnl *t = netdev_priv(dev); + struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id); struct __ip6_tnl_parm p; - struct ip6_tnl *t; t = ip6gre_changelink_common(dev, tb, data, &p, extack); if (IS_ERR(t)) @@ -2096,12 +2098,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((p->erspan_ver == 1 || p->erspan_ver == 2) && + !p->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 30337b38274b..cc01aa3f2b5e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1516,6 +1516,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, + (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } @@ -1524,10 +1527,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), - FIB_EVENT_ENTRY_DEL, - (struct mfc6_cache *)c, - mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 8b075f0bc351..6d0b1f3e927b 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 40b225f87d5e..964491cf3672 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4251,17 +4251,6 @@ struct rt6_nh { struct list_head next; }; -static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) -{ - struct rt6_nh *nh; - - list_for_each_entry(nh, rt6_nh_list, next) { - pr_warn("IPV6: multipath route replace failed (check consistency of installed routes): %pI6c nexthop %pI6c ifi %d\n", - &nh->r_cfg.fc_dst, &nh->r_cfg.fc_gateway, - nh->r_cfg.fc_ifindex); - } -} - static int ip6_route_info_append(struct net *net, struct list_head *rt6_nh_list, struct fib6_info *rt, @@ -4407,7 +4396,8 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, nh->fib6_info = NULL; if (err) { if (replace && nhn) - ip6_print_replace_route_err(&rt6_nh_list); + NL_SET_ERR_MSG_MOD(extack, + "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1e03305c0549..e8a1dabef803 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9cbf363172bd..2596ffdeebea 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -102,7 +102,7 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static void udp_v6_rehash(struct sock *sk) +void udp_v6_rehash(struct sock *sk) { u16 new_hash = ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, @@ -1132,15 +1132,23 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) + if (hlen + cork->gso_size > cork->fragsize) { + kfree_skb(skb); return -EINVAL; - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + } + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); return -EINVAL; - if (udp_sk(sk)->no_check6_tx) + } + if (udp_sk(sk)->no_check6_tx) { + kfree_skb(skb); return -EINVAL; + } if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) + dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); return -EIO; + } skb_shinfo(skb)->gso_size = cork->gso_size; skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; @@ -1390,10 +1398,7 @@ do_udp_sendmsg: ipc6.opt = opt; fl6.flowi6_proto = sk->sk_protocol; - if (!ipv6_addr_any(daddr)) - fl6.daddr = *daddr; - else - fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + fl6.daddr = *daddr; if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; @@ -1421,6 +1426,9 @@ do_udp_sendmsg: } } + if (ipv6_addr_any(&fl6.daddr)) + fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h index 5730e6503cb4..20e324b6f358 100644 --- a/net/ipv6/udp_impl.h +++ b/net/ipv6/udp_impl.h @@ -13,6 +13,7 @@ int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int, __be32, struct udp_table *); int udp_v6_get_port(struct sock *sk, unsigned short snum); +void udp_v6_rehash(struct sock *sk); int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index a125aebc29e5..f35907836444 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -49,6 +49,7 @@ struct proto udplitev6_prot = { .recvmsg = udpv6_recvmsg, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..fed6becc5daf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); @@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..0ae6899edac0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index de65fe3ed9cc..2493c74c2d37 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1490,6 +1490,10 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; + if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated) + return -EINVAL; + err = sta_apply_parameters(local, sta, params); if (err) { sta_info_free(local, sta); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 45aad3d3108c..bb4d71efb6fb 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -231,7 +231,7 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr_3addr hdr; u8 category; u8 action_code; - } __packed action; + } __packed __aligned(2) action; if (!sdata) return; @@ -2723,7 +2723,9 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) skb_set_queue_mapping(skb, q); if (!--mesh_hdr->ttl) { - IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl); + if (!is_multicast_ether_addr(hdr->addr1)) + IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, + dropped_frames_ttl); goto out; } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..928f13a208b0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1938,9 +1938,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1948,8 +1955,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 432141f04af3..7d6318664eb2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2221,6 +2221,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user u->udp_timeout); #ifdef CONFIG_IP_VS_PROTO_TCP + if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || + u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { + return -EINVAL; + } +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP + if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) + return -EINVAL; +#endif + +#ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 741b533148ba..db4d46332e86 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1007,6 +1007,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index fa0844e2a68d..c0c72ae9df42 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -28,6 +28,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, { struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple; + struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; ft->dir = dir; @@ -50,8 +51,8 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, ft->src_port = ctt->src.u.tcp.port; ft->dst_port = ctt->dst.u.tcp.port; - ft->iifidx = route->tuple[dir].ifindex; - ft->oifidx = route->tuple[!dir].ifindex; + ft->iifidx = other_dst->dev->ifindex; + ft->oifidx = dst->dev->ifindex; ft->dst_cache = dst; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2b0a93300dd7..5a92f23f179f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -116,6 +116,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + nft_trans_set_bound(trans) = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -211,18 +228,6 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } -/* either expr ops provide both activate/deactivate, or neither */ -static bool nft_expr_check_ops(const struct nft_expr_ops *ops) -{ - if (!ops) - return true; - - if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate))) - return false; - - return true; -} - static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { @@ -238,14 +243,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -296,7 +302,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -1929,9 +1935,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, */ int nft_register_expr(struct nft_expr_type *type) { - if (!nft_expr_check_ops(type->ops)) - return -EINVAL; - nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -2079,10 +2082,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); goto err1; } - if (!nft_expr_check_ops(ops)) { - err = -EINVAL; - goto err1; - } } else ops = type->ops; @@ -2304,7 +2303,6 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); unsigned int s_idx = cb->args[0]; const struct nft_rule *rule; - int rc = 1; list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) @@ -2321,16 +2319,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NLM_F_MULTI | NLM_F_APPEND, table->family, table, chain, rule) < 0) - goto out_unfinished; + return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: (*idx)++; } - rc = 0; -out_unfinished: - cb->args[0] = *idx; - return rc; + return 0; } static int nf_tables_dump_rules(struct sk_buff *skb, @@ -2354,7 +2349,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, if (ctx && ctx->table && strcmp(ctx->table, table->name) != 0) continue; - if (ctx && ctx->chain) { + if (ctx && ctx->table && ctx->chain) { struct rhlist_head *list, *tmp; list = rhltable_lookup(&table->chains_ht, ctx->chain, @@ -2382,6 +2377,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb, } done: rcu_read_unlock(); + + cb->args[0] = idx; return skb->len; } @@ -2513,7 +2510,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -3710,39 +3707,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) -{ - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - list_add_tail_rcu(&set->list, &ctx->table->sets); - - list_add_tail_rcu(&binding->list, &set->bindings); -} -EXPORT_SYMBOL_GPL(nf_tables_rebind_set); - void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) { - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(set); - } } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -4508,6 +4496,8 @@ err6: err5: kfree(trans); err4: + if (obj) + obj->use--; kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) @@ -6535,6 +6525,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6621,7 +6614,8 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + if (!nft_trans_set_bound(trans)) + nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -6682,7 +6676,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6692,7 +6688,8 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del_rcu(&nft_trans_set(trans)->list); + if (!nft_trans_set_bound(trans)) + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 6f41dd74729d..1f1d90c1716b 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -66,6 +66,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb, int ttl_check, struct nf_osf_hdr_ctx *ctx) { + const __u8 *optpinit = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; @@ -155,6 +156,9 @@ static bool nf_osf_match_one(const struct sk_buff *skb, } } + if (fmatch != FMATCH_OK) + ctx->optp = optpinit; + return fmatch == FMATCH_OK; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 7334e0b80a5e..fe64df848365 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -22,11 +22,15 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netns/generic.h> struct nft_xt { struct list_head head; struct nft_expr_ops ops; - unsigned int refcnt; + refcount_t refcnt; + + /* used only when transaction mutex is locked */ + unsigned int listcnt; /* Unlike other expressions, ops doesn't have static storage duration. * nft core assumes they do. We use kfree_rcu so that nft core can @@ -43,10 +47,39 @@ struct nft_xt_match_priv { void *info; }; +struct nft_compat_net { + struct list_head nft_target_list; + struct list_head nft_match_list; +}; + +static unsigned int nft_compat_net_id __read_mostly; +static struct nft_expr_type nft_match_type; +static struct nft_expr_type nft_target_type; + +static struct nft_compat_net *nft_compat_pernet(struct net *net) +{ + return net_generic(net, nft_compat_net_id); +} + +static void nft_xt_get(struct nft_xt *xt) +{ + /* refcount_inc() warns on 0 -> 1 transition, but we can't + * init the reference count to 1 in .select_ops -- we can't + * undo such an increase when another expression inside the same + * rule fails afterwards. + */ + if (xt->listcnt == 0) + refcount_set(&xt->refcnt, 1); + else + refcount_inc(&xt->refcnt); + + xt->listcnt++; +} + static bool nft_xt_put(struct nft_xt *xt) { - if (--xt->refcnt == 0) { - list_del(&xt->head); + if (refcount_dec_and_test(&xt->refcnt)) { + WARN_ON_ONCE(!list_empty(&xt->head)); kfree_rcu(xt, rcu_head); return true; } @@ -273,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + nft_xt_get(nft_xt); return 0; } @@ -486,7 +519,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + nft_xt_get(nft_xt); return 0; } @@ -540,6 +573,18 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } +static void nft_compat_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); + + if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { + if (--xt->listcnt == 0) + list_del_init(&xt->head); + } +} + static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -734,10 +779,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, }; -static LIST_HEAD(nft_match_list); - -static struct nft_expr_type nft_match_type; - static bool nft_match_cmp(const struct xt_match *match, const char *name, u32 rev, u32 family) { @@ -749,6 +790,7 @@ static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_match; struct xt_match *match; unsigned int matchsize; @@ -765,8 +807,10 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; + cn = nft_compat_pernet(ctx->net); + /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &nft_match_list, head) { + list_for_each_entry(nft_match, &cn->nft_match_list, head) { struct xt_match *match = nft_match->ops.data; if (nft_match_cmp(match, mt_name, rev, family)) @@ -789,11 +833,12 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - nft_match->refcnt = 0; + refcount_set(&nft_match->refcnt, 0); nft_match->ops.type = &nft_match_type; nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; + nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; nft_match->ops.data = match; @@ -810,7 +855,8 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - list_add(&nft_match->head, &nft_match_list); + nft_match->listcnt = 0; + list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; err: @@ -826,10 +872,6 @@ static struct nft_expr_type nft_match_type __read_mostly = { .owner = THIS_MODULE, }; -static LIST_HEAD(nft_target_list); - -static struct nft_expr_type nft_target_type; - static bool nft_target_cmp(const struct xt_target *tg, const char *name, u32 rev, u32 family) { @@ -841,6 +883,7 @@ static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_target; struct xt_target *target; char *tg_name; @@ -861,8 +904,9 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); + cn = nft_compat_pernet(ctx->net); /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_target_list, head) { + list_for_each_entry(nft_target, &cn->nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (!target->target) @@ -893,11 +937,12 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - nft_target->refcnt = 0; + refcount_set(&nft_target->refcnt, 0); nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; + nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; nft_target->ops.data = target; @@ -907,7 +952,8 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - list_add(&nft_target->head, &nft_target_list); + nft_target->listcnt = 0; + list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; err: @@ -923,13 +969,74 @@ static struct nft_expr_type nft_target_type __read_mostly = { .owner = THIS_MODULE, }; +static int __net_init nft_compat_init_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + + INIT_LIST_HEAD(&cn->nft_target_list); + INIT_LIST_HEAD(&cn->nft_match_list); + + return 0; +} + +static void __net_exit nft_compat_exit_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + struct nft_xt *xt, *next; + + if (list_empty(&cn->nft_match_list) && + list_empty(&cn->nft_target_list)) + return; + + /* If there was an error that caused nft_xt expr to not be initialized + * fully and noone else requested the same expression later, the lists + * contain 0-refcount entries that still hold module reference. + * + * Clean them here. + */ + mutex_lock(&net->nft.commit_mutex); + list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) { + struct xt_target *target = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(target->me); + kfree(xt); + } + + list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) { + struct xt_match *match = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(match->me); + kfree(xt); + } + mutex_unlock(&net->nft.commit_mutex); +} + +static struct pernet_operations nft_compat_net_ops = { + .init = nft_compat_init_net, + .exit = nft_compat_exit_net, + .id = &nft_compat_net_id, + .size = sizeof(struct nft_compat_net), +}; + static int __init nft_compat_module_init(void) { int ret; + ret = register_pernet_subsys(&nft_compat_net_ops); + if (ret < 0) + goto err_target; + ret = nft_register_expr(&nft_match_type); if (ret < 0) - return ret; + goto err_pernet; ret = nft_register_expr(&nft_target_type); if (ret < 0) @@ -942,45 +1049,21 @@ static int __init nft_compat_module_init(void) } return ret; - err_target: nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); +err_pernet: + unregister_pernet_subsys(&nft_compat_net_ops); return ret; } static void __exit nft_compat_module_exit(void) { - struct nft_xt *xt, *next; - - /* list should be empty here, it can be non-empty only in case there - * was an error that caused nft_xt expr to not be initialized fully - * and noone else requested the same expression later. - * - * In this case, the lists contain 0-refcount entries that still - * hold module reference. - */ - list_for_each_entry_safe(xt, next, &nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(match->me); - kfree(xt); - } nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); + unregister_pernet_subsys(&nft_compat_net_ops); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 07d4efd3d851..f1172f99752b 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -235,20 +235,17 @@ err1: return err; } -static void nft_dynset_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_dynset *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_dynset_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_dynset_destroy(const struct nft_ctx *ctx, @@ -296,7 +293,6 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, - .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 974525eb92df..6e6b9adf7d38 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -12,6 +12,7 @@ #include <net/netfilter/nf_conntrack_core.h> #include <linux/netfilter/nf_conntrack_common.h> #include <net/netfilter/nf_flow_table.h> +#include <net/netfilter/nf_conntrack_helper.h> struct nft_flow_offload { struct nft_flowtable *flowtable; @@ -29,10 +30,12 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: - fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.dst.u3.ip; + fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; + fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; break; case NFPROTO_IPV6: - fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.dst.u3.in6; + fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; + fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; break; } @@ -41,9 +44,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, return -ENOENT; route->tuple[dir].dst = this_dst; - route->tuple[dir].ifindex = nft_in(pkt)->ifindex; route->tuple[!dir].dst = other_dst; - route->tuple[!dir].ifindex = nft_out(pkt)->ifindex; return 0; } @@ -66,6 +67,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; + const struct nf_conn_help *help; enum ip_conntrack_info ctinfo; struct nf_flow_route route; struct flow_offload *flow; @@ -88,7 +90,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto out; } - if (test_bit(IPS_HELPER_BIT, &ct->status)) + help = nfct_help(ct); + if (help) goto out; if (ctinfo == IP_CT_NEW || diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 0777a93211e2..3f6d1d2a6281 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 227b2b15a19c..14496da5141d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_lookup *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_lookup_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_lookup_destroy(const struct nft_ctx *ctx, @@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, - .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index a3185ca2a3a9..ae178e914486 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -155,20 +155,17 @@ nla_put_failure: return -1; } -static void nft_objref_map_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_objref_map *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_objref_map_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, @@ -185,7 +182,6 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, - .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index cbd51ed5a2d7..908e53ab47a4 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t1timer, jiffies + nr->t1); + sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1); } void nr_start_t2timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t2timer, jiffies + nr->t2); + sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2); } void nr_start_t4timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t4timer, jiffies + nr->t4); + sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4); } void nr_start_idletimer(struct sock *sk) @@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk) struct nr_sock *nr = nr_sk(sk); if (nr->idle > 0) - mod_timer(&nr->idletimer, jiffies + nr->idle); + sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle); } void nr_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void nr_stop_t1timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t1timer); + sk_stop_timer(sk, &nr_sk(sk)->t1timer); } void nr_stop_t2timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t2timer); + sk_stop_timer(sk, &nr_sk(sk)->t2timer); } void nr_stop_t4timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t4timer); + sk_stop_timer(sk, &nr_sk(sk)->t4timer); } void nr_stop_idletimer(struct sock *sk) { - del_timer(&nr_sk(sk)->idletimer); + sk_stop_timer(sk, &nr_sk(sk)->idletimer); } void nr_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } int nr_t1timer_running(struct sock *sk) diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 57e07768c9d1..f54cf17ef7a8 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -276,10 +276,12 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); if (flags & IP6_FH_F_FRAG) { - if (frag_off) + if (frag_off) { key->ip.frag = OVS_FRAG_TYPE_LATER; - else - key->ip.frag = OVS_FRAG_TYPE_FIRST; + key->ip.proto = nexthdr; + return 0; + } + key->ip.frag = OVS_FRAG_TYPE_FIRST; } else { key->ip.frag = OVS_FRAG_TYPE_NONE; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 435a4bdf8f89..691da853bef5 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -500,7 +500,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - if (!nz || !is_all_zero(nla_data(nla), expected_len)) { + if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) { attrs |= 1 << type; a[type] = nla; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index eedacdebcd4c..3b1a78906bc0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2628,7 +2628,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_put; } err = -ENXIO; @@ -2828,7 +2828,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) addr = saddr->sll_halen ? saddr->sll_addr : NULL; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (addr && dev && saddr->sll_halen < dev->addr_len) - goto out; + goto out_unlock; } err = -ENXIO; @@ -2887,7 +2887,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); - if (len < reserve) + if (len < reserve + sizeof(struct ipv6hdr) && + dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..17c9d9f0c848 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 2dcb555e6350..4e0c36acf866 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -522,7 +522,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, if (be32_to_cpu(rm->m_inc.i_hdr.h_len) == 0) i = 1; else - i = ceil(be32_to_cpu(rm->m_inc.i_hdr.h_len), RDS_FRAG_SIZE); + i = DIV_ROUND_UP(be32_to_cpu(rm->m_inc.i_hdr.h_len), RDS_FRAG_SIZE); work_alloc = rds_ib_ring_alloc(&ic->i_send_ring, i, &pos); if (work_alloc == 0) { @@ -879,7 +879,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) * Instead of knowing how to return a partial rdma read/write we insist that there * be enough work requests to send the entire message. */ - i = ceil(op->op_count, max_sge); + i = DIV_ROUND_UP(op->op_count, max_sge); work_alloc = rds_ib_ring_alloc(&ic->i_send_ring, i, &pos); if (work_alloc != i) { diff --git a/net/rds/message.c b/net/rds/message.c index f139420ba1f6..50f13f1d4ae0 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -341,7 +341,7 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in { struct rds_message *rm; unsigned int i; - int num_sgs = ceil(total_len, PAGE_SIZE); + int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); int ret; @@ -351,7 +351,7 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); - rm->data.op_nents = ceil(total_len, PAGE_SIZE); + rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); if (!rm->data.op_sg) { rds_message_put(rm); diff --git a/net/rds/rds.h b/net/rds/rds.h index 02ec4a3b2799..4ffe100ff5e6 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -48,10 +48,6 @@ void rdsdebug(char *fmt, ...) } #endif -/* XXX is there one of these somewhere? */ -#define ceil(x, y) \ - ({ unsigned long __x = (x), __y = (y); (__x + __y - 1) / __y; }) - #define RDS_FRAG_SHIFT 12 #define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT)) diff --git a/net/rds/send.c b/net/rds/send.c index 3d822bad7de9..fd8b687d5c05 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1107,7 +1107,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) size_t total_payload_len = payload_len, rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); - int num_sgs = ceil(payload_len, PAGE_SIZE); + int num_sgs = DIV_ROUND_UP(payload_len, PAGE_SIZE); int namelen; struct rds_iov_vector_arr vct; int ind; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 77e9f85a2c92..f2ff21d7df08 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev) /* * Route a frame to an appropriate AX.25 connection. + * A NULL ax25_cb indicates an internally generated frame. */ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) { @@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (skb->len < ROSE_MIN_LEN) return res; + + if (!ax25) + return rose_loopback_queue(skb, NULL); + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); if (frametype == ROSE_CALL_REQUEST && diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index a2522f9d71e2..96f2952bbdfd 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -419,76 +419,6 @@ u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call) EXPORT_SYMBOL(rxrpc_kernel_get_epoch); /** - * rxrpc_kernel_check_call - Check a call's state - * @sock: The socket the call is on - * @call: The call to check - * @_compl: Where to store the completion state - * @_abort_code: Where to store any abort code - * - * Allow a kernel service to query the state of a call and find out the manner - * of its termination if it has completed. Returns -EINPROGRESS if the call is - * still going, 0 if the call finished successfully, -ECONNABORTED if the call - * was aborted and an appropriate error if the call failed in some other way. - */ -int rxrpc_kernel_check_call(struct socket *sock, struct rxrpc_call *call, - enum rxrpc_call_completion *_compl, u32 *_abort_code) -{ - if (call->state != RXRPC_CALL_COMPLETE) - return -EINPROGRESS; - smp_rmb(); - *_compl = call->completion; - *_abort_code = call->abort_code; - return call->error; -} -EXPORT_SYMBOL(rxrpc_kernel_check_call); - -/** - * rxrpc_kernel_retry_call - Allow a kernel service to retry a call - * @sock: The socket the call is on - * @call: The call to retry - * @srx: The address of the peer to contact - * @key: The security context to use (defaults to socket setting) - * - * Allow a kernel service to try resending a client call that failed due to a - * network error to a new address. The Tx queue is maintained intact, thereby - * relieving the need to re-encrypt any request data that has already been - * buffered. - */ -int rxrpc_kernel_retry_call(struct socket *sock, struct rxrpc_call *call, - struct sockaddr_rxrpc *srx, struct key *key) -{ - struct rxrpc_conn_parameters cp; - struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - int ret; - - _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); - - if (!key) - key = rx->key; - if (key && !key->payload.data[0]) - key = NULL; /* a no-security key */ - - memset(&cp, 0, sizeof(cp)); - cp.local = rx->local; - cp.key = key; - cp.security_level = 0; - cp.exclusive = false; - cp.service_id = srx->srx_service; - - mutex_lock(&call->user_mutex); - - ret = rxrpc_prepare_call_for_retry(rx, call); - if (ret == 0) - ret = rxrpc_retry_client_call(rx, call, &cp, srx, GFP_KERNEL); - - mutex_unlock(&call->user_mutex); - rxrpc_put_peer(cp.peer); - _leave(" = %d", ret); - return ret; -} -EXPORT_SYMBOL(rxrpc_kernel_retry_call); - -/** * rxrpc_kernel_new_call_notification - Get notifications of new calls * @sock: The socket to intercept received messages on * @notify_new_call: Function to be called when new calls appear diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bc628acf4f4f..4b1a534d290a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -476,7 +476,6 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ - RXRPC_CALL_TX_LASTQ, /* Last packet has been queued */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ @@ -518,6 +517,18 @@ enum rxrpc_call_state { }; /* + * Call completion condition (state == RXRPC_CALL_COMPLETE). + */ +enum rxrpc_call_completion { + RXRPC_CALL_SUCCEEDED, /* - Normal termination */ + RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ + RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ + RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ + NR__RXRPC_CALL_COMPLETIONS +}; + +/* * Call Tx congestion management modes. */ enum rxrpc_congest_mode { @@ -761,15 +772,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); -int rxrpc_retry_client_call(struct rxrpc_sock *, - struct rxrpc_call *, - struct rxrpc_conn_parameters *, - struct sockaddr_rxrpc *, - gfp_t); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); -int rxrpc_prepare_call_for_retry(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); bool __rxrpc_queue_call(struct rxrpc_call *); bool rxrpc_queue_call(struct rxrpc_call *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8f1a8f85b1f9..8aa2937b069f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -325,48 +325,6 @@ error: } /* - * Retry a call to a new address. It is expected that the Tx queue of the call - * will contain data previously packaged for an old call. - */ -int rxrpc_retry_client_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) -{ - const void *here = __builtin_return_address(0); - int ret; - - /* Set up or get a connection record and set the protocol parameters, - * including channel number and call ID. - */ - ret = rxrpc_connect_call(rx, call, cp, srx, gfp); - if (ret < 0) - goto error; - - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); - - rxrpc_start_call_timer(call); - - _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); - - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - - _leave(" = 0"); - return 0; - -error: - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); - _leave(" = %d", ret); - return ret; -} - -/* * Set up an incoming call. call->conn points to the connection. * This is called in BH context and isn't allowed to fail. */ @@ -534,61 +492,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) } /* - * Prepare a kernel service call for retry. - */ -int rxrpc_prepare_call_for_retry(struct rxrpc_sock *rx, struct rxrpc_call *call) -{ - const void *here = __builtin_return_address(0); - int i; - u8 last = 0; - - _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), - here, (const void *)call->flags); - - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - ASSERTCMP(call->completion, !=, RXRPC_CALL_REMOTELY_ABORTED); - ASSERTCMP(call->completion, !=, RXRPC_CALL_LOCALLY_ABORTED); - ASSERT(list_empty(&call->recvmsg_link)); - - del_timer_sync(&call->timer); - - _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, call->conn); - - if (call->conn) - rxrpc_disconnect_call(call); - - if (rxrpc_is_service_call(call) || - !call->tx_phase || - call->tx_hard_ack != 0 || - call->rx_hard_ack != 0 || - call->rx_top != 0) - return -EINVAL; - - call->state = RXRPC_CALL_UNINITIALISED; - call->completion = RXRPC_CALL_SUCCEEDED; - call->call_id = 0; - call->cid = 0; - call->cong_cwnd = 0; - call->cong_extra = 0; - call->cong_ssthresh = 0; - call->cong_mode = 0; - call->cong_dup_acks = 0; - call->cong_cumul_acks = 0; - call->acks_lowest_nak = 0; - - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - last |= call->rxtx_annotations[i]; - call->rxtx_annotations[i] &= RXRPC_TX_ANNO_LAST; - call->rxtx_annotations[i] |= RXRPC_TX_ANNO_RETRANS; - } - - _leave(" = 0"); - return 0; -} - -/* * release all the calls associated with a socket */ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 521189f4b666..b2adfa825363 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -562,10 +562,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); write_lock_bh(&call->state_lock); - if (!test_bit(RXRPC_CALL_TX_LASTQ, &call->flags)) - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - else - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; write_unlock_bh(&call->state_lock); rxrpc_see_call(call); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index eaf19ebaa964..3f7bb11f3290 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index be01f9c5d963..46c9312085b1 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -169,10 +169,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) { + if (last) annotation |= RXRPC_TX_ANNO_LAST; - set_bit(RXRPC_CALL_TX_LASTQ, &call->flags); - } /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. @@ -386,6 +384,11 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, call->tx_total_len -= copy; } + /* check for the far side aborting the call or a network error + * occurring */ + if (call->state == RXRPC_CALL_COMPLETE) + goto call_terminated; + /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || (msg_data_left(msg) == 0 && !more)) { @@ -425,16 +428,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, notify_end_tx); skb = NULL; } - - /* Check for the far side aborting the call or a network error - * occurring. If this happens, save any packet that was under - * construction so that in the case of a network error, the - * call can be retried or redirected. - */ - if (call->state == RXRPC_CALL_COMPLETE) { - ret = call->error; - goto out; - } } while (msg_data_left(msg) > 0); success: @@ -444,6 +437,11 @@ out: _leave(" = %d", ret); return ret; +call_terminated: + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + _leave(" = %d", call->error); + return call->error; + maybe_error: if (copied) goto success; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index c3b90fadaff6..8b43fe0130f7 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -197,6 +197,15 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; +static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) +{ + if (!p) + return; + if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) + dst_release(&p->tcft_enc_metadata->dst); + kfree_rcu(p, rcu); +} + static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, @@ -360,8 +369,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, rcu_swap_protected(t->params, params_new, lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); - if (params_new) - kfree_rcu(params_new, rcu); + tunnel_key_release_params(params_new); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -385,12 +393,7 @@ static void tunnel_key_release(struct tc_action *a) struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); - if (params) { - if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) - dst_release(¶ms->tcft_enc_metadata->dst); - - kfree_rcu(params, rcu); - } + tunnel_key_release_params(params); } static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8ce2a0507970..e2b5cb2eb34e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1277,7 +1277,6 @@ EXPORT_SYMBOL(tcf_block_cb_unregister); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { - __be16 protocol = tc_skb_protocol(skb); #ifdef CONFIG_NET_CLS_ACT const int max_reclassify_loop = 4; const struct tcf_proto *orig_tp = tp; @@ -1287,6 +1286,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { + __be16 protocol = tc_skb_protocol(skb); int err; if (tp->protocol != protocol && @@ -1319,7 +1319,6 @@ reset: } tp = first_tp; - protocol = tc_skb_protocol(skb); goto reclassify; #endif } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index dad04e710493..12ca9d13db83 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1290,17 +1290,23 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *fold = *arg; struct cls_fl_filter *fnew; + struct fl_flow_mask *mask; struct nlattr **tb; - struct fl_flow_mask mask = {}; int err; if (!tca[TCA_OPTIONS]) return -EINVAL; - tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); - if (!tb) + mask = kzalloc(sizeof(struct fl_flow_mask), GFP_KERNEL); + if (!mask) return -ENOBUFS; + tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); + if (!tb) { + err = -ENOBUFS; + goto errout_mask_alloc; + } + err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy, NULL); if (err < 0) @@ -1343,12 +1349,12 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } } - err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr, + err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], ovr, tp->chain->tmplt_priv, extack); if (err) goto errout_idr; - err = fl_check_assign_mask(head, fnew, fold, &mask); + err = fl_check_assign_mask(head, fnew, fold, mask); if (err) goto errout_idr; @@ -1365,7 +1371,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_mask; + goto errout_mask_ht; } if (!tc_in_hw(fnew->flags)) @@ -1392,8 +1398,13 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } kfree(tb); + kfree(mask); return 0; +errout_mask_ht: + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + errout_mask: fl_mask_put(head, fnew->mask, false); @@ -1405,6 +1416,8 @@ errout: kfree(fnew); errout_tb: kfree(tb); +errout_mask_alloc: + kfree(mask); return err; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index b910cd5c56f7..73940293700d 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1667,7 +1667,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); - unsigned int slen = 0; + unsigned int slen = 0, numsegs = 0; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) @@ -1683,6 +1683,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, flow_queue_add(flow, segs); sch->q.qlen++; + numsegs++; slen += segs->len; q->buffer_used += segs->truesize; b->packets++; @@ -1696,7 +1697,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, sch->qstats.backlog += slen; q->avg_window_bytes += slen; - qdisc_tree_reduce_backlog(sch, 1, len); + qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); consume_skb(skb); } else { /* not splitting */ diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index e689e11b6d0f..c6a502933fe7 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -88,13 +88,14 @@ static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); int err; err = child->ops->enqueue(skb, child, to_free); if (err != NET_XMIT_SUCCESS) return err; - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index cdebaed0f8cf..09b800991065 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -350,9 +350,11 @@ static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch, static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct drr_sched *q = qdisc_priv(sch); struct drr_class *cl; int err = 0; + bool first; cl = drr_classify(skb, sch, &err); if (cl == NULL) { @@ -362,6 +364,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } + first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -371,12 +374,12 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - if (cl->qdisc->q.qlen == 1) { + if (first) { list_add_tail(&cl->alist, &q->active); cl->deficit = cl->quantum; } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return err; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index f6f480784bc6..42471464ded3 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -199,6 +199,7 @@ static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct dsmark_qdisc_data *p = qdisc_priv(sch); int err; @@ -271,7 +272,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b18ec1f6de60..24cc220a3218 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1539,8 +1539,10 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb) static int hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct hfsc_class *cl; int uninitialized_var(err); + bool first; cl = hfsc_classify(skb, sch, &err); if (cl == NULL) { @@ -1550,6 +1552,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } + first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { @@ -1559,9 +1562,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } - if (cl->qdisc->q.qlen == 1) { - unsigned int len = qdisc_pkt_len(skb); - + if (first) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) @@ -1576,7 +1577,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 58b449490757..30f9da7e1076 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -581,6 +581,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { int uninitialized_var(ret); + unsigned int len = qdisc_pkt_len(skb); struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = htb_classify(skb, sch, &ret); @@ -610,7 +611,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, htb_activate(q, cl); } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index cdf68706e40f..847141cd900f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -72,6 +72,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) static int prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb); struct Qdisc *qdisc; int ret; @@ -88,7 +89,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) ret = qdisc_enqueue(skb, qdisc, to_free); if (ret == NET_XMIT_SUCCESS) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index dc37c4ead439..29f5c4a24688 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -1210,10 +1210,12 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { + unsigned int len = qdisc_pkt_len(skb), gso_segs; struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl; struct qfq_aggregate *agg; int err = 0; + bool first; cl = qfq_classify(skb, sch, &err); if (cl == NULL) { @@ -1224,17 +1226,18 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid); - if (unlikely(cl->agg->lmax < qdisc_pkt_len(skb))) { + if (unlikely(cl->agg->lmax < len)) { pr_debug("qfq: increasing maxpkt from %u to %u for class %u", - cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid); - err = qfq_change_agg(sch, cl, cl->agg->class_weight, - qdisc_pkt_len(skb)); + cl->agg->lmax, len, cl->common.classid); + err = qfq_change_agg(sch, cl, cl->agg->class_weight, len); if (err) { cl->qstats.drops++; return qdisc_drop(skb, sch, to_free); } } + gso_segs = skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1; + first = !cl->qdisc->q.qlen; err = qdisc_enqueue(skb, cl->qdisc, to_free); if (unlikely(err != NET_XMIT_SUCCESS)) { pr_debug("qfq_enqueue: enqueue failed %d\n", err); @@ -1245,16 +1248,17 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - bstats_update(&cl->bstats, skb); - qdisc_qstats_backlog_inc(sch, skb); + cl->bstats.bytes += len; + cl->bstats.packets += gso_segs; + sch->qstats.backlog += len; ++sch->q.qlen; agg = cl->agg; /* if the queue was not empty, then done here */ - if (cl->qdisc->q.qlen != 1) { + if (!first) { if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) && list_first_entry(&agg->active, struct qfq_class, alist) - == cl && cl->deficit < qdisc_pkt_len(skb)) + == cl && cl->deficit < len) list_move_tail(&cl->alist, &agg->active); return err; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 942dcca09cf2..7f272a9070c5 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -185,6 +185,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct tbf_sched_data *q = qdisc_priv(sch); + unsigned int len = qdisc_pkt_len(skb); int ret; if (qdisc_pkt_len(skb) > q->max_size) { @@ -200,7 +201,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch, return ret; } - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; return NET_XMIT_SUCCESS; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index b9ed271b7ef7..6200cd2b4b99 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -97,11 +97,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; - addr->a.v6.sin6_flowinfo = 0; addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; @@ -282,7 +280,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (saddr) { fl6->saddr = saddr->v6.sin6_addr; - fl6->fl6_sport = saddr->v6.sin6_port; + if (!fl6->fl6_sport) + fl6->fl6_sport = saddr->v6.sin6_port; pr_debug("src=%pI6 - ", &fl6->saddr); } @@ -434,7 +433,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v6.sin6_family = AF_INET6; - addr->a.v6.sin6_port = 0; addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; addr->valid = 1; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d5878ae55840..6abc8b274270 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -101,7 +101,6 @@ static void sctp_v4_copy_addrlist(struct list_head *addrlist, addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; INIT_LIST_HEAD(&addr->list); @@ -441,7 +440,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } if (saddr) { fl4->saddr = saddr->v4.sin_addr.s_addr; - fl4->fl4_sport = saddr->v4.sin_port; + if (!fl4->fl4_sport) + fl4->fl4_sport = saddr->v4.sin_port; } pr_debug("%s: dst:%pI4, src:%pI4 - ", __func__, &fl4->daddr, @@ -776,10 +776,9 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, switch (ev) { case NETDEV_UP: - addr = kmalloc(sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + addr = kzalloc(sizeof(*addr), GFP_ATOMIC); if (addr) { addr->a.v4.sin_family = AF_INET; - addr->a.v4.sin_port = 0; addr->a.v4.sin_addr.s_addr = ifa->ifa_local; addr->valid = 1; spin_lock_bh(&net->sctp.local_addr_lock); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index f4ac6c592e13..d05c57664e36 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -495,7 +495,10 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, * * [INIT ACK back to where the INIT came from.] */ - retval->transport = chunk->transport; + if (chunk->transport) + retval->transport = + sctp_assoc_lookup_paddr(asoc, + &chunk->transport->ipaddr); retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(initack), &initack); @@ -642,8 +645,10 @@ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, * * [COOKIE ACK back to where the COOKIE ECHO came from.] */ - if (retval && chunk) - retval->transport = chunk->transport; + if (retval && chunk && chunk->transport) + retval->transport = + sctp_assoc_lookup_paddr(asoc, + &chunk->transport->ipaddr); return retval; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..65d6d04546ae 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 3892e7630f3a..f24633114dfd 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -147,6 +160,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } @@ -585,9 +605,9 @@ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_strreset_outreq *outreq = param.v; struct sctp_stream *stream = &asoc->stream; __u32 result = SCTP_STRRESET_DENIED; - __u16 i, nums, flags = 0; __be16 *str_p = NULL; __u32 request_seq; + __u16 i, nums; request_seq = ntohl(outreq->request_seq); @@ -615,6 +635,15 @@ struct sctp_chunk *sctp_process_strreset_outreq( if (!(asoc->strreset_enable & SCTP_ENABLE_RESET_STREAM_REQ)) goto out; + nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16); + str_p = outreq->list_of_streams; + for (i = 0; i < nums; i++) { + if (ntohs(str_p[i]) >= stream->incnt) { + result = SCTP_STRRESET_ERR_WRONG_SSN; + goto out; + } + } + if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( asoc, outreq->response_seq, @@ -637,32 +666,19 @@ struct sctp_chunk *sctp_process_strreset_outreq( sctp_chunk_put(asoc->strreset_chunk); asoc->strreset_chunk = NULL; } - - flags = SCTP_STREAM_RESET_INCOMING_SSN; } - nums = (ntohs(param.p->length) - sizeof(*outreq)) / sizeof(__u16); - if (nums) { - str_p = outreq->list_of_streams; - for (i = 0; i < nums; i++) { - if (ntohs(str_p[i]) >= stream->incnt) { - result = SCTP_STRRESET_ERR_WRONG_SSN; - goto out; - } - } - + if (nums) for (i = 0; i < nums; i++) SCTP_SI(stream, ntohs(str_p[i]))->mid = 0; - } else { + else for (i = 0; i < stream->incnt; i++) SCTP_SI(stream, i)->mid = 0; - } result = SCTP_STRRESET_PERFORMED; *evp = sctp_ulpevent_make_stream_reset_event(asoc, - flags | SCTP_STREAM_RESET_OUTGOING_SSN, nums, str_p, - GFP_ATOMIC); + SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC); out: sctp_update_strreset_result(asoc, result); @@ -738,9 +754,6 @@ struct sctp_chunk *sctp_process_strreset_inreq( result = SCTP_STRRESET_PERFORMED; - *evp = sctp_ulpevent_make_stream_reset_event(asoc, - SCTP_STREAM_RESET_INCOMING_SSN, nums, str_p, GFP_ATOMIC); - out: sctp_update_strreset_result(asoc, result); err: @@ -873,6 +886,14 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( if (!(asoc->strreset_enable & SCTP_ENABLE_CHANGE_ASSOC_REQ)) goto out; + in = ntohs(addstrm->number_of_streams); + incnt = stream->incnt + in; + if (!in || incnt > SCTP_MAX_STREAM) + goto out; + + if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) + goto out; + if (asoc->strreset_chunk) { if (!sctp_chunk_lookup_strreset_param( asoc, 0, SCTP_PARAM_RESET_ADD_IN_STREAMS)) { @@ -896,14 +917,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_out( } } - in = ntohs(addstrm->number_of_streams); - incnt = stream->incnt + in; - if (!in || incnt > SCTP_MAX_STREAM) - goto out; - - if (sctp_stream_alloc_in(stream, incnt, GFP_ATOMIC)) - goto out; - stream->incnt = incnt; result = SCTP_STRRESET_PERFORMED; @@ -973,9 +986,6 @@ struct sctp_chunk *sctp_process_strreset_addstrm_in( result = SCTP_STRRESET_PERFORMED; - *evp = sctp_ulpevent_make_stream_change_event(asoc, - 0, 0, ntohs(addstrm->number_of_streams), GFP_ATOMIC); - out: sctp_update_strreset_result(asoc, result); err: @@ -1036,10 +1046,10 @@ struct sctp_chunk *sctp_process_strreset_resp( sout->mid_uo = 0; } } - - flags = SCTP_STREAM_RESET_OUTGOING_SSN; } + flags |= SCTP_STREAM_RESET_OUTGOING_SSN; + for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; @@ -1058,6 +1068,8 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = (ntohs(inreq->param_hdr.length) - sizeof(*inreq)) / sizeof(__u16); + flags |= SCTP_STREAM_RESET_INCOMING_SSN; + *evp = sctp_ulpevent_make_stream_reset_event(asoc, flags, nums, str_p, GFP_ATOMIC); } else if (req->type == SCTP_PARAM_RESET_TSN_REQUEST) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4da4a78d369..b04a813fc865 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -146,6 +146,9 @@ static int smc_release(struct socket *sock) sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; } + + sk->sk_prot->unhash(sk); + if (smc->clcsock) { if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ @@ -170,7 +173,6 @@ static int smc_release(struct socket *sock) smc_conn_free(&smc->conn); release_sock(sk); - sk->sk_prot->unhash(sk); sock_put(sk); /* final sock_put */ out: return rc; @@ -1503,6 +1505,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1838,7 +1845,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..a712c9f8699b 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -21,13 +21,6 @@ /********************************** send *************************************/ -struct smc_cdc_tx_pend { - struct smc_connection *conn; /* socket connection */ - union smc_host_cursor cursor; /* tx sndbuf cursor sent */ - union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ - u16 ctrl_seq; /* conn. tx sequence # */ -}; - /* handler for send/transmission completion of a CDC msg */ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, struct smc_link *link, @@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend) { struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int rc; rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, + wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); if (!conn->alert_token_local) /* abnormal termination */ @@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed; struct smc_link *link; int rc; @@ -107,10 +103,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, &conn->local_tx_ctrl, conn); + smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); + smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); return rc; } @@ -121,11 +117,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend); if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index b5bfe38c7f9b..271e2524dc8f 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, #endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and + * difference cannot exceed size + */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) @@ -185,6 +187,28 @@ static inline int smc_curs_comp(unsigned int size, return smc_curs_diff(size, old, new); } +/* calculate cursor difference between old and new, where old <= new and + * difference may exceed size + */ +static inline int smc_curs_diff_large(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap < new->wrap) + return min_t(int, + (size - old->count) + new->count + + (new->wrap - old->wrap - 1) * size, + size); + + if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ + return min_t(int, + (size - old->count) + new->count + + (new->wrap + 0xffff - old->wrap) * size, + size); + + return max_t(int, 0, (new->count - old->count)); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, struct smc_connection *conn) @@ -270,10 +294,16 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, smcr_cdc_msg_to_host(local, peer, conn); } -struct smc_cdc_tx_pend; +struct smc_cdc_tx_pend { + struct smc_connection *conn; /* socket connection */ + union smc_host_cursor cursor; /* tx sndbuf cursor sent */ + union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ + u16 ctrl_seq; /* conn. tx sequence # */ +}; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..e39cadda1bf5 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work) switch (sk->sk_state) { case SMC_INIT: - if (atomic_read(&conn->bytes_to_rcv) || - (rxflags->peer_done_writing && - !smc_cdc_rxed_any_close(conn))) { - sk->sk_state = SMC_APPCLOSEWAIT1; - } else { - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - } + sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..aa1c551cee81 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -128,6 +128,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -300,13 +302,13 @@ static void smc_buf_unuse(struct smc_connection *conn, conn->sndbuf_desc->used = 0; if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { - conn->rmb_desc->used = 0; if (!lgr->is_smcd) { /* unregister rmb with peer */ smc_llc_do_delete_rkey( &lgr->lnk[SMC_SINGLE_LINK], conn->rmb_desc); } + conn->rmb_desc->used = 0; } else { /* buf registration failed, reuse not possible */ write_lock_bh(&lgr->rmbs_lock); @@ -628,6 +630,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index b00287989a3d..8806d2afa6ed 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -52,6 +52,24 @@ enum smc_wr_reg_state { FAILED /* ib_wr_reg_mr response: failure */ }; +struct smc_rdma_sge { /* sges for RDMA writes */ + struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; +}; + +#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per + * message send + */ + +struct smc_rdma_sges { /* sges per message send */ + struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; +}; + +struct smc_rdma_wr { /* work requests per message + * send + */ + struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; +}; + struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ @@ -64,6 +82,8 @@ struct smc_link { struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ + struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ + struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..76487a16934e 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -289,8 +289,8 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { @@ -298,7 +298,7 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) case IB_EVENT_GID_CHANGE: case IB_EVENT_PORT_ERR: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; + port_idx = ibevent->element.qp->port - 1; set_bit(port_idx, &smcibdev->port_event_mask); schedule_work(&smcibdev->port_event_work); break; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a6d3623d06f4..4fd60c522802 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link, { int rc; - rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend); + rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL, + pend); if (rc < 0) return rc; BUILD_BUG_ON_MSG( diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..f93f3580c100 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -165,12 +165,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } @@ -267,27 +266,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, - int num_sges, struct ib_sge sges[]) + int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; - struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; - memset(&rdma_wr, 0, sizeof(rdma_wr)); link = &lgr->lnk[SMC_SINGLE_LINK]; - rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link); - rdma_wr.wr.sg_list = sges; - rdma_wr.wr.num_sge = num_sges; - rdma_wr.wr.opcode = IB_WR_RDMA_WRITE; - rdma_wr.remote_addr = + rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); + rdma_wr->wr.num_sge = num_sges; + rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; - rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); + rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; + rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); @@ -314,24 +309,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, - size_t dst_off, size_t dst_len) + size_t dst_off, size_t dst_len, + struct smc_rdma_wr *wr_rdma_buf) { dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int src_len_sum = src_len, dst_len_sum = dst_len; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { + struct ib_sge *sge = + wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list; + num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + sge[srcchunk].addr = dma_addr + src_off; + sge[srcchunk].length = src_len; num_sges++; src_off += src_len; @@ -344,7 +340,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + rc = smc_tx_rdma_write(conn, dst_off, num_sges, + &wr_rdma_buf->wr_tx_rdma[dstchunk]); if (rc) return rc; if (dst_len_sum == len) @@ -403,7 +400,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ -static int smc_tx_rdma_writes(struct smc_connection *conn) +static int smc_tx_rdma_writes(struct smc_connection *conn, + struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; @@ -464,7 +462,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, - dst_off, dst_len); + dst_off, dst_len, wr_rdma_buf); if (rc) return rc; @@ -485,31 +483,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; + struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], (struct smc_wr_tx_pend_priv *)pend); @@ -536,7 +533,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); @@ -598,7 +595,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - - smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + smc_curs_diff_large(conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..253aa75dc2b6 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) * @link: Pointer to smc_link used to later send the message. * @handler: Send completion handler function pointer. * @wr_buf: Out value returns pointer to message buffer. + * @wr_rdma_buf: Out value returns pointer to rdma work request. * @wr_pend_priv: Out value returns pointer serving as handler context. * * Return: 0 on success, or -errno on error. @@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_wr_tx_pend_priv **wr_pend_priv) { struct smc_wr_tx_pend *wr_pend; @@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, wr_ib = &link->wr_tx_ibs[idx]; wr_ib->wr_id = wr_id; *wr_buf = &link->wr_tx_bufs[idx]; + if (wr_rdma_buf) + *wr_rdma_buf = &link->wr_tx_rdmas[idx]; *wr_pend_priv = &wr_pend->priv; return 0; } @@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; } @@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; lnk->wr_tx_ibs[i].next = NULL; lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i]; lnk->wr_tx_ibs[i].num_sge = 1; lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } for (i = 0; i < lnk->wr_rx_cnt; i++) { lnk->wr_rx_sges[i].addr = @@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_tx_mask = NULL; kfree(lnk->wr_tx_sges); lnk->wr_tx_sges = NULL; + kfree(lnk->wr_tx_rdma_sges); + lnk->wr_tx_rdma_sges = NULL; kfree(lnk->wr_rx_sges); lnk->wr_rx_sges = NULL; + kfree(lnk->wr_tx_rdmas); + lnk->wr_tx_rdmas = NULL; kfree(lnk->wr_rx_ibs); lnk->wr_rx_ibs = NULL; kfree(lnk->wr_tx_ibs); @@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; + link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdmas[0]), + GFP_KERNEL); + if (!link->wr_tx_rdmas) + goto no_mem_wr_rx_ibs; + link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdma_sges[0]), + GFP_KERNEL); + if (!link->wr_tx_rdma_sges) + goto no_mem_wr_tx_rdmas; link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) - goto no_mem_wr_rx_ibs; + goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, sizeof(link->wr_rx_sges[0]), GFP_KERNEL); @@ -579,6 +611,10 @@ no_mem_wr_rx_sges: kfree(link->wr_rx_sges); no_mem_wr_tx_sges: kfree(link->wr_tx_sges); +no_mem_wr_tx_rdma_sges: + kfree(link->wr_tx_rdma_sges); +no_mem_wr_tx_rdmas: + kfree(link->wr_tx_rdmas); no_mem_wr_rx_ibs: kfree(link->wr_rx_ibs); no_mem_wr_tx_ibs: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 1d85bb14fd6f..09bf32fd3959 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev); int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); diff --git a/net/socket.c b/net/socket.c index e89884e2197b..d80d87a395ea 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,8 +941,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +967,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1070,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2780,8 +2778,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2797,8 +2794,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -2994,6 +2990,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCGIFNAME: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3109,8 +3153,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3210,21 +3253,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSARP: - case SIOCGARP: - case SIOCDARP: - case SIOCATMARK: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return compat_ifreq_ioctl(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 1ff9768f5456..f3023bbc0b7f 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -41,6 +41,9 @@ static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), +#ifdef CONFIG_DEBUG_CREDENTIALS + .magic = CRED_MAGIC, +#endif }; /* diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index dc86713b32b6..1531b0219344 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1549,8 +1549,10 @@ gss_marshal(struct rpc_task *task, __be32 *p) cred_len = p++; spin_lock(&ctx->gc_seq_lock); - req->rq_seqno = ctx->gc_seq++; + req->rq_seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ; spin_unlock(&ctx->gc_seq_lock); + if (req->rq_seqno == MAXSEQ) + goto out_expired; *p++ = htonl((u32) RPC_GSS_VERSION); *p++ = htonl((u32) ctx->gc_proc); @@ -1572,14 +1574,18 @@ gss_marshal(struct rpc_task *task, __be32 *p) mic.data = (u8 *)(p + 1); maj_stat = gss_get_mic(ctx->gc_gss_ctx, &verf_buf, &mic); if (maj_stat == GSS_S_CONTEXT_EXPIRED) { - clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); + goto out_expired; } else if (maj_stat != 0) { - printk("gss_marshal: gss_get_mic FAILED (%d)\n", maj_stat); + pr_warn("gss_marshal: gss_get_mic FAILED (%d)\n", maj_stat); + task->tk_status = -EIO; goto out_put_ctx; } p = xdr_encode_opaque(p, NULL, mic.len); gss_put_ctx(ctx); return p; +out_expired: + clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); + task->tk_status = -EKEYEXPIRED; out_put_ctx: gss_put_ctx(ctx); return NULL; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 71d9599b5816..d7ec6132c046 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1739,14 +1739,10 @@ rpc_xdr_encode(struct rpc_task *task) xdr_buf_init(&req->rq_rcv_buf, req->rq_rbuffer, req->rq_rcvsize); - req->rq_bytes_sent = 0; p = rpc_encode_header(task); - if (p == NULL) { - printk(KERN_INFO "RPC: couldn't encode RPC header, exit EIO\n"); - rpc_exit(task, -EIO); + if (p == NULL) return; - } encode = task->tk_msg.rpc_proc->p_encode; if (encode == NULL) @@ -1771,10 +1767,17 @@ call_encode(struct rpc_task *task) /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ - if (task->tk_status == -EAGAIN || task->tk_status == -ENOMEM) + switch (task->tk_status) { + case -EAGAIN: + case -ENOMEM: rpc_delay(task, HZ >> 4); - else + break; + case -EKEYEXPIRED: + task->tk_action = call_refresh; + break; + default: rpc_exit(task, task->tk_status); + } return; } @@ -2336,7 +2339,8 @@ rpc_encode_header(struct rpc_task *task) *p++ = htonl(clnt->cl_vers); /* program version */ *p++ = htonl(task->tk_msg.rpc_proc->p_proc); /* procedure */ p = rpcauth_marshcred(task, p); - req->rq_slen = xdr_adjust_iovec(&req->rq_svec[0], p); + if (p) + req->rq_slen = xdr_adjust_iovec(&req->rq_svec[0], p); return p; } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 73547d17d3c6..f1ec2110efeb 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1151,6 +1151,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task) struct rpc_xprt *xprt = req->rq_xprt; if (xprt_request_need_enqueue_transmit(task, req)) { + req->rq_bytes_sent = 0; spin_lock(&xprt->queue_lock); /* * Requests that carry congestion control credits are added @@ -1177,7 +1178,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task) INIT_LIST_HEAD(&req->rq_xmit2); goto out; } - } else { + } else if (!req->rq_seqno) { list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) { if (pos->rq_task->tk_owner != task->tk_owner) continue; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index cf51b8f9b15f..1f200119268c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 924c17d46903..57f86c63a463 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ - newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE; - if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) { - pr_err("svcrdma: too few Send SGEs available (%d needed)\n", - newxprt->sc_max_send_sges); - goto errout; - } + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 7749a2bf6887..4994e75945b8 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -845,17 +845,13 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt) for (i = 0; i <= buf->rb_sc_last; i++) { sc = rpcrdma_sendctx_create(&r_xprt->rx_ia); if (!sc) - goto out_destroy; + return -ENOMEM; sc->sc_xprt = r_xprt; buf->rb_sc_ctxs[i] = sc; } return 0; - -out_destroy: - rpcrdma_sendctxs_destroy(buf); - return -ENOMEM; } /* The sendctx queue is not guaranteed to have a size that is a @@ -1113,8 +1109,10 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) WQ_MEM_RECLAIM | WQ_HIGHPRI, 0, r_xprt->rx_xprt.address_strings[RPC_DISPLAY_ADDR]); - if (!buf->rb_completion_wq) + if (!buf->rb_completion_wq) { + rc = -ENOMEM; goto out; + } return 0; out: diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 13559e6a460b..7754aa3e434f 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -48,6 +48,7 @@ #include <net/udp.h> #include <net/tcp.h> #include <linux/bvec.h> +#include <linux/highmem.h> #include <linux/uio.h> #include <trace/events/sunrpc.h> @@ -376,6 +377,26 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags, return sock_recvmsg(sock, msg, flags); } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +static void +xs_flush_bvec(const struct bio_vec *bvec, size_t count, size_t seek) +{ + struct bvec_iter bi = { + .bi_size = count, + }; + struct bio_vec bv; + + bvec_iter_advance(bvec, &bi, seek & PAGE_MASK); + for_each_bvec(bv, bvec, bi, bi) + flush_dcache_page(bv.bv_page); +} +#else +static inline void +xs_flush_bvec(const struct bio_vec *bvec, size_t count, size_t seek) +{ +} +#endif + static ssize_t xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, struct xdr_buf *buf, size_t count, size_t seek, size_t *read) @@ -409,6 +430,7 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, seek + buf->page_base); if (ret <= 0) goto sock_err; + xs_flush_bvec(buf->bvec, ret, seek + buf->page_base); offset += ret - buf->page_base; if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC)) goto out; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 40f5cae623a7..4ad3586da8f0 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -87,6 +87,11 @@ static int tipc_skb_tailroom(struct sk_buff *skb) return limit; } +static inline int TLV_GET_DATA_LEN(struct tlv_desc *tlv) +{ + return TLV_GET_LEN(tlv) - TLV_SPACE(0); +} + static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) { struct tlv_desc *tlv = (struct tlv_desc *)skb_tail_pointer(skb); @@ -166,6 +171,11 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } +static inline bool string_is_valid(char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -379,6 +389,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, struct nlattr *prop; struct nlattr *bearer; struct tipc_bearer_config *b; + int len; b = (struct tipc_bearer_config *)TLV_DATA(msg->req); @@ -386,6 +397,10 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + if (!string_is_valid(b->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) return -EMSGSIZE; @@ -411,6 +426,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *bearer; + int len; name = (char *)TLV_DATA(msg->req); @@ -418,6 +434,10 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) return -EMSGSIZE; @@ -478,6 +498,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, struct nlattr *prop[TIPC_NLA_PROP_MAX + 1]; struct nlattr *stats[TIPC_NLA_STATS_MAX + 1]; int err; + int len; if (!attrs[TIPC_NLA_LINK]) return -EINVAL; @@ -504,6 +525,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return err; name = (char *)TLV_DATA(msg->req); + + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) return 0; @@ -644,6 +670,7 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *media; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -651,6 +678,10 @@ static int tipc_nl_compat_media_set(struct sk_buff *skb, if (!media) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_MEDIA_NAME, lc->name)) return -EMSGSIZE; @@ -671,6 +702,7 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, struct nlattr *prop; struct nlattr *bearer; struct tipc_link_config *lc; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); @@ -678,6 +710,10 @@ static int tipc_nl_compat_bearer_set(struct sk_buff *skb, if (!bearer) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_MEDIA_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, lc->name)) return -EMSGSIZE; @@ -726,9 +762,14 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, struct tipc_link_config *lc; struct tipc_bearer *bearer; struct tipc_media *media; + int len; lc = (struct tipc_link_config *)TLV_DATA(msg->req); + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(lc->name, len)) + return -EINVAL; + media = tipc_media_find(lc->name); if (media) { cmd->doit = &__tipc_nl_media_set; @@ -750,6 +791,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, { char *name; struct nlattr *link; + int len; name = (char *)TLV_DATA(msg->req); @@ -757,6 +799,10 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (!link) return -EMSGSIZE; + len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + if (!string_is_valid(name, len)) + return -EINVAL; + if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) return -EMSGSIZE; @@ -778,6 +824,8 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); + if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + return -EINVAL; depth = ntohl(ntq->depth); @@ -904,8 +952,10 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock) hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_PUBL_GET); - if (!hdr) + if (!hdr) { + kfree_skb(args); return -EMSGSIZE; + } nest = nla_nest_start(args, TIPC_NLA_SOCK); if (!nest) { @@ -1206,7 +1256,7 @@ static int tipc_nl_compat_recv(struct sk_buff *skb, struct genl_info *info) } len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN); - if (len && !TLV_OK(msg.req, len)) { + if (!len || !TLV_OK(msg.req, len)) { msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED); err = -EOPNOTSUPP; goto send; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index efb16f69bd2c..a457c0fbbef1 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -398,7 +398,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; - if (ret > 0) { + if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 11cdc8f7db63..bf5b54b513bc 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -439,6 +439,8 @@ static int tls_do_encryption(struct sock *sk, struct scatterlist *sge = sk_msg_elem(msg_en, start); int rc; + memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data)); + sge->offset += tls_ctx->tx.prepend_size; sge->length -= tls_ctx->tx.prepend_size; @@ -448,7 +450,7 @@ static int tls_do_encryption(struct sock *sk, aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); aead_request_set_crypt(aead_req, rec->sg_aead_in, rec->sg_aead_out, - data_len, tls_ctx->tx.iv); + data_len, rec->iv_data); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_encrypt_done, sk); @@ -1792,7 +1794,9 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + release_sock(sk); cancel_delayed_work_sync(&ctx->tx_work.work); + lock_sock(sk); /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..15eb5d3d4750 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); @@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.h b/net/wireless/core.h index c5d6f3418601..f6b40563dc63 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5e49492d5911..74150ad95823 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -555,7 +555,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { }, [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = - NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX, + NLA_POLICY_NESTED(NL80211_PMSR_ATTR_MAX, nl80211_pmsr_attr_policy), }; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index ecfb1a06dbb2..dd58b9909ac9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1024,8 +1024,13 @@ static void regdb_fw_cb(const struct firmware *fw, void *context) } rtnl_lock(); - if (WARN_ON(regdb && !IS_ERR(regdb))) { - /* just restore and free new db */ + if (regdb && !IS_ERR(regdb)) { + /* negative case - a bug + * positive case - can happen due to race in case of multiple cb's in + * queue, due to usage of asynchronous callback + * + * Either case, just restore and free new db. + */ } else if (set_error) { regdb = ERR_PTR(set_error); } else if (fw) { @@ -1255,7 +1260,7 @@ static bool is_valid_rd(const struct ieee80211_regdomain *rd) * definitions (the "2.4 GHz band", the "5 GHz band" and the "60GHz band"), * however it is safe for now to assume that a frequency rule should not be * part of a frequency's band if the start freq or end freq are off by more - * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 10 GHz for the + * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 20 GHz for the * 60 GHz band. * This resolution can be lowered and should be considered as we add * regulatory rule support for other "bands". @@ -1270,7 +1275,7 @@ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, * with the Channel starting frequency above 45 GHz. */ u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ? - 10 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; + 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; if (abs(freq_khz - freq_range->start_freq_khz) <= limit) return true; if (abs(freq_khz - freq_range->end_freq_khz) <= limit) diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f741d8376a46..7d34cb884840 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index a264cf2accd0..d4de871e7d4d 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -41,13 +41,20 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) * not know if the device has more tx queues than rx, or the opposite. * This might also change during run time. */ -static void xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, - u16 queue_id) +static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, + u16 queue_id) { + if (queue_id >= max_t(unsigned int, + dev->real_num_rx_queues, + dev->real_num_tx_queues)) + return -EINVAL; + if (queue_id < dev->real_num_rx_queues) dev->_rx[queue_id].umem = umem; if (queue_id < dev->real_num_tx_queues) dev->_tx[queue_id].umem = umem; + + return 0; } struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, @@ -88,7 +95,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, goto out_rtnl_unlock; } - xdp_reg_umem_at_qid(dev, umem, queue_id); + err = xdp_reg_umem_at_qid(dev, umem, queue_id); + if (err) + goto out_rtnl_unlock; + umem->dev = dev; umem->queue_id = queue_id; if (force_copy) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 934492bad8e0..ba0a4048c846 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -680,16 +680,6 @@ static void xfrm_hash_resize(struct work_struct *work) mutex_unlock(&hash_resize_mutex); } -static void xfrm_hash_reset_inexact_table(struct net *net) -{ - struct xfrm_pol_inexact_bin *b; - - lockdep_assert_held(&net->xfrm.xfrm_policy_lock); - - list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins) - INIT_HLIST_HEAD(&b->hhead); -} - /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be sucessful * (provided xfrm_policy_lock is held throughout). @@ -833,13 +823,13 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, u16 family) { unsigned int matched_s, matched_d; - struct hlist_node *newpos = NULL; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (!policy->bydst_reinsert) @@ -849,16 +839,19 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { - if (policy->priority >= p->priority) + if (policy->priority > p->priority) + newpos = &p->bydst; + else if (policy->priority == p->priority && + policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos) - hlist_add_behind(&policy->bydst, newpos); + hlist_add_behind_rcu(&policy->bydst, newpos); else - hlist_add_head(&policy->bydst, &n->hhead); + hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least @@ -893,12 +886,13 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, struct rb_root *new, u16 family) { - struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; + struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); - +restart: + parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; @@ -918,12 +912,11 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, } else { struct xfrm_policy *tmp; - hlist_for_each_entry(tmp, &node->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&node->hhead); xfrm_policy_inexact_list_reinsert(net, node, family); if (node->prefixlen == n->prefixlen) { @@ -935,8 +928,7 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, kfree_rcu(n, rcu); n = node; n->prefixlen = prefixlen; - *p = new->rb_node; - parent = NULL; + goto restart; } } @@ -965,12 +957,11 @@ static void xfrm_policy_inexact_node_merge(struct net *net, family); } - hlist_for_each_entry(tmp, &v->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&n->hhead); xfrm_policy_inexact_list_reinsert(net, n, family); } @@ -1235,6 +1226,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); + write_seqcount_begin(&xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1278,10 +1270,14 @@ static void xfrm_hash_rebuild(struct work_struct *work) } /* reset the bydst and inexact table in all directions */ - xfrm_hash_reset_inexact_table(net); - for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { - INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); + struct hlist_node *n; + + hlist_for_each_entry_safe(policy, n, + &net->xfrm.policy_inexact[dir], + bydst_inexact_list) + hlist_del_init(&policy->bydst_inexact_list); + hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; for (i = hmask; i >= 0; i--) @@ -1313,6 +1309,9 @@ static void xfrm_hash_rebuild(struct work_struct *work) newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); + + hlist_del_rcu(&policy->bydst); + if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); @@ -1334,6 +1333,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); + write_seqcount_end(&xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2600,7 +2600,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { - __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + __u32 mark = 0; + + if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) + mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 277c1c46fe94..c6d26afcf89d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1488,10 +1488,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; - if ((ut[i].mode == XFRM_MODE_TRANSPORT) && - (ut[i].family != prev_family)) - return -EINVAL; - + switch (ut[i].mode) { + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + break; + default: + if (ut[i].family != prev_family) + return -EINVAL; + break; + } if (ut[i].mode >= XFRM_MODE_MAX) return -EINVAL; |