diff options
Diffstat (limited to 'net')
197 files changed, 3250 insertions, 2029 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index e40aa3e3641c..422f726346ea 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -131,7 +131,8 @@ int vlan_check_real_dev(struct net_device *real_dev, { const char *name = real_dev->name; - if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { + if (real_dev->features & NETIF_F_VLAN_CHALLENGED || + real_dev->type != ARPHRD_ETHER) { pr_info("VLANs not supported on %s\n", name); NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device"); return -EOPNOTSUPP; @@ -357,6 +358,35 @@ static int __vlan_device_event(struct net_device *dev, unsigned long event) return err; } +static void vlan_vid0_add(struct net_device *dev) +{ + struct vlan_info *vlan_info; + int err; + + if (!(dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + return; + + pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); + + err = vlan_vid_add(dev, htons(ETH_P_8021Q), 0); + if (err) + return; + + vlan_info = rtnl_dereference(dev->vlan_info); + vlan_info->auto_vid0 = true; +} + +static void vlan_vid0_del(struct net_device *dev) +{ + struct vlan_info *vlan_info = rtnl_dereference(dev->vlan_info); + + if (!vlan_info || !vlan_info->auto_vid0) + return; + + vlan_info->auto_vid0 = false; + vlan_vid_del(dev, htons(ETH_P_8021Q), 0); +} + static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -378,15 +408,10 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, return notifier_from_errno(err); } - if ((event == NETDEV_UP) && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { - pr_info("adding VLAN 0 to HW filter on device %s\n", - dev->name); - vlan_vid_add(dev, htons(ETH_P_8021Q), 0); - } - if (event == NETDEV_DOWN && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) - vlan_vid_del(dev, htons(ETH_P_8021Q), 0); + if (event == NETDEV_UP) + vlan_vid0_add(dev); + else if (event == NETDEV_DOWN) + vlan_vid0_del(dev); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5eaf38875554..c7ffe591d593 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -33,6 +33,7 @@ struct vlan_info { struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; + bool auto_vid0; struct rcu_head rcu; }; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index d3e511e1eba8..c08228d48834 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -272,17 +272,6 @@ static int vlan_dev_open(struct net_device *dev) goto out; } - if (dev->flags & IFF_ALLMULTI) { - err = dev_set_allmulti(real_dev, 1); - if (err < 0) - goto del_unicast; - } - if (dev->flags & IFF_PROMISC) { - err = dev_set_promiscuity(real_dev, 1); - if (err < 0) - goto clear_allmulti; - } - ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr); if (vlan->flags & VLAN_FLAG_GVRP) @@ -296,12 +285,6 @@ static int vlan_dev_open(struct net_device *dev) netif_carrier_on(dev); return 0; -clear_allmulti: - if (dev->flags & IFF_ALLMULTI) - dev_set_allmulti(real_dev, -1); -del_unicast: - if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) - dev_uc_del(real_dev, dev->dev_addr); out: netif_carrier_off(dev); return err; @@ -314,10 +297,6 @@ static int vlan_dev_stop(struct net_device *dev) dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); - if (dev->flags & IFF_ALLMULTI) - dev_set_allmulti(real_dev, -1); - if (dev->flags & IFF_PROMISC) - dev_set_promiscuity(real_dev, -1); if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr)) dev_uc_del(real_dev, dev->dev_addr); @@ -474,12 +453,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - if (dev->flags & IFF_UP) { - if (change & IFF_ALLMULTI) - dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); - } + if (change & IFF_ALLMULTI) + dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); } static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) diff --git a/net/9p/client.c b/net/9p/client.c index e876d6fea2fc..e89a91802e03 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1545,7 +1545,8 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, struct p9_client *clnt = fid->clnt; struct p9_req_t *req; int count = iov_iter_count(to); - int rsize, received, non_zc = 0; + u32 rsize, received; + bool non_zc = false; char *dataptr; *err = 0; @@ -1568,7 +1569,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, 0, 11, "dqd", fid->fid, offset, rsize); } else { - non_zc = 1; + non_zc = true; req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, rsize); } @@ -1589,11 +1590,11 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, return 0; } if (rsize < received) { - pr_err("bogus RREAD count (%d > %d)\n", received, rsize); + pr_err("bogus RREAD count (%u > %u)\n", received, rsize); received = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); + p9_debug(P9_DEBUG_9P, "<<< RREAD count %u\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); @@ -1620,9 +1621,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) *err = 0; while (iov_iter_count(from)) { - int count = iov_iter_count(from); - int rsize = fid->iounit; - int written; + size_t count = iov_iter_count(from); + u32 rsize = fid->iounit; + u32 written; if (!rsize || rsize > clnt->msize - P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; @@ -1630,7 +1631,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) if (count < rsize) rsize = count; - p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", + p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %u (/%zu)\n", fid->fid, offset, rsize, count); /* Don't bother zerocopy for small IO (< 1024) */ @@ -1656,11 +1657,11 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) break; } if (rsize < written) { - pr_err("bogus RWRITE count (%d > %d)\n", written, rsize); + pr_err("bogus RWRITE count (%u > %u)\n", written, rsize); written = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); + p9_debug(P9_DEBUG_9P, "<<< RWRITE count %u\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); @@ -2056,7 +2057,8 @@ EXPORT_SYMBOL_GPL(p9_client_xattrcreate); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) { - int err, rsize, non_zc = 0; + int err, non_zc = 0; + u32 rsize; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; @@ -2065,7 +2067,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) iov_iter_kvec(&to, ITER_DEST, &kv, 1, count); - p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", + p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %u\n", fid->fid, offset, count); err = 0; @@ -2101,11 +2103,11 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) goto free_and_error; } if (rsize < count) { - pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); + pr_err("bogus RREADDIR count (%u > %u)\n", count, rsize); count = rsize; } - p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); + p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %u\n", count); if (non_zc) memmove(data, dataptr, count); diff --git a/net/Makefile b/net/Makefile index 0914bea9c335..103cd8d61f68 100644 --- a/net/Makefile +++ b/net/Makefile @@ -17,7 +17,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_INET) += ipv4/ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ -obj-$(CONFIG_UNIX_SCM) += unix/ +obj-$(CONFIG_UNIX) += unix/ obj-y += ipv6/ obj-$(CONFIG_BPFILTER) += bpfilter/ obj-$(CONFIG_PACKET) += packet/ diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index c7236daa2415..0d7c14a49668 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -35,6 +35,7 @@ #include <linux/seq_file.h> #include <linux/export.h> #include <linux/etherdevice.h> +#include <linux/refcount.h> int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME; int sysctl_aarp_tick_time = AARP_TICK_TIME; @@ -44,6 +45,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; /* Lists of aarp entries */ /** * struct aarp_entry - AARP entry + * @refcnt: Reference count * @last_sent: Last time we xmitted the aarp request * @packet_queue: Queue of frames wait for resolution * @status: Used for proxy AARP @@ -55,6 +57,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; * @next: Next entry in chain */ struct aarp_entry { + refcount_t refcnt; /* These first two are only used for unresolved entries */ unsigned long last_sent; struct sk_buff_head packet_queue; @@ -79,6 +82,17 @@ static DEFINE_RWLOCK(aarp_lock); /* Used to walk the list and purge/kick entries. */ static struct timer_list aarp_timer; +static inline void aarp_entry_get(struct aarp_entry *a) +{ + refcount_inc(&a->refcnt); +} + +static inline void aarp_entry_put(struct aarp_entry *a) +{ + if (refcount_dec_and_test(&a->refcnt)) + kfree(a); +} + /* * Delete an aarp queue * @@ -87,7 +101,7 @@ static struct timer_list aarp_timer; static void __aarp_expire(struct aarp_entry *a) { skb_queue_purge(&a->packet_queue); - kfree(a); + aarp_entry_put(a); } /* @@ -380,9 +394,11 @@ static void aarp_purge(void) static struct aarp_entry *aarp_alloc(void) { struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC); + if (!a) + return NULL; - if (a) - skb_queue_head_init(&a->packet_queue); + refcount_set(&a->refcnt, 1); + skb_queue_head_init(&a->packet_queue); return a; } @@ -508,6 +524,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) entry->dev = atif->dev; write_lock_bh(&aarp_lock); + aarp_entry_get(entry); hash = sa->s_node % (AARP_HASH_SIZE - 1); entry->next = proxies[hash]; @@ -533,6 +550,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) retval = 1; } + aarp_entry_put(entry); write_unlock_bh(&aarp_lock); out: return retval; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index f67f14db1633..5c9a9652449d 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -563,6 +563,7 @@ static int atrtr_create(struct rtentry *r, struct net_device *devhint) /* Fill in the routing entry */ rt->target = ta->sat_addr; + dev_put(rt->dev); /* Release old device */ dev_hold(devhint); rt->dev = devhint; rt->flags = r->rt_flags; diff --git a/net/atm/clip.c b/net/atm/clip.c index 294cb9efe3d3..53d62361ae46 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -45,7 +45,8 @@ #include <net/atmclip.h> static struct net_device *clip_devs; -static struct atm_vcc *atmarpd; +static struct atm_vcc __rcu *atmarpd; +static DEFINE_MUTEX(atmarpd_lock); static struct timer_list idle_timer; static const struct neigh_ops clip_neigh_ops; @@ -53,24 +54,35 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { struct sock *sk; struct atmarp_ctrl *ctrl; + struct atm_vcc *vcc; struct sk_buff *skb; + int err = 0; pr_debug("(%d)\n", type); - if (!atmarpd) - return -EUNATCH; + + rcu_read_lock(); + vcc = rcu_dereference(atmarpd); + if (!vcc) { + err = -EUNATCH; + goto unlock; + } skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + err = -ENOMEM; + goto unlock; + } ctrl = skb_put(skb, sizeof(struct atmarp_ctrl)); ctrl->type = type; ctrl->itf_num = itf; ctrl->ip = ip; - atm_force_charge(atmarpd, skb->truesize); + atm_force_charge(vcc, skb->truesize); - sk = sk_atm(atmarpd); + sk = sk_atm(vcc); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk); - return 0; +unlock: + rcu_read_unlock(); + return err; } static void link_vcc(struct clip_vcc *clip_vcc, struct atmarp_entry *entry) @@ -193,12 +205,6 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("\n"); - if (!clip_devs) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - return; - } - if (!skb) { pr_debug("removing VCC %p\n", clip_vcc); if (clip_vcc->entry) @@ -208,6 +214,11 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb) return; } atm_return(vcc, skb->truesize); + if (!clip_devs) { + kfree_skb(skb); + return; + } + skb->dev = clip_vcc->entry ? clip_vcc->entry->neigh->dev : clip_devs; /* clip_vcc->entry == NULL if we don't have an IP address yet */ if (!skb->dev) { @@ -418,6 +429,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout) if (!vcc->push) return -EBADFD; + if (vcc->user_back) + return -EINVAL; clip_vcc = kmalloc(sizeof(struct clip_vcc), GFP_KERNEL); if (!clip_vcc) return -ENOMEM; @@ -608,17 +621,27 @@ static void atmarpd_close(struct atm_vcc *vcc) { pr_debug("\n"); - rtnl_lock(); - atmarpd = NULL; + mutex_lock(&atmarpd_lock); + RCU_INIT_POINTER(atmarpd, NULL); + mutex_unlock(&atmarpd_lock); + + synchronize_rcu(); skb_queue_purge(&sk_atm(vcc)->sk_receive_queue); - rtnl_unlock(); pr_debug("(done)\n"); module_put(THIS_MODULE); } +static int atmarpd_send(struct atm_vcc *vcc, struct sk_buff *skb) +{ + atm_return_tx(vcc, skb); + dev_kfree_skb_any(skb); + return 0; +} + static const struct atmdev_ops atmarpd_dev_ops = { - .close = atmarpd_close + .close = atmarpd_close, + .send = atmarpd_send }; @@ -632,15 +655,18 @@ static struct atm_dev atmarpd_dev = { static int atm_init_atmarp(struct atm_vcc *vcc) { - rtnl_lock(); + if (vcc->push == clip_push) + return -EINVAL; + + mutex_lock(&atmarpd_lock); if (atmarpd) { - rtnl_unlock(); + mutex_unlock(&atmarpd_lock); return -EADDRINUSE; } mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - atmarpd = vcc; + rcu_assign_pointer(atmarpd, vcc); set_bit(ATM_VF_META, &vcc->flags); set_bit(ATM_VF_READY, &vcc->flags); /* allow replies and avoid getting closed if signaling dies */ @@ -649,13 +675,14 @@ static int atm_init_atmarp(struct atm_vcc *vcc) vcc->push = NULL; vcc->pop = NULL; /* crash */ vcc->push_oam = NULL; /* crash */ - rtnl_unlock(); + mutex_unlock(&atmarpd_lock); return 0; } static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct atm_vcc *vcc = ATM_SD(sock); + struct sock *sk = sock->sk; int err = 0; switch (cmd) { @@ -676,14 +703,18 @@ static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) err = clip_create(arg); break; case ATMARPD_CTRL: + lock_sock(sk); err = atm_init_atmarp(vcc); if (!err) { sock->state = SS_CONNECTED; __module_get(THIS_MODULE); } + release_sock(sk); break; case ATMARP_MKIP: + lock_sock(sk); err = clip_mkip(vcc, arg); + release_sock(sk); break; case ATMARP_SETENTRY: err = clip_setentry(vcc, (__force __be32)arg); diff --git a/net/atm/common.c b/net/atm/common.c index f7019df41c3e..9cc82acbc735 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -635,6 +635,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size) skb->dev = NULL; /* for paths shared with net_device interfaces */ if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) { + atm_return_tx(vcc, skb); kfree_skb(skb); error = -EFAULT; goto out; diff --git a/net/atm/lec.c b/net/atm/lec.c index 6257bf12e5a0..b7fa48a9b720 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -124,6 +124,7 @@ static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; /* Device structures */ static struct net_device *dev_lec[MAX_LEC_ITF]; +static DEFINE_MUTEX(lec_mutex); #if IS_ENABLED(CONFIG_BRIDGE) static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev) @@ -181,6 +182,7 @@ static void lec_send(struct atm_vcc *vcc, struct sk_buff *skb) { struct net_device *dev = skb->dev; + unsigned int len = skb->len; ATM_SKB(skb)->vcc = vcc; atm_account_tx(vcc, skb); @@ -191,7 +193,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb) } dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += len; } static void lec_tx_timeout(struct net_device *dev, unsigned int txqueue) @@ -684,6 +686,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) int bytes_left; struct atmlec_ioc ioc_data; + lockdep_assert_held(&lec_mutex); /* Lecd must be up in this case */ bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); if (bytes_left != 0) @@ -709,6 +712,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) static int lec_mcast_attach(struct atm_vcc *vcc, int arg) { + lockdep_assert_held(&lec_mutex); if (arg < 0 || arg >= MAX_LEC_ITF) return -EINVAL; arg = array_index_nospec(arg, MAX_LEC_ITF); @@ -724,6 +728,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) int i; struct lec_priv *priv; + lockdep_assert_held(&lec_mutex); if (arg < 0) arg = 0; if (arg >= MAX_LEC_ITF) @@ -741,6 +746,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg) snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i); if (register_netdev(dev_lec[i])) { free_netdev(dev_lec[i]); + dev_lec[i] = NULL; return -EINVAL; } @@ -903,7 +909,6 @@ static void *lec_itf_walk(struct lec_state *state, loff_t *l) v = (dev && netdev_priv(dev)) ? lec_priv_walk(state, l, netdev_priv(dev)) : NULL; if (!v && dev) { - dev_put(dev); /* Partial state reset for the next time we get called */ dev = NULL; } @@ -927,6 +932,7 @@ static void *lec_seq_start(struct seq_file *seq, loff_t *pos) { struct lec_state *state = seq->private; + mutex_lock(&lec_mutex); state->itf = 0; state->dev = NULL; state->locked = NULL; @@ -944,8 +950,9 @@ static void lec_seq_stop(struct seq_file *seq, void *v) if (state->dev) { spin_unlock_irqrestore(&state->locked->lec_arp_lock, state->flags); - dev_put(state->dev); + state->dev = NULL; } + mutex_unlock(&lec_mutex); } static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -1002,6 +1009,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return -ENOIOCTLCMD; } + mutex_lock(&lec_mutex); switch (cmd) { case ATMLEC_CTRL: err = lecd_attach(vcc, (int)arg); @@ -1016,6 +1024,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } + mutex_unlock(&lec_mutex); return err; } diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 033871e718a3..583c27131b7d 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1314,6 +1314,8 @@ static void MPOA_cache_impos_rcvd(struct k_message *msg, holding_time = msg->content.eg_info.holding_time; dprintk("(%s) entry = %p, holding_time = %u\n", mpc->dev->name, entry, holding_time); + if (entry == NULL && !holding_time) + return; if (entry == NULL && holding_time) { entry = mpc->eg_ops->add_entry(msg, mpc); mpc->eg_ops->put(entry); diff --git a/net/atm/raw.c b/net/atm/raw.c index 2b5f78a7ec3e..1e6511ec842c 100644 --- a/net/atm/raw.c +++ b/net/atm/raw.c @@ -36,7 +36,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb) pr_debug("(%d) %d -= %d\n", vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize); - WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc)); + atm_return_tx(vcc, skb); dev_kfree_skb_any(skb); sk->sk_write_space(sk); } diff --git a/net/atm/resources.c b/net/atm/resources.c index 995d29e7fb13..b19d851e1f44 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -146,11 +146,10 @@ void atm_dev_deregister(struct atm_dev *dev) */ mutex_lock(&atm_dev_mutex); list_del(&dev->dev_list); - mutex_unlock(&atm_dev_mutex); - atm_dev_release_vccs(dev); atm_unregister_sysfs(dev); atm_proc_dev_deregister(dev); + mutex_unlock(&atm_dev_mutex); atm_dev_put(dev); } diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 7f6a7c96ac92..02e084b44053 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -325,8 +325,7 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len, /* check if there is enough space for the optional TVLV */ next_buff_pos += ntohs(ogm_packet->tvlv_len); - return (next_buff_pos <= packet_len) && - (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); + return next_buff_pos <= packet_len; } /* send a batman ogm to a given interface */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 9f4815f4c8e8..deef817b28f0 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -840,8 +840,7 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len, /* check if there is enough space for the optional TVLV */ next_buff_pos += ntohs(ogm2_packet->tvlv_len); - return (next_buff_pos <= packet_len) && - (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES); + return next_buff_pos <= packet_len; } /** diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4eb1b3ced0d2..db119071a0ea 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -825,11 +825,16 @@ static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb) { + struct sk_buff *skb; + /* Note that we must allocate using GFP_ATOMIC here as * this function is called originally from netdev hard xmit * function in atomic context. */ - return bt_skb_alloc(hdr_len + len, GFP_ATOMIC); + skb = bt_skb_alloc(hdr_len + len, GFP_ATOMIC); + if (!skb) + return ERR_PTR(-ENOMEM); + return skb; } static void chan_suspend_cb(struct l2cap_chan *chan) diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c index 1bc51e2b05a3..3e1713673ecc 100644 --- a/net/bluetooth/eir.c +++ b/net/bluetooth/eir.c @@ -366,17 +366,19 @@ u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr) void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len) { - while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, len))) { + size_t dlen; + + while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, &dlen))) { u16 value = get_unaligned_le16(eir); if (uuid == value) { if (len) - *len -= 2; + *len = dlen - 2; return &eir[2]; } - eir += *len; - eir_len -= *len; + eir += dlen; + eir_len -= dlen; } return NULL; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 496dac042b9c..a26323400bf5 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -58,6 +58,7 @@ DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); +DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); @@ -1872,10 +1873,8 @@ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) if (monitor->handle) idr_remove(&hdev->adv_monitors_idr, monitor->handle); - if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) { + if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) hdev->adv_monitors_cnt--; - mgmt_adv_monitor_removed(hdev, monitor->handle); - } kfree(monitor); } @@ -2977,7 +2976,9 @@ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - list_add_tail_rcu(&cb->list, &hci_cb_list); + mutex_lock(&hci_cb_list_lock); + list_add_tail(&cb->list, &hci_cb_list); + mutex_unlock(&hci_cb_list_lock); return 0; } @@ -2987,8 +2988,9 @@ int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - list_del_rcu(&cb->list); - synchronize_rcu(); + mutex_lock(&hci_cb_list_lock); + list_del(&cb->list); + mutex_unlock(&hci_cb_list_lock); return 0; } @@ -3398,23 +3400,18 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type) bt_dev_err(hdev, "link tx timeout"); - rcu_read_lock(); + hci_dev_lock(hdev); /* Kill stalled connections */ - list_for_each_entry_rcu(c, &h->list, list) { + list_for_each_entry(c, &h->list, list) { if (c->type == type && c->sent) { bt_dev_err(hdev, "killing stalled connection %pMR", &c->dst); - /* hci_disconnect might sleep, so, we have to release - * the RCU read lock before calling it. - */ - rcu_read_unlock(); hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM); - rcu_read_lock(); } } - rcu_read_unlock(); + hci_dev_unlock(hdev); } static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index b6fe5e15981f..866462c97dba 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2196,40 +2196,6 @@ static u8 hci_cc_set_adv_param(struct hci_dev *hdev, void *data, return rp->status; } -static u8 hci_cc_set_ext_adv_param(struct hci_dev *hdev, void *data, - struct sk_buff *skb) -{ - struct hci_rp_le_set_ext_adv_params *rp = data; - struct hci_cp_le_set_ext_adv_params *cp; - struct adv_info *adv_instance; - - bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); - - if (rp->status) - return rp->status; - - cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS); - if (!cp) - return rp->status; - - hci_dev_lock(hdev); - hdev->adv_addr_type = cp->own_addr_type; - if (!cp->handle) { - /* Store in hdev for instance 0 */ - hdev->adv_tx_power = rp->tx_power; - } else { - adv_instance = hci_find_adv_instance(hdev, cp->handle); - if (adv_instance) - adv_instance->tx_power = rp->tx_power; - } - /* Update adv data as tx power is known now */ - hci_update_adv_data(hdev, cp->handle); - - hci_dev_unlock(hdev); - - return rp->status; -} - static u8 hci_cc_read_rssi(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -3477,23 +3443,30 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, hci_update_scan(hdev); } - params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); - if (params) { - switch (params->auto_connect) { - case HCI_AUTO_CONN_LINK_LOSS: - if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) + /* Re-enable passive scanning if disconnected device is marked + * as auto-connectable. + */ + if (conn->type == LE_LINK) { + params = hci_conn_params_lookup(hdev, &conn->dst, + conn->dst_type); + if (params) { + switch (params->auto_connect) { + case HCI_AUTO_CONN_LINK_LOSS: + if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT) + break; + fallthrough; + + case HCI_AUTO_CONN_DIRECT: + case HCI_AUTO_CONN_ALWAYS: + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, + &hdev->pend_le_conns); + hci_update_passive_scan(hdev); break; - fallthrough; - case HCI_AUTO_CONN_DIRECT: - case HCI_AUTO_CONN_ALWAYS: - hci_pend_le_list_del_init(params); - hci_pend_le_list_add(params, &hdev->pend_le_conns); - hci_update_passive_scan(hdev); - break; - - default: - break; + default: + break; + } } } @@ -4165,8 +4138,6 @@ static const struct hci_cc { HCI_CC(HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS, hci_cc_le_read_num_adv_sets, sizeof(struct hci_rp_le_read_num_supported_adv_sets)), - HCI_CC(HCI_OP_LE_SET_EXT_ADV_PARAMS, hci_cc_set_ext_adv_param, - sizeof(struct hci_rp_le_set_ext_adv_params)), HCI_CC_STATUS(HCI_OP_LE_SET_EXT_ADV_ENABLE, hci_cc_le_set_ext_adv_enable), HCI_CC_STATUS(HCI_OP_LE_SET_ADV_SET_RAND_ADDR, @@ -6241,11 +6212,12 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!ext_adv && !has_pending_adv_report(hdev)) { + if (!has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index c6108e68f5a9..3f905ee4338f 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -1181,9 +1181,129 @@ static int hci_set_adv_set_random_addr_sync(struct hci_dev *hdev, u8 instance, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } +static int +hci_set_ext_adv_params_sync(struct hci_dev *hdev, struct adv_info *adv, + const struct hci_cp_le_set_ext_adv_params *cp, + struct hci_rp_le_set_ext_adv_params *rp) +{ + struct sk_buff *skb; + + skb = __hci_cmd_sync(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(*cp), + cp, HCI_CMD_TIMEOUT); + + /* If command return a status event, skb will be set to -ENODATA */ + if (skb == ERR_PTR(-ENODATA)) + return 0; + + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", + HCI_OP_LE_SET_EXT_ADV_PARAMS, PTR_ERR(skb)); + return PTR_ERR(skb); + } + + if (skb->len != sizeof(*rp)) { + bt_dev_err(hdev, "Invalid response length for 0x%4.4x: %u", + HCI_OP_LE_SET_EXT_ADV_PARAMS, skb->len); + kfree_skb(skb); + return -EIO; + } + + memcpy(rp, skb->data, sizeof(*rp)); + kfree_skb(skb); + + if (!rp->status) { + hdev->adv_addr_type = cp->own_addr_type; + if (!cp->handle) { + /* Store in hdev for instance 0 */ + hdev->adv_tx_power = rp->tx_power; + } else if (adv) { + adv->tx_power = rp->tx_power; + } + } + + return rp->status; +} + +static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + struct { + struct hci_cp_le_set_ext_adv_data cp; + u8 data[HCI_MAX_EXT_AD_LENGTH]; + } pdu; + u8 len; + struct adv_info *adv = NULL; + int err; + + memset(&pdu, 0, sizeof(pdu)); + + if (instance) { + adv = hci_find_adv_instance(hdev, instance); + if (!adv || !adv->adv_data_changed) + return 0; + } + + len = eir_create_adv_data(hdev, instance, pdu.data); + + pdu.cp.length = len; + pdu.cp.handle = instance; + pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + + err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, + sizeof(pdu.cp) + len, &pdu.cp, + HCI_CMD_TIMEOUT); + if (err) + return err; + + /* Update data if the command succeed */ + if (adv) { + adv->adv_data_changed = false; + } else { + memcpy(hdev->adv_data, pdu.data, len); + hdev->adv_data_len = len; + } + + return 0; +} + +static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + struct hci_cp_le_set_adv_data cp; + u8 len; + + memset(&cp, 0, sizeof(cp)); + + len = eir_create_adv_data(hdev, instance, cp.data); + + /* There's nothing to do if the data hasn't changed */ + if (hdev->adv_data_len == len && + memcmp(cp.data, hdev->adv_data, len) == 0) + return 0; + + memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + hdev->adv_data_len = len; + + cp.length = len; + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA, + sizeof(cp), &cp, HCI_CMD_TIMEOUT); +} + +int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance) +{ + if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) + return 0; + + if (ext_adv_capable(hdev)) + return hci_set_ext_adv_data_sync(hdev, instance); + + return hci_set_adv_data_sync(hdev, instance); +} + int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_ext_adv_params cp; + struct hci_rp_le_set_ext_adv_params rp; bool connectable; u32 flags; bdaddr_t random_addr; @@ -1204,7 +1324,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) * Command Disallowed error, so we must first disable the * instance if it is active. */ - if (adv && !adv->pending) { + if (adv) { err = hci_disable_ext_adv_instance_sync(hdev, instance); if (err) return err; @@ -1290,8 +1410,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance) cp.secondary_phy = HCI_ADV_PHY_1M; } - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); + err = hci_set_ext_adv_params_sync(hdev, adv, &cp, &rp); + if (err) + return err; + + /* Update adv data as tx power is known now */ + err = hci_set_ext_adv_data_sync(hdev, cp.handle); if (err) return err; @@ -1539,7 +1663,8 @@ static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance) static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv) { u8 bid[3]; - u8 ad[4 + 3]; + u8 ad[HCI_MAX_EXT_AD_LENGTH]; + u8 len; /* Skip if NULL adv as instance 0x00 is used for general purpose * advertising so it cannot used for the likes of Broadcast Announcement @@ -1565,8 +1690,10 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv) /* Generate Broadcast ID */ get_random_bytes(bid, sizeof(bid)); - eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid)); - hci_set_adv_instance_data(hdev, adv->instance, sizeof(ad), ad, 0, NULL); + len = eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid)); + memcpy(ad + len, adv->adv_data, adv->adv_data_len); + hci_set_adv_instance_data(hdev, adv->instance, len + adv->adv_data_len, + ad, 0, NULL); return hci_update_adv_data_sync(hdev, adv->instance); } @@ -1583,8 +1710,15 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, if (instance) { adv = hci_find_adv_instance(hdev, instance); - /* Create an instance if that could not be found */ - if (!adv) { + if (adv) { + /* Turn it into periodic advertising */ + adv->periodic = true; + adv->per_adv_data_len = data_len; + if (data) + memcpy(adv->per_adv_data, data, data_len); + adv->flags = flags; + } else if (!adv) { + /* Create an instance if that could not be found */ adv = hci_add_per_instance(hdev, instance, flags, data_len, data, sync_interval, @@ -1805,82 +1939,6 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason) sizeof(cp), &cp, HCI_CMD_TIMEOUT); } -static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - struct { - struct hci_cp_le_set_ext_adv_data cp; - u8 data[HCI_MAX_EXT_AD_LENGTH]; - } pdu; - u8 len; - struct adv_info *adv = NULL; - int err; - - memset(&pdu, 0, sizeof(pdu)); - - if (instance) { - adv = hci_find_adv_instance(hdev, instance); - if (!adv || !adv->adv_data_changed) - return 0; - } - - len = eir_create_adv_data(hdev, instance, pdu.data); - - pdu.cp.length = len; - pdu.cp.handle = instance; - pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA, - sizeof(pdu.cp) + len, &pdu.cp, - HCI_CMD_TIMEOUT); - if (err) - return err; - - /* Update data if the command succeed */ - if (adv) { - adv->adv_data_changed = false; - } else { - memcpy(hdev->adv_data, pdu.data, len); - hdev->adv_data_len = len; - } - - return 0; -} - -static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - struct hci_cp_le_set_adv_data cp; - u8 len; - - memset(&cp, 0, sizeof(cp)); - - len = eir_create_adv_data(hdev, instance, cp.data); - - /* There's nothing to do if the data hasn't changed */ - if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) - return 0; - - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); - hdev->adv_data_len = len; - - cp.length = len; - - return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); -} - -int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance) -{ - if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) - return 0; - - if (ext_adv_capable(hdev)) - return hci_set_ext_adv_data_sync(hdev, instance); - - return hci_set_adv_data_sync(hdev, instance); -} - int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance, bool force) { @@ -1956,13 +2014,10 @@ static int hci_clear_adv_sets_sync(struct hci_dev *hdev, struct sock *sk) static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force) { struct adv_info *adv, *n; - int err = 0; if (ext_adv_capable(hdev)) /* Remove all existing sets */ - err = hci_clear_adv_sets_sync(hdev, sk); - if (ext_adv_capable(hdev)) - return err; + return hci_clear_adv_sets_sync(hdev, sk); /* This is safe as long as there is no command send while the lock is * held. @@ -1990,13 +2045,11 @@ static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force) static int hci_remove_adv_sync(struct hci_dev *hdev, u8 instance, struct sock *sk) { - int err = 0; + int err; /* If we use extended advertising, instance has to be removed first. */ if (ext_adv_capable(hdev)) - err = hci_remove_ext_adv_instance_sync(hdev, instance, sk); - if (ext_adv_capable(hdev)) - return err; + return hci_remove_ext_adv_instance_sync(hdev, instance, sk); /* This is safe as long as there is no command send while the lock is * held. @@ -2095,16 +2148,13 @@ int hci_read_tx_power_sync(struct hci_dev *hdev, __le16 handle, u8 type) int hci_disable_advertising_sync(struct hci_dev *hdev) { u8 enable = 0x00; - int err = 0; /* If controller is not advertising we are done. */ if (!hci_dev_test_flag(hdev, HCI_LE_ADV)) return 0; if (ext_adv_capable(hdev)) - err = hci_disable_ext_adv_instance_sync(hdev, 0x00); - if (ext_adv_capable(hdev)) - return err; + return hci_disable_ext_adv_instance_sync(hdev, 0x00); return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable, HCI_CMD_TIMEOUT); @@ -2472,6 +2522,10 @@ static int hci_pause_advertising_sync(struct hci_dev *hdev) int err; int old_state; + /* If controller is not advertising we are done. */ + if (!hci_dev_test_flag(hdev, HCI_LE_ADV)) + return 0; + /* If already been paused there is nothing to do. */ if (hdev->advertising_paused) return 0; @@ -6121,6 +6175,7 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev, struct hci_conn *conn) { struct hci_cp_le_set_ext_adv_params cp; + struct hci_rp_le_set_ext_adv_params rp; int err; bdaddr_t random_addr; u8 own_addr_type; @@ -6163,8 +6218,12 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev, if (err) return err; - err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); + err = hci_set_ext_adv_params_sync(hdev, NULL, &cp, &rp); + if (err) + return err; + + /* Update adv data as tx power is known now */ + err = hci_set_ext_adv_data_sync(hdev, cp.handle); if (err) return err; @@ -6502,8 +6561,8 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, return 0; } - /* No privacy so use a public address. */ - *own_addr_type = ADDR_LE_DEV_PUBLIC; + /* No privacy, use the current address */ + hci_copy_identity_address(hdev, rand_addr, own_addr_type); return 0; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index f62df9097f5e..437cbeaa9619 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1579,11 +1579,6 @@ done: return lm; } -static bool iso_match(struct hci_conn *hcon) -{ - return hcon->type == ISO_LINK || hcon->type == LE_LINK; -} - static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != ISO_LINK) { @@ -1753,7 +1748,6 @@ drop: static struct hci_cb iso_cb = { .name = "ISO", - .match = iso_match, .connect_cfm = iso_connect_cfm, .disconn_cfm = iso_disconn_cfm, }; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 36d6122f2e12..8bb6d2690e2b 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1561,7 +1561,8 @@ static void l2cap_request_info(struct l2cap_conn *conn) sizeof(req), &req); } -static bool l2cap_check_enc_key_size(struct hci_conn *hcon) +static bool l2cap_check_enc_key_size(struct hci_conn *hcon, + struct l2cap_chan *chan) { /* The minimum encryption key size needs to be enforced by the * host stack before establishing any L2CAP connections. The @@ -1575,7 +1576,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon) int min_key_size = hcon->hdev->min_enc_key_size; /* On FIPS security level, key size must be 16 bytes */ - if (hcon->sec_level == BT_SECURITY_FIPS) + if (chan->sec_level == BT_SECURITY_FIPS) min_key_size = 16; return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || @@ -1603,7 +1604,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) !__l2cap_no_conn_pending(chan)) return; - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -1685,7 +1686,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) continue; } - if (l2cap_check_enc_key_size(conn->hcon)) + if (l2cap_check_enc_key_size(conn->hcon, chan)) l2cap_start_connection(chan); else l2cap_chan_close(chan, ECONNREFUSED); @@ -3599,7 +3600,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; struct l2cap_conf_efs efs; u8 remote_efs = 0; - u16 mtu = L2CAP_DEFAULT_MTU; + u16 mtu = 0; u16 result = L2CAP_CONF_SUCCESS; u16 size; @@ -3710,6 +3711,29 @@ done: /* Configure output options and let the other side know * which ones we don't like. */ + /* If MTU is not provided in configure request, try adjusting it + * to the current output MTU if it has been set + * + * Bluetooth Core 6.1, Vol 3, Part A, Section 4.5 + * + * Each configuration parameter value (if any is present) in an + * L2CAP_CONFIGURATION_RSP packet reflects an ‘adjustment’ to a + * configuration parameter value that has been sent (or, in case + * of default values, implied) in the corresponding + * L2CAP_CONFIGURATION_REQ packet. + */ + if (!mtu) { + /* Only adjust for ERTM channels as for older modes the + * remote stack may not be able to detect that the + * adjustment causing it to silently drop packets. + */ + if (chan->mode == L2CAP_MODE_ERTM && + chan->omtu && chan->omtu != L2CAP_DEFAULT_MTU) + mtu = chan->omtu; + else + mtu = L2CAP_DEFAULT_MTU; + } + if (mtu < L2CAP_DEFAULT_MIN_MTU) result = L2CAP_CONF_UNACCEPT; else { @@ -4186,7 +4210,8 @@ static struct l2cap_chan *l2cap_connect(struct l2cap_conn *conn, /* Check if the ACL is secure enough (if not SDP) */ if (psm != cpu_to_le16(L2CAP_PSM_SDP) && - !hci_conn_check_link_mode(conn->hcon)) { + (!hci_conn_check_link_mode(conn->hcon) || + !l2cap_check_enc_key_size(conn->hcon, pchan))) { conn->disc_reason = HCI_ERROR_AUTH_FAILURE; result = L2CAP_CR_SEC_BLOCK; goto response; @@ -5881,7 +5906,8 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, if (!smp_sufficient_security(conn->hcon, pchan->sec_level, SMP_ALLOW_STK)) { - result = L2CAP_CR_LE_AUTHENTICATION; + result = pchan->sec_level == BT_SECURITY_MEDIUM ? + L2CAP_CR_LE_ENCRYPTION : L2CAP_CR_LE_AUTHENTICATION; chan = NULL; goto response_unlock; } @@ -8278,11 +8304,6 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c, return NULL; } -static bool l2cap_match(struct hci_conn *hcon) -{ - return hcon->type == ACL_LINK || hcon->type == LE_LINK; -} - static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) { struct hci_dev *hdev = hcon->hdev; @@ -8290,6 +8311,9 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) struct l2cap_chan *pchan; u8 dst_type; + if (hcon->type != ACL_LINK && hcon->type != LE_LINK) + return; + BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (status) { @@ -8354,6 +8378,9 @@ int l2cap_disconn_ind(struct hci_conn *hcon) static void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) { + if (hcon->type != ACL_LINK && hcon->type != LE_LINK) + return; + BT_DBG("hcon %p reason %d", hcon, reason); l2cap_conn_del(hcon, bt_to_errno(reason)); @@ -8416,7 +8443,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) } if (chan->state == BT_CONNECT) { - if (!status && l2cap_check_enc_key_size(hcon)) + if (!status && l2cap_check_enc_key_size(hcon, chan)) l2cap_start_connection(chan); else __set_chan_timer(chan, L2CAP_DISC_TIMEOUT); @@ -8426,7 +8453,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) struct l2cap_conn_rsp rsp; __u16 res, stat; - if (!status && l2cap_check_enc_key_size(hcon)) { + if (!status && l2cap_check_enc_key_size(hcon, chan)) { if (test_bit(FLAG_DEFER_SETUP, &chan->flags)) { res = L2CAP_CR_PEND; stat = L2CAP_CS_AUTHOR_PEND; @@ -8641,7 +8668,6 @@ drop: static struct hci_cb l2cap_cb = { .name = "L2CAP", - .match = l2cap_match, .connect_cfm = l2cap_connect_cfm, .disconn_cfm = l2cap_disconn_cfm, .security_cfm = l2cap_security_cfm, diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index bdfc83eb7aef..c89277848ca8 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1723,6 +1723,9 @@ static void l2cap_sock_resume_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; + if (!sk) + return; + if (test_and_clear_bit(FLAG_PENDING_SECURITY, &chan->flags)) { sk->sk_state = BT_CONNECTED; chan->state = BT_CONNECTED; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 4f116e8c84a0..919e1bae2b26 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1085,7 +1085,8 @@ static int mesh_send_done_sync(struct hci_dev *hdev, void *data) struct mgmt_mesh_tx *mesh_tx; hci_dev_clear_flag(hdev, HCI_MESH_SENDING); - hci_disable_advertising_sync(hdev); + if (list_empty(&hdev->adv_instances)) + hci_disable_advertising_sync(hdev); mesh_tx = mgmt_mesh_next(hdev, NULL); if (mesh_tx) @@ -2223,6 +2224,9 @@ static int set_mesh_sync(struct hci_dev *hdev, void *data) else hci_dev_clear_flag(hdev, HCI_MESH); + hdev->le_scan_interval = __le16_to_cpu(cp->period); + hdev->le_scan_window = __le16_to_cpu(cp->window); + len -= sizeof(*cp); /* If filters don't fit, forward all adv pkts */ @@ -2237,6 +2241,7 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_set_mesh *cp = data; struct mgmt_pending_cmd *cmd; + __u16 period, window; int err = 0; bt_dev_dbg(hdev, "sock %p", sk); @@ -2250,6 +2255,23 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, MGMT_STATUS_INVALID_PARAMS); + /* Keep allowed ranges in sync with set_scan_params() */ + period = __le16_to_cpu(cp->period); + + if (period < 0x0004 || period > 0x4000) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + + window = __le16_to_cpu(cp->window); + + if (window < 0x0004 || window > 0x4000) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + + if (window > period) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER, + MGMT_STATUS_INVALID_PARAMS); + hci_dev_lock(hdev); cmd = mgmt_pending_add(sk, MGMT_OP_SET_MESH_RECEIVER, hdev, data, len); @@ -5236,24 +5258,14 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev, mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk); } -void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle) +static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev, + __le16 handle) { struct mgmt_ev_adv_monitor_removed ev; - struct mgmt_pending_cmd *cmd; - struct sock *sk_skip = NULL; - struct mgmt_cp_remove_adv_monitor *cp; - cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev); - if (cmd) { - cp = cmd->param; + ev.monitor_handle = handle; - if (cp->monitor_handle) - sk_skip = cmd->sk; - } - - ev.monitor_handle = cpu_to_le16(handle); - - mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk_skip); + mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk); } static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev, @@ -5355,8 +5367,7 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, if (pending_find(MGMT_OP_SET_LE, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || - pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev) || - pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) { + pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) { status = MGMT_STATUS_BUSY; goto unlock; } @@ -5526,8 +5537,7 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, struct mgmt_pending_cmd *cmd = data; struct mgmt_cp_remove_adv_monitor *cp; - if (status == -ECANCELED || - cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) + if (status == -ECANCELED) return; hci_dev_lock(hdev); @@ -5536,12 +5546,14 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, rp.monitor_handle = cp->monitor_handle; - if (!status) + if (!status) { + mgmt_adv_monitor_removed(cmd->sk, hdev, cp->monitor_handle); hci_update_passive_scan(hdev); + } mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(status), &rp, sizeof(rp)); - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); hci_dev_unlock(hdev); bt_dev_dbg(hdev, "remove monitor %d complete, status %d", @@ -5551,10 +5563,6 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, static int mgmt_remove_adv_monitor_sync(struct hci_dev *hdev, void *data) { struct mgmt_pending_cmd *cmd = data; - - if (cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) - return -ECANCELED; - struct mgmt_cp_remove_adv_monitor *cp = cmd->param; u16 handle = __le16_to_cpu(cp->monitor_handle); @@ -5573,14 +5581,13 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); if (pending_find(MGMT_OP_SET_LE, hdev) || - pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) || pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) { status = MGMT_STATUS_BUSY; goto unlock; } - cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len); + cmd = mgmt_pending_new(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len); if (!cmd) { status = MGMT_STATUS_NO_RESOURCES; goto unlock; @@ -5590,7 +5597,7 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev, mgmt_remove_adv_monitor_complete); if (err) { - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); if (err == -ENOMEM) status = MGMT_STATUS_NO_RESOURCES; @@ -6622,6 +6629,7 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev, return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS, MGMT_STATUS_NOT_SUPPORTED); + /* Keep allowed ranges in sync with set_mesh() */ interval = __le16_to_cpu(cp->interval); if (interval < 0x0004 || interval > 0x4000) @@ -9733,6 +9741,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0) + eir_precalc_len(sizeof(conn->dev_class))); + if (!skb) + return; + ev = skb_put(skb, sizeof(*ev)); bacpy(&ev->addr.bdaddr, &conn->dst); ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type); @@ -10514,6 +10525,8 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_FOUND, sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0)); + if (!skb) + return; ev = skb_put(skb, sizeof(*ev)); bacpy(&ev->addr.bdaddr, bdaddr); diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index 0115f783bde8..17e32605d9b0 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -321,7 +321,7 @@ void mgmt_mesh_foreach(struct hci_dev *hdev, { struct mgmt_mesh_tx *mesh_tx, *tmp; - list_for_each_entry_safe(mesh_tx, tmp, &hdev->mgmt_pending, list) { + list_for_each_entry_safe(mesh_tx, tmp, &hdev->mesh_pending, list) { if (!sk || mesh_tx->sk == sk) cb(mesh_tx, data); } diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 1686fa60e278..4f54c7df3a94 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2130,11 +2130,6 @@ static int rfcomm_run(void *unused) return 0; } -static bool rfcomm_match(struct hci_conn *hcon) -{ - return hcon->type == ACL_LINK; -} - static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) { struct rfcomm_session *s; @@ -2181,7 +2176,6 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) static struct hci_cb rfcomm_cb = { .name = "RFCOMM", - .match = rfcomm_match, .security_cfm = rfcomm_security_cfm }; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 127479bf475b..fe8728041ad0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -1367,13 +1367,11 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) return lm; } -static bool sco_match(struct hci_conn *hcon) -{ - return hcon->type == SCO_LINK || hcon->type == ESCO_LINK; -} - static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { + if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) + return; + BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { @@ -1388,6 +1386,9 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { + if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) + return; + BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); @@ -1413,7 +1414,6 @@ drop: static struct hci_cb sco_cb = { .name = "SCO", - .match = sco_match, .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index b93494790877..a03920fe44d9 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1373,7 +1373,7 @@ static void smp_timeout(struct work_struct *work) bt_dev_dbg(conn->hcon->hdev, "conn %p", conn); - hci_disconnect(conn->hcon, HCI_ERROR_REMOTE_USER_TERM); + hci_disconnect(conn->hcon, HCI_ERROR_AUTH_FAILURE); } static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) @@ -2971,8 +2971,25 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb) if (code > SMP_CMD_MAX) goto drop; - if (smp && !test_and_clear_bit(code, &smp->allow_cmd)) + if (smp && !test_and_clear_bit(code, &smp->allow_cmd)) { + /* If there is a context and the command is not allowed consider + * it a failure so the session is cleanup properly. + */ + switch (code) { + case SMP_CMD_IDENT_INFO: + case SMP_CMD_IDENT_ADDR_INFO: + case SMP_CMD_SIGN_INFO: + /* 3.6.1. Key distribution and generation + * + * A device may reject a distributed key by sending the + * Pairing Failed command with the reason set to + * "Key Rejected". + */ + smp_failure(conn, SMP_KEY_REJECTED); + break; + } goto drop; + } /* If we don't have a context the only allowed commands are * pairing request and security request. diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index 87a59ec2c9f0..c5da53dfab04 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -138,6 +138,7 @@ struct smp_cmd_keypress_notify { #define SMP_NUMERIC_COMP_FAILED 0x0c #define SMP_BREDR_PAIRING_IN_PROGRESS 0x0d #define SMP_CROSS_TRANSP_NOT_ALLOWED 0x0e +#define SMP_KEY_REJECTED 0x0f #define SMP_MIN_ENC_KEY_SIZE 7 #define SMP_MAX_ENC_KEY_SIZE 16 diff --git a/net/bridge/br_mst.c b/net/bridge/br_mst.c index 1820f09ff59c..3f24b4ee49c2 100644 --- a/net/bridge/br_mst.c +++ b/net/bridge/br_mst.c @@ -80,10 +80,10 @@ static void br_mst_vlan_set_state(struct net_bridge_vlan_group *vg, if (br_vlan_get_state(v) == state) return; - br_vlan_set_state(v, state); - if (v->vid == vg->pvid) br_vlan_set_pvid_state(vg, state); + + br_vlan_set_state(v, state); } int br_mst_set_state(struct net_bridge_port *p, u16 msti, u8 state, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3cd2b648408d..e28c9db0c4db 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1931,12 +1931,17 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) } } -void br_multicast_enable_port(struct net_bridge_port *port) +static void br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) { - struct net_bridge *br = port->br; + struct net_bridge *br = pmctx->port->br; spin_lock_bh(&br->multicast_lock); - __br_multicast_enable_port_ctx(&port->multicast_ctx); + if (br_multicast_port_ctx_is_vlan(pmctx) && + !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) { + spin_unlock_bh(&br->multicast_lock); + return; + } + __br_multicast_enable_port_ctx(pmctx); spin_unlock_bh(&br->multicast_lock); } @@ -1963,11 +1968,67 @@ static void __br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) br_multicast_rport_del_notify(pmctx, del); } +static void br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) +{ + struct net_bridge *br = pmctx->port->br; + + spin_lock_bh(&br->multicast_lock); + if (br_multicast_port_ctx_is_vlan(pmctx) && + !(pmctx->vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) { + spin_unlock_bh(&br->multicast_lock); + return; + } + + __br_multicast_disable_port_ctx(pmctx); + spin_unlock_bh(&br->multicast_lock); +} + +static void br_multicast_toggle_port(struct net_bridge_port *port, bool on) +{ +#if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) + if (br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *vlan; + + rcu_read_lock(); + vg = nbp_vlan_group_rcu(port); + if (!vg) { + rcu_read_unlock(); + return; + } + + /* iterate each vlan, toggle vlan multicast context */ + list_for_each_entry_rcu(vlan, &vg->vlan_list, vlist) { + struct net_bridge_mcast_port *pmctx = + &vlan->port_mcast_ctx; + u8 state = br_vlan_get_state(vlan); + /* enable vlan multicast context when state is + * LEARNING or FORWARDING + */ + if (on && br_vlan_state_allowed(state, true)) + br_multicast_enable_port_ctx(pmctx); + else + br_multicast_disable_port_ctx(pmctx); + } + rcu_read_unlock(); + return; + } +#endif + /* toggle port multicast context when vlan snooping is disabled */ + if (on) + br_multicast_enable_port_ctx(&port->multicast_ctx); + else + br_multicast_disable_port_ctx(&port->multicast_ctx); +} + +void br_multicast_enable_port(struct net_bridge_port *port) +{ + br_multicast_toggle_port(port, true); +} + void br_multicast_disable_port(struct net_bridge_port *port) { - spin_lock_bh(&port->br->multicast_lock); - __br_multicast_disable_port_ctx(&port->multicast_ctx); - spin_unlock_bh(&port->br->multicast_lock); + br_multicast_toggle_port(port, false); } static int __grp_src_delete_marked(struct net_bridge_port_group *pg) @@ -4037,6 +4098,32 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx) #endif } +void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, u8 state) +{ +#if IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) + struct net_bridge *br; + + if (!br_vlan_should_use(v)) + return; + + if (br_vlan_is_master(v)) + return; + + br = v->port->br; + + if (!br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return; + + if (br_vlan_state_allowed(state, true)) + br_multicast_enable_port_ctx(&v->port_mcast_ctx); + + /* Multicast is not disabled for the vlan when it goes in + * blocking state because the timers will expire and stop by + * themselves without sending more queries. + */ +#endif +} + void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) { struct net_bridge *br; @@ -4130,9 +4217,9 @@ int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, __br_multicast_open(&br->multicast_ctx); list_for_each_entry(p, &br->port_list, list) { if (on) - br_multicast_disable_port(p); + br_multicast_disable_port_ctx(&p->multicast_ctx); else - br_multicast_enable_port(p); + br_multicast_enable_port_ctx(&p->multicast_ctx); } list_for_each_entry(vlan, &vg->vlan_list, vlist) diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 8c69f0c95a8e..b8c8deb87407 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -65,17 +65,14 @@ static struct dst_ops fake_dst_ops = { * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ -static const u32 br_dst_default_metrics[RTAX_MAX] = { - [RTAX_MTU - 1] = 1500, -}; - void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; atomic_set(&rt->dst.__refcnt, 1); rt->dst.dev = br->dev; - dst_init_metrics(&rt->dst, br_dst_default_metrics, true); + dst_init_metrics(&rt->dst, br->metrics, false); + dst_metric_set(&rt->dst, RTAX_MTU, br->dev->mtu); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 940de9516768..767f0e81dd26 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -478,6 +478,7 @@ struct net_bridge { struct rtable fake_rtable; struct rt6_info fake_rt6_info; }; + u32 metrics[RTAX_MAX]; #endif u16 group_fwd_mask; u16 group_fwd_mask_required; @@ -976,6 +977,7 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port, struct net_bridge_vlan *vlan, struct net_bridge_mcast_port *pmctx); void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx); +void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, u8 state); void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on); int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, struct netlink_ext_ack *extack); @@ -1402,6 +1404,11 @@ static inline void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pm { } +static inline void br_multicast_update_vlan_mcast_ctx(struct net_bridge_vlan *v, + u8 state) +{ +} + static inline void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) { @@ -1751,7 +1758,9 @@ bool br_vlan_global_opts_can_enter_range(const struct net_bridge_vlan *v_curr, bool br_vlan_global_opts_fill(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts); -/* vlan state manipulation helpers using *_ONCE to annotate lock-free access */ +/* vlan state manipulation helpers using *_ONCE to annotate lock-free access, + * while br_vlan_set_state() may access data protected by multicast_lock. + */ static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v) { return READ_ONCE(v->state); @@ -1760,6 +1769,7 @@ static inline u8 br_vlan_get_state(const struct net_bridge_vlan *v) static inline void br_vlan_set_state(struct net_bridge_vlan *v, u8 state) { WRITE_ONCE(v->state, state); + br_multicast_update_vlan_mcast_ctx(v, state); } static inline u8 br_vlan_get_pvid_state(const struct net_bridge_vlan_group *vg) diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index b61ef2dff7a4..a0974374bf71 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -17,6 +17,9 @@ static bool nbp_switchdev_can_offload_tx_fwd(const struct net_bridge_port *p, if (!static_branch_unlikely(&br_switchdev_tx_fwd_offload)) return false; + if (br_multicast_igmp_type(skb)) + return false; + return (p->flags & BR_TX_FWD_OFFLOAD) && (p->hwdom != BR_INPUT_SKB_CB(skb)->src_hwdom); } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9ffd40b8270c..23a82567fe62 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -715,8 +715,8 @@ static int br_vlan_add_existing(struct net_bridge *br, u16 flags, bool *changed, struct netlink_ext_ack *extack) { - bool would_change = __vlan_flags_would_change(vlan, flags); bool becomes_brentry = false; + bool would_change = false; int err; if (!br_vlan_is_brentry(vlan)) { @@ -725,6 +725,8 @@ static int br_vlan_add_existing(struct net_bridge *br, return -EINVAL; becomes_brentry = true; + } else { + would_change = __vlan_flags_would_change(vlan, flags); } /* Master VLANs that aren't brentries weren't notified before, diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index e60c38670f22..e7df2911d2be 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -60,19 +60,19 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct ip_fraglist_iter iter; struct sk_buff *frag; - if (first_len - hlen > mtu || - skb_headroom(skb) < ll_rs) + if (first_len - hlen > mtu) goto blackhole; - if (skb_cloned(skb)) + if (skb_cloned(skb) || + skb_headroom(skb) < ll_rs) goto slow_path; skb_walk_frags(skb, frag) { - if (frag->len > mtu || - skb_headroom(frag) < hlen + ll_rs) + if (frag->len > mtu) goto blackhole; - if (skb_shared(frag)) + if (skb_shared(frag) || + skb_headroom(frag) < hlen + ll_rs) goto slow_path; } diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 8480684f2762..10eeace2278b 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -351,17 +351,154 @@ int cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) return found; } +static int cfctrl_link_setup(struct cfctrl *cfctrl, struct cfpkt *pkt, u8 cmdrsp) +{ + u8 len; + u8 linkid = 0; + enum cfctrl_srv serv; + enum cfctrl_srv servtype; + u8 endpoint; + u8 physlinkid; + u8 prio; + u8 tmp; + u8 *cp; + int i; + struct cfctrl_link_param linkparam; + struct cfctrl_request_info rsp, *req; + + memset(&linkparam, 0, sizeof(linkparam)); + + tmp = cfpkt_extr_head_u8(pkt); + + serv = tmp & CFCTRL_SRV_MASK; + linkparam.linktype = serv; + + servtype = tmp >> 4; + linkparam.chtype = servtype; + + tmp = cfpkt_extr_head_u8(pkt); + physlinkid = tmp & 0x07; + prio = tmp >> 3; + + linkparam.priority = prio; + linkparam.phyid = physlinkid; + endpoint = cfpkt_extr_head_u8(pkt); + linkparam.endpoint = endpoint & 0x03; + + switch (serv) { + case CFCTRL_SRV_VEI: + case CFCTRL_SRV_DBG: + if (CFCTRL_ERR_BIT & cmdrsp) + break; + /* Link ID */ + linkid = cfpkt_extr_head_u8(pkt); + break; + case CFCTRL_SRV_VIDEO: + tmp = cfpkt_extr_head_u8(pkt); + linkparam.u.video.connid = tmp; + if (CFCTRL_ERR_BIT & cmdrsp) + break; + /* Link ID */ + linkid = cfpkt_extr_head_u8(pkt); + break; + + case CFCTRL_SRV_DATAGRAM: + linkparam.u.datagram.connid = cfpkt_extr_head_u32(pkt); + if (CFCTRL_ERR_BIT & cmdrsp) + break; + /* Link ID */ + linkid = cfpkt_extr_head_u8(pkt); + break; + case CFCTRL_SRV_RFM: + /* Construct a frame, convert + * DatagramConnectionID + * to network format long and copy it out... + */ + linkparam.u.rfm.connid = cfpkt_extr_head_u32(pkt); + cp = (u8 *) linkparam.u.rfm.volume; + for (tmp = cfpkt_extr_head_u8(pkt); + cfpkt_more(pkt) && tmp != '\0'; + tmp = cfpkt_extr_head_u8(pkt)) + *cp++ = tmp; + *cp = '\0'; + + if (CFCTRL_ERR_BIT & cmdrsp) + break; + /* Link ID */ + linkid = cfpkt_extr_head_u8(pkt); + + break; + case CFCTRL_SRV_UTIL: + /* Construct a frame, convert + * DatagramConnectionID + * to network format long and copy it out... + */ + /* Fifosize KB */ + linkparam.u.utility.fifosize_kb = cfpkt_extr_head_u16(pkt); + /* Fifosize bufs */ + linkparam.u.utility.fifosize_bufs = cfpkt_extr_head_u16(pkt); + /* name */ + cp = (u8 *) linkparam.u.utility.name; + caif_assert(sizeof(linkparam.u.utility.name) + >= UTILITY_NAME_LENGTH); + for (i = 0; i < UTILITY_NAME_LENGTH && cfpkt_more(pkt); i++) { + tmp = cfpkt_extr_head_u8(pkt); + *cp++ = tmp; + } + /* Length */ + len = cfpkt_extr_head_u8(pkt); + linkparam.u.utility.paramlen = len; + /* Param Data */ + cp = linkparam.u.utility.params; + while (cfpkt_more(pkt) && len--) { + tmp = cfpkt_extr_head_u8(pkt); + *cp++ = tmp; + } + if (CFCTRL_ERR_BIT & cmdrsp) + break; + /* Link ID */ + linkid = cfpkt_extr_head_u8(pkt); + /* Length */ + len = cfpkt_extr_head_u8(pkt); + /* Param Data */ + cfpkt_extr_head(pkt, NULL, len); + break; + default: + pr_warn("Request setup, invalid type (%d)\n", serv); + return -1; + } + + rsp.cmd = CFCTRL_CMD_LINK_SETUP; + rsp.param = linkparam; + spin_lock_bh(&cfctrl->info_list_lock); + req = cfctrl_remove_req(cfctrl, &rsp); + + if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) || + cfpkt_erroneous(pkt)) { + pr_err("Invalid O/E bit or parse error " + "on CAIF control channel\n"); + cfctrl->res.reject_rsp(cfctrl->serv.layer.up, 0, + req ? req->client_layer : NULL); + } else { + cfctrl->res.linksetup_rsp(cfctrl->serv.layer.up, linkid, + serv, physlinkid, + req ? req->client_layer : NULL); + } + + kfree(req); + + spin_unlock_bh(&cfctrl->info_list_lock); + + return 0; +} + static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) { u8 cmdrsp; u8 cmd; - int ret = -1; - u8 len; - u8 param[255]; + int ret = 0; u8 linkid = 0; struct cfctrl *cfctrl = container_obj(layer); - struct cfctrl_request_info rsp, *req; - cmdrsp = cfpkt_extr_head_u8(pkt); cmd = cmdrsp & CFCTRL_CMD_MASK; @@ -374,150 +511,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) switch (cmd) { case CFCTRL_CMD_LINK_SETUP: - { - enum cfctrl_srv serv; - enum cfctrl_srv servtype; - u8 endpoint; - u8 physlinkid; - u8 prio; - u8 tmp; - u8 *cp; - int i; - struct cfctrl_link_param linkparam; - memset(&linkparam, 0, sizeof(linkparam)); - - tmp = cfpkt_extr_head_u8(pkt); - - serv = tmp & CFCTRL_SRV_MASK; - linkparam.linktype = serv; - - servtype = tmp >> 4; - linkparam.chtype = servtype; - - tmp = cfpkt_extr_head_u8(pkt); - physlinkid = tmp & 0x07; - prio = tmp >> 3; - - linkparam.priority = prio; - linkparam.phyid = physlinkid; - endpoint = cfpkt_extr_head_u8(pkt); - linkparam.endpoint = endpoint & 0x03; - - switch (serv) { - case CFCTRL_SRV_VEI: - case CFCTRL_SRV_DBG: - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ - linkid = cfpkt_extr_head_u8(pkt); - break; - case CFCTRL_SRV_VIDEO: - tmp = cfpkt_extr_head_u8(pkt); - linkparam.u.video.connid = tmp; - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ - linkid = cfpkt_extr_head_u8(pkt); - break; - - case CFCTRL_SRV_DATAGRAM: - linkparam.u.datagram.connid = - cfpkt_extr_head_u32(pkt); - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ - linkid = cfpkt_extr_head_u8(pkt); - break; - case CFCTRL_SRV_RFM: - /* Construct a frame, convert - * DatagramConnectionID - * to network format long and copy it out... - */ - linkparam.u.rfm.connid = - cfpkt_extr_head_u32(pkt); - cp = (u8 *) linkparam.u.rfm.volume; - for (tmp = cfpkt_extr_head_u8(pkt); - cfpkt_more(pkt) && tmp != '\0'; - tmp = cfpkt_extr_head_u8(pkt)) - *cp++ = tmp; - *cp = '\0'; - - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ - linkid = cfpkt_extr_head_u8(pkt); - - break; - case CFCTRL_SRV_UTIL: - /* Construct a frame, convert - * DatagramConnectionID - * to network format long and copy it out... - */ - /* Fifosize KB */ - linkparam.u.utility.fifosize_kb = - cfpkt_extr_head_u16(pkt); - /* Fifosize bufs */ - linkparam.u.utility.fifosize_bufs = - cfpkt_extr_head_u16(pkt); - /* name */ - cp = (u8 *) linkparam.u.utility.name; - caif_assert(sizeof(linkparam.u.utility.name) - >= UTILITY_NAME_LENGTH); - for (i = 0; - i < UTILITY_NAME_LENGTH - && cfpkt_more(pkt); i++) { - tmp = cfpkt_extr_head_u8(pkt); - *cp++ = tmp; - } - /* Length */ - len = cfpkt_extr_head_u8(pkt); - linkparam.u.utility.paramlen = len; - /* Param Data */ - cp = linkparam.u.utility.params; - while (cfpkt_more(pkt) && len--) { - tmp = cfpkt_extr_head_u8(pkt); - *cp++ = tmp; - } - if (CFCTRL_ERR_BIT & cmdrsp) - break; - /* Link ID */ - linkid = cfpkt_extr_head_u8(pkt); - /* Length */ - len = cfpkt_extr_head_u8(pkt); - /* Param Data */ - cfpkt_extr_head(pkt, ¶m, len); - break; - default: - pr_warn("Request setup, invalid type (%d)\n", - serv); - goto error; - } - - rsp.cmd = cmd; - rsp.param = linkparam; - spin_lock_bh(&cfctrl->info_list_lock); - req = cfctrl_remove_req(cfctrl, &rsp); - - if (CFCTRL_ERR_BIT == (CFCTRL_ERR_BIT & cmdrsp) || - cfpkt_erroneous(pkt)) { - pr_err("Invalid O/E bit or parse error " - "on CAIF control channel\n"); - cfctrl->res.reject_rsp(cfctrl->serv.layer.up, - 0, - req ? req->client_layer - : NULL); - } else { - cfctrl->res.linksetup_rsp(cfctrl->serv. - layer.up, linkid, - serv, physlinkid, - req ? req-> - client_layer : NULL); - } - - kfree(req); - - spin_unlock_bh(&cfctrl->info_list_lock); - } + ret = cfctrl_link_setup(cfctrl, pkt, cmdrsp); break; case CFCTRL_CMD_LINK_DESTROY: linkid = cfpkt_extr_head_u8(pkt); @@ -544,9 +538,9 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) break; default: pr_err("Unrecognized Control Frame\n"); + ret = -1; goto error; } - ret = 0; error: cfpkt_destroy(pkt); return ret; diff --git a/net/can/af_can.c b/net/can/af_can.c index 7d8543e877b4..bbd8e959137d 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -287,8 +287,8 @@ int can_send(struct sk_buff *skb, int loop) netif_rx(newskb); /* update statistics */ - pkg_stats->tx_frames++; - pkg_stats->tx_frames_delta++; + atomic_long_inc(&pkg_stats->tx_frames); + atomic_long_inc(&pkg_stats->tx_frames_delta); return 0; @@ -648,8 +648,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) int matches; /* update statistics */ - pkg_stats->rx_frames++; - pkg_stats->rx_frames_delta++; + atomic_long_inc(&pkg_stats->rx_frames); + atomic_long_inc(&pkg_stats->rx_frames_delta); /* create non-zero unique skb identifier together with *skb */ while (!(can_skb_prv(skb)->skbcnt)) @@ -670,8 +670,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) consume_skb(skb); if (matches > 0) { - pkg_stats->matches++; - pkg_stats->matches_delta++; + atomic_long_inc(&pkg_stats->matches); + atomic_long_inc(&pkg_stats->matches_delta); } } diff --git a/net/can/af_can.h b/net/can/af_can.h index 7c2d9161e224..22f3352c77fe 100644 --- a/net/can/af_can.h +++ b/net/can/af_can.h @@ -66,9 +66,9 @@ struct receiver { struct can_pkg_stats { unsigned long jiffies_init; - unsigned long rx_frames; - unsigned long tx_frames; - unsigned long matches; + atomic_long_t rx_frames; + atomic_long_t tx_frames; + atomic_long_t matches; unsigned long total_rx_rate; unsigned long total_tx_rate; @@ -82,9 +82,9 @@ struct can_pkg_stats { unsigned long max_tx_rate; unsigned long max_rx_match_ratio; - unsigned long rx_frames_delta; - unsigned long tx_frames_delta; - unsigned long matches_delta; + atomic_long_t rx_frames_delta; + atomic_long_t tx_frames_delta; + atomic_long_t matches_delta; }; /* persistent statistics */ diff --git a/net/can/bcm.c b/net/can/bcm.c index 3817692e83af..4fb5cfaf74f3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -58,6 +58,7 @@ #include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -120,6 +121,7 @@ struct bcm_op { struct canfd_frame last_sframe; struct sock *sk; struct net_device *rx_reg_dev; + spinlock_t bcm_tx_lock; /* protect currframe/count in runtime updates */ }; struct bcm_sock { @@ -205,7 +207,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, " / bound %s", bcm_proc_getifname(net, ifname, bo->ifindex)); seq_printf(m, " <<<\n"); - list_for_each_entry(op, &bo->rx_ops, list) { + rcu_read_lock(); + + list_for_each_entry_rcu(op, &bo->rx_ops, list) { unsigned long reduction; @@ -261,6 +265,9 @@ static int bcm_proc_show(struct seq_file *m, void *v) seq_printf(m, "# sent %ld\n", op->frames_abs); } seq_putc(m, '\n'); + + rcu_read_unlock(); + return 0; } #endif /* CONFIG_PROC_FS */ @@ -273,13 +280,18 @@ static void bcm_can_tx(struct bcm_op *op) { struct sk_buff *skb; struct net_device *dev; - struct canfd_frame *cf = op->frames + op->cfsiz * op->currframe; + struct canfd_frame *cf; int err; /* no target device? => exit */ if (!op->ifindex) return; + /* read currframe under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + cf = op->frames + op->cfsiz * op->currframe; + spin_unlock_bh(&op->bcm_tx_lock); + dev = dev_get_by_index(sock_net(op->sk), op->ifindex); if (!dev) { /* RFC: should this bcm_op remove itself here? */ @@ -300,6 +312,10 @@ static void bcm_can_tx(struct bcm_op *op) skb->dev = dev; can_skb_set_owner(skb, op->sk); err = can_send(skb, 1); + + /* update currframe and count under lock protection */ + spin_lock_bh(&op->bcm_tx_lock); + if (!err) op->frames_abs++; @@ -308,6 +324,11 @@ static void bcm_can_tx(struct bcm_op *op) /* reached last frame? */ if (op->currframe >= op->nframes) op->currframe = 0; + + if (op->count > 0) + op->count--; + + spin_unlock_bh(&op->bcm_tx_lock); out: dev_put(dev); } @@ -404,7 +425,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) struct bcm_msg_head msg_head; if (op->kt_ival1 && (op->count > 0)) { - op->count--; + bcm_can_tx(op); if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ @@ -419,7 +440,6 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) bcm_send_to_user(op, &msg_head, NULL, 0); } - bcm_can_tx(op); } else if (op->kt_ival2) { bcm_can_tx(op); @@ -801,7 +821,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, REGMASK(op->can_id), bcm_rx_handler, op); - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -821,7 +841,7 @@ static int bcm_delete_tx_op(struct list_head *ops, struct bcm_msg_head *mh, list_for_each_entry_safe(op, n, ops, list) { if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return 1; /* done */ } @@ -914,6 +934,27 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } op->flags = msg_head->flags; + /* only lock for unlikely count/nframes/currframe changes */ + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX || + op->flags & SETTIMER) { + + spin_lock_bh(&op->bcm_tx_lock); + + if (op->nframes != msg_head->nframes || + op->flags & TX_RESET_MULTI_IDX) { + /* potentially update changed nframes */ + op->nframes = msg_head->nframes; + /* restart multiple frame transmission */ + op->currframe = 0; + } + + if (op->flags & SETTIMER) + op->count = msg_head->count; + + spin_unlock_bh(&op->bcm_tx_lock); + } + } else { /* insert new BCM operation for the given can_id */ @@ -921,9 +962,14 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->cfsiz = CFSIZ(msg_head->flags); op->flags = msg_head->flags; + op->nframes = msg_head->nframes; + + if (op->flags & SETTIMER) + op->count = msg_head->count; /* create array for CAN frames and copy the data */ if (msg_head->nframes > 1) { @@ -982,22 +1028,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, } /* if ((op = bcm_find_op(&bo->tx_ops, msg_head->can_id, ifindex))) */ - if (op->nframes != msg_head->nframes) { - op->nframes = msg_head->nframes; - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - - /* check flags */ - - if (op->flags & TX_RESET_MULTI_IDX) { - /* start multiple frame transmission with index 0 */ - op->currframe = 0; - } - if (op->flags & SETTIMER) { /* set timer values */ - op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); @@ -1014,11 +1046,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->flags |= TX_ANNOUNCE; } - if (op->flags & TX_ANNOUNCE) { + if (op->flags & TX_ANNOUNCE) bcm_can_tx(op); - if (op->count) - op->count--; - } if (op->flags & STARTTIMER) bcm_tx_start_timer(op); @@ -1234,7 +1263,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, bcm_rx_handler, op, "bcm", sk); if (err) { /* this bcm rx op is broken -> remove it */ - list_del(&op->list); + list_del_rcu(&op->list); bcm_remove_op(op); return err; } diff --git a/net/can/gw.c b/net/can/gw.c index 23a3d89cad81..5933423663cd 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -130,7 +130,7 @@ struct cgw_job { u32 handled_frames; u32 dropped_frames; u32 deleted_frames; - struct cf_mod mod; + struct cf_mod __rcu *cf_mod; union { /* CAN frame data source */ struct net_device *dev; @@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) struct cgw_job *gwj = (struct cgw_job *)data; struct canfd_frame *cf; struct sk_buff *nskb; + struct cf_mod *mod; int modidx = 0; /* process strictly Classic CAN or CAN FD frames */ @@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) * When there is at least one modification function activated, * we need to copy the skb as we want to modify skb->data. */ - if (gwj->mod.modfunc[0]) + mod = rcu_dereference(gwj->cf_mod); + if (mod->modfunc[0]) nskb = skb_copy(skb, GFP_ATOMIC); else nskb = skb_clone(skb, GFP_ATOMIC); @@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) cf = (struct canfd_frame *)nskb->data; /* perform preprocessed modification functions if there are any */ - while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx]) - (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod); + while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx]) + (*mod->modfunc[modidx++])(cf, mod); /* Has the CAN frame been modified? */ if (modidx) { @@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) } /* check for checksum updates */ - if (gwj->mod.csumfunc.crc8) - (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8); + if (mod->csumfunc.crc8) + (*mod->csumfunc.crc8)(cf, &mod->csum.crc8); - if (gwj->mod.csumfunc.xor) - (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor); + if (mod->csumfunc.xor) + (*mod->csumfunc.xor)(cf, &mod->csum.xor); } /* clear the skb timestamp if not configured the other way */ @@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head) { struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu); + /* cgw_job::cf_mod is always accessed from the same cgw_job object within + * the same RCU read section. Once cgw_job is scheduled for removal, + * cf_mod can also be removed without mandating an additional grace period. + */ + kfree(rcu_access_pointer(gwj->cf_mod)); kmem_cache_free(cgw_cache, gwj); } +/* Return cgw_job::cf_mod with RTNL protected section */ +static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj) +{ + return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked()); +} + static int cgw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { @@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, { struct rtcanmsg *rtcan; struct nlmsghdr *nlh; + struct cf_mod *mod; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags); if (!nlh) @@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } + mod = cgw_job_cf_mod(gwj); if (gwj->flags & CGW_FLAGS_CAN_FD) { struct cgw_fdframe_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } else { struct cgw_frame_mod mb; - if (gwj->mod.modtype.and) { - memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.and; + if (mod->modtype.and) { + memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf)); + mb.modtype = mod->modtype.and; if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.or) { - memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.or; + if (mod->modtype.or) { + memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf)); + mb.modtype = mod->modtype.or; if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.xor) { - memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.xor; + if (mod->modtype.xor) { + memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf)); + mb.modtype = mod->modtype.xor; if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0) goto cancel; } - if (gwj->mod.modtype.set) { - memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf)); - mb.modtype = gwj->mod.modtype.set; + if (mod->modtype.set) { + memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf)); + mb.modtype = mod->modtype.set; if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0) goto cancel; } } - if (gwj->mod.uid) { - if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0) + if (mod->uid) { + if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0) goto cancel; } - if (gwj->mod.csumfunc.crc8) { + if (mod->csumfunc.crc8) { if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN, - &gwj->mod.csum.crc8) < 0) + &mod->csum.crc8) < 0) goto cancel; } - if (gwj->mod.csumfunc.xor) { + if (mod->csumfunc.xor) { if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN, - &gwj->mod.csum.xor) < 0) + &mod->csum.xor) < 0) goto cancel; } @@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct rtcanmsg *r; struct cgw_job *gwj; - struct cf_mod mod; + struct cf_mod *mod; struct can_can_gw ccgw; u8 limhops = 0; int err = 0; @@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (r->gwtype != CGW_TYPE_CAN_CAN) return -EINVAL; - err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); + mod = kmalloc(sizeof(*mod), GFP_KERNEL); + if (!mod) + return -ENOMEM; + + err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops); if (err < 0) - return err; + goto out_free_cf; - if (mod.uid) { + if (mod->uid) { ASSERT_RTNL(); /* check for updating an existing job with identical uid */ hlist_for_each_entry(gwj, &net->can.cgw_list, list) { - if (gwj->mod.uid != mod.uid) + struct cf_mod *old_cf; + + old_cf = cgw_job_cf_mod(gwj); + if (old_cf->uid != mod->uid) continue; /* interfaces & filters must be identical */ - if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) - return -EINVAL; + if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) { + err = -EINVAL; + goto out_free_cf; + } - /* update modifications with disabled softirq & quit */ - local_bh_disable(); - memcpy(&gwj->mod, &mod, sizeof(mod)); - local_bh_enable(); + rcu_assign_pointer(gwj->cf_mod, mod); + kfree_rcu_mightsleep(old_cf); return 0; } } /* ifindex == 0 is not allowed for job creation */ - if (!ccgw.src_idx || !ccgw.dst_idx) - return -ENODEV; + if (!ccgw.src_idx || !ccgw.dst_idx) { + err = -ENODEV; + goto out_free_cf; + } gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL); - if (!gwj) - return -ENOMEM; + if (!gwj) { + err = -ENOMEM; + goto out_free_cf; + } gwj->handled_frames = 0; gwj->dropped_frames = 0; @@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, gwj->limit_hops = limhops; /* insert already parsed information */ - memcpy(&gwj->mod, &mod, sizeof(mod)); + RCU_INIT_POINTER(gwj->cf_mod, mod); memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw)); err = -ENODEV; @@ -1145,9 +1171,11 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (!err) hlist_add_head_rcu(&gwj->list, &net->can.cgw_list); out: - if (err) + if (err) { kmem_cache_free(cgw_cache, gwj); - +out_free_cf: + kfree(mod); + } return err; } @@ -1207,19 +1235,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, /* remove only the first matching entry */ hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { + struct cf_mod *cf_mod; + if (gwj->flags != r->flags) continue; if (gwj->limit_hops != limhops) continue; + cf_mod = cgw_job_cf_mod(gwj); /* we have a match when uid is enabled and identical */ - if (gwj->mod.uid || mod.uid) { - if (gwj->mod.uid != mod.uid) + if (cf_mod->uid || mod.uid) { + if (cf_mod->uid != mod.uid) continue; } else { /* no uid => check for identical modifications */ - if (memcmp(&gwj->mod, &mod, sizeof(mod))) + if (memcmp(cf_mod, &mod, sizeof(mod))) continue; } diff --git a/net/can/proc.c b/net/can/proc.c index bbce97825f13..25fdf060e30d 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -118,6 +118,13 @@ void can_stat_update(struct timer_list *t) struct can_pkg_stats *pkg_stats = net->can.pkg_stats; unsigned long j = jiffies; /* snapshot */ + long rx_frames = atomic_long_read(&pkg_stats->rx_frames); + long tx_frames = atomic_long_read(&pkg_stats->tx_frames); + long matches = atomic_long_read(&pkg_stats->matches); + long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta); + long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta); + long matches_delta = atomic_long_read(&pkg_stats->matches_delta); + /* restart counting in timer context on user request */ if (user_reset) can_init_stats(net); @@ -127,35 +134,33 @@ void can_stat_update(struct timer_list *t) can_init_stats(net); /* prevent overflow in calc_rate() */ - if (pkg_stats->rx_frames > (ULONG_MAX / HZ)) + if (rx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* prevent overflow in calc_rate() */ - if (pkg_stats->tx_frames > (ULONG_MAX / HZ)) + if (tx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* matches overflow - very improbable */ - if (pkg_stats->matches > (ULONG_MAX / 100)) + if (matches > (LONG_MAX / 100)) can_init_stats(net); /* calc total values */ - if (pkg_stats->rx_frames) - pkg_stats->total_rx_match_ratio = (pkg_stats->matches * 100) / - pkg_stats->rx_frames; + if (rx_frames) + pkg_stats->total_rx_match_ratio = (matches * 100) / rx_frames; pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j, - pkg_stats->tx_frames); + tx_frames); pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j, - pkg_stats->rx_frames); + rx_frames); /* calc current values */ - if (pkg_stats->rx_frames_delta) + if (rx_frames_delta) pkg_stats->current_rx_match_ratio = - (pkg_stats->matches_delta * 100) / - pkg_stats->rx_frames_delta; + (matches_delta * 100) / rx_frames_delta; - pkg_stats->current_tx_rate = calc_rate(0, HZ, pkg_stats->tx_frames_delta); - pkg_stats->current_rx_rate = calc_rate(0, HZ, pkg_stats->rx_frames_delta); + pkg_stats->current_tx_rate = calc_rate(0, HZ, tx_frames_delta); + pkg_stats->current_rx_rate = calc_rate(0, HZ, rx_frames_delta); /* check / update maximum values */ if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate) @@ -168,9 +173,9 @@ void can_stat_update(struct timer_list *t) pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio; /* clear values for 'current rate' calculation */ - pkg_stats->tx_frames_delta = 0; - pkg_stats->rx_frames_delta = 0; - pkg_stats->matches_delta = 0; + atomic_long_set(&pkg_stats->tx_frames_delta, 0); + atomic_long_set(&pkg_stats->rx_frames_delta, 0); + atomic_long_set(&pkg_stats->matches_delta, 0); /* restart timer (one second) */ mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ)); @@ -214,9 +219,12 @@ static int can_stats_proc_show(struct seq_file *m, void *v) struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; seq_putc(m, '\n'); - seq_printf(m, " %8ld transmitted frames (TXF)\n", pkg_stats->tx_frames); - seq_printf(m, " %8ld received frames (RXF)\n", pkg_stats->rx_frames); - seq_printf(m, " %8ld matched frames (RXMF)\n", pkg_stats->matches); + seq_printf(m, " %8ld transmitted frames (TXF)\n", + atomic_long_read(&pkg_stats->tx_frames)); + seq_printf(m, " %8ld received frames (RXF)\n", + atomic_long_read(&pkg_stats->rx_frames)); + seq_printf(m, " %8ld matched frames (RXMF)\n", + atomic_long_read(&pkg_stats->matches)); seq_putc(m, '\n'); diff --git a/net/core/filter.c b/net/core/filter.c index 370f61f9bf4b..cd0c28e94979 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -212,24 +212,36 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) return 0; } +static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) +{ + if (likely(offset >= 0)) + return offset; + + if (offset >= SKF_NET_OFF) + return offset - SKF_NET_OFF + skb_network_offset(skb); + + if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) + return offset - SKF_LL_OFF + skb_mac_offset(skb); + + return INT_MIN; +} + BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { - u8 tmp, *ptr; + u8 tmp; const int len = sizeof(tmp); - if (offset >= 0) { - if (headlen - offset >= len) - return *(u8 *)(data + offset); - if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) - return tmp; - } else { - ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); - if (likely(ptr)) - return *(u8 *)ptr; - } + offset = bpf_skb_load_helper_convert_offset(skb, offset); + if (offset == INT_MIN) + return -EFAULT; - return -EFAULT; + if (headlen - offset >= len) + return *(u8 *)(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return tmp; + else + return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, @@ -242,21 +254,19 @@ BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { - __be16 tmp, *ptr; + __be16 tmp; const int len = sizeof(tmp); - if (offset >= 0) { - if (headlen - offset >= len) - return get_unaligned_be16(data + offset); - if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) - return be16_to_cpu(tmp); - } else { - ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); - if (likely(ptr)) - return get_unaligned_be16(ptr); - } + offset = bpf_skb_load_helper_convert_offset(skb, offset); + if (offset == INT_MIN) + return -EFAULT; - return -EFAULT; + if (headlen - offset >= len) + return get_unaligned_be16(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be16_to_cpu(tmp); + else + return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, @@ -269,21 +279,19 @@ BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { - __be32 tmp, *ptr; + __be32 tmp; const int len = sizeof(tmp); - if (likely(offset >= 0)) { - if (headlen - offset >= len) - return get_unaligned_be32(data + offset); - if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) - return be32_to_cpu(tmp); - } else { - ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); - if (likely(ptr)) - return get_unaligned_be32(ptr); - } + offset = bpf_skb_load_helper_convert_offset(skb, offset); + if (offset == INT_MIN) + return -EFAULT; - return -EFAULT; + if (headlen - offset >= len) + return get_unaligned_be32(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be32_to_cpu(tmp); + else + return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, @@ -1950,10 +1958,11 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; + bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | - BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) + BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; @@ -1969,7 +1978,7 @@ BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, if (unlikely(from != 0)) return -EINVAL; - inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo); + inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); @@ -2492,6 +2501,7 @@ int skb_do_redirect(struct sk_buff *skb) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); + skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? @@ -9260,6 +9270,9 @@ static bool flow_dissector_is_valid_access(int off, int size, if (off < 0 || off >= sizeof(struct __sk_buff)) return false; + if (off % size != 0) + return false; + if (type == BPF_WRITE) return false; diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index 711cd3b4347a..f63586c9ce02 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -23,6 +23,8 @@ #include <net/ip6_fib.h> #include <net/rtnh.h> +#include "dev.h" + DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled); @@ -325,82 +327,132 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; - if (!dst) + local_bh_disable(); + + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; goto drop; + } + + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; + goto drop; + } lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || - lwtstate->type > LWTUNNEL_ENCAP_MAX) - return 0; + lwtstate->type > LWTUNNEL_ENCAP_MAX) { + ret = 0; + goto out; + } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->output)) + if (likely(ops && ops->output)) { + dev_xmit_recursion_inc(); ret = ops->output(net, sk, skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; - return ret; + goto out; drop: kfree_skb(skb); +out: + local_bh_enable(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_output); int lwtunnel_xmit(struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; - if (!dst) + local_bh_disable(); + + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; goto drop; + } + + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; + goto drop; + } lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || - lwtstate->type > LWTUNNEL_ENCAP_MAX) - return 0; + lwtstate->type > LWTUNNEL_ENCAP_MAX) { + ret = 0; + goto out; + } ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->xmit)) + if (likely(ops && ops->xmit)) { + dev_xmit_recursion_inc(); ret = ops->xmit(skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) goto drop; - return ret; + goto out; drop: kfree_skb(skb); +out: + local_bh_enable(); return ret; } EXPORT_SYMBOL_GPL(lwtunnel_xmit); int lwtunnel_input(struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); const struct lwtunnel_encap_ops *ops; struct lwtunnel_state *lwtstate; - int ret = -EINVAL; + struct dst_entry *dst; + int ret; + + DEBUG_NET_WARN_ON_ONCE(!in_softirq()); + + if (dev_xmit_recursion()) { + net_crit_ratelimited("%s(): recursion limit reached on datapath\n", + __func__); + ret = -ENETDOWN; + goto drop; + } - if (!dst) + dst = skb_dst(skb); + if (!dst) { + ret = -EINVAL; goto drop; + } lwtstate = dst->lwtstate; if (lwtstate->type == LWTUNNEL_ENCAP_NONE || @@ -410,8 +462,11 @@ int lwtunnel_input(struct sk_buff *skb) ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[lwtstate->type]); - if (likely(ops && ops->input)) + if (likely(ops && ops->input)) { + dev_xmit_recursion_inc(); ret = ops->input(skb); + dev_xmit_recursion_dec(); + } rcu_read_unlock(); if (ret == -EOPNOTSUPP) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2e2c009b5a2d..bcc3950638b9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2283,6 +2283,7 @@ static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = { static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { [NDTPA_IFINDEX] = { .type = NLA_U32 }, [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LENBYTES] = { .type = NLA_U32 }, [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, [NDTPA_APP_PROBES] = { .type = NLA_U32 }, [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 681eeb2b7399..89f5358d7a1b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -326,6 +326,7 @@ static int netpoll_owner_active(struct net_device *dev) static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { netdev_tx_t status = NETDEV_TX_BUSY; + netdev_tx_t ret = NET_XMIT_DROP; struct net_device *dev; unsigned long tries; /* It is up to the caller to keep npinfo alive. */ @@ -334,11 +335,12 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) lockdep_assert_irqs_disabled(); dev = np->dev; + rcu_read_lock(); npinfo = rcu_dereference_bh(dev->npinfo); if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { dev_kfree_skb_irq(skb); - return NET_XMIT_DROP; + goto out; } /* don't get messages out of order, and no recursion */ @@ -377,7 +379,10 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) skb_queue_tail(&npinfo->txq, skb); schedule_delayed_work(&npinfo->tx_work,0); } - return NETDEV_TX_OK; + ret = NETDEV_TX_OK; +out: + rcu_read_unlock(); + return ret; } netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) @@ -795,6 +800,13 @@ put_noaddr: goto put; netdev_tracker_alloc(ndev, &np->dev_tracker, GFP_KERNEL); rtnl_unlock(); + + /* Make sure all NAPI polls which started before dev->npinfo + * was visible have exited before we start calling NAPI poll. + * NAPI skips locking if dev->npinfo is NULL. + */ + synchronize_rcu(); + return 0; put: diff --git a/net/core/page_pool.c b/net/core/page_pool.c index caf6d950d54a..acc1d0d055cd 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -841,7 +841,13 @@ static void page_pool_release_retry(struct work_struct *wq) int inflight; inflight = page_pool_release(pool); - if (!inflight) + /* In rare cases, a driver bug may cause inflight to go negative. + * Don't reschedule release if inflight is 0 or negative. + * - If 0, the page_pool has been destroyed + * - if negative, we will never recover + * in both cases no reschedule is necessary. + */ + if (inflight <= 0) return; /* Periodic warning */ diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a2fb951996b8..a2838c15aa9d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -897,6 +897,10 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; + + if (n >= MAX_MPLS_LABELS) + return -E2BIG; + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; @@ -908,8 +912,6 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) return -EFAULT; i++; n++; - if (n >= MAX_MPLS_LABELS) - return -E2BIG; } while (c == ','); pkt_dev->nr_labels = n; @@ -1875,8 +1877,8 @@ static ssize_t pktgen_thread_write(struct file *file, i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1906,7 +1908,8 @@ static ssize_t pktgen_thread_write(struct file *file, if (!strcmp(name, "add_device")) { char f[32]; memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) { ret = len; goto out; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 45c54fb9ad03..6bc2f78a5ebb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1007,6 +1007,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, /* IFLA_VF_STATS_TX_DROPPED */ nla_total_size_64bit(sizeof(__u64))); } + if (dev->netdev_ops->ndo_get_vf_guid) + size += num_vfs * 2 * + nla_total_size(sizeof(struct ifla_vf_guid)); return size; } else return 0; diff --git a/net/core/scm.c b/net/core/scm.c index a877c4ef4c25..cdd4e5befb14 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -36,6 +36,7 @@ #include <net/compat.h> #include <net/scm.h> #include <net/cls_cgroup.h> +#include <net/af_unix.h> /* @@ -85,8 +86,15 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->count_unix = 0; fpl->max = SCM_MAX_FD; fpl->user = NULL; +#if IS_ENABLED(CONFIG_UNIX) + fpl->inflight = false; + fpl->dead = false; + fpl->edges = NULL; + INIT_LIST_HEAD(&fpl->vertices); +#endif } fpp = &fpl->fp[fpl->count]; @@ -109,6 +117,9 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) fput(file); return -EINVAL; } + if (unix_get_socket(file)) + fpl->count_unix++; + *fpp++ = file; fpl->count++; } @@ -367,8 +378,14 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (new_fpl) { for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); + new_fpl->max = new_fpl->count; new_fpl->user = get_uid(fpl->user); +#if IS_ENABLED(CONFIG_UNIX) + new_fpl->inflight = false; + new_fpl->edges = NULL; + INIT_LIST_HEAD(&new_fpl->vertices); +#endif } return new_fpl; } diff --git a/net/core/selftests.c b/net/core/selftests.c index acb1ee97bbd3..946e92cca211 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, ehdr->h_proto = htons(ETH_P_IP); if (attr->tcp) { + memset(thdr, 0, sizeof(*thdr)); thdr->source = htons(attr->sport); thdr->dest = htons(attr->dport); thdr->doff = sizeof(struct tcphdr) / 4; - thdr->check = 0; } else { uhdr->source = htons(attr->sport); uhdr->dest = htons(attr->dport); @@ -144,16 +144,25 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, attr->id = net_test_next_id; shdr->id = net_test_next_id++; - if (attr->size) - skb_put(skb, attr->size); - if (attr->max_size && attr->max_size > skb->len) - skb_put(skb, attr->max_size - skb->len); + if (attr->size) { + void *payload = skb_put(skb, attr->size); + + memset(payload, 0, attr->size); + } + + if (attr->max_size && attr->max_size > skb->len) { + size_t pad_len = attr->max_size - skb->len; + void *pad = skb_put(skb, pad_len); + + memset(pad, 0, pad_len); + } skb->csum = 0; skb->ip_summed = CHECKSUM_PARTIAL; if (attr->tcp) { - thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr, - ihdr->daddr, 0); + int l4len = skb->len - skb_transport_offset(skb); + + thdr->check = ~tcp_v4_check(l4len, ihdr->saddr, ihdr->daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 5a790cd1121b..01ca497fe2cd 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -528,16 +528,22 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, u32 off, u32 len, struct sk_psock *psock, struct sock *sk, - struct sk_msg *msg) + struct sk_msg *msg, + bool take_ref) { int num_sge, copied; + /* skb_to_sgvec will fail when the total number of fragments in + * frag_list and frags exceeds MAX_MSG_FRAGS. For example, the + * caller may aggregate multiple skbs. + */ num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (num_sge < 0) { /* skb linearize may fail with ENOMEM, but lets simply try again * later if this happens. Under memory pressure we don't want to * drop the skb. We need to linearize the skb so that the mapping * in skb_to_sgvec can not error. + * Note that skb_linearize requires the skb not to be shared. */ if (skb_linearize(skb)) return -EAGAIN; @@ -554,7 +560,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; - msg->skb = skb; + msg->skb = take_ref ? skb_get(skb) : skb; sk_psock_queue_msg(psock, msg); sk_psock_data_ready(sk, psock); @@ -562,7 +568,7 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, } static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len); + u32 off, u32 len, bool take_ref); static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) @@ -576,7 +582,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb, off, len); + return sk_psock_skb_ingress_self(psock, skb, off, len, true); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -588,7 +594,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, true); if (err < 0) kfree(msg); return err; @@ -599,7 +605,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, * because the skb is already accounted for here. */ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, - u32 off, u32 len) + u32 off, u32 len, bool take_ref) { struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; @@ -608,7 +614,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg, take_ref); if (err < 0) kfree(msg); return err; @@ -617,18 +623,13 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { - int err = 0; - if (!ingress) { if (!sock_writeable(psock->sk)) return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - skb_get(skb); - err = sk_psock_skb_ingress(psock, skb, off, len); - if (err < 0) - kfree_skb(skb); - return err; + + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -653,12 +654,21 @@ static void sk_psock_backlog(struct work_struct *work) bool ingress; int ret; - mutex_lock(&psock->work_mutex); - if (unlikely(state->len)) { - len = state->len; - off = state->off; - } + /* If sk is quickly removed from the map and then added back, the old + * psock should not be scheduled, because there are now two psocks + * pointing to the same sk. + */ + if (!sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + return; + /* Increment the psock refcnt to synchronize with close(fd) path in + * sock_map_close(), ensuring we wait for backlog thread completion + * before sk_socket freed. If refcnt increment fails, it indicates + * sock_map_close() completed with sk_socket potentially already freed. + */ + if (!sk_psock_get(psock->sk)) + return; + mutex_lock(&psock->work_mutex); while ((skb = skb_peek(&psock->ingress_skb))) { len = skb->len; off = 0; @@ -668,6 +678,13 @@ static void sk_psock_backlog(struct work_struct *work) off = stm->offset; len = stm->full_len; } + + /* Resume processing from previous partial state */ + if (unlikely(state->len)) { + len = state->len; + off = state->off; + } + ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); do { @@ -678,7 +695,8 @@ static void sk_psock_backlog(struct work_struct *work) if (ret <= 0) { if (ret == -EAGAIN) { sk_psock_skb_state(psock, state, len, off); - + /* Restore redir info we cleared before */ + skb_bpf_set_redir(skb, psock->sk, ingress); /* Delay slightly to prioritize any * other work that might be here. */ @@ -695,11 +713,14 @@ static void sk_psock_backlog(struct work_struct *work) len -= ret; } while (len); + /* The entire skb sent, clear state */ + sk_psock_skb_state(psock, state, 0, 0); skb = skb_dequeue(&psock->ingress_skb); kfree_skb(skb); } end: mutex_unlock(&psock->work_mutex); + sk_psock_put(psock->sk, psock); } struct sk_psock *sk_psock_init(struct sock *sk, int node) @@ -1012,7 +1033,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, off = stm->offset; len = stm->full_len; } - err = sk_psock_skb_ingress_self(psock, skb, off, len); + err = sk_psock_skb_ingress_self(psock, skb, off, len, false); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); diff --git a/net/core/sock.c b/net/core/sock.c index 168e7f42c054..d8c0650322ea 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3797,7 +3797,7 @@ static int assign_proto_idx(struct proto *prot) { prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR); - if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) { + if (unlikely(prot->inuse_idx == PROTO_INUSE_NR)) { pr_err("PROTO_INUSE_NR exhausted\n"); return -ENOSPC; } @@ -3808,7 +3808,7 @@ static int assign_proto_idx(struct proto *prot) static void release_proto_idx(struct proto *prot) { - if (prot->inuse_idx != PROTO_INUSE_NR - 1) + if (prot->inuse_idx != PROTO_INUSE_NR) clear_bit(prot->inuse_idx, proto_inuse_idx); } #else diff --git a/net/core/utils.c b/net/core/utils.c index 938495bc1d34..1eeb9131e2cf 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -473,11 +473,11 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, - __wsum diff, bool pseudohdr) + __wsum diff, bool pseudohdr, bool ipv6) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace_by_diff(sum, diff); - if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) + if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr && !ipv6) skb->csum = ~csum_sub(diff, skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); diff --git a/net/dsa/port.c b/net/dsa/port.c index 750fe68d9b2a..cd1741792f6a 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1599,6 +1599,21 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config, return pcs; } +static int dsa_port_phylink_mac_prepare(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + int err = 0; + + if (ds->ops->phylink_mac_prepare) + err = ds->ops->phylink_mac_prepare(ds, dp->index, mode, + interface); + + return err; +} + static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -1612,6 +1627,21 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } +static int dsa_port_phylink_mac_finish(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); + struct dsa_switch *ds = dp->ds; + int err = 0; + + if (ds->ops->phylink_mac_finish) + err = ds->ops->phylink_mac_finish(ds, dp->index, mode, + interface); + + return err; +} + static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); @@ -1667,7 +1697,9 @@ static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .validate = dsa_port_phylink_validate, .mac_select_pcs = dsa_port_phylink_mac_select_pcs, .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state, + .mac_prepare = dsa_port_phylink_mac_prepare, .mac_config = dsa_port_phylink_mac_config, + .mac_finish = dsa_port_phylink_mac_finish, .mac_an_restart = dsa_port_phylink_mac_an_restart, .mac_link_down = dsa_port_phylink_mac_link_down, .mac_link_up = dsa_port_phylink_mac_link_up, diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 89371b16416e..6a33f35a0f74 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -180,7 +180,7 @@ static int dsa_port_do_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid) err = ds->ops->tag_8021q_vlan_del(ds, port, vid); if (err) { - refcount_inc(&v->refcount); + refcount_set(&v->refcount, 1); return err; } diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index a65d62fb9009..04b57534fe4d 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -253,7 +253,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, int source_port; u8 *brcm_tag; - if (unlikely(!pskb_may_pull(skb, BRCM_LEG_PORT_ID))) + if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) return NULL; brcm_tag = dsa_etype_header_pos_rx(skb); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index e5efdf2817ef..98c064113882 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -384,7 +384,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ret = ops->prepare_data(req_info, reply_data, info); rtnl_unlock(); if (ret < 0) - goto err_cleanup; + goto err_dev; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; @@ -442,7 +442,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, NULL); rtnl_unlock(); if (ret < 0) - goto out; + goto out_cancel; ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr); if (ret < 0) goto out; @@ -451,6 +451,7 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); +out_cancel: ctx->reply_data->dev = NULL; if (ret < 0) genlmsg_cancel(skb, ehdr); @@ -636,7 +637,7 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, ethnl_init_reply_data(reply_data, ops, dev); ret = ops->prepare_data(req_info, reply_data, NULL); if (ret < 0) - goto err_cleanup; + goto err_rep; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; @@ -671,6 +672,7 @@ err_skb: err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); +err_rep: kfree(reply_data); kfree(req_info); return; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 419969b26822..8f5417ff355d 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -118,47 +118,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) } #ifdef CONFIG_INET_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, x->id.daddr.a4, @@ -171,20 +140,6 @@ static struct sock *esp_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -207,6 +162,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -391,6 +348,8 @@ static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 90ce87ffed46..7993ff46de23 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -829,19 +829,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, } } + if (cfg->fc_dst_len > 32) { + NL_SET_ERR_MSG(extack, "Invalid prefix length"); + err = -EINVAL; + goto errout; + } + + if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { + NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); + err = -EINVAL; + goto errout; + } + if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); - return -EINVAL; + err = -EINVAL; + goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - return -EINVAL; + err = -EINVAL; + goto errout; } if (!cfg->fc_table) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 513f475c6a53..298a9944a3d1 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -222,9 +222,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct net *net = sock_net(skb->sk); + struct fib4_rule *rule4 = (struct fib4_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct fib4_rule *rule4 = (struct fib4_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 77b97c48da5e..fa54b36b241a 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1192,22 +1192,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp, return 0; } -static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) -{ - if (plen > KEYLENGTH) { - NL_SET_ERR_MSG(extack, "Invalid prefix length"); - return false; - } - - if ((plen < KEYLENGTH) && (key << plen)) { - NL_SET_ERR_MSG(extack, - "Invalid prefix for given prefix length"); - return false; - } - - return true; -} - static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); @@ -1228,9 +1212,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); @@ -1723,9 +1704,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb, key = ntohl(cfg->fc_dst); - if (!fib_valid_key_len(key, plen, extack)) - return -EINVAL; - l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 321f509f2347..5e7cdcebd64f 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1218,22 +1218,37 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo) { unsigned int locksz = sizeof(spinlock_t); unsigned int i, nblocks = 1; + spinlock_t *ptr = NULL; - if (locksz != 0) { - /* allocate 2 cache lines or at least one spinlock per cpu */ - nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U); - nblocks = roundup_pow_of_two(nblocks * num_possible_cpus()); + if (locksz == 0) + goto set_mask; - /* no more locks than number of hash buckets */ - nblocks = min(nblocks, hashinfo->ehash_mask + 1); + /* Allocate 2 cache lines or at least one spinlock per cpu. */ + nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus(); - hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL); - if (!hashinfo->ehash_locks) - return -ENOMEM; + /* At least one page per NUMA node. */ + nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz); + + nblocks = roundup_pow_of_two(nblocks); + + /* No more locks than number of hash buckets. */ + nblocks = min(nblocks, hashinfo->ehash_mask + 1); - for (i = 0; i < nblocks; i++) - spin_lock_init(&hashinfo->ehash_locks[i]); + if (num_online_nodes() > 1) { + /* Use vmalloc() to allow NUMA policy to spread pages + * on all available nodes if desired. + */ + ptr = vmalloc_array(nblocks, locksz); + } + if (!ptr) { + ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL); + if (!ptr) + return -ENOMEM; } + for (i = 0; i < nblocks; i++) + spin_lock_init(&ptr[i]); + hashinfo->ehash_locks = ptr; +set_mask: hashinfo->ehash_locks_mask = nblocks - 1; return 0; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c82107bbd981..543d029102cf 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1580,7 +1580,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * so icmphdr does not in skb linear region and can not get icmp_type * by icmp_hdr(skb)->type. */ - if (sk->sk_type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_type == SOCK_RAW && + !(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH)) icmp_type = fl4->fl4_icmp_type; else icmp_type = icmp_hdr(skb)->type; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 80ccd6661aa3..deb08cab4464 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -415,7 +415,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, skb_dst_update_pmtu_no_confirm(skb, mtu); - if (!reply || skb->pkt_type == PACKET_HOST) + if (!reply) return 0; if (skb->protocol == htons(ETH_P_IP)) @@ -450,7 +450,7 @@ static const struct nla_policy geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, - [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ee0efd0efec4..c109bc376cc5 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -608,6 +608,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = 0; + fl4.fl4_icmp_code = 0; + if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 4574dcba9f19..870108101017 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -192,7 +192,11 @@ const __u8 ip_tos2prio[16] = { EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); +#ifndef CONFIG_PREEMPT_RT #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) +#else +#define RT_CACHE_STAT_INC(field) this_cpu_inc(rt_cache_stat.field) +#endif #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7d591a0cf0c7..b64d53590f25 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4745,6 +4745,12 @@ int tcp_abort(struct sock *sk, int err) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); + /* Avoid closing the same socket twice. */ + if (sk->sk_state == TCP_CLOSE) { + release_sock(sk); + return -ENOENT; + } + if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); @@ -4754,19 +4760,12 @@ int tcp_abort(struct sock *sk, int err) local_bh_disable(); bh_lock_sock(sk); - if (!sock_flag(sk, SOCK_DEAD)) { - WRITE_ONCE(sk->sk_err, err); - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - sk_error_report(sk); - if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC); - tcp_done(sk); - } + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); - tcp_write_queue_purge(sk); release_sock(sk); return 0; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index cb01c770d8cf..cbce1306bb08 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -3,6 +3,7 @@ #include <linux/tcp.h> #include <linux/rcupdate.h> #include <net/tcp.h> +#include <net/busy_poll.h> void tcp_fastopen_init_key_once(struct net *net) { @@ -279,6 +280,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, refcount_set(&req->rsk_refcnt, 2); + sk_mark_napi_id_set(child, skb); + /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3b81f6df829f..5ee1e1c2082c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -404,6 +404,20 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr return false; } +static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count) +{ + tp->delivered_ce += ecn_count; +} + +/* Updates the delivered and delivered_ce counts */ +static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, + bool ece_ack) +{ + tp->delivered += delivered; + if (ece_ack) + tcp_count_delivered_ce(tp, delivered); +} + /* Buffer size and advertised window tuning. * * 1. Tuning sk->sk_sndbuf, when connection enters established state. @@ -635,10 +649,12 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss); */ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) { - u32 new_sample = tp->rcv_rtt_est.rtt_us; - long m = sample; + u32 new_sample, old_sample = tp->rcv_rtt_est.rtt_us; + long m = sample << 3; - if (new_sample != 0) { + if (old_sample == 0 || m < old_sample) { + new_sample = m; + } else { /* If we sample in larger samples in the non-timestamp * case, we could grossly overestimate the RTT especially * with chatty applications or bulk transfer apps which @@ -649,17 +665,9 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep) * else with timestamps disabled convergence takes too * long. */ - if (!win_dep) { - m -= (new_sample >> 3); - new_sample += m; - } else { - m <<= 3; - if (m < new_sample) - new_sample = m; - } - } else { - /* No previous measure. */ - new_sample = m << 3; + if (win_dep) + return; + new_sample = old_sample - (old_sample >> 3) + sample; } tp->rcv_rtt_est.rtt_us = new_sample; @@ -1119,15 +1127,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb) } } -/* Updates the delivered and delivered_ce counts */ -static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, - bool ece_ack) -{ - tp->delivered += delivered; - if (ece_ack) - tp->delivered_ce += delivered; -} - /* This procedure tags the retransmission queue when SACKs arrive. * * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L). @@ -2442,20 +2441,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp) { const struct sock *sk = (const struct sock *)tp; - if (tp->retrans_stamp && - tcp_tsopt_ecr_before(tp, tp->retrans_stamp)) - return true; /* got echoed TS before first retransmission */ + /* Received an echoed timestamp before the first retransmission? */ + if (tp->retrans_stamp) + return tcp_tsopt_ecr_before(tp, tp->retrans_stamp); + + /* We set tp->retrans_stamp upon the first retransmission of a loss + * recovery episode, so normally if tp->retrans_stamp is 0 then no + * retransmission has happened yet (likely due to TSQ, which can cause + * fast retransmits to be delayed). So if snd_una advanced while + * (tp->retrans_stamp is 0 then apparently a packet was merely delayed, + * not lost. But there are exceptions where we retransmit but then + * clear tp->retrans_stamp, so we check for those exceptions. + */ - /* Check if nothing was retransmitted (retrans_stamp==0), which may - * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp - * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear - * retrans_stamp even if we had retransmitted the SYN. + /* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen() + * clears tp->retrans_stamp when snd_una == high_seq. */ - if (!tp->retrans_stamp && /* no record of a retransmit/SYN? */ - sk->sk_state != TCP_SYN_SENT) /* not the FLAG_SYN_ACKED case? */ - return true; /* nothing was retransmitted */ + if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq)) + return false; - return false; + /* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp + * when setting FLAG_SYN_ACKED is set, even if the SYN was + * retransmitted. + */ + if (sk->sk_state == TCP_SYN_SENT) + return false; + + return true; /* tp->retrans_stamp is zero; no retransmit yet */ } /* Undo procedures. */ @@ -3783,12 +3795,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) } } -static inline void tcp_in_ack_event(struct sock *sk, u32 flags) +static void tcp_in_ack_event(struct sock *sk, int flag) { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_ca_ops->in_ack_event) - icsk->icsk_ca_ops->in_ack_event(sk, flags); + if (icsk->icsk_ca_ops->in_ack_event) { + u32 ack_ev_flags = 0; + + if (flag & FLAG_WIN_UPDATE) + ack_ev_flags |= CA_ACK_WIN_UPDATE; + if (flag & FLAG_SLOWPATH) { + ack_ev_flags |= CA_ACK_SLOWPATH; + if (flag & FLAG_ECE) + ack_ev_flags |= CA_ACK_ECE; + } + + icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags); + } } /* Congestion control has updated the cwnd already. So if we're in @@ -3905,12 +3928,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; - tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS); } else { - u32 ack_ev_flags = CA_ACK_SLOWPATH; - if (ack_seq != TCP_SKB_CB(skb)->end_seq) flag |= FLAG_DATA; else @@ -3922,19 +3941,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, &sack_state); - if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) { + if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; - ack_ev_flags |= CA_ACK_ECE; - } if (sack_state.sack_delivered) tcp_count_delivered(tp, sack_state.sack_delivered, flag & FLAG_ECE); - - if (flag & FLAG_WIN_UPDATE) - ack_ev_flags |= CA_ACK_WIN_UPDATE; - - tcp_in_ack_event(sk, ack_ev_flags); } /* This is a deviation from RFC3168 since it states that: @@ -3961,6 +3973,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_rack_update_reo_wnd(sk, &rs); + tcp_in_ack_event(sk, flag); + if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); @@ -3992,6 +4006,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + tcp_in_ack_event(sk, flag); /* If data was DSACKed, see if we can undo a cwnd reduction. */ if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag, @@ -4819,8 +4834,9 @@ static void tcp_ofo_queue(struct sock *sk) if (before(TCP_SKB_CB(skb)->seq, dsack_high)) { __u32 dsack = dsack_high; + if (before(TCP_SKB_CB(skb)->end_seq, dsack_high)) - dsack_high = TCP_SKB_CB(skb)->end_seq; + dsack = TCP_SKB_CB(skb)->end_seq; tcp_dsack_extend(sk, TCP_SKB_CB(skb)->seq, dsack); } p = rb_next(p); @@ -6631,6 +6647,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); + if (tp->rx_opt.tstamp_ok) + tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; + if (req) { tcp_rcv_synrecv_state_fastopen(sk); } else { @@ -6655,9 +6674,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - if (tp->rx_opt.tstamp_ok) - tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - if (!inet_csk(sk)->icsk_ca_ops->cong_control) tcp_update_pacing_rate(sk); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 72a645bf05c9..ce84073e0b7b 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -12,12 +12,15 @@ #include <net/tcp.h> #include <net/protocol.h> -static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq, +static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb, unsigned int seq, unsigned int mss) { + u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP; + u32 ts_seq = skb_shinfo(gso_skb)->tskey; + while (skb) { if (before(ts_seq, seq + mss)) { - skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP; + skb_shinfo(skb)->tx_flags |= flags; skb_shinfo(skb)->tskey = ts_seq; return; } @@ -119,8 +122,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, th = tcp_hdr(skb); seq = ntohl(th->seq); - if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP)) - tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss); + if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP)) + tcp_gso_tstamp(segs, gso_skb, seq, mss); newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta)); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 88da11922d67..da96252dd8a1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1437,12 +1437,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb) } /* fully reclaim rmem/fwd memory allocated for skb */ -static void udp_rmem_release(struct sock *sk, int size, int partial, - bool rx_queue_lock_held) +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) { struct udp_sock *up = udp_sk(sk); struct sk_buff_head *sk_queue; - int amt; + unsigned int amt; if (likely(partial)) { up->forward_deficit += size; @@ -1462,10 +1462,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (!rx_queue_lock_held) spin_lock(&sk_queue->lock); - - sk_forward_alloc_add(sk, size); - amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); - sk_forward_alloc_add(sk, -amt); + amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); + sk_forward_alloc_add(sk, size - amt); if (amt) __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); @@ -1650,7 +1648,7 @@ EXPORT_SYMBOL_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, - int *total) + unsigned int *total) { struct sk_buff *skb; @@ -1683,8 +1681,8 @@ static int first_packet_length(struct sock *sk) { struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - int total = 0; int res; spin_lock_bh(&rcvq->lock); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 1456c8c2b8db..1a51c4b44c00 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -246,6 +246,62 @@ static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs) return segs; } +static void __udpv6_gso_segment_csum(struct sk_buff *seg, + struct in6_addr *oldip, + const struct in6_addr *newip, + __be16 *oldport, __be16 newport) +{ + struct udphdr *uh = udp_hdr(seg); + + if (ipv6_addr_equal(oldip, newip) && *oldport == newport) + return; + + if (uh->check) { + inet_proto_csum_replace16(&uh->check, seg, oldip->s6_addr32, + newip->s6_addr32, true); + + inet_proto_csum_replace2(&uh->check, seg, *oldport, newport, + false); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + + *oldip = *newip; + *oldport = newport; +} + +static struct sk_buff *__udpv6_gso_segment_list_csum(struct sk_buff *segs) +{ + const struct ipv6hdr *iph; + const struct udphdr *uh; + struct ipv6hdr *iph2; + struct sk_buff *seg; + struct udphdr *uh2; + + seg = segs; + uh = udp_hdr(seg); + iph = ipv6_hdr(seg); + uh2 = udp_hdr(seg->next); + iph2 = ipv6_hdr(seg->next); + + if (!(*(const u32 *)&uh->source ^ *(const u32 *)&uh2->source) && + ipv6_addr_equal(&iph->saddr, &iph2->saddr) && + ipv6_addr_equal(&iph->daddr, &iph2->daddr)) + return segs; + + while ((seg = seg->next)) { + uh2 = udp_hdr(seg); + iph2 = ipv6_hdr(seg); + + __udpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr, + &uh2->source, uh->source); + __udpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr, + &uh2->dest, uh->dest); + } + + return segs; +} + static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, netdev_features_t features, bool is_ipv6) @@ -258,7 +314,10 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); - return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb); + if (is_ipv6) + return __udpv6_gso_segment_list_csum(skb); + else + return __udpv4_gso_segment_list_csum(skb); } struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, @@ -272,6 +331,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, bool copy_dtor; __sum16 check; __be16 newlen; + int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) @@ -294,6 +354,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) return __udp_gso_segment_list(gso_skb, features, is_ipv6); + ret = __skb_linearize(gso_skb); + if (ret) + return ERR_PTR(ret); + /* Setup csum, as fraglist skips this in udp4_gro_receive. */ gso_skb->csum_start = skb_transport_header(gso_skb) - gso_skb->head; gso_skb->csum_offset = offsetof(struct udphdr, check); @@ -314,13 +378,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, /* clear destructor to avoid skb_segment assigning it to tail */ copy_dtor = gso_skb->destructor == sock_wfree; - if (copy_dtor) + if (copy_dtor) { gso_skb->destructor = NULL; + gso_skb->sk = NULL; + } segs = skb_segment(gso_skb, features); if (IS_ERR_OR_NULL(segs)) { - if (copy_dtor) + if (copy_dtor) { gso_skb->destructor = sock_wfree; + gso_skb->sk = sk; + } return segs; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f52527c86e71..69915bb8b96d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3162,16 +3162,13 @@ static void add_v4_addrs(struct inet6_dev *idev) struct in6_addr addr; struct net_device *dev; struct net *net = dev_net(idev->dev); - int scope, plen, offset = 0; + int scope, plen; u32 pflags = 0; ASSERT_RTNL(); memset(&addr, 0, sizeof(struct in6_addr)); - /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */ - if (idev->dev->addr_len == sizeof(struct in6_addr)) - offset = sizeof(struct in6_addr) - 4; - memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); + memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4); if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { scope = IPV6_ADDR_COMPATv4; @@ -3475,21 +3472,22 @@ static void addrconf_gre_config(struct net_device *dev) ASSERT_RTNL(); - idev = ipv6_find_idev(dev); - if (IS_ERR(idev)) { - pr_debug("%s: add_dev failed\n", __func__); + idev = addrconf_add_dev(dev); + if (IS_ERR(idev)) return; - } - if (dev->type == ARPHRD_ETHER) { + /* Generate the IPv6 link-local address using addrconf_addr_gen(), + * unless we have an IPv4 GRE device not bound to an IP address and + * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this + * case). Such devices fall back to add_v4_addrs() instead. + */ + if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 && + idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) { addrconf_addr_gen(idev, true); return; } add_v4_addrs(idev); - - if (dev->flags & IFF_POINTOPOINT) - addrconf_add_mroute(dev); } #endif @@ -5718,6 +5716,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } +static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb, + struct inet6_dev *idev) +{ + struct nlattr *nla; + + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); + + nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); + if (!nla) + goto nla_put_failure; + snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, u32 ext_filter_mask) { @@ -5739,18 +5758,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, /* XXX - MC not implemented */ - if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) - return 0; - - nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla)); - - nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64)); - if (!nla) - goto nla_put_failure; - snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla)); + if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) { + if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0) + goto nla_put_failure; + } nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr)); if (!nla) diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1578ed9e97d8..24666291c54a 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1075,8 +1075,13 @@ static int calipso_sock_getattr(struct sock *sk, struct ipv6_opt_hdr *hop; int opt_len, len, ret_val = -ENOMSG, offset; unsigned char *opt; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + + if (!pinfo) + return -EAFNOSUPPORT; + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; @@ -1128,8 +1133,13 @@ static int calipso_sock_setattr(struct sock *sk, { int ret_val; struct ipv6_opt_hdr *old, *new; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + if (!pinfo) + return -EAFNOSUPPORT; + + txopts = txopt_get(pinfo); old = NULL; if (txopts) old = txopts->hopopt; @@ -1156,8 +1166,13 @@ static int calipso_sock_setattr(struct sock *sk, static void calipso_sock_delattr(struct sock *sk) { struct ipv6_opt_hdr *new_hop; - struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk)); + struct ipv6_pinfo *pinfo = inet6_sk(sk); + struct ipv6_txoptions *txopts; + if (!pinfo) + return; + + txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; @@ -1195,6 +1210,10 @@ static int calipso_req_setattr(struct request_sock *req, struct ipv6_opt_hdr *old, *new; struct sock *sk = sk_to_full_sk(req_to_sk(req)); + /* sk is NULL for SYN+ACK w/ SYN Cookie */ + if (!sk) + return -ENOMEM; + if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt) old = req_inet->ipv6_opt->hopopt; else @@ -1235,6 +1254,10 @@ static void calipso_req_delattr(struct request_sock *req) struct ipv6_txoptions *txopts; struct sock *sk = sk_to_full_sk(req_to_sk(req)); + /* sk is NULL for SYN+ACK w/ SYN Cookie */ + if (!sk) + return; + if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt) return; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index a021c88d3d9b..085a83b807af 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -135,47 +135,16 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) } #ifdef CONFIG_INET6_ESPINTCP -struct esp_tcp_sk { - struct sock *sk; - struct rcu_head rcu; -}; - -static void esp_free_tcp_sk(struct rcu_head *head) -{ - struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); - - sock_put(esk->sk); - kfree(esk); -} - static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) { struct xfrm_encap_tmpl *encap = x->encap; struct net *net = xs_net(x); - struct esp_tcp_sk *esk; __be16 sport, dport; - struct sock *nsk; struct sock *sk; - sk = rcu_dereference(x->encap_sk); - if (sk && sk->sk_state == TCP_ESTABLISHED) - return sk; - spin_lock_bh(&x->lock); sport = encap->encap_sport; dport = encap->encap_dport; - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (sk && sk == nsk) { - esk = kmalloc(sizeof(*esk), GFP_ATOMIC); - if (!esk) { - spin_unlock_bh(&x->lock); - return ERR_PTR(-ENOMEM); - } - RCU_INIT_POINTER(x->encap_sk, NULL); - esk->sk = sk; - call_rcu(&esk->rcu, esp_free_tcp_sk); - } spin_unlock_bh(&x->lock); sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo, &x->id.daddr.in6, @@ -188,20 +157,6 @@ static struct sock *esp6_find_tcp_sk(struct xfrm_state *x) return ERR_PTR(-EINVAL); } - spin_lock_bh(&x->lock); - nsk = rcu_dereference_protected(x->encap_sk, - lockdep_is_held(&x->lock)); - if (encap->encap_sport != sport || - encap->encap_dport != dport) { - sock_put(sk); - sk = nsk ?: ERR_PTR(-EREMCHG); - } else if (sk == nsk) { - sock_put(sk); - } else { - rcu_assign_pointer(x->encap_sk, sk); - } - spin_unlock_bh(&x->lock); - return sk; } @@ -224,6 +179,8 @@ static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) err = espintcp_push_skb(sk, skb); bh_unlock_sock(sk); + sock_put(sk); + out: rcu_read_unlock(); return err; @@ -427,6 +384,8 @@ static struct ip_esp_hdr *esp6_output_tcp_encap(struct xfrm_state *x, if (IS_ERR(sk)) return ERR_CAST(sk); + sock_put(sk); + *lenp = htons(len); esph = (struct ip_esp_hdr *)(lenp + 1); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 6eeab21512ba..e0f0c5f8cccd 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -350,9 +350,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb, struct netlink_ext_ack *extack) { + struct fib6_rule *rule6 = (struct fib6_rule *)rule; + struct net *net = rule->fr_net; int err = -EINVAL; - struct net *net = sock_net(skb->sk); - struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (!inet_validate_dscp(frh->tos)) { NL_SET_ERR_MSG(extack, diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index 95e9146918cc..b8d43ed4689d 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -86,7 +86,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&th->check, skb, - diff, true); + diff, true, true); } break; case NEXTHDR_UDP: @@ -97,7 +97,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&uh->check, skb, - diff, true); + diff, true, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } @@ -111,7 +111,7 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, - diff, true); + diff, true, true); } break; } diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 9d37f7164e73..7397f764c66c 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -88,13 +88,15 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) goto drop; } - if (ilwt->connected) { + /* cache only if we don't create a dst reference loop */ + if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) { local_bh_disable(); dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr); local_bh_enable(); } } + skb_dst_drop(skb); skb_dst_set(skb, dst); return dst_output(net, sk, skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b6a7cbd6bee0..bb51a911a6ce 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -438,15 +438,17 @@ struct fib6_dump_arg { static int fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { enum fib_event_type fib_event = FIB_EVENT_ENTRY_REPLACE; + unsigned int nsiblings; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; - if (rt->fib6_nsiblings) + nsiblings = READ_ONCE(rt->fib6_nsiblings); + if (nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, - rt->fib6_nsiblings, + nsiblings, arg->extack); else err = call_fib6_entry_notifier(arg->nb, fib_event, rt, @@ -1119,7 +1121,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (rt6_duplicate_nexthop(iter, rt)) { if (rt->fib6_nsiblings) - rt->fib6_nsiblings = 0; + WRITE_ONCE(rt->fib6_nsiblings, 0); if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) @@ -1145,7 +1147,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) - rt->fib6_nsiblings++; + WRITE_ONCE(rt->fib6_nsiblings, + rt->fib6_nsiblings + 1); } if (iter->fib6_metric > rt->fib6_metric) @@ -1195,7 +1198,8 @@ next_iter: fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, &rt->fib6_siblings, fib6_siblings) { - sibling->fib6_nsiblings++; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings + 1); BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } @@ -1240,8 +1244,9 @@ add: list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) - sibling->fib6_nsiblings--; - rt->fib6_nsiblings = 0; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings - 1); + WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); return err; @@ -1953,8 +1958,9 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, notify_del = true; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) - sibling->fib6_nsiblings--; - rt->fib6_nsiblings = 0; + WRITE_ONCE(sibling->fib6_nsiblings, + sibling->fib6_nsiblings - 1); + WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 3ee345672849..171a5c1afefe 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -134,7 +134,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { - skb_reset_transport_header(skb); + if (!skb_reset_transport_header_careful(skb)) + goto out; + segs = ops->callbacks.gso_segment(skb, features); if (!segs) skb->network_header = skb_mac_header(skb) + nhoff - skb->head; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d7f7a714bd23..f7a225da8525 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1985,7 +1985,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; - if (sk->sk_socket->type == SOCK_RAW && !inet_sk(sk)->hdrincl) + if (sk->sk_socket->type == SOCK_RAW && + !(fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH)) icmp6_type = fl6->fl6_icmp_type; else icmp6_type = icmp6_hdr(skb)->icmp6_type; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 138f6aee70af..06f66531628f 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2045,6 +2045,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, struct sk_buff *skb, int vifi) { struct vif_device *vif = &mrt->vif_table[vifi]; + struct net_device *indev = skb->dev; struct net_device *vif_dev; struct ipv6hdr *ipv6h; struct dst_entry *dst; @@ -2107,7 +2108,7 @@ static int ip6mr_forward2(struct net *net, struct mr_table *mrt, IP6CB(skb)->flags |= IP6SKB_FORWARDED; return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, - net, NULL, skb, skb->dev, vif_dev, + net, NULL, skb, indev, skb->dev, ip6mr_forward2_finish); out_free: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a1b3f3e7921f..e9e59a83ba9b 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -803,8 +803,8 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) } else { im->mca_crcount = idev->mc_qrv; } - in6_dev_put(pmc->idev); ip6_mc_clear_src(pmc); + in6_dev_put(pmc->idev); kfree_rcu(pmc, rcu); } } diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 857713d7a38a..d873658fc821 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -163,20 +163,20 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct ip6_fraglist_iter iter; struct sk_buff *frag2; - if (first_len - hlen > mtu || - skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) + if (first_len - hlen > mtu) goto blackhole; - if (skb_cloned(skb)) + if (skb_cloned(skb) || + skb_headroom(skb) < (hroom + sizeof(struct frag_hdr))) goto slow_path; skb_walk_frags(skb, frag2) { - if (frag2->len > mtu || - skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr))) + if (frag2->len > mtu) goto blackhole; /* Partially cloned skb? */ - if (skb_shared(frag2)) + if (skb_shared(frag2) || + skb_headroom(frag2) < (hlen + hroom + sizeof(struct frag_hdr))) goto slow_path; } diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index a7690ec62325..9ea5ef56cb27 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -103,6 +103,10 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, struct sk_buff *data_skb = NULL; int doff = 0; int thoff = 0, tproto; +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + enum ip_conntrack_info ctinfo; + struct nf_conn const *ct; +#endif tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL); if (tproto < 0) { @@ -136,6 +140,25 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, return NULL; } +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + /* Do the lookup with the original socket address in + * case this is a reply packet of an established + * SNAT-ted connection. + */ + ct = nf_ct_get(skb, &ctinfo); + if (ct && + ((tproto != IPPROTO_ICMPV6 && + ctinfo == IP_CT_ESTABLISHED_REPLY) || + (tproto == IPPROTO_ICMPV6 && + ctinfo == IP_CT_RELATED_REPLY)) && + (ct->status & IPS_SRC_NAT_DONE)) { + daddr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6; + dport = (tproto == IPPROTO_TCP) ? + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port : + ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; + } +#endif + return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr, sport, dport, indev); } diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index c9f1634b3838..a89ce0fbfe4b 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -158,6 +158,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, { const struct nft_fib *priv = nft_expr_priv(expr); int noff = skb_network_offset(pkt->skb); + const struct net_device *found = NULL; const struct net_device *oif = NULL; u32 *dest = ®s->data[priv->dreg]; struct ipv6hdr *iph, _iph; @@ -202,11 +203,15 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL)) goto put_rt_err; - if (oif && oif != rt->rt6i_idev->dev && - l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex) - goto put_rt_err; + if (!oif) { + found = rt->rt6i_idev->dev; + } else { + if (oif == rt->rt6i_idev->dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == oif->ifindex) + found = oif; + } - nft_fib_store_result(dest, priv, rt->rt6i_idev->dev); + nft_fib_store_result(dest, priv, found); put_rt_err: ip6_rt_put(rt); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 17918f411386..07e3d59c2405 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -416,12 +416,37 @@ static bool rt6_check_expired(const struct rt6_info *rt) return false; } +static struct fib6_info * +rt6_multipath_first_sibling_rcu(const struct fib6_info *rt) +{ + struct fib6_info *iter; + struct fib6_node *fn; + + fn = rcu_dereference(rt->fib6_node); + if (!fn) + goto out; + iter = rcu_dereference(fn->leaf); + if (!iter) + goto out; + + while (iter) { + if (iter->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(iter)) + return iter; + iter = rcu_dereference(iter->fib6_next); + } + +out: + return NULL; +} + void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { - struct fib6_info *match = res->f6i; + struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; + int hash; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; @@ -444,16 +469,25 @@ void fib6_select_path(const struct net *net, struct fib6_result *res, return; } - if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) + first = rt6_multipath_first_sibling_rcu(match); + if (!first) goto out; - list_for_each_entry_rcu(sibling, &match->fib6_siblings, + hash = fl6->mp_hash; + if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) { + if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif, + strict) >= 0) + match = first; + goto out; + } + + list_for_each_entry_rcu(sibling, &first->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); - if (fl6->mp_hash > nh_upper_bound) + if (hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; @@ -3637,7 +3671,8 @@ out: in6_dev_put(idev); if (err) { - lwtstate_put(fib6_nh->fib_nh_lws); + fib_nh_common_release(&fib6_nh->nh_common); + fib6_nh->nh_common.nhc_pcpu_rth_output = NULL; fib6_nh->fib_nh_lws = NULL; dev_put(dev); } @@ -3797,10 +3832,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); + err = -EINVAL; goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); + err = -ENOENT; goto out_free; } rt->nh = nh; @@ -5196,7 +5233,8 @@ static void ip6_route_mpath_notify(struct fib6_info *rt, */ rcu_read_lock(); - if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { + if ((nlflags & NLM_F_APPEND) && rt_last && + READ_ONCE(rt_last->fib6_nsiblings)) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); @@ -5543,32 +5581,34 @@ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) static size_t rt6_nlmsg_size(struct fib6_info *f6i) { + struct fib6_info *sibling; + struct fib6_nh *nh; int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); - } else { - struct fib6_nh *nh = f6i->fib6_nh; - struct fib6_info *sibling; - - nexthop_len = 0; - if (f6i->fib6_nsiblings) { - rt6_nh_nlmsg_size(nh, &nexthop_len); - - rcu_read_lock(); + goto common; + } - list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, - fib6_siblings) { - rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); - } + rcu_read_lock(); +retry: + nh = f6i->fib6_nh; + nexthop_len = 0; + if (READ_ONCE(f6i->fib6_nsiblings)) { + rt6_nh_nlmsg_size(nh, &nexthop_len); - rcu_read_unlock(); + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { + rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); + if (!READ_ONCE(f6i->fib6_nsiblings)) + goto retry; } - nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } - + rcu_read_unlock(); + nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); +common: return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ @@ -5727,7 +5767,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (dst->lwtstate && lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; - } else if (rt->fib6_nsiblings) { + } else if (READ_ONCE(rt->fib6_nsiblings)) { struct fib6_info *sibling; struct nlattr *mp; @@ -5829,16 +5869,21 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i, if (f6i->fib6_nh->fib_nh_dev == dev) return true; - if (f6i->fib6_nsiblings) { - struct fib6_info *sibling, *next_sibling; + if (READ_ONCE(f6i->fib6_nsiblings)) { + const struct fib6_info *sibling; - list_for_each_entry_safe(sibling, next_sibling, - &f6i->fib6_siblings, fib6_siblings) { - if (sibling->fib6_nh->fib_nh_dev == dev) + rcu_read_lock(); + list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, + fib6_siblings) { + if (sibling->fib6_nh->fib_nh_dev == dev) { + rcu_read_unlock(); return true; + } + if (!READ_ONCE(f6i->fib6_nsiblings)) + break; } + rcu_read_unlock(); } - return false; } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 862ac1e2e191..952ec785853a 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -129,13 +129,13 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, struct dst_entry *cache_dst) { struct ipv6_rpl_sr_hdr *isrh, *csrh; - const struct ipv6hdr *oldhdr; + struct ipv6hdr oldhdr; struct ipv6hdr *hdr; unsigned char *buf; size_t hdrlen; int err; - oldhdr = ipv6_hdr(skb); + memcpy(&oldhdr, ipv6_hdr(skb), sizeof(oldhdr)); buf = kcalloc(struct_size(srh, segments.addr, srh->segments_left), 2, GFP_ATOMIC); if (!buf) @@ -147,7 +147,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, memcpy(isrh, srh, sizeof(*isrh)); memcpy(isrh->rpl_segaddr, &srh->rpl_segaddr[1], (srh->segments_left - 1) * 16); - isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr->daddr; + isrh->rpl_segaddr[srh->segments_left - 1] = oldhdr.daddr; ipv6_rpl_srh_compress(csrh, isrh, &srh->rpl_segaddr[0], isrh->segments_left - 1); @@ -169,7 +169,7 @@ static int rpl_do_srh_inline(struct sk_buff *skb, const struct rpl_lwt *rlwt, skb_mac_header_rebuild(skb); hdr = ipv6_hdr(skb); - memmove(hdr, oldhdr, sizeof(*hdr)); + memmove(hdr, &oldhdr, sizeof(*hdr)); isrh = (void *)hdr + sizeof(*hdr); memcpy(isrh, csrh, hdrlen); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 33cb0381b574..b7d9a68a265d 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -1250,10 +1250,8 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = { [SEG6_LOCAL_SRH] = { .type = NLA_BINARY }, [SEG6_LOCAL_TABLE] = { .type = NLA_U32 }, [SEG6_LOCAL_VRFTABLE] = { .type = NLA_U32 }, - [SEG6_LOCAL_NH4] = { .type = NLA_BINARY, - .len = sizeof(struct in_addr) }, - [SEG6_LOCAL_NH6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr) }, + [SEG6_LOCAL_NH4] = NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)), + [SEG6_LOCAL_NH6] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [SEG6_LOCAL_IIF] = { .type = NLA_U32 }, [SEG6_LOCAL_OIF] = { .type = NLA_U32 }, [SEG6_LOCAL_BPF] = { .type = NLA_NESTED }, diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 447031c5eac4..39c7d62c933f 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -888,15 +888,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (sk->sk_type != SOCK_STREAM) goto copy_uaddr; + /* Partial read */ + if (used + offset < skb_len) + continue; + if (!(flags & MSG_PEEK)) { skb_unlink(skb, &sk->sk_receive_queue); kfree_skb(skb); *seq = 0; } - - /* Partial read */ - if (used + offset < skb_len) - continue; } while (len > 0); out: diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index 06fb8e6944b0..7a0cae9a8111 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -24,7 +24,7 @@ #include <net/llc_s_ac.h> #include <net/llc_s_ev.h> #include <net/llc_sap.h> - +#include <net/sock.h> /** * llc_sap_action_unitdata_ind - forward UI PDU to network layer @@ -40,6 +40,26 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb) return 0; } +static int llc_prepare_and_xmit(struct sk_buff *skb) +{ + struct llc_sap_state_ev *ev = llc_sap_ev(skb); + struct sk_buff *nskb; + int rc; + + rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); + if (rc) + return rc; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + if (skb->sk) + skb_set_owner_w(nskb, skb->sk); + + return dev_queue_xmit(nskb); +} + /** * llc_sap_action_send_ui - sends UI PDU resp to UNITDATA REQ to MAC layer * @sap: SAP @@ -52,17 +72,12 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb) int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); - rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) { - skb_get(skb); - rc = dev_queue_xmit(skb); - } - return rc; + + return llc_prepare_and_xmit(skb); } /** @@ -77,17 +92,12 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); - rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) { - skb_get(skb); - rc = dev_queue_xmit(skb); - } - return rc; + + return llc_prepare_and_xmit(skb); } /** @@ -133,17 +143,12 @@ out: int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap, ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); - rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) { - skb_get(skb); - rc = dev_queue_xmit(skb); - } - return rc; + + return llc_prepare_and_xmit(skb); } int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 8a3af4144d3f..4cd413bd764f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1984,8 +1984,6 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, u32 info_flags, u32 ctrl_flags, u64 *cookie); -void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, - struct sk_buff_head *skbs); struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 8861f63e2cfb..fc60e80088a3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -688,6 +688,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ieee80211_txq_remove_vlan(local, sdata); + if (sdata->vif.txq) + ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq)); + sdata->bss = NULL; if (local->open_count == 0) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 9b1ce7c3925a..da9e152a7aab 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -365,6 +365,12 @@ u32 airtime_link_metric_get(struct ieee80211_local *local, return (u32)result; } +/* Check that the first metric is at least 10% better than the second one */ +static bool is_metric_better(u32 x, u32 y) +{ + return (x < y) && (x < (y - x / 10)); +} + /** * hwmp_route_info_get - Update routing info to originator and transmitter * @@ -455,8 +461,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, (mpath->sn == orig_sn && (rcu_access_pointer(mpath->next_hop) != sta ? - mult_frac(new_metric, 10, 9) : - new_metric) >= mpath->metric)) { + !is_metric_better(new_metric, mpath->metric) : + new_metric >= mpath->metric))) { process = false; fresh_info = false; } @@ -526,8 +532,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, if ((mpath->flags & MESH_PATH_FIXED) || ((mpath->flags & MESH_PATH_ACTIVE) && ((rcu_access_pointer(mpath->next_hop) != sta ? - mult_frac(last_hop_metric, 10, 9) : - last_hop_metric) > mpath->metric))) + !is_metric_better(last_hop_metric, mpath->metric) : + last_hop_metric > mpath->metric)))) fresh_info = false; } else { mpath = mesh_path_add(sdata, ta); @@ -619,7 +625,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, mesh_path_add_gate(mpath); } rcu_read_unlock(); - } else { + } else if (ifmsh->mshcfg.dot11MeshForwarding) { rcu_read_lock(); mpath = mesh_path_lookup(sdata, target_addr); if (mpath) { @@ -637,6 +643,8 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, } } rcu_read_unlock(); + } else { + forward = false; } if (reply) { @@ -654,7 +662,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, } } - if (forward && ifmsh->mshcfg.dot11MeshForwarding) { + if (forward) { u32 preq_id; u8 hopcount; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 9a5530ca2f6b..b300972c3150 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2896,7 +2896,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (tx) ieee80211_flush_queues(local, sdata, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); + if (tx || frame_buf) + drv_mgd_complete_tx(sdata->local, sdata, &info); /* clear AP addr only after building the needed mgmt frames */ eth_zero_addr(sdata->deflink.u.mgd.bssid); @@ -7311,7 +7312,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); - drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index b6077a97af1d..8c9267acb227 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4336,6 +4336,10 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx) if (!multicast && !ether_addr_equal(sdata->dev->dev_addr, hdr->addr1)) return false; + /* reject invalid/our STA address */ + if (!is_valid_ether_addr(hdr->addr2) || + ether_addr_equal(sdata->dev->dev_addr, hdr->addr2)) + return false; if (!rx->sta) { int rate_idx; if (status->encoding != RX_ENC_LEGACY) diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3f9ddd7f04b6..3a96aa306616 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -1294,3 +1294,4 @@ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, while ((skb = __skb_dequeue(skbs))) ieee80211_free_txskb(hw, skb); } +EXPORT_SYMBOL(ieee80211_purge_tx_queue); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index f4b4d25eef95..04531d18fa93 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1351,7 +1351,7 @@ int ieee80211_tdls_oper(struct wiphy *wiphy, struct net_device *dev, if (!(wiphy->flags & WIPHY_FLAG_SUPPORTS_TDLS)) return -ENOTSUPP; - if (sdata->vif.type != NL80211_IFTYPE_STATION) + if (sdata->vif.type != NL80211_IFTYPE_STATION || !sdata->vif.cfg.assoc) return -EINVAL; switch (oper) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 62b2817df2ba..e6cf5ab928a6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -644,6 +644,12 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) else tx->key = NULL; + if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { + if (tx->key && tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) + info->control.hw_key = &tx->key->conf; + return TX_CONTINUE; + } + if (tx->key) { bool skip_hw = false; @@ -1467,7 +1473,7 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, { struct fq *fq = &local->fq; struct fq_tin *tin = &txqi->tin; - u32 flow_idx = fq_flow_idx(fq, skb); + u32 flow_idx; ieee80211_set_skb_enqueue_time(skb); @@ -1483,6 +1489,7 @@ static void ieee80211_txq_enqueue(struct ieee80211_local *local, IEEE80211_TX_INTCFL_NEED_TXPROCESSING; __skb_queue_tail(&txqi->frags, skb); } else { + flow_idx = fq_flow_idx(fq, skb); fq_tin_enqueue(fq, tin, flow_idx, skb, fq_skb_free_func); } @@ -3800,6 +3807,7 @@ begin: * The key can be removed while the packet was queued, so need to call * this here to get the current key. */ + info->control.hw_key = NULL; r = ieee80211_tx_h_select_key(&tx); if (r != TX_CONTINUE) { ieee80211_free_txskb(&local->hw, skb); @@ -4024,7 +4032,9 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw, spin_lock_bh(&local->active_txq_lock[txq->ac]); - has_queue = force || txq_has_queue(txq); + has_queue = force || + (!test_bit(IEEE80211_TXQ_STOP, &txqi->flags) && + txq_has_queue(txq)); if (list_empty(&txqi->schedule_order) && (has_queue || ieee80211_txq_keep_active(txqi))) { /* If airtime accounting is active, always enqueue STAs at the diff --git a/net/mac80211/util.c b/net/mac80211/util.c index e8326e09d1b3..e60c8607e4b6 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -4452,7 +4452,7 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local, { u64 tsf = drv_get_tsf(local, sdata); u64 dtim_count = 0; - u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; + u32 beacon_int = sdata->vif.bss_conf.beacon_int * 1024; u8 dtim_period = sdata->vif.bss_conf.dtim_period; struct ps_data *ps; u8 bcns_from_dtim; diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 2316e7772b78..6a963eac1cc2 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -551,6 +551,9 @@ static int mctp_sk_hash(struct sock *sk) { struct net *net = sock_net(sk); + /* Bind lookup runs under RCU, remain live during that. */ + sock_set_flag(sk, SOCK_RCU_FREE); + mutex_lock(&net->mctp.bind_lock); sk_add_node_rcu(sk, &net->mctp.binds); mutex_unlock(&net->mctp.bind_lock); diff --git a/net/mctp/route.c b/net/mctp/route.c index e72cdd4ce588..62952ad5cb63 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -274,8 +274,10 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (WARN_ON(key->dev && key->dev != dev)) + if (key->dev) { + WARN_ON(key->dev != dev); return; + } mctp_dev_set_key(dev, key); } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index f1f43894efb8..2d29d230f569 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -80,8 +80,8 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) if (index < net->mpls.platform_labels) { struct mpls_route __rcu **platform_label = - rcu_dereference(net->mpls.platform_label); - rt = rcu_dereference(platform_label[index]); + rcu_dereference_rtnl(net->mpls.platform_label); + rt = rcu_dereference_rtnl(platform_label[index]); } return rt; } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index f04fa61a6323..929074f08713 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -649,6 +649,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * struct mptcp_sock *msk = mptcp_sk(subflow->conn); bool drop_other_suboptions = false; unsigned int opt_size = *size; + struct mptcp_addr_info addr; bool echo; int len; @@ -657,7 +658,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * */ if (!mptcp_pm_should_add_signal(msk) || (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) || - !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr, + !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr, &echo, &drop_other_suboptions)) return false; @@ -670,7 +671,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * else if (opts->suboptions & OPTION_MPTCP_DSS) return false; - len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); + len = mptcp_add_addr_len(addr.family, echo, !!addr.port); if (remaining < len) return false; @@ -687,6 +688,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->ahmac = 0; *size -= opt_size; } + opts->addr = addr; opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { opts->ahmac = add_addr_generate_hmac(msk->local_key, diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index fef7bb2a08d8..3391d4df2dbb 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -969,7 +969,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry, - bool needs_id) + bool needs_id, bool replace) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -1003,6 +1003,17 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, if (entry->addr.id) goto out; + /* allow callers that only need to look up the local + * addr's id to skip replacement. This allows them to + * avoid calling synchronize_rcu in the packet recv + * path. + */ + if (!replace) { + kfree(entry); + ret = cur->addr.id; + goto out; + } + pernet->addrs--; entry->addr.id = cur->addr.id; list_del_rcu(&cur->list); @@ -1149,7 +1160,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false); if (ret < 0) kfree(entry); @@ -1444,7 +1455,8 @@ static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) } } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, - !mptcp_pm_has_addr_attr_id(attr, info)); + !mptcp_pm_has_addr_attr_id(attr, info), + true); if (ret < 0) { GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); goto out_free; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 77e727d81cc2..25c1cda5c1bc 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -981,6 +981,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } + if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback))) + return; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 766797ace942..129c9e9ee396 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1266,6 +1266,32 @@ static int mptcp_getsockopt_v4(struct mptcp_sock *msk, int optname, switch (optname) { case IP_TOS: return mptcp_put_int_option(msk, optval, optlen, inet_sk(sk)->tos); + case IP_FREEBIND: + return mptcp_put_int_option(msk, optval, optlen, + inet_sk(sk)->freebind); + case IP_TRANSPARENT: + return mptcp_put_int_option(msk, optval, optlen, + inet_sk(sk)->transparent); + } + + return -EOPNOTSUPP; +} + +static int mptcp_getsockopt_v6(struct mptcp_sock *msk, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = (void *)msk; + + switch (optname) { + case IPV6_V6ONLY: + return mptcp_put_int_option(msk, optval, optlen, + sk->sk_ipv6only); + case IPV6_TRANSPARENT: + return mptcp_put_int_option(msk, optval, optlen, + inet_sk(sk)->transparent); + case IPV6_FREEBIND: + return mptcp_put_int_option(msk, optval, optlen, + inet_sk(sk)->freebind); } return -EOPNOTSUPP; @@ -1308,6 +1334,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, if (level == SOL_IP) return mptcp_getsockopt_v4(msk, optname, optval, option); + if (level == SOL_IPV6) + return mptcp_getsockopt_v6(msk, optname, optval, option); if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); if (level == SOL_MPTCP) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c3e0ad7beb57..a6237eb55537 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -643,8 +643,6 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req = mptcp_subflow_rsk(req); msk = subflow_req->msk; - if (!msk) - return false; subflow_generate_hmac(msk->remote_key, msk->local_key, subflow_req->remote_nonce, @@ -739,12 +737,8 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, } else if (subflow_req->mp_join) { mptcp_get_options(skb, &mp_opt); - if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK) || - !subflow_hmac_valid(req, &mp_opt) || - !mptcp_can_accept_new_subflow(subflow_req->msk)) { - SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); + if (!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK)) fallback = true; - } } create_child: @@ -794,6 +788,17 @@ create_child: goto dispose_child; } + if (!subflow_hmac_valid(req, &mp_opt)) { + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + goto dispose_child; + } + + if (!mptcp_can_accept_new_subflow(owner)) { + subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); + goto dispose_child; + } + /* move the msk reference ownership to the subflow */ subflow_req->msk = NULL; ctx->conn = (struct sock *)owner; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 4e0842df5234..2c260f33b55c 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -143,16 +143,15 @@ struct ncsi_channel_vlan_filter { }; struct ncsi_channel_stats { - u32 hnc_cnt_hi; /* Counter cleared */ - u32 hnc_cnt_lo; /* Counter cleared */ - u32 hnc_rx_bytes; /* Rx bytes */ - u32 hnc_tx_bytes; /* Tx bytes */ - u32 hnc_rx_uc_pkts; /* Rx UC packets */ - u32 hnc_rx_mc_pkts; /* Rx MC packets */ - u32 hnc_rx_bc_pkts; /* Rx BC packets */ - u32 hnc_tx_uc_pkts; /* Tx UC packets */ - u32 hnc_tx_mc_pkts; /* Tx MC packets */ - u32 hnc_tx_bc_pkts; /* Tx BC packets */ + u64 hnc_cnt; /* Counter cleared */ + u64 hnc_rx_bytes; /* Rx bytes */ + u64 hnc_tx_bytes; /* Tx bytes */ + u64 hnc_rx_uc_pkts; /* Rx UC packets */ + u64 hnc_rx_mc_pkts; /* Rx MC packets */ + u64 hnc_rx_bc_pkts; /* Rx BC packets */ + u64 hnc_tx_uc_pkts; /* Tx UC packets */ + u64 hnc_tx_mc_pkts; /* Tx MC packets */ + u64 hnc_tx_bc_pkts; /* Tx BC packets */ u32 hnc_fcs_err; /* FCS errors */ u32 hnc_align_err; /* Alignment errors */ u32 hnc_false_carrier; /* False carrier detection */ @@ -181,7 +180,7 @@ struct ncsi_channel_stats { u32 hnc_tx_1023_frames; /* Tx 512-1023 bytes frames */ u32 hnc_tx_1522_frames; /* Tx 1024-1522 bytes frames */ u32 hnc_tx_9022_frames; /* Tx 1523-9022 bytes frames */ - u32 hnc_rx_valid_bytes; /* Rx valid bytes */ + u64 hnc_rx_valid_bytes; /* Rx valid bytes */ u32 hnc_rx_runt_pkts; /* Rx error runt packets */ u32 hnc_rx_jabber_pkts; /* Rx error jabber packets */ u32 ncsi_rx_cmds; /* Rx NCSI commands */ diff --git a/net/ncsi/ncsi-pkt.h b/net/ncsi/ncsi-pkt.h index f2f3b5c1b941..24edb2737972 100644 --- a/net/ncsi/ncsi-pkt.h +++ b/net/ncsi/ncsi-pkt.h @@ -252,16 +252,15 @@ struct ncsi_rsp_gp_pkt { /* Get Controller Packet Statistics */ struct ncsi_rsp_gcps_pkt { struct ncsi_rsp_pkt_hdr rsp; /* Response header */ - __be32 cnt_hi; /* Counter cleared */ - __be32 cnt_lo; /* Counter cleared */ - __be32 rx_bytes; /* Rx bytes */ - __be32 tx_bytes; /* Tx bytes */ - __be32 rx_uc_pkts; /* Rx UC packets */ - __be32 rx_mc_pkts; /* Rx MC packets */ - __be32 rx_bc_pkts; /* Rx BC packets */ - __be32 tx_uc_pkts; /* Tx UC packets */ - __be32 tx_mc_pkts; /* Tx MC packets */ - __be32 tx_bc_pkts; /* Tx BC packets */ + __be64 cnt; /* Counter cleared */ + __be64 rx_bytes; /* Rx bytes */ + __be64 tx_bytes; /* Tx bytes */ + __be64 rx_uc_pkts; /* Rx UC packets */ + __be64 rx_mc_pkts; /* Rx MC packets */ + __be64 rx_bc_pkts; /* Rx BC packets */ + __be64 tx_uc_pkts; /* Tx UC packets */ + __be64 tx_mc_pkts; /* Tx MC packets */ + __be64 tx_bc_pkts; /* Tx BC packets */ __be32 fcs_err; /* FCS errors */ __be32 align_err; /* Alignment errors */ __be32 false_carrier; /* False carrier detection */ @@ -290,11 +289,11 @@ struct ncsi_rsp_gcps_pkt { __be32 tx_1023_frames; /* Tx 512-1023 bytes frames */ __be32 tx_1522_frames; /* Tx 1024-1522 bytes frames */ __be32 tx_9022_frames; /* Tx 1523-9022 bytes frames */ - __be32 rx_valid_bytes; /* Rx valid bytes */ + __be64 rx_valid_bytes; /* Rx valid bytes */ __be32 rx_runt_pkts; /* Rx error runt packets */ __be32 rx_jabber_pkts; /* Rx error jabber packets */ __be32 checksum; /* Checksum */ -}; +} __packed __aligned(4); /* Get NCSI Statistics */ struct ncsi_rsp_gns_pkt { diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 4a8ce2949fae..8668888c5a2f 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -926,16 +926,15 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr) /* Update HNC's statistics */ ncs = &nc->stats; - ncs->hnc_cnt_hi = ntohl(rsp->cnt_hi); - ncs->hnc_cnt_lo = ntohl(rsp->cnt_lo); - ncs->hnc_rx_bytes = ntohl(rsp->rx_bytes); - ncs->hnc_tx_bytes = ntohl(rsp->tx_bytes); - ncs->hnc_rx_uc_pkts = ntohl(rsp->rx_uc_pkts); - ncs->hnc_rx_mc_pkts = ntohl(rsp->rx_mc_pkts); - ncs->hnc_rx_bc_pkts = ntohl(rsp->rx_bc_pkts); - ncs->hnc_tx_uc_pkts = ntohl(rsp->tx_uc_pkts); - ncs->hnc_tx_mc_pkts = ntohl(rsp->tx_mc_pkts); - ncs->hnc_tx_bc_pkts = ntohl(rsp->tx_bc_pkts); + ncs->hnc_cnt = be64_to_cpu(rsp->cnt); + ncs->hnc_rx_bytes = be64_to_cpu(rsp->rx_bytes); + ncs->hnc_tx_bytes = be64_to_cpu(rsp->tx_bytes); + ncs->hnc_rx_uc_pkts = be64_to_cpu(rsp->rx_uc_pkts); + ncs->hnc_rx_mc_pkts = be64_to_cpu(rsp->rx_mc_pkts); + ncs->hnc_rx_bc_pkts = be64_to_cpu(rsp->rx_bc_pkts); + ncs->hnc_tx_uc_pkts = be64_to_cpu(rsp->tx_uc_pkts); + ncs->hnc_tx_mc_pkts = be64_to_cpu(rsp->tx_mc_pkts); + ncs->hnc_tx_bc_pkts = be64_to_cpu(rsp->tx_bc_pkts); ncs->hnc_fcs_err = ntohl(rsp->fcs_err); ncs->hnc_align_err = ntohl(rsp->align_err); ncs->hnc_false_carrier = ntohl(rsp->false_carrier); @@ -964,7 +963,7 @@ static int ncsi_rsp_handler_gcps(struct ncsi_request *nr) ncs->hnc_tx_1023_frames = ntohl(rsp->tx_1023_frames); ncs->hnc_tx_1522_frames = ntohl(rsp->tx_1522_frames); ncs->hnc_tx_9022_frames = ntohl(rsp->tx_9022_frames); - ncs->hnc_rx_valid_bytes = ntohl(rsp->rx_valid_bytes); + ncs->hnc_rx_valid_bytes = be64_to_cpu(rsp->rx_valid_bytes); ncs->hnc_rx_runt_pkts = ntohl(rsp->rx_runt_pkts); ncs->hnc_rx_jabber_pkts = ntohl(rsp->rx_jabber_pkts); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index ef04e556aadb..0bd6bf46f05f 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -63,7 +63,7 @@ struct hbucket { #define ahash_sizeof_regions(htable_bits) \ (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) #define ahash_region(n, htable_bits) \ - ((n) % ahash_numof_locks(htable_bits)) + ((n) / jhash_size(HTABLE_REGION_BITS)) #define ahash_bucket_start(h, htable_bits) \ ((htable_bits) < HTABLE_REGION_BITS ? 0 \ : (h) * jhash_size(HTABLE_REGION_BITS)) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 18e37b32a5d6..6cc50f05c46c 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2854,12 +2854,12 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IP_VS_SO_GET_SERVICES: { struct ip_vs_get_services *get; - int size; + size_t size; get = (struct ip_vs_get_services *)arg; size = struct_size(get, entrytable, get->num_services); if (*len != size) { - pr_err("length: %u != %u\n", *len, size); + pr_err("length: %u != %zu\n", *len, size); ret = -EINVAL; goto out; } @@ -2895,12 +2895,12 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IP_VS_SO_GET_DESTS: { struct ip_vs_get_dests *get; - int size; + size_t size; get = (struct ip_vs_get_dests *)arg; size = struct_size(get, entrytable, get->num_dests); if (*len != size) { - pr_err("length: %u != %u\n", *len, size); + pr_err("length: %u != %zu\n", *len, size); ret = -EINVAL; goto out; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index d40a4ca2b27f..e1437c72ca6e 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu) return false; } -/* Get route to daddr, update *saddr, optionally bind route to saddr */ +/* Get route to daddr, optionally bind route to saddr */ static struct rtable *do_output_route4(struct net *net, __be32 daddr, - int rt_mode, __be32 *saddr) + int rt_mode, __be32 *ret_saddr) { struct flowi4 fl4; struct rtable *rt; - bool loop = false; memset(&fl4, 0, sizeof(fl4)); fl4.daddr = daddr; @@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr, retry: rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) { - /* Invalid saddr ? */ - if (PTR_ERR(rt) == -EINVAL && *saddr && - rt_mode & IP_VS_RT_MODE_CONNECT && !loop) { - *saddr = 0; - flowi4_update_output(&fl4, 0, 0, daddr, 0); - goto retry; - } IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr); return NULL; - } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { + } + if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) { ip_rt_put(rt); - *saddr = fl4.saddr; - flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr); - loop = true; + flowi4_update_output(&fl4, 0, daddr, fl4.saddr); + rt_mode = 0; goto retry; } - *saddr = fl4.saddr; + if (ret_saddr) + *ret_saddr = fl4.saddr; return rt; } @@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, if (ret_saddr) *ret_saddr = dest_dst->dst_saddr.ip; } else { - __be32 saddr = htonl(INADDR_ANY); - noref = 0; /* For such unconfigured boxes avoid many route lookups * for performance reasons because we do not remember saddr */ rt_mode &= ~IP_VS_RT_MODE_CONNECT; - rt = do_output_route4(net, daddr, rt_mode, &saddr); + rt = do_output_route4(net, daddr, rt_mode, ret_saddr); if (!rt) goto err_unreach; - if (ret_saddr) - *ret_saddr = saddr; } local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0; diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 5885810da412..6156c0751056 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -132,7 +132,7 @@ static int __nf_conncount_add(struct net *net, struct nf_conn *found_ct; unsigned int collect = 0; - if (time_is_after_eq_jiffies((unsigned long)list->last_gc)) + if ((u32)jiffies == list->last_gc) goto add_new_node; /* check the saved connections */ @@ -234,7 +234,7 @@ bool nf_conncount_gc_list(struct net *net, bool ret = false; /* don't bother if we just did GC */ - if (time_is_after_eq_jiffies((unsigned long)READ_ONCE(list->last_gc))) + if ((u32)jiffies == READ_ONCE(list->last_gc)) return false; /* don't bother if other cpu is already doing GC */ @@ -377,6 +377,8 @@ restart: conn->tuple = *tuple; conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; memcpy(rbconn->key, key, sizeof(u32) * data->keylen); nf_conncount_list_init(&rbconn->list); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ec4c39641089..002d53ded404 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1087,6 +1087,12 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &nf_conntrack_hash[repl_idx]); + /* confirmed bit must be set after hlist add, not before: + * loser_ct can still be visible to other cpu due to + * SLAB_TYPESAFE_BY_RCU. + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &loser_ct->status); NF_CT_STAT_INC(net, clash_resolve); return NF_ACCEPT; @@ -1224,8 +1230,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) * user context, else we insert an already 'dead' hash, blocking * further use of that particular connection -JM. */ - ct->status |= IPS_CONFIRMED; - if (unlikely(nf_ct_is_dying(ct))) { NF_CT_STAT_INC(net, insert_failed); goto dying; @@ -1257,7 +1261,7 @@ chaintoolong: } } - /* Timer relative to confirmation time, not original + /* Timeout is relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; @@ -1265,11 +1269,21 @@ chaintoolong: __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after - * starting the timer and setting the CONFIRMED bit. The RCU barriers - * guarantee that no other CPU can find the conntrack before the above - * stores are visible. + * setting ct->timeout. The RCU barriers guarantee that no other CPU + * can find the conntrack before the above stores are visible. */ __nf_conntrack_hash_insert(ct, hash, reply_hash); + + /* IPS_CONFIRMED unset means 'ct not (yet) in hash', conntrack lookups + * skip entries that lack this bit. This happens when a CPU is looking + * at a stale entry that is being recycled due to SLAB_TYPESAFE_BY_RCU + * or when another CPU encounters this entry right after the insertion + * but before the set-confirm-bit below. This bit must not be set until + * after __nf_conntrack_hash_insert(). + */ + smp_mb__before_atomic(); + set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_double_unlock(hash, reply_hash); local_bh_enable(); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 52245dbfae31..c333132e2079 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -631,7 +631,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_COUNT] = { .procname = "nf_conntrack_count", @@ -667,7 +669,9 @@ static struct ctl_table nf_ct_sysctl_table[] = { .data = &nf_ct_expect_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_ACCT] = { .procname = "nf_conntrack_acct", @@ -970,7 +974,9 @@ static struct ctl_table nf_ct_netfilter_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, }, { } }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 656c4fb76773..df83224bef06 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2034,9 +2034,9 @@ static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) kvfree(chain->blob_next); } -void nf_tables_chain_destroy(struct nft_ctx *ctx) +void nf_tables_chain_destroy(struct nft_chain *chain) { - struct nft_chain *chain = ctx->chain; + const struct nft_table *table = chain->table; struct nft_hook *hook, *next; if (WARN_ON(chain->use > 0)) @@ -2048,7 +2048,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); @@ -2515,7 +2515,7 @@ err_chain_add: err_trans: nft_use_dec_restore(&table->use); err_destroy_chain: - nf_tables_chain_destroy(ctx); + nf_tables_chain_destroy(chain); return err; } @@ -3510,8 +3510,11 @@ void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) kfree(rule); } +/* can only be used if rule is no longer visible to dumps */ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { + WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net)); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -5247,6 +5250,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { + WARN_ON_ONCE(!lockdep_commit_lock_is_held(ctx->net)); + switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); @@ -8994,7 +8999,7 @@ static void nft_commit_release(struct nft_trans *trans) kfree(nft_trans_chain_name(trans)); break; case NFT_MSG_DELCHAIN: - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_DELRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); @@ -9955,7 +9960,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_table_destroy(&trans->ctx); break; case NFT_MSG_NEWCHAIN: - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_NEWRULE: nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); @@ -10662,23 +10667,43 @@ int nft_data_dump(struct sk_buff *skb, int attr, const struct nft_data *data, } EXPORT_SYMBOL_GPL(nft_data_dump); -int __nft_release_basechain(struct nft_ctx *ctx) +static void __nft_release_basechain_now(struct nft_ctx *ctx) { struct nft_rule *rule, *nr; - if (WARN_ON(!nft_is_base_chain(ctx->chain))) - return 0; - - nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); list_for_each_entry_safe(rule, nr, &ctx->chain->rules, list) { list_del(&rule->list); - nft_use_dec(&ctx->chain->use); nf_tables_rule_release(ctx, rule); } + nf_tables_chain_destroy(ctx->chain); +} + +int __nft_release_basechain(struct nft_ctx *ctx) +{ + struct nft_rule *rule; + + if (WARN_ON_ONCE(!nft_is_base_chain(ctx->chain))) + return 0; + + nf_tables_unregister_hook(ctx->net, ctx->chain->table, ctx->chain); + list_for_each_entry(rule, &ctx->chain->rules, list) + nft_use_dec(&ctx->chain->use); + nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - nf_tables_chain_destroy(ctx); + if (!maybe_get_net(ctx->net)) { + __nft_release_basechain_now(ctx); + return 0; + } + + /* wait for ruleset dumps to complete. Owning chain is no longer in + * lists, so new dumps can't find any of these rules anymore. + */ + synchronize_rcu(); + + __nft_release_basechain_now(ctx); + put_net(ctx->net); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); @@ -10753,10 +10778,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; nft_chain_del(chain); nft_use_dec(&table->use); - nf_tables_chain_destroy(&ctx); + nf_tables_chain_destroy(chain); } nf_tables_table_destroy(&ctx); } diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 781d3a26f5df..8d19bd001277 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/seqlock.h> +#include <linux/u64_stats_sync.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -17,6 +17,11 @@ #include <net/netfilter/nf_tables_offload.h> struct nft_counter { + u64_stats_t bytes; + u64_stats_t packets; +}; + +struct nft_counter_tot { s64 bytes; s64 packets; }; @@ -25,25 +30,24 @@ struct nft_counter_percpu_priv { struct nft_counter __percpu *counter; }; -static DEFINE_PER_CPU(seqcount_t, nft_counter_seq); +static DEFINE_PER_CPU(struct u64_stats_sync, nft_counter_sync); static inline void nft_counter_do_eval(struct nft_counter_percpu_priv *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); - - write_seqcount_begin(myseq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - this_cpu->bytes += pkt->skb->len; - this_cpu->packets++; + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->bytes, pkt->skb->len); + u64_stats_inc(&this_cpu->packets); + u64_stats_update_end(nft_sync); - write_seqcount_end(myseq); local_bh_enable(); } @@ -66,17 +70,16 @@ static int nft_counter_do_init(const struct nlattr * const tb[], if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); + this_cpu = raw_cpu_ptr(cpu_stats); if (tb[NFTA_COUNTER_PACKETS]) { - this_cpu->packets = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + u64_stats_set(&this_cpu->packets, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]))); } if (tb[NFTA_COUNTER_BYTES]) { - this_cpu->bytes = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); + u64_stats_set(&this_cpu->bytes, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]))); } - preempt_enable(); + priv->counter = cpu_stats; return 0; } @@ -104,40 +107,41 @@ static void nft_counter_obj_destroy(const struct nft_ctx *ctx, } static void nft_counter_reset(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); + nft_sync = this_cpu_ptr(&nft_counter_sync); + + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, -total->packets); + u64_stats_add(&this_cpu->bytes, -total->bytes); + u64_stats_update_end(nft_sync); - write_seqcount_begin(myseq); - this_cpu->packets -= total->packets; - this_cpu->bytes -= total->bytes; - write_seqcount_end(myseq); local_bh_enable(); } static void nft_counter_fetch(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { struct nft_counter *this_cpu; - const seqcount_t *myseq; u64 bytes, packets; unsigned int seq; int cpu; memset(total, 0, sizeof(*total)); for_each_possible_cpu(cpu) { - myseq = per_cpu_ptr(&nft_counter_seq, cpu); + struct u64_stats_sync *nft_sync = per_cpu_ptr(&nft_counter_sync, cpu); + this_cpu = per_cpu_ptr(priv->counter, cpu); do { - seq = read_seqcount_begin(myseq); - bytes = this_cpu->bytes; - packets = this_cpu->packets; - } while (read_seqcount_retry(myseq, seq)); + seq = u64_stats_fetch_begin(nft_sync); + bytes = u64_stats_read(&this_cpu->bytes); + packets = u64_stats_read(&this_cpu->packets); + } while (u64_stats_fetch_retry(nft_sync, seq)); total->bytes += bytes; total->packets += packets; @@ -148,7 +152,7 @@ static int nft_counter_do_dump(struct sk_buff *skb, struct nft_counter_percpu_priv *priv, bool reset) { - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -236,7 +240,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -244,11 +248,9 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); - this_cpu->packets = total.packets; - this_cpu->bytes = total.bytes; - preempt_enable(); + this_cpu = raw_cpu_ptr(cpu_stats); + u64_stats_set(&this_cpu->packets, total.packets); + u64_stats_set(&this_cpu->bytes, total.bytes); priv_clone->counter = cpu_stats; return 0; @@ -266,17 +268,17 @@ static void nft_counter_offload_stats(struct nft_expr *expr, const struct flow_stats *stats) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - write_seqcount_begin(myseq); - this_cpu->packets += stats->pkts; - this_cpu->bytes += stats->bytes; - write_seqcount_end(myseq); + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, stats->pkts); + u64_stats_add(&this_cpu->bytes, stats->bytes); + u64_stats_update_end(nft_sync); local_bh_enable(); } @@ -285,7 +287,7 @@ void nft_counter_init_seqcount(void) int cpu; for_each_possible_cpu(cpu) - seqcount_init(per_cpu_ptr(&nft_counter_seq, cpu)); + u64_stats_init(per_cpu_ptr(&nft_counter_sync, cpu)); } struct nft_expr_type nft_counter_type; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 6157f8b4a3ce..3641043ca8cc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -240,6 +240,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, enum ip_conntrack_info ctinfo; u16 value = nft_reg_load16(®s->data[priv->sreg]); struct nf_conn *ct; + int oldcnt; ct = nf_ct_get(skb, &ctinfo); if (ct) /* already tracked */ @@ -260,10 +261,11 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, ct = this_cpu_read(nft_ct_pcpu_template); - if (likely(refcount_read(&ct->ct_general.use) == 1)) { - refcount_inc(&ct->ct_general.use); + __refcount_inc(&ct->ct_general.use, &oldcnt); + if (likely(oldcnt == 1)) { nf_ct_zone_add(ct, &zone); } else { + refcount_dec(&ct->ct_general.use); /* previous skb got queued to userspace, allocate temporary * one until percpu template can be reused. */ diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index de588f7b69c4..60d18bd60d82 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -86,7 +86,6 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb, unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; struct iphdr *iph, _iph; - unsigned int start; bool found = false; __be32 info; int optlen; @@ -94,7 +93,6 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb, iph = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (!iph) return -EBADMSG; - start = sizeof(struct iphdr); optlen = iph->ihl * 4 - (int)sizeof(struct iphdr); if (optlen <= 0) @@ -104,7 +102,7 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb, /* Copy the options since __ip_options_compile() modifies * the options. */ - if (skb_copy_bits(skb, start, opt->__data, optlen)) + if (skb_copy_bits(skb, sizeof(struct iphdr), opt->__data, optlen)) return -EBADMSG; opt->optlen = optlen; @@ -119,18 +117,18 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb, found = target == IPOPT_SSRR ? opt->is_strictroute : !opt->is_strictroute; if (found) - *offset = opt->srr + start; + *offset = opt->srr; break; case IPOPT_RR: if (!opt->rr) break; - *offset = opt->rr + start; + *offset = opt->rr; found = true; break; case IPOPT_RA: if (!opt->router_alert) break; - *offset = opt->router_alert + start; + *offset = opt->router_alert; found = true; break; default: diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 55fcf0280c5c..731511d58b7c 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -221,7 +221,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } - nf_tables_chain_destroy(&chain_ctx); + nf_tables_chain_destroy(chain); break; default: break; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index ef8e7cdbd0e6..60e6d0c5f04e 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -19,10 +19,16 @@ struct nft_quota { }; static inline bool nft_overquota(struct nft_quota *priv, - const struct sk_buff *skb) + const struct sk_buff *skb, + bool *report) { - return atomic64_add_return(skb->len, priv->consumed) >= - atomic64_read(&priv->quota); + u64 consumed = atomic64_add_return(skb->len, priv->consumed); + u64 quota = atomic64_read(&priv->quota); + + if (report) + *report = consumed >= quota; + + return consumed > quota; } static inline bool nft_quota_invert(struct nft_quota *priv) @@ -34,7 +40,7 @@ static inline void nft_quota_do_eval(struct nft_quota *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { - if (nft_overquota(priv, pkt->skb) ^ nft_quota_invert(priv)) + if (nft_overquota(priv, pkt->skb, NULL) ^ nft_quota_invert(priv)) regs->verdict.code = NFT_BREAK; } @@ -51,13 +57,13 @@ static void nft_quota_obj_eval(struct nft_object *obj, const struct nft_pktinfo *pkt) { struct nft_quota *priv = nft_obj_data(obj); - bool overquota; + bool overquota, report; - overquota = nft_overquota(priv, pkt->skb); + overquota = nft_overquota(priv, pkt->skb, &report); if (overquota ^ nft_quota_invert(priv)) regs->verdict.code = NFT_BREAK; - if (overquota && + if (report && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 5c4209b49bda..a592cca7a61f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -310,7 +310,8 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, nft_setelem_expr_foreach(expr, elem_expr, size) { if (expr->ops->gc && - expr->ops->gc(read_pnet(&set->net), expr)) + expr->ops->gc(read_pnet(&set->net), expr) && + set->flags & NFT_SET_EVAL) return true; } diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index b8d3c3213efe..be7c16c79f71 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -994,8 +994,9 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, NFT_PIPAPO_AVX2_BUCKET_LOAD8(5, lt, 8, pkt[8], bsize); NFT_PIPAPO_AVX2_AND(6, 2, 3); + NFT_PIPAPO_AVX2_AND(3, 4, 7); NFT_PIPAPO_AVX2_BUCKET_LOAD8(7, lt, 9, pkt[9], bsize); - NFT_PIPAPO_AVX2_AND(0, 4, 5); + NFT_PIPAPO_AVX2_AND(0, 3, 5); NFT_PIPAPO_AVX2_BUCKET_LOAD8(1, lt, 10, pkt[10], bsize); NFT_PIPAPO_AVX2_AND(2, 6, 7); NFT_PIPAPO_AVX2_BUCKET_LOAD8(3, lt, 11, pkt[11], bsize); @@ -1113,6 +1114,25 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, } /** + * pipapo_resmap_init_avx2() - Initialise result map before first use + * @m: Matching data, including mapping table + * @res_map: Result map + * + * Like pipapo_resmap_init() but do not set start map bits covered by the first field. + */ +static inline void pipapo_resmap_init_avx2(const struct nft_pipapo_match *m, unsigned long *res_map) +{ + const struct nft_pipapo_field *f = m->f; + int i; + + /* Starting map doesn't need to be set to all-ones for this implementation, + * but we do need to zero the remaining bits, if any. + */ + for (i = f->bsize; i < m->bsize_max; i++) + res_map[i] = 0ul; +} + +/** * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation * @net: Network namespace * @set: nftables API set representation @@ -1170,7 +1190,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, res = scratch->map + (map_index ? m->bsize_max : 0); fill = scratch->map + (map_index ? 0 : m->bsize_max); - /* Starting map doesn't need to be set for this implementation */ + pipapo_resmap_init_avx2(m, res); nft_pipapo_avx2_prepare(); diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index efb505445eac..be741db50ffa 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -333,13 +333,13 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = { [NFTA_TUNNEL_KEY_GENEVE_CLASS] = { .type = NLA_U16 }, [NFTA_TUNNEL_KEY_GENEVE_TYPE] = { .type = NLA_U8 }, - [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, + [NFTA_TUNNEL_KEY_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static int nft_tunnel_obj_geneve_init(const struct nlattr *attr, struct nft_tunnel_opts *opts) { - struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len; + struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len); struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1]; int err, data_len; @@ -617,11 +617,11 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, struct geneve_opt *opt; int offset = 0; - inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_GENEVE); - if (!inner) - goto failure; while (opts->len > offset) { - opt = (struct geneve_opt *)opts->u.data + offset; + inner = nla_nest_start_noflag(skb, NFTA_TUNNEL_KEY_OPTS_GENEVE); + if (!inner) + goto failure; + opt = (struct geneve_opt *)(opts->u.data + offset); if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE, @@ -630,8 +630,8 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, opt->length * 4, opt->opt_data)) goto inner_failure; offset += sizeof(*opt) + opt->length * 4; + nla_nest_end(skb, inner); } - nla_nest_end(skb, inner); } nla_nest_end(skb, nest); return 0; diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 7c6bf1c16813..0ca1cdfc4095 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -38,8 +38,8 @@ nfacct_mt_checkentry(const struct xt_mtchk_param *par) nfacct = nfnl_acct_find_get(par->net, info->name); if (nfacct == NULL) { - pr_info_ratelimited("accounting object `%s' does not exists\n", - info->name); + pr_info_ratelimited("accounting object `%.*s' does not exist\n", + NFACCT_NAME_MAX, info->name); return -ENOENT; } info->nfacct = nfacct; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 27511c90a26f..daef0eeaea2c 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -1140,6 +1140,11 @@ int netlbl_conn_setattr(struct sock *sk, break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: + if (sk->sk_family != AF_INET6) { + ret_val = -EAFNOSUPPORT; + goto conn_setattr_return; + } + addr6 = (struct sockaddr_in6 *)addr; entry = netlbl_domhsh_getentry_af6(secattr->domain, &addr6->sin6_addr); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 8a74847dacaf..7e55328a4338 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) WARN_ON(skb->sk != NULL); skb->sk = sk; skb->destructor = netlink_skb_destructor; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); sk_mem_charge(sk, skb->truesize); } @@ -1211,41 +1210,48 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, int netlink_attachskb(struct sock *sk, struct sk_buff *skb, long *timeo, struct sock *ssk) { + DECLARE_WAITQUEUE(wait, current); struct netlink_sock *nlk; + unsigned int rmem; nlk = nlk_sk(sk); + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state))) { - DECLARE_WAITQUEUE(wait, current); - if (!*timeo) { - if (!ssk || netlink_is_kernel(ssk)) - netlink_overrun(sk); - sock_put(sk); - kfree_skb(skb); - return -EAGAIN; - } - - __set_current_state(TASK_INTERRUPTIBLE); - add_wait_queue(&nlk->wait, &wait); + if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) && + !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { + netlink_skb_set_owner_r(skb, sk); + return 0; + } - if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf || - test_bit(NETLINK_S_CONGESTED, &nlk->state)) && - !sock_flag(sk, SOCK_DEAD)) - *timeo = schedule_timeout(*timeo); + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&nlk->wait, &wait); + if (!*timeo) { + if (!ssk || netlink_is_kernel(ssk)) + netlink_overrun(sk); sock_put(sk); + kfree_skb(skb); + return -EAGAIN; + } - if (signal_pending(current)) { - kfree_skb(skb); - return sock_intr_errno(*timeo); - } - return 1; + __set_current_state(TASK_INTERRUPTIBLE); + add_wait_queue(&nlk->wait, &wait); + rmem = atomic_read(&sk->sk_rmem_alloc); + + if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) || + test_bit(NETLINK_S_CONGESTED, &nlk->state)) && + !sock_flag(sk, SOCK_DEAD)) + *timeo = schedule_timeout(*timeo); + + __set_current_state(TASK_RUNNING); + remove_wait_queue(&nlk->wait, &wait); + sock_put(sk); + + if (signal_pending(current)) { + kfree_skb(skb); + return sock_intr_errno(*timeo); } - netlink_skb_set_owner_r(skb, sk); - return 0; + + return 1; } static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb) @@ -1305,6 +1311,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, ret = -ECONNREFUSED; if (nlk->netlink_rcv != NULL) { ret = skb->len; + atomic_add(skb->truesize, &sk->sk_rmem_alloc); netlink_skb_set_owner_r(skb, sk); NETLINK_CB(skb).sk = ssk; netlink_deliver_tap_kernel(sk, ssk, skb); @@ -1381,13 +1388,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check); static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); + unsigned int rmem, rcvbuf; - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + + if ((rmem == skb->truesize || rmem <= rcvbuf) && !test_bit(NETLINK_S_CONGESTED, &nlk->state)) { netlink_skb_set_owner_r(skb, sk); __netlink_sendskb(sk, skb); - return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1); + return rmem > (rcvbuf >> 1); } + + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); return -1; } @@ -2155,6 +2168,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken) struct netlink_ext_ack extack = {}; struct netlink_callback *cb; struct sk_buff *skb = NULL; + unsigned int rmem, rcvbuf; size_t max_recvmsg_len; struct module *module; int err = -ENOBUFS; @@ -2168,9 +2182,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken) goto errout_skb; } - if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) - goto errout_skb; - /* NLMSG_GOODSIZE is small to avoid high order allocations being * required, but it makes sense to _attempt_ a 16K bytes allocation * to reduce number of system calls on dump operations, if user @@ -2193,6 +2204,13 @@ static int netlink_dump(struct sock *sk, bool lock_taken) if (!skb) goto errout_skb; + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc); + if (rmem != skb->truesize && rmem >= rcvbuf) { + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + goto errout_skb; + } + /* Trim skb to allocated size. User is expected to provide buffer as * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at * netlink_recvmsg())). dump will pack as many smaller messages as diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index cc8fa9e36159..03b72f74a171 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -119,22 +119,22 @@ static int nci_uart_set_driver(struct tty_struct *tty, unsigned int driver) memcpy(nu, nci_uart_drivers[driver], sizeof(struct nci_uart)); nu->tty = tty; - tty->disc_data = nu; skb_queue_head_init(&nu->tx_q); INIT_WORK(&nu->write_work, nci_uart_write_work); spin_lock_init(&nu->rx_lock); ret = nu->ops.open(nu); if (ret) { - tty->disc_data = NULL; kfree(nu); + return ret; } else if (!try_module_get(nu->owner)) { nu->ops.close(nu); - tty->disc_data = NULL; kfree(nu); return -ENOENT; } - return ret; + tty->disc_data = nu; + + return 0; } /* ------ LDISC part ------ */ diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 18d360aaf09b..a87c25e06baf 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -926,12 +926,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, pskb_trim(skb, ovs_mac_header_len(key)); } - /* Need to set the pkt_type to involve the routing layer. The - * packet movement through the OVS datapath doesn't generally - * use routing, but this is needed for tunnel cases. - */ - skb->pkt_type = PACKET_OUTGOING; - if (likely(!mru || (skb->len <= mru + vport->dev->hard_header_len))) { ovs_vport_send(vport, skb, ovs_key_mac_proto(key)); @@ -960,8 +954,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.cmd = OVS_PACKET_CMD_ACTION; upcall.mru = OVS_CB(skb)->mru; - for (a = nla_data(attr), rem = nla_len(attr); rem > 0; - a = nla_next(a, &rem)) { + nla_for_each_nested(a, attr, rem) { switch (nla_type(a)) { case OVS_USERSPACE_ATTR_USERDATA: upcall.userdata = a; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 78960a8a3892..60ebc42a20e7 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -785,7 +785,7 @@ static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key) memset(&key->ipv4, 0, sizeof(key->ipv4)); } } else if (eth_p_mpls(key->eth.type)) { - u8 label_count = 1; + size_t label_count = 1; memset(&key->mpls, 0, sizeof(key->mpls)); skb_set_inner_network_header(skb, skb->mac_len); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index e3c85ceb1f0a..0ed3953dbe52 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2302,14 +2302,10 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb) OVS_FLOW_ATTR_MASK, true, skb); } -#define MAX_ACTIONS_BUFSIZE (32 * 1024) - static struct sw_flow_actions *nla_alloc_flow_actions(int size) { struct sw_flow_actions *sfa; - WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE); - sfa = kmalloc(kmalloc_size_roundup(sizeof(*sfa) + size), GFP_KERNEL); if (!sfa) return ERR_PTR(-ENOMEM); @@ -2465,15 +2461,6 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); - if (new_acts_size > MAX_ACTIONS_BUFSIZE) { - if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) { - OVS_NLERR(log, "Flow action size exceeds max %u", - MAX_ACTIONS_BUFSIZE); - return ERR_PTR(-EMSGSIZE); - } - new_acts_size = MAX_ACTIONS_BUFSIZE; - } - acts = nla_alloc_flow_actions(new_acts_size); if (IS_ERR(acts)) return (void *)acts; @@ -2873,7 +2860,8 @@ static int validate_set(const struct nlattr *a, size_t key_len; /* There can be only one key in a action */ - if (nla_total_size(nla_len(ovs_key)) != nla_len(a)) + if (!nla_ok(ovs_key, nla_len(a)) || + nla_total_size(nla_len(ovs_key)) != nla_len(a)) return -EINVAL; key_len = nla_len(ovs_key); @@ -3492,7 +3480,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, int err; u32 mpls_label_count = 0; - *sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE)); + *sfa = nla_alloc_flow_actions(nla_len(attr)); if (IS_ERR(*sfa)) return PTR_ERR(*sfa); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f3bd3e126703..8c06e3e6b52b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2780,7 +2780,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; - long timeo = 0; + long timeo; mutex_lock(&po->pg_vec_lock); @@ -2834,22 +2834,28 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr) size_max = dev->mtu + reserve + VLAN_HLEN; + timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - if (need_wait && skb) { - timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); + /* Note: packet_read_pending() might be slow if we + * have to call it as it's per_cpu variable, but in + * fast-path we don't have to call it, only when ph + * is NULL, we need to check the pending_refcnt. + */ + if (need_wait && packet_read_pending(&po->tx_ring)) { timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } - } - /* check for additional frames */ - continue; + /* check for additional frames */ + continue; + } else + break; } skb = NULL; @@ -2939,14 +2945,7 @@ tpacket_error: } packet_increment_head(&po->tx_ring); len_sum += tp_len; - } while (likely((ph != NULL) || - /* Note: packet_read_pending() might be slow if we have - * to call it as it's per_cpu variable, but in fast-path - * we already short-circuit the loop with the first - * condition, and luckily don't have to go that path - * anyway. - */ - (need_wait && packet_read_pending(&po->tx_ring)))); + } while (1); err = len_sum; goto out_put; @@ -4542,10 +4541,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); was_running = po->running; num = po->num; - if (was_running) { - WRITE_ONCE(po->num, 0); + WRITE_ONCE(po->num, 0); + if (was_running) __unregister_prot_hook(sk, false); - } + spin_unlock(&po->bind_lock); synchronize_net(); @@ -4577,10 +4576,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); - if (was_running) { - WRITE_ONCE(po->num, num); + WRITE_ONCE(po->num, num); + if (was_running) register_prot_hook(sk); - } + spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 607f54c23647..240f4c385234 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -826,6 +826,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, } /* Check for duplicate pipe handle */ + pn_skb_get_dst_sockaddr(skb, &dst); newsk = pep_find_pipe(&pn->hlist, &dst, pipe_handle); if (unlikely(newsk)) { __sock_put(newsk); @@ -850,7 +851,6 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, newsk->sk_destruct = pipe_destruct; newpn = pep_sk(newsk); - pn_skb_get_dst_sockaddr(skb, &dst); pn_skb_get_src_sockaddr(skb, &src); newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst); newpn->pn_sk.dobject = pn_sockaddr_get_object(&src); diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index fee772b4637c..a7054546f52d 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -497,22 +497,15 @@ void rose_rt_device_down(struct net_device *dev) t = rose_node; rose_node = rose_node->next; - for (i = 0; i < t->count; i++) { + for (i = t->count - 1; i >= 0; i--) { if (t->neighbour[i] != s) continue; t->count--; - switch (i) { - case 0: - t->neighbour[0] = t->neighbour[1]; - fallthrough; - case 1: - t->neighbour[1] = t->neighbour[2]; - break; - case 2: - break; - } + memmove(&t->neighbour[i], &t->neighbour[i + 1], + sizeof(t->neighbour[0]) * + (t->count - i)); } if (t->count <= 0) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 99e10eea3732..658b592e58e0 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -270,6 +270,9 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, unsigned short call_tail, conn_tail, peer_tail; unsigned short call_count, conn_count; + if (!b) + return NULL; + /* #calls >= #conns >= #peers must hold true. */ call_head = smp_load_acquire(&b->call_backlog_head); call_tail = b->call_backlog_tail; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 7275ad869f8e..34a1fb617a0f 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -43,9 +43,9 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, newdscp); - ca->stats_dscp_set++; + atomic64_inc(&ca->stats_dscp_set); } else { - ca->stats_dscp_error++; + atomic64_inc(&ca->stats_dscp_error); } } break; @@ -56,9 +56,9 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, newdscp); - ca->stats_dscp_set++; + atomic64_inc(&ca->stats_dscp_set); } else { - ca->stats_dscp_error++; + atomic64_inc(&ca->stats_dscp_error); } } break; @@ -71,7 +71,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct tcf_ctinfo_params *cp, struct sk_buff *skb) { - ca->stats_cpmark_set++; + atomic64_inc(&ca->stats_cpmark_set); skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } @@ -321,15 +321,18 @@ static int tcf_ctinfo_dump(struct sk_buff *skb, struct tc_action *a, } if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_SET, - ci->stats_dscp_set, TCA_CTINFO_PAD)) + atomic64_read(&ci->stats_dscp_set), + TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_DSCP_ERROR, - ci->stats_dscp_error, TCA_CTINFO_PAD)) + atomic64_read(&ci->stats_dscp_error), + TCA_CTINFO_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CTINFO_STATS_CPMARK_SET, - ci->stats_cpmark_set, TCA_CTINFO_PAD)) + atomic64_read(&ci->stats_cpmark_set), + TCA_CTINFO_PAD)) goto nla_put_failure; spin_unlock_bh(&ci->tcf_lock); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 36395e5db3b4..bbc34987bd09 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -255,31 +255,31 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); + is_redirect = tcf_mirred_is_act_redirect(m_eaction); retval = READ_ONCE(m->tcf_action); dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); - goto out; + goto err_cant_do; } if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); - goto out; + goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ - is_redirect = tcf_mirred_is_act_redirect(m_eaction); at_ingress = skb_at_tc_ingress(skb); use_reinsert = at_ingress && is_redirect && tcf_mirred_can_reinsert(retval); if (!use_reinsert) { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) - goto out; + goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); @@ -321,12 +321,16 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, } err = tcf_mirred_forward(want_ingress, skb2); - if (err) { -out: + if (err) tcf_action_inc_overlimit_qstats(&m->common); - if (tcf_mirred_is_act_redirect(m_eaction)) - retval = TC_ACT_SHOT; - } + __this_cpu_dec(mirred_nest_level); + + return retval; + +err_cant_do: + if (is_redirect) + retval = TC_ACT_SHOT; + tcf_action_inc_overlimit_qstats(&m->common); __this_cpu_dec(mirred_nest_level); return retval; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2691a3d8e451..55a9dff1cc1e 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -66,7 +66,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 445ab1b0537d..89da596be1b8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1824,6 +1824,7 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); + int ret = -EMSGSIZE; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -1868,11 +1869,45 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, return skb->len; +cls_op_not_supp: + ret = -EOPNOTSUPP; out_nlmsg_trim: nla_put_failure: -cls_op_not_supp: nlmsg_trim(skb, b); - return -1; + return ret; +} + +static struct sk_buff *tfilter_notify_prep(struct net *net, + struct sk_buff *oskb, + struct nlmsghdr *n, + struct tcf_proto *tp, + struct tcf_block *block, + struct Qdisc *q, u32 parent, + void *fh, int event, + u32 portid, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + unsigned int size = oskb ? max(NLMSG_GOODSIZE, oskb->len) : NLMSG_GOODSIZE; + struct sk_buff *skb; + int ret; + +retry: + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOBUFS); + + ret = tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, + n->nlmsg_seq, n->nlmsg_flags, event, false, + rtnl_held, extack); + if (ret <= 0) { + kfree_skb(skb); + if (ret == -EMSGSIZE) { + size += NLMSG_GOODSIZE; + goto retry; + } + return ERR_PTR(-EINVAL); + } + return skb; } static int tfilter_notify(struct net *net, struct sk_buff *oskb, @@ -1885,16 +1920,13 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err = 0; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + if (!unicast && !rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return 0; - if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, event, - false, rtnl_held, extack) <= 0) { - kfree_skb(skb); - return -EINVAL; - } + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, event, + portid, rtnl_held, extack); + if (IS_ERR(skb)) + return PTR_ERR(skb); if (unicast) err = rtnl_unicast(skb, net, portid); @@ -1914,16 +1946,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; int err; - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; + if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) + return tp->ops->delete(tp, fh, last, rtnl_held, extack); - if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, - false, rtnl_held, extack) <= 0) { + skb = tfilter_notify_prep(net, oskb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, portid, rtnl_held, extack); + if (IS_ERR(skb)) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); - kfree_skb(skb); - return -EINVAL; + return PTR_ERR(skb); } err = tp->ops->delete(tp, fh, last, rtnl_held, extack); @@ -2731,6 +2761,9 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, struct sk_buff *skb; int err = 0; + if (!unicast && !rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; @@ -2760,6 +2793,9 @@ static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, struct net *net = block->net; struct sk_buff *skb; + if (!rtnl_notify_needed(net, flags, RTNLGRP_TC)) + return 0; + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b4a7952c5d7d..a40a9e84c75f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -732,7 +732,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, - .len = 128 }, + .len = 127 }, }; static const struct nla_policy diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index cb379849c51a..e53149a973a6 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -333,17 +333,22 @@ out: return q; } -static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) +static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, + struct netlink_ext_ack *extack) { unsigned long cl; const struct Qdisc_class_ops *cops = p->ops->cl_ops; - if (cops == NULL) - return NULL; + if (cops == NULL) { + NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); + return ERR_PTR(-EOPNOTSUPP); + } cl = cops->find(p, classid); - if (cl == 0) - return NULL; + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return ERR_PTR(-ENOENT); + } return cops->leaf(p, cl); } @@ -776,15 +781,12 @@ static u32 qdisc_alloc_handle(struct net_device *dev) void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { - bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; - if (n == 0 && len == 0) - return; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { @@ -793,17 +795,8 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) if (sch->flags & TCQ_F_NOPARENT) break; - /* Notify parent qdisc only if child qdisc becomes empty. - * - * If child was empty even before update then backlog - * counter is screwed and we skip notification because - * parent class is already passive. - * - * If the original child was offloaded then it is allowed - * to be seem as empty, so the parent is notified anyway. - */ - notify = !sch->q.qlen && !WARN_ON_ONCE(!n && - !qdisc_is_offloaded); + /* Notify parent qdisc only if child qdisc becomes empty. */ + notify = !sch->q.qlen; /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { @@ -812,6 +805,9 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { + /* Note that qlen_notify must be idempotent as it may get called + * multiple times. + */ cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } @@ -1509,7 +1505,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } @@ -1520,6 +1516,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } + if (IS_ERR(q)) + return PTR_ERR(q); if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); @@ -1613,7 +1611,9 @@ replay: NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); + if (IS_ERR(q)) + return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } @@ -2200,6 +2200,12 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, return -EOPNOTSUPP; } + /* Prevent creation of traffic classes with classid TC_H_ROOT */ + if (clid == TC_H_ROOT) { + NL_SET_ERR_MSG(extack, "Cannot create traffic class with classid TC_H_ROOT"); + return -EINVAL; + } + new_cl = cl; err = -EOPNOTSUPP; if (cops->change) diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index d7a4874543de..63c02040b426 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -95,10 +95,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) &q->stats, qdisc_pkt_len, codel_get_enqueue_time, drop_func, dequeue_func); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->stats.drop_count && sch->q.qlen) { + if (q->stats.drop_count) { qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; q->stats.drop_len = 0; @@ -171,7 +168,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index e35a4e90f4e6..3aee041c7bdb 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -36,6 +36,11 @@ struct drr_sched { struct Qdisc_class_hash clhash; }; +static bool cl_is_active(struct drr_class *cl) +{ + return !list_empty(&cl->alist); +} + static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) { struct drr_sched *q = qdisc_priv(sch); @@ -106,6 +111,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, return -ENOBUFS; gnet_stats_basic_sync_init(&cl->bstats); + INIT_LIST_HEAD(&cl->alist); cl->common.classid = classid; cl->quantum = quantum; cl->qdisc = qdisc_create_dflt(sch->dev_queue, @@ -228,7 +234,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg) { struct drr_class *cl = (struct drr_class *)arg; - list_del(&cl->alist); + list_del_init(&cl->alist); } static int drr_dump_class(struct Qdisc *sch, unsigned long arg, @@ -335,7 +341,6 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, 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) { @@ -345,7 +350,6 @@ 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)) { @@ -355,7 +359,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - if (first) { + if (!cl_is_active(cl)) { list_add_tail(&cl->alist, &q->active); cl->deficit = cl->quantum; } @@ -389,7 +393,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch) if (unlikely(skb == NULL)) goto out; if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del_init(&cl->alist); bstats_update(&cl->bstats, skb); qdisc_bstats_update(sch, skb); @@ -430,7 +434,7 @@ static void drr_reset_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->qdisc->q.qlen) - list_del(&cl->alist); + list_del_init(&cl->alist); qdisc_reset(cl->qdisc); } } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 9fd70462b41d..3ee46f6e005d 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -74,6 +74,11 @@ static const struct nla_policy ets_class_policy[TCA_ETS_MAX + 1] = { [TCA_ETS_QUANTA_BAND] = { .type = NLA_U32 }, }; +static bool cl_is_active(struct ets_class *cl) +{ + return !list_empty(&cl->alist); +} + static int ets_quantum_parse(struct Qdisc *sch, const struct nlattr *attr, unsigned int *quantum, struct netlink_ext_ack *extack) @@ -293,7 +298,7 @@ static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg) * to remove them. */ if (!ets_class_is_strict(q, cl) && sch->q.qlen) - list_del(&cl->alist); + list_del_init(&cl->alist); } static int ets_class_dump(struct Qdisc *sch, unsigned long arg, @@ -416,7 +421,6 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct ets_sched *q = qdisc_priv(sch); struct ets_class *cl; int err = 0; - bool first; cl = ets_classify(skb, sch, &err); if (!cl) { @@ -426,7 +430,6 @@ static int ets_qdisc_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)) { @@ -436,7 +439,7 @@ static int ets_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, return err; } - if (first && !ets_class_is_strict(q, cl)) { + if (!cl_is_active(cl) && !ets_class_is_strict(q, cl)) { list_add_tail(&cl->alist, &q->active); cl->deficit = cl->quantum; } @@ -488,7 +491,7 @@ static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch) if (unlikely(!skb)) goto out; if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); + list_del_init(&cl->alist); return ets_qdisc_dequeue_skb(sch, skb); } @@ -657,8 +660,8 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, } for (i = q->nbands; i < oldbands; i++) { if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del(&q->classes[i].alist); - qdisc_tree_flush_backlog(q->classes[i].qdisc); + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); @@ -713,7 +716,7 @@ static void ets_qdisc_reset(struct Qdisc *sch) for (band = q->nstrict; band < q->nbands; band++) { if (q->classes[band].qdisc->q.qlen) - list_del(&q->classes[band].alist); + list_del_init(&q->classes[band].alist); } for (band = 0; band < q->nbands; band++) qdisc_reset(q->classes[band].qdisc); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f59a2cb2c803..91f5ef6be0f2 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -901,7 +901,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); } while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 8c4fee063436..47b5a056165c 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -314,10 +314,8 @@ begin: } qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); - /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, - * or HTB crashes. Defer it for next round. - */ - if (q->cstats.drop_count && sch->q.qlen) { + + if (q->cstats.drop_count) { qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); q->cstats.drop_count = 0; @@ -433,7 +431,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit || q->memory_usage > q->memory_limit) { - struct sk_buff *skb = fq_codel_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); q->cstats.drop_len += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 68e6acd0f130..607c580d75e4 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -357,7 +357,7 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = fq_pie_qdisc_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); len_dropped += qdisc_pkt_len(skb); num_dropped += 1; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 872d127c9db4..fa7a1b69c0f3 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -913,7 +913,8 @@ static void gred_destroy(struct Qdisc *sch) for (i = 0; i < table->DPs; i++) gred_destroy_vq(table->tab[i]); - gred_offload(sch, TC_GRED_DESTROY); + if (table->opt) + gred_offload(sch, TC_GRED_DESTROY); kfree(table->opt); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 54dddc2ff502..61b91de8065f 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -176,6 +176,11 @@ struct hfsc_sched { #define HT_INFINITY 0xffffffffffffffffULL /* infinite time value */ +static bool cl_in_el_or_vttree(struct hfsc_class *cl) +{ + return ((cl->cl_flags & HFSC_FSC) && cl->cl_nactive) || + ((cl->cl_flags & HFSC_RSC) && !RB_EMPTY_NODE(&cl->el_node)); +} /* * eligible tree holds backlogged classes being sorted by their eligible times. @@ -204,7 +209,10 @@ eltree_insert(struct hfsc_class *cl) static inline void eltree_remove(struct hfsc_class *cl) { - rb_erase(&cl->el_node, &cl->sched->eligible); + if (!RB_EMPTY_NODE(&cl->el_node)) { + rb_erase(&cl->el_node, &cl->sched->eligible); + RB_CLEAR_NODE(&cl->el_node); + } } static inline void @@ -959,6 +967,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl != NULL) { int old_flags; + int len = 0; if (parentid) { if (cl->cl_parent && @@ -989,9 +998,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (usc != NULL) hfsc_change_usc(cl, usc, cur_time); + if (cl->qdisc->q.qlen != 0) + len = qdisc_peek_len(cl->qdisc); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ if (cl->qdisc->q.qlen != 0) { - int len = qdisc_peek_len(cl->qdisc); - if (cl->cl_flags & HFSC_RSC) { if (old_flags & HFSC_RSC) update_ed(cl, len); @@ -1033,6 +1046,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl == NULL) return -ENOBUFS; + RB_CLEAR_NODE(&cl->el_node); + err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); if (err) { kfree(cl); @@ -1217,7 +1232,8 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg) /* vttree is now handled in update_vf() so that update_vf(cl, 0, 0) * needs to be called explicitly to remove a class from vttree. */ - update_vf(cl, 0, 0); + if (cl->cl_nactive) + update_vf(cl, 0, 0); if (cl->cl_flags & HFSC_RSC) eltree_remove(cl); } @@ -1559,7 +1575,10 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) return err; } - if (first) { + sch->qstats.backlog += len; + sch->q.qlen++; + + if (first && !cl_in_el_or_vttree(cl)) { if (cl->cl_flags & HFSC_RSC) init_ed(cl, len); if (cl->cl_flags & HFSC_FSC) @@ -1574,9 +1593,6 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) } - sch->qstats.backlog += len; - sch->q.qlen++; - return NET_XMIT_SUCCESS; } @@ -1631,10 +1647,16 @@ hfsc_dequeue(struct Qdisc *sch) if (cl->qdisc->q.qlen != 0) { /* update ed */ next_len = qdisc_peek_len(cl->qdisc); - if (realtime) - update_ed(cl, next_len); - else - update_d(cl, next_len); + /* Check queue length again since some qdisc implementations + * (e.g., netem/codel) might empty the queue during the peek + * operation. + */ + if (cl->qdisc->q.qlen != 0) { + if (realtime) + update_ed(cl, next_len); + else + update_d(cl, next_len); + } } else { /* the class becomes passive */ eltree_remove(cl); diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index d26cd436cbe3..83fc44f20e31 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -560,7 +560,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, qlen = sch->q.qlen; prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = hhf_dequeue(sch); + struct sk_buff *skb = qdisc_dequeue_internal(sch, false); rtnl_kfree_skbs(skb, skb); } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index d23f8ea63082..1e19d3ffbf21 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -345,7 +345,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q, */ static inline void htb_next_rb_node(struct rb_node **n) { - *n = rb_next(*n); + if (*n) + *n = rb_next(*n); } /** @@ -606,8 +607,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) */ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(!cl->prio_activity); - + if (!cl->prio_activity) + return; htb_deactivate_prios(q, cl); cl->prio_activity = 0; } @@ -817,7 +818,9 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) u32 *pid; } stk[TC_HTB_MAXDEPTH], *sp = stk; - BUG_ON(!hprio->row.rb_node); + if (unlikely(!hprio->row.rb_node)) + return NULL; + sp->root = hprio->row.rb_node; sp->pptr = &hprio->ptr; sp->pid = &hprio->last_ptr_id; @@ -1733,8 +1736,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, if (cl->parent) cl->parent->children--; - if (cl->prio_activity) - htb_deactivate(q, cl); + htb_deactivate(q, cl); if (cl->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&cl->pq_node, @@ -1946,8 +1948,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); parent_qdisc = parent->leaf.q; - if (parent->prio_activity) - htb_deactivate(q, parent); + htb_deactivate(q, parent); /* remove from evt list because of level change */ if (parent->cmode != HTB_CAN_SEND) { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index cb38e58ee771..2613353defde 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -962,6 +962,41 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } +static const struct Qdisc_class_ops netem_class_ops; + +static int check_netem_in_tree(struct Qdisc *sch, bool duplicates, + struct netlink_ext_ack *extack) +{ + struct Qdisc *root, *q; + unsigned int i; + + root = qdisc_root_sleeping(sch); + + if (sch != root && root->ops->cl_ops == &netem_class_ops) { + if (duplicates || + ((struct netem_sched_data *)qdisc_priv(root))->duplicate) + goto err; + } + + if (!qdisc_dev(root)) + return 0; + + hash_for_each(qdisc_dev(root)->qdisc_hash, i, q, hash) { + if (sch != q && q->ops->cl_ops == &netem_class_ops) { + if (duplicates || + ((struct netem_sched_data *)qdisc_priv(q))->duplicate) + goto err; + } + } + + return 0; + +err: + NL_SET_ERR_MSG(extack, + "netem: cannot mix duplicating netems with other netems in tree"); + return -EINVAL; +} + /* Parse netlink message to set options */ static int netem_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) @@ -1020,6 +1055,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt, q->gap = qopt->gap; q->counter = 0; q->loss = qopt->loss; + + ret = check_netem_in_tree(sch, qopt->duplicate, extack); + if (ret) + goto unlock; + q->duplicate = qopt->duplicate; /* for compatibility with earlier versions. diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b60b31ef71cc..e1bb151a9719 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -190,7 +190,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, /* Drop excess packets if new limit is lower */ qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { - struct sk_buff *skb = __qdisc_dequeue_head(&sch->q); + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index fdc5ef52c3ee..fdd9caa41e80 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -211,7 +211,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt, memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); for (i = q->bands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->queues[i]); + qdisc_purge_queue(q->queues[i]); for (i = oldbands; i < q->bands; i++) { q->queues[i] = queues[i]; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index ed01634af82c..2f2863ae18ad 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -204,6 +204,11 @@ struct qfq_sched { */ enum update_reason {enqueue, requeue}; +static bool cl_is_active(struct qfq_class *cl) +{ + return !list_empty(&cl->alist); +} + static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) { struct qfq_sched *q = qdisc_priv(sch); @@ -349,7 +354,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl) struct qfq_aggregate *agg = cl->agg; - list_del(&cl->alist); /* remove from RR queue of the aggregate */ + list_del_init(&cl->alist); /* remove from RR queue of the aggregate */ if (list_empty(&agg->active)) /* agg is now inactive */ qfq_deactivate_agg(q, agg); } @@ -409,7 +414,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, bool existing = false; struct nlattr *tb[TCA_QFQ_MAX + 1]; struct qfq_aggregate *new_agg = NULL; - u32 weight, lmax, inv_w; + u32 weight, lmax, inv_w, old_weight, old_lmax; int err; int delta_w; @@ -443,12 +448,16 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; - if (cl != NULL && - lmax == cl->agg->lmax && - weight == cl->agg->class_weight) - return 0; /* nothing to change */ + if (cl != NULL) { + sch_tree_lock(sch); + old_weight = cl->agg->class_weight; + old_lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (lmax == old_lmax && weight == old_weight) + return 0; /* nothing to change */ + } - delta_w = weight - (cl ? cl->agg->class_weight : 0); + delta_w = weight - (cl ? old_weight : 0); if (q->wsum + delta_w > QFQ_MAX_WSUM) { pr_notice("qfq: total weight out of range (%d + %u)\n", @@ -478,6 +487,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, gnet_stats_basic_sync_init(&cl->bstats); cl->common.classid = classid; cl->deficit = lmax; + INIT_LIST_HEAD(&cl->alist); cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, NULL); @@ -530,9 +540,6 @@ destroy_class: static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); @@ -551,6 +558,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); + qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); @@ -621,6 +629,7 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, { struct qfq_class *cl = (struct qfq_class *)arg; struct nlattr *nest; + u32 class_weight, lmax; tcm->tcm_parent = TC_H_ROOT; tcm->tcm_handle = cl->common.classid; @@ -629,8 +638,13 @@ static int qfq_dump_class(struct Qdisc *sch, unsigned long arg, nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_QFQ_WEIGHT, cl->agg->class_weight) || - nla_put_u32(skb, TCA_QFQ_LMAX, cl->agg->lmax)) + + sch_tree_lock(sch); + class_weight = cl->agg->class_weight; + lmax = cl->agg->lmax; + sch_tree_unlock(sch); + if (nla_put_u32(skb, TCA_QFQ_WEIGHT, class_weight) || + nla_put_u32(skb, TCA_QFQ_LMAX, lmax)) goto nla_put_failure; return nla_nest_end(skb, nest); @@ -647,8 +661,10 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, memset(&xstats, 0, sizeof(xstats)); + sch_tree_lock(sch); xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; + sch_tree_unlock(sch); if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || @@ -984,7 +1000,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg, cl->deficit -= (int) len; if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */ - list_del(&cl->alist); + list_del_init(&cl->alist); else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) { cl->deficit += agg->lmax; list_move_tail(&cl->alist, &agg->active); @@ -1216,7 +1232,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct qfq_class *cl; struct qfq_aggregate *agg; int err = 0; - bool first; cl = qfq_classify(skb, sch, &err); if (cl == NULL) { @@ -1238,7 +1253,6 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, } 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); @@ -1254,8 +1268,8 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch, ++sch->q.qlen; agg = cl->agg; - /* if the queue was not empty, then done here */ - if (!first) { + /* if the class is active, then done here */ + if (cl_is_active(cl)) { if (unlikely(skb == cl->qdisc->ops->peek(cl->qdisc)) && list_first_entry(&agg->active, struct qfq_class, alist) == cl && cl->deficit < len) @@ -1417,6 +1431,8 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) struct qfq_sched *q = qdisc_priv(sch); struct qfq_class *cl = (struct qfq_class *)arg; + if (list_empty(&cl->alist)) + return; qfq_deactivate_class(q, cl); } @@ -1487,6 +1503,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 16277b6a0238..3c6b4460cf2c 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -283,7 +283,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, q->userbits = userbits; q->limit = ctl->limit; if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old_child = q->qdisc; q->qdisc = child; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 60754f366ab7..e871cb53946a 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -310,7 +310,10 @@ drop: /* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */ x = q->tail->next; slot = &q->slots[x]; - q->tail->next = slot->next; + if (slot->next == x) + q->tail = NULL; /* no more active slots */ + else + q->tail->next = slot->next; q->ht[slot->hash] = SFQ_EMPTY_SLOT; goto drop; } @@ -631,6 +634,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, struct red_parms *p = NULL; struct sk_buff *to_free = NULL; struct sk_buff *tail = NULL; + unsigned int maxflows; + unsigned int quantum; + unsigned int divisor; + int perturb_period; + u8 headdrop; + u8 maxdepth; + int limit; + u8 flags; + if (opt->nla_len < nla_attr_size(sizeof(*ctl))) return -EINVAL; @@ -644,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); return -EINVAL; } + + if (ctl->perturb_period < 0 || + ctl->perturb_period > INT_MAX / HZ) { + NL_SET_ERR_MSG_MOD(extack, "invalid perturb period"); + return -EINVAL; + } + perturb_period = ctl->perturb_period * HZ; + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; @@ -652,39 +672,62 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt, if (!p) return -ENOMEM; } - if (ctl->limit == 1) { - NL_SET_ERR_MSG_MOD(extack, "invalid limit"); - return -EINVAL; - } + sch_tree_lock(sch); + + limit = q->limit; + divisor = q->divisor; + headdrop = q->headdrop; + maxdepth = q->maxdepth; + maxflows = q->maxflows; + quantum = q->quantum; + flags = q->flags; + + /* update and validate configuration */ if (ctl->quantum) - q->quantum = ctl->quantum; - WRITE_ONCE(q->perturb_period, ctl->perturb_period * HZ); + quantum = ctl->quantum; if (ctl->flows) - q->maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); + maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS); if (ctl->divisor) { - q->divisor = ctl->divisor; - q->maxflows = min_t(u32, q->maxflows, q->divisor); + divisor = ctl->divisor; + maxflows = min_t(u32, maxflows, divisor); } if (ctl_v1) { if (ctl_v1->depth) - q->maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); + maxdepth = min_t(u32, ctl_v1->depth, SFQ_MAX_DEPTH); if (p) { - swap(q->red_parms, p); - red_set_parms(q->red_parms, + red_set_parms(p, ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog, ctl_v1->Plog, ctl_v1->Scell_log, NULL, ctl_v1->max_P); } - q->flags = ctl_v1->flags; - q->headdrop = ctl_v1->headdrop; + flags = ctl_v1->flags; + headdrop = ctl_v1->headdrop; } if (ctl->limit) { - q->limit = min_t(u32, ctl->limit, q->maxdepth * q->maxflows); - q->maxflows = min_t(u32, q->maxflows, q->limit); + limit = min_t(u32, ctl->limit, maxdepth * maxflows); + maxflows = min_t(u32, maxflows, limit); } + if (limit == 1) { + sch_tree_unlock(sch); + kfree(p); + NL_SET_ERR_MSG_MOD(extack, "invalid limit"); + return -EINVAL; + } + + /* commit configuration */ + q->limit = limit; + q->divisor = divisor; + q->headdrop = headdrop; + q->maxdepth = maxdepth; + q->maxflows = maxflows; + WRITE_ONCE(q->perturb_period, perturb_period); + q->quantum = quantum; + q->flags = flags; + if (p) + swap(q->red_parms, p); qlen = sch->q.qlen; while (sch->q.qlen > q->limit) { diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 5df2dacb7b1a..05aa363a7fee 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -121,8 +121,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Check to update highest and lowest priorities. */ if (skb_queue_empty(lp_qdisc)) { if (q->lowest_prio == q->highest_prio) { - /* The incoming packet is the only packet in queue. */ - BUG_ON(sch->q.qlen != 1); q->lowest_prio = prio; q->highest_prio = prio; } else { @@ -154,7 +152,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch) /* Update highest priority field. */ if (skb_queue_empty(hpq)) { if (q->lowest_prio == q->highest_prio) { - BUG_ON(sch->q.qlen); q->highest_prio = 0; q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1; } else { diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index c4c91b55e98b..ebf67b8a6ee7 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -451,7 +451,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); if (child) { - qdisc_tree_flush_backlog(q->qdisc); + qdisc_purge_queue(q->qdisc); old = q->qdisc; q->qdisc = child; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index bcd3384ab07a..036dc574af4f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -497,9 +497,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, continue; fl4->fl4_sport = laddr->a.v4.sin_port; - flowi4_update_output(fl4, - asoc->base.sk->sk_bound_dev_if, - RT_CONN_FLAGS_TOS(asoc->base.sk, tos), + flowi4_update_output(fl4, asoc->base.sk->sk_bound_dev_if, daddr->v4.sin_addr.s_addr, laddr->a.v4.sin_addr.s_addr); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0b201cd811a1..8a8a5cf8d8e6 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -70,8 +70,9 @@ /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); -static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len); +static int sctp_wait_for_sndbuf(struct sctp_association *asoc, + struct sctp_transport *transport, + long *timeo_p, size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -1826,7 +1827,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); + err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len); if (err) goto err; if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { @@ -9088,7 +9089,8 @@ static void __sctp_write_space(struct sctp_association *asoc) wq = rcu_dereference(sk->sk_wq); if (wq) { if (waitqueue_active(&wq->wait)) - wake_up_interruptible(&wq->wait); + wake_up_interruptible_poll(&wq->wait, EPOLLOUT | + EPOLLWRNORM | EPOLLWRBAND); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. @@ -9203,8 +9205,9 @@ void sctp_sock_rfree(struct sk_buff *skb) /* Helper function to wait for space in the sndbuf. */ -static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len) +static int sctp_wait_for_sndbuf(struct sctp_association *asoc, + struct sctp_transport *transport, + long *timeo_p, size_t msg_len) { struct sock *sk = asoc->base.sk; long current_timeo = *timeo_p; @@ -9214,7 +9217,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); - /* Increment the association's refcnt. */ + /* Increment the transport and association's refcnt. */ + if (transport) + sctp_transport_hold(transport); sctp_association_hold(asoc); /* Wait on the association specific sndbuf space. */ @@ -9223,7 +9228,7 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, TASK_INTERRUPTIBLE); if (asoc->base.dead) goto do_dead; - if (!*timeo_p) + if ((!*timeo_p) || (transport && transport->dead)) goto do_nonblock; if (sk->sk_err || asoc->state >= SCTP_STATE_SHUTDOWN_PENDING) goto do_error; @@ -9248,7 +9253,9 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, out: finish_wait(&asoc->wait, &wait); - /* Release the association's refcnt. */ + /* Release the transport and association's refcnt. */ + if (transport) + sctp_transport_put(transport); sctp_association_put(asoc); return err; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index ee6514af830f..0527728aee98 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 916dc2e81e42..f3d09998c24d 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -518,6 +518,8 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } +static DEFINE_MUTEX(sctp_sysctl_mutex); + static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -542,6 +544,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, if (new_value > max || new_value < min) return -EINVAL; + mutex_lock(&sctp_sysctl_mutex); net->sctp.udp_port = new_value; sctp_udp_sock_stop(net); if (new_value) { @@ -554,6 +557,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, lock_sock(sk); sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); release_sock(sk); + mutex_unlock(&sctp_sysctl_mutex); } return ret; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 2990365c2f2c..87ed33b9db1b 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -117,6 +117,8 @@ fail: */ void sctp_transport_free(struct sctp_transport *transport) { + transport->dead = 1; + /* Try to delete the heartbeat timer. */ if (del_timer(&transport->hb_timer)) sctp_transport_put(transport); diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 399314cfab90..af12e0215274 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -1080,14 +1080,16 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; + struct net_device *base_ndev; struct net *net; - ndev = pnet_find_base_ndev(ndev); + base_ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); - if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, + if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid) && + smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { - smc_pnet_find_rdma_dev(ndev, ini); + smc_pnet_find_rdma_dev(base_ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b6529a9d37d3..a390a4e5592f 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -275,9 +275,6 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, old = rcu_dereference_protected(clnt->cl_xprt, lockdep_is_held(&clnt->cl_lock)); - if (!xprt_bound(xprt)) - clnt->cl_autobind = 1; - clnt->cl_timeout = timeout; rcu_assign_pointer(clnt->cl_xprt, xprt); spin_unlock(&clnt->cl_lock); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 82afb56695f8..1ec20163a0b7 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -797,9 +797,10 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) } trace_rpcb_setport(child, map->r_status, map->r_port); - xprt->ops->set_port(xprt, map->r_port); - if (map->r_port) + if (map->r_port) { + xprt->ops->set_port(xprt, map->r_port); xprt_set_bound(xprt); + } } /* diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 9b45fbdc90ca..73bc39281ef5 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,6 +276,8 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { + if (unlikely(current->flags & PF_EXITING)) + return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2e14d4c37e2d..9aec24490e8f 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -381,7 +381,7 @@ bool switchdev_port_obj_act_is_deferred(struct net_device *dev, EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); -static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); +static RAW_NOTIFIER_HEAD(switchdev_blocking_notif_chain); /** * register_switchdev_notifier - Register notifier @@ -427,17 +427,27 @@ EXPORT_SYMBOL_GPL(call_switchdev_notifiers); int register_switchdev_blocking_notifier(struct notifier_block *nb) { - struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain; + struct raw_notifier_head *chain = &switchdev_blocking_notif_chain; + int err; + + rtnl_lock(); + err = raw_notifier_chain_register(chain, nb); + rtnl_unlock(); - return blocking_notifier_chain_register(chain, nb); + return err; } EXPORT_SYMBOL_GPL(register_switchdev_blocking_notifier); int unregister_switchdev_blocking_notifier(struct notifier_block *nb) { - struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain; + struct raw_notifier_head *chain = &switchdev_blocking_notif_chain; + int err; - return blocking_notifier_chain_unregister(chain, nb); + rtnl_lock(); + err = raw_notifier_chain_unregister(chain, nb); + rtnl_unlock(); + + return err; } EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier); @@ -445,10 +455,11 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info, struct netlink_ext_ack *extack) { + ASSERT_RTNL(); info->dev = dev; info->extack = extack; - return blocking_notifier_call_chain(&switchdev_blocking_notif_chain, - val, info); + return raw_notifier_call_chain(&switchdev_blocking_notif_chain, + val, info); } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 25c18f8783ce..d52829c6aa47 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -425,7 +425,7 @@ static void tipc_aead_free(struct rcu_head *rp) } free_percpu(aead->tfm_entry); kfree_sensitive(aead->key); - kfree(aead); + kfree_sensitive(aead); } static int tipc_aead_users(struct tipc_aead __rcu *aead) @@ -817,12 +817,20 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb, goto exit; } + /* Get net to avoid freed tipc_crypto when delete namespace */ + if (!maybe_get_net(aead->crypto->net)) { + tipc_bearer_put(b); + rc = -ENODEV; + goto exit; + } + /* Now, do encrypt */ rc = crypto_aead_encrypt(req); if (rc == -EINPROGRESS || rc == -EBUSY) return rc; tipc_bearer_put(b); + put_net(aead->crypto->net); exit: kfree(ctx); @@ -860,6 +868,7 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err) kfree(tx_ctx); tipc_bearer_put(b); tipc_aead_put(aead); + put_net(net); } /** diff --git a/net/tipc/link.c b/net/tipc/link.c index 8715c9b05f90..d6a8f0aa531b 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1068,6 +1068,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) { if (imp == TIPC_SYSTEM_IMPORTANCE) { pr_warn("%s<%s>, link overflow", link_rst_msg, l->name); + __skb_queue_purge(list); return -ENOBUFS; } rc = link_schedule_user(l, hdr); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 9618e4429f0f..23efd35adaa3 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net) if (!mon) continue; write_lock_bh(&mon->lock); - mon->self->addr = tipc_own_addr(net); + if (mon->self) + mon->self->addr = tipc_own_addr(net); write_unlock_bh(&mon->lock); } } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 69c88cc03887..0445c91db009 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -699,8 +699,10 @@ static void tipc_topsrv_stop(struct net *net) for (id = 0; srv->idr_in_use; id++) { con = idr_find(&srv->conn_idr, id); if (con) { + conn_get(con); spin_unlock_bh(&srv->idr_lock); tipc_conn_close(con); + conn_put(con); spin_lock_bh(&srv->idr_lock); } } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index f5bd75d931c1..e1305d159834 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -489,7 +489,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = tipc_bearer_find(net, bname); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } @@ -500,7 +500,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); b = rtnl_dereference(tn->bearer_list[bid]); - if (!b) { + if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) { rtnl_unlock(); return -EINVAL; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 75cd20c0e3fd..14d01558311d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -900,6 +900,11 @@ static int tls_setsockopt(struct sock *sk, int level, int optname, return do_tls_setsockopt(sk, optname, optval, optlen); } +static int tls_disconnect(struct sock *sk, int flags) +{ + return -EOPNOTSUPP; +} + struct tls_context *tls_ctx_create(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -995,6 +1000,7 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_BASE][TLS_BASE] = *base; prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; + prot[TLS_BASE][TLS_BASE].disconnect = tls_disconnect; prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index f37f4a0fcd3c..b7ed76c0e576 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -396,7 +396,6 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) return 0; shinfo = skb_shinfo(strp->anchor); - shinfo->frag_list = NULL; /* If we don't know the length go max plus page for cipher overhead */ need_spc = strp->stm.full_len ?: TLS_MAX_PAYLOAD_SIZE + PAGE_SIZE; @@ -412,6 +411,8 @@ static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) page, 0, 0); } + shinfo->frag_list = NULL; + strp->copy_mode = 1; strp->stm.offset = 0; @@ -511,9 +512,8 @@ static int tls_strp_read_sock(struct tls_strparser *strp) if (inq < strp->stm.full_len) return tls_strp_read_copy(strp, true); + tls_strp_load_anchor_with_queue(strp, inq); if (!strp->stm.full_len) { - tls_strp_load_anchor_with_queue(strp, inq); - sz = tls_rx_msg_size(strp, strp->anchor); if (sz < 0) { tls_strp_abort_strp(strp, sz); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5310441240e7..6ac3dcbe87b5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -868,6 +868,19 @@ more_data: delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); delta -= msg->sg.size; + + if ((s32)delta > 0) { + /* It indicates that we executed bpf_msg_pop_data(), + * causing the plaintext data size to decrease. + * Therefore the encrypted data size also needs to + * correspondingly decrease. We only need to subtract + * delta to calculate the new ciphertext length since + * ktls does not support block encryption. + */ + struct sk_msg *enc = &ctx->open_rec->msg_encrypted; + + sk_msg_trim(sk, enc, enc->sg.size - delta); + } } if (msg->cork_bytes && msg->cork_bytes > msg->sg.size && !enospc && !full_record) { @@ -904,6 +917,13 @@ more_data: &msg_redir, send, flags); lock_sock(sk); if (err < 0) { + /* Regardless of whether the data represented by + * msg_redir is sent successfully, we have already + * uncharged it via sk_msg_return_zero(). The + * msg->sg.size represents the remaining unprocessed + * data, which needs to be uncharged here. + */ + sk_mem_uncharge(sk, msg->sg.size); *copied -= sk_msg_free_nocharge(sk, &msg_redir); msg->sg.size = 0; } @@ -1075,9 +1095,13 @@ alloc_encrypted: num_async++; else if (ret == -ENOMEM) goto wait_for_memory; - else if (ctx->open_rec && ret == -ENOSPC) + else if (ctx->open_rec && ret == -ENOSPC) { + if (msg_pl->cork_bytes) { + ret = 0; + goto send_end; + } goto rollback_iter; - else if (ret != -EAGAIN) + } else if (ret != -EAGAIN) goto send_end; } continue; diff --git a/net/unix/Kconfig b/net/unix/Kconfig index b7f811216820..8b5d04210d7c 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -4,7 +4,7 @@ # config UNIX - tristate "Unix domain sockets" + bool "Unix domain sockets" help If you say Y here, you will include support for Unix domain sockets; sockets are the standard Unix mechanism for establishing and @@ -14,17 +14,8 @@ config UNIX an embedded system or something similar, you therefore definitely want to say Y here. - To compile this driver as a module, choose M here: the module will be - called unix. Note that several important services won't work - correctly if you say M here and then neglect to load the module. - Say Y unless you know what you are doing. -config UNIX_SCM - bool - depends on UNIX - default y - config AF_UNIX_OOB bool depends on UNIX diff --git a/net/unix/Makefile b/net/unix/Makefile index 20491825b4d0..4ddd125c4642 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -11,5 +11,3 @@ unix-$(CONFIG_BPF_SYSCALL) += unix_bpf.o obj-$(CONFIG_UNIX_DIAG) += unix_diag.o unix_diag-y := diag.o - -obj-$(CONFIG_UNIX_SCM) += scm.o diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5ce60087086c..2c33d787b860 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -116,8 +116,6 @@ #include <linux/file.h> #include <linux/btf_ids.h> -#include "scm.h" - static atomic_long_t unix_nr_socks; static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2]; static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; @@ -579,6 +577,11 @@ static void unix_sock_destructor(struct sock *sk) #endif } +static unsigned int unix_skb_len(const struct sk_buff *skb) +{ + return skb->len - UNIXCB(skb).consumed; +} + static void unix_release_sock(struct sock *sk, int embrion) { struct unix_sock *u = unix_sk(sk); @@ -606,20 +609,23 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } + u->oob_skb = NULL; #endif wake_up_interruptible_all(&u->peer_wait); if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (skb && !unix_skb_len(skb)) + skb = skb_peek_next(skb, &sk->sk_receive_queue); +#endif unix_state_lock(skpair); /* No more writes */ WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK); - if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion) + if (skb || embrion) WRITE_ONCE(skpair->sk_err, ECONNRESET); unix_state_unlock(skpair); skpair->sk_state_change(skpair); @@ -956,11 +962,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; u = unix_sk(sk); - u->inflight = 0; + u->listener = NULL; + u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1559,6 +1565,7 @@ restart: newsk->sk_type = sk->sk_type; init_peercred(newsk); newu = unix_sk(newsk); + newu->listener = other; RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); @@ -1652,8 +1659,8 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { struct sock *sk = sock->sk; - struct sock *tsk; struct sk_buff *skb; + struct sock *tsk; int err; err = -EOPNOTSUPP; @@ -1683,6 +1690,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags, /* attach accepted sock to socket */ unix_state_lock(tsk); + unix_update_edges(unix_sk(tsk)); newsock->state = SS_CONNECTED; unix_sock_inherit_flags(sock, newsock); sock_graft(tsk, newsock); @@ -1726,51 +1734,65 @@ out: return err; } +/* The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + +static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + + /* Need to duplicate file references for the sake of garbage + * collection. Otherwise a socket in the fps might become a + * candidate for GC while the skb is not yet queued. + */ + UNIXCB(skb).fp = scm_fp_dup(scm->fp); + if (!UNIXCB(skb).fp) + return -ENOMEM; + + if (unix_prepare_fpl(UNIXCB(skb).fp)) + return -ENOMEM; + + return 0; +} + +static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) +{ + scm->fp = UNIXCB(skb).fp; + UNIXCB(skb).fp = NULL; + + unix_destroy_fpl(scm->fp); +} + static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb) { scm->fp = scm_fp_dup(UNIXCB(skb).fp); +} - /* - * Garbage collection of unix sockets starts by selecting a set of - * candidate sockets which have reference only from being in flight - * (total_refs == inflight_refs). This condition is checked once during - * the candidate collection phase, and candidates are marked as such, so - * that non-candidates can later be ignored. While inflight_refs is - * protected by unix_gc_lock, total_refs (file count) is not, hence this - * is an instantaneous decision. - * - * Once a candidate, however, the socket must not be reinstalled into a - * file descriptor while the garbage collection is in progress. - * - * If the above conditions are met, then the directed graph of - * candidates (*) does not change while unix_gc_lock is held. - * - * Any operations that changes the file count through file descriptors - * (dup, close, sendmsg) does not change the graph since candidates are - * not installed in fds. - * - * Dequeing a candidate via recvmsg would install it into an fd, but - * that takes unix_gc_lock to decrement the inflight count, so it's - * serialized with garbage collection. - * - * MSG_PEEK is special in that it does not change the inflight count, - * yet does install the socket into an fd. The following lock/unlock - * pair is to ensure serialization with garbage collection. It must be - * done between incrementing the file count and installing the file into - * an fd. - * - * If garbage collection starts after the barrier provided by the - * lock/unlock, then it will see the elevated refcount and not mark this - * as a candidate. If a garbage collection is already in progress - * before the file count was incremented, then the lock/unlock pair will - * ensure that garbage collection is finished before progressing to - * installing the fd. - * - * (*) A -> B where B is on the queue of A or B is on the queue of C - * which is on the queue of listening socket A. - */ - spin_lock(&unix_gc_lock); - spin_unlock(&unix_gc_lock); +static void unix_destruct_scm(struct sk_buff *skb) +{ + struct scm_cookie scm; + + memset(&scm, 0, sizeof(scm)); + scm.pid = UNIXCB(skb).pid; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); + + /* Alas, it calls VFS */ + /* So fscking what? fput() had been SMP-safe since the last Summer */ + scm_destroy(&scm); + sock_wfree(skb); } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1845,8 +1867,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_add(fp->count, &u->scm_stat.nr_fds); + unix_add_edges(fp, u); + } } static void scm_stat_del(struct sock *sk, struct sk_buff *skb) @@ -1854,8 +1878,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb) struct scm_fp_list *fp = UNIXCB(skb).fp; struct unix_sock *u = unix_sk(sk); - if (unlikely(fp && fp->count)) + if (unlikely(fp && fp->count)) { atomic_sub(fp->count, &u->scm_stat.nr_fds); + unix_del_edges(fp); + } } /* @@ -1875,11 +1901,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, long timeo; int err; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags&MSG_OOB) goto out; @@ -2114,13 +2141,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other } maybe_add_creds(skb, sock, other); - skb_get(skb); - scm_stat_add(other, skb); spin_lock(&other->sk_receive_queue.lock); - if (ousk->oob_skb) - consume_skb(ousk->oob_skb); WRITE_ONCE(ousk->oob_skb, skb); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); @@ -2145,11 +2168,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, bool fds_sent = false; int data_len; - wait_for_unix_gc(); err = scm_send(sock, msg, &scm, false); if (err < 0) return err; + wait_for_unix_gc(scm.fp); + err = -EOPNOTSUPP; if (msg->msg_flags & MSG_OOB) { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) @@ -2580,11 +2604,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, return timeo; } -static unsigned int unix_skb_len(const struct sk_buff *skb) -{ - return skb->len - UNIXCB(skb).consumed; -} - struct unix_stream_read_state { int (*recv_actor)(struct sk_buff *, int, int, struct unix_stream_read_state *); @@ -2599,11 +2618,11 @@ struct unix_stream_read_state { #if IS_ENABLED(CONFIG_AF_UNIX_OOB) static int unix_stream_recv_urg(struct unix_stream_read_state *state) { + struct sk_buff *oob_skb, *read_skb = NULL; struct socket *sock = state->socket; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); int chunk = 1; - struct sk_buff *oob_skb; mutex_lock(&u->iolock); unix_state_lock(sk); @@ -2618,10 +2637,15 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) oob_skb = u->oob_skb; - if (!(state->flags & MSG_PEEK)) + if (!(state->flags & MSG_PEEK)) { WRITE_ONCE(u->oob_skb, NULL); - else - skb_get(oob_skb); + + if (oob_skb->prev != (struct sk_buff *)&sk->sk_receive_queue && + !unix_skb_len(oob_skb->prev)) { + read_skb = oob_skb->prev; + __skb_unlink(read_skb, &sk->sk_receive_queue); + } + } spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); @@ -2631,10 +2655,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - consume_skb(oob_skb); - mutex_unlock(&u->iolock); + consume_skb(read_skb); + if (chunk < 0) return -EFAULT; @@ -2660,12 +2684,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (copied) { skb = NULL; } else if (!(flags & MSG_PEEK)) { - if (sock_flag(sk, SOCK_URGINLINE)) { - WRITE_ONCE(u->oob_skb, NULL); - consume_skb(skb); - } else { + WRITE_ONCE(u->oob_skb, NULL); + + if (!sock_flag(sk, SOCK_URGINLINE)) { __skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); unlinked_skb = skb; skb = skb_peek(&sk->sk_receive_queue); } @@ -2676,10 +2698,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, spin_unlock(&sk->sk_receive_queue.lock); - if (unlinked_skb) { - WARN_ON_ONCE(skb_unref(unlinked_skb)); - kfree_skb(unlinked_skb); - } + kfree_skb(unlinked_skb); } return skb; } @@ -2722,7 +2741,6 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) unix_state_unlock(sk); if (drop) { - WARN_ON_ONCE(skb_unref(skb)); kfree_skb(skb); return -EAGAIN; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index d2fc795394a5..0068e758be4d 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -81,278 +81,533 @@ #include <net/scm.h> #include <net/tcp_states.h> -#include "scm.h" +struct unix_sock *unix_get_socket(struct file *filp) +{ + struct inode *inode = file_inode(filp); + + /* Socket ? */ + if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { + struct socket *sock = SOCKET_I(inode); + const struct proto_ops *ops; + struct sock *sk = sock->sk; + + ops = READ_ONCE(sock->ops); -/* Internal data structures and random procedures: */ + /* PF_UNIX ? */ + if (sk && ops && ops->family == PF_UNIX) + return unix_sk(sk); + } -static LIST_HEAD(gc_candidates); -static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); + return NULL; +} -static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) { - struct sk_buff *skb; - struct sk_buff *next; - - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - /* Do we have file descriptors ? */ - if (UNIXCB(skb).fp) { - bool hit = false; - /* Process the descriptors of this socket */ - int nfd = UNIXCB(skb).fp->count; - struct file **fp = UNIXCB(skb).fp->fp; - - while (nfd--) { - /* Get the socket the fd matches if it indeed does so */ - struct sock *sk = unix_get_socket(*fp++); - - if (sk) { - struct unix_sock *u = unix_sk(sk); - - /* Ignore non-candidates, they could - * have been added to the queues after - * starting the garbage collection - */ - if (test_bit(UNIX_GC_CANDIDATE, &u->gc_flags)) { - hit = true; - - func(u); - } - } - } - if (hit && hitlist != NULL) { - __skb_unlink(skb, &x->sk_receive_queue); - __skb_queue_tail(hitlist, skb); - } - } + /* If an embryo socket has a fd, + * the listener indirectly holds the fd's refcnt. + */ + if (edge->successor->listener) + return unix_sk(edge->successor->listener)->vertex; + + return edge->successor->vertex; +} + +static bool unix_graph_maybe_cyclic; +static bool unix_graph_grouped; + +static void unix_update_graph(struct unix_vertex *vertex) +{ + /* If the receiver socket is not inflight, no cyclic + * reference could be formed. + */ + if (!vertex) + return; + + unix_graph_maybe_cyclic = true; + unix_graph_grouped = false; +} + +static LIST_HEAD(unix_unvisited_vertices); + +enum unix_vertex_index { + UNIX_VERTEX_INDEX_MARK1, + UNIX_VERTEX_INDEX_MARK2, + UNIX_VERTEX_INDEX_START, +}; + +static unsigned long unix_vertex_unvisited_index = UNIX_VERTEX_INDEX_MARK1; + +static void unix_add_edge(struct scm_fp_list *fpl, struct unix_edge *edge) +{ + struct unix_vertex *vertex = edge->predecessor->vertex; + + if (!vertex) { + vertex = list_first_entry(&fpl->vertices, typeof(*vertex), entry); + vertex->index = unix_vertex_unvisited_index; + vertex->out_degree = 0; + INIT_LIST_HEAD(&vertex->edges); + INIT_LIST_HEAD(&vertex->scc_entry); + + list_move_tail(&vertex->entry, &unix_unvisited_vertices); + edge->predecessor->vertex = vertex; } - spin_unlock(&x->sk_receive_queue.lock); + + vertex->out_degree++; + list_add_tail(&edge->vertex_entry, &vertex->edges); + + unix_update_graph(unix_edge_successor(edge)); } -static void scan_children(struct sock *x, void (*func)(struct unix_sock *), - struct sk_buff_head *hitlist) +static void unix_del_edge(struct scm_fp_list *fpl, struct unix_edge *edge) { - if (x->sk_state != TCP_LISTEN) { - scan_inflight(x, func, hitlist); - } else { - struct sk_buff *skb; - struct sk_buff *next; - struct unix_sock *u; - LIST_HEAD(embryos); + struct unix_vertex *vertex = edge->predecessor->vertex; - /* For a listening socket collect the queued embryos - * and perform a scan on them as well. - */ - spin_lock(&x->sk_receive_queue.lock); - skb_queue_walk_safe(&x->sk_receive_queue, skb, next) { - u = unix_sk(skb->sk); + if (!fpl->dead) + unix_update_graph(unix_edge_successor(edge)); - /* An embryo cannot be in-flight, so it's safe - * to use the list link. - */ - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &embryos); - } - spin_unlock(&x->sk_receive_queue.lock); + list_del(&edge->vertex_entry); + vertex->out_degree--; - while (!list_empty(&embryos)) { - u = list_entry(embryos.next, struct unix_sock, link); - scan_inflight(&u->sk, func, hitlist); - list_del_init(&u->link); - } + if (!vertex->out_degree) { + edge->predecessor->vertex = NULL; + list_move_tail(&vertex->entry, &fpl->vertices); } } -static void dec_inflight(struct unix_sock *usk) +static void unix_free_vertices(struct scm_fp_list *fpl) { - usk->inflight--; + struct unix_vertex *vertex, *next_vertex; + + list_for_each_entry_safe(vertex, next_vertex, &fpl->vertices, entry) { + list_del(&vertex->entry); + kfree(vertex); + } } -static void inc_inflight(struct unix_sock *usk) +static DEFINE_SPINLOCK(unix_gc_lock); +unsigned int unix_tot_inflight; + +void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { - usk->inflight++; + int i = 0, j = 0; + + spin_lock(&unix_gc_lock); + + if (!fpl->count_unix) + goto out; + + do { + struct unix_sock *inflight = unix_get_socket(fpl->fp[j++]); + struct unix_edge *edge; + + if (!inflight) + continue; + + edge = fpl->edges + i++; + edge->predecessor = inflight; + edge->successor = receiver; + + unix_add_edge(fpl, edge); + } while (i < fpl->count_unix); + + receiver->scm_stat.nr_unix_fds += fpl->count_unix; + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = true; + + unix_free_vertices(fpl); } -static void inc_inflight_move_tail(struct unix_sock *u) +void unix_del_edges(struct scm_fp_list *fpl) { - u->inflight++; + struct unix_sock *receiver; + int i = 0; + + spin_lock(&unix_gc_lock); + + if (!fpl->count_unix) + goto out; + + do { + struct unix_edge *edge = fpl->edges + i++; + + unix_del_edge(fpl, edge); + } while (i < fpl->count_unix); + + if (!fpl->dead) { + receiver = fpl->edges[0].successor; + receiver->scm_stat.nr_unix_fds -= fpl->count_unix; + } + WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); +out: + WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); + + spin_unlock(&unix_gc_lock); + + fpl->inflight = false; +} - /* If this still might be part of a cycle, move it to the end - * of the list, so that it's checked even if it was already - * passed over +void unix_update_edges(struct unix_sock *receiver) +{ + /* nr_unix_fds is only updated under unix_state_lock(). + * If it's 0 here, the embryo socket is not part of the + * inflight graph, and GC will not see it, so no lock needed. */ - if (test_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags)) - list_move_tail(&u->link, &gc_candidates); + if (!receiver->scm_stat.nr_unix_fds) { + receiver->listener = NULL; + } else { + spin_lock(&unix_gc_lock); + unix_update_graph(unix_sk(receiver->listener)->vertex); + receiver->listener = NULL; + spin_unlock(&unix_gc_lock); + } } -static bool gc_in_progress; -#define UNIX_INFLIGHT_TRIGGER_GC 16000 +int unix_prepare_fpl(struct scm_fp_list *fpl) +{ + struct unix_vertex *vertex; + int i; + + if (!fpl->count_unix) + return 0; + + for (i = 0; i < fpl->count_unix; i++) { + vertex = kmalloc(sizeof(*vertex), GFP_KERNEL); + if (!vertex) + goto err; + + list_add(&vertex->entry, &fpl->vertices); + } + + fpl->edges = kvmalloc_array(fpl->count_unix, sizeof(*fpl->edges), + GFP_KERNEL_ACCOUNT); + if (!fpl->edges) + goto err; -void wait_for_unix_gc(void) + return 0; + +err: + unix_free_vertices(fpl); + return -ENOMEM; +} + +void unix_destroy_fpl(struct scm_fp_list *fpl) { - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight() and gc_in_progress(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); - wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); + if (fpl->inflight) + unix_del_edges(fpl); + + kvfree(fpl->edges); + unix_free_vertices(fpl); } -/* The external entry point: unix_gc() */ -void unix_gc(void) +static bool unix_vertex_dead(struct unix_vertex *vertex) { - struct sk_buff *next_skb, *skb; + struct unix_edge *edge; struct unix_sock *u; - struct unix_sock *next; - struct sk_buff_head hitlist; - struct list_head cursor; - LIST_HEAD(not_cycle_list); + long total_ref; - spin_lock(&unix_gc_lock); + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); - /* Avoid a recursive GC. */ - if (gc_in_progress) - goto out; + /* The vertex's fd can be received by a non-inflight socket. */ + if (!next_vertex) + return false; - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ - WRITE_ONCE(gc_in_progress, true); + /* The vertex's fd can be received by an inflight socket in + * another SCC. + */ + if (next_vertex->scc_index != vertex->scc_index) + return false; + } - /* First, select candidates for garbage collection. Only - * in-flight sockets are considered, and from those only ones - * which don't have any external reference. - * - * Holding unix_gc_lock will protect these candidates from - * being detached, and hence from gaining an external - * reference. Since there are no possible receivers, all - * buffers currently on the candidates' queues stay there - * during the garbage collection. - * - * We also know that no new candidate can be added onto the - * receive queues. Other, non candidate sockets _can_ be - * added to queue, so we must make sure only to touch - * candidates. - * - * Embryos, though never candidates themselves, affect which - * candidates are reachable by the garbage collector. Before - * being added to a listener's queue, an embryo may already - * receive data carrying SCM_RIGHTS, potentially making the - * passed socket a candidate that is not yet reachable by the - * collector. It becomes reachable once the embryo is - * enqueued. Therefore, we must ensure that no SCM-laden - * embryo appears in a (candidate) listener's queue between - * consecutive scan_children() calls. - */ - list_for_each_entry_safe(u, next, &gc_inflight_list, link) { - struct sock *sk = &u->sk; - long total_refs; - - total_refs = file_count(sk->sk_socket->file); - - BUG_ON(!u->inflight); - BUG_ON(total_refs < u->inflight); - if (total_refs == u->inflight) { - list_move_tail(&u->link, &gc_candidates); - __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - - if (sk->sk_state == TCP_LISTEN) { - unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); - unix_state_unlock(sk); + /* No receiver exists out of the same SCC. */ + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + total_ref = file_count(u->sk.sk_socket->file); + + /* If not close()d, total_ref > out_degree. */ + if (total_ref != vertex->out_degree) + return false; + + return true; +} + +static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) +{ + struct unix_vertex *vertex; + + list_for_each_entry_reverse(vertex, scc, scc_entry) { + struct sk_buff_head *queue; + struct unix_edge *edge; + struct unix_sock *u; + + edge = list_first_entry(&vertex->edges, typeof(*edge), vertex_entry); + u = edge->predecessor; + queue = &u->sk.sk_receive_queue; + + spin_lock(&queue->lock); + + if (u->sk.sk_state == TCP_LISTEN) { + struct sk_buff *skb; + + skb_queue_walk(queue, skb) { + struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; + + spin_lock(&embryo_queue->lock); + skb_queue_splice_init(embryo_queue, hitlist); + spin_unlock(&embryo_queue->lock); } + } else { + skb_queue_splice_init(queue, hitlist); } + + spin_unlock(&queue->lock); } +} - /* Now remove all internal in-flight reference to children of - * the candidates. - */ - list_for_each_entry(u, &gc_candidates, link) - scan_children(&u->sk, dec_inflight, NULL); +static bool unix_scc_cyclic(struct list_head *scc) +{ + struct unix_vertex *vertex; + struct unix_edge *edge; - /* Restore the references for children of all candidates, - * which have remaining references. Do this recursively, so - * only those remain, which form cyclic references. - * - * Use a "cursor" link, to make the list traversal safe, even - * though elements might be moved about. + /* SCC containing multiple vertices ? */ + if (!list_is_singular(scc)) + return true; + + vertex = list_first_entry(scc, typeof(*vertex), scc_entry); + + /* Self-reference or a embryo-listener circle ? */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + if (unix_edge_successor(edge) == vertex) + return true; + } + + return false; +} + +static LIST_HEAD(unix_visited_vertices); +static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; + +static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, + struct sk_buff_head *hitlist) +{ + LIST_HEAD(vertex_stack); + struct unix_edge *edge; + LIST_HEAD(edge_stack); + +next_vertex: + /* Push vertex to vertex_stack and mark it as on-stack + * (index >= UNIX_VERTEX_INDEX_START). + * The vertex will be popped when finalising SCC later. */ - list_add(&cursor, &gc_candidates); - while (cursor.next != &gc_candidates) { - u = list_entry(cursor.next, struct unix_sock, link); + list_add(&vertex->scc_entry, &vertex_stack); - /* Move cursor to after the current position. */ - list_move(&cursor, &u->link); + vertex->index = *last_index; + vertex->scc_index = *last_index; + (*last_index)++; - if (u->inflight) { - list_move_tail(&u->link, ¬_cycle_list); - __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); - scan_children(&u->sk, inc_inflight_move_tail, NULL); + /* Explore neighbour vertices (receivers of the current vertex's fd). */ + list_for_each_entry(edge, &vertex->edges, vertex_entry) { + struct unix_vertex *next_vertex = unix_edge_successor(edge); + + if (!next_vertex) + continue; + + if (next_vertex->index == unix_vertex_unvisited_index) { + /* Iterative deepening depth first search + * + * 1. Push a forward edge to edge_stack and set + * the successor to vertex for the next iteration. + */ + list_add(&edge->stack_entry, &edge_stack); + + vertex = next_vertex; + goto next_vertex; + + /* 2. Pop the edge directed to the current vertex + * and restore the ancestor for backtracking. + */ +prev_vertex: + edge = list_first_entry(&edge_stack, typeof(*edge), stack_entry); + list_del_init(&edge->stack_entry); + + next_vertex = vertex; + vertex = edge->predecessor->vertex; + + /* If the successor has a smaller scc_index, two vertices + * are in the same SCC, so propagate the smaller scc_index + * to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else if (next_vertex->index != unix_vertex_grouped_index) { + /* Loop detected by a back/cross edge. + * + * The successor is on vertex_stack, so two vertices are in + * the same SCC. If the successor has a smaller *scc_index*, + * propagate it to skip SCC finalisation. + */ + vertex->scc_index = min(vertex->scc_index, next_vertex->scc_index); + } else { + /* The successor was already grouped as another SCC */ } } - list_del(&cursor); - /* Now gc_candidates contains only garbage. Restore original - * inflight counters for these as well, and remove the skbuffs - * which are creating the cycle(s). - */ - skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) { - scan_children(&u->sk, inc_inflight, &hitlist); - -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; + if (vertex->index == vertex->scc_index) { + struct unix_vertex *v; + struct list_head scc; + bool scc_dead = true; + + /* SCC finalised. + * + * If the scc_index was not updated, all the vertices above on + * vertex_stack are in the same SCC. Group them using scc_entry. + */ + __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); + + list_for_each_entry_reverse(v, &scc, scc_entry) { + /* Don't restart DFS from this vertex in unix_walk_scc(). */ + list_move_tail(&v->entry, &unix_visited_vertices); + + /* Mark vertex as off-stack. */ + v->index = unix_vertex_grouped_index; + + if (scc_dead) + scc_dead = unix_vertex_dead(v); } -#endif + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); } - /* not_cycle_list contains those sockets which do not make up a - * cycle. Restore these to the inflight list. + /* Need backtracking ? */ + if (!list_empty(&edge_stack)) + goto prev_vertex; +} + +static void unix_walk_scc(struct sk_buff_head *hitlist) +{ + unsigned long last_index = UNIX_VERTEX_INDEX_START; + + unix_graph_maybe_cyclic = false; + + /* Visit every vertex exactly once. + * __unix_walk_scc() moves visited vertices to unix_visited_vertices. */ - while (!list_empty(¬_cycle_list)) { - u = list_entry(not_cycle_list.next, struct unix_sock, link); - __clear_bit(UNIX_GC_CANDIDATE, &u->gc_flags); - list_move_tail(&u->link, &gc_inflight_list); + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + __unix_walk_scc(vertex, &last_index, hitlist); } - spin_unlock(&unix_gc_lock); + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); - /* We need io_uring to clean its registered files, ignore all io_uring - * originated skbs. It's fine as io_uring doesn't keep references to - * other io_uring instances and so killing all other files in the cycle - * will put all io_uring references forcing it to go through normal - * release.path eventually putting registered files. - */ - skb_queue_walk_safe(&hitlist, skb, next_skb) { - if (skb->scm_io_uring) { - __skb_unlink(skb, &hitlist); - skb_queue_tail(&skb->sk->sk_receive_queue, skb); + unix_graph_grouped = true; +} + +static void unix_walk_scc_fast(struct sk_buff_head *hitlist) +{ + unix_graph_maybe_cyclic = false; + + while (!list_empty(&unix_unvisited_vertices)) { + struct unix_vertex *vertex; + struct list_head scc; + bool scc_dead = true; + + vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); + list_add(&scc, &vertex->scc_entry); + + list_for_each_entry_reverse(vertex, &scc, scc_entry) { + list_move_tail(&vertex->entry, &unix_visited_vertices); + + if (scc_dead) + scc_dead = unix_vertex_dead(vertex); } + + if (scc_dead) + unix_collect_skb(&scc, hitlist); + else if (!unix_graph_maybe_cyclic) + unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + + list_del(&scc); } - /* Here we are. Hitlist is filled. Die. */ - __skb_queue_purge(&hitlist); + list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); +} + +static bool gc_in_progress; + +static void __unix_gc(struct work_struct *work) +{ + struct sk_buff_head hitlist; + struct sk_buff *skb; spin_lock(&unix_gc_lock); - /* There could be io_uring registered files, just push them back to - * the inflight list - */ - list_for_each_entry_safe(u, next, &gc_candidates, link) - list_move_tail(&u->link, &gc_inflight_list); + if (!unix_graph_maybe_cyclic) { + spin_unlock(&unix_gc_lock); + goto skip_gc; + } + + __skb_queue_head_init(&hitlist); + + if (unix_graph_grouped) + unix_walk_scc_fast(&hitlist); + else + unix_walk_scc(&hitlist); + + spin_unlock(&unix_gc_lock); - /* All candidates should have been detached by now. */ - BUG_ON(!list_empty(&gc_candidates)); + skb_queue_walk(&hitlist, skb) { + if (UNIXCB(skb).fp) + UNIXCB(skb).fp->dead = true; + } - /* Paired with READ_ONCE() in wait_for_unix_gc(). */ + __skb_queue_purge(&hitlist); +skip_gc: WRITE_ONCE(gc_in_progress, false); +} - wake_up(&unix_gc_wait); +static DECLARE_WORK(unix_gc_work, __unix_gc); - out: - spin_unlock(&unix_gc_lock); +void unix_gc(void) +{ + WRITE_ONCE(gc_in_progress, true); + queue_work(system_unbound_wq, &unix_gc_work); +} + +#define UNIX_INFLIGHT_TRIGGER_GC 16000 +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) + +void wait_for_unix_gc(struct scm_fp_list *fpl) +{ + /* If number of inflight sockets is insane, + * force a garbage collect right now. + * + * Paired with the WRITE_ONCE() in unix_inflight(), + * unix_notinflight(), and __unix_gc(). + */ + if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && + !READ_ONCE(gc_in_progress)) + unix_gc(); + + /* Penalise users who want to send AF_UNIX sockets + * but whose sockets have not been received yet. + */ + if (!fpl || !fpl->count_unix || + READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + return; + + if (READ_ONCE(gc_in_progress)) + flush_work(&unix_gc_work); } diff --git a/net/unix/scm.c b/net/unix/scm.c deleted file mode 100644 index 4eff7da9f6f9..000000000000 --- a/net/unix/scm.c +++ /dev/null @@ -1,154 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/socket.h> -#include <linux/net.h> -#include <linux/fs.h> -#include <net/af_unix.h> -#include <net/scm.h> -#include <linux/init.h> -#include <linux/io_uring.h> - -#include "scm.h" - -unsigned int unix_tot_inflight; -EXPORT_SYMBOL(unix_tot_inflight); - -LIST_HEAD(gc_inflight_list); -EXPORT_SYMBOL(gc_inflight_list); - -DEFINE_SPINLOCK(unix_gc_lock); -EXPORT_SYMBOL(unix_gc_lock); - -struct sock *unix_get_socket(struct file *filp) -{ - struct sock *u_sock = NULL; - struct inode *inode = file_inode(filp); - - /* Socket ? */ - if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) { - struct socket *sock = SOCKET_I(inode); - struct sock *s = sock->sk; - - /* PF_UNIX ? */ - if (s && sock->ops && sock->ops->family == PF_UNIX) - u_sock = s; - } - - return u_sock; -} -EXPORT_SYMBOL(unix_get_socket); - -/* Keep the number of times in flight count for the file - * descriptor if it is for an AF_UNIX socket. - */ -void unix_inflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - if (!u->inflight) { - BUG_ON(!list_empty(&u->link)); - list_add_tail(&u->link, &gc_inflight_list); - } else { - BUG_ON(list_empty(&u->link)); - } - u->inflight++; - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1); - spin_unlock(&unix_gc_lock); -} - -void unix_notinflight(struct user_struct *user, struct file *fp) -{ - struct sock *s = unix_get_socket(fp); - - spin_lock(&unix_gc_lock); - - if (s) { - struct unix_sock *u = unix_sk(s); - - BUG_ON(!u->inflight); - BUG_ON(list_empty(&u->link)); - - u->inflight--; - if (!u->inflight) - list_del_init(&u->link); - /* Paired with READ_ONCE() in wait_for_unix_gc() */ - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); - } - WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1); - spin_unlock(&unix_gc_lock); -} - -/* - * The "user->unix_inflight" variable is protected by the garbage - * collection lock, and we just read it locklessly here. If you go - * over the limit, there might be a tiny race in actually noticing - * it across threads. Tough. - */ -static inline bool too_many_unix_fds(struct task_struct *p) -{ - struct user_struct *user = current_user(); - - if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE))) - return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); - return false; -} - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - if (too_many_unix_fds(current)) - return -ETOOMANYREFS; - - /* - * Need to duplicate file references for the sake of garbage - * collection. Otherwise a socket in the fps might become a - * candidate for GC while the skb is not yet queued. - */ - UNIXCB(skb).fp = scm_fp_dup(scm->fp); - if (!UNIXCB(skb).fp) - return -ENOMEM; - - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->user, scm->fp->fp[i]); - return 0; -} -EXPORT_SYMBOL(unix_attach_fds); - -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) -{ - int i; - - scm->fp = UNIXCB(skb).fp; - UNIXCB(skb).fp = NULL; - - for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->user, scm->fp->fp[i]); -} -EXPORT_SYMBOL(unix_detach_fds); - -void unix_destruct_scm(struct sk_buff *skb) -{ - struct scm_cookie scm; - - memset(&scm, 0, sizeof(scm)); - scm.pid = UNIXCB(skb).pid; - if (UNIXCB(skb).fp) - unix_detach_fds(&scm, skb); - - /* Alas, it calls VFS */ - /* So fscking what? fput() had been SMP-safe since the last Summer */ - scm_destroy(&scm); - sock_wfree(skb); -} -EXPORT_SYMBOL(unix_destruct_scm); diff --git a/net/unix/scm.h b/net/unix/scm.h deleted file mode 100644 index 5a255a477f16..000000000000 --- a/net/unix/scm.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef NET_UNIX_SCM_H -#define NET_UNIX_SCM_H - -extern struct list_head gc_inflight_list; -extern spinlock_t unix_gc_lock; - -int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb); -void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb); - -#endif diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 88b5702a0a47..4184e8110f56 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -116,12 +116,14 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); +static void vsock_close(struct sock *sk, long timeout); /* Protocol family. */ static struct proto vsock_proto = { .name = "AF_VSOCK", .owner = THIS_MODULE, .obj_size = sizeof(struct vsock_sock), + .close = vsock_close, }; /* The default peer timeout indicates how long we will wait for a peer response @@ -331,7 +333,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { - vsock_remove_bound(vsk); + /* Transport reassignment must not remove the binding. */ + if (sock_flag(sk_vsock(vsk), SOCK_DEAD)) + vsock_remove_bound(vsk); + vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); @@ -398,6 +403,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept); static bool vsock_use_local_transport(unsigned int remote_cid) { + lockdep_assert_held(&vsock_register_mutex); + if (!transport_local) return false; @@ -455,6 +462,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) remote_flags = vsk->remote_addr.svm_flags; + mutex_lock(&vsock_register_mutex); + switch (sk->sk_type) { case SOCK_DGRAM: new_transport = transport_dgram; @@ -470,12 +479,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_h2g; break; default: - return -ESOCKTNOSUPPORT; + ret = -ESOCKTNOSUPPORT; + goto err; } if (vsk->transport) { - if (vsk->transport == new_transport) - return 0; + if (vsk->transport == new_transport) { + ret = 0; + goto err; + } /* transport->release() must be called with sock lock acquired. * This path can only be taken during vsock_connect(), where we @@ -499,8 +511,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) /* We increase the module refcnt to prevent the transport unloading * while there are open sockets assigned to it. */ - if (!new_transport || !try_module_get(new_transport->module)) - return -ENODEV; + if (!new_transport || !try_module_get(new_transport->module)) { + ret = -ENODEV; + goto err; + } + + /* It's safe to release the mutex after a successful try_module_get(). + * Whichever transport `new_transport` points at, it won't go away until + * the last module_put() below or in vsock_deassign_transport(). + */ + mutex_unlock(&vsock_register_mutex); if (sk->sk_type == SOCK_SEQPACKET) { if (!new_transport->seqpacket_allow || @@ -519,12 +539,31 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) vsk->transport = new_transport; return 0; +err: + mutex_unlock(&vsock_register_mutex); + return ret; } EXPORT_SYMBOL_GPL(vsock_assign_transport); +/* + * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks. + * Otherwise we may race with module removal. Do not use on `vsk->transport`. + */ +static u32 vsock_registered_transport_cid(const struct vsock_transport **transport) +{ + u32 cid = VMADDR_CID_ANY; + + mutex_lock(&vsock_register_mutex); + if (*transport) + cid = (*transport)->get_local_cid(); + mutex_unlock(&vsock_register_mutex); + + return cid; +} + bool vsock_find_cid(unsigned int cid) { - if (transport_g2h && cid == transport_g2h->get_local_cid()) + if (cid == vsock_registered_transport_cid(&transport_g2h)) return true; if (transport_h2g && cid == VMADDR_CID_HOST) @@ -647,7 +686,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port <= LAST_RESERVED_PORT) + if (port == VMADDR_PORT_ANY || + port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; @@ -803,39 +843,44 @@ static bool sock_type_connectible(u16 type) static void __vsock_release(struct sock *sk, int level) { - if (sk) { - struct sock *pending; - struct vsock_sock *vsk; + struct vsock_sock *vsk; + struct sock *pending; - vsk = vsock_sk(sk); - pending = NULL; /* Compiler warning. */ + vsk = vsock_sk(sk); + pending = NULL; /* Compiler warning. */ - /* When "level" is SINGLE_DEPTH_NESTING, use the nested - * version to avoid the warning "possible recursive locking - * detected". When "level" is 0, lock_sock_nested(sk, level) - * is the same as lock_sock(sk). - */ - lock_sock_nested(sk, level); + /* When "level" is SINGLE_DEPTH_NESTING, use the nested + * version to avoid the warning "possible recursive locking + * detected". When "level" is 0, lock_sock_nested(sk, level) + * is the same as lock_sock(sk). + */ + lock_sock_nested(sk, level); - if (vsk->transport) - vsk->transport->release(vsk); - else if (sock_type_connectible(sk->sk_type)) - vsock_remove_sock(vsk); + /* Indicate to vsock_remove_sock() that the socket is being released and + * can be removed from the bound_table. Unlike transport reassignment + * case, where the socket must remain bound despite vsock_remove_sock() + * being called from the transport release() callback. + */ + sock_set_flag(sk, SOCK_DEAD); - sock_orphan(sk); - sk->sk_shutdown = SHUTDOWN_MASK; + if (vsk->transport) + vsk->transport->release(vsk); + else if (sock_type_connectible(sk->sk_type)) + vsock_remove_sock(vsk); - skb_queue_purge(&sk->sk_receive_queue); + sock_orphan(sk); + sk->sk_shutdown = SHUTDOWN_MASK; - /* Clean up any sockets that never were accepted. */ - while ((pending = vsock_dequeue_accept(sk)) != NULL) { - __vsock_release(pending, SINGLE_DEPTH_NESTING); - sock_put(pending); - } + skb_queue_purge(&sk->sk_receive_queue); - release_sock(sk); - sock_put(sk); + /* Clean up any sockets that never were accepted. */ + while ((pending = vsock_dequeue_accept(sk)) != NULL) { + __vsock_release(pending, SINGLE_DEPTH_NESTING); + sock_put(pending); } + + release_sock(sk); + sock_put(sk); } static void vsock_sk_destruct(struct sock *sk) @@ -912,9 +957,22 @@ void vsock_data_ready(struct sock *sk) } EXPORT_SYMBOL_GPL(vsock_data_ready); +/* Dummy callback required by sockmap. + * See unconditional call of saved_close() in sock_map_close(). + */ +static void vsock_close(struct sock *sk, long timeout) +{ +} + static int vsock_release(struct socket *sock) { - __vsock_release(sock->sk, 0); + struct sock *sk = sock->sk; + + if (!sk) + return 0; + + sk->sk_prot->close(sk, 0); + __vsock_release(sk, 0); sock->sk = NULL; sock->state = SS_FREE; @@ -1414,7 +1472,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, timeout = vsk->connect_timeout; prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) { + /* If the socket is already closing or it is in an error state, there + * is no point in waiting. + */ + while (sk->sk_state != TCP_ESTABLISHED && + sk->sk_state != TCP_CLOSING && sk->sk_err == 0) { if (flags & O_NONBLOCK) { /* If we're not going to block, we schedule a timeout * function to generate a timeout on the connection @@ -2293,18 +2355,19 @@ static long vsock_dev_do_ioctl(struct file *filp, unsigned int cmd, void __user *ptr) { u32 __user *p = ptr; - u32 cid = VMADDR_CID_ANY; int retval = 0; + u32 cid; switch (cmd) { case IOCTL_VM_SOCKETS_GET_LOCAL_CID: /* To be compatible with the VMCI behavior, we prioritize the * guest CID instead of well-know host CID (VMADDR_CID_HOST). */ - if (transport_g2h) - cid = transport_g2h->get_local_cid(); - else if (transport_h2g) - cid = transport_h2g->get_local_cid(); + cid = vsock_registered_transport_cid(&transport_g2h); + if (cid == VMADDR_CID_ANY) + cid = vsock_registered_transport_cid(&transport_h2g); + if (cid == VMADDR_CID_ANY) + cid = vsock_registered_transport_cid(&transport_local); if (put_user(cid, p) != 0) retval = -EFAULT; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 36eb16a40745..95f34dffe3c2 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -119,6 +119,8 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt, u16 proto, struct vmci_handle handle) { + memset(pkt, 0, sizeof(*pkt)); + /* We register the stream control handler as an any cid handle so we * must always send from a source address of VMADDR_CID_ANY */ @@ -131,8 +133,6 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt, pkt->type = type; pkt->src_port = src->svm_port; pkt->dst_port = dst->svm_port; - memset(&pkt->proto, 0, sizeof(pkt->proto)); - memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2)); switch (pkt->type) { case VMCI_TRANSPORT_PACKET_TYPE_INVALID: diff --git a/net/wireless/core.c b/net/wireless/core.c index 2bed30621fa6..1788431c8220 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -546,6 +546,9 @@ use_default_name: INIT_WORK(&rdev->mgmt_registrations_update_wk, cfg80211_mgmt_registrations_update_wk); spin_lock_init(&rdev->mgmt_registrations_lock); + INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work); + INIT_LIST_HEAD(&rdev->wiphy_work_list); + spin_lock_init(&rdev->wiphy_work_lock); #ifdef CONFIG_CFG80211_DEFAULT_PS rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; @@ -563,9 +566,6 @@ use_default_name: return NULL; } - INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work); - INIT_LIST_HEAD(&rdev->wiphy_work_list); - spin_lock_init(&rdev->wiphy_work_lock); INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work); INIT_WORK(&rdev->conn_work, cfg80211_conn_work); INIT_WORK(&rdev->event_work, cfg80211_event_work); @@ -1146,6 +1146,13 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) { struct cfg80211_internal_bss *scan, *tmp; struct cfg80211_beacon_registration *reg, *treg; + unsigned long flags; + + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); + WARN_ON(!list_empty(&rdev->wiphy_work_list)); + spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); + cancel_work_sync(&rdev->wiphy_work); + rfkill_destroy(rdev->wiphy.rfkill); list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) { list_del(®->list); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0ba824c3fd1b..3ff2fe98a974 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4050,6 +4050,11 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags) if (flags[flag]) *mntrflags |= (1<<flag); + /* cooked monitor mode is incompatible with other modes */ + if (*mntrflags & MONITOR_FLAG_COOK_FRAMES && + *mntrflags != MONITOR_FLAG_COOK_FRAMES) + return -EOPNOTSUPP; + *mntrflags |= MONITOR_FLAG_CHANGED; return 0; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 5da1a641ef17..34a6bc43119b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -405,7 +405,8 @@ static bool is_an_alpha2(const char *alpha2) { if (!alpha2) return false; - return isalpha(alpha2[0]) && isalpha(alpha2[1]); + return isascii(alpha2[0]) && isalpha(alpha2[0]) && + isascii(alpha2[1]) && isalpha(alpha2[1]); } static bool alpha2_equal(const char *alpha2_x, const char *alpha2_y) diff --git a/net/wireless/util.c b/net/wireless/util.c index c71b85fd6052..00c1530e1979 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -813,6 +813,52 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, bool mesh_hdr) } EXPORT_SYMBOL(ieee80211_is_valid_amsdu); + +/* + * Detects if an MSDU frame was maliciously converted into an A-MSDU + * frame by an adversary. This is done by parsing the received frame + * as if it were a regular MSDU, even though the A-MSDU flag is set. + * + * For non-mesh interfaces, detection involves checking whether the + * payload, when interpreted as an MSDU, begins with a valid RFC1042 + * header. This is done by comparing the A-MSDU subheader's destination + * address to the start of the RFC1042 header. + * + * For mesh interfaces, the MSDU includes a 6-byte Mesh Control field + * and an optional variable-length Mesh Address Extension field before + * the RFC1042 header. The position of the RFC1042 header must therefore + * be calculated based on the mesh header length. + * + * Since this function intentionally parses an A-MSDU frame as an MSDU, + * it only assumes that the A-MSDU subframe header is present, and + * beyond this it performs its own bounds checks under the assumption + * that the frame is instead parsed as a non-aggregated MSDU. + */ +static bool +is_amsdu_aggregation_attack(struct ethhdr *eth, struct sk_buff *skb, + enum nl80211_iftype iftype) +{ + int offset; + + /* Non-mesh case can be directly compared */ + if (iftype != NL80211_IFTYPE_MESH_POINT) + return ether_addr_equal(eth->h_dest, rfc1042_header); + + offset = __ieee80211_get_mesh_hdrlen(eth->h_dest[0]); + if (offset == 6) { + /* Mesh case with empty address extension field */ + return ether_addr_equal(eth->h_source, rfc1042_header); + } else if (offset + ETH_ALEN <= skb->len) { + /* Mesh case with non-empty address extension field */ + u8 temp[ETH_ALEN]; + + skb_copy_bits(skb, offset, temp, ETH_ALEN); + return ether_addr_equal(temp, rfc1042_header); + } + + return false; +} + void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, @@ -857,8 +903,10 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, /* the last MSDU has no padding */ if (subframe_len > remaining) goto purge; - /* mitigate A-MSDU aggregation injection attacks */ - if (ether_addr_equal(hdr.eth.h_dest, rfc1042_header)) + /* mitigate A-MSDU aggregation injection attacks, to be + * checked when processing first subframe (offset == 0). + */ + if (offset == 0 && is_amsdu_aggregation_attack(&hdr.eth, skb, iftype)) goto purge; offset += sizeof(struct ethhdr); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 3321ca7eb76c..21d5fdba47c4 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -102,7 +102,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, if (pool->unaligned) pool->free_heads[i] = xskb; else - xp_init_xskb_addr(xskb, pool, i * pool->chunk_size); + xp_init_xskb_addr(xskb, pool, (u64)i * pool->chunk_size); } return pool; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 85501b77f4e3..45466fa4ace4 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -871,7 +871,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } - if (p.collect_md) { + if (p.collect_md || xi->p.collect_md) { NL_SET_ERR_MSG(extack, "collect_md can't be changed"); return -EINVAL; } @@ -882,11 +882,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], } else { if (xi->dev != dev) return -EEXIST; - if (xi->p.collect_md) { - NL_SET_ERR_MSG(extack, - "device can't be changed to collect_md"); - return -EINVAL; - } } return xfrmi_update(xi, &p); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 07a7ee43b8ae..c59c548d8fc1 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -738,7 +738,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) skb->encapsulation = 1; if (skb_is_gso(skb)) { - if (skb->inner_protocol) + if (skb->inner_protocol && x->props.mode == XFRM_MODE_TUNNEL) return xfrm_output_gso(net, sk, skb); skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a022f4984687..e015ff225b27 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1597,6 +1597,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; + /* Sanitize mark before store */ + policy->mark.v &= policy->mark.m; + spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 2f4cf976b59a..58c53bb1c583 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -694,9 +694,6 @@ int __xfrm_state_delete(struct xfrm_state *x) net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); - if (x->encap_sk) - sock_put(rcu_dereference_raw(x->encap_sk)); - xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. @@ -1278,6 +1275,9 @@ static void __xfrm_state_insert(struct xfrm_state *x) list_add(&x->km.all, &net->xfrm.state_all); + /* Sanitize mark before store */ + x->mark.v &= x->mark.m; + h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); |